CN114757716A - Method and device for device call-through, electronic device and storage medium - Google Patents

Method and device for device call-through, electronic device and storage medium Download PDF

Info

Publication number
CN114757716A
CN114757716A CN202210504954.0A CN202210504954A CN114757716A CN 114757716 A CN114757716 A CN 114757716A CN 202210504954 A CN202210504954 A CN 202210504954A CN 114757716 A CN114757716 A CN 114757716A
Authority
CN
China
Prior art keywords
equipment
address
getting
opening
pair
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210504954.0A
Other languages
Chinese (zh)
Inventor
韩坤
卫海天
张轲祺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Minglue Zhaohui Technology Co Ltd
Original Assignee
Beijing Minglue Zhaohui Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Minglue Zhaohui Technology Co Ltd filed Critical Beijing Minglue Zhaohui Technology Co Ltd
Priority to CN202210504954.0A priority Critical patent/CN114757716A/en
Publication of CN114757716A publication Critical patent/CN114757716A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to the technical field of data processing, and discloses a method for equipment getting through, which comprises the following steps: and acquiring Internet Protocol (IP) addresses corresponding to a plurality of advertisement records and the occurrence time of each advertisement record, wherein the advertisement records are used for representing data records generated by equipment touched by the delivered advertisements. And determining a plurality of equipment pairs according to each IP address and each occurrence time, and acquiring the equipment communication characteristics corresponding to each equipment pair. And inputting the opening characteristics of each device into a preset prediction model, and predicting whether the device in each device pair is an opening device or not. Therefore, more and more comprehensive equipment opening characteristics are considered when the equipment is opened, and the accuracy of predicting whether the equipment is opened or not is improved. The application also discloses a device for opening the equipment, the electronic equipment and a storage medium.

