CN115293823A - User preference identification method based on advertisement click data analysis - Google Patents
User preference identification method based on advertisement click data analysis Download PDFInfo
- Publication number
- CN115293823A CN115293823A CN202211169761.0A CN202211169761A CN115293823A CN 115293823 A CN115293823 A CN 115293823A CN 202211169761 A CN202211169761 A CN 202211169761A CN 115293823 A CN115293823 A CN 115293823A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- user
- time
- sequence
- watching
- 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.)
- Granted
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
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/1805—Append-only file systems, e.g. using logs or journals to store data
- G06F16/1815—Journaling file systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data identification, in particular to a user preference identification method based on advertisement click data analysis, which comprises the following steps: acquiring the watching times and the watching duration of each advertisement by each user, acquiring the attention of the user when watching the advertisement each time, acquiring a watching sequence-attention curve, and acquiring the times of the demand of the user on advertisement commodities and the demand duration when the user demands each time; the method and the device have the advantages that the preference degree of the user to the advertisements of the same type within the required times is obtained, the preference degree curve is obtained, the final preference degree is obtained, the target advertisement type is determined according to the final preference degree, and the advertisements are pushed to the user.
Description
Technical Field
The invention relates to the technical field of data identification, in particular to a user preference identification method based on advertisement click data analysis.
Background
The advertisement is a technology derived from information propagation, the information propagation is mainly carried out through a billboard in the past, but the billboard placement occupies a large space and has certain blindness, and the placement is realized mainly according to the sales volume of commodities and a small-range manual investigation, so that the commodity advertisement information interested by customers cannot be timely and effectively placed, and the advertisement conversion rate is low.
With the continuous development of society, the advertisement is mainly realized by showing pictures and characters of the advertisement or dynamic pictures and videos on an electronic advertisement screen and a liquid crystal advertisement screen, but the technology is also put in a large amount, and no way is provided for timely response according to the favor of customers.
Until the arrival of artificial intelligence technology, advertising is mainly based on the number of clicks of an advertisement and user information, then the number of clicks and the user information are quantitatively classified, so that the user who prefers the advertisement is identified, and then the user is correspondingly pushed, however, due to the influence of time and the age increase of the user, the preference of the user for advertisement products is changed, especially for some consumed goods, the user needs to purchase the consumed goods for many times, such as tissues and laundry detergent, so the part of goods is only a short-term requirement for the user, certainly, the number of times of clicking the type of advertisement by the user when purchasing the user is higher, and therefore, the number of clicks is used for judging the advertisement of the goods preferred by the user, and the type of advertisement is pushed to the user, so that the advertisement pushed by the user is not accurate.
Therefore, it is desirable to provide a user preference identification method based on advertisement click data analysis to solve the above problems.
Disclosure of Invention
The invention provides a user preference identification method based on advertisement click data analysis, which aims to solve the problem that the advertisement of the existing user preference commodity is not accurately identified, so that the advertisement is not accurately pushed.
The invention discloses a user preference identification method based on advertisement click data analysis, which adopts the following technical scheme:
acquiring the watching times and duration of each advertisement of each user;
acquiring the attention degree of the corresponding advertisement watched by the user each time according to the watching time length of each advertisement watched by the user each time and the total time length of the advertisement; constructing a watching sequence-attention curve according to the attention of the user for watching the advertisement each time;
clustering the continuous watching times in the watching sequence-attention degree curve to obtain a plurality of watching sequence categories, and recording each watching sequence category as a required time;
acquiring the required time of the user for the advertisement each time according to the advertisement viewing time and the total advertisement time of the corresponding sequence number in each viewing sequence category, and acquiring the required time of the user for the same type of advertisement each time;
calculating the preference degree of the user to the type of advertisement within each demand time according to the demand duration of the user to the advertisement commodity each time, the demand times of the user to the advertisement and the attention degree of the user to watch the advertisement each time, and constructing a preference degree curve according to the preference degree;
and determining the final preference degree of each type of advertisement according to the abscissa value and the slope value corresponding to each point on the preference degree curve, taking the type advertisement corresponding to the highest preference degree in the final preference degrees corresponding to all types of advertisements by the user as a target advertisement type, and pushing the user according to the target advertisement type.
Preferably, a ratio of a viewing time length of each advertisement viewed by the user to a total time length of the advertisement is used as the attention degree of the corresponding advertisement viewed by the user.
