CN115329203A - Content recommendation method and apparatus - Google Patents
Content recommendation method and apparatus Download PDFInfo
- Publication number
- CN115329203A CN115329203A CN202211071952.3A CN202211071952A CN115329203A CN 115329203 A CN115329203 A CN 115329203A CN 202211071952 A CN202211071952 A CN 202211071952A CN 115329203 A CN115329203 A CN 115329203A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- identity information
- content
- characteristic data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004891 communication Methods 0.000 claims description 71
- 230000004044 response Effects 0.000 claims description 4
- 230000000295 complement effect Effects 0.000 abstract description 4
- 238000012217 deletion Methods 0.000 abstract description 2
- 230000037430 deletion Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a content recommendation method and device, which are used in the field of big data and comprise the following steps: acquiring first user identity information provided inside a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform, wherein the first user identity information and the second user identity information comprise different identity information aiming at the same user; determining a target user according to the first user identity information and the second user identity information; and recommending the content corresponding to the content recommendation platform to the target user. Therefore, the target user is determined according to the information provided by the internal platform and the information provided by the external platform, and then content recommendation is performed on the target user, wherein the internal information and the external information are complementary, and the phenomenon that the possessed user information is ambiguous and has a high deletion rate is avoided, so that the success rate of content recommendation is improved.
Description
Technical Field
The present application relates to the field of big data, and in particular, to a content recommendation method and apparatus.
Background
In the aspect of product content recommendation, accurate and refined operation on inventory customers is one of the important stages of customer management. The traditional product content recommendation mode is achieved through simple and rough modes such as direct electricity marketing and contact of agents, and the mode can cause resource waste, high cost, dispersed customer information and other adverse effects.
In addition, the content recommendation method at present is to recommend content to a user by using internal information of a content recommendation platform, and since content recommendation is performed to a client by using the internal information of the content recommendation platform, the client information has the phenomena of ambiguity and high missing rate, so that the content recommendation success rate is low.
Therefore, how to improve the success rate of content recommendation is a key issue to be focused on by those skilled in the art.
Disclosure of Invention
In view of the above problems, the present application provides a content recommendation method and apparatus, to improve the success rate of content recommendation. The embodiment of the application discloses the following technical scheme:
in a first aspect, the present application discloses a content recommendation method, including:
obtaining first user identity information provided in content recommendation platform and removing the first user identity information second user identity information provided by an external platform other than the content recommendation platform, the first user identity information and the second user identity information comprise different identity information for the same user;
determining a first target user according to the first user identity information and the second user identity information;
and recommending the content corresponding to the content recommendation platform to the first target user.
Optionally, the determining a first target user according to the first user identity information and the second user identity information, the method comprises the following steps:
generating user sets corresponding to different asset levels and user sets corresponding to different age groups according to the first user identity information and the second user identity information;
and determining the first target user according to the user sets corresponding to the different asset classes and the user sets corresponding to the different age groups.
Optionally, the method further includes:
acquiring user purchase content information and user telephone communication information provided by the content recommendation platform;
determining a characteristic data type corresponding to the required characteristic data information based on the user purchase content information and the user telephone communication information;
and acquiring user characteristic data information which is provided by the external platform and corresponds to the characteristic data type.
Optionally, the method further includes:
acquiring the user characteristic data information, and determining a sample purchase label corresponding to the user characteristic data information according to the user purchase content information, wherein the sample purchase label is used for identifying whether a user corresponding to the user characteristic data information purchases content recommended by the content recommendation platform;
inputting the user characteristic data information into an initial user purchase rate model to obtain a to-be-determined purchase label;
and adjusting the initial user purchase rate model according to the difference between the sample purchase label and the label to be purchased to obtain a user purchase rate model.
Optionally, the method further includes:
acquiring user characteristic data information, and determining a sample telephone communication label corresponding to the user characteristic data information according to the user telephone communication information, wherein the sample telephone communication label is used for identifying whether a user corresponding to the user characteristic data information connects a telephone dialed by the content recommendation platform;
inputting the user characteristic data information into an initial user telephone communication rate model to obtain a communication label of a pending telephone;
and adjusting the initial user telephone communication rate model according to the difference between the sample telephone communication label and the undetermined telephone communication label to obtain a user telephone communication rate model.
In the alternative, further comprising:
acquiring target characteristic data information of a user to be analyzed;
inputting the target characteristic data information into the user purchase rate model, and generating the probability that the user to be analyzed purchases the content recommended by the content recommendation platform;
and inputting the target characteristic data information into the user telephone communication rate model to generate the probability of the user to be analyzed calling the content recommendation platform.
Optionally, the method further includes:
determining the user to be analyzed as a second target user in response to the fact that the probability that the user to be analyzed purchases the content recommended by the content recommendation platform and the probability that the user to be analyzed makes a call through the content recommendation platform are both greater than a first threshold value;
and recommending the content corresponding to the content recommendation platform to the second target user.
In a second aspect of the present invention, the application discloses content recommendation device includes:
the system comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring first user identity information provided by a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform, and the first user identity information and the second user identity information comprise different identity information aiming at the same user;
the determining module is used for determining a first target user according to the first user identity information and the second user identity information;
and the recommending module is used for recommending the content corresponding to the content recommending platform to the first target user.
Optionally, the determining module includes:
a module for generating a plurality of data files, the system comprises a first user identity information acquisition module, a second user identity information acquisition module, a first user identity information acquisition module, a second user identity information acquisition module and a second user identity information acquisition module, wherein the first user identity information acquisition module is used for acquiring first user identity information and second user identity information;
a first determination sub-module for determining a first determination sub-module, and the first target user is determined according to the user sets corresponding to the different asset classes and the user sets corresponding to the different age groups.
Optional, further comprising:
the first acquisition sub-module is used for acquiring user purchase content information and user telephone communication information provided by the content recommendation platform;
the second determining submodule is used for determining the characteristic data type corresponding to the required characteristic data information based on the user purchasing content information and the user telephone communication information;
and the second acquisition submodule is used for acquiring the user characteristic data information which is provided by the external platform and corresponds to the characteristic data type.
Optionally, the method further includes:
a third obtaining sub-module, configured to obtain the user characteristic data information, and determine, according to the user purchase content information, a sample purchase tag corresponding to the user characteristic data information, where the sample purchase tag is used to identify whether a user corresponding to the user characteristic data information purchases content recommended by the content recommendation platform;
the first obtaining module is used for inputting the user characteristic data information into an initial user purchase rate model to obtain a to-be-determined purchase label;
and the first adjusting module is used for adjusting the initial user purchase rate model according to the difference between the sample purchase label and the undetermined purchase label to obtain a user purchase rate model.
Optionally, the method further includes:
a fourth obtaining sub-module, configured to obtain user feature data information, and determine, according to the user telephone communication information, a sample telephone communication tag corresponding to the user feature data information, where the sample telephone communication tag is used to identify whether a user corresponding to the user feature data information connects a telephone called by the content recommendation platform;
the second obtaining module is used for inputting the user characteristic data information into an initial user telephone communication rate model to obtain a communication label of a to-be-determined telephone;
a second adjusting module, configured to adjust the sample phone communication label according to a difference between the sample phone communication label and the communication label to be called, and adjusting the initial user telephone communication rate model to obtain a user telephone communication rate model.
Optionally, the method further includes:
the fifth acquisition sub-module is used for acquiring target characteristic data information of a user to be analyzed;
the first generation module is used for inputting the target characteristic data information into the user purchase rate model and generating the probability of the user to be analyzed for purchasing the content recommended by the content recommendation platform;
and the second generation module is used for inputting the target characteristic data information into the user telephone communication rate model and generating the probability that the user to be analyzed makes a call by connecting the content recommendation platform.
