CN111882370A - Advertisement recommendation method and device and electronic equipment - Google Patents
Advertisement recommendation method and device and electronic equipment Download PDFInfo
- Publication number
- CN111882370A CN111882370A CN202011033383.4A CN202011033383A CN111882370A CN 111882370 A CN111882370 A CN 111882370A CN 202011033383 A CN202011033383 A CN 202011033383A CN 111882370 A CN111882370 A CN 111882370A
- Authority
- CN
- China
- Prior art keywords
- user
- advertisement
- social media
- keyword
- keywords
- 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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Abstract
The invention provides an advertisement recommendation method, an advertisement recommendation device and electronic equipment, wherein the method comprises the following steps: the method comprises the steps of determining a user interest keyword from a user interest model, determining the determined user interest keyword as a to-be-processed keyword of a social media user corresponding to a user identifier, inquiring an advertisement identifier matched with the to-be-processed keyword from an advertisement classification model, pushing an advertisement corresponding to the advertisement identifier to the social media user corresponding to the user identifier, and compared with the mode that a social media platform pushes all advertisements to the user to watch in the related technology, inquiring the advertisement matched with the user interest keyword, namely inquiring the advertisement which the user is interested in, and then pushing the inquired advertisement which the user is interested in to the user, so that the social media user can watch the advertisement which the user is interested in, and the experience of the social media user in using the social media is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an advertisement recommendation method and device and electronic equipment.
Background
Currently, browsing information on a social media platform and interacting with friends on the social media platform have become a daily habit for people. The social media platform may recommend advertisements to people when they use the social media platform.
The social media platform pushes the advertisement to all social media users, so that the social media users can see the advertisement pushed by the social media platform after being online.
Social media users see a large number of advertisements on the social media platform that are not of interest to the social media users, reducing the experience of the social media users.
Disclosure of Invention
In order to solve the above problem, embodiments of the present invention provide an advertisement recommendation method, an advertisement recommendation device, and an electronic device.
In a first aspect, an embodiment of the present invention provides an advertisement recommendation method, including:
obtaining a user interest model and an advertisement classification model, wherein the user interest model comprises: the user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight; the advertisement classification model comprises: the corresponding relation among the advertisement type, the advertisement identification and the advertisement key word;
determining user interest keywords of which the keyword weights are greater than or equal to a keyword threshold value in the user interest keywords of the social media users corresponding to the user identifications from the user interest model, and determining the determined user interest keywords of which the keyword weights are greater than or equal to the keyword threshold value as to-be-processed keywords of the social media users corresponding to the user identifications;
and inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, and pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification.
In a second aspect, an embodiment of the present invention further provides an advertisement recommendation apparatus, including:
the obtaining module is used for obtaining a user interest model and an advertisement classification model, wherein the user interest model comprises: the user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight; the advertisement classification model comprises: the corresponding relation among the advertisement type, the advertisement identification and the advertisement key word;
the determining module is used for determining user interest keywords of which the keyword weights are more than or equal to a keyword threshold value from the user interest keywords of the social media users corresponding to the user identifications in the user interest model, and determining the determined user interest keywords of which the keyword weights are more than or equal to the keyword threshold value as the keywords to be processed of the social media users corresponding to the user identifications;
and the pushing module is used for inquiring the advertisement identification matched with the keyword to be processed from the advertisement classification model and pushing the advertisement corresponding to the advertisement identification to the social media user corresponding to the user identification.
In a third aspect, the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the method in the first aspect.
In a fourth aspect, embodiments of the present invention also provide an electronic device, which includes a memory, a processor, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor to perform the steps of the method according to the first aspect.
In the solutions provided in the foregoing first aspect to the fourth aspect of the embodiments of the present invention, by determining the user interest keyword from the user interest model, and determining the determined user interest keywords as the keywords to be processed of the social media user corresponding to the user identification, then inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification, compared with the mode that the social media platform pushes all the advertisements to the user for watching in the related art, the advertisements matched with the interest keywords of the user can be inquired out, that is, the advertisements which are relatively interested by the user are inquired, and then the inquired advertisements which are interested by the user are pushed to the user, the social media users can watch advertisements which are interested by the users, and experience of the social media users in using the social media is improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
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 flowchart illustrating an advertisement recommendation method according to embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram illustrating an advertisement recommendation apparatus according to embodiment 2 of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device provided in embodiment 3 of the present invention.
Detailed Description
Currently, browsing information on a social media platform and interacting with friends on the social media platform have become a daily habit for people. The social media platform may recommend advertisements to people when they use the social media platform. The social media platform pushes the advertisement to all social media users, so that the social media users can see the advertisement pushed by the social media platform after being online. Social media users see a large number of advertisements on the social media platform that are not of interest to the social media users, reducing the experience of the social media users.
Based on this, the embodiment provides an advertisement recommendation method, an advertisement recommendation device and electronic equipment, which determine a user interest keyword from a user interest model, determine the determined user interest keyword as a to-be-processed keyword of a social media user corresponding to a user identifier, then query an advertisement identifier matched with the to-be-processed keyword from an advertisement classification model, and push an advertisement corresponding to the advertisement identifier to a social media user corresponding to the user identifier, so that advertisements in which users are interested in comparison can be queried, and then push the queried advertisement in which the users are interested to the user, so that the social media user can view the advertisement in which the user is interested, and experience of the social media user in using social media is improved.