Preferably, the step of obtaining the number of viewing times and the viewing duration of each advertisement by each user comprises:
acquiring advertisement log data of an advertisement push platform;
viewing times and viewing duration of each advertisement by each user according to the advertisement log data;
wherein the advertisement log data includes: the account name of the user, the starting time and the ending time of the advertisement watched by the user, the watching times of the advertisement watched by the user, the total duration of the advertisement watched by the user and the category of the advertisement.
Preferably, the step of constructing a viewing order-attention curve according to the attention of the user to view the advertisement each time includes:
acquiring a sequence according to the watching sequence of the same advertisement watched by the user each time;
acquiring an attention sequence of a user watching the same advertisement each time according to the time sequence;
and taking the sequence serial number in the sequence as an abscissa and the attention corresponding to the sequence serial number in the sequence as an ordinate to obtain an attention curve.
Preferably, the step of clustering time values corresponding to the number of consecutive views in the view order-attention degree curve to obtain a plurality of view order categories includes:
acquiring a coordinate point corresponding to the attention value larger than 0 on the time-attention curve;
and clustering continuous sequence numbers in sequence numbers corresponding to coordinate points with the attention value larger than 0 into a class by using a mean shift clustering method to obtain a sequence section, and taking each different sequence section as a watching sequence class.
Preferably, the step of obtaining the time length required by the user for the advertisement each time according to the advertisement viewing time length of the corresponding sequence number in each viewing sequence category and the total advertisement time length includes:
acquiring the maximum advertisement viewing time length in the advertisement viewing time lengths of all sequence numbers in each viewing sequence category;
the maximum advertisement viewing time period is taken as a demand time period at each demand of the user for the advertisement commodity.
Preferably, the formula for calculating the preference degree of the user for the type advertisement within each required number is as follows:
in the formula (I), the compound is shown in the specification,
representing a user
In the first place
Preference for this type of advertisement within a number of demand times;
Preferably, the step of constructing a preference degree curve according to the preference degree includes:
the preference degree of the type of advertisement in each required time length is taken as a vertical coordinate;
and obtaining a preference degree curve by taking the order of the advertisements of the same type corresponding to each required time length as an abscissa.
Preferably, the step of determining the final preference degree of the corresponding type of advertisement according to the abscissa value and the slope value corresponding to each point on the preference degree curve includes:
acquiring a time difference value from the starting time to the current time of each watching according to the horizontal coordinate value of each type of advertisement on the preference degree curve;
calculating a function value of an index with a constant e as a base and a time difference value as e;
acquiring the slope of a point corresponding to the demand sequence of each demand of each advertisement on the preference degree curve;
and calculating the final preference degree according to the slopes of all advertisement corresponding points of the type of advertisement and the index function value.
The method for identifying the user preference based on the advertisement click data analysis has the advantages that:
1. by acquiring the attention of the user to the advertisement, clustering the watching times based on the attention, and judging the short-term preference and long-term preference data of the user by clustering the watching times, the influence on the judgment of the preference degree of the user is avoided.
2. The preference degrees of different advertisements of the same type are accumulated to describe the change of the preference degrees of different advertisements of the same type by the user, namely, the increasing trend of the preference degrees is reflected by the slope of each point of a preference degree curve, so that the final preference degrees of the user to the advertisements of different types are determined according to the watching duration and in combination with the change of the preference degrees.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of an embodiment of a user preference identification method based on advertisement click data analysis according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of a user preference identification method based on advertisement click data analysis according to the present invention is shown in fig. 1, and the steps of the embodiment include:
s1, obtaining the watching times and the watching duration of each user to each advertisement from an advertisement push platform.
Specifically, advertisement log data are obtained through an advertisement data acquisition system of an advertisement push platform, wherein the advertisement log data comprise account names of users, starting time and ending time of watching advertisements by the users, and time of watching advertisements by the usersThe number of viewing times, the total duration of the advertisement, and the type of the advertisement, the embodiment uses
An advertisement and
the user is taken as the example, then set the first
A user watchesiAn advertisement time is recorded
And is currently the first
Total time length of each advertisement
。
S2, obtaining the attention of the corresponding advertisement watched by the user each time according to the watching time length of each advertisement watched by the user each time and the total time length of the advertisement; and constructing a watching sequence-attention curve according to the attention of the user for watching the advertisement each time.
