CN109033149B - Information recommendation method and device, server and storage medium - Google Patents
Information recommendation method and device, server and storage medium Download PDFInfo
- Publication number
- CN109033149B CN109033149B CN201810601202.XA CN201810601202A CN109033149B CN 109033149 B CN109033149 B CN 109033149B CN 201810601202 A CN201810601202 A CN 201810601202A CN 109033149 B CN109033149 B CN 109033149B
- Authority
- CN
- China
- Prior art keywords
- user
- terminal
- log data
- label
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an information recommendation method, an information recommendation device, a server and a storage medium, wherein the method comprises the following steps: when detecting that a first terminal is connected with a second terminal through multi-screen interaction, acquiring single-user internet log data of the first terminal and multi-user internet log data of the second terminal; generating a user portrait corresponding to both the first terminal and the second terminal according to the single-user internet log data and the multi-user internet log data; when the multi-screen interaction connection disconnection between the first terminal and the second terminal is detected, acquiring current internet log data of the second terminal; matching the current internet log data with at least one user image corresponding to the second terminal; determining a target user portrait with the matching degree larger than a preset threshold value; and recommending target information to the second terminal according to the target user image. According to the invention, an accurate user portrait can be generated according to the log data of the internet access during multi-screen interactive connection, so that accurate information recommendation is carried out, and the accuracy of information recommendation is improved.
Description
Technical Field
The present invention relates to the field of computer processing technologies, and in particular, to an information recommendation method, apparatus, server, and storage medium.
Background
With the development of the internet, people have more and more lives which are closely connected with the internet. In this fast-paced age, users want to be able to find their own desired products quickly through the internet, but huge amounts of product data are constantly generated in the internet every day, which makes it difficult for internet users to find their desired or interested information quickly.
In order to allow a user to quickly find information and products of interest, a conventional information recommendation method is to recommend products (e.g., goods) or information (e.g., videos, short videos, advertisements, etc.) according to user history information (e.g., purchase history, play history, search history, etc.) recorded on a terminal device.
However, when a terminal device may be a multi-user shared device (i.e. a device that can be used by multiple users in a cross-way), such as a television, a computer, etc., the history information recorded therein covers usage records of multiple users (e.g. a couple uses a television by two people, and the usage records include those of the husband and the wife). When information recommendation is performed through the user history information on the terminal device, the recommendation accuracy is generally low.
Therefore, the information recommendation method in the conventional technology generally has the problems of low information recommendation accuracy and poor recommendation effect.
Disclosure of Invention
The invention provides an information recommendation method, an information recommendation device, a server and a storage medium, and aims to solve the problems of low information recommendation accuracy and poor recommendation effect of an information recommendation method in the prior art.
In order to solve the above problem, in a first aspect, an embodiment of the present invention provides an information recommendation method, where the method includes:
when detecting that a first terminal is in multi-screen interactive connection with a second terminal, acquiring single-user internet log data of the first terminal and multi-user internet log data of the second terminal, wherein the first terminal is a personal device, the second terminal is a multi-user shared device, and the multi-user internet log data comprises internet log data generated when users of at least two first terminals use the second terminal;
generating a user portrait corresponding to the first terminal and the second terminal according to the single-user internet log data and the multi-user internet log data;
when the multi-screen interaction connection disconnection between the first terminal and the second terminal is detected, acquiring current internet log data of the second terminal;
matching the current internet log data with at least one user image corresponding to the second terminal;
determining a target user portrait with the matching degree larger than a preset threshold value;
and recommending target information to the second terminal according to the target user figure.
Optionally, the generating a user portrait corresponding to both the first terminal and the second terminal according to the single-user internet log data and the multi-user internet log data includes:
extracting attribute features of the single-user internet log data to obtain first attribute features corresponding to the first terminal;
extracting attribute features of the multi-user internet log data to obtain second attribute features corresponding to the second terminal;
respectively matching the first attribute feature and the second attribute feature with attribute features in a preset multi-dimensional label library, and determining a first label corresponding to the first attribute feature and a second label corresponding to the second attribute feature, wherein the preset multi-dimensional label library comprises a corresponding relation between a trained label and the attribute features;
and constructing a user portrait corresponding to the first terminal and the second terminal according to a same first target tag in the first tag and the second tag, wherein the user portrait comprises the first target tag.
Optionally, the matching the current internet log data with at least one user portrait corresponding to the second terminal includes:
extracting attribute features of the current internet log data to obtain target attribute features corresponding to the second terminal;
matching the target attribute features with attribute features in the preset multi-dimensional label library, and determining a second target label corresponding to the target attribute features;
matching the second target tag with the first target tag of each user portrait corresponding to the second terminal respectively, wherein the second terminal corresponds to at least one user portrait;
the determining of the target user portrait with the matching degree greater than the preset threshold value includes:
and determining a target user portrait corresponding to a first target label of which the matching degree of the second target label is greater than a preset threshold value in at least one user portrait corresponding to the second terminal.
In a second aspect, an embodiment of the present invention further provides an information recommendation apparatus, where the apparatus includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring single-user internet log data of a first terminal and multi-user internet log data of a second terminal when detecting that the first terminal and the second terminal are in multi-screen interactive connection, the first terminal is personal equipment, the second terminal is multi-user shared equipment, and the multi-user internet log data comprises internet log data generated when users of at least two first terminals use the second terminal;
the generating module is used for generating a user portrait corresponding to the first terminal and the second terminal according to the single-user internet log data and the multi-user internet log data;
the second acquisition module is used for acquiring current internet log data of the second terminal when the multi-screen interaction connection disconnection between the first terminal and the second terminal is detected;
the matching module is used for matching the current internet log data with at least one user image corresponding to the second terminal;
the determining module is used for determining the target user portrait with the matching degree larger than a preset threshold value;
and the recommending module is used for recommending target information to the second terminal according to the target user portrait.