The advertisement recommendation method provided by the embodiment uses the user interest model to determine the user interest keywords interested by the social media user.
In order to use the user interest model in the advertisement recommendation method, the user interest model needs to be set in advance in a server that executes the advertisement recommendation method.
The advertisement recommendation method provided in this embodiment adopts a vector space model to represent a user interest model of a user, and when the user interest model is established based on the vector space model, the following steps may be performed:
1. and (6) collecting data. The collected data specifically includes: social media information published by social media users and behavior information of the social media users. The behavior information of the social media user includes forwarding, praise, and comment of the user.
2. Chinese word segmentation. And dividing the collected data into user interest keywords by using a word segmentation tool. Optionally, the server may use a word segmentation tool such as the ICTCLAS chinese word segmentation system to perform word segmentation and part-of-speech tagging on the collected data, so as to obtain the user interest keywords.
3. And denoising the data. And processing the noise data contained in the user interest keywords processed by the word segmentation tool, and removing the noise data in the user interest keywords.
4. Feature selection and weight calculation. And providing a TF and TF-IDF combined method based on the part of speech of the user interest keyword to score the user interest keyword, wherein for nouns in the user interest keyword, a TF-IDF method is adopted for weight calculation, and other parts of speech words are directly adopted for weight calculation, so that the keyword weights corresponding to different user interest keywords are obtained. The specific process of calculating the weight of the keyword is not described herein again.
After obtaining the keyword weights corresponding to different user interest keywords of the same social media user, the server distributes a user identifier to the social media user, so that the user identifier of the social media user and the corresponding relation between the user interest keywords and the keyword weights are generated, and a user interest model of the social media user is obtained.
And then storing the generated user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight into a user interest model database.
The user interest model database is stored in the server.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
Example 1
In the advertisement recommendation method provided by this embodiment, the execution subject is a server.
The server may use any computing device capable of performing advertisement recommendation on social media users in the prior art, and details are not repeated here.
Referring to a flowchart of an advertisement recommendation method shown in fig. 1, the present embodiment provides an advertisement recommendation method, including the following specific steps:
The advertisement classification model is pre-stored in the server and is obtained through a K-nearest neighbor algorithm.
And 102, determining user interest keywords of which the keyword weights are more than or equal to a keyword threshold value from the user interest keywords of the social media users corresponding to the user identifications in the user interest model, and determining the determined user interest keywords of which the keyword weights are more than or equal to the keyword threshold value as the keywords to be processed of the social media users corresponding to the user identifications.
In step 102, the server may query the user interest model of the social media user from the user interest model database according to the user identifier of the social media user who needs to perform advertisement recommendation, that is, query the corresponding relationship between the user interest keyword and the keyword weight of the social media user.
And the keyword threshold value is stored in the server.
The server compares the keyword weight of each user interest keyword with the size of the keyword threshold value respectively, and determines the user interest keywords with the keyword weight more than or equal to the keyword threshold value as the keywords to be processed of the social media user corresponding to the user identification.
And 104, inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, and pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification.
In step 104, the server may query, by using the keyword to be processed, an advertisement identifier corresponding to an advertisement keyword that is the same as the keyword to be processed from the advertisement classification model, as the advertisement identifier that is matched with the keyword to be processed and is queried from the advertisement classification model.
After the advertisement corresponding to the advertisement identification is pushed to the social media user corresponding to the user identification, the advertisement type of the advertisement corresponding to the advertisement identification can be determined according to the corresponding relation among the advertisement type, the advertisement identification and the advertisement keyword recorded in the advertisement classification model, and the corresponding relation between the advertisement type of the advertisement pushed to the social media user corresponding to the user identification and the advertisement type weight is inquired from the corresponding relation between the advertisement type and the advertisement type weight stored in the server and stored.
When the social media user corresponding to the user identifier operates the pushed advertisement, the advertisement recommendation method provided by this embodiment may further perform the following steps (1) to (6):
(1) acquiring an operation type used when the social media user corresponding to the user identification operates the pushed advertisement, and acquiring an operation evaluation value matched with the operation type;
(2) generating a corresponding relation between the advertisement identification of the advertisement operated by the social media user corresponding to the user identification and the operation evaluation value;
(3) when it is determined that the social media user corresponding to the user identifier has the unoperated advertisement according to the generated corresponding relationship, calculating the similarity between the unoperated advertisement of the social media user corresponding to the user identifier and the operated advertisement of the social media user corresponding to the user identifier;
(4) calculating to obtain a predictive evaluation value of the advertisement which is not operated by the social media user corresponding to the user identifier by using the operation evaluation value of the advertisement which is operated by the social media user corresponding to the user identifier and the calculated similarity;
(5) taking the operation evaluation value and the prediction evaluation value as advertisement recommendation coefficients;
(6) and determining the advertisements respectively corresponding to the larger advertisement recommendation coefficients in the advertisement recommendation coefficients as the advertisements recommended again to the social media users corresponding to the user identifications, and pushing the advertisements respectively corresponding to the larger advertisement recommendation coefficients to the social media users corresponding to the user identifications.
In step (1) above, the operation types include, but are not limited to: forward, comment, and like.
The operation evaluation value that matches the operation type can be obtained from the correspondence relationship between the operation type and the operation evaluation value.
And the corresponding relation between the operation type and the operation evaluation value is set in the server.