Specifically, for a user, it takes more time to watch only if a product is interested, and certainly does not interest or watch for a long time, for example, when purchasing a product, the user searches for what the user wants to buy each time, however, the things the user wants to buy each time may be different, and in order to accurately push some products for the user, it is necessary to obtain the attention degree according to the attention time of the user to some types of products in each time.
Based on this, the present embodiment takes the viewing time as the attention degree for judging the interest degree of the user in the advertisement product, wherein when the attention degree is obtained, the present embodiment takes the ratio of the viewing time length of each advertisement viewed by the user each time to the total time length of the advertisement as the attention degree of the corresponding advertisement viewed by the user each timeIn which a
A user to
The attention of an individual advertisement may be expressed as:
in the formula (I), the compound is shown in the specification,
is shown as
A user to
The attention of each advertisement;
is shown as
The total duration of each advertisement;
is shown as
A user watches
A viewing duration of the individual advertisement;
note that the viewing duration
The larger the value of (A), the longer the viewing time, indicating that the user is more concerned with the commercial product of the advertisement, and therefore, the higher the value of (B)When the total duration of the advertisement is not changed, the longer the watching duration is, the greater the attention degree is; secondly, in this embodiment, the attention degree of the advertisement is calculated each time when the advertisement is watched once, that is, after the advertisement is watched once, the attention degree is calculated once, and if the advertisement is watched next time, the time is recalculated, and the attention degree of the advertisement is recalculated.
Specifically, in order to analyze the preference degree of the user for each type, the step of constructing the viewing sequence-attention degree curve according to the attention degree of the user viewing the advertisement each time in the embodiment includes: therefore, the sequence is obtained according to the watching sequence of the user watching the same advertisement each time; acquiring an attention sequence of a user watching the same advertisement each time according to the time sequence; and taking the sequence serial number in the sequence as an abscissa and the attention corresponding to the sequence serial number in the sequence as an ordinate to obtain an attention curve.
S3, clustering the continuous watching times in the watching sequence-attention curve to obtain a plurality of watching sequence categories, and recording each watching sequence category as a required time; acquiring the required time of the user for the advertisement each time according to the advertisement viewing time and the total advertisement time of the corresponding sequence number in each viewing sequence category, and acquiring the required time of the user for the same type of advertisement each time;
in the prior art, a common user preference identification method is to perform data statistics, then classify the advertisement according to quantitative indicators such as attention points and click times, and complete user preference identification, where a user has a higher long-term attention to an advertisement, which indicates that the user has a higher attention to the advertisement and a higher preference to the product displayed by the advertisement.
Specifically, the method includes clustering the continuous viewing times in a viewing sequence-attention degree curve to obtain a plurality of viewing sequence categories, and it should be noted that, when the attention degree of a user to an advertisement is relatively high in a short period, the distribution of the viewing times of the user to the advertisement in the attention degree curve is relatively concentrated, so that when analyzing the preference degree of the user to a single advertisement, the advertisement distribution on the attention degree curve needs to be performed first, if the distribution is more concentrated, the advertisement is only a short-period requirement for the user, and the short-period requirement may appear many times, because some commercial advertisements are consumables and need to be purchased many times, such as tissues, laundry detergents and the like, the demand times of the corresponding commodities of the user need to be analyzed are required to be higher, the demand times are higher, the short-time requirement common to the user is indicated, the preference degree of the user to the commercial advertisements is high, the demand times for the commercial advertisements are considered to be less short-time requirements of the current customer, the preference degree of the commercial advertisements is low, based on that the demand times of the continuous viewing sequence-attention degree curve are high, the clustering times of the continuous viewing sequence-attention degree curve are clustered, and the viewing sequence categories are obtained, wherein the clustering method includes a conventional method for obtaining a plurality of viewing sequence categories by clustering, wherein the viewing sequence categories, the method includes: acquiring a coordinate point corresponding to the attention value larger than 0 on the time-attention curve; and clustering continuous sequence numbers in sequence numbers corresponding to coordinate points with the attention value larger than 0 into a class by using a mean shift clustering method to obtain a sequence section, and taking each different sequence section as a watching sequence class.
