Hot event pushing method and device, electronic equipment and storage medium

Abstract

The invention provides a hot event pushing method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of media content pushing. According to the specific implementation scheme, a target hotspot event is determined based on a hotspot event preference vector and candidate hotspot events, and the hotspot event preference vector is obtained by performing inter-event feature cross learning on hotspot events in a historical hotspot event watching list of a user; and pushing the target hotspot event to the user. According to the invention, the hot events are pushed in a personalized manner, and the pushing precision is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of media content push technology, and in particular to a hot event push method, device, electronic device and storage medium. Background Art

[0002] With the development of mobile Internet, online media platforms have become an important channel for people to obtain and exchange information.

[0003] The behavior of users of online media platforms expressing their opinions and breaking news on the platform has led to a large number of hot events being produced every day. In order to increase user stickiness and expand the influence of the platform, online media platforms will spontaneously push hot events to users. However, since different users have different preferences for information, personalized push will play a significant role in improving push efficiency. Summary of the invention

[0004] The present invention provides a hot event push method, device, electronic device and storage medium, which can personalize the push of hot events and improve the push accuracy.

[0005] According to a first aspect of the present disclosure, a hot event push method is provided, comprising: determining a target hot event based on a hot event preference vector and candidate hot events, wherein the hot event preference vector is obtained by cross-learning inter-event features of hot events in a user's historical hot event viewing list; and pushing the target hot event to the user.

[0006] According to a second aspect of the present disclosure, a hot event pushing device is provided, including: a determination module is configured to determine a target hot event based on a hot event preference vector and candidate hot events, wherein the hot event preference vector is obtained by cross-learning inter-event features of hot events in a user's historical hot event viewing list; and a push module is configured to push the target hot event to the user.

[0007] According to the third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the hot event push method provided by the first aspect.

[0008] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the hot event push method provided by the first aspect.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the hot event push method provided in the first aspect is implemented.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is an exemplary system architecture diagram in which the present disclosure may be applied;

[0013] Figure 2 is a flow chart of an embodiment of a hot event push method according to the present disclosure;

[0014] Figure 3 is a flow chart of another embodiment of a hot event push method according to the present disclosure;

[0015] Figure 4 is a schematic diagram of the training process of the first feature cross-learning model according to the present disclosure;

[0016] Figure 5 is a flow chart of another embodiment of a hot event push method according to the present disclosure;

[0017] Figure 6 It is a structural schematic diagram of an embodiment of a hot event push device according to the present disclosure;

[0018] Figure 7 It is a block diagram of an electronic device used to implement the hot event push method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the hot event push method and hot event push device of the present disclosure can be applied.

[0021] like Figure 1 As shown, the system architecture 100 may include mobile devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the mobile devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables.

[0022] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104, or can interact with each other through server 105. Terminal devices 101, 102, 103 can be installed with various client applications, such as online news media applications, social media applications, and video media applications.

[0023] The terminal devices 101, 102, 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, laptop computers, desktop computers, etc. When the terminal devices 101, 102, 103 are software, they may be installed in the above electronic devices. They may be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0024] The server 105 can provide various interactive services. For example, the server 105 analyzes and processes the user's historical hot event viewing list obtained from the terminal devices 101, 102, and 103 to obtain a hot event preference vector; or obtains the hot event preference vector corresponding to the user from other servers or terminal devices; and then selects a target hot event from multiple candidate hot events based on the hot event preference vector and pushes it to the user.

[0025] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0026] It should be noted that the hot event push method provided in the embodiment of the present disclosure is generally executed by the server 105 , and accordingly, the hot event push device is generally set in the server 105 .

[0027] It should be understood that Figure 1 The number of mobile devices, networks and servers in the embodiment is only for illustration. Any number of mobile devices, networks and servers may be provided as required.

[0028] Continue to refer Figure 2 , which shows a process 200 of an embodiment of a hot event push method according to the present disclosure. The push method includes the following steps:

[0029] Step 201: Determine a target hot event based on the hot event preference vector and candidate hot events.