In the step (3), the server may determine whether there is an advertisement that has not been operated by the social media user corresponding to the user identifier according to the advertisement identifier of the advertisement that has been operated by the social media user and the advertisement identifier of the advertisement that is pushed to the social media user, which are recorded in the generated correspondence.
In an embodiment, the server calculates, by using a person similarity coefficient formula, a similarity between an advertisement that is not operated by the social media user corresponding to the user identifier and an advertisement that is operated by the social media user corresponding to the user identifier, where a specific process is the prior art and is not described herein again.
Here, the similarity is a numerical value between [0, 1 ].
In the step (4), the predictive evaluation value of the advertisement which is not operated by the social media user corresponding to the user identifier is calculated by the following formula:
predictive evaluation value = operational evaluation value × similarity.
Through the content of the steps (1) to (6), the predictive evaluation value of the advertisement which is not operated by the user can be predicted according to the advertisement which is operated by the social media user, so that the advertisement pushed to the social media user can be dynamically adjusted, and the accuracy of advertisement pushing is further improved.
The advertisement recommendation method provided in this embodiment may also adjust the weight value corresponding to the advertisement type periodically, including the following steps (1) to (7):
(1) when the time length from a first time point of last adjustment of the advertisement type weight reaches a first preset time length, determining the advertisement type of the advertisement operated by the social media user corresponding to the user identification in the time length from the first time point to the current time point, and counting a first number of the advertisement types of the advertisement operated by the social media user corresponding to the user identification;
(2) acquiring the corresponding relation between the advertisement type and the advertisement type weight of the pushed advertisement of the social media user corresponding to the user identification;
(3) determining the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identifier belongs based on the corresponding relation between the advertisement type and the advertisement type weight and the advertisement type to which the advertisement which is operated by the social media user and corresponds to the user identifier belongs, and counting a second number of the advertisement types to which the advertisement which is not operated by the social media user and corresponds to the user identifier belongs;
(4) reducing the advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification belongs;
(5) based on the second quantity, calculating to obtain a weight decrement accumulated value of advertisement type weights corresponding to advertisement types to which the advertisements which are not operated by the social media user and correspond to the user identification belong;
(6) calculating to obtain a weight increment value of the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs through the following formula:
weight increment value = weight decrement cumulative value/first number;
(7) and performing increment operation on the advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs by using the calculated weight increment value to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs.
In the step (1), the first preset duration is set in the server.
The server may determine, according to the advertisement identifier recorded in the correspondence between the advertisement identifier of the advertisement operated by the social media user and the operation evaluation value corresponding to the user identifier, an advertisement type to which the advertisement operated by the social media user corresponding to the user identifier belongs from the correspondence between the advertisement type, the advertisement identifier, and the advertisement keyword included in the advertisement classification model.
In the step (2), the correspondence between the advertisement type and the advertisement type weight to which the pushed advertisement belongs to the social media user corresponding to the user identifier is stored in the server in advance.
In the step (3), the advertisement type to which the advertisement operated by the social media user corresponding to the user identifier belongs may be determined according to the determined advertisement type to which the advertisement operated by the social media user corresponding to the user identifier belongs, and the correspondence between the advertisement type to which the advertisement belongs and the advertisement type weight that has been pushed to the social media user corresponding to the user identifier, and the advertisement type to which the advertisement not operated by the social media user corresponding to the user identifier belongs may be determined.
In the step (4), a decrement unit weight value is used to decrement the advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identifier belongs, so as to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identifier belongs.
And the decrement unit weight value is cached in the server in advance.
In the step (5), a weight decrement cumulative value of an advertisement type weight corresponding to an advertisement type to which an advertisement which is not operated by the social media user and corresponds to the user identifier belongs is calculated by the following formula:
the weight reduction integrated value = a second number × (reduction unit weight).
In the above steps (1) to (7), the weight of the advertisement type pushed to the social media user can be adjusted according to the advertisement type operated by the social media user, so that the purpose of dynamically adjusting the advertisement type pushed to the social media user is achieved according to the user feedback, and the accuracy of advertisement pushing is improved.
The advertisement recommendation method provided in this embodiment may also periodically adjust the user interest model of the social media user, and in order to periodically adjust the user interest model of the social media user, the following steps (1) to (4) may be performed:
(1) when the time length from a second time point of last updating of the user interest model reaches a second preset time length, obtaining newly published social information of the user corresponding to the user identification of the social media in the time length from the second time point to the current time point, and processing the social information to obtain keywords of the social information and keyword weights of the keywords of the social information;
(2) obtaining a user interest model of the social media user corresponding to the user identification;
(3) when a user interest keyword which is the same as the keyword of the social information can be inquired from a user interest model of a user of the social media corresponding to the user identification, updating the keyword weight of the user interest keyword which is the same as the keyword of the social information in the user interest model through the following formula:
wherein the content of the first and second substances,
representing user interest keywords in the user interest model which are the same as the keywords of the social information;
representing an update coefficient;
representing a current point in time;
representing a second preset time length;
representing the current keyword weight of the user interest keywords which are the same as the keywords of the social information in the user interest model;
a keyword weight representing a keyword of social information;
a keyword weight representing a user interest keyword in the updated user interest model that is the same as the keyword of the social information;
(4) when the keywords which are the same as the keywords of the social information cannot be inquired from the user interest model of the social media user corresponding to the user identification, generating the corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information, and storing the generated corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information as the corresponding relation between the user interest keywords and the keyword weights into the user interest model of the social media user corresponding to the user identification.