Specifically, the step of obtaining the time length required by the user for the advertisement each time according to the advertisement viewing time length of the corresponding sequence number in each viewing sequence category and the total advertisement time length includes: acquiring the maximum advertisement watching time length in the advertisement watching time lengths of all sequence numbers in each watching sequence category; the maximum advertisement viewing time period is taken as a demand time period at each demand of the user for the advertisement commodity.
And S4, calculating the preference degree of the user to the advertisement of the type within each demand time according to the demand time of the user to the advertisement commodity each time, the demand time of the user to the advertisement and the attention degree of watching the advertisement each time, and constructing a preference degree curve according to the preference degree.
The lower the watching times of the advertisement by the user, the lower the preference degree of the advertisement and the type of advertisement by the user, the shorter the demand duration of the advertisement for each demand for goods is, the lower the preference is, and the lower the attention degree of the advertisement for each watching is, the lower the preference is, so that the watching times, the demand duration and the attention degree of the advertisement by the user are parameters influencing the preference degree of the advertisement by the user.
Based on this, the step of calculating the preference degree of the user for the type of advertisement within each demand time according to the demand time length of the user for the advertisement commodity each time, the demand time of the user for the advertisement commodity, and the attention degree of each advertisement watching includes: acquiring the watching times in the required time length corresponding to each required time; calculating the attention degree and value of the advertisement corresponding to all the watching times from the starting time of the user for watching the advertisement for the first time to the ending time of the advertisement watched for the last time corresponding to each required time; calculating the product of the required duration of each required time and the attention degree and the value corresponding to the required time from the starting time of the user for watching the advertisement for the first time to the ending time of watching the advertisement for the last time corresponding to each required time; summing the products of the demand duration corresponding to all the demand times and the attention sum value to obtain a target sum value; according to the target and value of all the same type advertisements watched by the user, the total required times from the starting time of the first advertisement watching by the user to the ending time of the last advertisement watching corresponding to each required time, calculating the preference degree of the user to the type advertisements in each required time, specifically, calculating the preference degree of the user to the type advertisements in each required time according to a formula:
in the formula (I), the compound is shown in the specification,
representing a user
In the first place
Preference for this type of advertisement within a number of demand times;
it should be noted that, the lower the number of times that the user views the advertisement is, the lower the preference degree of the user for the advertisement and the type of advertisement is, the shorter the demand duration is when the user demands the product in the advertisement each time, the lower the preference is, and the lower the attention degree is shown when the user watches the advertisement each time in each demand, the lower the preference is, and secondly, the preference degree calculated each time is the preference degree of the user for the type of advertisement in each demand, that is, the preference degree of the user for the type of advertisement in the second demand actually includes the variation value of the preference degree of the user for the type of advertisement in the first demand from the ending time of the last watching of the second demand to the starting time of the first watching of the advertisement, so that the preference degree of the user for the type of advertisement in the second demand actually indicates that the preference degree of the user for the type of advertisement in the first demand is higher, and the corresponding preference degree is higher when the demand is higher, that the value of the preference degree is not increased according to the order of the demand.
Specifically, a preference degree curve is constructed according to the preference degree, wherein the preference degree curve is constructed by taking the preference degree of the advertisement of the type in each demand duration as a vertical coordinate and taking the demand times of the advertisement of the same type corresponding to each demand duration as a horizontal coordinate.
And S5, determining the final preference degree of each type of advertisement according to the abscissa value and the slope value corresponding to each point on the preference degree curve, taking the type advertisement corresponding to the highest preference degree in the final preference degrees corresponding to all types of advertisements by the user as a target advertisement type, and pushing the user according to the target advertisement type.
Because the prior art completes the identification of the advertisement commodity preferred by the user through the high and low preference degree values, although the user may have a high preference degree for some commodity advertisements in a long time period, the preference degree is rather reduced along with the increase of the age of the user in the time shift until a new preference is formed, so the prior art is inaccurate in preference identification.
