CN113592535B - Advertisement recommendation method and device, electronic equipment and storage medium - Google Patents
Advertisement recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113592535B CN113592535B CN202110745247.6A CN202110745247A CN113592535B CN 113592535 B CN113592535 B CN 113592535B CN 202110745247 A CN202110745247 A CN 202110745247A CN 113592535 B CN113592535 B CN 113592535B
- Authority
- CN
- China
- Prior art keywords
- user
- preset
- equipment
- behavior data
- historical behavior
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000006399 behavior Effects 0.000 claims description 117
- 230000000875 corresponding effect Effects 0.000 claims description 115
- 230000000694 effects Effects 0.000 claims description 92
- 238000013507 mapping Methods 0.000 claims description 36
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000014759 maintenance of location Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 12
- 210000000744 eyelid Anatomy 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000003066 decision tree Methods 0.000 description 4
- 210000004709 eyebrow Anatomy 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000003416 augmentation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses an advertisement recommendation method, an advertisement recommendation device, electronic equipment and a storage medium, wherein the advertisement recommendation method comprises the following steps: acquiring historical behavior data of a user; judging whether the historical behavior data of the user meets a first preset condition or not, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending is conducted in a second preset mode. According to the advertisement recommendation method provided by the embodiment of the disclosure, the old user can be accurately recommended, the advertisement meeting the preference of the new user can be accurately predicted, the accuracy of recommending the advertisement to the new user is greatly improved, and indexes such as the recommendation click rate and the retention time of the new user are improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an advertisement recommendation method, an advertisement recommendation device, an electronic device, and a storage medium.
Background
In the existing advertisement recommendation system, related recommendations are generally made through historical behavior characteristics of users, and the recommendations are products or contents which are more interesting to the users, so that clicking of the users is increased, and further value conversion of the users is improved.
The existing advertisement recommendation system often depends on behavior characteristic data of a user, such as user historical click data, user historical browsing data and user purchase data, and predicts according to the behavior characteristic data as key data predicted by a model, predicts to obtain recommended advertisements and pushes the recommended advertisements.
However, most of the behaviors of the current users are limited to historical behaviors, namely, the behaviors which are historically operated and browsed on the product, and the premise is that the user has installed the product and used the product, but the pulled new user has no historical behaviors, and the user who installs and uses the product for the first time cannot conduct relevant recommendation according to the characteristic data of the historical behaviors, so that compared with the historical user, the accuracy of advertisement recommendation to the new user is lower, and indexes such as recommendation click rate, retention time and the like of the new user are lower.
How to provide a new advertisement recommendation method is not only suitable for old users with enough historical behavior data to conduct accurate advertisement recommendation, but also suitable for new users without enough historical behavior data to conduct accurate advertisement recommendation, and is a technical problem to be solved.
Disclosure of Invention
Based on this, it is necessary to provide an advertisement recommendation method, an apparatus, an electronic device and a storage medium, which are aimed at the problems that the existing advertisement recommendation method has a limited application range and the advertisement recommendation accuracy is low for new users.
In a first aspect, an embodiment of the present application provides an advertisement recommendation method, where the method includes:
acquiring historical behavior data of a user;
judging whether the historical behavior data of the user meets a first preset condition or not, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending in a second preset mode.
In one embodiment, the first preset condition includes whether the number of the historical behavior data of the user is greater than or equal to a preset threshold, and if it is determined that the historical behavior data of the user meets the first preset condition, recommending in a first preset manner includes:
and if the number of the historical behavior data of the user is larger than or equal to the preset threshold, recommending according to the historical behavior data of the user and a first preset recommendation model.
In one embodiment, the first preset condition includes whether the number of the historical behavior data of the user is greater than or equal to the preset threshold, and if it is determined that the historical behavior data of the user does not meet the first preset condition, recommending in the second preset manner includes:
and if the number of the historical behavior data of the user is smaller than the preset threshold, determining a corresponding target category directory according to the user operation behavior, and recommending according to the target category directory and a second preset recommendation model to obtain a second recommendation advertisement.
In one embodiment, the determining the corresponding target category directory according to the user operation behavior includes:
acquiring the mapping relation between the equipment information of the user and the target activity corresponding to the user operation behavior;
inquiring a target activity number with the mapping relation with the equipment information according to the equipment information and the mapping relation;
acquiring association relations between a plurality of activities and corresponding category catalogues, wherein any one activity has a corresponding activity number;
and inquiring and determining a corresponding target category catalog according to the target activity number and the association relation.
In one embodiment, the obtaining the mapping relationship between the device information of the user and the target activity corresponding to the user operation behavior includes:
under the condition that an operating system corresponding to the user operation behavior is an android operating system, sequentially matching an international mobile equipment identification code of a clicking device corresponding to the user operation behavior, a corresponding anonymous equipment identifier and data used for identifying the identity of the android device step by step in a first preset database to generate first equipment information, wherein the first equipment information at least comprises a first mapping relation between the android equipment information of a user and the target activity corresponding to the user operation behavior; and acquiring the first mapping relation from the first equipment information.
In one embodiment, the obtaining the mapping relationship between the device information of the user and the target activity corresponding to the user operation behavior includes:
under the condition that the operating system corresponding to the user operation behavior is an apple operating system, matching data, which is used for identifying the advertising identifier of the apple equipment, of the clicking equipment corresponding to the user operation behavior in a second preset database, and generating second equipment information, wherein the second equipment information at least comprises second mapping relations between the apple equipment information of the user and the target activities corresponding to the user operation behavior; and acquiring the second mapping relation from the second equipment information.
In one embodiment, before the obtaining the association relationship between the plurality of activities and the corresponding category directory, the method further includes:
and creating the association relation between a plurality of activities and the corresponding category catalogs.
In one embodiment, each of the plurality of activities corresponds to a unique catalog; alternatively, each of the plurality of activities corresponds to the same category directory.
In one embodiment, the method further comprises:
receiving an operation log corresponding to the user operation behavior;
and attributing the operation log in real time in a third preset mode to generate the equipment information.
In an embodiment, the attributing the operation log in real time through a third preset manner, and generating the device information includes:
sequentially analyzing the identifiers in the configuration links in the operation log, and operating systems of the mobile terminals;
under the condition that the operating system is an android operating system, sequentially analyzing and matching the international mobile equipment identification code of the corresponding clicking equipment, the corresponding anonymous equipment identifier and the identifier for identifying the android equipment until the identifier is matched with any piece of data in the first preset database, and generating corresponding equipment information;
And under the condition that the operating system is an apple operating system, analyzing and matching an advertisement identifier of the clicking equipment for identifying the apple equipment until the advertisement identifier is matched with any piece of data in the second preset database, and generating corresponding equipment information.
In one embodiment, the recommending according to the target category directory and the second preset recommendation model includes:
acquiring the target category catalogue and geographic position information;
according to the target category catalogue and the geographic position information, recall related commodities to obtain corresponding related commodities;
estimating and scoring the click through rate of the related commodity according to the click through rate estimation model to obtain a corresponding related commodity score;
and sequencing the scores of the related commodities in sequence, and taking the related commodities meeting the second preset condition as recommended commodities so as to generate corresponding recommended advertisements according to the recommended commodities.
In one embodiment, the method further comprises:
reading the second preset condition, wherein the second preset condition comprises:
the ordering of the related commodities is within a preset ordering range, or the ordering of the related commodities is a preset ordering threshold.
In a second aspect, an embodiment of the present application provides an advertisement recommendation apparatus, including:
the acquisition module is used for acquiring historical behavior data of the user;
the recommendation module is used for judging whether the historical behavior data of the user acquired by the acquisition module meets a first preset condition, and if so, recommending in a first preset mode; if the historical behavior data of the user acquired by the acquisition module is judged not to meet the first preset condition, recommending in a second preset mode.
In a third aspect, embodiments of the present application provide an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor running the computer program to implement the method steps as described above.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the method steps described above.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
In the embodiment of the application, historical behavior data of a user is obtained; judging whether the historical behavior data of the user meets a first preset condition or not, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending is conducted in a second preset mode. According to the advertisement recommendation method provided by the embodiment of the disclosure, the old user can be accurately recommended, the advertisement conforming to the preference degree of the new user can be accurately predicted, the accuracy of recommending the advertisement to the new user is greatly improved, indexes such as the recommendation click rate and the retention time of the new user are improved, and it is to be understood that the general description and the following detailed description are only exemplary and explanatory and are not restrictive to the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow chart of an advertisement recommendation method provided in an embodiment of the present disclosure;
Fig. 2 is a flowchart of an advertisement recommendation method in a specific application scenario provided in an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of an advertisement recommendation device according to an embodiment of the present disclosure;
fig. 4 shows a schematic diagram of an electronic device connection structure according to an embodiment of the present disclosure.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.
It should be understood that the described embodiments are merely some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Alternative embodiments of the present disclosure are described in detail below with reference to the drawings.
As shown in fig. 1, an embodiment of the present disclosure provides an advertisement recommendation method, which specifically includes the following method steps:
s102: historical behavior data of a user is obtained.
In the embodiment of the present application, the historical behavior data of the user may be historical purchase data of the user, which is not exhaustive herein.
S104: judging whether the historical behavior data of the user meets a first preset condition or not, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending is conducted in a second preset mode.
In one possible implementation manner, the first preset condition includes whether the number of the historical behavior data of the user is greater than or equal to a preset threshold, and if it is determined that the historical behavior data of the user meets the first preset condition, recommending in the first preset manner includes the following steps:
if the number of the historical behavior data of the user is larger than or equal to the preset threshold, recommending according to the historical behavior data of the user and a first preset recommendation model to obtain a first recommended advertisement, and pushing the first recommended advertisement to first terminal equipment of the user.
In this embodiment of the present application, the preset threshold is not specifically limited, and conventional recommendation algorithms are adopted in the first preset recommendation model, which are not described herein.
In one possible implementation manner, the first preset condition includes whether the number of the historical behavior data of the user is greater than or equal to a preset threshold, and if it is determined that the historical behavior data of the user does not meet the first preset condition, recommending in the second preset manner includes the following steps:
if the number of the historical behavior data of the user is judged to be smaller than the preset threshold, determining a corresponding target category catalog according to the user operation behavior, recommending according to the target category catalog and a second preset recommendation model, obtaining a second recommendation advertisement, and pushing the second recommendation advertisement to second terminal equipment of the user.
In the embodiment of the present application, the preset threshold is not particularly limited.
In one possible implementation, the recommending according to the target category directory and the second preset recommending model includes the following steps:
obtaining target category catalogues and geographic position information;
according to the target category catalogue and the geographic position information, recall the related commodity to obtain a corresponding related commodity;
performing predictive scoring on the click through rate of the related commodity according to the click through rate predictive model to obtain a corresponding related commodity score;
and sequencing the scores of the related commodities in sequence, and taking the related commodities meeting the second preset condition as recommended commodities so as to generate corresponding recommended advertisements according to the recommended commodities.
In the embodiment of the application, the click through rate estimation model may adopt a GBDT (Gradient Boosting Decision Tree) algorithm, which is an iterative decision tree algorithm. A plurality of decision trees are constructed in the algorithm, and the conclusions of all the decision trees are accumulated to be used as a final answer.
Each time a model is built up in the gradient descent direction of the model loss function previously built up. The loss function was used to evaluate the performance of the model. The smaller the loss function, the better the performance. If the loss function can continue to drop, the performance of the model can continue to improve. The best way to keep the loss function down is to drop the loss function along the gradient direction.
The core of the GBDT algorithm is: each tree learns the residual error of the sum of all previous tree conclusions, and the residual error is the accumulated quantity of the true value obtained by adding the predicted value.
The GBDT-based algorithm is a conventional algorithm and will not be described in detail here.
After the basic data is obtained, the click through rate of the related commodity is estimated and scored according to a click through rate estimation model (a click through rate estimation model constructed by GBDT algorithm), so as to obtain a corresponding related commodity score, wherein the specific implementation process is as follows:
step b1: preparing data, configuring the data in the data set into a training set and a testing set, wherein in practical application, the data of the training set is often more than the data of the testing set, and the proportion of the training set and the testing set is not particularly limited;
step b2: loading a GBDT algorithm package training model in a machine learning library;
step b3: and carrying out model evaluation to obtain a model evaluation result, taking the model meeting the conditions as a final click through rate estimation model, and carrying out estimated scoring on the click through rate of the related commodity to obtain a corresponding related commodity score.
The model meeting the conditions is not particularly limited, and a model with the loss function of the estimated model in the model evaluation result approaching zero infinitely is used as a final click through rate estimated model.
In the embodiment of the present application, the preset conditions include: the ordering of the related commodities is within a preset ordering range, or the ordering of the related commodities is a preset ordering threshold.
In an actual application scenario, the preset condition may be configured to be in a larger range, for example, related commodities in a preset sorting range are recommended, so that multiple possibilities can be provided for the user, and the user has more choices. For example, the preset conditions are configured to: related commodities with scores sequentially ordered from high to low and in the first five preset orders can be used as recommended commodities.
For another example, to improve the accuracy of recommending advertisements, the preset condition may be configured to be a smaller range, for example, only relevant commodities meeting a preset ranking threshold are recommended. For example, the preset conditions are configured to: the related commodities with the scores sequentially ordered from high to low and the related commodities with the scores being 2 before a preset ordering threshold can be used as recommended commodities. The above is merely an example, and different preset conditions may be configured according to requirements of different application scenarios, so as to obtain recommended goods meeting requirements of new users, so that corresponding recommended advertisements are generated according to the recommended goods.
In a possible implementation manner, the advertisement recommendation method provided by the embodiment of the present disclosure further includes:
reading a second preset condition, wherein the second preset condition comprises the following steps: the ordering of the related commodities is within a preset ordering range, or the ordering of the related commodities is a preset ordering threshold.
In this embodiment of the present application, for the description of the second preset condition, reference is made to the description of the same or similar parts, which is not repeated here.
In one possible implementation, determining the corresponding target category directory according to the user operation behavior includes the following steps:
acquiring a mapping relation between equipment information of a user and a target activity corresponding to user operation behaviors;
inquiring a target activity number with a mapping relation with the equipment information according to the equipment information and the mapping relation;
acquiring association relations between a plurality of activities and corresponding category catalogues, wherein any one activity has a corresponding activity number;
in the embodiment of the application, each of the activities corresponds to a unique category directory; alternatively, each of the plurality of activities corresponds to the same category directory.
In an application scenario, if a plurality of activities respectively correspond to different category directories, the association relationship between the created plurality of activities (where each activity may be represented by its corresponding unique activity number) and the corresponding category directory may be specifically shown in the following table 1:
| Activity numbering | Category catalogue |
| 1 | Double eyelid |
| 2 | Eyebrow tattooing |
| 3 | Hump nose |
TABLE 1
According to the association relation shown in the above table 1, the category list corresponding to any activity number is accurately determined, and only the common category list, such as double eyelid, eyebrow tattooing and nose augmentation, may also have other category lists, such as face thinning, etc., and other category lists may be introduced according to the requirements of different application scenarios, which will not be described herein.
In another application scenario, if the plurality of activities respectively correspond to the same category directory, the association relationship between the created plurality of activities (where each activity may be represented by its corresponding unique activity number) and the corresponding category directory may be specifically shown in the following table 2:
| activity numbering | Category catalogue |
| 4 | Double eyelid |
| 5 | Double eyelid |
TABLE 2
In addition to each of the activities listed above corresponding to a different category list, it is also possible that the activities each correspond to the same category list.
According to the association relation shown in the above table 2, the category directory corresponding to any one activity number is accurately determined, and only the application scenes of two activity numbers corresponding to the double eyelid of the same category directory are listed, or a plurality of activity numbers corresponding to the application scenes of eyebrow tattooing of the same category directory, wherein each activity number corresponds to a eyebrow shape to be tattooed, and the above is only an example and is not repeated herein.
In a practical application scenario, different pictures or different videos may be used to correspond to different activities in order to distinguish between the different activities. For example, for table 1 above, an activity with activity number 1 is represented by picture a or video a of star a; similarly, an activity with activity number 2 is represented by picture B or video B of star B; similarly, an activity with activity number 3 is represented by picture C or video C of star C; in this way, different activities can be quickly distinguished according to the representative picture or video employed by any one activity.
