CN111209477A - Information recommendation method and device, electronic equipment and storage medium - Google Patents
Information recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111209477A CN111209477A CN201911423248.8A CN201911423248A CN111209477A CN 111209477 A CN111209477 A CN 111209477A CN 201911423248 A CN201911423248 A CN 201911423248A CN 111209477 A CN111209477 A CN 111209477A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- recall
- target
- user side
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000013598 vector Substances 0.000 claims abstract description 121
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012163 sequencing technique Methods 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 embodiment of the application provides a method and a device for recommending information, electronic equipment and a storage medium, wherein the method comprises the following steps: when a user request is received, user side characteristics corresponding to the user request are obtained; generating a plurality of user side sub-vectors corresponding to the user side features by adopting a preset user side network, wherein each user side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight; adopting the recall target weight to form a user side vector by the plurality of user side sub-vectors; and searching target information matched with the user lateral quantity from a preset information database, and recommending the target information to the user. According to the method and the device, information recommendation of multiple recall targets is combined, the recall targets can be adjusted in time when the business turns, and resource waste caused by retraining is avoided.
Description
Technical Field
The present application relates to the field of information recommendation, and in particular, to a method and an apparatus for information recommendation, an electronic device, and a storage medium.
Background
With the development of internet technology, information resources are explosively increased, and personalized recommendation becomes an indispensable basic technology in products such as news, short videos, music and the like.
Taking a short video scene as an example, similarity between a user and a short video is calculated, and then a single recall target is fitted as much as possible by using the similarity, so that a recommended video is obtained, but the recall targets are usually different in different service periods, so that when the recall target changes, retraining according to a new recall target is required, a large amount of resources are consumed, and the recall target is difficult to adjust in time, so that the short video becomes a service-oriented short board.
Disclosure of Invention
In view of the above problems, it is proposed to provide a method and apparatus, an electronic device, and a storage medium for information recommendation that overcome or at least partially solve the above problems, including:
a method of information recommendation, the method comprising:
when a user request is received, user side characteristics corresponding to the user request are obtained;
generating a plurality of user side sub-vectors corresponding to the user side features by adopting a preset user side network, wherein each user side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
adopting the recall target weight to form a user side vector by the plurality of user side sub-vectors;
and searching target information matched with the user lateral quantity from a preset information database, and recommending the target information to the user.
An apparatus for information recommendation, the apparatus comprising:
the user side characteristic acquisition module is used for acquiring user side characteristics corresponding to a user request when the user request is received;
the user side sub-vector generating module is used for generating a plurality of user side sub-vectors corresponding to the user side characteristics by adopting a preset user side network, each user side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
a user side vector composition module, configured to adopt the recall target weight to compose the plurality of user side sub-vectors into a user side vector;
and the information recommendation module is used for searching target information matched with the user lateral quantity from a preset information database and recommending the target information to the user.
An electronic device comprising a processor, a memory and a computer program stored on the memory and being executable on the processor, the computer program, when being executed by the processor, realizing the steps of the method of information recommendation as described above.
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 of information recommendation as set forth above.
The embodiment of the application has the following advantages:
in the embodiment of the application, when a user request is received, user side features corresponding to the user request are obtained, a preset user side network is adopted, a plurality of user side sub-vectors corresponding to the user side features are generated, each user side sub-vector corresponds to a recall target, each recall target corresponds to a recall target weight, then the recall target weights are adopted, the user side sub-vectors form the user side vectors, target information matched with the user side vectors is searched from a preset information database, and the target information is recommended to a user, so that information recommendation combining the plurality of recall targets is realized, the recall targets can be adjusted in time when the service turns, and waste of resources is avoided.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings needed to be used in the description of the present application will be briefly introduced below, and it is apparent 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 labor.
FIG. 1 is a flow chart illustrating steps of a method for information recommendation provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of a system for information recommendation provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a network for information recommendation provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an information recommendation apparatus according to an embodiment of the present application.
Detailed Description
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. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a flowchart illustrating steps of a method for information recommendation provided in an embodiment of the present application is shown, which may specifically include the following steps:
as an example, the user-side features may include any one or more of:
user attribute characteristics, information preference characteristics.
In products such as news, short videos, music, etc., in response to a User (User) operation, such as turning on a short video client, the client may generate a User request and send the User request to the server.
