Method, device and apparatus for data updating

Abstract

The present application relates to the field of data processing technology, and discloses a method for data updating, including: obtaining a netizen attribute data set and a candidate netizen attribute data set; determining an inactive sample to be replaced in the netizen attribute data set, and the first user information corresponding to the inactive sample to be replaced; the first user information includes the first user attribute, the advertisement corresponding to the first user information, the advertisement source type corresponding to the first user information, and the first user activity; determining the candidate sample corresponding to the inactive sample to be replaced in the candidate netizen attribute data set according to the first user information; and updating the netizen attribute data set using the candidate sample. Determining the candidate sample using the first user information corresponding to the inactive sample to be replaced, and updating the netizen attribute data set using the candidate sample, reduces the difference before and after the data update, and improves the stability of the data update process. The present application also discloses a device and equipment for data updating.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, for example, to a method, apparatus and device for data updating. Background Art

[0002] Currently, in the field of third-party advertising monitoring, data analysis about users is inseparable from the user's attribute information, so there is a need for a data set containing the basic information of user samples and to dynamically update the data set periodically.

[0003] In the process of implementing the embodiments of the present disclosure, it was found that at least the following problems exist in the related technology: the existing data update directly replaces inactive samples with active samples based on the same user attributes, without considering the advertisements corresponding to the user information and the user's activity, and the stability of the data update process is low. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] The embodiments of the present disclosure provide a method for data updating, an apparatus for data updating, and a device for data updating, which improve the stability during the data updating process.

[0006] In some embodiments, the method includes: obtaining a netizen attribute data set and a candidate netizen attribute data set; determining an inactive sample to be replaced in the netizen attribute data set, and first user information corresponding to the inactive sample to be replaced; the first user information includes a first user attribute, an advertisement corresponding to the first user information, an advertisement source type corresponding to the first user information, and the first user activity; determining a candidate sample corresponding to the inactive sample to be replaced in the candidate netizen attribute data set based on the first user information; and updating the netizen attribute data set using the candidate sample.

[0007] In some embodiments, the device includes: a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for product recommendation when executing the program instructions.

[0008] In some embodiments, the device comprises the above-mentioned means for data updating.

[0009] The method, apparatus and device for data updating provided by the embodiments of the present disclosure can achieve the following technical effects: determining candidate samples corresponding to the inactive samples to be replaced in the candidate netizen attribute data set through the first user attributes corresponding to the inactive samples to be replaced in the netizen attribute data set, the advertisements corresponding to the first user information, the advertisement source type corresponding to the first user information and the first user activity, and updating the netizen attribute data set using the candidate samples, thereby reducing the difference between the updated data set and the data set before the update, thereby reducing fluctuations during data updating and improving stability during the data updating process.

[0010] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0012] Figure 1 is a schematic diagram of a method for data updating provided by an embodiment of the present disclosure;

[0013] Figure 2 is a schematic diagram of another method for data updating provided by an embodiment of the present disclosure;

[0014] Figure 3 It is a schematic diagram of a device for data updating provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0016] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0017] Unless otherwise stated, the term "plurality" means two or more.

[0018] 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 indicates: A or B.

[0019] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0020] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for updating data, including:

[0021] S101, obtaining a netizen attribute dataset and a candidate netizen attribute dataset;

[0022] S102, determining an inactive sample to be replaced in the netizen attribute data set, and first user information corresponding to the inactive sample to be replaced; the first user information includes a first user attribute, an advertisement corresponding to the first user information, an advertisement source type corresponding to the first user information, and first user activity;

[0023] S103, determining a candidate sample corresponding to the inactive sample to be replaced in the candidate netizen attribute data set according to the first user information;

[0024] S104: Update the Internet user attribute dataset using the candidate samples.

[0025] By adopting the method for data updating provided by the embodiment of the present disclosure, candidate samples corresponding to the inactive samples to be replaced are determined in the candidate netizen attribute data set through the first user attribute corresponding to the inactive samples to be replaced in the netizen attribute data set, the advertisement corresponding to the first user information, the advertisement source type corresponding to the first user information, and the first user activity, and the netizen attribute data set is updated using the candidate samples, thereby reducing the difference between the updated data set and the data set before the update, thereby reducing the fluctuation during data updating and improving the stability during the data updating process.