Description

Method and device for device call-through, electronic device and storage medium
Technical Field
The present application relates to the field of data processing technologies, and for example, to a method and an apparatus for device call-through, an electronic device, and a storage medium.
Background
Nowadays, with the development of technologies, the multi-screen marketing discussion of smart phones, tablets, computers, internet televisions and the like is more and more frequent. One of the core points is "multi-screen communication". Usually, a person will have multiple devices in a smart phone, a tablet, a computer, and an internet television at the same time. A multi-screen call is to determine which smart devices belong to the same person. And multi-screen opening can help identify multiple devices of the same consumer, and provides similar brand consumption experience for the consumer. The multi-screen opening can help the advertisement platform to optimize the delivery strategy, and the excessive exposure of the same person on different devices is avoided. The multi-screen opening can realize the calculation from equipment to people, and help the advertiser know how many people the advertisements put on each equipment really reach effectively.
In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:
in the related art, the equipment opening characteristics considered in the process of opening the equipment are less, and the accuracy is poor when whether the equipment is opened or not is predicted.
Disclosure of Invention
The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments, but is intended to be a prelude to the more detailed description that is presented later.
The embodiment of the disclosure provides a method and a device for getting through equipment, electronic equipment and a storage medium, so as to improve the accuracy of judging whether the equipment to be predicted is the getting through equipment.
In some embodiments, the method for device arming comprises: and acquiring Internet Protocol (IP) addresses corresponding to a plurality of advertisement records respectively and occurrence time of each advertisement record, wherein the advertisement records are used for representing data records generated by equipment which is touched by the delivered advertisement. And determining a plurality of equipment pairs according to the IP addresses and the occurrence times, and acquiring equipment access characteristics corresponding to the equipment pairs respectively. The equipment getting through characteristics comprise the pairing times of equipment pairs, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the getting through IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the getting through IP address or not, the exposure times of the equipment on the getting through IP address, the active days of the equipment on the getting through IP address, the exposure times of the equipment on the getting through IP address, the first proportion of the total exposure times of the equipment and the second proportion of the active days of the equipment on the getting through IP address to the total active days of the equipment; the communication IP address is an IP address corresponding to the equipment; and the active IP address is the IP address with the most exposure times. And inputting the opening characteristics of each piece of equipment into a preset prediction model, and predicting whether the equipment in each equipment pair is the opening equipment or not.
In some embodiments, the obtaining the internet protocol IP addresses respectively corresponding to a plurality of advertisement records and the occurrence time of each advertisement record includes: advertisement log data is obtained, wherein the advertisement log data comprises a plurality of advertisement records. And extracting the Internet protocol IP address corresponding to each advertisement record and the occurrence time of each advertisement record from the advertisement log data.
In some embodiments, determining a plurality of device pairs according to each of the IP addresses and each of the occurrence times includes: and pairing the devices corresponding to the advertisement records with the same IP addresses within the same preset time period to obtain the device pairs.
In some embodiments, inputting the opening characteristics of each of the devices into a preset prediction model to predict whether the devices in each of the device pairs are opening devices comprises: and obtaining the equipment opening probability of each equipment pair by using the prediction model of the opening characteristics of each equipment. And determining whether the equipment in each equipment pair is the access equipment or not according to the access probability of each equipment.
In some embodiments, determining whether a device in the pair of devices is a get-through device according to the device get-through probability includes: and determining the equipment in the equipment pair as the access equipment under the condition that the equipment access probability is greater than or equal to the preset probability.
In some embodiments, determining whether a device in the pair of devices is a get-through device according to the device get-through probability includes: and under the condition that the equipment opening probability is smaller than the preset probability, determining that the equipment in the equipment pair is not the opening equipment.
In some embodiments, the predictive model is obtained by: and acquiring the characteristics of the sample device pair and a sample label corresponding to the characteristics of the sample device pair, wherein the sample label is used for representing whether the device pair corresponding to the characteristics of the sample device pair is a communication device. And training the characteristic input preset model of the sample equipment with the sample label to obtain the prediction model.
In some embodiments, the apparatus for device arming comprises: the first acquisition module is configured to acquire Internet Protocol (IP) addresses respectively corresponding to a plurality of advertisement records and the occurrence time of each advertisement record; the advertisement records are used to characterize data records generated by devices that have been reached by the delivered advertisements. A determining module configured to determine a number of device pairs according to each of the IP addresses and each of the occurrence times. And the second acquisition module is configured to acquire the device opening characteristics of each device pair. The equipment getting through feature comprises the pairing times of equipment pairs, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the getting through IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the getting through IP address or not, the exposure times of the equipment on the getting through IP address, the active days of the equipment on the getting through IP address, the exposure times of the equipment on the getting through IP address accounting for the first proportion of the total exposure times of the equipment and the active days of the equipment on the getting through IP address accounting for the second proportion of the total active days of the equipment. The communication IP address is an IP address corresponding to the equipment, and the active IP address is the IP address with the largest exposure times. And the prediction module is configured to input each equipment opening characteristic into a preset prediction model and predict whether the equipment in each equipment pair is the opening equipment.
In some embodiments, the electronic device comprises a processor and a memory storing program instructions, the processor being configured to, when executing the program instructions, perform the method for device punch-through as described above.
In some embodiments, the storage medium stores program instructions that, when executed, perform the method for device drill-through described above.
The method and the device for getting through the equipment, the electronic equipment and the storage medium provided by the embodiment of the disclosure can realize the following technical effects: by considering various device opening characteristics such as the number of pairs of devices in the device pair, the number of active days of the devices, the number of exposure times of the devices, the number of devices related to the opening IP address, the number of pairs of the devices, whether the active IP address of the devices is consistent with the opening IP address, the ratio of the number of exposure times of the devices on the opening IP address, the ratio of the number of active days of the devices on the opening IP address, the ratio of the number of exposure times of the devices on the opening IP address to the total number of exposure times of the devices, and the second ratio of the number of active days of the devices on the opening IP address to the total number of active days of the devices, more and more comprehensive device opening characteristics are considered when the devices are opened, and the accuracy of judging whether the devices to be predicted are the opening devices is improved.