After receiving the user request, the server may generate a user-side feature corresponding to the user request, where the user-side feature may include features such as user attributes and information preferences.
The user attribute can be basic data of the user, such as age, gender, location and the like, and the information preference can be operation data of the user on the information, such as clicking, sharing, commenting, playing time and the like.
102, generating a plurality of user side sub-vectors corresponding to the user side features by adopting a preset user side network, wherein each user side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
as an example, the target information may include any one or more of:
news, short videos, music.
As an example, the recall target may include the following:
click, share, comment, play duration.
In a specific implementation, a plurality of recall targets may be preset, then a user-side Network is trained according to the recall targets, the user-side Network may be a Network model using a Neural Network algorithm, such as DNN (Deep Neural Network), and a recall target weight corresponding to each recall target may be set according to a current service period.
After the user side features are obtained, the user side features can be input into a trained user side network, and the user side network can generate user side subvectors corresponding to each recall target by adopting the user side features.
In an embodiment of the present application, the method may further include the steps of:
and obtaining a plurality of sample user side characteristics, and training the plurality of sample user side characteristics according to the plurality of recall targets to obtain a user side network.
In a specific implementation, as shown in fig. 2, the information recommendation may be composed of a feature extraction module, an offline training module, and an online service system, the original features are obtained by collecting logs, the feature extraction module may obtain a plurality of sample user-side features from the original features, and then the obtained plurality of sample user-side features may be trained offline according to a plurality of recall targets to obtain a user-side network.
And the information can be released after the user side network is obtained, and then online information recommendation can be completed through feature service, recall service and sequencing service in the online service system.
103, combining the plurality of user side sub-vectors into a user side vector by adopting the recall target weight;
after the user-side subvectors are obtained, a plurality of user-side subvectors can be weighted by adopting the recall target weight, and then the weighted user-side subvectors form the user-side vectors.
In an embodiment of the present application, step 103 may include the following sub-steps:
weighting the plurality of user-side subvectors by respectively adopting the recall target weights; establishing connection for the weighted plurality of user side sub-vectors to obtain a user side vector;
in practical application, the weight of the recall target can be set by background staff, and for a plurality of user-side sub-vectors corresponding to each recall target, the weight of the recall target can be adopted for weighting, so that the weighted plurality of user-side sub-vectors are connected to obtain the user-side vector.
For example, there are 3 recall targets l1, l2, l3 with recall target weights W1, W2, W3, respectively, and user-side subvectors generated using the user-side network are UV1, UV2, UV3, respectively, then the user-side vector UV-UV 1W 1 concatauv 2W 2 concatant UV 3W 3 can be determined.
Wherein ". x" may characterize each dimension in the vector multiplied by a weight, respectively, "concat" may characterize the vector being concatenated.
And 104, searching target information matched with the user lateral quantity from a preset information database, and recommending the target information to the user.
In a specific implementation, a plurality of pieces of information (Item) can be stored in a preset information database, and after a user side vector is obtained, target information matched with the user side vector can be searched from the user side vector, and then the target information can be pushed to a client, so that a user can view the target information in the client.
In an embodiment of the present application, the method may further include the steps of:
for the information in the information database, acquiring information side characteristics corresponding to the information; generating a plurality of information side sub-vectors corresponding to the information side features by adopting a preset information side network, wherein each information side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight; and adopting the recall target weight to form the information side sub-vectors into the information side vectors.
As an example, the information-side Network may be a Network model that employs a neural Network algorithm, such as DNN (deep neural Network).
For each piece of information stored in the information database, the information side feature corresponding to the information can be acquired, then a plurality of information side sub-vectors corresponding to the information side feature can be generated by adopting a preset information side network, and then the plurality of information side sub-vectors are combined into the information side vector by adopting the recall target weight.
In an embodiment of the present application, the step of combining the plurality of information-side sub-vectors into an information-side vector by using the recall target weight may include the following sub-steps:
weighting the plurality of information side sub-vectors by respectively adopting the recall target weight; and establishing connection for the weighted information side sub-vectors to obtain the information side vector.
In practical application, for a plurality of information side sub-vectors corresponding to each recall target, the recall target weight may be adopted for weighting, and then the weighted plurality of information side sub-vectors are connected to obtain the information side vector.
In an embodiment of the present application, the method may further include the steps of:
and acquiring a plurality of sample information side characteristics, and training the sample information side characteristics according to the plurality of recall targets to obtain an information side network.
In specific implementation, the original features can be obtained by collecting logs, the feature extraction module can obtain a plurality of sample information side features from the original features, and then the obtained plurality of sample information side features can be trained offline according to a plurality of recall targets to obtain an information side network.
In an embodiment of the present application, step 104 may include the following sub-steps:
for a plurality of pieces of information in a preset information database, respectively carrying out similarity calculation on the user side vector and the information side vector to obtain a plurality of recall target similarities; and sorting the plurality of information according to the recall target similarity, and selecting one or more pieces of information sorted in the front as target information.
Because the user side vector and the information side vector are obtained, the recall target similarity between the user and the plurality of information can be obtained by adopting a mode of calculating Euclidean distance, then the plurality of information can be sequenced according to the recall target similarity, and one or more pieces of information sequenced at the front are selected as target information to recommend the target information.
In an embodiment of the present application, the step of calculating the similarity between the user-side vector and the information-side vector to obtain the similarity of the plurality of recall targets may include the following sub-steps:
calculating the Euclidean distance between the user side vector and the information side vector; and determining the similarity of the recall target by adopting the Euclidean distance.
Taking 3 recall targets as an example, as shown in fig. 3, in the offline stage, feature normalization is performed on input features, User _ input and Item _ input, so as to obtain User _ normal _ input and Item _ normal _ input, and then through full connection and relu activation, three hidden layers h1_ User, h2_ User and h3_ User are obtained, so as to train to obtain a User side network and an Item side network which fit in 3 recall targets, User _ vec _ task.
Correspondingly, in the online stage, the target similarity can be recalled by calculating the Euclidean distance between the user side vector and the information side vector, then adopting the Euclidean distance and combining a Sigmoid function, and further adopting the recall target similarity to determine matched target information so as to recommend the matched target information to the user.
In an embodiment of the present application, the method may further include the following steps:
and carrying out normalization processing on the user side characteristics.
Because the input features are normalized in the training process of the user side network and the information side network, the user side features can be normalized after the user side features are obtained.
In an embodiment of the present application, the method may further include the steps of:
and adjusting the weight of the recall target corresponding to the recall target.
Because the recall targets are different in different service periods, that is, under the condition of service steering, the weight of the recall target corresponding to the recall target can be adjusted, for example, a video with a long playing time is considered to be favored by users at first, and then revenue is created for the platform, the weight of the recall target with the long playing time is set to be larger, and a video with comments is considered to be favored by users at present, and the weight of the recall target with the comments is set to be larger.
Due to the adjustment of the weight of the recall target, the adjusted weight of the recall target can be adopted to form a user side vector by a plurality of user side sub-vectors, namely the user side vector is adjusted, and the adjusted weight of the recall target is adopted to form an information side vector by a plurality of information side sub-vectors, namely the information side vector is adjusted, so that the information matched with the adjusted recall target can be obtained, and the retraining of the network model is avoided.
In the embodiment of the application, when a user request is received, user side features corresponding to the user request are obtained, a preset user side network is adopted, a plurality of user side sub-vectors corresponding to the user side features are generated, each user side sub-vector corresponds to a recall target, each recall target corresponds to a recall target weight, then the recall target weights are adopted, the user side sub-vectors form the user side vectors, target information matched with the user side vectors is searched from a preset information database, and the target information is recommended to a user, so that information recommendation combining the plurality of recall targets is realized, the recall targets can be adjusted in time when the service turns, and resource waste is avoided.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the embodiments. Further, those skilled in the art will also appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the embodiments of the application.
Referring to fig. 4, a schematic structural diagram of an information recommendation apparatus provided in an embodiment of the present application is shown, which may specifically include the following modules:
a user-side feature obtaining module 401, configured to obtain, when a user request is received, a user-side feature corresponding to the user request;
a user-side sub-vector generating module 402, configured to generate, by using a preset user-side network, a plurality of user-side sub-vectors corresponding to the user-side features, where each user-side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
a user-side vector composing module 403, configured to compose the plurality of user-side sub-vectors into a user-side vector by using the recall target weight;
and the information recommending module 404 is configured to search target information matched with the user lateral quantity from a preset information database, and recommend the target information to the user.
In an embodiment of the present application, the method further includes:
the information side characteristic acquisition module is used for acquiring information side characteristics corresponding to the information for the information in the information database;
the information side sub-vector generating module is used for generating a plurality of information side sub-vectors corresponding to the information side characteristics by adopting a preset information side network, each information side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
and the information side vector forming module is used for forming the information side vectors by the plurality of information side sub-vectors by adopting the recall target weight.
In an embodiment of the present application, the user-side vector composing module 403 includes:
the user side weighting submodule is used for weighting the plurality of user side sub-vectors by respectively adopting the recall target weights;
the user side establishing connection submodule is used for establishing connection for the weighted plurality of user side sub-vectors to obtain user side vectors;
the information lateral quantity composition module comprises:
the information side weighting submodule is used for weighting the plurality of information side subvectors by respectively adopting the recall target weights;
and the information side connection establishing submodule is used for establishing connection for the weighted information side sub-vectors to obtain the information side vectors.
In an embodiment of the present application, the information recommendation module 404 includes:
a recall target similarity obtaining submodule, configured to perform similarity calculation on the user side vector and the information side vector, respectively, for a plurality of pieces of information in a preset information database, so as to obtain a plurality of recall target similarities;
and the sorting and selecting submodule is used for sorting the plurality of information according to the recall target similarity and selecting one or more pieces of information sorted in the front as target information.
In an embodiment of the present application, the recall target similarity obtaining sub-module includes:
the Euclidean distance calculating unit is used for calculating the Euclidean distance between the user side vector and the information side vector;
and the recall target similarity determining unit is used for determining the similarity of the recall target by adopting the Euclidean distance.
In an embodiment of the present application, the method further includes:
and the weight adjusting module is used for adjusting the weight of the recall target corresponding to the recall target.
In an embodiment of the present application, the method further includes:
the user side network training module is used for acquiring a plurality of sample user side characteristics and training the plurality of sample user side characteristics according to the plurality of recall targets to obtain a user side network;
and the information side network training module is used for acquiring a plurality of sample information side characteristics and training the sample information side characteristics according to the plurality of recall targets to obtain an information side network.
In an embodiment of the present application, the method further includes:
and the normalization processing module is used for performing normalization processing on the user side characteristics.
In an embodiment of the application, the user-side features include any one or more of:
user attribute characteristics, information preference characteristics.
In an embodiment of the application, the target information includes any one or more of the following:
news, short videos, music;
the recall target includes a plurality of:
click, share, comment, play duration.
In an embodiment of the present application, the user-side network and/or the information-side network are network models that employ a neural network algorithm.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
An embodiment of the present application also provides an electronic device, which may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for recommending information as above.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above information recommendation method.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and apparatus for information recommendation, the electronic device, and the storage medium provided above are introduced in detail, and a specific example is applied in the present disclosure to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (14)
1. A method for information recommendation, the method comprising:
when a user request is received, user side characteristics corresponding to the user request are obtained;
generating a plurality of user side sub-vectors corresponding to the user side features by adopting a preset user side network, wherein each user side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
adopting the recall target weight to form a user side vector by the plurality of user side sub-vectors;
and searching target information matched with the user lateral quantity from a preset information database, and recommending the target information to the user.
2. The method of claim 1, further comprising:
for the information in the information database, acquiring information side characteristics corresponding to the information;
generating a plurality of information side sub-vectors corresponding to the information side features by adopting a preset information side network, wherein each information side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
and adopting the recall target weight to form the information side sub-vectors into the information side vectors.
3. The method of claim 2, wherein the step of using the recall target weight to form the plurality of user-side subvectors into a user-side vector comprises:
weighting the plurality of user-side subvectors by respectively adopting the recall target weights;
establishing connection for the weighted plurality of user side sub-vectors to obtain a user side vector;
the step of using the recall target weight to form the information-side sub-vectors into information-side vectors comprises:
weighting the plurality of information side sub-vectors by respectively adopting the recall target weight;
and establishing connection for the weighted information side sub-vectors to obtain the information side vector.
4. The method according to claim 2 or 3, wherein the step of searching for target information matching the user lateral quantity from a preset information database comprises:
for a plurality of pieces of information in a preset information database, respectively carrying out similarity calculation on the user side vector and the information side vector to obtain a plurality of recall target similarities;
and sorting the plurality of information according to the recall target similarity, and selecting one or more pieces of information sorted in the front as target information.
5. The method of claim 4, wherein the step of calculating the similarity between the user-side vector and the information-side vector to obtain a plurality of recall target similarities comprises:
calculating the Euclidean distance between the user side vector and the information side vector;
and determining the similarity of the recall target by adopting the Euclidean distance.
6. The method of claim 1, 2 or 3, further comprising:
and adjusting the weight of the recall target corresponding to the recall target.
7. The method of claim 1, further comprising:
obtaining a plurality of sample user side characteristics, and training the plurality of sample user side characteristics according to the plurality of recall targets to obtain a user side network;
and acquiring a plurality of sample information side characteristics, and training the sample information side characteristics according to the plurality of recall targets to obtain an information side network.
8. The method of claim 1, further comprising:
and carrying out normalization processing on the user side characteristics.
9. The method of claim 1, wherein the user-side features comprise any one or more of:
user attribute characteristics, information preference characteristics.
10. The method of claim 1, wherein the target information comprises any one or more of:
news, short videos, music;
the recall target includes a plurality of:
click, share, comment, play duration.
11. The method according to claim 2, characterized in that the user-side network and/or the information-side network are network models employing neural network algorithms.
12. An apparatus for information recommendation, the apparatus comprising:
the user side characteristic acquisition module is used for acquiring user side characteristics corresponding to a user request when the user request is received;
the user side sub-vector generating module is used for generating a plurality of user side sub-vectors corresponding to the user side characteristics by adopting a preset user side network, each user side sub-vector corresponds to a recall target, and each recall target corresponds to a recall target weight;
a user side vector composition module, configured to adopt the recall target weight to compose the plurality of user side sub-vectors into a user side vector;
and the information recommendation module is used for searching target information matched with the user lateral quantity from a preset information database and recommending the target information to the user.
13. An electronic device, comprising a processor, a memory and a computer program stored on the memory and being executable on the processor, the computer program, when executed by the processor, implementing the steps of the method of information recommendation according to any one of claims 1 to 11.
14. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method of information recommendation according to any one of claims 1 to 11.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911423248.8A CN111209477B (en) | 2019-12-31 | 2019-12-31 | Information recommendation method and device, electronic equipment and storage medium |
| PCT/CN2020/129863 WO2021135701A1 (en) | 2019-12-31 | 2020-11-18 | Information recommendation method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911423248.8A CN111209477B (en) | 2019-12-31 | 2019-12-31 | Information recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111209477A true CN111209477A (en) | 2020-05-29 |
| CN111209477B CN111209477B (en) | 2023-06-09 |
Family
ID=70788488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911423248.8A Active CN111209477B (en) | 2019-12-31 | 2019-12-31 | Information recommendation method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111209477B (en) |
| WO (1) | WO2021135701A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949703A (en) * | 2021-02-23 | 2021-06-11 | 广州市百果园信息技术有限公司 | Video recall method and device and electronic equipment |
| WO2021135701A1 (en) * | 2019-12-31 | 2021-07-08 | 百果园技术(新加坡)有限公司 | Information recommendation method and apparatus, electronic device, and storage medium |
| CN113379449A (en) * | 2021-05-31 | 2021-09-10 | 北京达佳互联信息技术有限公司 | Multimedia resource recall method and device, electronic equipment and storage medium |
| CN113468347A (en) * | 2021-07-26 | 2021-10-01 | 北京明略软件系统有限公司 | Method and device for data recall, electronic equipment and readable storage medium |
| CN114677168A (en) * | 2022-03-11 | 2022-06-28 | 百果园技术(新加坡)有限公司 | Resource recommendation method, device, equipment and medium |
| WO2023005419A1 (en) * | 2021-07-29 | 2023-02-02 | 北京快乐茄信息技术有限公司 | Target information recommendation method and apparatus, electronic device, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399563A (en) * | 2019-08-05 | 2019-11-01 | 中国人民解放军军事科学院评估论证研究中心 | A kind of preference pattern and customized information active recommended method based on user behavior analysis |
| CN110427463A (en) * | 2019-08-08 | 2019-11-08 | 腾讯科技（深圳）有限公司 | Search statement response method, device and server and storage medium |
| CN110543598A (en) * | 2019-09-06 | 2019-12-06 | 腾讯科技（深圳）有限公司 | information recommendation method and device and terminal |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10657575B2 (en) * | 2017-01-31 | 2020-05-19 | Walmart Apollo, Llc | Providing recommendations based on user-generated post-purchase content and navigation patterns |
| CN107862022B (en) * | 2017-10-31 | 2020-12-11 | 中国科学院自动化研究所 | Culture resource recommendation system |
| CN108182621A (en) * | 2017-12-07 | 2018-06-19 | 合肥美的智能科技有限公司 | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium |
| CN111209477B (en) * | 2019-12-31 | 2023-06-09 | 广州市百果园信息技术有限公司 | Information recommendation method and device, electronic equipment and storage medium |
-
2019
- 2019-12-31 CN CN201911423248.8A patent/CN111209477B/en active Active
-
2020
- 2020-11-18 WO PCT/CN2020/129863 patent/WO2021135701A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399563A (en) * | 2019-08-05 | 2019-11-01 | 中国人民解放军军事科学院评估论证研究中心 | A kind of preference pattern and customized information active recommended method based on user behavior analysis |
| CN110427463A (en) * | 2019-08-08 | 2019-11-08 | 腾讯科技（深圳）有限公司 | Search statement response method, device and server and storage medium |
| CN110543598A (en) * | 2019-09-06 | 2019-12-06 | 腾讯科技（深圳）有限公司 | information recommendation method and device and terminal |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021135701A1 (en) * | 2019-12-31 | 2021-07-08 | 百果园技术(新加坡)有限公司 | Information recommendation method and apparatus, electronic device, and storage medium |
| CN112949703A (en) * | 2021-02-23 | 2021-06-11 | 广州市百果园信息技术有限公司 | Video recall method and device and electronic equipment |
| CN113379449A (en) * | 2021-05-31 | 2021-09-10 | 北京达佳互联信息技术有限公司 | Multimedia resource recall method and device, electronic equipment and storage medium |
| CN113468347A (en) * | 2021-07-26 | 2021-10-01 | 北京明略软件系统有限公司 | Method and device for data recall, electronic equipment and readable storage medium |
| WO2023005419A1 (en) * | 2021-07-29 | 2023-02-02 | 北京快乐茄信息技术有限公司 | Target information recommendation method and apparatus, electronic device, and storage medium |
| CN114677168A (en) * | 2022-03-11 | 2022-06-28 | 百果园技术(新加坡)有限公司 | Resource recommendation method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111209477B (en) | 2023-06-09 |
| WO2021135701A1 (en) | 2021-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111209477B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| WO2017096877A1 (en) | Recommendation method and device | |
| CN108108821A (en) | Model training method and device | |
| CN111061946A (en) | Scenario content recommendation method and device, electronic equipment and storage medium | |
| CN111506820B (en) | Recommendation model, recommendation method, recommendation device, recommendation equipment and recommendation storage medium | |
| CN110532469B (en) | Information recommendation method, device, equipment and storage medium | |
| KR101804967B1 (en) | Method and system to recommend music contents by database composed of user's context, recommended music and use pattern | |
| CN111444380B (en) | Music search ordering method, device, equipment and storage medium | |
| CN111046188A (en) | User preference degree determining method and device, electronic equipment and readable storage medium | |
| CN112100504A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN108540860B (en) | Video recall method and device | |
| CN111883131B (en) | Voice data processing method and device | |
| CN110598105A (en) | Recommendation method, device, equipment and medium based on probability sampling | |
| CN112100221A (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN112085058A (en) | Object combination recall method and device, electronic equipment and storage medium | |
| CN108628886B (en) | Audio file recommendation method and device | |
| CN111241381A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN112182281B (en) | Audio recommendation method, device and storage medium | |
| CN115618024A (en) | Multimedia recommendation method and device and electronic equipment | |
| CN111143670A (en) | Information determination method and related product | |
| CN112269943B (en) | Information recommendation system and method | |
| CN108932262B (en) | Song recommendation method and device | |
| CN113836390A (en) | Resource recommendation method and device, computer equipment and storage medium | |
| CN110827078A (en) | Information recommendation method, device, equipment and storage medium | |
| CN114422824A (en) | Data processing method, video processing method, display method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231007 Address after: 31a, 15th floor, building 30, maple commercial city, bangrang Road, Brazil Patentee after: Baiguoyuan Technology (Singapore) Co.,Ltd. Address before: 511400 floor 5-13, West Tower, building C, 274 Xingtai Road, Shiqiao street, Panyu District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU BAIGUOYUAN INFORMATION TECHNOLOGY Co.,Ltd. |