For another example, for table 2 above, an activity with activity number 4 is represented by picture D or video D of star D, and features of the double eyelid represented by it, for example, the euro-major double eyelid, may be exhibited in picture D or video D; similarly, the activity with activity number 5 is represented by a picture E or a video E of the star E, and features of double eyelid represented by the activity may be shown in the picture E or the video E, for example, small double eyelid, which is not described herein.
And inquiring and determining the corresponding target category catalogue according to the target activity number and the association relation.
The user operation behavior is not particularly limited, and may be, for example, a click operation of the user, which is not exhaustive here. In this embodiment of the present application, according to the association relationship between the target activity number and the table 1 or table 2 as described above, the target category directory having the association relationship with the target activity number may be queried, for example, when determining that the target activity number is number 4, according to the association relationship stored in the database as shown in the table 2 as described above, it may be determined that the target category directory having the association relationship with the target activity number 4 is double eyelid; advertisement of double eyelid is recommended preferentially, so that accuracy of advertisement recommendation to new users can be improved greatly.
In one possible implementation manner, obtaining the mapping relationship between the device information of the user and the target activity corresponding to the user operation behavior includes the following steps:
under the condition that the operating system corresponding to the user operation behavior is an android operating system, sequentially matching the international mobile equipment identification code of the clicking equipment corresponding to the user operation behavior, the corresponding anonymous equipment identifier and the data used for identifying the identity of the android equipment step by step in a first preset database, and generating first equipment information, wherein the first equipment information at least comprises a first mapping relation between the android equipment information of the user and a target activity corresponding to the user operation behavior; and acquiring a first mapping relation from the first equipment information.
In one possible implementation manner, obtaining the mapping relationship between the device information of the user and the target activity corresponding to the user operation behavior includes the following steps:
under the condition that the operating system corresponding to the user operation behavior is an apple operating system, matching data, which is consistent with the advertisement identifier of the clicking equipment corresponding to the user operation behavior and is used for identifying the apple equipment, in a second preset database, and generating second equipment information, wherein the second equipment information at least comprises a second mapping relation between the apple equipment information of the user and a target activity corresponding to the user operation behavior; and obtaining a second mapping relation from the second equipment information.
In one possible implementation manner, before acquiring the association relationship between the plurality of activities and the corresponding category catalogue, the advertisement recommendation method provided by the embodiment of the disclosure further includes the following steps:
and creating association relations between the activities and the corresponding category catalogs.
In the embodiment of the application, each of the activities corresponds to a unique category directory; alternatively, each of the plurality of activities corresponds to the same category directory. The association relationship between each of the plurality of activities and the corresponding category directory is referred to the description of the same or similar parts above, and will not be described in detail herein.
In one possible implementation manner, the advertisement recommendation method provided by the embodiment of the present disclosure further includes the following steps:
receiving an operation log corresponding to the operation behavior of the user;
and attributing the operation log in real time in a third preset mode to generate equipment information.
In this embodiment of the present application, the preset manner may be to perform real-time attribution through a link system, and generate device information, where the device information specifically includes: mapping relation between long-type main key identification and activity number created for same equipment.
In the embodiment of the present application, the commodity recommendation system based on the link system used in the advertisement recommendation method may be a Recs system.
The workflow of the Recs system is specifically as follows:
step a1: the user logs in or registers with the system;
step a2: the user scores the commodity;
step a3: the scoring data is sent to a real-time recommendation task of the recommendation module through Kafka;
step a4: the Recs system performs real-time recommendation tasks and stores the data in the hbase's rating and userProduct tables. The real-time tasks include: real-time topN and user behavior based recommendation;
step a5: the real-time topN stores the calculation result in an onlineHot table of the hbase, and stores the calculation result in a table onlineRecommendations of the hbase based on user behavior recommendation;
step a6: the web side obtains the data required by the related module through inquiring hbase and displays the result.
In one possible implementation manner, the attribution is performed on the operation log in real time through a third preset manner, and the generating the device information includes the following steps:
sequentially analyzing the identification in the configuration link in the operation log and the mobile terminal operating system;
under the condition that the operating system is an android operating system, sequentially analyzing and matching the international mobile equipment identification code of the corresponding clicking equipment, the corresponding anonymous equipment identifier and the identifier for identifying the android equipment until the identifier is matched with any piece of data in a first preset database, and generating corresponding equipment information;
And under the condition that the operating system is an apple operating system, analyzing and matching an advertisement identifier of the clicking equipment for identifying the apple equipment until the advertisement identifier is matched with any piece of data in a second preset database, and generating corresponding equipment information.
In a specific application scenario, the logic adopted for specifically generating the mapping relationship between the device information and the activity number in real-time attribution is specifically as follows:
parsing an operation log (i.e., a click log) from a put media (e.g., https:// example. Com/t; if the information is the IOS system, further acquiring an idfa advertisement identifier, then matching the idfa with the idfa of the internal device information (for example, the device information table in the second preset database has such a piece of data that idfa=31a19 fec-73a5-4407-8f 98-3062ff 420009 and devId=10004), obtaining corresponding devId device information, and recording the cid activity number and the devId device information into a redis cache.
Fig. 2 is a schematic flow chart of an advertisement recommendation method in a specific application scenario according to an embodiment of the present disclosure.