[0026] Optionally, determining the inactive samples to be replaced in the netizen attribute data set and the first user information corresponding to the inactive samples to be replaced includes: obtaining netizen category proportion data and first log data corresponding to the netizen attribute data set; determining the inactive samples to be replaced in the netizen attribute data set based on the netizen category proportion data and the netizen attribute data set; and obtaining the first user information corresponding to the inactive samples to be replaced based on the first log data and the inactive samples to be replaced.

[0027] Optionally, the netizen attribute data set stores a user sample, a user ID (Identity document, identity identification number) corresponding to the user sample, and a fourth user attribute corresponding to the user sample.

[0028] Optionally, the fourth user attribute includes: one or more of: city, gender, age, education level, personal income, family income and average family income.

[0029] In some embodiments, as shown in Table 1, Table 1 is an example table of a netizen attribute data set. Among them, user ID is the user ID corresponding to the user sample, city is the city corresponding to the user sample, sex is the gender corresponding to the user sample, age is the age corresponding to the user sample, edu is the education level corresponding to the user sample, pmi is the personal income corresponding to the user sample, fmi is the family income corresponding to the user sample, and hmi is the average family income corresponding to the user sample. The fourth user attributes corresponding to the user sample include: city, gender, age, education level, personal income, family income and average family income.

[0030]

[0031] Table 1

[0032] In some embodiments, as shown in Table 1, the city code corresponding to the user sample with user ID "00000743-c6f7-42f3-b917-e8b444a9badd" is 802, the gender code corresponding to the user sample is 1, where the gender code "1" is male and the gender code "2" is female, the age corresponding to the user sample is 6 years old, the encrypted data of the education level corresponding to the user sample is 18, the encrypted data of the personal income corresponding to the user sample is 20, the encrypted data of the family income corresponding to the user sample is 30, and the encrypted data of the average family income corresponding to the user sample is 35.

[0033] Optionally, the first log data includes the user ID corresponding to the user sample in the netizen attribute data set and the label information of the fourth user information corresponding to the user sample. Optionally, the label information of the fourth user information includes: the advertisement corresponding to the fourth user information, the advertisement source type corresponding to the fourth user information and the fourth user activity. Optionally, the advertisement source type corresponding to the fourth user information includes: cookie (data stored on the user's local terminal), IMEI (International Mobile Equ ipment Identity), IDFA (Identifier For Advertising) or OAID (Open Anonymous Device Identifier). Optionally, the fourth user activity is the number of times the corresponding user sample appears within a preset time period. Optionally, the netizen attribute data set is periodically updated according to the preset time period. Optionally, the preset time period is set according to the business scenario. Optionally, the preset time period is 1 month. Optionally, the user samples are divided into active samples and inactive samples according to the fourth user activity corresponding to the user samples. Optionally, when the fourth user activity is 0, the corresponding user sample is determined as an inactive sample; when the fourth user activity is not 0, the corresponding user sample is determined as an active sample. Optionally, the user ID corresponding to the active sample and the fifth user attribute corresponding to the active sample are obtained from the netizen attribute data set; the user ID corresponding to the inactive sample and the sixth user attribute corresponding to the inactive sample are obtained from the netizen attribute data set.

[0034] Optionally, the netizen category proportion data is the percentage of netizens of each age group to the total netizens. Optionally, the inactive samples to be replaced are determined in the netizen attribute data set according to the netizen category proportion data. In this way, the percentage of active samples of each age group to the total active samples in the updated netizen attribute data set can be the same as the netizen category proportion data.

[0035] Optionally, obtaining the first user information corresponding to the inactive sample to be replaced according to the first log data and the inactive sample to be replaced includes: obtaining the label information of the first user information corresponding to the inactive sample to be replaced in the first log data according to the user ID corresponding to the inactive sample to be replaced. In some embodiments, as shown in Table 2, Table 2 is an example table of the user ID and the first user information corresponding to the inactive sample to be replaced, wherein ID type is the type of advertisement source corresponding to the inactive sample to be replaced, act is the first user activity corresponding to the inactive sample to be replaced, spids is the advertisement corresponding to the inactive sample to be replaced, user ID is the user ID corresponding to the inactive sample to be replaced, city is the city corresponding to the inactive sample to be replaced, sex is the gender corresponding to the inactive sample to be replaced, age is the age corresponding to the inactive sample to be replaced, edu is the education level corresponding to the inactive sample to be replaced, pmi is the personal income corresponding to the inactive sample to be replaced, fmi is the family income corresponding to the inactive sample to be replaced, and hmi is the average family income corresponding to the inactive sample to be replaced.

