1. A method for recommending cell dynamic content, comprising:

acquiring basic user information, monitoring continuous operation behaviors of a user, and constructing a user portrait based on the user operation behaviors and browsing records by a cloud, wherein the user portrait comprises the basic user information and content information;

and matching the user portrait with pre-recommended contents in a database, and selecting a preset number of contents with higher matching degrees for recommending the dynamic contents of the cell.

2. The method of claim 1, wherein said matching the user representation with the pre-recommended content in the database is specifically:

constructing mapping between user basic features and content information, wherein the content information comprises a content feature label;

and calculating the cosine similarity of the content information characteristics corresponding to the current user and the pre-recommended content in the characteristic space based on the mapping of the basic characteristics of the user and the content information.

3. The method of claim 1, wherein the selecting a predetermined number of contents with top-ranked matching degrees for cell dynamic content recommendation further comprises;

and selecting at least one piece of cell dynamic content with different types, different ranges and different time periods for recommendation, wherein the cell dynamic content consists of dynamic information with different time periods, different ranges and different types.

4. The method of claim 1, wherein the selecting a predetermined number of contents with top-ranked matching degrees for cell dynamic content recommendation further comprises;

and when the user operation terminal is not detected or the continuous operation behavior of the user is not detected within a preset time span, recommending different dynamic contents according to a preset proportion when the dynamic contents are refreshed.

5. A cell dynamic content recommendation system, comprising:

the monitoring module is used for acquiring basic information of the user and monitoring continuous operation behaviors of the user;

the construction module is used for constructing a user portrait at a cloud end based on user operation behaviors and browsing records, wherein the user portrait comprises user basic information and content information;

and the recommending module is used for matching and calculating the user portrait with pre-recommended contents in the database, and selecting a preset number of contents with matching degrees ranked at the top for recommending the dynamic contents of the cell.

6. The system of claim 5, wherein the building module comprises:

the system comprises a construction unit, a mapping unit and a mapping unit, wherein the construction unit is used for constructing mapping between user basic characteristics and content information, and the content information comprises a content characteristic label;

and the matching calculation unit is used for calculating the cosine similarity of the content information characteristics corresponding to the current user and the pre-recommended content in the characteristic space based on the mapping between the basic characteristics of the user and the content information.

7. The system according to claim 5, wherein said selecting a predetermined number of top-ranked matching content for cell dynamic content recommendation further comprises;

and selecting at least one piece of cell dynamic content with different types, different ranges and different time periods for recommendation, wherein the cell dynamic content consists of dynamic information with different time periods, different ranges and different types.

8. The system according to claim 5, wherein said selecting a predetermined number of top-ranked matching content for cell dynamic content recommendation further comprises;

and when the user operation terminal is not detected or the continuous operation behavior of the user is not detected within a preset time span, recommending different dynamic contents according to a preset proportion when the dynamic contents are refreshed.

9. An intelligent terminal, comprising:

the monitoring module is used for acquiring basic information of the user and monitoring continuous operation behaviors of the user;

and the display module is used for displaying the cell dynamic content recommended by the cloud.

10. A server, comprising:

the receiving module is used for receiving the continuous operation behaviors of the user and the basic information of the user, which are acquired by the terminal equipment;

the system comprises a construction module, a display module and a display module, wherein the construction module is used for constructing a user portrait, and the user portrait comprises user basic information and content information;

and the recommending module is used for matching and calculating the user portrait with pre-recommended contents in the database, and selecting a preset number of contents with matching degrees ranked at the top for recommending the dynamic contents of the cell.

Background

With the fact that intelligent equipment becomes more and more popular in daily life, the number of received information is increased, people can pay attention to surrounding dynamic news conveniently, and meanwhile the problem of excessive information is brought. When the news is refreshed through a mobile phone and a computer in daily life, irrelevant information can be manually shielded, the functions of an advertising machine, a vertical intelligent terminal and the like are limited, the facing users are different, the interests of the following users are often ignored when information filtering is carried out, for example, a cell dynamic display terminal is used, and when the relevant dynamic content of a cell is recommended, the problem that the subsequent recommended content is inaccurate is often caused due to the operation behavior of one user.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and a system for recommending cell dynamic content, so as to solve the problem that the existing cell dynamic content recommendation is inaccurate.

In a first aspect of the embodiments of the present invention, a method for recommending cell dynamic content is provided, including:

acquiring basic user information, monitoring continuous operation behaviors of a user, and constructing a user portrait based on the user operation behaviors and browsing records by a cloud, wherein the user portrait comprises the basic user information and content information;

and matching the user portrait with pre-recommended contents in a database, and selecting a preset number of contents with higher matching degrees for recommending the dynamic contents of the cell.