Optionally, the generating module includes:
the first extraction submodule is used for extracting attribute characteristics of the single-user internet log data to obtain first attribute characteristics corresponding to the first terminal;
the second extraction submodule is used for extracting attribute features of the multi-user internet log data to obtain second attribute features corresponding to the second terminal;
the first matching submodule is used for respectively matching the first attribute feature and the second attribute feature with attribute features in a preset multi-dimensional label library, and determining a first label corresponding to the first attribute feature and a second label corresponding to the second attribute feature, wherein the preset multi-dimensional label library comprises a corresponding relation between a trained label and the attribute features;
and the construction sub-module is used for constructing a user portrait corresponding to the first terminal and the second terminal according to a same first target tag in the first tag and the second tag, wherein the user portrait comprises the first target tag.
Optionally, the matching module comprises:
the third extraction submodule is used for extracting attribute features of the current internet log data to obtain target attribute features corresponding to the second terminal;
the second matching submodule is used for matching the target attribute features with the attribute features in the preset multi-dimensional label library and determining a second target label corresponding to the target attribute features;
the third matching submodule is used for respectively matching the second target label with the first target label of each user portrait corresponding to the second terminal, wherein the second terminal corresponds to at least one user portrait;
the determining module comprises:
and the determining submodule is used for determining a target user portrait corresponding to a first target label of which the matching degree of the second target label is greater than a preset threshold value in at least one user portrait corresponding to the second terminal.
In a third aspect, an embodiment of the present invention further provides a server, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the information recommendation method.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the information recommendation method are implemented.
Compared with the prior art, the invention has the following advantages:
therefore, after a user carries out multi-screen interactive connection on personal equipment and multi-user shared equipment, the method can generate a three-dimensional user portrait for the user, and after the multi-screen interactive connection is disconnected between the personal equipment and the multi-user shared equipment, when the user operates the multi-user shared equipment again, the user portrait corresponding to the user in at least one user portrait corresponding to the multi-user shared equipment can be determined according to current internet log data of the user portrait, so that accurate information recommendation is carried out on the user portrait according to the user portrait, the accuracy of information recommendation is improved, and the recommendation effect is good.
Drawings
FIG. 1 is a flow chart of the steps of an embodiment of a method for information recommendation of the present invention;
fig. 2 is a block diagram of an embodiment of an information recommendation apparatus according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flow chart of steps of an embodiment of an information recommendation method of the present invention is shown, which can be applied to a server alone; the method can also be applied to a plurality of devices respectively, and the method can comprise a first terminal, a second terminal and a server; but may also be applied separately to the second terminal.
The method specifically comprises the following steps:
101, when detecting that a first terminal is in multi-screen interactive connection with a second terminal, acquiring single-user internet log data of the first terminal and multi-user internet log data of the second terminal, wherein the first terminal is a personal device, and the second terminal is a multi-user shared device;
the multi-user internet log data comprises internet log data generated when users of at least two first terminals use the second terminal;
for example, the personal device includes a mobile phone of a user a and a mobile phone of a user B, the multi-user shared device is a television used by both the user a and the user B, and the internet log data on the television includes internet log data generated when the user a uses the television and internet log data generated when the user B uses the television.
Wherein, many screen interaction connect and refer to: two multimedia terminals (such as different common intelligent terminal devices based on different operating systems such as IOS, Android and Symbian, for example, mobile phones, PADs, TVs and the like) are connected through the same WIFI network by using a preset protocol (including but not limited to a flash internet protocol, a Miracast protocol, a DLNA protocol, other proprietary protocols and the like).
Through multi-screen interactive connection, a series of operations such as transmission, analysis, display and control of multimedia (audio, video, picture and the like) contents can be carried out on different multimedia terminals, and the displayed contents can be shared on different multimedia terminals at the same time, so that the multimedia life of a user is enriched.
In popular terms, multi-screen interactive connection means that a first terminal and a second terminal can be connected and converted with each other through special connecting equipment. For example, a movie on a mobile phone can be played on a television, pictures on a tablet computer can be shared on the television, and the content of the computer can be projected on the television for watching.
In this step, when it is detected that the first terminal and the second terminal are connected through the multi-screen interaction explained above (where the first terminal is a personal device, and the second terminal is a multi-user shared device), single-user internet log data of the first terminal and multi-user internet log data of the second terminal may be obtained.
Wherein, the personal device is a personal device used by a single user, such as a personal computer, a personal mobile phone, etc. (here, the internet log data recorded on the personal device by default all belong to the owner of the personal device, even if the owner authorizes others to use the personal device, the internet log data recorded on the personal device by default are in accordance with the watching requirement of the owner); a multi-user shared device is a device that can be shared by multiple users, such as a home television.
The log data of the single-user internet access and the log data of the multi-user internet access are both the log data of the user internet access on the terminal, and the log data of the user internet access and the log data of the multi-user internet access are distinguished and named because the first terminal is used by the same person by default, and the corresponding log data of the internet access corresponds to one user and is called the log data of the single-user internet access; the second terminal is a shared device used by a plurality of users, so that the log data of the internet access thereof corresponds to the plurality of users, and is called multi-user internet log data.
And the internet log data includes, but is not limited to, mobile internet log data, wired/wireless internet log data, and the like.