Based on this, through the steps S1 to S4 in this embodiment, preference degrees of different users for different types of advertisements within each demand number can be obtained, and therefore, the preference degree calculated within each demand number reflects a variation value of the preference degree calculated within the previous demand number of the user, and therefore, an increasing portion in the preference degree curve in the step S4 in this embodiment is obtained, that is, an abscissa value and a slope value corresponding to each point on the preference degree curve are obtained first, and then a final preference degree of each type of advertisement is determined according to the abscissa value and the slope value corresponding to each point, and the step of determining the final preference degree includes: acquiring a time difference value from the starting time to the current time of each watching according to the horizontal coordinate value of each type of advertisement on the preference degree curve; calculating a function value of an index with a constant e as a base and a time difference value as e; acquiring the slope of a point corresponding to the demand sequence of each demand of each advertisement on the preference degree curve; calculating the final preference degree according to the slopes of all advertisement corresponding points of the type of advertisements and the exponential function value, specifically, a formula for calculating the final preference degree of each type of advertisements is as follows:
in the formula (I), the compound is shown in the specification,
the first on the curve representing the degree of preference
The time difference from the starting time of each watching to the current time corresponding to each advertisement;
note that the time difference value
The larger, the longer the viewing time is indicated, the lower the impact on user preferences, and thus by an exponential function
Difference of time
Performing a negative correlation mapping so that the time difference is
The larger, the final preference level
The smaller the preference degree of the user to the type of advertisement is, because the change value of the preference degree of the type of advertisement in the current demand times to the preference degree of the type of advertisement in the previous demand times is represented between each point and each point on the preference degree curve, the slope represents the change degree, namely the larger the slope is, the faster the preference degree is increased, the slope of 0 represents that no new viewing record exists, the preference degree does not increase, and the slope value cannot be a negative value.
And then analyzing the final preference degrees corresponding to all types of advertisements watched by each user, taking the type advertisement corresponding to the highest preference degree in the final preference degrees corresponding to all types of advertisements by the user as a target advertisement type, and pushing the user according to the target advertisement type.
The invention relates to a user preference identification method based on advertisement click data analysis, which comprises the steps of obtaining the attention degree of a user to advertisements, clustering the watching times based on the attention degree, judging the short-term preference and long-term preference data of the user by clustering the watching times, thereby avoiding the influence on the judgment of the preference degree of the user, then accumulating the preference degrees of different advertisements of the same type to describe the change of the preference degree of the user to different advertisements of the same type, namely reflecting the increasing trend of the preference degree through the slope of each point of a preference degree curve, thereby determining the final preference degree of the user to different types of advertisements according to the watching duration and in combination with the change of the preference degree, therefore, the invention accurately judges the preference degree of the user by combining the attention degree, the watching duration and the change trend of the preference degree, thereby providing reference for the accurate pushing of the advertisements.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A user preference identification method based on advertisement click data analysis is characterized by comprising the following steps:
acquiring the watching times and the watching duration of each advertisement by each user;
acquiring the attention degree of the corresponding advertisement watched by the user each time according to the watching time length of each advertisement watched by the user each time and the total time length of the advertisement; constructing a watching sequence-attention curve according to the attention of the user for watching the advertisement each time;
clustering the continuous watching times in the watching sequence-attention curve to obtain a plurality of watching sequence categories, and marking each watching sequence category as a required time;
acquiring the required time length of the user for the advertisement each time according to the advertisement watching time length of the corresponding sequence number in each watching sequence category and the total advertisement time length, and acquiring the required time length of the user for the same type of advertisement each time;
calculating the preference degree of the user to the type of advertisement within each demand time according to the demand duration of the user to the advertisement commodity each time, the demand times of the user to the advertisement and the attention degree of the user to watch the advertisement each time, and constructing a preference degree curve according to the preference degree;
and determining the final preference degree of each type of advertisement according to the abscissa value and the slope value corresponding to each point on the preference degree curve, taking the type advertisement corresponding to the highest preference degree in the final preference degrees corresponding to all types of advertisements by the user as a target advertisement type, and pushing the user according to the target advertisement type.
2. The method of claim 1, wherein a ratio of a viewing time of each advertisement viewed by the user to a total time of the advertisement is used as the attention of the corresponding advertisement viewed by the user.
3. The method of claim 1, wherein the step of obtaining the number of times each user views each advertisement and the viewing duration from the advertisement push platform comprises:
acquiring advertisement log data of an advertisement push platform;
viewing times and viewing duration of each advertisement by each user according to the advertisement log data;
wherein the advertisement log data includes: the account name of the user, the starting time and the ending time of the advertisement watched by the user, the watching times of the advertisement watched by the user, the total duration of the advertisement watched by the user and the category of the advertisement.