As shown in fig. 2, when recommending according to the category list and the second preset recommendation model, if the number of recommended products is not enough, the city list may be used for supplementary recommendation.
Based on the description of the same parts of fig. 2 as those of fig. 1, reference is made to the description of the same or similar parts as previously described, and the description thereof will not be repeated here.
In the embodiment of the disclosure, historical behavior data of a user is obtained; judging whether the historical behavior data of the user meets a first preset condition or not, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending is conducted in a second preset mode. According to the advertisement recommendation method provided by the embodiment of the disclosure, the old user can be accurately recommended, the advertisement meeting the preference of the new user can be accurately predicted, the accuracy of recommending the advertisement to the new user is greatly improved, and indexes such as the recommendation click rate and the retention time of the new user are improved.
The actual test results show that the advertisement recommendation method provided by the embodiment of the disclosure improves the click rate and the retention time of the new user. And (3) data display: for the new user, the click rate of the new user is improved by 3.9%, the retention time of the new user is improved by 3%, and the effective acquisition rate is improved by 1.9%.
The following is an embodiment of an advertisement recommendation apparatus implemented by the present disclosure, and may be used to perform an embodiment of an advertisement recommendation method according to the present disclosure. For details not disclosed in the embodiment of the advertisement recommendation device in the embodiment of the present disclosure, please refer to the embodiment of the advertisement recommendation method in the embodiment of the present disclosure.
Referring to fig. 3, a schematic diagram of an advertisement recommendation device according to an exemplary embodiment of the present invention is shown. The advertisement recommendation device may be implemented as all or part of the terminal by software, hardware or a combination of both. The advertisement recommendation device includes an acquisition module 302 and a recommendation module 304.
Specifically, an obtaining module 302, configured to obtain historical behavior data of a user;
the recommending module 304 is configured to determine whether the historical behavior data of the user acquired by the acquiring module 302 meets a first preset condition, and if it is determined that the historical behavior data of the user acquired by the acquiring module 302 meets the first preset condition, recommend the historical behavior data in a first preset manner; if the historical behavior data of the user acquired by the acquisition module 302 does not meet the first preset condition, recommending is performed in a second preset mode.
Optionally, the first preset condition includes whether the number of historical behavior data of the user is greater than or equal to a preset threshold, and the recommendation module 304 is configured to:
if the number of the historical behavior data of the user is larger than or equal to the preset threshold, recommending is carried out according to the historical behavior data of the user and a first preset recommendation model, and a first recommendation advertisement is obtained.
Optionally, the first preset condition includes whether the number of historical behavior data of the user is greater than or equal to a preset threshold, and the recommendation module 304 is configured to:
if the number of the historical behavior data of the user is smaller than the preset threshold, determining a corresponding target category directory according to the user operation behavior, and recommending according to the target category directory and a second preset recommendation model to obtain a second recommendation advertisement.
Optionally, the recommendation module 304 is specifically configured to:
acquiring a mapping relation between equipment information of a user and a target activity corresponding to user operation behaviors;
inquiring a target activity number with a mapping relation with the equipment information according to the equipment information and the mapping relation;
acquiring association relations between a plurality of activities and corresponding category catalogues, wherein any one activity has a corresponding activity number;
and inquiring and determining the corresponding target category catalogue according to the target activity number and the association relation.
Optionally, the recommendation module 304 is specifically configured to:
under the condition that the operating system corresponding to the user operation behavior is an android operating system, sequentially matching the international mobile equipment identification code of the clicking equipment corresponding to the user operation behavior, the corresponding anonymous equipment identifier and the data used for identifying the identity of the android equipment step by step in a first preset database, and generating first equipment information, wherein the first equipment information at least comprises a first mapping relation between the android equipment information of the user and a target activity corresponding to the user operation behavior; and acquiring a first mapping relation from the first equipment information.
Optionally, the recommendation module 304 is specifically configured to:
under the condition that the operating system corresponding to the user operation behavior is an apple operating system, matching data, which is consistent with the advertisement identifier of the clicking equipment corresponding to the user operation behavior and is used for identifying the apple equipment, in a second preset database, and generating second equipment information, wherein the second equipment information at least comprises a second mapping relation between the apple equipment information of the user and a target activity corresponding to the user operation behavior; and obtaining a second mapping relation from the second equipment information.
Optionally, the apparatus further includes:
A creation module (not shown in fig. 3) for creating association relations between the plurality of activities and the corresponding category directory before acquiring association relations between the plurality of activities and the corresponding category directory.
Optionally, each of the plurality of activities corresponds to a unique catalog; alternatively, each of the plurality of activities corresponds to the same category directory.
Optionally, the apparatus further includes:
a receiving module (not shown in fig. 3) for receiving an operation log corresponding to the operation behavior of the user;
a generating module (not shown in fig. 3) configured to perform real-time attribution on the operation log received by the receiving module in a third preset manner, so as to generate device information.
Optionally, the generating module is specifically configured to:
sequentially analyzing the identification in the configuration link in the operation log and the mobile terminal operating system;
under the condition that the operating system is an android operating system, sequentially analyzing and matching the international mobile equipment identification code of the corresponding clicking equipment, the corresponding anonymous equipment identifier and the identifier for identifying the android equipment until the identifier is matched with any piece of data in a first preset database, and generating corresponding equipment information;
and under the condition that the operating system is an apple operating system, analyzing and matching an advertisement identifier of the clicking equipment for identifying the apple equipment until the advertisement identifier is matched with any piece of data in a second preset database, and generating corresponding equipment information.