102, generating a user portrait corresponding to the first terminal and the second terminal according to the single-user internet log data and the multi-user internet log data;
for example, a user corresponding to the first terminal is user a, and users corresponding to the second terminal are user a and user B, so that in the prior art, when a user portrait is formed, a user portrait corresponding to the first terminal is generated mainly by using user history data of the first terminal, so that information recommendation is performed according to the user portrait; and generating a user profile corresponding to the second terminal by using historical data of a plurality of users of the second terminal, thereby performing information recommendation according to the user profile. When information recommendation is performed through the user history data recorded by the single terminal, the generated user portrait cannot completely or accurately express the characteristics of the user using the terminal, so that the problems of low information recommendation accuracy and poor recommendation effect are caused.
In order to solve the above technical problem, in an embodiment of the present invention, when a user image of one user (for example, a user a) is generated on a multi-user shared device side, a user image of the user a (that is, a user image corresponding to both the first terminal and the second terminal, which are personal devices of the user a, or the multi-user shared device-the second terminal, which are commonly used by the user a and the user B, is generated based on log data on a single-user internet access on the personal device of the user a and log data on a multi-user internet access on a multi-user shared device including the user a in a user group, that is, internet access log data of a plurality of terminals used by the same user.
Similarly, when the user B uses its own personal device to perform multi-screen interactive connection with the multi-user shared device (the device shared by the user a and the user B), the method of the embodiment of the present invention may also generate a user portrait of the user B on the side of the multi-user shared device according to the log data of internet access recorded on the two devices, where the user portrait corresponds to both the personal device of the user B and the multi-user shared device used by the user a and the user B.
Thus, by means of the method of the embodiment of the present invention, the user portrait a dedicated to the user a is generated for the multiple user shared device in combination with the internet log data of the user a on the personal device a and the multiple user shared device (the user group includes the user a and the user B); similarly, a user representation B specific to that user B may also be generated for a multi-user shared device, and so on.
The implementation method for step 102 may be implemented by any one of known methods, and the method for generating a user portrait by using user online log data is not limited to this, and the method for generating a user portrait according to an embodiment of the present invention is shown here, and specifically may include the following sub-steps:
s21, extracting attribute features of the single-user internet log data to obtain a first attribute feature corresponding to the first terminal;
s22, extracting attribute features of the multi-user internet log data to obtain second attribute features corresponding to the second terminal;
by extracting the attribute features of the log data of the internet surfing, the attribute features of the user using the terminal can be obtained. Wherein the first attribute characteristic is for a user, such as user a. And the second attribute features correspond to a plurality of users, including user a and user B, for example.
The attribute characteristics of the user refer to key information that can identify the characteristics of the user.
In the embodiment of the invention, when the attribute feature extraction is performed on the internet log data, the feature extraction can be respectively performed on the two internet log data in an online (real-time) and offline combined mode, so that the attribute feature of the user is obtained. The online processing mode can only process the current internet log data, and the offline processing mode can be combined with the historical storage data for analysis and processing, so that the user attribute features which are not extracted in the online processing mode can be supplemented and perfected.
The internet log data are processed in an online and offline processing mode, so that the current data and the historical data can be subjected to associated mining analysis, and the extracted user attribute features are more comprehensive and complete.
S23, matching the first attribute feature and the second attribute feature with attribute features in a preset multi-dimensional label library respectively, and determining a first label corresponding to the first attribute feature and a second label corresponding to the second attribute feature, wherein the preset multi-dimensional label library comprises a corresponding relation between a trained label and the attribute features;
in the embodiment of the present invention, the multidimensional tag library refers to a general name of combining a plurality of different feature libraries. The feature library is formed by corresponding relations of labels and attribute features obtained by analyzing and counting big data and continuously training. Wherein the tag may be multi-dimensional.
In one embodiment, the embodiment of the invention can integrate the statistics of the user internet behavior rules, the APP usage rules, the user internet content feature word extraction and the mobile phone terminal information in advance to form a multidimensional label library of multidimensional portrait analysis features.
For example, analyzing and counting the internet surfing log data of all users, determining that the visited website contains a predetermined field as a tourism website, taking all websites containing the predetermined field as attribute features of the tourism website, and taking tourism as a label corresponding to the attribute features, and then forming a huge multi-dimensional label library by continuously carrying out operations such as user internet surfing behavior rule statistics, APP usage rule statistics, user internet surfing content feature word extraction and the like.
When the attribute features extracted from the internet log data are matched with the attribute features in the multi-dimensional label library, as long as the website accessed by the user belongs to the website containing the preset field, the condition that one label of the user is 'travel' can be obtained through the matching of the multi-dimensional label library. In the matching process with the multidimensional label library, labels with multiple dimensions can be obtained, so that the multidimensional labels are obtained.
For example, user a has searched for website 1, website 2, and website 3 on a personal device. And the websites of the three websites all include a certain field specific to the travel website, the method of the embodiment of the present invention can match the website 1, the website 2, and the website 3 with the attribute features in the multidimensional tag library, and then find that the three attribute features all correspond to the tag "travel" through matching, so that the tag "travel" is a tag matched with the three attribute features.
In this embodiment, the first attribute features of the user a from the personal device may be respectively matched with the attribute features in the preset multi-dimensional tag library, so as to determine a first tag matched with the first attribute features (where, since one tag in the multi-dimensional tag library may correspond to multiple attribute features, different attribute features may be matched to the same tag); wherein the number of the first labels is one or more.
Similarly, second attribute features from the multi-user shared device, which embody internet access features of multiple users, may be respectively matched with attribute features in a preset multi-dimensional tag library, so as to determine a second tag matched with the second attribute features. Wherein the number of the second labels is one or more.
In addition, in an embodiment, the multidimensional tag library in the embodiment of the present invention includes, but is not limited to, an operator basic information library, a terminal type basic library, an application classification library, a Uniform Resource Locator (URL) classification library, an accessed website and behavior rule statistical feature library, an internet content clustering result library, a user group classification library, a named entity identification content extraction library, a dynamic tag classification management library, an internet website feature library, a historical user interest point, a terminal movement trajectory change library, and the like.
In the embodiment of the invention, the multi-dimensional label of the user is a main element for constructing the user portrait. The multi-dimensional label in the present invention refers to a label reflecting the user characteristics from a plurality of dimensions. The multidimensional labels in the embodiment of the present invention at least include, but are not limited to, a basic attribute label, a social attribute label, an internet behavior attribute label, a behavior habit attribute label, and an interest attribute feature label of a first end user (for example, user a).
Further, the basic attribute tag of the user includes, but is not limited to, one or more of a user name, a user identification, a gender, a nationality, an age block, a scholarly, an occupation, an income level, a user terminal, an international subscriber identity, an international mobile terminal identification code, an affiliated operator, a network type, a home location, a roaming location, a terminal brand type, a terminal model, a terminal operating device, and a terminal-installed application. And social attribute tags include, but are not limited to, one or more of industry, profession, workplace, place of residence, bank card, membership card, and vehicle. The internet behavior attribute tags include but are not limited to browsing, searching, downloading, purchasing, commenting and the like, and the behavior habit attribute tags include but are not limited to average daily internet time, frequently-logged-in websites, frequently-used applications and the like. Interest attribute feature tags include, but are not limited to, sports, music, social, information, shopping, leisure, travel, games, and financing.
The basic attribute label of the user usually represents a static attribute of the user, and is relatively stable information, such as gender, age, and the like. The social attribute, the internet behavior attribute, the behavior habit attribute and the interest attribute feature represent the dynamic attribute of the user and are attributes which change constantly along with time. It is the dynamic attributes that change constantly that can really embody the differentiation characteristics of the user groups.
In specific implementation, the dynamic attribute characteristics of the user can be comprehensively analyzed and determined in the following ways:
1) by counting the daily average internet surfing time of the user, the website (type) that the user frequently logs in to surf the internet, the frequently-used application program APP of the user and the time for using the frequently-used APP, the behavior habit attribute characteristics of the user are analyzed.
2) And comprehensively analyzing the interest attribute characteristics of the user from the aspects of user content preference/fragmented internet surfing time preference/user service preference and the like. Such as different behavior and action behaviors according to the user surfing the internet (e.g., browsing, searching, downloading, purchasing, commenting, etc.), or APP types used by the user (e.g., including various APP applications, frequently visited website types, etc.), or content data generated by the user surfing the internet: and comprehensively analyzing the types of purchased commodities, browsed webpage contents, searched contents, downloaded contents and the like to obtain the interest attribute characteristics of the user. For example, in the internet log data of a user, most of searching and browsing are shopping websites or most of used application programs are shopping applications, shopping can be determined as an interest attribute feature of the user, or most of searching, browsing and commenting of the user are tourism websites or most of used application programs are tourism applications, and then tourism can be determined as an interest attribute feature of the user, and the like.
The tags are typically artificially defined highly refined signatures, such as age-group tags: 25-35 years old, region label: in Beijing, the label exhibits two important features: 1. semantization, people can conveniently understand the meaning of each label. This also makes the user representation model of practical significance. The service requirement can be better met. E.g., determining user preferences. 2. Short texts, each label usually only represents one meaning, and the labels do not need to be subjected to preprocessing work such as excessive text analysis and the like, so that convenience is provided for extracting standardized information by using a machine. So it is understood in this sense that the user representation is the sum of the user tags.
S24, constructing a user portrait corresponding to the first terminal and the second terminal according to the same first target label of the first label and the second label, wherein the user portrait comprises the first target label.
Wherein the same one of the first tag and the second tag, i.e. the first target tag, may be determined. Because the first target tag can embody the browsing characteristics of the user a on the personal device and the multiuser shared device in the above example, the first target tag can be used to construct a user representation corresponding to both the personal device and the multiuser shared device, that is, a representation of the user a on the multiuser shared device.
Similarly, when the user B uses the own mobile phone to be interactively connected with the multiple screens of the television, the method provided by the embodiment of the invention can also construct the portrait of the user B corresponding to both the mobile phone of the user B and the television, so that for the television used by multiple users, the method provided by the embodiment of the invention can independently construct the portrait of the user of the personal equipment when the personal equipment is interactively connected with the multiple screens of the personal equipment, and the television has a plurality of independent portraits of the user.
Through the multi-dimensional labels obtained by matching the multi-dimensional label libraries, namely the first target label, the method provided by the embodiment of the invention can be used for performing association fusion on all labels in the first target label, printing the multi-dimensional labels for the user, or updating and supplementing the printed multi-dimensional labels, so as to complete the construction of the portrait of the user.
Since the user a is an individual user of the first terminal and one of the plurality of users of the second terminal, the user image of the user a generated in this step corresponds to both the first terminal and the second terminal.
In the actual application process, the online log data on the two terminals can be obtained in real time, so that the latest multi-dimensional label of the user A is obtained by analyzing and processing the online log data of the single user/multiple users obtained in real time, the existing multi-dimensional label on the user image is updated or supplemented, and the latest holographic multi-dimensional user image containing the space-time characteristics is depicted.
Thus, the method of the embodiment of the invention can determine the attribute characteristics of a single user on the first terminal by means of two sets of internet log data on the two terminals, and attribute characteristics of a plurality of users on the second terminal, and matching the attribute characteristics of the single user and the attribute characteristics of the plurality of users with the attribute characteristics in a preset multi-dimensional feature library respectively, thereby obtaining a first label corresponding to the first attribute characteristic and a second label corresponding to the second attribute characteristic, and finally, taking the same label in the first label and the second label as the multi-dimensional attribute label of the single user, the generation of the multi-dimensional attribute label is realized by means of the internet log data of two different types of terminals (personal equipment and multi-user shared equipment) used by the single user, the expressed characteristics are more accurate, and the user portrait constructed by the multi-dimensional attribute label is more three-dimensional.
In addition, the method of the embodiment of the invention can also add the attribute characteristics of the user and the corresponding multi-dimensional labels to the multi-dimensional characteristic library when the multi-dimensional labels matched with the attribute characteristics of the user cannot be found in the established multi-dimensional label library. In this way, the multidimensional label library is continuously updated and refined.
With the aid of the methods in step 101 and step 102, as long as the personal device and the multi-user shared device perform multi-screen interactive connection, the method in the embodiment of the present invention can construct a stereoscopic user image of a single user corresponding to the personal device, so that not only a stereoscopic user image corresponding to the single user of the personal device is generated for the personal device, but also a stereoscopic user image corresponding to one of multiple users of the multi-user shared device is generated.
In practical application, a husband and a wife both use a home television, so that when the husband carries out multi-screen interactive connection between the mobile phone of the husband and the home television, the method provided by the embodiment of the invention can generate the user portrait of the husband (the user portrait information is more accurate, and not only the personal mobile phone used by the user but also the internet surfing data when the user uses the television); when the wife connects his mobile phone with the home television in a multi-screen interactive manner, the method of the embodiment of the invention can also generate the user portrait of the wife (the user portrait information is more comprehensive, and not only refers to the personal mobile phone used by the wife, but also refers to the internet surfing data when the wife uses the television). The user portrait label generated by the embodiment of the invention is more comprehensive and has accurate characteristics.
103, when detecting that the multi-screen interaction connection between the first terminal and the second terminal is disconnected, acquiring current internet log data of the second terminal;
in which, for example, the user a disconnects the multi-screen interactive connection between the first terminal (e.g., a personal mobile phone) and the second terminal (e.g., a home television) that the user uses, for example, exits from movie screen projection. The method of the embodiment of the invention can acquire the current internet log data of the family television.
The current internet log data is all data of the current internet operation. For example, to search for search behavior data of a certain tv show on the internet.
104, matching the current internet log data with at least one user image corresponding to the second terminal;
after the screen projection is finished, for example, the user a operates the television, that is, performs a network operation on the second terminal, the method of the embodiment of the present invention may acquire current internet log data corresponding to the network operation, and may match the current internet log data with at least one user portrait corresponding to the television according to a preset algorithm, where the television may correspond to one or more user portraits of users who have used the television.
Since the multi-screen interactive connection with the television set can further include other personal devices, such as a mobile phone of the user B, in the process of performing the step 101 and the step 102, after the step 101 and the step 102, a user representation of the user B can also be generated, where the user representation corresponds to both the personal mobile phone of the user B and the television set. Therefore, when the user a is on the internet after the screen projection is finished, the television can correspond to the user portrait of the user a and the user portrait of the user B, and here, the current internet log data of the user a needs to be matched with the user portrait of the user a and the user portrait of the user B respectively.
the second terminal is a television set shared by multiple users (including user a and user B), and the television set may correspond to user representations of the multiple users, including a user representation of user a and a user representation of user B. In practical application, because the operation behavior of the same user is consistent, the user image of the user a is inevitably the user image of the user a whose matching degree with the current operation data of the user a is greater than the preset threshold value. So in this step, the determined target user representation is the user representation of user A.
Optionally, in one embodiment, when performing step 104, it may be implemented by:
extracting attribute features of the current internet log data to obtain target attribute features corresponding to the second terminal;
for the specific attribute feature extraction principle, reference is made to the above sub-steps S21 and S22, which are not described herein again.
Matching the target attribute features with attribute features in the preset multi-dimensional label library, and determining a second target label corresponding to the target attribute features;
the specific matching principle can refer to the explanation of the above substep S23, which is not described herein again.
Matching the second target tag with the first target tag of each user portrait corresponding to the second terminal respectively, wherein the second terminal corresponds to at least one user portrait;
accordingly, in step 105, a target user portrait corresponding to a first target tag having a matching degree of the second target tag greater than a preset threshold may be determined in at least one user portrait corresponding to the second terminal.
Since the users of the multi-user shared device, such as a television, include user a and user B, and through step 101 and step 102, two user images of user a and user B are generated for the television. In this step, the user tag of the user currently using the television, that is, the second target tag, may be respectively matched with the user tags in the two user images corresponding to the television, for example, the second target tag may be matched with the tags in the image of the user a to obtain a tag matching degree; and matching the second target label with the label in the picture of the user B to obtain a label matching degree. Then, in the two tag matching degrees, the user portrait corresponding to the tag matching degree greater than the preset threshold is selected as the user portrait of the user currently using the television, for example, the user a uses the television to watch television, and then the user portrait of the user a can be matched here.
In this way, the method of the embodiment of the present invention may determine the target user portrait matched with the second target tag by matching the second target tag corresponding to the attribute feature in the current internet log data with the multidimensional tag of each user portrait corresponding to the second terminal. Namely, after the multi-screen interactive connection is carried out between the personal equipment of the user and the multi-user shared equipment, and then the multi-user shared equipment is disconnected, the user operates the multi-user shared equipment again.
And 106, recommending target information to the second terminal according to the target user image.
Because the user portrait has labels with multiple dimensions, and the labels correspond to the user of the user portrait, the target information corresponding to the labels in the user portrait can be directly recommended to the second terminal, and the target information includes but is not limited to video, audio, pictures, commodity purchasing links and the like.
Therefore, after a user carries out multi-screen interactive connection on personal equipment and multi-user shared equipment, the method provided by the embodiment of the invention can generate a three-dimensional user portrait for the user, and after the multi-screen interactive connection between the personal equipment and the multi-user shared equipment is disconnected, when the user operates the multi-user shared equipment again, the user portrait corresponding to the user in at least one user portrait corresponding to the multi-user shared equipment can be determined according to current internet log data of the user portrait, so that accurate information recommendation is carried out on the user portrait according to the user portrait, the accuracy of information recommendation is improved, and the information recommendation effect is good.
Corresponding to the information recommendation method, the embodiment of the invention also provides an information recommendation device, and the device can be completely applied to a cloud server; but also can be applied to a terminal (multi-user shared equipment and personal equipment) partially, and a cloud server partially; but also to the multiple user shared device, i.e. the second terminal.
In this embodiment, a part of the information recommendation device is applied to the terminal, and a part of the information recommendation device is applied to the cloud server. The device can comprise a plurality of user data acquisition modules and a matching module;
in this example, the plurality of user data acquisition modules may be respectively deployed to different terminals, and are configured to complete the acquisition of the internet log data and upload the internet log data to the cloud server; the matching module can be deployed to a cloud server side and used for generating a user portrait by utilizing the collected multi-terminal internet log data, matching a label corresponding to the attribute feature in the current internet log data with the corresponding user portrait and the like, so that a target user portrait is determined, and target information is recommended to the multi-user shared equipment according to the target user portrait.
In another embodiment, the information recommendation device is completely applied to the cloud server side. Namely, the plurality of user data acquisition modules and the matching module are all deployed on the cloud server side, wherein the plurality of user data acquisition modules are respectively used for acquiring the internet log data of different terminals. Other processes are similar to the above embodiments and are not described herein again.
In yet another embodiment, the information recommendation device is fully applied to the second terminal side. The plurality of user data acquisition modules and the matching module are all deployed at the second terminal side, wherein the plurality of user data acquisition modules can comprise a second user data acquisition module for acquiring multi-user internet log data of the second terminal and can also comprise a plurality of first user data acquisition modules for acquiring single-user internet log data of the first terminal; the functions of the modules are similar to the above method applied to the cloud server, and are different only in the execution main body, which is not described herein again.
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 present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Corresponding to the method provided by the embodiment of the present invention, referring to fig. 2, a block diagram of an embodiment of an information recommendation apparatus according to the present invention is shown, and the method may specifically include the following modules:
the first obtaining module 21 is configured to, when it is detected that a first terminal and a second terminal are in multi-screen interactive connection, obtain single-user internet log data of the first terminal and multi-user internet log data of the second terminal, where the first terminal is a personal device, the second terminal is a multi-user shared device, and the multi-user internet log data includes internet log data generated when users of at least two first terminals use the second terminal;
a generating module 22, configured to generate a user portrait corresponding to both the first terminal and the second terminal according to the single-user internet log data and the multi-user internet log data;
the second obtaining module 23 is configured to obtain current internet log data of the second terminal when it is detected that the multi-screen interaction connection between the first terminal and the second terminal is disconnected;
a matching module 24, configured to match the current internet log data with at least one user image corresponding to the second terminal;
a determining module 25, configured to determine a target user portrait with a matching degree greater than a preset threshold;
and the recommending module 26 is used for recommending target information to the second terminal according to the target user figure.
Optionally, the generating module 22 includes:
the first extraction submodule is used for extracting attribute characteristics of the single-user internet log data to obtain first attribute characteristics corresponding to the first terminal;
the second extraction submodule is used for extracting attribute features of the multi-user internet log data to obtain second attribute features corresponding to the second terminal;
the first matching submodule is used for respectively matching the first attribute feature and the second attribute feature with attribute features in a preset multi-dimensional label library, and determining a first label corresponding to the first attribute feature and a second label corresponding to the second attribute feature, wherein the preset multi-dimensional label library comprises a corresponding relation between a trained label and the attribute features;
and the construction sub-module is used for constructing a user portrait corresponding to the first terminal and the second terminal according to a same first target tag in the first tag and the second tag, wherein the user portrait comprises the first target tag.
Optionally, the matching module 24 includes:
the third extraction submodule is used for extracting attribute features of the current internet log data to obtain target attribute features corresponding to the second terminal;
the second matching submodule is used for matching the target attribute features with the attribute features in the preset multi-dimensional label library and determining a second target label corresponding to the target attribute features;
the third matching submodule is used for respectively matching the second target label with the first target label of each user portrait corresponding to the second terminal, wherein the second terminal corresponds to at least one user portrait;
the determination module 25 includes:
and the determining submodule is used for determining a target user portrait corresponding to a first target label of which the matching degree of the second target label is greater than a preset threshold value in at least one user portrait corresponding to the second terminal.
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 invention further provides a server, including: the information recommendation method comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the steps of the information recommendation method according to any one of the above embodiments when being executed by the processor.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the information recommendation method according to any of the above embodiments are implemented.
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 invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention 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 invention 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 invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the invention. 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 invention 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 preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
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 above detailed description is provided for an information recommendation method, an information recommendation apparatus, a server and a computer-readable storage medium, and the specific examples are applied herein to explain the principles and embodiments of the present invention, and the descriptions of the above embodiments are only used to help understand the method and the core ideas of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, 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 invention.
Claims (8)
1. An information recommendation method, comprising:
when detecting that a first terminal is in multi-screen interactive connection with a second terminal, acquiring single-user internet log data of the first terminal and multi-user internet log data of the second terminal, wherein the first terminal is a personal device, the second terminal is a multi-user shared device, and the multi-user internet log data comprises internet log data generated when users of at least two first terminals use the second terminal;
determining a first label of a single user according to the single-user internet log data and a preset label library, and determining a second label of each user in a plurality of users according to the multi-user internet log data and the preset label library;
generating a user representation corresponding to both the first terminal and the second terminal, comprising: constructing a user portrait of the same user corresponding to the first terminal and the second terminal according to a same first target label in the first label and the second label; wherein the user representation includes the first target tag;
when the multi-screen interaction connection between the first terminal and the second terminal is detected to be disconnected, acquiring current internet log data of the second terminal;
matching the current internet log data with at least one user image corresponding to the second terminal;
determining a target user portrait with the matching degree larger than a preset threshold value;
and recommending target information to the second terminal according to the target user figure.
2. The method of claim 1, wherein determining a first tag of a single user according to the single-user online log data and a preset tag library, and determining a second tag of each of a plurality of users according to the multi-user online log data and the preset tag library, comprises:
extracting attribute features of the single-user internet log data to obtain first attribute features corresponding to the first terminal;
extracting attribute features of the multi-user internet log data to obtain second attribute features corresponding to the second terminal;
and matching the first attribute feature and the second attribute feature with attribute features in a preset multi-dimensional label library respectively, and determining a first label corresponding to the first attribute feature and a second label corresponding to the second attribute feature, wherein the preset multi-dimensional label library comprises a corresponding relation between a trained label and the attribute features.
3. The method of claim 2, wherein the matching the current blog data with at least one user profile corresponding to the second terminal comprises:
extracting attribute features of the current internet log data to obtain target attribute features corresponding to the second terminal;
matching the target attribute features with attribute features in the preset multi-dimensional label library, and determining a second target label corresponding to the target attribute features;
matching the second target tag with the first target tag of each user portrait corresponding to the second terminal respectively, wherein the second terminal corresponds to at least one user portrait;
the determining of the target user portrait with the matching degree greater than the preset threshold value includes:
and determining a target user portrait corresponding to a first target label of which the matching degree of the second target label is greater than a preset threshold value in at least one user portrait corresponding to the second terminal.
4. An information recommendation apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring single-user internet log data of a first terminal and multi-user internet log data of a second terminal when detecting that the first terminal and the second terminal are in multi-screen interactive connection, the first terminal is personal equipment, the second terminal is multi-user shared equipment, and the multi-user internet log data comprises internet log data generated when users of at least two first terminals use the second terminal;
the first determining module is used for determining a first label of a single user according to the single-user internet log data and a preset label library, and determining a second label of each user in a plurality of users according to the multi-user internet log data and the preset label library;
a generating module configured to generate a user representation corresponding to both the first terminal and the second terminal, comprising: constructing a user portrait of the same user corresponding to the first terminal and the second terminal according to a same first target label in the first label and the second label; wherein the user representation includes the first target tag;
the second acquisition module is used for acquiring current internet log data of the second terminal when the multi-screen interaction connection disconnection between the first terminal and the second terminal is detected;
the matching module is used for matching the current internet log data with at least one user image corresponding to the second terminal;
the second determination module is used for determining the target user portrait with the matching degree larger than a preset threshold value;
and the recommending module is used for recommending target information to the second terminal according to the target user portrait.
5. The apparatus of claim 4, wherein the first determining module comprises:
the first extraction submodule is used for extracting attribute characteristics of the single-user internet log data to obtain first attribute characteristics corresponding to the first terminal;
the second extraction submodule is used for extracting attribute features of the multi-user internet log data to obtain second attribute features corresponding to the second terminal;
and the first matching submodule is used for respectively matching the first attribute feature and the second attribute feature with attribute features in a preset multi-dimensional label library, and determining a first label corresponding to the first attribute feature and a second label corresponding to the second attribute feature, wherein the preset multi-dimensional label library comprises a corresponding relation between a trained label and the attribute features.
6. The apparatus of claim 5, wherein the matching module comprises:
the third extraction submodule is used for extracting attribute features of the current internet log data to obtain target attribute features corresponding to the second terminal;
the second matching submodule is used for matching the target attribute features with the attribute features in the preset multi-dimensional label library and determining a second target label corresponding to the target attribute features;
the third matching submodule is used for respectively matching the second target label with the first target label of each user portrait corresponding to the second terminal, wherein the second terminal corresponds to at least one user portrait;
the determining module comprises:
and the determining submodule is used for determining a target user portrait corresponding to a first target label of which the matching degree of the second target label is greater than a preset threshold value in at least one user portrait corresponding to the second terminal.
7. A server, comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when being executed by the processor, carries out the steps of the information recommendation method according to any one of claims 1 to 3.
8. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps in the information recommendation method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810601202.XA CN109033149B (en) | 2018-06-12 | 2018-06-12 | Information recommendation method and device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810601202.XA CN109033149B (en) | 2018-06-12 | 2018-06-12 | Information recommendation method and device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109033149A CN109033149A (en) | 2018-12-18 |
| CN109033149B true CN109033149B (en) | 2020-11-13 |
Family
ID=64612798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810601202.XA Active CN109033149B (en) | 2018-06-12 | 2018-06-12 | Information recommendation method and device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109033149B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113366523B (en) * | 2019-06-20 | 2024-05-07 | 深圳市欢太科技有限公司 | Resource pushing method and related products |
| CN113383360B (en) * | 2019-06-26 | 2023-11-24 | 深圳市欢太科技有限公司 | Content pushing method, device, server side and storage medium |
| CN110532472B (en) * | 2019-08-28 | 2022-09-27 | 百度在线网络技术（北京）有限公司 | Content synchronous recommendation method and device, electronic equipment and storage medium |
| CN112749292B (en) * | 2019-10-31 | 2024-05-03 | 深圳云天励飞技术有限公司 | User tag generation method and device, computer device and storage medium |
| CN110941738B (en) * | 2019-11-27 | 2023-03-28 | 北京奇艺世纪科技有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111479143B (en) * | 2020-03-12 | 2022-04-01 | 深圳市酷开网络科技股份有限公司 | Television advertisement pushing method based on user portrait and electronic equipment |
| CN113596898A (en) * | 2020-04-30 | 2021-11-02 | 华为技术有限公司 | Method, device, equipment, storage medium and system for determining terminal portrait |
| CN112055075B (en) * | 2020-09-02 | 2022-09-09 | 上海基玉金融信息服务股份有限公司 | Internet product monitoring method, device, server and readable storage medium |
| CN112188287A (en) * | 2020-10-14 | 2021-01-05 | 广州欢网科技有限责任公司 | Method, system and equipment for identifying film viewing subject |
| CN112650883B (en) * | 2020-12-10 | 2022-11-22 | 聚源众视(天津)信息技术有限公司 | Video recommendation method for multi-dimension analysis of multiple users |
| CN113936765A (en) * | 2021-12-17 | 2022-01-14 | 北京因数健康科技有限公司 | Method and device for generating periodic behavior report, storage medium and electronic equipment |
| CN115695897B (en) * | 2022-09-29 | 2024-04-30 | 中国广播电视网络集团有限公司 | Multi-role-based multi-screen interactive content recommendation method, storage medium and equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002024694A (en) * | 2000-07-11 | 2002-01-25 | Nippon Telegr & Teleph Corp <Ntt> | Recommendatory information introducing method, recommendatory information introducing system, and recording medium with recommendatory information introducing program recorded thereon |
| CN103354518A (en) * | 2013-07-24 | 2013-10-16 | 江苏晓山信息产业股份有限公司 | Web log mining-based intelligent household gateway and web log mining-based intelligent household system |
| CN105630918A (en) * | 2015-12-22 | 2016-06-01 | 青岛海贝易通信息技术有限公司 | Whole-network user tag fusion and user identification unifying method |
| CN105677844A (en) * | 2016-01-06 | 2016-06-15 | 北京摩比万思科技有限公司 | Mobile advertisement big data directional pushing and user cross-screen recognition method |
| CN106504099A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of system for building user's portrait |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324636B (en) * | 2012-03-22 | 2016-04-06 | 三星电子（中国）研发中心 | The system and method for commending friends in social networks |
| CN104717366B (en) * | 2015-03-31 | 2017-11-14 | 小米科技有限责任公司 | The recommendation method and device of contact head image |
| KR20160120238A (en) * | 2015-04-07 | 2016-10-17 | 주식회사 컴퍼니원헌드레드 | Clothes recommendation system |
| CN105447147B (en) * | 2015-11-26 | 2019-02-01 | 晶赞广告（上海）有限公司 | A kind of data processing method and device |
| CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
-
2018
- 2018-06-12 CN CN201810601202.XA patent/CN109033149B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002024694A (en) * | 2000-07-11 | 2002-01-25 | Nippon Telegr & Teleph Corp <Ntt> | Recommendatory information introducing method, recommendatory information introducing system, and recording medium with recommendatory information introducing program recorded thereon |
| CN103354518A (en) * | 2013-07-24 | 2013-10-16 | 江苏晓山信息产业股份有限公司 | Web log mining-based intelligent household gateway and web log mining-based intelligent household system |
| CN106504099A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of system for building user's portrait |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN105630918A (en) * | 2015-12-22 | 2016-06-01 | 青岛海贝易通信息技术有限公司 | Whole-network user tag fusion and user identification unifying method |
| CN105677844A (en) * | 2016-01-06 | 2016-06-15 | 北京摩比万思科技有限公司 | Mobile advertisement big data directional pushing and user cross-screen recognition method |
| CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109033149A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033149B (en) | Information recommendation method and device, server and storage medium | |
| RU2729956C2 (en) | Detecting objects from visual search requests | |
| JP6855595B2 (en) | Using machine learning to recommend live stream content | |
| CN105095508B (en) | A kind of multimedia content recommended method and multimedia content recommendation apparatus | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| US11487769B2 (en) | Arranging stories on newsfeeds based on expected value scoring on a social networking system | |
| US20140172877A1 (en) | Boosting ranks of stories by a needy user on a social networking system | |
| US10775968B2 (en) | Systems and methods for analyzing visual content items | |
| US20130268513A1 (en) | Annotations based on hierarchical categories and groups | |
| CN111818370B (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| US10853424B1 (en) | Content delivery using persona segments for multiple users | |
| US10440435B1 (en) | Performing searches while viewing video content | |
| CN110858134A (en) | Data, display processing method and device, electronic equipment and storage medium | |
| US11496801B2 (en) | Identifying viewing characteristics of an audience of a content channel | |
| US11430049B2 (en) | Communication via simulated user | |
| CN113382301A (en) | Video processing method, storage medium and processor | |
| CN111722766A (en) | Multimedia resource display method and device | |
| US8725795B1 (en) | Content segment optimization techniques | |
| CN116541602A (en) | Recommendation content pushing method and system, electronic equipment and storage medium | |
| KR20210059593A (en) | Method, apparatus and computer program for providing sale mediate service based on influencer's contents | |
| US9336553B2 (en) | Diversity enforcement on a social networking system newsfeed | |
| US20210365962A1 (en) | Systems and methods of selecting visual elements based on sentiment analysis | |
| CN116150488A (en) | Method, apparatus, device, medium and program product for presenting recommended content | |
| KR20230001086A (en) | Method and application for displaying comment for media |
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 |