The foregoing general description and the following description are exemplary and explanatory only and are not restrictive of the application.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the accompanying drawings and not in limitation thereof, in which elements having the same reference numeral designations are shown as like elements and not in limitation thereof, and wherein:
FIG. 1 is a schematic diagram of a method for device drill-through provided by an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of another method for device drill-through provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of another method for device drill-through provided by an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a method for obtaining a predictive model according to an embodiment of the disclosure;
FIG. 5 is a schematic diagram of an apparatus for opening a device according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
So that the manner in which the features and elements of the disclosed embodiments can be understood in detail, a more particular description of the disclosed embodiments, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may be practiced without these details. In other instances, well-known structures and devices may be shown in simplified form in order to simplify the drawing.
The terms "first," "second," and the like in the description and claims of the embodiments of the disclosure and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged as appropriate for the embodiments of the disclosure described herein. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
The term "plurality" means two or more, unless otherwise specified.
In the embodiment of the present disclosure, the character "/" indicates that the preceding and following objects are in an or relationship. For example, A/B represents: a or B.
The term "and/or" is an associative relationship that describes objects, meaning that three relationships may exist. E.g., a and/or B, represents: a or B, or A and B.
The term "correspond" may refer to an association or binding relationship, and a corresponds to B refers to an association or binding relationship between a and B.
The technical scheme in the embodiment of the invention can be applied to electronic equipment such as a computer or a server.
In the embodiment of the invention, by carrying out data mining on the advertisement records, various equipment opening characteristics are obtained, such as the pairing times of equipment pairs, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the opening IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the opening IP address, the exposure time ratio of the equipment on the opening IP address, the active days ratio of the equipment on the opening IP address, the first ratio of the exposure times of the equipment on the opening IP address to the total exposure times of the equipment, the second ratio of the active days of the equipment on the opening IP address to the total active days of the equipment and other equipment opening characteristics. The communication relation among the devices can be obtained through the device communication characteristics, and whether the devices in the device pair are communication devices or not can be accurately predicted without the limitation of television media, television manufacturers, regions and time.
With reference to fig. 1, an embodiment of the present disclosure provides a method for opening a device, where the method includes:
step S101, the electronic device obtains Internet protocol IP addresses respectively corresponding to a plurality of advertisement records and occurrence time of each advertisement record. The advertisement records are used to characterize data records generated by devices that have been reached by the delivered advertisements.
And S102, the electronic equipment determines a plurality of equipment pairs according to each IP address and each occurrence time.
And step S103, the electronic equipment acquires the equipment getting-through characteristics of each equipment to the corresponding equipment. The device getting through characteristics comprise the pairing number of the devices in the device pair, the active days of the devices, the exposure number of the devices, the number of the devices related to the getting through IP address, the pairing number of the devices, whether the active IP address of the devices is consistent with the getting through IP address or not, the exposure number ratio of the devices on the getting through IP address, the active days ratio of the devices on the getting through IP address, the first ratio of the exposure number of the devices on the getting through IP address to the total exposure number of the devices, and the second ratio of the active days of the devices on the getting through IP address to the total active days of the devices. The get-through IP address is an IP address corresponding to the equipment, and the active IP address is the IP address with the largest exposure times.
And step S104, the electronic equipment inputs the opening characteristics of each equipment into a preset prediction model, and predicts whether the equipment in each equipment pair is the opening equipment or not.
By adopting the method for getting through the equipment provided by the embodiment of the disclosure, various equipment getting through characteristics such as the pairing times of the equipment in the equipment pair, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the getting through IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the getting through IP address or not, the exposure time ratio of the equipment on the getting through IP address, the active days ratio of the equipment on the getting through IP address, the first ratio of the exposure times of the equipment on the getting through IP address to the total equipment exposure times, the second ratio of the active days of the equipment on the getting through IP address to the total active days of the equipment and the like are considered, so that more and more comprehensive equipment getting through characteristics are considered when the equipment gets through, and the accuracy of predicting whether the equipment is the getting through equipment or not is improved.
Further, the electronic device obtains the internet protocol IP addresses respectively corresponding to the plurality of advertisement records and the occurrence time of each advertisement record, and the method includes: the electronic device obtains advertisement log data, which includes a plurality of advertisement records. And extracting the IP address corresponding to each advertisement record and the occurrence time of each advertisement record from the advertisement log data. Therefore, the advertisement log data is easy to obtain, and the IP address and the occurrence time corresponding to the advertisement record are extracted from the advertisement log data, so that the user can conveniently dig out the communication relation among the devices, and the limitation of television media, television manufacturers, regions or time is not easy to generate.
Further, the electronic device determines a plurality of device pairs according to the IP addresses corresponding to the advertisement records and the occurrence times corresponding to the advertisement records, including: the electronic equipment pairs the devices corresponding to the advertisement records with the same IP addresses within the same preset time period to obtain a device pair.
In some embodiments, the devices to which the advertisement records respectively correspond include a mobile phone 1, a mobile phone 2, a mobile phone 3, a television 1, a television 2, and a television 3. And when the occurrence time corresponding to each advertisement record is in the same preset time period and the IP addresses are the same, pairing the mobile phone 1, the mobile phone 2, the mobile phone 3, the television 1, the television 2 and the television 3 in pairs to obtain an equipment pair. And determines the IP address as the make-up IP address. For example, the device pair is "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".
As shown in fig. 2, an embodiment of the present disclosure provides a method for opening a device, where the method includes:
step S201, the electronic equipment acquires advertisement log data; the advertisement log data includes a plurality of advertisement records. The ad record is used to characterize the data records generated by the devices that were reached by the delivered ad.
Step S202, the electronic device extracts the Internet protocol IP address corresponding to each advertisement record and the occurrence time of each advertisement record from the advertisement log data.
Step S203, the electronic device pairs the devices corresponding to the advertisement records with the same IP address and the same occurrence time within the same preset time period to obtain a device pair.
And S204, the electronic equipment acquires the equipment getting-through characteristics of each equipment to the corresponding equipment. The device getting through characteristics comprise the pairing number of the devices in the device pair, the active days of the devices, the exposure number of the devices, the number of the devices related to the getting through IP address, the pairing number of the devices, whether the active IP address of the devices is consistent with the getting through IP address or not, the exposure number ratio of the devices on the getting through IP address, the active days ratio of the devices on the getting through IP address, the first ratio of the exposure number of the devices on the getting through IP address to the total exposure number of the devices, and the second ratio of the active days of the devices on the getting through IP address to the total active days of the devices. The get-through IP address is an IP address corresponding to the equipment, and the active IP address is the IP address with the largest exposure times.