4. The method of claim 1, wherein the step of constructing a viewing order-attention curve according to the attention of the user to view the advertisement each time comprises:
acquiring a sequence according to the watching sequence of the same advertisement watched by the user each time;
acquiring an attention sequence of a user watching the same advertisement each time according to the time sequence;
and taking the sequence serial number in the sequence as an abscissa and the attention corresponding to the sequence serial number in the sequence as an ordinate to obtain a viewing sequence-attention curve.
5. The method of claim 1, wherein the step of clustering time values corresponding to the number of consecutive views in the view order-attention curve to obtain a plurality of view order categories comprises:
acquiring a coordinate point corresponding to the attention value larger than 0 on the time-attention curve;
and clustering continuous sequence numbers in sequence numbers corresponding to coordinate points with the attention value larger than 0 into a class by using a mean shift clustering method to obtain a sequence section, and taking each different sequence section as a watching sequence class.
6. The method of claim 1, wherein the step of obtaining the time length required by the user for the advertisement each time according to the advertisement viewing time length and the total advertisement time length of the corresponding sequence number in each viewing sequence category comprises:
acquiring the maximum advertisement viewing time length in the advertisement viewing time lengths of all sequence numbers in each viewing sequence category;
the maximum advertisement viewing time period is taken as a demand time period at each demand of the user for the advertisement commodity.
7. The method of claim 1, wherein the formula for calculating the preference degree of the user for the type of advertisement within each required number of times is:
in the formula (I), the compound is shown in the specification,
representing a user
In the first place
Preference for this type of advertisement within a number of demand times;
8. The method of claim 1, wherein the step of constructing a preference degree curve according to the preference degree comprises:
the preference degree of the type of advertisement in each required time length is taken as a vertical coordinate;
and obtaining a preference degree curve by taking the demand times of the same type of advertisements corresponding to each demand duration as an abscissa.
9. The method of claim 1, wherein the step of determining the final preference degree of the corresponding type of advertisement according to the abscissa value and the slope value corresponding to each point on the preference degree curve comprises:
acquiring a time difference value from the starting time to the current time of each watching according to the horizontal coordinate value of each type of advertisement on the preference degree curve;
calculating a function value of an index with a constant e as a base and a time difference value as e;
obtaining the slope of a point corresponding to the demand sequence of each demand of each advertisement on the preference degree curve;
and calculating the final preference degree according to the slopes of all advertisement corresponding points of the type of advertisement and the index function value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211169761.0A CN115293823B (en) | 2022-09-26 | 2022-09-26 | User preference identification method based on advertisement click data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211169761.0A CN115293823B (en) | 2022-09-26 | 2022-09-26 | User preference identification method based on advertisement click data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115293823A true CN115293823A (en) | 2022-11-04 |
| CN115293823B CN115293823B (en) | 2023-01-03 |
Family
ID=83833885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211169761.0A Active CN115293823B (en) | 2022-09-26 | 2022-09-26 | User preference identification method based on advertisement click data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115293823B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436957A (en) * | 2023-12-20 | 2024-01-23 | 锦诚实业科技(深圳)有限公司 | Game software advertisement accurate delivery method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090158307A1 (en) * | 2007-12-14 | 2009-06-18 | Tatsuki Kashitani | Content processing apparatus, content processing method, program, and recording medium |
| WO2018023342A1 (en) * | 2016-08-01 | 2018-02-08 | 王晓光 | Method and system for counting number of viewing times in video advertisement |
| US20190132645A1 (en) * | 2017-10-30 | 2019-05-02 | Samsung Electronics Co., Ltd. | Electronic apparatus and controlling method thereof |
| CN109816421A (en) * | 2018-12-13 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Advertisement machine launches contents controlling method, device, computer equipment and storage medium |