Optionally, the recommendation module 304 is specifically configured to:
obtaining target category catalogues and geographic position information;
according to the target category catalogue and the geographic position information, recall the related commodity to obtain a corresponding related commodity;
performing predictive scoring on the click through rate of the related commodity according to the click through rate predictive model to obtain a corresponding related commodity score;
and sequencing the scores of the related commodities in sequence, and taking the related commodities meeting the second preset condition as recommended commodities so as to generate corresponding recommended advertisements according to the recommended commodities.
Optionally, the apparatus further includes:
a reading module (not shown in fig. 3) for reading the second preset condition, the second preset condition read by the reading module includes: the ordering of the related commodities is within a preset ordering range, or the ordering of the related commodities is a preset ordering threshold.
It should be noted that, when the advertisement recommendation apparatus provided in the foregoing embodiment performs the advertisement recommendation method, only the division of the foregoing functional units is used as an example, in practical application, the foregoing functional allocation may be performed by different functional units according to needs, that is, the internal structure of the device is divided into different functional units, so as to complete all or part of the functions described above. In addition, the advertisement recommendation device and the advertisement recommendation method provided in the foregoing embodiments belong to the same concept, and the implementation process is detailed in the advertisement recommendation method embodiment, which is not described herein again.
In the embodiment of the disclosure, the acquisition module is used for acquiring historical behavior data of a user; the recommendation module is used for judging whether the historical behavior data of the user meets a first preset condition, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending is conducted in a second preset mode. According to the advertisement recommendation device provided by the embodiment of the disclosure, the old user can be accurately recommended, the advertisement meeting the preference degree of the new user can be accurately predicted, the accuracy of recommending the advertisement to the new user is greatly improved, and indexes such as the recommendation click rate and the retention time of the new user are improved.
As shown in fig. 4, the present embodiment provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor running the computer program to implement the method steps as described above.
The disclosed embodiments provide a storage medium storing computer readable instructions having a computer program stored thereon, the program being executed by a processor to perform the method steps described above.
Referring now to fig. 4, a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure is shown. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 4, the electronic device may include a processing means (e.g., a central processor, a graphics processor, etc.) 401, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data required for the operation of the electronic device are also stored. The processing device 401, the ROM402, and the RAM403 are connected to each other by a bus 409. An input/output (I/O) interface 405 is also connected to bus 404.
In general, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, magnetic tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communications device 409, or from storage 408, or from ROM 402. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 401.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
Claims (13)
1. An advertisement recommendation method, the method comprising:
acquiring historical behavior data of a user;
judging whether the historical behavior data of the user meets a first preset condition or not, and if so, recommending in a first preset mode; if the historical behavior data of the user is judged not to meet the first preset condition, recommending in a second preset mode;
the first preset condition includes whether the number of the historical behavior data of the user is greater than or equal to a preset threshold, and if the historical behavior data of the user is judged not to meet the first preset condition, recommending in a second preset mode includes:
if the number of the historical behavior data of the user is smaller than the preset threshold, determining a corresponding target category list according to the user operation behavior, recommending according to the target category list and a second preset recommendation model, and obtaining a second recommendation advertisement, wherein the method comprises the following steps:
Acquiring the target category catalogue and geographic position information;
according to the target category catalogue and the geographic position information, recall related commodities to obtain corresponding related commodities;
estimating and scoring the click through rate of the related commodity according to the click through rate estimation model to obtain a corresponding related commodity score;
and sequencing the scores of the related commodities in sequence, and taking the related commodities meeting the second preset condition as recommended commodities so as to generate corresponding recommended advertisements according to the recommended commodities.
2. The method of claim 1, wherein if it is determined that the historical behavior data of the user meets the first preset condition, recommending in a first preset manner comprises:
and if the number of the historical behavior data of the user is larger than or equal to the preset threshold, recommending according to the historical behavior data of the user and a first preset recommendation model to obtain a first recommended advertisement.
3. The method of claim 1, wherein determining the corresponding target category directory based on user operational behavior comprises:
acquiring the mapping relation between the equipment information of the user and the target activity corresponding to the user operation behavior;
Inquiring a target activity number with the mapping relation with the equipment information according to the equipment information and the mapping relation;
acquiring association relations between a plurality of activities and corresponding category catalogues, wherein any one activity has a corresponding activity number;
and inquiring and determining a corresponding target category catalog according to the target activity number and the association relation.
4. The method of claim 3, wherein the obtaining the mapping relationship between the device information of the user and the target activity corresponding to the user operation behavior comprises:
under the condition that an operating system corresponding to the user operation behavior is an android operating system, sequentially matching an international mobile equipment identification code of a clicking device corresponding to the user operation behavior, a corresponding anonymous equipment identifier and data used for identifying the identity of the android device step by step in a first preset database to generate first equipment information, wherein the first equipment information at least comprises a first mapping relation between the android equipment information of a user and the target activity corresponding to the user operation behavior; and acquiring the first mapping relation from the first equipment information.
5. The method of claim 3, wherein the obtaining the mapping relationship between the device information of the user and the target activity corresponding to the user operation behavior comprises:
under the condition that the operating system corresponding to the user operation behavior is an apple operating system, matching data, which is used for identifying the advertising identifier of the apple equipment, of the clicking equipment corresponding to the user operation behavior in a second preset database, and generating second equipment information, wherein the second equipment information at least comprises second mapping relations between the apple equipment information of the user and the target activities corresponding to the user operation behavior; and acquiring the second mapping relation from the second equipment information.
6. The method of claim 3, wherein prior to the obtaining the association of the plurality of activities with the corresponding category directory, the method further comprises:
and creating the association relation between a plurality of activities and the corresponding category catalogs.
7. The method of claim 6, wherein the step of providing the first layer comprises,
each of the plurality of activities corresponds to a unique catalog; or,
each of the plurality of activities corresponds to the same category directory.
8. The method of claim 7, wherein the method further comprises:
receiving an operation log corresponding to the user operation behavior;
and attributing the operation log in real time in a third preset mode to generate the equipment information.
9. The method of claim 8, wherein the attributing the operation log in real time through a third preset manner, generating the device information comprises:
sequentially analyzing the identifiers in the configuration links in the operation log, and operating systems of the mobile terminals;
under the condition that the operating system is an android operating system, sequentially analyzing and matching the international mobile equipment identification code of the corresponding clicking equipment, the corresponding anonymous equipment identifier and the identification for identifying the android equipment until the identification is matched with any piece of data in a first preset database, and generating corresponding equipment information;
and under the condition that the operating system is an apple operating system, analyzing and matching an advertisement identifier of the clicking equipment for identifying the apple equipment until the advertisement identifier is matched with any piece of data in a second preset database, and generating corresponding equipment information.
10. The method according to claim 1, wherein the method further comprises:
Reading the second preset condition, wherein the second preset condition comprises:
the ordering of the related goods is within a preset ordering range, or,
the ordering of the related commodities is a preset ordering threshold.
11. An advertisement recommendation device, the device comprising:
the acquisition module is used for acquiring historical behavior data of the user;
the recommendation module is used for judging whether the historical behavior data of the user acquired by the acquisition module meets a first preset condition, and if so, recommending in a first preset mode; if the historical behavior data of the user acquired by the acquisition module is judged not to meet the first preset condition, recommending in a second preset mode;
the first preset condition includes whether the number of the historical behavior data of the user is greater than or equal to a preset threshold, and if the historical behavior data of the user is judged not to meet the first preset condition, recommending in a second preset mode includes:
if the number of the historical behavior data of the user is smaller than the preset threshold, determining a corresponding target category list according to the user operation behavior, recommending according to the target category list and a second preset recommendation model, and obtaining a second recommendation advertisement, wherein the method comprises the following steps:
Acquiring the target category catalogue and geographic position information;
according to the target category catalogue and the geographic position information, recall related commodities to obtain corresponding related commodities;
estimating and scoring the click through rate of the related commodity according to the click through rate estimation model to obtain a corresponding related commodity score;
and sequencing the scores of the related commodities in sequence, and taking the related commodities meeting the second preset condition as recommended commodities so as to generate corresponding recommended advertisements according to the recommended commodities.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor runs the computer program to implement the method of any one of claims 1-10.
13. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the method of any of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110745247.6A CN113592535B (en) | 2021-06-30 | 2021-06-30 | Advertisement recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110745247.6A CN113592535B (en) | 2021-06-30 | 2021-06-30 | Advertisement recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592535A CN113592535A (en) | 2021-11-02 |
| CN113592535B true CN113592535B (en) | 2024-04-16 |
Family
ID=78245743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110745247.6A Active CN113592535B (en) | 2021-06-30 | 2021-06-30 | Advertisement recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592535B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114675766A (en) * | 2022-02-25 | 2022-06-28 | 北京得间科技有限公司 | Electronic book processing method, server and storage medium |
| CN114936885B (en) * | 2022-07-21 | 2022-11-04 | 成都薯片科技有限公司 | Advertisement information matching pushing method, device, system, equipment and storage medium |
| CN116308545B (en) * | 2023-02-21 | 2023-09-29 | 欢聚时代文化传媒（北京）有限公司 | Advertisement online dynamic pushing method combining user behaviors |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629257A (en) * | 2012-02-29 | 2012-08-08 | 南京大学 | Commodity recommending method of e-commerce website based on keywords |
| CN104539742A (en) * | 2015-01-26 | 2015-04-22 | 北京奇艺世纪科技有限公司 | Information push method, information push device and information push system |
| CN105719163A (en) * | 2016-01-20 | 2016-06-29 | 四川长虹电器股份有限公司 | Commodity recommending method based on user browsing records |
| CN107343047A (en) * | 2017-07-06 | 2017-11-10 | 北京奇虎科技有限公司 | Application system and method |
| CN108880877A (en) * | 2018-06-07 | 2018-11-23 | 深圳市茁壮网络股份有限公司 | A kind of acquisition methods and device of log |
| CN109727088A (en) * | 2018-11-08 | 2019-05-07 | 深圳壹账通智能科技有限公司 | A kind of Method of Commodity Recommendation and device based on browser |
| CN110489644A (en) * | 2019-08-13 | 2019-11-22 | 腾讯科技（北京）有限公司 | Information-pushing method, device, computer readable storage medium and computer equipment |
| CN111737579A (en) * | 2020-06-28 | 2020-10-02 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN111737501A (en) * | 2020-06-22 | 2020-10-02 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN111741060A (en) * | 2020-05-08 | 2020-10-02 | 广州三七互娱科技有限公司 | Message pushing method and device, computer equipment and storage medium |
| CN111782943A (en) * | 2020-06-24 | 2020-10-16 | 中国平安财产保险股份有限公司 | Information recommendation method, device, equipment and medium based on historical data record |
| CN111899047A (en) * | 2020-07-14 | 2020-11-06 | 拉扎斯网络科技（上海）有限公司 | Resource recommendation method and device, computer equipment and computer-readable storage medium |
| WO2021004121A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Vehicle insurance recommendation method, apparatus and device, and computer-readable storage medium |
| CN112837106A (en) * | 2019-11-22 | 2021-05-25 | 上海哔哩哔哩科技有限公司 | Commodity recommendation method and device and computer equipment |
| CN112950325A (en) * | 2021-03-16 | 2021-06-11 | 山西大学 | Social behavior fused self-attention sequence recommendation method |
| CN113051183A (en) * | 2021-04-30 | 2021-06-29 | 中国工商银行股份有限公司 | Test data recommendation method and system, electronic device and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975472A (en) * | 2015-12-09 | 2016-09-28 | 乐视网信息技术（北京）股份有限公司 | Method and device for recommendation |
| CN107679211B (en) * | 2017-10-17 | 2021-12-28 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
| CN110674406A (en) * | 2019-09-29 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Recommendation method and device, electronic equipment and storage medium |
-
2021
- 2021-06-30 CN CN202110745247.6A patent/CN113592535B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629257A (en) * | 2012-02-29 | 2012-08-08 | 南京大学 | Commodity recommending method of e-commerce website based on keywords |
| CN104539742A (en) * | 2015-01-26 | 2015-04-22 | 北京奇艺世纪科技有限公司 | Information push method, information push device and information push system |
| CN105719163A (en) * | 2016-01-20 | 2016-06-29 | 四川长虹电器股份有限公司 | Commodity recommending method based on user browsing records |
| CN107343047A (en) * | 2017-07-06 | 2017-11-10 | 北京奇虎科技有限公司 | Application system and method |
| CN108880877A (en) * | 2018-06-07 | 2018-11-23 | 深圳市茁壮网络股份有限公司 | A kind of acquisition methods and device of log |
| CN109727088A (en) * | 2018-11-08 | 2019-05-07 | 深圳壹账通智能科技有限公司 | A kind of Method of Commodity Recommendation and device based on browser |
| WO2021004121A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Vehicle insurance recommendation method, apparatus and device, and computer-readable storage medium |
| CN110489644A (en) * | 2019-08-13 | 2019-11-22 | 腾讯科技（北京）有限公司 | Information-pushing method, device, computer readable storage medium and computer equipment |
| CN112837106A (en) * | 2019-11-22 | 2021-05-25 | 上海哔哩哔哩科技有限公司 | Commodity recommendation method and device and computer equipment |
| CN111741060A (en) * | 2020-05-08 | 2020-10-02 | 广州三七互娱科技有限公司 | Message pushing method and device, computer equipment and storage medium |
| CN111737501A (en) * | 2020-06-22 | 2020-10-02 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN111782943A (en) * | 2020-06-24 | 2020-10-16 | 中国平安财产保险股份有限公司 | Information recommendation method, device, equipment and medium based on historical data record |
| CN111737579A (en) * | 2020-06-28 | 2020-10-02 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN111899047A (en) * | 2020-07-14 | 2020-11-06 | 拉扎斯网络科技（上海）有限公司 | Resource recommendation method and device, computer equipment and computer-readable storage medium |
| CN112950325A (en) * | 2021-03-16 | 2021-06-11 | 山西大学 | Social behavior fused self-attention sequence recommendation method |
| CN113051183A (en) * | 2021-04-30 | 2021-06-29 | 中国工商银行股份有限公司 | Test data recommendation method and system, electronic device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张俊杰.《内容平台产品运营方案与实践》.机械工业出版社,2021,第225页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113592535A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902849B (en) | User behavior prediction method and device, and behavior prediction model training method and device | |
| CN113592535B (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
| US20170169341A1 (en) | Method for intelligent recommendation | |
| CN107577807B (en) | Method and device for pushing information | |
| CN107426328B (en) | Information pushing method and device | |
| CN110020162B (en) | User identification method and device | |
| CN108491540B (en) | Text information pushing method and device and intelligent terminal | |
| CN109862100B (en) | Method and device for pushing information | |
| CN110619078B (en) | Method and device for pushing information | |
| CN111104599B (en) | Method and device for outputting information | |
| CN112836128A (en) | Information recommendation method, device, equipment and storage medium | |
| CN111897950A (en) | Method and apparatus for generating information | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN109377284B (en) | Method and electronic equipment for pushing information | |
| CN109978594B (en) | Order processing method, device and medium | |
| CN113032676A (en) | Recommendation method and system based on micro-feedback | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| CN111026849A (en) | Data processing method and device | |
| CN113360773B (en) | Recommendation method and device, storage medium and electronic equipment | |
| CN111125502A (en) | Method and apparatus for generating information | |
| CN111475722B (en) | Method and apparatus for transmitting information | |
| CN111310016B (en) | Label mining method, device, server and storage medium | |
| CN113792952A (en) | Method and apparatus for generating a model | |
| CN111125501B (en) | Method and device for processing information | |
| CN113742564A (en) | Target resource pushing method and device |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240511 Address after: 100102 room 1201, 12 / F, building 8, yard 34, Chuangyuan Road, Chaoyang District, Beijing Patentee after: Beijing new oxygen world wide Technology Consulting Co.,Ltd. Country or region after: China Address before: 100102 room 901, 9 / F, room 1001, 10 / F, building 8, yard 34, Chuangyuan Road, Chaoyang District, Beijing Patentee before: Beijing New Oxygen Technology Co.,Ltd. Country or region before: China |