In a second aspect of the embodiments of the present invention, a cell dynamic content recommendation system is provided, including:

the monitoring module is used for acquiring basic information of the user and monitoring continuous operation behaviors of the user;

the construction module is used for constructing a user portrait at a cloud end based on user operation behaviors and browsing records, wherein the user portrait comprises user basic information and content information;

and the recommending module is used for matching and calculating the user portrait with pre-recommended contents in the database, and selecting a preset number of contents with matching degrees ranked at the top for recommending the dynamic contents of the cell.

In a third aspect of the embodiments of the present invention, an intelligent terminal is provided, including:

the monitoring module is used for acquiring basic information of the user and monitoring continuous operation behaviors of the user;

and the display module is used for displaying the cell dynamic content recommended by the cloud.

In a fourth aspect of the embodiments of the present invention, a server is provided, including:

the receiving module is used for receiving the continuous operation behaviors of the user and the basic information of the user, which are acquired by the terminal equipment;

the system comprises a construction module, a display module and a display module, wherein the construction module is used for constructing a user portrait, and the user portrait comprises user basic information and content information;

a recommending module for matching the user portrait with pre-recommended content in the database, selecting a predetermined number of contents with matching degrees ranked at the top for recommending the dynamic content in the cell

In the embodiment of the invention, the basic information of the user is collected, the continuous operation behavior of the user is monitored, the user portrait is constructed, the user portrait is matched and calculated with the pre-recommended content in the database, and the dynamic content of the cell is selected for recommendation. Therefore, content recommendation can be performed according to user behaviors, recommended content is matched with user interests, accuracy of content recommendation is guaranteed, meanwhile, operation influences of different users are reduced, and user experience is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.

Fig. 1 is a flowchart illustrating a method for recommending dynamic content in a cell according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a cell dynamic content recommendation system according to an embodiment of the present invention.

Detailed Description

In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the 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 invention.

The terms "comprises" and "comprising," when used in this specification and claims, and in the accompanying drawings and figures, are intended to cover non-exclusive inclusions, such that a process, method or system, or apparatus that comprises a list of steps or elements is not limited to the listed steps or elements. In addition, "first" and "second" are used to distinguish different objects, and are not used to describe a specific order.

Referring to fig. 1, fig. 1 is a schematic flowchart of a method for recommending cell dynamic content according to an embodiment of the present invention, including:

s101, collecting basic user information, monitoring continuous operation behaviors of a user, and constructing a user portrait based on the user operation behaviors and browsing records by a cloud, wherein the user portrait comprises the basic user information and content information;

it can be understood that to the vertical intelligent terminal that the district was put, it can provide abundant information for the resident, like district news, notice, activity, question and answer, little share etc. its scope can not be restricted to this district, can include with city district, city or whole net, all can demonstrate through the terminal screen, to the wisdom community, can regard as important information display platform.

The basic user information can be historical registration information of the user, and also can be user information acquired by a terminal content micro camera, for example, when the user approaches, a camera acquires a face image of the user. Preferably, the face image of the user is collected through a terminal camera, the identity of the user is authenticated, and the identity information of the current user is obtained.

The intelligent terminal monitors and collects user operation information, if a user clicks a certain dynamic content or the user hovers over dynamic information of a reading cell, the user clicking reading content is recorded, and if the user returns quickly or slides quickly, the content which is not interesting to the user can be marked. The mistouch judgment can be carried out on the continuous operation of the user in a short time and the clicking of the user on a certain type of content which does not accord with the interest of the user, and the mistouch content is not marked or recorded.

And determining the content of interest of the user based on the current operation behavior of the user, and meanwhile, if the historical operation behavior of the user can be inquired, determining the content of interest of the user by combining the historical browsing content of the user.

And sending the user basic information (identity information or face information and the like), the operation behavior and the user browsing record collected by the terminal to the cloud end, and acquiring and analyzing the user basic information and the user interested content by the cloud end to further construct the user portrait.

In one embodiment, the dynamic content information of the cell includes different types such as articles, micro-shares, votes, activities, reviews, questions and answers, and can be divided into 0-3 days, 3-7 days, 7-30 days and more than 30 days according to time periods, the dynamic content information of the cell can be divided into the cell, the cell in the same city, the city and the whole network according to ranges, and the dynamic content information of the cell can be divided into characters, videos and the like according to forms.

According to the classification of the dynamic content of the cell, a characteristic label of the content which the user is interested in can be constructed, if a certain content browsed by the user, a characteristic label such as content A can be added to the content information, and the label is an article, 0-3 days, a city and characters.

And S102, matching the user portrait with pre-recommended contents in a database, and selecting a preset number of contents with matching degrees ranked at the top for recommending the dynamic contents of the cell.