[0030] In this embodiment, the execution subject of the hot event push method (for example Figure 1 The server 105 shown in the figure can obtain the hot event preference vector corresponding to the user, and then select the target hot event to be pushed from the current candidate hot events according to the hot event preference vector.

[0031] The above-mentioned hot events refer to events or topics that have attracted widespread public attention and discussion due to social, economic, cultural and other factors during a specific period of time. These events are often timely, sudden and have a wide social influence, and can quickly become the focus of public opinion.

[0032] The above-mentioned hot event preference vector is used to characterize the user's viewing tendency for hot events, and it is obtained based on the user's historical hot event viewing list, wherein the user's historical hot event viewing list can be an event list consisting of hot events watched by the user within a preset historical period, or an event list consisting of the first preset number of hot events that the user's viewing time is closest to the current time, or an event list consisting of the first preset number of hot events that are determined to be within the preset historical period and are closest to the current time. The above-mentioned preset historical period can be the past few days, the past month, the past six months, etc.

[0033] As an example, the above hot event preference vector can be obtained by cross-learning the inter-event features of the hot events in the user's historical hot event viewing list, for example, identifying the theme of each hot event in the historical hot event viewing list, and performing inter-event feature cross-learning on the theme features of each hot event to obtain the hot event preference vector. Another example is to select key hot events from the historical hot event viewing list, where key hot events refer to hot events for which users have interactive operations such as forwarding, commenting, and liking; and perform inter-event feature cross-learning on each key hot event to obtain the hot event preference vector.

[0034] Step 202: Push target hot events to users.

[0035] In this embodiment, the execution subject pushes the target hot event to the user's client application after determining the target hot event.

[0036] In this embodiment, the hot event push method provided by the embodiment of the present disclosure determines the target hot event based on the hot event preference vector and the candidate hot events, wherein the hot event preference vector is obtained by cross-learning the features between the hot events in the user's historical hot event viewing list; and pushes the target hot event to the user. According to the user's hot event preference, personalized hot event push is performed to the user, which improves the push accuracy and enhances the user's viewing experience of hot events.

[0037] Continue to refer Figure 3 , which shows a process 300 of another embodiment of a hot event push method according to the present disclosure. The push method includes the following steps:

[0038] Step 301: Determine a target event based on a historical hot event viewing list.

[0039] In this embodiment, steps 301 to 304 are distinguished from Figure 2 The execution body of the hot event push method shown (for example Figure 1 The server 105 shown in FIG. 104 is executed by a server or a mobile terminal. In special cases, steps 301 to 304 may also be executed by Figure 2 The execution body of the hot event push method shown (for example Figure 1 After acquiring the user's historical hot event viewing list from the terminal devices 101, 102, 103, the subject of this step selects a target event from the historical hot event viewing list.

[0040] It should be noted that when users watch hot events, they may repeatedly watch the same hot event pushed by different pushers. Therefore, the number of list items in the user's historical hot event viewing list is not equal to the number of hot events included in the list.

[0041] As an example, the above-mentioned determining the target attention event based on the historical hot event viewing list includes: determining the viewing time of each hot event in the historical hot event viewing list; and taking the hot events with a viewing time greater than a preset viewing time threshold or the second preset number of hot events with the highest viewing time ranking as the target attention event.

[0042] As another example, the above-mentioned determining the target attention event based on the historical hot event viewing list includes: determining the average viewing time of each hot event in the historical hot event viewing list; and determining the hot event with an average viewing time greater than a preset viewing time as the target attention event.

[0043] The above preset viewing time is the average viewing time of all hot events in the historical hot event viewing list.

[0044] As another example, the above-mentioned determining the target event based on the historical hot event viewing list includes: determining the viewing count of each hot event in the historical hot event viewing list, and determining the hot event with a viewing count greater than a threshold as the target event.

[0045] Step 302: Determine a hot event sequence corresponding to the target event.

[0046] After determining the target event, the execution subject of this step generates a hot event sequence corresponding to the target event.

[0047] As an example, the above determination is made whether the number of target attention events is less than a third preset number, the third preset number represents a predetermined sequence length, and in response to the number of target attention events being less than the third preset number, the insufficient part is filled with blank events; and then a hot event sequence is generated. In response to the number of target attention events being not less than the third preset number, a third preset number of hot events are selected from the target attention events to generate a hot event sequence.

[0048] Step 303: Determine the hot event feature coding sequence corresponding to the hot event sequence.

[0049] After determining the hot event sequence, the execution subject of this step determines the hot event feature coding sequence corresponding to the hot event sequence.

[0050] As an example, the above-mentioned determination of the hot event feature coding sequence corresponding to the hot event sequence includes: determining the event name coding sequence corresponding to the hot event sequence; and determining the hot event feature coding sequence based on the event name coding sequence.

[0051] As an implementable manner, the above-mentioned determination of the hot event feature coding sequence based on the event name coding sequence includes: determining the event name coding sequence as the hot event feature coding sequence.

[0052] Among them, the event name is a text representation that can reflect the core content of the hot event. Therefore, the event name of the hot event can be used as a feature of the hot event to achieve accurate representation of the hot event.

[0053] As another achievable method, the above-mentioned determination of the hot event feature coding sequence based on the event name coding sequence includes: determining the heat value coding sequence corresponding to the hot event sequence; adding the event name coding sequence and the heat value coding sequence bit by bit to obtain the hot event feature coding sequence.

[0054] Among them, the heat value is an important indicator of the spread of hot events. Introducing the heat value into the characteristics of hot events can more accurately represent hot events. The above implementation adopts a method similar to constructing position encoding for the input sequence of the transformer model, and the heat value encoding features of each hot event in the hot event are included in the corresponding event name encoding features.

[0055] In this embodiment, the event name coding sequence or heat value coding sequence corresponding to the hot event sequence is determined, and the pre-trained large prediction model (Large Language Model, LLM model) can be used to embed the event name or heat value of each hot event in the hot event sequence to obtain the event name coding sequence or heat value coding sequence corresponding to the hot event sequence. The above-mentioned large prediction model (Large Language Model, LLM model) is a type of basic model that can understand and generate natural language and other types of content after a large amount of data training to perform various tasks. It includes a bidirectional encoder representation model (Bidirectional Encoder Representations from Transformers, BERT model), a Chinese and English semantic vector model (BAAI General Embedding, BGE model), etc.

[0056] Step 304: Perform inter-event feature cross-learning on the hot event feature coding sequence to obtain a hot event preference vector.

[0057] After determining the hot event feature coding sequence, the execution subject of this step performs inter-event feature cross-learning on the hot event feature coding sequence to obtain the hot event preference vector.

[0058] As an example, the above-mentioned inter-event feature cross-learning of the hot event feature coding sequence to obtain the hot event preference vector includes: inputting the hot event feature coding sequence into the first feature cross-learning model to obtain the output hot event preference vector; wherein the first feature cross-learning model is a converter model for inter-event feature cross-learning;.

[0059] Among them, the above-mentioned converter model refers to the Transformer model. The execution subject of this step uses the hot event feature encoding sequence as the input representation of the Transformer model, and uses the self-attention mechanism in the self-attention layer in each encoder to perform cross-event feature learning. The output of the learned Transformer model is used as the hot event preference vector.

[0060] As another example, the above-mentioned inter-event feature cross-learning of the hot event feature coding sequence to obtain the hot event preference vector includes: determining the user attribute feature coding vector corresponding to the user; inputting the hot event feature coding sequence and the user attribute feature coding vector into the second feature cross-learning model to obtain the output hot event preference vector; wherein the second feature cross-learning model is a converter model for inter-event feature cross-learning and cross-learning of user attribute features and event features.

[0061] The user attribute feature encoding vector corresponding to the user is obtained by encoding the user attribute information. The user attribute information refers to the basic information of the user obtained after the user's authorization, including but not limited to age, gender, zodiac sign, etc.

[0062] Among them, the above-mentioned converter model refers to the Transformer model. The execution subject of this step uses the hot event feature encoding sequence as the input representation of the Transformer model, and inputs the user attribute feature encoding vector in the feedforward neural network of the Transformer model. The self-attention mechanism is used in the self-attention layer in each encoder to perform cross-event feature learning, and user attribute features and event features are cross-learned in the feedforward neural network layer. The output of the learned Transformer model is used as the hot event preference vector.

[0063] The second feature cross-learning model mentioned above introduces user-side features to complete feature cross-learning between user features and time features, thereby improving the performance of hot event preference learning.

[0064] The training processes of the first feature cross-learning model and the second feature cross-learning model are roughly the same, and the first feature cross-learning model is used as an example for explanation.

[0065] See also Figure 4 A schematic diagram of the training process of the first disclosed feature cross-learning model, the training process comprising:

[0066] Step 1: Obtain sample data, each sample includes a user hot event sequence; in particular, the sample data of the second feature cross-learning model includes a user hot event sequence and a user attribute feature encoding vector.

[0067] Step 2: Perform data enhancement on the sample data.

[0068] Step 3: Use the pre-trained Large Language Model (LLM model) to perform event name embedding coding (or event name embedding coding and heat value embedding coding) on ​​the hot event sequence in the enhanced sample data to obtain the hot event feature coding sequence.

[0069] Step 4: Perform comparative learning on the hot event feature coding sequence. Specifically, introduce a comparative learning structure in the encoder part of the Transformer model. The comparative learning structure has a first branch and a second branch that is completely consistent with the first branch. The first branch is formed by connecting the encoder of the Transformer model with a fully connected layer, and the second branch uses momentum update to update parameters. Input the hot event feature coding sequence into the first branch and the second branch respectively to obtain the corresponding first output vector and second output vector.

[0070] Step 5: Input the first output vector into a fully connected layer so that the spatial dimension of the first output vector is updated to be consistent with the second output vector.

[0071] Step 6: Use the spatial L2 distance between the updated first output vector and the second output vector as the contrast loss, and use the contrast loss to optimize the model parameters.

[0072] The above training process adopts a contrastive learning method to improve the accuracy of model training.

[0073] Step 305: Determine a target hot event based on the hot event preference vector and the candidate hot events.

[0074] Step 306: Push the target hot event to the user.

[0075] Step 305 to step 306 are Figure 2 The execution body of the hot event push method shown (for example Figure 1 The server 105 shown in FIG. 1 is executed, and the specific operations of step 305 and step 306 are already Figure 2 In the illustrated embodiment, steps 201 and 202 are described in detail and will not be repeated here.

[0076] In this embodiment, the hot event push method provided by the embodiment of the present disclosure selects hot events that the user pays more attention to from a historical hot event viewing list to generate a hot event sequence; based on the event name and heat value of the hot event, determines the hot event feature coding sequence corresponding to the hot event sequence; cross-event feature learning is performed on the hot event feature coding sequence to obtain a hot event preference vector, and accurate learning of the user's hot event preferences is achieved through machine learning. Then, according to the user's hot event preferences, personalized hot event push is performed to the user, thereby improving the push accuracy and enhancing the user's viewing experience of hot events.

[0077] Continue to refer Figure 5 , which shows a process 500 of another embodiment of a hot event push method according to the present disclosure. The push method includes the following steps:

[0078] Step 501: Determine a target event based on a historical hot event viewing list, wherein the target event is a hot event whose average viewing time is longer than a preset viewing time.

[0079] In this embodiment, steps 501 to 504 are distinguished from Figure 2 The execution body of the hot event push method shown (for example Figure 1 The server 105 shown in FIG. 100 is executed by a server or a mobile terminal. In special cases, steps 501 to 504 may also be executed by Figure 2 The execution body of the hot event push method shown (for example Figure 1 Server 105 shown) is executed.

[0080] The specific operations from step 501 to step 504 are described in Figure 3 In the illustrated embodiment, steps 301 to 304 are described in detail and will not be repeated here.

[0081] Step 502: Determine a hot event sequence corresponding to the target event.

[0082] Step 503: Determine the hot event feature coding sequence corresponding to the hot event sequence.

[0083] Step 504: Perform inter-event feature cross-learning on the hot event feature coding sequence to obtain a hot event preference vector.

[0084] Step 505: Determine the predicted viewing duration of the candidate hot event based on the hot event preference vector and the candidate hot event.

[0085] Step 505 and step 507 are composed of Figure 2 The execution body of the hot event push method shown (for example Figure 1 After determining the hot event preference vector, the subject executing this step can use the hot event preference vector to select a target hot event to be pushed from a plurality of candidate hot events.

[0086] As an example, the above-mentioned method of determining the predicted viewing time of candidate hot events based on the hot event preference vector and the candidate hot events includes: determining the feature coding vector of the candidate hot event; splicing the feature coding vector and the hot event preference vector to obtain a spliced ​​vector; inputting the spliced ​​vector into a preset viewing time prediction model to obtain the output predicted viewing time of the candidate hot event.

[0087] Among them, the method for determining the feature coding vector of the candidate hot event is consistent with the method for determining the hot event feature coding sequence corresponding to the above-mentioned hot event sequence.

[0088] The training process of the above viewing time prediction model includes:

[0089] Step A: obtaining a training sample, wherein the training sample includes a hot event and an actual predicted duration of the hot event;

[0090] Step B: input the features (event name or event name and heat value) of the hot events in the training sample into a large language model (LLM model), and determine the feature encoding vector of the hot events based on the output results;

[0091] Step C: concatenate the feature encoding vector of the hot event with the hot event preference vector in the fully connected layer to obtain a concatenated vector; wherein the function of the fully connected layer is to update the spatial dimension of the feature encoding vector of the hot event to be consistent with the hot event preference vector;

[0092] Step D: Input the concatenated vector into the initial prediction network to determine the predicted viewing time of the hot event;

[0093] Step E: Using the cross entropy loss between the predicted viewing time and the actual viewing time of the hot events as the loss function, update the parameters of the initial prediction network;

[0094] Step F: Repeat the above steps until the preset iteration termination condition is reached, and use the final prediction network as the viewing time prediction model.

[0095] Step 506: Determine a target hot event based on the predicted viewing duration.

[0096] The execution subject of this step determines the target hot event based on the predicted viewing time after the candidate hot event is predicted to be viewed for a long time.

[0097] As an example, the above-mentioned determining the target hot event based on the predicted viewing time includes: sorting the predicted viewing time in descending order, and taking the candidate hot events corresponding to the fourth preset number of predicted viewing times located at the front of the sequence as the target hot event.

[0098] As another example, the above-mentioned determining the target hot event based on the predicted viewing time includes: determining the candidate hot event whose predicted viewing time is greater than a preset viewing time threshold as the target hot event.

[0099] Step 507: Push the target hot event to the user.

[0100] In this embodiment, the hot event push method provided by the embodiment of the present disclosure sends the user's hot event preference vector and the feature vector of the candidate hot event into a pre-trained viewing time prediction model to predict the viewing time of the candidate hot event, and then selects and pushes the target hot event according to the predicted viewing time, thereby improving the push accuracy.

[0101] Continue to refer Figure 6 , Figure 6 A structural diagram 600 of an embodiment of a hot event push device disclosed in the present invention is illustrated; Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0102] like Figure 6 As shown, the hot event push device of this embodiment may include a determination module 601 and a push module 602. The determination module 601 is configured to determine the target hot event based on the hot event preference vector and the candidate hot events, wherein the hot event preference vector is obtained by cross-learning the features between the hot events in the user's historical hot event viewing list; the push module 602 is configured to push the target hot event to the user.

[0103] In this embodiment, the specific processing of the determination module 601 and the push module 602 and the technical effects thereof can be referred to in Figure 2 The relevant descriptions of steps 201 - 202 in the corresponding embodiment are not repeated here.

[0104] In some optional implementations of this embodiment, the device also includes a hot event preference vector generation module 603; the hot event preference vector generation module 603 includes: a first determination submodule is configured to determine a target event of interest based on a historical hot event viewing list, wherein the target event of interest is a hot event whose average viewing time is longer than a preset viewing time; a second determination submodule is configured to determine a hot event sequence corresponding to the target event of interest; a third determination submodule is configured to determine a hot event feature coding sequence corresponding to the hot event sequence; and a cross-learning submodule is configured to perform inter-event feature cross-learning on the hot event feature coding sequence to obtain a hot event preference vector.

[0105] In some optional implementations of this embodiment, the third determination submodule includes: a first determination unit is configured to determine an event name coding sequence corresponding to a hot event sequence; and a second determination unit is configured to determine a hot event feature coding sequence based on the event name coding sequence.

[0106] In some optional implementations of this embodiment, the second determination unit includes: the first determination subunit is configured to determine the heat value coding sequence corresponding to the hot event sequence; the coding fusion subunit is configured to add the event name coding sequence and the heat value coding sequence bit by bit to obtain the hot event feature coding sequence.

[0107] In some optional implementations of this embodiment, the cross-learning submodule includes: a first cross-learning unit is configured to input a hot event feature encoding sequence into a first feature cross-learning model to obtain an output hot event preference vector; wherein the first feature cross-learning model is a converter model for feature cross-learning between events.

[0108] In some optional implementations of this embodiment, the cross-learning submodule also includes: a third determination unit is configured to determine a user attribute feature encoding vector corresponding to the user; the second cross-learning unit is configured to input the hot event feature encoding sequence and the user attribute feature encoding vector into a second feature cross-learning model to obtain an output hot event preference vector; wherein the second feature cross-learning model is a converter model for feature cross-learning between events and cross-learning of user attribute features and event features.

[0109] In some optional implementations of this embodiment, the preset viewing time is the average viewing time of all hot events in the historical hot event viewing list.

[0110] In some optional implementations of this embodiment, the determination module includes: a fourth determination submodule is configured to determine the predicted viewing time of the candidate hot event based on the hot event preference vector and the candidate hot event; and a fifth determination submodule is configured to determine the target hot event based on the predicted viewing time.

[0111] In some optional implementations of this embodiment, the fourth determination submodule includes: the sixth determination unit is configured to determine the feature coding vector of the candidate hot event; the splicing unit is configured to splice the feature coding vector and the hot event preference vector to obtain a spliced ​​vector; the prediction unit is configured to input the spliced ​​vector into a preset viewing time prediction model to obtain the output predicted viewing time of the candidate hot event.

[0112] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0113] Figure 7A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0114] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0115] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0116] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as hot event push methods. For example, in some embodiments, the hot event push method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the hot event push method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the hot event push method in any other appropriate manner (e.g., by means of firmware).

[0117] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0119] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the systems and techniques described herein 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 the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 can be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0122] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0123] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0124] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0125] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A hot event push method, comprising: Determine a target hot event based on a hot event preference vector and candidate hot events, wherein the hot event preference vector is obtained by cross-learning event features between hot events in a user's historical hot event viewing list; Push the target hot event to the user.

2. The method according to claim 1, wherein: The hot event preference vector is obtained by the following steps: Based on the historical hot event viewing list, determining a target event of interest, wherein the target event of interest is a hot event whose average viewing time is longer than a preset viewing time; Determine a hot event sequence corresponding to the target event of interest; Determine a hot event feature coding sequence corresponding to the hot event sequence; The hot event feature coding sequence is subjected to inter-event feature cross-learning to obtain the hot event preference vector.

3. The method according to claim 2, wherein: The step of determining the hot event feature coding sequence corresponding to the hot event sequence comprises: Determine an event name coding sequence corresponding to the hot event sequence; The hot event feature coding sequence is determined based on the event name coding sequence.

4. The method according to claim 3, wherein: The step of determining the hot event feature coding sequence based on the event name coding sequence includes: Determine a heat value encoding sequence corresponding to the hot event sequence; The event name coding sequence and the heat value coding sequence are added bit by bit to obtain the hot event feature coding sequence.

5. The method according to claim 2, wherein: The performing inter-event feature cross-learning on the hot event feature coding sequence to obtain the hot event preference vector includes: The hot event feature coding sequence is input into a first feature cross-learning model to obtain the output hot event preference vector; wherein the first feature cross-learning model is a converter model for feature cross-learning between events.

6. The method according to claim 2, wherein: The performing inter-event feature cross-learning on the hot event feature coding sequence to obtain the hot event preference vector includes: Determine a user attribute feature encoding vector corresponding to the user; The hot event feature coding sequence and the user attribute feature coding vector are input into a second feature cross-learning model to obtain the output hot event preference vector; wherein the second feature cross-learning model is a converter model used for feature cross-learning between events and cross-learning of user attribute features and event features.

7. The method according to claim 2, wherein: The preset viewing time It is the average viewing time of all hot events in the historical hot event viewing list.

8. The method according to any one of claims 1 to 7, wherein: The step of determining a target hot event based on the hot event preference vector and the candidate hot events includes: Based on the hot event preference vector and the candidate hot event, determining the predicted viewing time of the candidate hot event; Based on the predicted viewing time, the target hot event is determined.

9. The method according to claim 8, wherein: The step of determining the predicted viewing duration of the candidate hot event based on the hot event preference vector and the candidate hot event includes: Determine a feature encoding vector of the candidate hot event; Concatenating the feature coding vector and the hot event preference vector to obtain a concatenated vector; The concatenated vector is input into a preset viewing time prediction model to obtain the output predicted viewing time of the candidate hot event.

10. A hot event push device, comprising: A determination module is configured to determine a target hot event based on a hot event preference vector and candidate hot events, wherein the hot event preference vector is obtained by cross-learning event features between hot events in a user's historical hot event viewing list; The push module is configured to push the target hot event to the user.

11. The device according to claim 10, wherein: The device also includes a hot event preference vector generation module; The hot event preference vector generation module includes: A first determination submodule is configured to determine a target event based on the historical hot event viewing list, wherein the target event is a hot event whose average viewing time is longer than a preset viewing time; A second determination submodule is configured to determine a hot event sequence corresponding to the target event of interest; A third determination submodule is configured to determine a hot event feature coding sequence corresponding to the hot event sequence; The cross-learning submodule is configured to perform inter-event feature cross-learning on the hot event feature coding sequence to obtain the hot event preference vector.

12. The device according to claim 11, wherein The third determining submodule includes: A first determining unit is configured to determine an event name coding sequence corresponding to the hot event sequence; The second determining unit is configured to determine the hot event feature coding sequence based on the event name coding sequence.

13. The device according to claim 12, wherein: The second determining unit includes: A first determining subunit is configured to determine a heat value coding sequence corresponding to the hot event sequence; The coding fusion subunit is configured to add the event name coding sequence and the heat value coding sequence bit by bit to obtain the hot event feature coding sequence.

14. The device according to claim 11, wherein: The cross-learning submodule includes: The first cross-learning unit is configured to input the hot event feature coding sequence into a first feature cross-learning model to obtain the output hot event preference vector; wherein the first feature cross-learning model is a converter model for feature cross-learning between events.

15. The device according to claim 11, wherein The cross-learning submodule further includes: A third determining unit is configured to determine a user attribute feature encoding vector corresponding to the user; The second cross-learning unit is configured to input the hot event feature coding sequence and the user attribute feature coding vector into a second feature cross-learning model to obtain the output hot event preference vector; wherein the second feature cross-learning model is a converter model for feature cross-learning between events and cross-learning of user attribute features and event features.

16. The device according to claim 11, wherein The preset viewing time is the average viewing time of all hot events in the historical hot event viewing list.

17. The device according to any one of claims 10 to 16, wherein: The determining module comprises: A fourth determination submodule is configured to determine the predicted viewing duration of the candidate hot event based on the hot event preference vector and the candidate hot event; The fifth determination submodule is configured to determine the target hot event based on the predicted viewing time.

18. The device according to claim 17, wherein: The fourth determining submodule includes: A sixth determining unit is configured to determine a feature coding vector of the candidate hot event; A concatenation unit is configured to concatenate the feature coding vector and the hot event preference vector to obtain a concatenated vector; The prediction unit is configured to input the spliced ​​vector into a preset viewing time prediction model to obtain the output predicted viewing time of the candidate hot event.

19. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor, wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 9.

21. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 9.

Images