And S205, the electronic equipment inputs the opening characteristics of each piece of equipment into a preset prediction model, and predicts whether the equipment in each equipment pair is the opening equipment or not.
By adopting the method for getting through the equipment, the data mining is carried out from the advertisement log data by utilizing the data capacity, and the characteristics of the equipment pair can be extracted, so that the getting-through relation among the equipment is obtained, the limitation of television media, television manufacturers, regions and time is avoided, and whether the equipment in the equipment pair is the getting-through equipment or not can be accurately predicted. Meanwhile, due to the fact that various equipment opening characteristics are considered, more and more comprehensive equipment opening characteristics are considered when equipment opening is conducted, and accuracy of predicting whether the equipment is the opening equipment or not is improved.
Optionally, the device get through feature includes a pairing number of the devices in the device pair, and the electronic device obtains the device get through feature corresponding to each device pair, including: the device counts the triggering times under the condition that the preset pairing conditions are triggered on a plurality of preset time periods or a plurality of IP addresses, and obtains the pairing times of the device pair. The preset pairing condition is that the occurrence time is within the same preset time period, and the IP addresses are the same.
Optionally, the device get through feature includes an active day number of the device in the pair of devices, and the electronic device obtains the device get through feature corresponding to each device pair, including: and respectively counting the number of active days of each device in the device pair in a preset time period.
Optionally, the device get-through feature includes exposure times of the devices in the pair, and the obtaining, by the electronic device, the device get-through feature corresponding to each device pair includes: and respectively counting the exposure times of each device in the device pair in a preset time period.
Optionally, the device get through feature includes a number of devices associated with the get through IP address, and the obtaining, by the electronic device, of the device get through feature of each device for a corresponding device, including: and counting the number of exposed devices on the get-through IP address to obtain the number of devices associated with the get-through IP address.
Optionally, the device get through feature includes a pairing number of the devices, and the electronic device obtains the device get through feature corresponding to each device, including: and respectively counting the number of the equipment pairs comprising the equipment to obtain the pairing number of each equipment. For example, if device 1 is paired with device 2 and device 3, respectively, then there are two pairs of devices including device 1, and then the number of pairs for device 1 is 2.
Optionally, the device get-through feature includes whether an active IP address of the device is consistent with the get-through IP address, and the obtaining, by the electronic device, the device get-through feature corresponding to each device, including: and determining the IP address which is most exposed by the equipment as the active IP address of the equipment, and judging whether the active IP address of the equipment is consistent with the make-through IP address of the equipment or not.
Optionally, the device getting through feature includes an exposure number of the device on the getting through IP address, and the obtaining, by the electronic device, the device getting through feature corresponding to each device includes: counting the exposure times of the equipment on the open IP address and the total exposure times of the open IP address, and calculating Z1＝B1/ZGeneral (1)And obtaining the ratio of the exposure times of the equipment on the opening IP address. Wherein, Z1Ratio of number of exposures on the opened IP address for the device, B1Number of exposures on the opened IP address for the device, ZGeneral assemblyThe total number of exposures for that open IP address.
Optionally, the device getting through feature includes an active day ratio of the device on the getting through IP address, and the obtaining, by the electronic device, the device getting through feature corresponding to each device pair includes: counting the number of active days of the equipment on the getting through IP address and the total number of active days of the getting through IP address, and calculating Z2＝H1/HGeneral assemblyThe percentage of active days of the device on the getting-through IP address is obtained. Wherein Z is2Ratio of active days on the device on the getting through IP address, H1Number of days active for a device on a communicating IP address, HGeneral assemblyThe total number of active days for the open IP address.
Optionally, the device getting through feature includes a first ratio of exposure times of the device on the getting through IP address to total exposure times of the device, and the obtaining, by the electronic device, the device getting through features corresponding to the respective device pairs includes: counting the number of active days of the equipment on the getting-through IP address and the total number of active days of the equipment, and calculating Z 3＝B1/SGeneral (1)A first proportion of the exposure times of the device on the opening IP address to the total exposure times of the device is obtained. Wherein, Z3The exposure times of the equipment on the opening IP address account for the first proportion of the total exposure times of the equipment, B1Number of exposures for a device at a communicating IP address, SGeneral (1)Is the total exposure times of the device.
Optionally, the device getting through feature includes a second ratio of the number of active days of the device on the getting through IP address to the total number of active days of the device, and the electronic device obtains the device getting through features corresponding to the respective device pairs, including: counting the active days of the equipment on the getting-through IP address and the total active days of the equipment, and calculating Z4＝H1/YGeneral (1)A second ratio of the number of active days of the device on the get-through IP address to the total number of active days of the device is obtained. Wherein, Z4For a second ratio of the number of active days of the device on the make-up IP address to the total number of active days of the device, H1Number of days alive for a device at a communicating IP address, YGeneral assemblyThe total number of active days of the device.
Further, the electronic device inputs the opening characteristics of each device into a preset prediction model, and predicts whether the device in each device pair is an opening device, including: and the electronic equipment makes the equipment get through the characteristic prediction model to obtain the equipment getting through probability of each equipment pair. And determining whether the equipment in each equipment pair is the access equipment or not according to the access probability of each equipment.
Further, the electronic device determines whether the device in the device pair is the access device according to the device access probability, including: and the electronic equipment determines the equipment in the equipment pair as the access equipment under the condition that the equipment access probability is greater than or equal to the preset probability. Wherein the preset probability is 0.5.
Optionally, the determining, by the electronic device, whether the device in the device pair is the get-through device according to the device get-through probability includes: and the electronic equipment determines that the equipment in the equipment pair is not the access equipment under the condition that the equipment access probability is smaller than the preset probability. Wherein the preset probability is 0.5.
In some embodiments, in the case that the device make-up probability is greater than or equal to 0.5, determining a device in the pair of devices as a make-up device; or determining that the equipment in the equipment pair is not the open equipment under the condition that the equipment open probability is less than 0.5.
As shown in fig. 3, an embodiment of the present disclosure provides a method for opening a device, where the method includes:
step S301, the electronic device obtains Internet protocol IP addresses corresponding to a plurality of advertisement records respectively and occurrence time of each advertisement record. The advertisement records are used to characterize data records generated by devices that have been reached by the delivered advertisements.