In the step (1), the second preset duration is preset in the server.
The social information may be, but is not limited to: dynamic information and advertising information sent by social media users.
The process of processing the social information to obtain the keywords of the social information and the keyword weights of the keywords of the social information is the prior art, and is not repeated here.
Through the contents of the steps (1) to (4), the user interest model of the social media user can be updated according to the social information newly issued by the social media user, so that the corresponding relation between the user interest keywords and the keyword weights of the social media user can be adjusted in real time, and advertisements in which the social media user is interested are pushed to the social media user more accurately.
In summary, the advertisement recommendation method provided in this embodiment determines the user interest keywords from the user interest model, and determining the determined user interest keywords as the keywords to be processed of the social media user corresponding to the user identification, then inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification, compared with the mode that the social media platform pushes all the advertisements to the user for watching in the related art, the advertisements matched with the interest keywords of the user can be inquired out, that is, the advertisements which are relatively interested by the user are inquired, and then the inquired advertisements which are interested by the user are pushed to the user, the social media users can watch advertisements which are interested by the users, and experience of the social media users in using the social media is improved.
Example 2
An advertisement recommendation apparatus provided in this embodiment is configured to execute the advertisement recommendation method provided in embodiment 1.
Referring to a schematic structural diagram of an advertisement recommendation apparatus shown in fig. 2, an advertisement recommendation apparatus provided in this embodiment includes:
an obtaining module 200, configured to obtain a user interest model and an advertisement classification model, where the user interest model includes: the user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight; the advertisement classification model comprises: the corresponding relation among the advertisement type, the advertisement identification and the advertisement key word;
a determining module 202, configured to determine, from the user interest model, a user interest keyword of which a keyword weight is greater than or equal to a keyword threshold value among user interest keywords of the social media users corresponding to the user identifier, and determine the user interest keyword of which the determined keyword weight is greater than or equal to the keyword threshold value as a to-be-processed keyword of the social media user corresponding to the user identifier;
and the pushing module 204 is configured to query an advertisement identifier matching the keyword to be processed from the advertisement classification model, and push an advertisement corresponding to the advertisement identifier to a social media user corresponding to the user identifier.
Further, the advertisement recommendation apparatus provided in this embodiment further includes:
the second acquisition module is used for acquiring an operation type used when the social media user corresponding to the user identifier operates the pushed advertisement, and acquiring an operation evaluation value matched with the operation type;
the generating module is used for generating the corresponding relation between the advertisement identification and the operation evaluation value of the advertisement operated by the social media user corresponding to the user identification;
the first calculation module is used for calculating the similarity between the advertisement which is not operated by the social media user corresponding to the user identifier and the advertisement which is operated by the social media user corresponding to the user identifier when the social media user corresponding to the user identifier has the advertisement which is not operated according to the corresponding relation;
the second calculation module is used for calculating to obtain a predictive evaluation value of the advertisement which is not operated by the social media user corresponding to the user identifier by utilizing the operation evaluation value of the advertisement which is operated by the social media user corresponding to the user identifier and the calculated similarity;
a processing module, configured to use the operation evaluation value and the predictive evaluation value as advertisement recommendation coefficients;
and the secondary pushing module is used for determining the advertisements corresponding to the larger advertisement recommendation coefficients in the advertisement recommendation coefficients as the advertisements recommended again to the social media users corresponding to the user identifications, and pushing the advertisements corresponding to the larger advertisement recommendation coefficients to the social media users corresponding to the user identifications.
Further, the advertisement recommendation apparatus provided in this embodiment further includes:
the second processing module is used for determining the advertisement type of the advertisement operated by the social media user corresponding to the user identifier in the time length from the first time point of last adjustment of the advertisement type weight to a first preset time length, and counting a first number of the advertisement types of the advertisement operated by the social media user corresponding to the user identifier;
the third acquisition module is used for acquiring the corresponding relation between the advertisement type and the advertisement type weight of the pushed advertisement of the social media user corresponding to the user identification;
a third processing module, configured to determine, based on the correspondence between the advertisement type and the advertisement type weight and the advertisement type to which the advertisement operated by the social media user corresponding to the user identifier belongs, an advertisement type to which the advertisement not operated by the social media user corresponding to the user identifier belongs, and count a second number of advertisement types to which the advertisement not operated by the social media user corresponding to the user identifier belongs;
the third calculation module is used for performing decrement operation on the advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification belongs;
a fourth calculating module, configured to calculate, based on the second number, a weight decrement cumulative value of an advertisement type weight corresponding to an advertisement type to which an advertisement that is not operated by the social media user and corresponds to the user identifier belongs;
a fifth calculating module, configured to calculate, by using the following formula, a weight increment value of an advertisement type to which an advertisement operated by a social media user corresponding to the user identifier belongs:
weight increment value = weight decrement cumulative value/first number;
and the adjusting module is used for performing increment operation on the advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs by using the calculated weight increment value to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs.