Optionally, the method further includes:
a third determining submodule, configured to determine the user to be analyzed as a second target user in response to that both a probability that the user to be analyzed purchases the content recommended by the content recommendation platform and a probability that the user to be analyzed makes a call to the content recommendation platform are greater than a first threshold;
and the first sub-recommending module is used for recommending the content corresponding to the content recommending platform to the second target user.
Compared with the prior art, the method has the following beneficial effects:
according to the method and the device, first user identity information provided by a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform are obtained, the first user identity information and the second user identity information comprise different identity information aiming at the same user, then a target user is determined according to the first user identity information and the second user identity information, and finally content corresponding to the content recommendation platform is recommended to the target user. Therefore, the target user is determined according to the information provided by the internal platform and the information provided by the external platform, and then content recommendation is performed on the target user, wherein the internal information and the external information are complementary, and the phenomenon of ambiguity and high missing rate of the owned user information does not exist, so that the success rate of content recommendation is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a content recommendation method according to an embodiment of the present application;
fig. 2 is a flowchart of another content recommendation method provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a content recommendation device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
It should be noted that, the content recommendation method and apparatus provided by the present application are used in the field of big data, the foregoing is merely an example, and does not limit the application fields of the names of the methods and apparatuses provided in the present application.
As described above, the current content recommendation method is to perform content recommendation on a user by using internal information of a content recommendation platform, and since content recommendation is performed on a client by using the internal information of the content recommendation platform, the client information has the disadvantages of ambiguity and high missing rate, which results in a low success rate of content recommendation. Therefore, how to improve the success rate of content recommendation is a key issue to be focused on by those skilled in the art.
Therefore, the inventor proposes a technical scheme of the present application, in which first user identity information provided inside a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform are first obtained, the first user identity information and the second user identity information include different identity information for the same user, then a target user is determined according to the first user identity information and the second user identity information, and finally content corresponding to the content recommendation platform is recommended to the target user. Therefore, the target user is determined according to the information provided by the internal platform and the information provided by the external platform, and then content recommendation is performed on the target user, wherein the internal information and the external information are complementary, and the phenomenon of ambiguity and high missing rate of the owned user information does not exist, so that the success rate of content recommendation is improved.
The method provided by the embodiment of the application can be executed by software on the terminal equipment. The terminal device may be, for example, a mobile phone, a tablet computer, a computer, or the like. The software may be, for example, system software.
In order that those skilled in the art will better understand the present application, the present application will be described in further detail with reference to the following drawings and detailed description.
Method embodiment
A content recommendation method provided in the present application is described below by an embodiment.
Referring to fig. 1, which is a flowchart of a content recommendation method provided in an embodiment of the present application, as shown in fig. 1, the method may include:
s101: the method comprises the steps of obtaining first user identity information provided by the inside of a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform.
In this step, the first user identity information and the second user identity information include different identity information for the same user, that is, the first user identity information and the second user identity information have complementarity, so that the identity information of the same user is as complete as possible. The first identity user information is provided by an internal recommendation platform, and the second identity user information is provided by an external platform except the content recommendation platform. It should be further noted that, after the first user identity information and the second user identity information are obtained, a data cleansing operation is performed.
S102: and determining a first target user according to the first user identity information and the second user identity information.
In this step, the first user identity information includes user basic information (such as information about age, child presence, marriage and elder), the second user identity information also includes user basic information (such as information about age, child presence, marriage and elder), and then combining the first user identity information and the second user identity information to obtain final user identity information, wherein the final user identity information is used for determining a target user, so that the portrait of the user is enriched, and the success rate of content recommendation is improved.
Further, a user set corresponding to different asset classes and a user set corresponding to different age groups are generated according to the first user identity information and the second user identity information, and then a target user is determined according to the user set corresponding to the different asset classes and the user set corresponding to the different age groups. It can be understood that the asset class corresponding to the first user identity information is compared with the asset class corresponding to the second user identity information, and the largest asset class is selected as the user asset class; and when the age information corresponding to the first user identity information is missing, selecting age information corresponding to the second user identity information for supplementation to obtain the age information.
S103: and recommending the content corresponding to the content recommendation platform to the first target user.
In this step, the content corresponding to the content recommendation platform is recommended according to the determined target user, and since the target user is determined according to the internal information and the external information, the integrity of the user information is high, and the success rate of content recommendation is improved accordingly.
Therefore, the alternative scheme mainly explains how to determine the target user and recommend the content of the target user. Specifically, in this alternative, first user identity information provided inside a content recommendation platform and second user identity information provided by an external platform other than the content recommendation platform are first obtained, where the first user identity information and the second user identity information include different identity information for the same user, a target user is then determined according to the first user identity information and the second user identity information, and finally, content corresponding to the content recommendation platform is recommended to the target user.
In summary, in the embodiment, the target user is determined according to the information provided by the internal platform and the information provided by the external platform, and then content recommendation is performed on the target user, wherein the internal information and the external information are complementary, and the owned user information does not have the phenomena of ambiguity and high deletion rate, so that the success rate of content recommendation is improved.
Referring to fig. 2, which is a flowchart of another content recommendation method provided in an embodiment of the present application, as shown in fig. 2, the method may include:
s201: and acquiring user purchase content information and user telephone communication information provided by the content recommendation platform.
In this step, user purchase content information and user telephone communication information provided by the content recommendation platform are also obtained, the user purchase content information comprises user purchased content information and user unpurchased content information, and the user telephone communication information comprises user call connection information and call disconnection information.
S202: and determining the characteristic data type corresponding to the required characteristic data information based on the user purchase content information and the user telephone communication information.
In this step, the feature data type corresponding to the required feature data information is determined according to the content information purchased by the user, for example, whether the user shields recommended content received by a mobile phone number corresponding to the user; and determining the type of the characteristic data corresponding to the required characteristic data information according to the telephone communication information of the user, such as a time period when a mobile phone number corresponding to the user is active.
S203: and acquiring user characteristic data information which is provided by the external platform and corresponds to the characteristic data type.
In this step, the external platform obtains the user characteristic data information corresponding to the characteristic data type, where the user characteristic data information includes the time period when the mobile phone number corresponding to the user is active and the content shielded by the mobile phone number corresponding to the user. In this way, the content recommendation platform knows, based on the active time periods, which time periods it is easy to call the user on, and the content recommendation platform knows, based on the masked content, which content to recommend to the user is not easy to reject.
As an implementation manner, the model is trained according to the user purchase content information, the user telephone communication information, and the user characteristic data information, and the model may be a secureboost model, which is not specifically limited herein. A privacy channel is established between the external platform and the internal platform to acquire the user characteristic data information so as to ensure the safety of the user characteristic data information. Specifically, a sample purchase label corresponding to the user characteristic data information is determined according to the user purchase content information, the sample purchase label is used for identifying whether a user corresponding to the user characteristic data information purchases content recommended by a content recommendation platform or not, then the user characteristic data information is input into an initial user purchase rate model to obtain a to-be-determined purchase label, and finally the initial user purchase rate model is adjusted according to the difference between the sample purchase label and the to-be-determined purchase label to obtain a user purchase rate model.
As another implementation manner, user characteristic data information is obtained, a sample telephone communication tag corresponding to the user characteristic data information is determined according to the user telephone communication information, the sample telephone communication tag is used for identifying whether a user corresponding to the user characteristic data information connects a telephone dialed by a content recommendation platform, then the user characteristic data information is input into an initial user telephone communication rate model to obtain an undetermined telephone communication tag, and finally the initial user telephone communication rate model is adjusted according to a difference between the sample telephone communication tag and the undetermined telephone communication tag to obtain a user telephone communication rate model. It should be further noted that the prediction capabilities of the user purchase rate model and the user telephone communication rate model are evaluated by using AUC, KS and the promotion index.
Further, target characteristic data information corresponding to a user to be analyzed is obtained firstly, then the target characteristic data information is input into a user purchase rate model, the probability that the user to be analyzed purchases the content recommended by the content recommendation platform is generated, the target characteristic data information is input into a user telephone communication rate model, the probability that the user to be analyzed makes a call through the content recommendation platform is generated, and finally when the probability that the user to be analyzed purchases the content recommended by the content recommendation platform and the probability that the user to be analyzed makes a call through the content recommendation platform are both greater than a first threshold value, the user to be analyzed is determined as the target user.
Therefore, the alternative scheme mainly explains how to determine the target user and recommend the content of the target user. Specifically, in this alternative, in the present application, first, user purchase content information and user telephone communication information provided by the content recommendation platform are obtained, then, a feature data type corresponding to required feature data information is determined based on the user purchase content information and the user telephone communication information, and finally, user feature data information corresponding to the feature data type and provided by the external platform is obtained.
In summary, the target user determined according to the first user identity information, the second user identity information, the user purchase rate model and the user telephone communication rate model in the application has higher reliability and the success rate of content recommendation is higher.
Device embodiment
In the following, a content recommendation apparatus provided in an embodiment of the present application is introduced, and a content recommendation apparatus described below and a content recommendation method described above may be referred to correspondingly.
Referring to fig. 3, which is a schematic structural diagram of a content recommendation device according to an embodiment of the present application, as shown in fig. 3, the device may include:
an obtaining module 100, configured to obtain first user identity information provided inside a content recommendation platform and second user identity information provided by an external platform other than the content recommendation platform, the first user identity information and the second user identity information comprise different identity information for the same user;
a determining module 200, configured to determine a first target user according to the first user identity information and the second user identity information;
a recommending module 300, configured to recommend, to the first target user, content corresponding to the content recommending platform.
Optionally, the determining module 200 includes:
the generating module is used for generating user sets corresponding to different asset levels and user sets corresponding to different age groups according to the first user identity information and the second user identity information;
and the first determining submodule is used for determining the first target user according to the user sets corresponding to the different asset levels and the user sets corresponding to the different age groups.
Alternatively to this, the first and second parts may, further comprising:
the first acquisition submodule is used for acquiring user purchase content information and user telephone communication information provided by the content recommendation platform;
the second determining submodule is used for determining the characteristic data type corresponding to the required characteristic data information based on the user purchasing content information and the user telephone communication information;
and the second acquisition sub-module is used for acquiring the user characteristic data information which is provided by the external platform and corresponds to the characteristic data type.
Optionally, the method further includes:
a third obtaining sub-module, configured to obtain the user characteristic data information, and determine, according to the user purchase content information, a sample purchase tag corresponding to the user characteristic data information, where the sample purchase tag is used to identify whether a user corresponding to the user characteristic data information purchases content recommended by the content recommendation platform;
the first obtaining module is used for inputting the user characteristic data information into an initial user purchase rate model to obtain a to-be-determined purchase label;
and the first adjusting module is used for adjusting the initial user purchase rate model according to the difference between the sample purchase label and the undetermined purchase label to obtain a user purchase rate model.
Optionally, the method further includes:
a fourth obtaining sub-module, configured to obtain user feature data information, and determine, according to the user telephone communication information, a sample telephone communication tag corresponding to the user feature data information, where the sample telephone communication tag is used to identify whether a user corresponding to the user feature data information connects a telephone called by the content recommendation platform;
the second obtaining module is used for inputting the user characteristic data information into an initial user telephone communication rate model to obtain a communication label of the phone to be determined;
and the second adjusting module is used for adjusting the initial user telephone communication rate model according to the difference between the sample telephone communication label and the undetermined telephone communication label to obtain a user telephone communication rate model.
Optionally, the method further includes:
the fifth acquisition sub-module is used for acquiring target characteristic data information of a user to be analyzed;
the first generation module is used for inputting the target characteristic data information into the user purchase rate model and generating the probability of the user to be analyzed purchasing the content recommended by the content recommendation platform;
and the second generation module is used for inputting the target characteristic data information into the user telephone communication rate model and generating the probability that the user to be analyzed makes a call by connecting the content recommendation platform.
Optionally, the method further includes:
a third determining submodule, configured to determine the user to be analyzed as a second target user in response to that both a probability that the user to be analyzed purchases the content recommended by the content recommendation platform and a probability that the user to be analyzed makes a call to the content recommendation platform are greater than a first threshold;
and the first sub-recommending module is used for recommending the content corresponding to the content recommending platform to the second target user. .
The content recommendation device provided by the embodiment of the application has the same beneficial effects as the content recommendation method provided by the embodiment, and therefore, the description is omitted.
It should be noted that, in the names "first" and "second" (if any), the names "first" and "second" mentioned in the embodiments of the present application are only used for name identification, and do not represent the sequential first and second.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The content recommendation method and apparatus provided by the present application are described in detail above. The principles and embodiments of the present application are described herein using specific examples, which are only used to help understand the method and its core idea of the present application. It should be noted that, for those skilled in the art, without departing from the principle of the present application, the present application can also make several improvements and modifications, and those improvements and modifications also fall into the protection scope of the claims of the present application.
Claims (10)
1. A content recommendation method, comprising:
acquiring first user identity information provided inside a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform, wherein the first user identity information and the second user identity information comprise different identity information aiming at the same user;
determining a first target user according to the first user identity information and the second user identity information;
and recommending the content corresponding to the content recommendation platform to the first target user.
2. The method of claim 1, wherein determining the first target user based on the first user identity information and the second user identity information comprises:
generating user sets corresponding to different asset levels and user sets corresponding to different age groups according to the first user identity information and the second user identity information;
and determining the first target user according to the user sets corresponding to the different asset levels and the user sets corresponding to the different age groups.
3. The method of claim 1, further comprising:
acquiring user purchase content information and user telephone communication information provided by the content recommendation platform;
determining a characteristic data type corresponding to the required characteristic data information based on the user purchase content information and the user telephone communication information;
and acquiring user characteristic data information which is provided by the external platform and corresponds to the characteristic data type.
4. The method of claim 3, further comprising:
acquiring the user characteristic data information, and determining a sample purchase label corresponding to the user characteristic data information according to the user purchase content information, wherein the sample purchase label is used for identifying whether a user corresponding to the user characteristic data information purchases content recommended by the content recommendation platform;
inputting the user characteristic data information into an initial user purchase rate model to obtain a to-be-determined purchase label;
and adjusting the initial user purchase rate model according to the difference between the sample purchase label and the label to be purchased to obtain a user purchase rate model.
5. The method of claim 4, further comprising:
obtaining user characteristic data information, and determining a sample telephone communication label corresponding to the user characteristic data information according to the user telephone communication information, wherein the sample telephone communication label is used for identifying whether a user corresponding to the user characteristic data information connects a telephone dialed by the content recommendation platform or not;
inputting the user characteristic data information into an initial user telephone communication rate model to obtain a communication label of a to-be-determined telephone;
and adjusting the initial user telephone communication rate model according to the difference between the sample telephone communication label and the undetermined telephone communication label to obtain a user telephone communication rate model.
6. The method of claim 4, further comprising:
acquiring target characteristic data information of a user to be analyzed;
inputting the target characteristic data information into the user purchase rate model, and generating the probability of the user to be analyzed purchasing the content recommended by the content recommendation platform;
and inputting the target characteristic data information into the user telephone communication rate model to generate the probability that the user to be analyzed makes a call by connecting the content recommendation platform.
7. The method of claim 6, further comprising:
determining the user to be analyzed as a second target user in response to the fact that the probability that the user to be analyzed purchases the content recommended by the content recommendation platform and the probability that the user to be analyzed makes a call through the content recommendation platform are both greater than a first threshold value;
and recommending the content corresponding to the content recommendation platform to the second target user.
8. A content recommendation apparatus characterized by comprising:
the system comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring first user identity information provided by a content recommendation platform and second user identity information provided by an external platform except the content recommendation platform, and the first user identity information and the second user identity information comprise different identity information aiming at the same user;
the determining module is used for determining a first target user according to the first user identity information and the second user identity information;
and the recommending module is used for recommending the content corresponding to the content recommending platform to the first target user.
9. The apparatus of claim 8, wherein the determining module comprises:
the generating module is used for generating user sets corresponding to different asset levels and user sets corresponding to different age groups according to the first user identity information and the second user identity information;
and the first determining submodule is used for determining the first target user according to the user sets corresponding to the different asset levels and the user sets corresponding to the different age groups.
10. The apparatus of claim 8, further comprising:
the first acquisition sub-module is used for acquiring user purchase content information and user telephone communication information provided by the content recommendation platform;
the second determining submodule is used for determining the characteristic data type corresponding to the required characteristic data information based on the user purchasing content information and the user telephone communication information;
and the second acquisition sub-module is used for acquiring the user characteristic data information which is provided by the external platform and corresponds to the characteristic data type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211071952.3A CN115329203A (en) | 2022-09-02 | 2022-09-02 | Content recommendation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211071952.3A CN115329203A (en) | 2022-09-02 | 2022-09-02 | Content recommendation method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115329203A true CN115329203A (en) | 2022-11-11 |
Family
ID=83930370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211071952.3A Pending CN115329203A (en) | 2022-09-02 | 2022-09-02 | Content recommendation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115329203A (en) |
-
2022
- 2022-09-02 CN CN202211071952.3A patent/CN115329203A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109862018B (en) | Anti-crawler method and system based on user access behavior | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN109660823A (en) | Video distribution method, apparatus, electronic equipment and storage medium | |
| CN105005582A (en) | Recommendation method and device for multimedia information | |
| CN107808346B (en) | Evaluation method and evaluation device for potential target object | |
| CN112804541B (en) | User behavior tracking method and device, electronic equipment and storage medium | |
| CN105681257B (en) | Information reporting method, device, equipment and system based on instant messaging interaction platform and computer storage medium | |
| CN111311294A (en) | Data processing method, device, medium and electronic equipment | |
| CN109086317A (en) | Risk control method and relevant apparatus | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN112150252A (en) | Credit-based service processing method and device | |
| CN112035676A (en) | User operation behavior knowledge graph construction method and device | |
| CN109451334B (en) | User portrait generation processing method and device and electronic equipment | |
| CN107729124A (en) | Transaction methods and device, electronic equipment | |
| CN111027065B (en) | Leucavirus identification method and device, electronic equipment and storage medium | |
| CN117252429A (en) | Risk user identification method and device, storage medium and electronic equipment | |
| CN111401478A (en) | Data abnormity identification method and device | |
| CN110929153A (en) | Personalized start page pushing method, device and system | |
| CN115329203A (en) | Content recommendation method and apparatus | |
| CN115983907A (en) | Data recommendation method and device, electronic equipment and computer readable medium | |
| US10225406B1 (en) | Method, apparatus and computer program product for determining whether to establish a call in a click-to-call environment | |
| CN111488180A (en) | Service information processing method and device, electronic equipment and storage medium | |
| CN110599135B (en) | Method and device for evaluating third party payment account of user and electronic equipment | |
| Androulidakis et al. | Surveying users' practices regarding mobile phones' security features | |
| CN109831417A (en) | Method, apparatus, server and the storage medium of anti-harassment processing account number |
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 |