Step S302, the electronic device determines a plurality of device pairs according to each IP address and each occurrence time.
And step S303, the electronic equipment acquires the opening characteristics of the equipment corresponding to each equipment. The equipment opening characteristic comprises the pairing times of equipment in equipment pairs, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the opening IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the opening IP address or not, the exposure time ratio of the equipment on the opening IP address, the active days ratio of the equipment on the opening IP address, the first proportion of the exposure time of the equipment on the opening IP address to the total exposure time of the equipment and the second proportion of the active days of the equipment on the opening IP address to the total active days of the equipment. The get-through IP address is an IP address corresponding to the equipment, and the active IP address is the IP address with the largest exposure times.
And step S304, the electronic equipment makes the equipment get-through characteristic prediction model of each equipment, and obtains the equipment get-through probability of each equipment pair.
Step S305, the electronic equipment determines whether the equipment in each equipment pair is the access equipment according to the access probability of each equipment.
By adopting the method for opening the equipment, which is provided by the embodiment of the disclosure, the opening characteristics of the equipment are considered, so that more and more comprehensive opening characteristics of the equipment are considered when the equipment is opened, and the accuracy of predicting whether the equipment is opened or not is improved. Meanwhile, the preset prediction model is used for predicting the equipment opening probability of the equipment pair, so that a user can conveniently judge whether the equipment in the equipment pair is the opening equipment.
Further, the electronic device prediction model is obtained by the following steps: the electronic equipment acquires the characteristics of the sample equipment pair and the sample labels corresponding to the characteristics of the sample equipment pair, and the sample labels are used for representing whether the equipment pair corresponding to the characteristics of the sample equipment pair is the communication equipment or not. And training the characteristic input preset model of the sample equipment with the sample label to obtain a prediction model. Wherein the preset model is a tree model. For example, the Tree model includes a random forest model, a GBDT (Gradient Boosting Decision Tree) model, a Light gbm (Light Gradient Boosting Machine) model, an Xgboost (Extreme Gradient Boosting) model, or a catboost (category Features + Gradient Boosting) model, and the like.
Further, training the sample equipment with the sample label on the feature input preset model to obtain a prediction model, including: inputting the characteristics of sample equipment with sample labels into a plurality of preset models for training to obtain alternative models corresponding to the preset models respectively; and fusing the alternative models by using a model fusion technology to obtain a prediction model.
In some embodiments, the method includes inputting features of a sample device with a sample label into a random forest model to obtain a first candidate model, inputting features of the sample device with the sample label into a GBDT model to obtain a second candidate model, inputting features of the sample device with the sample label into a LightGBM model to obtain a third candidate model, inputting features of the sample device with the sample label into an xgboost model to obtain a fourth candidate model, and inputting features of the sample device with the sample label into a catboost model to obtain a fifth candidate model. And fusing the first candidate model, the second candidate model, the third candidate model, the fourth candidate model and the fifth candidate model by using a model fusion technology to obtain a prediction model.
Further, the model fusion technique includes an averaging method, a voting method, or a stacking fusion method.
In some embodiments, the averaging method is to obtain an average of the predicted probabilities output by each candidate model. Wherein the prediction probability is a turn-on probability.
In some embodiments, the voting method obtains the judgment result predicted by each candidate model, and determines the judgment result with the largest number as the judgment result of the prediction model. And judging whether the equipment in the equipment pair is the communication equipment or not according to the judgment result.
In some embodiments, the stacking fusion method is to obtain the predicted judgment result of each candidate model, obtain a sample label of each predicted judgment result, and determine the predicted judgment result as a training sample. And inputting the training samples with the sample labels into the simple model for training to obtain a prediction model. The simple model comprises a tree model and a logistic regression model.
As shown in fig. 4, an embodiment of the present disclosure provides a method for obtaining a prediction model, where the method includes:
step S401, the electronic device obtains the sample device pair characteristics and the sample label corresponding to the sample device pair characteristics. The sample label is used for representing whether the device pair corresponding to the sample device pair characteristic is a communication device.
Step S402, inputting the characteristics of the sample equipment with the sample label into a plurality of preset models by the electronic equipment for training, and obtaining alternative models respectively corresponding to the preset models.
And S403, fusing the alternative models by the electronic equipment by using a model fusion technology to obtain a prediction model.
By adopting the method for obtaining the prediction model provided by the embodiment of the disclosure, a plurality of candidate models are obtained by training a plurality of preset models, and the prediction model is obtained by fusing the candidate models by using the model fusion technology, so that the prediction accuracy of the prediction model can be higher, and a user can conveniently predict whether equipment in an equipment pair is the communication equipment by using the prediction model.
With reference to fig. 5, an embodiment of the present disclosure provides an apparatus for opening a device, where the apparatus includes: a first acquisition module 501, a determination module 502, a second acquisition module 503, and a prediction module 504. The first obtaining module 501 is configured to obtain internet protocol IP addresses and occurrence times of the advertisement records corresponding to the advertisement records, and send the IP addresses and the occurrence times corresponding to the advertisement records to the determining module. The advertisement records are used to characterize data records generated by devices that have been reached by the delivered advertisements. The determining module 502 is configured to receive the IP addresses and the occurrence times corresponding to the advertisement records, determine a plurality of device pairs according to each IP address and each occurrence time, and send the device pairs to the second obtaining module. The second obtaining module 503 is configured to obtain the device pairs sent by the determining module, obtain device get-through characteristics corresponding to each device pair, and send the device get-through characteristics to the predicting module. The device getting through characteristics comprise the pairing number of the devices in the device pair, the active days of the devices, the exposure number of the devices, the number of the devices related to the getting through IP address, the pairing number of the devices, whether the active IP address of the devices is consistent with the getting through IP address or not, the exposure number ratio of the devices on the getting through IP address, the active days ratio of the devices on the getting through IP address, the first ratio of the exposure number of the devices on the getting through IP address to the total exposure number of the devices, and the second ratio of the active days of the devices on the getting through IP address to the total active days of the devices. The get-through IP address is an IP address corresponding to the equipment, and the active IP address is the IP address with the largest exposure times. The prediction module 504 is configured to receive the device opening characteristics sent by the second obtaining module, input each device opening characteristic into a preset prediction model, and predict whether the device in each device pair is an opening device.
By adopting the device for equipment getting through provided by the embodiment of the disclosure, the internet protocol IP addresses corresponding to a plurality of advertisement records and the occurrence time of each advertisement record are obtained through the first obtaining module, and the advertisement records are used for representing data records generated by equipment touched by the delivered advertisements. The determining module determines a plurality of equipment pairs according to each IP address and each occurrence time. And the second acquisition module acquires the getting-through characteristics of the equipment corresponding to each equipment. And the prediction module inputs the opening characteristics of each device into a preset prediction model and predicts whether the device in each device pair is an opening device or not. By considering various equipment opening characteristics such as the number of pairs of equipment in equipment pairs, the number of active days of the equipment, the number of exposure times of the equipment, the number of equipment associated with the opening IP address, the number of pairs of the equipment, whether the active IP address of the equipment is consistent with the opening IP address or not, the ratio of the number of exposure times of the equipment on the opening IP address to the number of active days of the equipment on the opening IP address, the ratio of the number of active days of the equipment on the opening IP address to the total number of exposure times of the equipment, the second ratio of the number of active days of the equipment on the opening IP address to the total number of active days of the equipment and the like, more and more comprehensive equipment opening characteristics are considered when the equipment is opened, and the accuracy of predicting whether the equipment is the opening equipment or not is improved.
Further, the first obtaining module is configured to obtain internet protocol IP addresses respectively corresponding to the plurality of advertisement records and occurrence times of the advertisement records by: and acquiring advertisement log data, wherein the advertisement log data comprises a plurality of advertisement records, and extracting the Internet protocol IP address corresponding to each advertisement record and the occurrence time of each advertisement record from the advertisement log data.
Further, the determining module is configured to determine a number of device pairs from each IP address and each occurrence time by: and pairing the devices corresponding to the advertisement records with the same IP addresses within the same preset time period to obtain a device pair.
Further, the prediction module is configured to input the opening characteristics of each device into a preset prediction model, and predict whether the devices in each device pair are opening devices by: and (3) opening the equipment by the characteristic prediction model to obtain the equipment opening probability of each equipment pair, and determining whether the equipment in each equipment pair is the opening equipment or not according to the equipment opening probability.
Further, determining whether the device in the device pair is the access device according to the device access probability, including: and under the condition that the equipment opening probability is greater than or equal to the preset probability, determining that the equipment in the equipment pair is the opening equipment.
Further, determining whether the device in the device pair is the access device according to the device access probability includes: and under the condition that the equipment opening probability is smaller than the preset probability, determining that the equipment in the equipment pair is not the opening equipment.
Further, the apparatus for device cut-through further includes a third obtaining module configured to obtain the prediction model by: and obtaining the characteristics of the sample device pair and a sample label corresponding to the characteristics of the sample device pair, wherein the sample label is used for representing whether the device pair corresponding to the characteristics of the sample device pair is a communication device. And training the characteristic input preset model of the sample equipment with the sample label to obtain a prediction model.
As shown in fig. 6, an embodiment of the present disclosure provides an electronic device including a processor (processor)600 and a memory (memory) 601. Optionally, the electronic device may further comprise a Communication Interface 602 and a bus 603. The processor 600, the communication interface 602, and the memory 601 may communicate with each other via a bus 603. The communication interface 602 may be used for information transfer. The processor 600 may call logic instructions in the memory 601 to perform the method for device drill-through of the above-described embodiments.
By adopting the electronic equipment provided by the embodiment of the disclosure, various equipment opening characteristics such as the number of pairing of equipment in equipment pairing, the number of active days of the equipment, the number of exposure times of the equipment, the number of equipment associated with the opening IP address, whether the active IP address of the equipment is consistent with the opening IP address or not, the ratio of the number of exposure times of the equipment on the opening IP address, the ratio of the number of active days of the equipment on the opening IP address, the first proportion of the number of exposure times of the equipment on the opening IP address to the total equipment exposure times, the second proportion of the number of active days of the equipment on the opening IP address to the total active days of the equipment and the like are considered, so that more and more comprehensive equipment opening characteristics are considered when the equipment is opened, and the accuracy of predicting whether the equipment is the opening equipment or not is improved.
In addition, the logic instructions in the memory 601 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products.
Optionally, the electronic device comprises a computer, a tablet computer, a server, or the like.
The memory 601 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, such as program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The processor 600 executes functional applications and data processing by executing program instructions/modules stored in the memory 601, i.e. implements the method for device punch-through in the above-described embodiments.
The memory 601 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. In addition, the memory 601 may include a high speed random access memory, and may also include a non-volatile memory.
The embodiment of the disclosure provides a storage medium, which stores program instructions, and when the program instructions are executed, the method for opening the equipment is executed.
Embodiments of the present disclosure provide a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the above-described method for device punch-through.
The computer-readable storage medium described above may be a transitory computer-readable storage medium or a non-transitory computer-readable storage medium.
The technical solution of the embodiments of the present disclosure may be embodied in the form of a software product, where the computer software product is stored in a storage medium and includes one or more instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium comprising: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes, and may also be a transient storage medium.
The above description and the drawings sufficiently illustrate embodiments of the disclosure to enable those skilled in the art to practice them. Other embodiments may incorporate structural, logical, electrical, process, and other changes. The examples merely typify possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in or substituted for those of others. Furthermore, the words used in the specification are words of description for example only and are not limiting upon the claims. As used in the description of the embodiments and the claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and/or" as used in this application is meant to encompass any and all possible combinations of one or more of the associated listed. Furthermore, the terms "comprises" and/or "comprising," when used in this application, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other like elements in a process, method or apparatus that comprises the element. In this document, each embodiment may be described with emphasis on differences from other embodiments, and the same and similar parts between the respective embodiments may be referred to each other. For methods, products, etc. of the embodiment disclosures, reference may be made to the description of the method section for relevance if it corresponds to the method section of the embodiment disclosure.
Those of skill in the art would appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software may depend upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments. It can be clearly understood by the skilled person that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses, and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, apparatuses, etc.) may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be merely a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to implement the present embodiment. In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two sequential operations or steps may in fact be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. Each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Claims (10)

1. A method for device drill-through, comprising:
acquiring Internet Protocol (IP) addresses respectively corresponding to a plurality of advertisement records and the occurrence time of each advertisement record; the advertisement records are used for representing data records generated by equipment touched by the delivered advertisements;
determining a plurality of equipment pairs according to the IP addresses and the occurrence times;
acquiring the communication characteristic of each device to the corresponding device; the equipment getting through characteristics comprise the pairing times of equipment pairs, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the getting through IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the getting through IP address or not, the exposure times of the equipment on the getting through IP address, the active days of the equipment on the getting through IP address, the exposure times of the equipment on the getting through IP address, the first proportion of the total exposure times of the equipment and the second proportion of the active days of the equipment on the getting through IP address to the total active days of the equipment; the communication IP address is an IP address corresponding to the equipment; the active IP address is the IP address with the largest exposure times;
and inputting the opening characteristics of each piece of equipment into a preset prediction model, and predicting whether the equipment in each equipment pair is the opening equipment or not.
2. The method of claim 1, wherein obtaining the IP addresses corresponding to the advertisement records and the occurrence times of the advertisement records comprises:
acquiring advertisement log data; the advertisement log data comprises a plurality of advertisement records;
and extracting the Internet protocol IP address corresponding to each advertisement record and the occurrence time of each advertisement record from the advertisement log data.
3. The method of claim 1, wherein determining a number of device pairs based on each of the IP addresses and each of the time of occurrence comprises:
and pairing the devices corresponding to the advertisement records with the same IP addresses within the same preset time period to obtain the device pairs.
4. The method of claim 1, wherein inputting the opening characteristics of each of the devices into a predetermined prediction model to predict whether the devices in each of the device pairs are opening devices comprises:
obtaining the equipment opening probability of each equipment pair by using the prediction model of the opening characteristics of each equipment;
and determining whether the equipment in each equipment pair is the access equipment or not according to the access probability of each equipment.
5. The method of claim 4, wherein determining whether a device in the pair of devices is a clearing device based on the device clearing probability comprises:
and determining the equipment in the equipment pair as the access equipment under the condition that the equipment access probability is greater than or equal to the preset probability.
6. The method of claim 4, wherein determining whether a device in the pair of devices is a clearing device based on the device clearing probability comprises:
and under the condition that the equipment opening probability is smaller than the preset probability, determining that the equipment in the equipment pair is not the opening equipment.
7. The method of claim 1, wherein the predictive model is obtained by:
acquiring sample equipment pair characteristics and sample labels corresponding to the sample equipment pair characteristics; the sample label is used for representing whether the device pair corresponding to the sample device pair characteristic is a communication device;
and training the characteristic input preset model of the sample equipment with the sample label to obtain the prediction model.
8. An apparatus for device arming, comprising:
the first acquisition module is configured to acquire Internet Protocol (IP) addresses respectively corresponding to a plurality of advertisement records and occurrence time of each advertisement record; the advertisement records are used for representing data records generated by equipment touched by the delivered advertisements;
A determining module configured to determine a plurality of device pairs according to each of the IP addresses and each of the occurrence times;
the second acquisition module is configured to acquire the device getting-through characteristics corresponding to the devices respectively; the equipment getting through characteristics comprise the pairing times of equipment pairs, the active days of the equipment, the exposure times of the equipment, the equipment number associated with the getting through IP address, the pairing number of the equipment, whether the active IP address of the equipment is consistent with the getting through IP address or not, the exposure times of the equipment on the getting through IP address, the active days of the equipment on the getting through IP address, the exposure times of the equipment on the getting through IP address, the first proportion of the total exposure times of the equipment and the second proportion of the active days of the equipment on the getting through IP address to the total active days of the equipment; the communication IP address is an IP address corresponding to the equipment; the active IP address is the IP address with the largest exposure times;
and the prediction module is configured to input each equipment opening characteristic into a preset prediction model and predict whether the equipment in each equipment pair is the opening equipment.
9. An electronic device comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for device arming of any one of claims 1-7 when executing the program instructions.
10. A storage medium storing program instructions which, when executed, perform a method for device arming as claimed in any one of claims 1 to 7.
CN202210504954.0A 2022-05-10 2022-05-10 Method and device for device call-through, electronic device and storage medium Pending CN114757716A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210504954.0A CN114757716A (en) 2022-05-10 2022-05-10 Method and device for device call-through, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210504954.0A CN114757716A (en) 2022-05-10 2022-05-10 Method and device for device call-through, electronic device and storage medium