Further, the advertisement recommendation apparatus provided in this embodiment further includes:
the fourth processing module is used for acquiring social information newly issued by the social media user corresponding to the user identifier in a time length from the second time point to the current time point when the time length from the last updated user interest model to the second time point reaches a second preset time length, and processing the social information to obtain keywords of the social information and keyword weights of the keywords of the social information;
the fourth obtaining module is used for obtaining a user interest model of the social media user corresponding to the user identification;
a sixth calculating module, configured to update, when a user interest keyword that is the same as the keyword of the social information can be queried in a user interest model of a social media user corresponding to the user identifier, a keyword weight of the user interest keyword that is the same as the keyword of the social information in the user interest model by using the following formula:
wherein the content of the first and second substances,
representing user interest keywords in the user interest model which are the same as the keywords of the social information;
representing an update coefficient;
representing a current point in time;
representing a second preset time length;
representing the current keyword weight of the user interest keywords which are the same as the keywords of the social information in the user interest model;
representing social messagesThe keyword weight of the keyword;
a keyword weight representing a user interest keyword in the updated user interest model that is the same as the keyword of the social information;
and the fifth processing module is used for generating a corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information when the keywords which are the same as the keywords of the social information cannot be inquired from the user interest model of the social media user corresponding to the user identifier, and storing the generated corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information into the user interest model of the social media user corresponding to the user identifier as the corresponding relation between the user interest keywords and the keyword weights.
In summary, the advertisement recommendation apparatus provided in this embodiment determines the user interest keywords from the user interest model, and determining the determined user interest keywords as the keywords to be processed of the social media user corresponding to the user identification, then inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification, compared with the mode that the social media platform pushes all the advertisements to the user for watching in the related art, the advertisements matched with the interest keywords of the user can be inquired out, that is, the advertisements which are relatively interested by the user are inquired, and then the inquired advertisements which are interested by the user are pushed to the user, the social media users can watch advertisements which are interested by the users, and experience of the social media users in using the social media is improved.
Example 3
The present embodiment proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the advertisement recommendation method described in embodiment 1 above. For specific implementation, refer to method embodiment 1, which is not described herein again.
In addition, referring to the schematic structural diagram of an electronic device shown in fig. 3, the present embodiment further provides an electronic device, where the electronic device includes a bus 51, a processor 52, a transceiver 53, a bus interface 54, a memory 55, and a user interface 56. The electronic device comprises a memory 55.
In this embodiment, the electronic device further includes: one or more programs stored on the memory 55 and executable on the processor 52, configured to be executed by the processor for performing the following steps (1) to (3):
(1) obtaining a user interest model and an advertisement classification model, wherein the user interest model comprises: the user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight; the advertisement classification model comprises: the corresponding relation among the advertisement type, the advertisement identification and the advertisement key word;
(2) determining user interest keywords of which the keyword weights are greater than or equal to a keyword threshold value in the user interest keywords of the social media users corresponding to the user identifications from the user interest model, and determining the determined user interest keywords of which the keyword weights are greater than or equal to the keyword threshold value as to-be-processed keywords of the social media users corresponding to the user identifications;
(3) and inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, and pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification.
A transceiver 53 for receiving and transmitting data under the control of the processor 52.
Where a bus architecture (represented by bus 51) is used, bus 51 may include any number of interconnected buses and bridges, with bus 51 linking together various circuits including one or more processors, represented by general purpose processor 52, and memory, represented by memory 55. The bus 51 may also link various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further in this embodiment. A bus interface 54 provides an interface between the bus 51 and the transceiver 53. The transceiver 53 may be one element or may be multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. For example: the transceiver 53 receives external data from other devices. The transceiver 53 is used for transmitting data processed by the processor 52 to other devices. Depending on the nature of the computing system, a user interface 56, such as a keypad, display, speaker, microphone, joystick, may also be provided.
The processor 52 is responsible for managing the bus 51 and the usual processing, running a general-purpose operating system as described above. And memory 55 may be used to store data used by processor 52 in performing operations.
Alternatively, processor 52 may be, but is not limited to: a central processing unit, a singlechip, a microprocessor or a programmable logic device.
It will be appreciated that the memory 55 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (ddr DRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 55 of the systems and methods described in this embodiment is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 55 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof: an operating system 551 and application programs 552.
The operating system 551 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 552 includes various applications, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. A program implementing the method of an embodiment of the present invention may be included in the application 552.
In summary, the electronic device and the computer-readable storage medium of the present embodiment determine the user interest keyword from the user interest model, and determining the determined user interest keywords as the keywords to be processed of the social media user corresponding to the user identification, then inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification, compared with the mode that the social media platform pushes all the advertisements to the user for watching in the related art, the advertisements matched with the interest keywords of the user can be inquired out, that is, the advertisements which are relatively interested by the user are inquired, and then the inquired advertisements which are interested by the user are pushed to the user, the social media users can watch advertisements which are interested by the users, and experience of the social media users in using the social media is improved.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (8)
1. An advertisement recommendation method, comprising:
obtaining a user interest model and an advertisement classification model, wherein the user interest model comprises: the user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight; the advertisement classification model comprises: the corresponding relation among the advertisement type, the advertisement identification and the advertisement key word;
determining user interest keywords of which the keyword weights are greater than or equal to a keyword threshold value in the user interest keywords of the social media users corresponding to the user identifications from the user interest model, and determining the determined user interest keywords of which the keyword weights are greater than or equal to the keyword threshold value as to-be-processed keywords of the social media users corresponding to the user identifications;
inquiring an advertisement identification matched with the keyword to be processed from the advertisement classification model, and pushing an advertisement corresponding to the advertisement identification to a social media user corresponding to the user identification;
acquiring an operation type used when the social media user corresponding to the user identification operates the pushed advertisement, and acquiring an operation evaluation value matched with the operation type;
generating a corresponding relation between the advertisement identification of the advertisement operated by the social media user corresponding to the user identification and the operation evaluation value;
when it is determined that the social media user corresponding to the user identifier has the unoperated advertisement according to the corresponding relationship, calculating the similarity between the unoperated advertisement of the social media user corresponding to the user identifier and the advertisement operated by the social media user corresponding to the user identifier;
calculating to obtain a predictive evaluation value of the advertisement which is not operated by the social media user corresponding to the user identifier by using the operation evaluation value of the advertisement which is operated by the social media user corresponding to the user identifier and the calculated similarity;
taking the operation evaluation value and the prediction evaluation value as advertisement recommendation coefficients;
and determining the advertisements respectively corresponding to the larger advertisement recommendation coefficients in the advertisement recommendation coefficients as the advertisements recommended again to the social media users corresponding to the user identifications, and pushing the advertisements respectively corresponding to the larger advertisement recommendation coefficients to the social media users corresponding to the user identifications.
2. The method of claim 1, further comprising:
when the time length from a first time point of last adjustment of the advertisement type weight reaches a first preset time length, determining the advertisement type of the advertisement operated by the social media user corresponding to the user identification in the time length from the first time point to the current time point, and counting a first number of the advertisement types of the advertisement operated by the social media user corresponding to the user identification;
acquiring the corresponding relation between the advertisement type and the advertisement type weight of the pushed advertisement of the social media user corresponding to the user identification;
determining the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identifier belongs based on the corresponding relation between the advertisement type and the advertisement type weight and the advertisement type to which the advertisement which is operated by the social media user and corresponds to the user identifier belongs, and counting a second number of the advertisement types to which the advertisement which is not operated by the social media user and corresponds to the user identifier belongs;
reducing the advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification belongs;
based on the second quantity, calculating to obtain a weight decrement accumulated value of advertisement type weights corresponding to advertisement types to which the advertisements which are not operated by the social media user and correspond to the user identification belong;
calculating to obtain a weight increment value of the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs through the following formula:
weight increment value = weight decrement cumulative value/first number;
and performing increment operation on the advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs by using the calculated weight increment value to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs.
3. The method of claim 1, further comprising:
when the time length from a second time point of last updating of the user interest model reaches a second preset time length, obtaining newly published social information of the user corresponding to the user identification of the social media in the time length from the second time point to the current time point, and processing the social information to obtain keywords of the social information and keyword weights of the keywords of the social information;
obtaining a user interest model of the social media user corresponding to the user identification;
when a user interest keyword which is the same as the keyword of the social information can be inquired from a user interest model of a user of the social media corresponding to the user identification, updating the keyword weight of the user interest keyword which is the same as the keyword of the social information in the user interest model through the following formula:
wherein the content of the first and second substances,
representing user interest keywords in the user interest model which are the same as the keywords of the social information;
representing an update coefficient;
representing a current point in time;
representing a second preset time length;
representing the current keyword weight of the user interest keywords which are the same as the keywords of the social information in the user interest model;
a keyword weight representing a keyword of social information;
a keyword weight representing a user interest keyword in the updated user interest model that is the same as the keyword of the social information;
when the keywords which are the same as the keywords of the social information cannot be inquired from the user interest model of the social media user corresponding to the user identification, generating the corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information, and storing the generated corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information as the corresponding relation between the user interest keywords and the keyword weights into the user interest model of the social media user corresponding to the user identification.
4. An advertisement recommendation apparatus, comprising:
the obtaining module is used for obtaining a user interest model and an advertisement classification model, wherein the user interest model comprises: the user identification of the social media user and the corresponding relation between the user interest keywords and the keyword weight; the advertisement classification model comprises: the corresponding relation among the advertisement type, the advertisement identification and the advertisement key word;
the determining module is used for determining user interest keywords of which the keyword weights are more than or equal to a keyword threshold value from the user interest keywords of the social media users corresponding to the user identifications in the user interest model, and determining the determined user interest keywords of which the keyword weights are more than or equal to the keyword threshold value as the keywords to be processed of the social media users corresponding to the user identifications;
the pushing module is used for inquiring the advertisement identification matched with the keyword to be processed from the advertisement classification model and pushing the advertisement corresponding to the advertisement identification to the social media user corresponding to the user identification;
the second acquisition module is used for acquiring an operation type used when the social media user corresponding to the user identifier operates the pushed advertisement, and acquiring an operation evaluation value matched with the operation type;
the generating module is used for generating the corresponding relation between the advertisement identification and the operation evaluation value of the advertisement operated by the social media user corresponding to the user identification;
the first calculation module is used for calculating the similarity between the advertisement which is not operated by the social media user corresponding to the user identifier and the advertisement which is operated by the social media user corresponding to the user identifier when the social media user corresponding to the user identifier has the advertisement which is not operated according to the corresponding relation;
the second calculation module is used for calculating to obtain a predictive evaluation value of the advertisement which is not operated by the social media user corresponding to the user identifier by utilizing the operation evaluation value of the advertisement which is operated by the social media user corresponding to the user identifier and the calculated similarity;
a processing module, configured to use the operation evaluation value and the predictive evaluation value as advertisement recommendation coefficients;
and the secondary pushing module is used for determining the advertisements corresponding to the larger advertisement recommendation coefficients in the advertisement recommendation coefficients as the advertisements recommended again to the social media users corresponding to the user identifications, and pushing the advertisements corresponding to the larger advertisement recommendation coefficients to the social media users corresponding to the user identifications.
5. The apparatus of claim 4, further comprising:
the second processing module is used for determining the advertisement type of the advertisement operated by the social media user corresponding to the user identifier in the time length from the first time point of last adjustment of the advertisement type weight to a first preset time length, and counting a first number of the advertisement types of the advertisement operated by the social media user corresponding to the user identifier;
the third acquisition module is used for acquiring the corresponding relation between the advertisement type and the advertisement type weight of the pushed advertisement of the social media user corresponding to the user identification;
a third processing module, configured to determine, based on the correspondence between the advertisement type and the advertisement type weight and the advertisement type to which the advertisement operated by the social media user corresponding to the user identifier belongs, an advertisement type to which the advertisement not operated by the social media user corresponding to the user identifier belongs, and count a second number of advertisement types to which the advertisement not operated by the social media user corresponding to the user identifier belongs;
the third calculation module is used for performing decrement operation on the advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement which is not operated by the social media user and corresponds to the user identification belongs;
a fourth calculating module, configured to calculate, based on the second number, a weight decrement cumulative value of an advertisement type weight corresponding to an advertisement type to which an advertisement that is not operated by the social media user and corresponds to the user identifier belongs;
a fifth calculating module, configured to calculate, by using the following formula, a weight increment value of an advertisement type to which an advertisement operated by a social media user corresponding to the user identifier belongs:
weight increment value = weight decrement cumulative value/first number;
and the adjusting module is used for performing increment operation on the advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs by using the calculated weight increment value to obtain the adjusted advertisement type weight corresponding to the advertisement type to which the advertisement operated by the social media user corresponding to the user identification belongs.
6. The apparatus of claim 4, further comprising:
the fourth processing module is used for acquiring social information newly issued by the social media user corresponding to the user identifier in a time length from the second time point to the current time point when the time length from the last updated user interest model to the second time point reaches a second preset time length, and processing the social information to obtain keywords of the social information and keyword weights of the keywords of the social information;
the fourth obtaining module is used for obtaining a user interest model of the social media user corresponding to the user identification;
a sixth calculating module, configured to update, when a user interest keyword that is the same as the keyword of the social information can be queried in a user interest model of a social media user corresponding to the user identifier, a keyword weight of the user interest keyword that is the same as the keyword of the social information in the user interest model by using the following formula:
wherein the content of the first and second substances,
representing user interest keywords in the user interest model which are the same as the keywords of the social information;
representing an update coefficient;
representing a current point in time;
representing a second preset time length;
representing the current keyword weight of the user interest keywords which are the same as the keywords of the social information in the user interest model;
a keyword weight representing a keyword of social information;
a keyword weight representing a user interest keyword in the updated user interest model that is the same as the keyword of the social information;
and the fifth processing module is used for generating a corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information when the keywords which are the same as the keywords of the social information cannot be inquired from the user interest model of the social media user corresponding to the user identifier, and storing the generated corresponding relation between the keywords of the social information and the keyword weights of the keywords of the social information into the user interest model of the social media user corresponding to the user identifier as the corresponding relation between the user interest keywords and the keyword weights.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1-3.
8. An electronic device comprising a memory, a processor, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor to perform the steps of the method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011033383.4A CN111882370B (en) | 2020-09-27 | 2020-09-27 | Advertisement recommendation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011033383.4A CN111882370B (en) | 2020-09-27 | 2020-09-27 | Advertisement recommendation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111882370A true CN111882370A (en) | 2020-11-03 |
| CN111882370B CN111882370B (en) | 2020-12-08 |
Family
ID=73199955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011033383.4A Active CN111882370B (en) | 2020-09-27 | 2020-09-27 | Advertisement recommendation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111882370B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270579A (en) * | 2020-12-05 | 2021-01-26 | 杭州次元岛科技有限公司 | Intelligent advertising system based on big data |
| CN112990986A (en) * | 2021-04-29 | 2021-06-18 | 广州宜推网络科技有限公司 | Advertisement service information publishing system based on block chain |
| CN112989824A (en) * | 2021-05-12 | 2021-06-18 | 武汉卓尔数字传媒科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113674012A (en) * | 2020-05-14 | 2021-11-19 | 南宁富桂精密工业有限公司 | Advertisement information pushing method and system |
| CN113672804A (en) * | 2021-08-02 | 2021-11-19 | 上海浦东发展银行股份有限公司 | Recommendation information generation method, system, computer device and storage medium |
| CN115471262A (en) * | 2022-09-15 | 2022-12-13 | 武汉精阅数字传媒科技有限公司 | Advertisement distribution system and intelligent advertisement distributor |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120030025A1 (en) * | 2010-07-28 | 2012-02-02 | Yang Pan | Delivering Highly Targeted Advertisements to a User of a Computing Device by Statistically Analyzing of Key Words Used in a Communication Module |
| CN102414705A (en) * | 2009-03-03 | 2012-04-11 | 谷歌公司 | Method and system for providing advertising to users of social network |
| CN102414706A (en) * | 2009-03-03 | 2012-04-11 | 谷歌公司 | Adheat advertisement model for social network |
| CN102708198A (en) * | 2012-05-16 | 2012-10-03 | 杭州通策会综合服务有限公司 | Individualized network advertisement pushing method |
| CN105512916A (en) * | 2015-12-18 | 2016-04-20 | 北京讯达网脉科技有限公司 | Advertisement accurate delivery method and advertisement accurate delivery system |
| CN109993570A (en) * | 2019-01-14 | 2019-07-09 | 深圳市东信时代信息技术有限公司 | A kind of orientation launches the method and system of moving advertising |
| CN110378732A (en) * | 2019-07-18 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Information display method, information correlation method, device, equipment and storage medium |
| US10592930B2 (en) * | 2005-09-14 | 2020-03-17 | Millenial Media, LLC | Syndication of a behavioral profile using a monetization platform |
-
2020
- 2020-09-27 CN CN202011033383.4A patent/CN111882370B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10592930B2 (en) * | 2005-09-14 | 2020-03-17 | Millenial Media, LLC | Syndication of a behavioral profile using a monetization platform |
| CN102414705A (en) * | 2009-03-03 | 2012-04-11 | 谷歌公司 | Method and system for providing advertising to users of social network |
| CN102414706A (en) * | 2009-03-03 | 2012-04-11 | 谷歌公司 | Adheat advertisement model for social network |
| US20120030025A1 (en) * | 2010-07-28 | 2012-02-02 | Yang Pan | Delivering Highly Targeted Advertisements to a User of a Computing Device by Statistically Analyzing of Key Words Used in a Communication Module |
| CN102708198A (en) * | 2012-05-16 | 2012-10-03 | 杭州通策会综合服务有限公司 | Individualized network advertisement pushing method |
| CN105512916A (en) * | 2015-12-18 | 2016-04-20 | 北京讯达网脉科技有限公司 | Advertisement accurate delivery method and advertisement accurate delivery system |
| CN109993570A (en) * | 2019-01-14 | 2019-07-09 | 深圳市东信时代信息技术有限公司 | A kind of orientation launches the method and system of moving advertising |
| CN110378732A (en) * | 2019-07-18 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Information display method, information correlation method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 金紫嫣 等: "一种带标签的协同过滤广告推荐算法", 《计算机工程》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674012A (en) * | 2020-05-14 | 2021-11-19 | 南宁富桂精密工业有限公司 | Advertisement information pushing method and system |
| CN112270579A (en) * | 2020-12-05 | 2021-01-26 | 杭州次元岛科技有限公司 | Intelligent advertising system based on big data |
| CN112270579B (en) * | 2020-12-05 | 2022-05-03 | 杭州次元岛科技有限公司 | Intelligent advertising system based on big data |
| CN112990986A (en) * | 2021-04-29 | 2021-06-18 | 广州宜推网络科技有限公司 | Advertisement service information publishing system based on block chain |
| CN112990986B (en) * | 2021-04-29 | 2021-07-16 | 广州宜推网络科技有限公司 | Advertisement service information publishing system based on block chain |
| CN112989824A (en) * | 2021-05-12 | 2021-06-18 | 武汉卓尔数字传媒科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113672804A (en) * | 2021-08-02 | 2021-11-19 | 上海浦东发展银行股份有限公司 | Recommendation information generation method, system, computer device and storage medium |
| CN115471262A (en) * | 2022-09-15 | 2022-12-13 | 武汉精阅数字传媒科技有限公司 | Advertisement distribution system and intelligent advertisement distributor |
| CN115471262B (en) * | 2022-09-15 | 2023-12-01 | 武汉精阅数字传媒科技有限公司 | Advertisement distribution system and intelligent advertisement distributor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111882370B (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111882370B (en) | Advertisement recommendation method and device and electronic equipment | |
| CN111444428B (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| US11928601B2 (en) | Neural network compression | |
| US10217058B2 (en) | Predicting interesting things and concepts in content | |
| US20180196800A1 (en) | Learning document embeddings with convolutional neural network architectures | |
| CN109190049B (en) | Keyword recommendation method, system, electronic device and computer readable medium | |
| US10102482B2 (en) | Factorized models | |
| CN109800307B (en) | Product evaluation analysis method and device, computer equipment and storage medium | |
| JP6854748B2 (en) | Information providing equipment, information providing method, and program | |
| US9141966B2 (en) | Opinion aggregation system | |
| US20160125028A1 (en) | Systems and methods for query rewriting | |
| CN111459993B (en) | Configuration updating method, device, equipment and storage medium based on behavior analysis | |
| US20120278332A1 (en) | Category-sensitive ranking for text | |
| CN105069036A (en) | Information recommendation method and apparatus | |
| CN109117442B (en) | Application recommendation method and device | |
| CN112183994A (en) | Method and device for evaluating equipment state, computer equipment and storage medium | |
| CN113221019B (en) | Personalized recommendation method and system based on instant learning | |
| JP6593873B2 (en) | Information analysis apparatus and information analysis method | |
| CN107562788B (en) | Interaction method, interaction device and computer-readable storage medium | |
| CN113010788B (en) | Information pushing method and device, electronic equipment and computer readable storage medium | |
| CN112581195B (en) | Advertisement pushing method and device and electronic equipment | |
| CN113934825B (en) | Question answering method and device and electronic equipment | |
| US20240119366A1 (en) | Online training of machine learning models using bayesian inference over noise | |
| Guo et al. | Web page prediction based on conditional random fields | |
| CN113886695A (en) | Resource recommendation 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 |