[0036]

[0037]

[0038] Table 2

[0039] In some embodiments, as shown in Table 2, the code of the city corresponding to the inactive sample to be replaced with user ID "00000743-c6f7-42f3-b917-e8b444a9badd" is 802, the gender code corresponding to the inactive sample to be replaced is 1, the age corresponding to the inactive sample to be replaced is 6 years old, the encrypted data of the education level corresponding to the inactive sample to be replaced is 18, the encrypted data of the personal income corresponding to the inactive sample to be replaced is 20, the encrypted data of the family income corresponding to the inactive sample to be replaced is 30, the encrypted data of the average family income corresponding to the inactive sample to be replaced is 35, the advertising source type corresponding to the inactive sample to be replaced is IMEI, the first user activity corresponding to the inactive sample to be replaced is 0, and the advertisement corresponding to the inactive sample to be replaced is "109560125; 118560427".

[0040] The inactive samples to be replaced in the netizen attribute data set are determined through the netizen category proportion data and the netizen attribute data set, and the first user information corresponding to the inactive samples to be replaced is obtained according to the first log data and the inactive samples to be replaced, so as to facilitate the determination of candidate samples corresponding to the inactive samples to be replaced through the first user information, thereby facilitating the reduction of the difference between the updated data set and the data set before the update, and can facilitate the reduction of fluctuations during data update and improve the stability during the data update process.

[0041] Optionally, determining a candidate sample corresponding to the inactive sample to be replaced in the candidate netizen attribute data set based on the first user information includes: obtaining second log data corresponding to the candidate netizen attribute data set; determining second user information of the first candidate sample in the candidate netizen attribute data set based on the second log data; the second user information includes second user attributes, advertisements corresponding to the second user information, advertisement source types corresponding to the second user information, and second user activity; when the first user information and the second user information meet a first preset condition, determining the first candidate sample corresponding to the second user information as the candidate sample corresponding to the inactive sample to be replaced.

[0042] Optionally, the candidate netizen attribute data set stores a first candidate sample, a user ID corresponding to the first candidate sample, and a second user attribute corresponding to the first candidate sample.

[0043] Optionally, the second log data includes the user ID corresponding to the first candidate sample in the candidate netizen attribute data set and the label information of the second user information corresponding to the first candidate sample. Optionally, the label information of the second user information includes: the advertisement corresponding to the second user information, the advertisement source type corresponding to the second user information, and the activity of the second user. Optionally, the advertisement source type corresponding to the second user information includes: cookie, IMEI, IDFA or OAID.

[0044] Optionally, the second user attribute includes: one or more of city, gender, age, education level, personal income, family income and average family income. In some embodiments, as shown in Table 3, Table 3 is an example table of the candidate netizen attribute data set. Among them, user ID is the user ID corresponding to the first candidate sample, city is the city corresponding to the first candidate sample, sex is the gender corresponding to the first candidate sample, age is the age corresponding to the first candidate sample, edu is the education level corresponding to the first candidate sample, pmi is the personal income corresponding to the first candidate sample, fmi is the family income corresponding to the first candidate sample, and hmi is the average family income corresponding to the first candidate sample.

[0045]

[0046] Table 3

[0047] In some embodiments, as shown in Table 3, the city code corresponding to the first candidate sample with user ID "47B209551FD0D1C5CAB15A586B491A5F" is 802, the gender code corresponding to the first candidate sample is 1, the age corresponding to the first candidate sample is 6 years old, the encrypted data of the education level corresponding to the first candidate sample is 18, the encrypted data of the personal income corresponding to the first candidate sample is 20, the encrypted data of the family income corresponding to the first candidate sample is 30, and the encrypted data of the average family income corresponding to the first candidate sample is 35.

[0048] Optionally, determining the second user information of the first candidate sample in the candidate netizen attribute data set according to the second log data includes: obtaining the label information of the second user information corresponding to the first candidate sample in the second log data according to the user ID corresponding to the first candidate sample. In some embodiments, as shown in Table 4, Table 4 is an example table of the user ID and the second user information corresponding to the first candidate sample; wherein act is the second user activity corresponding to the first candidate sample, spids is the advertisement corresponding to the first candidate sample, ID type is the advertisement source type corresponding to the first candidate sample, user ID is the user ID corresponding to the first candidate sample, city is the city corresponding to the first candidate sample, sex is the gender corresponding to the first candidate sample, age is the age corresponding to the first candidate sample, edu is the education level corresponding to the first candidate sample, pmi is the personal income corresponding to the first candidate sample, fmi is the family income corresponding to the first candidate sample, and hmi is the average family income corresponding to the first candidate sample.

[0049]

[0050]

[0051] Table 4

[0052] In some embodiments, as shown in Table 4, the city code corresponding to the first candidate sample with user ID "47B209551FD0D1C5CAB15A586B491A5F" is 802, the gender code corresponding to the first candidate sample is 1, the age corresponding to the first candidate sample is 6 years old, the encrypted data of the education level corresponding to the first candidate sample is 18, the encrypted data of the personal income corresponding to the first candidate sample is 20, the encrypted data of the family income corresponding to the first candidate sample is 30, the encrypted data of the average family income corresponding to the first candidate sample is 35, the advertising source type corresponding to the first candidate sample is IMEI, the second user activity corresponding to the first candidate sample is 70, and the advertisement corresponding to the first candidate sample is "109560125; 118560427".

[0053] In this way, the second user information of the first candidate sample in the candidate netizen attribute data set is determined according to the second log data, and the candidate sample corresponding to the inactive sample to be replaced is determined through the second user information, which facilitates the use of the candidate sample to update the netizen attribute data set, reduces the difference between the updated data set and the data set before the update, thereby reducing the fluctuation during data update and improving the stability of the data update process.

[0054] Optionally, when the first user information and the second user information meet the first preset condition, determining the first candidate sample corresponding to the second user information as the candidate sample corresponding to the inactive sample to be replaced includes: when the proportion of advertisements corresponding to the second user information and the advertisements corresponding to the first user information that are the same is greater than a first threshold and the activity of the second user meets the second preset condition, determining the first candidate sample corresponding to the second user information as the candidate sample corresponding to the inactive sample to be replaced. Optionally, the first threshold is 50%.

[0055] Optionally, the second preset condition is that the second user activity is within a preset first interval. Optionally, the second user activity is within a preset first interval, including: the second user activity is less than or equal to the first set value and greater than or equal to the second set value; wherein the first set value is greater than the second set value. Optionally, the first set value is twice the average activity value of the fifth user corresponding to the active sample; optionally, the second set value is half the average activity value of the fifth user corresponding to the active sample.

[0056] Optionally, the fifth user activity corresponding to the active sample is obtained in the first log data according to the user ID corresponding to the active sample.

[0057] In some embodiments, there are 10 advertisements corresponding to the first user information, with an average activity of 60, and 5 of the advertisements corresponding to the second user information are the same as the advertisements corresponding to the first user information. When the second user activity is less than or equal to 120 and the second user activity is greater than or equal to 30, the first candidate sample corresponding to the second user information is determined as the candidate sample corresponding to the inactive sample to be replaced.

[0058] Optionally, the second preset condition is that the second user activity is within a preset second interval. Optionally, the second user activity is within a preset second interval, including: the second user activity is less than or equal to a third setting value and greater than or equal to a fourth setting value; wherein the third setting value is greater than the fourth setting value. Optionally, the third setting value is the first user activity of the inactive sample to be replaced corresponding to the second user information in the previous cycle plus 5; the fourth setting value is the first user activity of the inactive sample to be replaced corresponding to the second user information in the previous cycle minus 5.

[0059] In some embodiments, there are 10 advertisements corresponding to the first user information, the first user activity in the previous cycle is 60, and 5 of the advertisements corresponding to the second user information are the same as the advertisements corresponding to the first user information, and when the second user activity is less than or equal to 65 and the second user activity is greater than or equal to 55, the first candidate sample corresponding to the second user information is determined as the candidate sample corresponding to the inactive sample to be replaced.

[0060] Optionally, when the first user information and the second user information meet a first preset condition, the first candidate sample corresponding to the second user information is determined as the candidate sample corresponding to the inactive sample to be replaced, including: when the proportion of advertisements corresponding to the second user information and those corresponding to the first user information is greater than a first threshold, the second user activity meets a second preset condition, the second user attributes are the same as the first user attributes, and the advertisement source type corresponding to the second user information is the same as the advertisement source type corresponding to the first user information, the first candidate sample corresponding to the second user information is determined as the candidate sample corresponding to the inactive sample to be replaced.

[0061] In this way, the candidate sample corresponding to the inactive sample to be replaced is determined by the first user information and the second user information, which makes it easier to use the candidate sample to update the netizen attribute data set, reducing the difference between the updated data set and the data set before the update, thereby reducing fluctuations during data updating and improving stability during the data updating process.

[0062] Optionally, updating the netizen attribute dataset using candidate samples corresponding to the inactive samples to be replaced includes: determining a first candidate active sample from the candidate samples according to a preset rule; and replacing the inactive samples to be replaced with the first candidate active sample.

[0063] Optionally, a candidate sample corresponding to the inactive sample to be replaced is randomly selected, and the selected candidate sample is determined as the first candidate active sample.

[0064] In this way, the first candidate active sample is determined from the candidate samples through preset rules, and the first candidate active sample replaces the inactive sample to be replaced, which facilitates testing the replaced data to obtain test results, thereby facilitating adjustment of the replaced data set through the test results, thereby facilitating reducing the difference between the updated data and the data before the update, reducing fluctuations during data updating, and improving stability during the data updating process.

[0065] Optionally, after updating the netizen attribute dataset using candidate samples, it also includes: obtaining an updated netizen attribute dataset; obtaining active samples in the updated netizen attribute dataset, and updating third user information corresponding to the active samples in the netizen attribute dataset; the third user information includes third user attributes, advertisements corresponding to the third user information, advertisement source types corresponding to the third user information, and third user activity; testing the updated netizen attribute dataset according to the advertisements corresponding to the third user information and the third user attributes to obtain test results; if the test results are unqualified, updating the netizen attribute dataset.

[0066] Optionally, updating the active samples in the netizen attribute data set includes: the active samples in the netizen attribute data set and the first candidate active samples.

[0067] Optionally, the third user attribute includes: one or more of city, gender, age, education level, personal income, family income and average family income. In some embodiments, as shown in Table 5, Table 5 is an example table of user IDs and third user information corresponding to active samples in the updated netizen attribute data set, wherein city is the city corresponding to the updated active sample in the netizen attribute data set, sex is the gender corresponding to the updated active sample in the netizen attribute data set, age is the age corresponding to the updated active sample in the netizen attribute data set, edu is the education level corresponding to the updated active sample in the netizen attribute data set, pmi is the personal income corresponding to the updated active sample in the netizen attribute data set, fmi is the family income corresponding to the updated active sample in the netizen attribute data set, hmi is the average family income corresponding to the updated active sample in the netizen attribute data set, ID type is the advertising source type corresponding to the updated active sample in the netizen attribute data set, act is the third user activity corresponding to the updated active sample in the netizen attribute data set, and spids is the advertisement corresponding to the updated active sample in the netizen attribute data set.

[0068]

[0069]

[0070] Table 5

[0071] In some embodiments, as shown in Table 5, the code of the city corresponding to the active sample in the updated netizen attribute data set with user ID "47B209551FD0D1C5CAB15A586B491A5F" is 802, the gender code corresponding to the active sample is 1, the age corresponding to the active sample is 6 years old, the encrypted data of the education level corresponding to the active sample is 18, the encrypted data of the personal income corresponding to the active sample is 20, the encrypted data of the family income corresponding to the active sample is 30, the encrypted data of the average family income corresponding to the active sample is 35, the advertising source type corresponding to the active sample is IMEI, the third user activity corresponding to the active sample is 70, and the advertisement corresponding to the active sample is "109560125; 118560427".

[0072] Optionally, the updated netizen attribute data set is tested according to the advertisement corresponding to the third user information and the third user attribute to obtain the test result, including: taking the advertisement corresponding to the third user information and the advertisement corresponding to the fourth user information as the test advertisement; obtaining the user attribute type; obtaining the first ratio of the number of test advertisements corresponding to each user attribute type before the update to the total number of the test advertisements; obtaining the second ratio of the number of test advertisements corresponding to each user attribute type after the update to the total number of the test advertisements; obtaining the absolute value of the difference between the first ratio and the second ratio corresponding to each user attribute type; when the absolute value of the difference is greater than or equal to the second threshold, the test advertisement corresponding to the user attribute type is unqualified; when the number of unqualified test advertisements corresponding to the user attribute type accounts for the total number of test advertisements greater than or equal to the third threshold, the test result is unqualified. Optionally, the second threshold is 0.03. Optionally, the third threshold is set according to the application scenario. Optionally, the third threshold is 3%.

[0073] Optionally, obtaining the user attribute type includes: dividing the fourth user attribute and the third user attribute according to age and gender to obtain the user attribute type. In some embodiments, the user attribute type includes "male, 0 to 60 years old", "male, over 60 years old", "female, 0 to 60 years old", and "female, over 60 years old".

[0074] In some embodiments, as shown in Table 6, Table 6 is an example table of the number of test advertisements corresponding to each user attribute type before the update, where M0-60 means "male, 0 to 60 years old", M60+ means "male, over 60 years old", F0-60 means "female, 0 to 60 years old", and F60+ means "female, over 60 years old".

[0075]

[0076] Table 6

[0077] In some embodiments, as shown in Table 6, in the netizen attribute data set, the number of test advertisements 109560125 corresponding to the user attribute type of "male, 0 to 60 years old" is 0, the number of test advertisements 109560125 corresponding to the user attribute type of "male, over 60 years old" is 2, the number of test advertisements 109560125 corresponding to the user attribute type of "female, 0 to 60 years old" is 1, and the number of test advertisements 109560125 corresponding to the user attribute type of "female, over 60 years old" is 0. Table 7 is an example table of the first proportion of the number of test advertisements corresponding to each user attribute type in Table 6 to the total number of test advertisements.

[0078]

[0079] Table 7

[0080] In some embodiments, as shown in Table 7, in the netizen attribute data set, the first proportion of the test advertisement 109560125 corresponding to the user attribute type of "male, 0 to 13 years old" is 0, the first proportion of the test advertisement 109560125 corresponding to the user attribute type of "male, over 60 years old" is 2 / 3, the first proportion of the test advertisement 109560125 corresponding to the user attribute type of "female, 0 to 13 years old" is 1 / 3, and the first proportion of the test advertisement 109560125 corresponding to the user attribute type of "female, over 60 years old" is 0.

[0081] In some embodiments, as shown in Table 8, Table 8 is an example table of statistics of the number of test advertisements corresponding to each user attribute type after update, wherein M0-60 means "male, 0 to 60 years old", M60+ means "male, over 60 years old", F0-60 means "female, 0 to 60 years old", and F60+ means "female, over 60 years old".

[0082]

[0083] Table 8

[0084] In some embodiments, as shown in Table 8, in the updated netizen attribute data set, the number of test advertisements 109560125 corresponding to the user attribute type "male, 0 to 60 years old" is 1, the number of test advertisements 109560125 corresponding to the user attribute type "male, over 60 years old" is 2, the number of test advertisements 109560125 corresponding to the user attribute type "female, 0 to 60 years old" is 1, and the number of test advertisements 109560125 corresponding to the user attribute type "female, over 60 years old" is 0. Table 8 is an example table of the second proportion of the number of test advertisements corresponding to each user attribute type in Table 7 to the total number of test advertisements.

[0085]

[0086] Table 9

[0087] In some embodiments, as shown in Table 9, in the updated netizen attribute data set, the second proportion of the test advertisement 109560125 corresponding to the user attribute type of "male, 0 to 13 years old" is 1 / 4, the second proportion of the test advertisement 109560125 corresponding to the user attribute type of "male, over 60 years old" is 1 / 2, the second proportion of the test advertisement 109560125 corresponding to the user attribute type of "female, 0 to 13 years old" is 1 / 4, and the second proportion of the test advertisement 109560125 corresponding to the user attribute type of "female, over 60 years old" is 0.

[0088] In some embodiments, as shown in Table 10, Table 10 is an example table of the absolute value of the difference between the first ratio of Table 7 and the second ratio of Table 9 and the corresponding user attribute types and test advertisements.

[0089]

[0090] Table 10

[0091] In some embodiments, as shown in Table 10, the absolute value of the difference between the first ratio and the second ratio of the test advertisement 109560125 corresponding to the user attribute type of "male, 0 to 13 years old" is 1 / 4, the absolute value of the difference between the first ratio and the second ratio of the test advertisement 109560125 corresponding to the user attribute type of "male, over 60 years old" is 1 / 6, the absolute value of the difference between the first ratio and the second ratio of the test advertisement 109560125 corresponding to the user attribute type of "female, 0 to 13 years old" is 1 / 12, and the absolute value of the difference between the first ratio and the second ratio of the test advertisement 109560125 corresponding to the user attribute type of "female, over 60 years old" is 0.

[0092] In some embodiments, the absolute value of the difference between the first ratio and the second ratio of the test advertisement 109560125 corresponding to the user attribute type "male, 0 to 13 years old" is 1 / 4, and 1 / 4 is greater than 0.03, then the test advertisement 109560125 corresponding to the user attribute type "male, 0 to 13 years old" is unqualified.

[0093] The updated netizen attribute dataset is tested according to the active samples in the updated netizen attribute dataset and the third user information corresponding to the active samples, and the test results are obtained. If the test results are unqualified, the netizen attribute dataset is updated. The netizen attribute dataset is updated according to the test results, which facilitates the adjustment of the updated dataset so that the updated dataset can better meet the requirements.

[0094] Optionally, when the test result is unqualified, the netizen attribute dataset is updated, including: determining a second candidate active sample from the candidate samples according to a preset rule; replacing the second candidate active sample with the inactive sample to be replaced, and updating the netizen attribute dataset.

[0095] Optionally, after replacing the second candidate active sample with the inactive sample to be replaced and updating the netizen attribute dataset, an updated netizen attribute dataset is obtained; the active sample in the updated netizen attribute dataset and the third user information corresponding to the active sample are obtained; the third user information includes the third user attributes, the advertisement corresponding to the third user information, the advertisement source type corresponding to the third user information and the third user activity; the updated netizen attribute dataset is tested according to the advertisement corresponding to the third user information and the third user attributes to obtain the test result; if the test result is unqualified, the netizen attribute dataset is updated.

[0096] Optionally, t is an update cumulative value. Optionally, when the netizen attribute dataset is updated for the first time, the initial value of the update cumulative value is 0, and the update cumulative value is increased by 1 each time it is updated.

[0097] In some embodiments, when the update cumulative value is 20 and the test result is unqualified, the updated netizen attribute data set corresponding to the minimum absolute value of the difference is used as the updated netizen attribute data set.

[0098] In this way, when the test results are unqualified, the second candidate active sample is determined from the candidate samples according to the preset rules and the second candidate active sample is replaced with the inactive sample to be replaced, so as to update the netizen attribute data set, so as to make the updated data set meet the requirements, thereby facilitating reducing the difference between the updated data and the data before the update, reducing the fluctuation during data update, and improving the stability of the data update process.

[0099] In some embodiments, in combination Figure 2 , a method for updating data provided by an embodiment of the present disclosure includes:

[0100] Step S201, obtaining a netizen attribute data set, a candidate netizen attribute data set, first log data, second log data, and netizen category ratio data;

[0101] Step S202, determining an inactive sample to be replaced in the netizen attribute data set according to the netizen category proportion data and the netizen attribute data set, and obtaining first user information corresponding to the inactive sample to be replaced according to the first log data;

[0102] Step S203, determining the first candidate sample and the second user information corresponding to the first candidate sample through the candidate netizen attribute data set and the second log data;

[0103] Step S204, when the first user information and the second user information meet the first preset condition, determine the first candidate sample corresponding to the second user information that meets the first preset condition as the candidate sample corresponding to the inactive sample to be replaced;

[0104] Step S205, determining a first candidate active sample from the candidate samples corresponding to the inactive sample to be replaced according to a preset rule, and replacing the first candidate active sample with the active sample to be replaced;

[0105] Step S206, obtaining the updated netizen attribute data set after replacement;

[0106] Step S207, testing the updated netizen attribute data set to obtain a test result;

[0107] Step S208, determining whether the test result is qualified, if the test result is qualified, executing step S209; if the test result is unqualified, executing step S205;

[0108] Step S209, obtaining an updated netizen attribute data set.

[0109] Combination Figure 3 As shown, an embodiment of the present disclosure provides a device for data update, including a processor 100 and a memory 101 storing program instructions. Optionally, the device may also include a communication interface 102 and a bus 103. The processor 100, the communication interface 102, and the memory 101 may communicate with each other through the bus 103. The communication interface 102 may be used for information transmission. The processor 100 may call the program instructions in the memory 101 to execute the method for data update of the above embodiment.

[0110] In addition, the program instructions in the above-mentioned memory 101 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0111] The memory 101 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 100 executes functional applications and data processing by running the program instructions / modules stored in the memory 101, that is, implementing the method for data updating in the above embodiments.

[0112] The memory 101 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 101 may include a high-speed random access memory and may also include a non-volatile memory.

[0113] By using the device for data updating provided by the embodiment of the present disclosure, it is possible to determine candidate samples corresponding to the inactive samples to be replaced in the candidate netizen attribute data set through the first user attribute corresponding to the inactive samples to be replaced in the netizen attribute data set, the advertisement corresponding to the first user information, the advertisement source type corresponding to the first user information, and the first user activity, and use the candidate samples to update the netizen attribute data set, thereby reducing the difference between the updated data set and the data set before the update, thereby reducing fluctuations during data updating and improving stability during the data updating process.

[0114] An embodiment of the present disclosure provides a device, comprising the above-mentioned apparatus for data updating.

[0115] Optionally, the device includes a server.

[0116] The device can determine candidate samples corresponding to the inactive samples to be replaced in the candidate netizen attribute data set through the first user attributes corresponding to the inactive samples to be replaced in the netizen attribute data set, the advertisements corresponding to the first user information, the advertisement source type corresponding to the first user information, and the first user activity, and use the candidate samples to update the netizen attribute data set, thereby reducing the difference between the updated data set and the data set before the update, thereby reducing the fluctuation during data update and improving the stability during the data update process.

[0117] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above method for data updating.

[0118] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned method for data updating.

[0119] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0120] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0121] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0122] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0123] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0124] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for data updating, characterized in that: include: Obtaining a netizen attribute dataset and a candidate netizen attribute dataset; Determining an inactive sample to be replaced in the netizen attribute data set, and first user information corresponding to the inactive sample; The first user information includes a first user attribute, an advertisement corresponding to the first user information, an advertisement source type corresponding to the first user information, and the first user activity; Determine, in the candidate netizen attribute data set, a candidate sample corresponding to the inactive sample according to the first user information; Using the candidate samples to update the netizen attribute dataset; Determining, according to the first user information, a candidate sample corresponding to the inactive sample in the candidate netizen attribute data set includes: Obtaining second log data corresponding to the candidate netizen attribute data set; Determine the second user information of the first candidate sample in the candidate netizen attribute data set according to the second log data; the second user information includes the second user attribute, the advertisement corresponding to the second user information, the advertisement source type corresponding to the second user information, and the second user activity; When the first user information and the second user information satisfy a first preset condition, a first candidate sample corresponding to the second user information is determined as a candidate sample corresponding to the inactive sample.

2. The method according to claim 1, characterized in that Determining the inactive sample to be replaced in the netizen attribute data set and the first user information corresponding to the inactive sample includes: Obtaining the first log data corresponding to the netizen category proportion data and the netizen attribute data set; Determine the inactive sample in the netizen attribute data set according to the netizen category proportion data and the netizen attribute data set; The first user information corresponding to the inactive sample is acquired according to the first log data and the inactive sample.

3. The method according to claim 1, characterized in that When the first user information and the second user information meet a first preset condition, determining a first candidate sample corresponding to the second user information as a candidate sample corresponding to the inactive sample includes: When the proportion of advertisements corresponding to the second user information that are identical to the advertisements corresponding to the first user information is greater than a first threshold and the activity of the second user meets a second preset condition, the first candidate sample corresponding to the second user information is determined as the candidate sample corresponding to the inactive sample.

4. The method according to claim 1, characterized in that When the first user information and the second user information meet a first preset condition, determining a first candidate sample corresponding to the second user information as a candidate sample corresponding to the inactive sample includes: When the proportion of advertisements corresponding to the second user information that are identical to the advertisements corresponding to the first user information is greater than a first threshold, the second user activity satisfies a second preset condition, the second user attributes are identical to the first user attributes, and the advertisement source type corresponding to the second user information is identical to the advertisement source type corresponding to the first user information, the first candidate sample corresponding to the second user information is determined as the candidate sample corresponding to the inactive sample.

5. The method according to claim 1, characterized in that The updating of the netizen attribute dataset using the candidate samples includes: Determine a first candidate active sample from the candidate samples according to a preset rule; The inactive sample is replaced by the first candidate active sample.

6. The method according to claim 1, characterized in that After the netizen attribute data set is updated using the candidate samples, the method further includes: Obtain the updated netizen attribute dataset; Obtaining active samples in the updated netizen attribute data set, and third user information corresponding to the active samples; the third user information includes third user attributes, advertisements corresponding to the third user information, advertisement source types corresponding to the third user information, and third user activity; Testing the updated netizen attribute data set according to the advertisement corresponding to the third user information and the third user attribute to obtain a test result; When the test result is unqualified, the netizen attribute data set is updated.

7. The method according to claim 6, characterized in that When the test result is unqualified, the netizen attribute data set is updated, including: Determining a second candidate active sample from the candidate samples according to a preset rule; The second candidate active sample is replaced with the inactive sample, and the netizen attribute dataset is updated.

8. A device for updating data, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method for data updating according to any one of claims 1 to 7 when executing the program instructions.

9. An electronic device, characterized in that: Comprising the device for data updating as claimed in claim 8.

Images