Publications (1)

Publication Number Publication Date
CN114757716A true CN114757716A (en) 2022-07-15

Family

ID=82336010

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210504954.0A Pending CN114757716A (en) 2022-05-10 2022-05-10 Method and device for device call-through, electronic device and storage medium

Country Status (1)

Country Link
CN (1) CN114757716A (en)

Similar Documents

Publication Publication Date Title
CN112543176A (en) Abnormal network access detection method, device, storage medium and terminal
CN107305611B (en) Method and device for establishing model corresponding to malicious account and method and device for identifying malicious account
CN107678800B (en) Background application cleaning method and device, storage medium and electronic equipment
CN113383362B (en) User identification method and related product
CN112613917A (en) Information pushing method, device and equipment based on user portrait and storage medium
CN103309998A (en) Message query method, message query device and terminal equipment
CN105760522A (en) Information search method and device based on application program
CN113412607B (en) Content pushing method and device, mobile terminal and storage medium
CN113435912A (en) Data analysis method, device, equipment and medium based on client portrait
CN113505272B (en) Control method and device based on behavior habit, electronic equipment and storage medium
CN110392155A (en) It has been shown that, processing method, device and the equipment of notification message
CN113344682A (en) Order processing method and device, electronic equipment and computer readable storage medium
CN103544150A (en) Method and system for providing recommendation information for mobile terminal browser
CN111126071A (en) Method and device for determining questioning text data and data processing method of customer service group
CN114143402A (en) AI outbound method, device, computer equipment and storage medium
CN111724098B (en) Information display method and system, electronic equipment and storage medium
CN105610698B (en) The treating method and apparatus of event result
CN105630996B (en) Information processing method and server
CN104240107A (en) Community data screening system and method thereof
CN114757716A (en) Method and device for device call-through, electronic device and storage medium
CN115586937A (en) Interface display method and device, electronic equipment and readable storage medium
CN115002508A (en) Live data stream method and device, computer equipment and storage medium
CN115221892A (en) Work order data processing method and device, storage medium and electronic equipment
CN109241381A (en) Information matching method and device
CN113656731A (en) Advertisement page processing method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination