CN112261423B - Method, device, equipment and storage medium for pushing information - Google Patents
Method, device, equipment and storage medium for pushing information Download PDFInfo
- Publication number
- CN112261423B CN112261423B CN202011109890.1A CN202011109890A CN112261423B CN 112261423 B CN112261423 B CN 112261423B CN 202011109890 A CN202011109890 A CN 202011109890A CN 112261423 B CN112261423 B CN 112261423B
- Authority
- CN
- China
- Prior art keywords
- live broadcast
- information
- user
- determining
- related information
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Abstract
The application discloses a method, a device, equipment and a storage medium for pushing information, and relates to the field of deep learning. The specific implementation scheme is as follows: acquiring first related information of a user; acquiring historical interactive information generated by watching live broadcast by a user; acquiring second related information of live broadcast watched by a user; determining target live broadcast according to the first relevant information, the historical interaction information, the second relevant information and a preset live broadcast determination model, wherein the live broadcast determination model is used for representing the corresponding relation between the first relevant information, the historical interaction information, the second relevant information and the target live broadcast; and pushing information to the user according to the target live broadcast. According to the implementation mode, the interest of the user and the characteristics of the information are comprehensively considered during information pushing, so that the pushed information is more in line with the interest of the user, and the browsing experience of the user is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to the field of deep learning, and in particular, to a method, an apparatus, a device, and a storage medium for pushing information.
Background
Most of the current video playing platforms push videos or live broadcasts of a certain account frequently browsed by a user according to browsing records and browsing contents of the user, and the current video playing platforms are rarely related to recommending live broadcast contents and live broadcast types to the user according to watching preferences of the user on the video contents and characteristics of the live broadcasts. Therefore, the video pushed by the video playing platform does not accord with the interest of the user, and the browsing experience of the user is reduced.
Disclosure of Invention
A method, an apparatus, a device and a storage medium for pushing information are provided.
According to a first aspect, there is provided a method for pushing information, comprising: acquiring first related information of a user; acquiring historical interactive information generated by watching live broadcast by a user; acquiring second related information of live broadcast watched by a user; determining a target live broadcast according to the first relevant information, the historical interaction information, the second relevant information and a preset information determination model, wherein the live broadcast determination model is used for representing the corresponding relation between the first relevant information, the historical interaction information, the second relevant information and the target live broadcast; and pushing information to the user according to the target live broadcast.
According to a second aspect, there is provided an apparatus for pushing information, comprising: a first acquisition unit configured to acquire first related information of a user; the second acquisition unit is configured to acquire historical interaction information generated by live broadcast watching of a user; a third acquisition unit configured to acquire second related information of a live broadcast viewed by a user; the live broadcast determining unit is configured to determine a target live broadcast according to the first relevant information, the historical interaction information, the second relevant information and a preset live broadcast determining model, wherein the live broadcast determining model is used for representing the corresponding relation between the first relevant information, the historical interaction information, the second relevant information and the target live broadcast; and the information pushing unit is configured to push information to the user according to the target live broadcast.
According to a third aspect, there is provided an electronic device for pushing information, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.
According to a fourth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method as described in the first aspect.
According to the technology of the application, the interest of the user and the characteristics of the information are comprehensively considered during information pushing, so that the pushed information is more in line with the interest of the user, and the browsing experience of the user is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be considered limiting of the present application. Wherein:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for pushing information, according to the present application;
FIG. 3 is a schematic diagram of an application scenario for a method for pushing information according to the present application;
FIG. 4 is a flow diagram of another embodiment of a method for pushing information according to the present application;
FIG. 5 is a schematic block diagram of one embodiment of an apparatus for pushing information in accordance with the present application;
fig. 6 is a block diagram of an electronic device used to implement the method for pushing information according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the present method for pushing information or apparatus for pushing information may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may use terminal devices 101, 102, 103 to interact with a server 105 over a network 104 to receive or send messages or the like. Various communication client applications, such as a video playing application, a shopping application, a browser application, etc., may be installed on the terminal devices 101, 102, 103.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, e-book readers, car computers, laptop portable computers, desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It may be implemented as a plurality of software or software modules (for example to provide distributed services) or as a single software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background server that provides support for a video playback application installed on the terminal device 101, 102, 103. The background server may obtain information of the user, may also obtain live information watched by the user, determine information pushed to the user, and push the information to the terminal devices 101, 102, and 103.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the method for pushing information provided by the embodiment of the present application is generally performed by the server 105. Accordingly, means for pushing information is typically provided in the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to fig. 2, a flow 200 of one embodiment of a method for pushing information in accordance with the present application is shown. The method for pushing information of the embodiment comprises the following steps:
In this embodiment, an execution subject (for example, the server 105 shown in fig. 1) of the method for pushing information may obtain the first relevant information of the user. Here, the user may be a user registered at a certain shopping website or a video live website. The first related information may include various related information of the user, and may include, for example, an age, a sex, an occupation, a login habit, a viewing habit, and the like of the user.
The execution subject can also acquire historical interactive information generated by watching live broadcast by the user. The live broadcast viewed by the user may be a live broadcast recorded in real time by the anchor. A user may interact with the anchor while watching the live broadcast. The interaction may include posting comment information, commenting on, sharing live broadcasts, or purchasing items sold in live broadcasts. The execution subject may obtain the above-mentioned historical interaction information in various ways, for example, by obtaining the historical interaction information from a background server of the live application or from a database for storing live information.
The execution subject may also obtain second related information of a live broadcast viewed by the user. Here, the second related information may include various information related to the live broadcast. For example, information of the anchor, information of the item sold, the number of viewers, the number of praise, the number of fans, the number of comments, the number of orders committed during live broadcasting can be included. The information of the anchor may include, among other things, the identity of the anchor, the field of excellence, the live date, the rating of the anchor, etc. The information of the sold item may include a link, price, identification, etc. of the item. The number of watching people refers to the number of users watching the live broadcast in the single live broadcast process. The number of praise refers to the number of praise the user has on the live broadcast. The number of fans refers to the number of users who are interested in the live room. The number of comments may be the number of comments the user posts in the live room. The number of orders committed during the live broadcast may be the number of orders generated by the user after payment via the merchandise link during the live broadcast.
And 204, determining the target live broadcast according to the first relevant information, the historical interaction information, the second relevant information and a preset live broadcast determination model.
In this embodiment, after acquiring the first relevant information, the historical interaction information, and the second relevant information, the execution main body may determine the target live broadcast by combining a preset live broadcast determination model. Here, the live broadcast determining model is used for representing a corresponding relationship between the first relevant information, the historical interaction information, the second relevant information and the target live broadcast. The live broadcast determination model can be a model trained based on a deep learning algorithm. The execution main body can input the first related information, the historical interaction information and the second related information into the live broadcast determination model, and the output of the live broadcast determination model is target live broadcast. The target live broadcast is live broadcast information which is predicted by the live broadcast determination model and is interested by the user. The target live may be identified with a live identification. The live broadcast identification may include information of the anchor and live broadcast time information.
And step 205, pushing information to the user according to the target live broadcast.
In this embodiment, after determining the target live broadcast, the execution subject may generate information to be pushed to the user according to the target live broadcast. Specifically, the execution subject can directly push the related information of the target live broadcast to the user so as to be browsed by the user. Or, the execution subject can further judge whether the target live broadcast meets the interest of the user, and if so, the related information of the target live broadcast is output.
With continued reference to fig. 3, a schematic diagram of one application scenario of a method for pushing information according to the present application is shown. In the application scenario of fig. 3, the user watches live through a live-like application installed in the terminal 301. The server 302 determines the target live broadcast according to the first related information of the user, the historical interaction information, the second related information of the live broadcast and the live broadcast determination model. The target live broadcast is then output to the user, who can browse it on the first screen or on a specific channel (e.g., "recommend to you") of the live-like application.
According to the method for pushing the information, the first relevant information of the user, the historical interaction information generated in the live broadcast watching process of the user and the second relevant information of the live broadcast are obtained, and the target live broadcast pushed to the user is determined by combining the live broadcast determining model trained in advance, so that the pertinence of information pushing is improved, and the browsing experience of the user can be improved.
With continued reference to fig. 4, a flow 400 of another embodiment of a method for pushing information in accordance with the present application is shown. In this embodiment, the method for pushing information may include the following steps:
In this embodiment, the execution subject may obtain a training sample set. Here, the training sample includes first sample-related information of the sample user, historical interaction information of the sample user generated by watching live broadcast, second sample-related information of live broadcast watched by the sample user, and a corresponding label. The corresponding label is used to indicate whether the training sample belongs to a positive or a negative sample. The label may be determined by comparing a portion of the data in the second sample-related information with a preset threshold. A portion of the data may include the number of likes, the number of orders committed, the number of viewers, and so on. If the data are larger than the preset threshold value, the training sample is considered as a positive sample, otherwise, the task training sample is a negative sample.
In this embodiment, the execution subject may take the first sample related information, the sample history interaction information, and the second sample related information of each training sample in the training sample set as input. And training to obtain an information determination model by taking the label corresponding to the input information as a learning target. Specifically, the executing agent may adjust parameters of the information determination model multiple times in the training process, so that the loss function of the information determination model satisfies the preset condition.
In step 403, first relevant information of the user is obtained.
And step 405, acquiring second related information of live broadcast watched by the user.
And step 406, determining a model according to the first relevant information, the historical interaction information, the second relevant information and the preset information, and determining target live broadcast information.
In this embodiment, the execution main body may further obtain third related information of live broadcasts that are not watched by the user. The execution agent may first acquire all live broadcasts in the live space. And then, removing the live broadcast watched by the user, wherein the rest live broadcasts are live broadcasts which are not watched by the user. The execution subject may obtain third related information from the electronic device for storing related information of the live broadcast. Here, the content included in the third related information may be the same as the content included in the first related information.
And step 408, determining an interest degree matrix of the user according to the historical interaction information, the second relevant information, the third relevant information and a preset similarity set.
In this embodiment, after the execution main body obtains the third relevant information, the interest degree matrix of the user may be determined by combining the historical interaction information, the second relevant information, and a preset similarity set. Here, the preset similarity set includes the similarity of any two live broadcasts in a live broadcast set, where the live broadcast set includes live broadcasts watched by the user and live broadcasts not watched by the user. Specifically, the second related information may include a theme of live broadcasting, the third related information may also include a theme of live broadcasting, and the historical interactive information may include the number of times of live broadcasting watched by the user. The execution subject may regard a live broadcast in which the number of viewing times is greater than a preset number threshold as a live broadcast in which the user is interested. And then, determining live broadcasts similar to the live broadcasts interested by the user by combining a preset similarity set, the topics of the interested live broadcasts and the subjects of the unviewed live broadcasts, and taking the live broadcasts as the live broadcasts interested by the user. The remaining live is live that is not of interest to the user. Specifically, the execution subject may set an interest level corresponding to the live broadcast that is interested to a first preset value, and set an interest level corresponding to the live broadcast that is not interested to a second preset value. And combining the first preset value with the second preset value to obtain the interestingness matrix of the user.
In some optional implementations of this embodiment, the step 408 may also be implemented by the following steps not shown in fig. 4: determining a first interest degree of a user in watching live broadcast according to historical interaction information; predicting a second interest degree of the user in the unviewed live broadcast according to the first interest degree, a preset similarity set, the second related information and the third related information; and determining an interest degree matrix according to the first interest degree and the second interest degree.
In the implementation mode, the execution main body can analyze the historical interactive information and determine the first interest degree of the user in watching the live broadcast. Specifically, the executive body can perform emotion analysis on comments issued by the user in the historical interaction information to determine whether the emotion of the user is happy or angry when watching the live broadcast. The popularity, the watching duration, etc. of the user can also be analyzed (for example, weighted calculation), and the first interestingness is determined according to the analysis result. After determining the first interest level, the execution subject may predict a second interest level of the user in the unviewed live broadcast according to the similarity set, the second related information, and the third related information. Specifically, the execution subject may calculate the similarity between the live broadcasts according to the topic in the second related information and the topic in the third related information. Then, the similarity in the similarity set and the first interestingness are weighted, and the obtained result is used as a second interestingness. And finally, taking the obtained first interestingness and the second interestingness as elements in an interestingness matrix to obtain the interestingness matrix.
In some optional implementations of this embodiment, the preset similarity set may be determined through the following steps not shown in fig. 4: for each live broadcast, determining a third interest degree of a user who watches the live broadcast in the live broadcast; and determining the similarity of each live broadcast according to the third interestingness to obtain a similarity set.
In the implementation mode, the execution main body can analyze each live broadcast, and the third interestingness of each user in the live broadcast is determined according to comments, praise numbers and purchase quantity issued by the users in each live broadcast. For example, the comments made by the user, the number of praise and the number of purchases are subjected to weighted analysis, and the result is taken as the third interestingness. After the interest degrees of the users in live broadcasting are obtained, the live broadcasting similarity with the same interest degree can be determined to be higher, and the live broadcasting similarity with different interest degrees is lower. And according to the relation between the preset interest degree and the similarity, obtaining the similarity of each live broadcast to obtain a similarity set.
And step 409, responding to the fact that the target live broadcast is matched with the interestingness matrix, and pushing the target live broadcast to the user.
If the target live broadcast does not match the interest of the user, namely the interest level is lower than a preset threshold, the execution subject can consider that the target live broadcast determined by the live broadcast recommendation model does not meet the interest of the user. If the interest degree is higher than the preset threshold value, the execution subject can consider that the target live broadcast determined by the live broadcast recommendation model accords with the interest of the user, and the target live broadcast can be pushed to the user.
In some optional implementations of this embodiment, the executing subject may determine whether the target live broadcast matches the interestingness matrix by the following steps not shown in fig. 4: determining the target interest degree of the user on the target live broadcast according to the user interest degree matrix; and in response to determining that the target interest level is greater than a preset interest level threshold, determining that the target live broadcast is matched with the interest level matrix.
In the implementation manner, because the interestingness matrix of the user comprises the interestingness of the user in each live broadcast, after the target live broadcast is obtained, the execution main body can search the interestingness matrix and determine the interestingness corresponding to the target live broadcast. If the found interest degree is larger than the preset interest degree threshold value, the target live broadcast preset by the live broadcast determining model can be determined to be in accordance with the interest of the user, namely the target live broadcast is matched with the interest degree matrix.
In this embodiment, the execution main body may further obtain incremental data of the first related information, incremental data of the historical interaction information, and incremental data of the second related information. Here, the incremental data refers to newly added data generated by the user in a certain period. The execution principal may then determine an incremental training sample set using the incremental data. It will be appreciated that the incremental training samples in the incremental training sample set are the same form as the training samples in the training sample set. And updating the live broadcast determination model by using the incremental training sample set. This may enable real-time updating of the live determination model.
In this embodiment, the execution subject may further obtain a parameter value of the at least one evaluation parameter for the live broadcast determination model. Here, the at least one evaluation parameter may include a subjective evaluation parameter, and may also include an objective evaluation parameter. The subjective evaluation parameters may include the degree of satisfaction of the user with the pushed target live broadcast. The objective evaluation parameters may include a loss function of the live broadcast determination model. The execution subject may acquire the parameter value of each evaluation parameter. The execution subject may compare each parameter value with a preset condition, and if each parameter value does not satisfy the preset condition, the target live broadcast may be output. The output here may be a targeted live output to a technician. The technical personnel can modify the target live broadcast and send the modification information to the execution main body. And after receiving the modification information, the execution subject can push the modified target live broadcast to the user.
The method for pushing the information provided by the embodiment of the application can enable the information pushed to the user to better accord with the interest of the user; meanwhile, the live broadcast determination model can be updated in real time, and timeliness of information pushing is improved; in addition, if the effect of determining the model by live broadcast is not ideal, technicians can be operated to modify the pushed information, and the accuracy is further improved.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for pushing information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 5, the information push device 500 of the present embodiment includes: a first acquisition unit 501, a second acquisition unit 502, a third acquisition unit 503, a live broadcast determination unit 504, and an information push unit 505.
A first obtaining unit 501 configured to obtain first relevant information of a user.
A second obtaining unit 502 configured to obtain historical interaction information generated by a user watching a live broadcast.
A third obtaining unit 503 configured to obtain second related information of the live broadcast viewed by the user.
And a live broadcast determining unit 504 configured to determine a target live broadcast according to the first relevant information, the historical interaction information, the second relevant information, and a preset live broadcast determining model. The live broadcast determining model is used for representing the corresponding relation among the first related information, the historical interaction information, the second related information and the target live broadcast.
And an information pushing unit 505 configured to push information to the user according to the target live broadcast.
In some optional implementations of this embodiment, the apparatus 500 may further include a fourth obtaining unit and an interestingness matrix determining unit that are not shown in fig. 5.
A fourth acquisition unit configured to acquire third related information of a live broadcast not viewed by the user.
The interestingness matrix determining unit is configured to determine an interestingness matrix of the user according to the historical interaction information, the second related information, the third related information and a preset similarity set, wherein the preset similarity set comprises similarities of any two live broadcasts in a live broadcast set, and the live broadcast set comprises live broadcasts watched by the user and live broadcasts not watched by the user.
In some optional implementations of this embodiment, the interestingness matrix determination unit may be further configured to: determining a first interest degree of a user in second related information of watched live broadcast according to the first related information; predicting a second interest degree of the user in the unviewed live broadcast according to the live broadcast in which the user is interested, a preset similarity set and third related information; and determining an interest degree matrix according to the first interest degree and the second interest degree.
In some optional implementations of this embodiment, the apparatus 500 may further include a similarity set determining unit, not shown in fig. 5, configured to determine the preset similarity set by: for each live broadcast, determining a third interest degree of a user who watches the live broadcast in the live broadcast; and determining the similarity of the related information of each live broadcast according to the third interest degree to obtain a similarity set.
In some optional implementations of this embodiment, the information pushing unit 504 may be further configured to: and responding to the fact that the target live broadcast is matched with the interestingness matrix, and pushing target live broadcast information to the user.
In some optional implementations of this embodiment, the apparatus 500 may further include a matching determining unit, not shown in fig. 5, configured to: determining the target interest degree of the user on the target live broadcast according to the user interest degree matrix; and in response to determining that the target interestingness is greater than a preset interestingness threshold, determining that the target live broadcast is matched with the interestingness matrix.
In some optional implementations of this embodiment, the apparatus 500 may further include a training unit, not shown in fig. 5, configured to: acquiring a training sample set, wherein the training sample comprises first sample related information of a sample user, sample historical interaction information generated by the sample user watching live broadcast, second sample related information of the sample user watching live broadcast and labels corresponding to the information; and taking the first sample related information, the sample historical interaction information and the second sample related information of the training samples in the training sample set as input, taking the labels corresponding to the input information as learning targets, and training to obtain a live broadcast determination model.
In some optional implementations of this embodiment, the apparatus 500 may further include an updating unit, not shown in fig. 5, configured to: obtaining incremental data of first relevant information, incremental data of historical interaction information and incremental data of second relevant information; determining an incremental training sample set by utilizing the incremental data; updating the live broadcast determination model by using the incremental training sample set.
In some optional implementations of this embodiment, the apparatus 500 may further include a modification unit, not shown in fig. 5, configured to: acquiring parameter values of at least one evaluation parameter of a live broadcast determination model; in response to the fact that the obtained at least one parameter value does not meet the preset condition, outputting the target live broadcast; and in response to receiving modification information aiming at the target live broadcast, pushing the modified target live broadcast to a user.
It should be understood that units 501 to 505, which are described in the apparatus 500 for pushing information, correspond to respective steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method for pushing information are also applicable to the apparatus 500 and the units included therein, and are not described herein again.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 6, is a block diagram of an electronic device executing a method for pushing information according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method for pushing information as provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method for pushing information provided by the present application.
The memory 602 is used as a non-transitory computer readable storage medium and can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method for pushing information (for example, the first obtaining unit 501, the second obtaining unit 502, the third obtaining unit 503, the live broadcast determining unit 504, and the information pushing unit 505 shown in fig. 5) in the embodiment of the present application. The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 602, namely, implements the method for pushing information in the above method embodiments.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of an electronic device performed for pushing information, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 may optionally include memory remotely located from the processor 601, such remote memory may be connected through a network to an electronic device executing instructions for pushing information. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device performing the method for pushing information may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
The input device 603 may receive input numeric or character information and generate key signal inputs related to performing user settings and function control of the electronic apparatus for pushing information, such as an input device like a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, etc. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, the interest of the user and the characteristics of the information are comprehensively considered during information pushing, so that the pushed information is more in line with the interest of the user, and the browsing experience of the user is improved.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (14)
1. A method for pushing information, comprising:
acquiring first related information of a user;
acquiring historical interaction information generated by watching live broadcast by the user;
acquiring second related information of live broadcast watched by the user;
acquiring third related information of live broadcast which is not watched by the user;
determining target live broadcast according to the first relevant information, the historical interaction information, the second relevant information and a preset live broadcast determining model, wherein the live broadcast determining model is used for representing the corresponding relation among the first relevant information, the historical interaction information, the second relevant information and the target live broadcast information;
determining an interest degree matrix of the user according to the historical interaction information, the second relevant information, the third relevant information and a preset similarity set, wherein the preset similarity set comprises similarity of any two live broadcasts in a live broadcast set, the live broadcast set comprises live broadcasts watched by the user and live broadcasts not watched by the user, and the preset similarity set is determined through the following steps: for each live broadcast, determining a third interest degree of a user who watches the live broadcast in the live broadcast; according to the third interestingness, determining the similarity of each live broadcast to obtain a similarity set;
in response to determining that the target live broadcast matches the interestingness matrix, pushing the target live broadcast to the user.
2. The method of claim 1, wherein the determining the interestingness matrix of the user according to the historical interaction information, the second relevant information, the third relevant information and a preset similarity set comprises:
determining a first interest degree of the user in the watched live broadcast according to the historical interaction information;
predicting a second interest degree of the user in the unviewed live broadcast according to the first interest degree, the preset similarity set, the second related information and the third related information;
and determining the interestingness matrix according to the first interestingness and the second interestingness.
3. The method of claim 2, wherein the method further comprises:
determining the target interest degree of the user on the target live broadcast according to the user interest degree matrix;
in response to determining that the target interestingness is greater than a preset interestingness threshold, determining that the target live broadcast matches the interestingness matrix.
4. The method of claim 1, wherein the live determination model is trained by:
acquiring a training sample set, wherein the training sample comprises first sample related information of a sample user, sample historical interaction information generated when the sample user watches live broadcast, second sample related information of live broadcast watched by the sample user and labels corresponding to the information;
and taking the first sample related information, the sample historical interaction information and the second sample related information of the training samples in the training sample set as input, taking a label corresponding to the input information as a learning target, and training to obtain the live broadcast determining model.
5. The method of claim 1, wherein the method further comprises:
acquiring incremental data of the first related information, incremental data of the historical interaction information and incremental data of the second related information;
determining an incremental training sample set by using the incremental data;
updating the live broadcast determination model with the incremental training sample set.
6. The method of claim 1, wherein the method further comprises:
acquiring parameter values of at least one evaluation parameter of the live broadcast determination model;
responding to the fact that the obtained at least one parameter value does not meet a preset condition, and outputting the target live broadcast;
and responding to the received modification information aiming at the target live broadcast, and pushing the modified target live broadcast to the user.
7. An apparatus for pushing information, comprising:
a first acquisition unit configured to acquire first related information of a user;
a second obtaining unit configured to obtain historical interaction information generated by live watching of the user;
a third acquisition unit configured to acquire second related information of a live broadcast viewed by the user;
a fourth acquisition unit configured to acquire third related information of live broadcast not viewed by the user;
the live broadcast determining unit is configured to determine a target live broadcast according to the first relevant information, the historical interaction information, the second relevant information and a preset live broadcast determining model, wherein the live broadcast determining model is used for representing the corresponding relation among the first relevant information, the historical interaction information, the second relevant information and the target live broadcast;
an interest degree matrix determining unit, configured to determine an interest degree matrix of the user according to the historical interaction information, the second related information, the third related information, and a preset similarity set, where the preset similarity set includes similarities of any two live broadcasts in a live broadcast set, the live broadcast set includes live broadcasts watched by the user and live broadcasts not watched by the user, and the preset similarity set is determined through the following steps: for each live broadcast, determining a third interest degree of a user who watches the live broadcast in the live broadcast; according to the third interestingness, determining the similarity of related information of each live broadcast to obtain a similarity set;
an information pushing unit configured to push the target live broadcast to the user in response to determining that the target live broadcast matches the interestingness matrix.
8. The apparatus of claim 7, wherein the interestingness matrix determination unit is further configured to:
determining a first interest degree of the user in the watched live second related information according to the first related information;
predicting a second interest degree of the user in the unviewed live broadcast according to the first interest degree, the preset similarity set and the third relevant information;
and determining the interestingness matrix according to the first interestingness and the second interestingness.
9. The apparatus of claim 8, wherein the apparatus further comprises a match determination unit configured to:
determining the target interest degree of the user on the target live broadcast according to the user interest degree matrix;
in response to determining that the target interestingness is greater than a preset interestingness threshold, determining that the target live broadcast matches the interestingness matrix.
10. The apparatus of claim 7, wherein the apparatus further comprises a training unit configured to:
acquiring a training sample set, wherein the training sample comprises first sample related information of a sample user, sample historical interaction information generated when the sample user watches live broadcast, second sample related information of live broadcast watched by the sample user and labels corresponding to the information;
and taking the first sample related information, the sample historical interaction information and the second sample related information of the training samples in the training sample set as input, taking a label corresponding to the input information as a learning target, and training to obtain the live broadcast determining model.
11. The apparatus of claim 7, wherein the apparatus further comprises an update unit configured to:
acquiring incremental data of the first related information, incremental data of the historical interaction information and incremental data of the second related information;
determining an incremental training sample set by using the incremental data;
updating the live broadcast determination model with the incremental training sample set.
12. The apparatus of claim 7, wherein the apparatus further comprises a modification unit configured to:
acquiring parameter values of at least one evaluation parameter of the live broadcast determination model;
responding to the fact that the obtained at least one parameter value does not meet a preset condition, and outputting the target live broadcast;
and responding to the received modification information aiming at the target live broadcast, and pushing the modified target live broadcast to the user.
13. An electronic device for pushing information, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011109890.1A CN112261423B (en) | 2020-10-16 | 2020-10-16 | Method, device, equipment and storage medium for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011109890.1A CN112261423B (en) | 2020-10-16 | 2020-10-16 | Method, device, equipment and storage medium for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112261423A CN112261423A (en) | 2021-01-22 |
| CN112261423B true CN112261423B (en) | 2022-07-22 |
Family
ID=74244370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011109890.1A Active CN112261423B (en) | 2020-10-16 | 2020-10-16 | Method, device, equipment and storage medium for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112261423B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113542779B (en) * | 2021-06-04 | 2023-07-28 | 广州虎牙科技有限公司 | User data prediction method, computer equipment and storage device |
| CN113259774B (en) * | 2021-06-25 | 2021-10-12 | 大学长(北京)网络教育科技有限公司 | Live broadcast information pushing method and device |
| CN113626712A (en) * | 2021-08-19 | 2021-11-09 | 云南腾云信息产业有限公司 | Content determination method and device based on user interaction behavior |
| CN114595016B (en) * | 2022-01-12 | 2024-03-26 | 北京达佳互联信息技术有限公司 | Comment information display method, comment information generation method, comment information display device, comment information generation device and electronic equipment |
| CN115225921B (en) * | 2022-06-08 | 2024-02-06 | 深圳软银思创科技有限公司 | Live broadcast interactive control method, device, equipment and storage medium based on big data |
| CN115086700A (en) * | 2022-06-15 | 2022-09-20 | 北京有竹居网络技术有限公司 | Push processing method, device, equipment and medium |
| CN116823407B (en) * | 2023-08-29 | 2024-01-12 | 北京国电通网络技术有限公司 | Product information pushing method, device, electronic equipment and computer readable medium |
| CN117221663A (en) * | 2023-10-11 | 2023-12-12 | 北京惠买在线网络科技有限公司 | User behavior prediction method and system based on data interaction |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110035302A (en) * | 2018-01-11 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Information recommendation and model training method and device calculate equipment, storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10284916B2 (en) * | 2014-11-19 | 2019-05-07 | Comcast Cable Communications, Llc | Personalized menus and media content interface |
| CN108235045B (en) * | 2018-01-04 | 2019-09-10 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, electronic equipment and readable storage medium storing program for executing |
| CN109165347B (en) * | 2018-08-20 | 2021-03-26 | 腾讯科技（深圳）有限公司 | Data pushing method and device, storage medium and electronic device |
| CN108989893B (en) * | 2018-08-21 | 2020-12-15 | 武汉斗鱼网络科技有限公司 | Live broadcast room recommendation method and device, terminal and storage medium |
| CN110856003B (en) * | 2019-10-17 | 2021-11-02 | 网易（杭州）网络有限公司 | Live list pushing method and device, electronic equipment and storage medium |
-
2020
- 2020-10-16 CN CN202011109890.1A patent/CN112261423B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110035302A (en) * | 2018-01-11 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Information recommendation and model training method and device calculate equipment, storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112261423A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112261423B (en) | Method, device, equipment and storage medium for pushing information | |
| US11127032B2 (en) | Optimizing and predicting campaign attributes | |
| CN107426328B (en) | Information pushing method and device | |
| JP2017174062A (en) | Purchase behavior analyzing device and program | |
| CN113312512B (en) | Training method, recommending device, electronic equipment and storage medium | |
| CN110163703B (en) | Classification model establishing method, file pushing method and server | |
| CN110020162B (en) | User identification method and device | |
| CN112235613B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN112163676A (en) | Multitask service prediction model training method, device, equipment and storage medium | |
| CN111259222A (en) | Article recommendation method, system, electronic device and storage medium | |
| US20190287143A1 (en) | Retrieving reviews based on user profile information | |
| US20170076222A1 (en) | System and method to cognitively process and answer questions regarding content in images | |
| US20180218432A1 (en) | Recommendation integrated online digital sales service chat system | |
| CN112818224B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN111522940A (en) | Method and device for processing comment information | |
| CN111046292A (en) | Live broadcast recommendation method and device, computer-readable storage medium and electronic device | |
| CN111597446B (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
| CN111339406A (en) | Personalized recommendation method, device, equipment and storage medium | |
| CN111563198A (en) | Material recall method, device, equipment and storage medium | |
| CN111787042B (en) | Method and device for pushing information | |
| CN112702619A (en) | Anchor interface display method, device, equipment and storage medium | |
| CN111783013A (en) | Comment information publishing method, device, equipment and computer-readable storage medium | |
| CN113365138B (en) | Content display method and device, electronic equipment and storage medium | |
| CN114358871A (en) | Commodity recommendation method and electronic equipment | |
| CN113626638A (en) | Short video recommendation processing method and device, intelligent terminal and storage medium |
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 |