Specifically, a mapping between the user basic features and content information is constructed, wherein the content information comprises a content feature label; and calculating the cosine similarity of the content information characteristics corresponding to the current user and the pre-recommended content in the characteristic space based on the mapping of the basic characteristics of the user and the content information.

According to the mapping relation between different users and the interested contents, a mapping model is built, based on the mapping between the current user and the interested contents, the cosine similarity can be calculated based on the characteristics of the interested contents and the characteristics of pre-recommended contents, the characteristic similarity degree is judged, and then a certain amount of dynamic contents are selected for recommendation according to the similarity degree.

Preferably, at least one piece of cell dynamic content of different types, different ranges and different time periods is selected for recommendation, wherein the cell dynamic content is composed of dynamic information of different time periods, different ranges and different types.

In order to ensure the richness of recommended contents, at least one piece of contents of different types, different ranges and different time periods which are not recommended can be reserved after a certain piece of recommended contents are selected, if the recommended contents do not include the selection type, a piece of selected content can be randomly selected for recommendation, if the recommended contents do not include the same-city cell, a piece of content of the same-city cell can be selected for recommendation, specifically, a piece of content of a corresponding type, range or time period can be randomly selected for recommendation according to the contents of the unremitted type, range or time period, and the excessive similar information is avoided.

Optionally, when the user operation terminal is not detected, or a continuous operation behavior from the user is not detected within a predetermined time period, different dynamic content recommendations are performed according to a preset ratio during dynamic content refresh.

When the user does not operate the terminal, does not operate the behavior within a certain time, and the camera does not detect the user, content recommendation with a default proportion is resumed within a refresh period, that is, the content in different types, different ranges and different time periods is recommended according to a fixed proportion, so that the use experience of the next user is prevented from being influenced.

According to the method provided by the embodiment, the user portrait is constructed according to different user operation behaviors, and the accuracy of the recommended content can be guaranteed based on the matching calculation of the recommended content and the user interest. Meanwhile, after the user uses the recommendation method, the recommendation content with the default proportion can be recovered, the influence among different users is reduced, and the user experience is improved. The occurrence of different contents is reserved in the recommended contents, and the excessive recommendation of similar information can be avoided.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, but should not constitute any limitation to the implementation process of the embodiments of the present invention,

fig. 2 is a schematic structural diagram of a cell dynamic content recommendation system according to an embodiment of the present invention, where the system includes:

the monitoring module 210 is configured to collect basic information of a user and monitor a continuous operation behavior of the user;

the construction module 220 is configured to construct a user portrait at a cloud based on a user operation behavior and a browsing record, where the user portrait includes user basic information and content information;

wherein the building block 220 comprises:

the system comprises a construction unit, a mapping unit and a mapping unit, wherein the construction unit is used for constructing mapping between user basic characteristics and content information, and the content information comprises a content characteristic label;

and the matching calculation unit is used for calculating the cosine similarity of the content information characteristics corresponding to the current user and the pre-recommended content in the characteristic space based on the mapping between the basic characteristics of the user and the content information.

And the recommending module 230 is used for performing matching calculation on the user portrait and pre-recommended contents in the database, and selecting a preset number of contents with matching degrees ranked at the top for recommending the dynamic contents of the cell.

Preferably, at least one piece of cell dynamic content of different types, different ranges and different time periods is selected for recommendation, wherein the cell dynamic content is composed of dynamic information of different time periods, different ranges and different types.

Preferably, when the user operation terminal is not detected, or a continuous operation behavior from the user is not detected within a predetermined time period, different dynamic content recommendations are performed according to a preset ratio during dynamic content refresh.

In one embodiment, there is also provided a smart terminal, including:

the monitoring module is used for acquiring basic information of the user and monitoring continuous operation behaviors of the user;

and the display module is used for displaying the cell dynamic content recommended by the cloud.

It can be understood that the intelligent terminal can be a common vertical intelligent terminal used for displaying dynamic cell information. The terminal can comprise hardware such as a touch screen, a miniature camera, a wireless communication module, a processor, a memory and the like, and is used for realizing all functions of the monitoring module and the display module.

In one embodiment, a server for cell dynamic recommendation content generation is provided

The receiving module is used for receiving the continuous operation behaviors of the user and the basic information of the user, which are acquired by the terminal equipment;

the system comprises a construction module, a display module and a display module, wherein the construction module is used for constructing a user portrait, and the user portrait comprises user basic information and content information;

and the recommending module is used for matching and calculating the user portrait with pre-recommended contents in the database, and selecting a preset number of contents with matching degrees ranked at the top for recommending the dynamic contents of the cell.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by using a program to instruct related hardware, where the program may be stored in a computer-readable storage medium, and when the program is executed, the program includes some or all of the steps S101 to S102, and the storage medium includes, for example, ROM/RAM.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.