| CN109840810A (en) * | 2019-03-19 | 2019-06-04 | 深圳创维－Rgb电子有限公司 | Data analyze method for pushing, device, background server and readable storage medium storing program for executing |
| CN111526419A (en) * | 2020-04-29 | 2020-08-11 | 四川虹美智能科技有限公司 | Vending machine advertisement recommendation method |
| CN112163909A (en) * | 2020-10-29 | 2021-01-01 | 杭州次元岛科技有限公司 | Advertisement delivery system based on big data |
| CN112837098A (en) * | 2021-02-04 | 2021-05-25 | 南京鼓佳玺电子科技有限公司 | Mobile internet advertisement intelligent pushing system based on big data analysis |
| CN112950256A (en) * | 2021-02-02 | 2021-06-11 | 广东便捷神科技股份有限公司 | Method and system for pushing customized advertisement form based on App |
-
2022
- 2022-09-26 CN CN202211169761.0A patent/CN115293823B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090158307A1 (en) * | 2007-12-14 | 2009-06-18 | Tatsuki Kashitani | Content processing apparatus, content processing method, program, and recording medium |
| WO2018023342A1 (en) * | 2016-08-01 | 2018-02-08 | 王晓光 | Method and system for counting number of viewing times in video advertisement |
| US20190132645A1 (en) * | 2017-10-30 | 2019-05-02 | Samsung Electronics Co., Ltd. | Electronic apparatus and controlling method thereof |
| CN109816421A (en) * | 2018-12-13 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Advertisement machine launches contents controlling method, device, computer equipment and storage medium |
| CN109840810A (en) * | 2019-03-19 | 2019-06-04 | 深圳创维－Rgb电子有限公司 | Data analyze method for pushing, device, background server and readable storage medium storing program for executing |
| CN111526419A (en) * | 2020-04-29 | 2020-08-11 | 四川虹美智能科技有限公司 | Vending machine advertisement recommendation method |
| CN112163909A (en) * | 2020-10-29 | 2021-01-01 | 杭州次元岛科技有限公司 | Advertisement delivery system based on big data |
| CN112950256A (en) * | 2021-02-02 | 2021-06-11 | 广东便捷神科技股份有限公司 | Method and system for pushing customized advertisement form based on App |
| CN112837098A (en) * | 2021-02-04 | 2021-05-25 | 南京鼓佳玺电子科技有限公司 | Mobile internet advertisement intelligent pushing system based on big data analysis |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436957A (en) * | 2023-12-20 | 2024-01-23 | 锦诚实业科技(深圳)有限公司 | Game software advertisement accurate delivery method |
| CN117436957B (en) * | 2023-12-20 | 2024-03-29 | 深圳市艾森互动科技有限公司 | Game software advertisement accurate delivery method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115293823B (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8103663B2 (en) | Advertising medium determination device and method therefor | |
| US9824367B2 (en) | Measuring effectiveness of marketing campaigns across multiple channels | |
| Gensch | Media factors: A review article | |
| US20060293976A1 (en) | System and method for managing online record store | |
| US20140351008A1 (en) | Calculating machine, prediction method, and prediction program | |
| JP4936636B2 (en) | Advertisement management program, advertisement management method, and advertisement management apparatus | |
| US20170345048A1 (en) | Attribution Marketing Recommendations | |
| KR101817042B1 (en) | System, method and computer-readable medium recorded with program for mediation of online video advertisement contract | |
| JP5303606B2 (en) | ADVERTISING SYSTEM, ADVERTISING SYSTEM CONTROL METHOD, PROGRAM, AND INFORMATION STORAGE MEDIUM | |
| JP2015097094A (en) | Learning system for using competing valuation models for real-time advertisement bidding | |
| US20140200992A1 (en) | Retail product lagged promotional effect prediction system | |
| WO2008079966A2 (en) | System and method for managing a plurality of advertising networks | |
| US8015185B2 (en) | Method and system for detecting search terms whose popularity increase rapidly | |
| CN115293823B (en) | User preference identification method based on advertisement click data analysis | |
| JP2012234271A (en) | Information processing device, information processing method, information processing program, and storage medium storing information processing program | |
| CN115496566B (en) | Regional specialty recommendation method and system based on big data | |
| CN112488756A (en) | System and method for automatically selecting advertisements according to time dimension | |
| US20150142782A1 (en) | Method for associating metadata with images | |
| US8051082B2 (en) | System and method for facilitating interactive selection of clusters and presentation of related datasets | |
| CN112488760A (en) | System and method for automatically selecting non-real-time advertisements according to time dimension | |
| JP6473194B2 (en) | Sales estimation system | |
| CN111932315A (en) | Data display method and device, electronic equipment and computer readable storage medium | |
| Anum et al. | Brand Credibility: Navigating the Pathway to Customer Satisfaction and Loyalty | |
| JP6711870B2 (en) | Exposure situation measuring system, method and program | |
| CN117057838A (en) | Customer big data screening, classifying and counting system based on B2C platform |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |