Message reminding method and system based on big data

Abstract

The invention provides a message reminding method and system based on big data, and relates to the technical field of message reminding, and the method comprises the steps: obtaining a historical chat record of a user, and a plurality of to-be-received video files in the chat record; generating a plurality of user interest pictures by using a variational auto-encoder based on the user historical chat records; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by a user; determining a plurality of video files needing message reminding based on a plurality of to-be-received video files in the chat record and a plurality of target interest pictures selected by the user; and receiving and storing the video file which needs to be subjected to message reminding and performing message reminding on the user, and the method can intelligently screen out the video file which the user may be interested in and perform message reminding.

Description

Technical Field

[0001] The present invention relates to the technical field of message reminder, and in particular to a message reminder method and system based on big data. Background Art

[0002] With the rapid development of the Internet and mobile communication technologies, social media and instant messaging applications have become an indispensable part of people's daily lives. In social media and instant messaging applications, users receive a large number of messages every day, including a large number of video files. If these video files are not effectively screened and managed, users may feel overloaded with information and find it difficult to find the content they are really interested in.

[0003] Therefore, how to effectively manage and screen these video files so that they can attract users' attention in a timely manner is a problem that needs to be solved urgently. Summary of the invention

[0004] The main technical problem solved by the present invention is how to intelligently filter out video files that a user may be interested in and issue a message reminder.

[0005] According to a first aspect, the present invention provides a message reminder method based on big data, including: obtaining a user's historical chat records and a plurality of video files to be received in the chat records; generating a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by the user; determining a plurality of video files that require message reminders based on the plurality of video files to be received in the chat records and the plurality of target interest pictures selected by the user; receiving and storing the video files that require message reminders and providing message reminders to the user.

[0006] In a possible implementation, the determining of the multiple video files for which message reminders are required based on the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user includes: Based on the interest determination model, the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user are processed to determine multiple key frames of each video file to be received and the user interest of each video file to be received; Constructing a message reminder graph structure, the message reminder graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a user node and a plurality of video file nodes, each video file node respectively establishing an edge with the user node, the node feature of the user node comprising a plurality of target interest pictures selected by the user, the node feature of each video file node comprising a plurality of key frames of each video file to be received, and the feature of each video file node respectively establishing an edge with the user node comprising the user interest level of each video file to be received; The message reminder graph structure is processed based on a graph convolutional network to determine multiple video files that require message reminders.

[0007] In a possible implementation, the input of the variational autoencoder is the user's historical chat records, and the output of the variational autoencoder is a plurality of pictures of user interest.

[0008] In one possible implementation, the interest determination model is a recurrent neural network model, the input of the interest determination model is a plurality of video files to be received in the chat record and a plurality of target interest pictures selected by the user, and the output of the interest determination model is a plurality of key frames of each video file to be received and the user interest of each video file to be received.

[0009] According to a second aspect, the present invention provides a message reminder system based on big data, comprising: An acquisition module is used to acquire a user's historical chat records and multiple video files to be received in the chat records; A generation module, used to generate a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; A display module, used to display the plurality of user interest pictures on the user software interface, and obtain a plurality of target interest pictures selected by the user; A determination module, used to determine a plurality of video files that need to be reminded of messages based on a plurality of video files to be received in the chat record and a plurality of target interest pictures selected by the user; The reminder module is used to receive and store the video file that needs message reminder and to send message reminder to the user.

[0010] In a possible implementation manner, the probability value determination module is further used to: Based on the interest determination model, the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user are processed to determine multiple key frames of each video file to be received and the user interest of each video file to be received; Constructing a message reminder graph structure, the message reminder graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a user node and a plurality of video file nodes, each video file node respectively establishing an edge with the user node, the node feature of the user node comprising a plurality of target interest pictures selected by the user, the node feature of each video file node comprising a plurality of key frames of each video file to be received, and the feature of each video file node respectively establishing an edge with the user node comprising the user interest level of each video file to be received; The message reminder graph structure is processed based on a graph convolutional network to determine multiple video files that require message reminders.

[0011] In a possible implementation, the input of the variational autoencoder is the user's historical chat records, and the output of the variational autoencoder is a plurality of pictures of user interest.

[0012] In one possible implementation, the interest determination model is a recurrent neural network model, the input of the interest determination model is a plurality of video files to be received in the chat record and a plurality of target interest pictures selected by the user, and the output of the interest determination model is a plurality of key frames of each video file to be received and the user interest of each video file to be received.

[0013] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement a method as described above, the method comprising: obtaining a user's historical chat records and a plurality of video files to be received in the chat records; generating a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by the user; determining a plurality of video files that require message reminders based on the plurality of video files to be received in the chat records and the plurality of target interest pictures selected by the user; receiving and storing the video files that require message reminders and providing message reminders to the user.

[0014] According to the fourth aspect, the present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned message reminder method based on big data, the method comprising: obtaining a user's historical chat records and a plurality of video files to be received in the chat records; generating a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by the user; determining a plurality of video files requiring message reminders based on the plurality of video files to be received in the chat records and the plurality of target interest pictures selected by the user; receiving and storing the video files requiring message reminders and providing message reminders to the user.

[0015] The present invention provides a message reminder method and system based on big data, the method comprising obtaining a user's historical chat records and a plurality of video files to be received in the chat records; generating a plurality of user interest pictures using a variational autoencoder based on the user's historical chat records; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by the user; determining a plurality of video files that require message reminders based on the plurality of video files to be received in the chat records and the plurality of target interest pictures selected by the user; receiving and storing the video files that require message reminders and providing message reminders to the user. The method can intelligently screen out video files that the user may be interested in and provide message reminders. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an application scenario of a message reminder method based on big data provided by an embodiment of the present invention; Figure 2 A flowchart of a message reminder method based on big data provided by an embodiment of the present invention; Figure 3 A schematic diagram of a process for determining multiple video files that require message reminders provided by an embodiment of the present invention; Figure 4 A schematic diagram of a message reminder system based on big data provided by an embodiment of the present invention; Figure 5 A schematic diagram of an electronic device provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0018] Figure 1 A schematic diagram of an application scenario of a message reminder method based on big data provided by an embodiment of the present invention. Figure 1 The application scenario of the message reminder method based on big data may include a server 11, a network 12, a terminal 13 and a storage device 14.

[0019] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 The message reminder method based on big data is shown in .

[0020] The network 12 may facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0021] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, and the like.

[0022] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of a message reminder method based on big data.

[0023] In an embodiment of the present invention, there is provided Figure 2 A message reminder method based on big data is shown, and the message reminder method based on big data includes steps S1 to S5: Step S1, obtaining a user's historical chat records and a plurality of video files to be received in the chat records.

[0024] User chat history records are all chat records sent and received by the user in the past period of time, including multiple types of messages such as text, pictures, audio and video. For example, user A sent multiple messages in the past chat records, such as "Today's weather is so nice", "This photo is so beautiful", and received some video files.

[0025] The video files to be received are video files in the current chat history that the user has not viewed or processed. For example, user A has received three video files in the current chat history, namely "video1.mp4", "video2.mp4" and "video3.mp4".

[0026] Step S2, using a variational autoencoder to generate multiple user interest pictures based on the user's historical chat records.

[0027] The input of the variational autoencoder is the user's historical chat records, and the output of the variational autoencoder is a plurality of user interest pictures.

[0028] The user interest picture is a picture generated by the variational autoencoder based on the user's historical chat records, and the user interest picture reflects the user's interest preferences. For example, the generated user interest picture may include the user's favorite scenery, characters, activities, etc.

[0029] Variational Autoencoder (VAE) is a generative model that can learn the latent representation of data and generate new samples from it. Variational Autoencoder consists of an encoder and a decoder. The encoder is used to learn the distribution of data and find the latent structure of the data. The decoder is used to generate new samples with similar characteristics from the latent structure learned by the encoder. The encoder converts the user's historical chat records into latent variables. These latent variables capture the key features and patterns in the chat records, such as common vocabulary, topics, emotions, etc. The decoder generates new samples from the latent variables sampled in the latent space. These new samples appear as new pictures in the data space that are similar to the original data.

[0030] User historical chat records contain the communication content of users at different times and situations, which covers information on users' interests, hobbies, emotions, etc. As a generative model, the variational autoencoder can generate new samples with similar features from the latent space. This means that even if the original data (user historical chat records) does not directly contain pictures, the variational autoencoder can generate pictures related to the user's interests by learning the latent structure of the data. For example, if users often discuss scenery and travel, the variational autoencoder can generate pictures reflecting beautiful scenery; if users often discuss sports and fitness, the variational autoencoder can generate pictures reflecting sports scenes.

[0031] Step S3, displaying the plurality of user interest pictures on the user software interface, and obtaining a plurality of target interest pictures selected by the user.

[0032] The user software interface is the interface through which the user interacts with the application, such as the main interface of a mobile phone application.

[0033] The target interest picture is a picture selected by the user from the generated multiple user interest pictures, and the target interest picture is the picture that the user is currently most interested in. For example, the user selects two target interest pictures of "beautiful scenery" and "sports competition" from the generated pictures.

[0034] Step S4, determining multiple video files that need to be messaged based on the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user.

[0035] In some embodiments, Figure 3 A schematic diagram of a process for determining a plurality of video files for which a message reminder is required is provided in an embodiment of the present invention, wherein the process for determining a plurality of video files for which a message reminder is required comprises steps S21 to S23: Step S21, based on the interest determination model, the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user are processed to determine multiple key frames of each video file to be received and the user interest of each video file to be received.

[0036] The interest determination model is a recurrent neural network model, the input of the interest determination model is a plurality of video files to be received in the chat record and a plurality of target interest pictures selected by the user, and the output of the interest determination model is a plurality of key frames of each video file to be received and the user interest of each video file to be received. The recurrent neural network model includes a recurrent neural network (RNN). The recurrent neural network model can process sequence data, capture sequence information, and output results based on the correlation between the previous and next data in the sequence. By processing a plurality of video files to be received in the chat records of continuous time periods with a recurrent neural network model, it is possible to output features that comprehensively consider the correlation between the sequences at each time point, so that the output features are more accurate and comprehensive.

[0037] Key frames are representative frames extracted from video files and can be used to reflect the video content.

[0038] User interest is a numerical value used to measure the user's interest in a certain video file.

[0039] In some embodiments, the interest determination model includes a key frame determination layer, a key frame association determination layer, and a user interest determination layer. The key frame determination layer, the key frame association determination layer, and the user interest determination layer all include a recurrent neural network. The input of the key frame determination layer is a plurality of video files to be received in the chat record, the output of the key frame determination layer is a plurality of key frames of each video file to be received, the input of the key frame association determination layer is a plurality of key frames of each video file to be received and a plurality of target interest pictures selected by the user, the output of the key frame association determination layer is the association between each key frame and each target interest picture selected by the user, the input of the user interest determination layer is the association between each key frame and each target interest picture selected by the user, and the output of the user interest determination layer is the user interest of each video file to be received.

[0040] The key frame determination layer is responsible for extracting key frames from video files. The output of this layer can be directly used to verify the effect of key frame extraction.

[0041] The key frame relevance determination layer is responsible for calculating the relevance between the key frame and the target interest picture selected by the user. The output of this layer can be directly used to evaluate the matching degree between the key frame and the user's interest.

[0042] The user interest determination layer is responsible for calculating the user interest of each video file based on the correlation between the key frame and the target interest picture. The output of this layer can be directly used to evaluate the user's interest in the video file.

[0043] Step S22, constructing a message reminder graph structure, wherein the message reminder graph structure includes multiple nodes and multiple edges between the multiple nodes, the multiple nodes include a user node and multiple video file nodes, each video file node establishes an edge with the user node, the node features of the user node include multiple target interest pictures selected by the user, the node features of each video file node include multiple key frames of each video file to be received, and the features of each video file node that establishes an edge with the user node include the user interest level of each video file to be received.

[0044] The message reminder graph structure is a graph structure used to represent the relationship between users and video files. The nodes in the graph include user nodes and video file nodes, and the edges represent the user's interest in the video file.

[0045] Nodes are vertices in the graph, representing users or video files.

[0046] An edge is a line connecting two nodes, indicating the user's interest in a video file.

[0047] Node features are the attributes of each node. The features of user nodes include multiple target interest pictures selected by the user, and the features of video file nodes include multiple key frames.

[0048] The edge feature is the attribute of the edge connecting two nodes, which indicates the user's interest in the video file.

[0049] For example, the user node is user A, and the video file nodes are the video files "video1.mp4", "video2.mp4", and "video3.mp4". The user node feature is the target interest pictures selected by user A, such as "beautiful scenery" and "sports competition". The video file node feature is the key frame of the video file "video1.mp4". The edge feature is that user A's user interest in the video file "video1.mp4" is 0.85.

[0050] Step S23: Process the message reminder graph structure based on a graph convolutional network to determine a plurality of video files for which message reminders are required.

[0051] Graph Convolutional Network (GCN) is a deep learning model used to process graph structure data. The input of the graph convolutional network is the message reminder graph structure, and the output of the graph convolutional network is multiple video files that need to be reminded. The graph convolutional network processes the nodes and edges in the graph through convolution operations and learns the feature representation of the nodes. The convolution operation can capture the local dependencies between nodes, so as to better understand the information in the graph structure.

[0052] The message reminder graph structure intuitively represents the relationship between users and video files through nodes and edges. The edge between the user node and the video file node represents the user's interest in the video file, and this representation method makes the relationship clear. The features of the user node include multiple target interest pictures selected by the user, and the features of the video file node include multiple key frames. These features integrate multiple aspects of the user and the video file. The features of the edge represent the user's interest in the video file, and this information helps to more accurately capture the relationship between the user and the video file. The message reminder graph structure is a graph structure data, which is very suitable for processing with a graph convolutional network. The graph convolutional network can capture the complex relationships in the graph structure, so as to more accurately determine the video files that need message reminders.

[0053] Step S5, receiving and storing the video file that needs to be reminded by a message and making a message reminder to the user.

[0054] For example, a video file that requires a message reminder may be downloaded and stored on the user's device.

[0055] Users can also be informed through the notification function of the application that there are new video files to view.

[0056] Based on the same inventive concept, Figure 4 A schematic diagram of a message reminder system based on big data provided by an embodiment of the present invention, the message reminder system based on big data includes: An acquisition module 41 is used to acquire a user's historical chat records and a plurality of video files to be received in the chat records; A generating module 42, configured to generate a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; A display module 43 is used to display the plurality of user interest pictures on the user software interface and obtain a plurality of target interest pictures selected by the user; A determination module 44, configured to determine a plurality of video files for which a message reminder is required based on a plurality of video files to be received in the chat record and a plurality of target interest pictures selected by the user; The reminder module 45 is used to receive and store the video file that needs to be reminded by a message and to remind the user by a message.

[0057] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, such as Figure 5 As shown, including: It includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and is configured to be executed by the processor 51 to implement the message reminder method based on big data as provided above, the method including: obtaining a user's historical chat records and a plurality of video files to be received in the chat records; generating a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by the user; determining a plurality of video files that need to be reminded of messages based on the plurality of video files to be received in the chat records and the plurality of target interest pictures selected by the user; receiving and storing the video files that need to be reminded of messages and making message reminders to the user.

[0058] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by the processor 51, implements the aforementioned message reminder method based on big data, the method comprising: obtaining a user's historical chat records and a plurality of video files to be received in the chat records; generating a plurality of user interest pictures using a variational autoencoder based on the user's historical chat records; displaying the plurality of user interest pictures on a user software interface, and obtaining a plurality of target interest pictures selected by the user; determining a plurality of video files that require message reminders based on the plurality of video files to be received in the chat records and the plurality of target interest pictures selected by the user; receiving and storing the video files that require message reminders and providing message reminders to the user.

[0059] The message reminder method based on big data provided in the embodiment of the present application can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (ultra-mobile personal computers, UMPCs), handheld computers, netbooks, personal digital assistants (personal digital assistants, PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (augmented reality, AR) \ virtual reality (virtualreality, VR) devices, smart home devices, car computers and other electronic devices, and the embodiment of the present application does not impose any restrictions on this.

[0060] Taking the mobile phone 100 as an example of the electronic device, Figure 6 A schematic structural diagram of the mobile phone 100 is shown.

[0061] like Figure 6 As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0062] The processing module 110 may include one or more processing units, for example, the processing module 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0063] The processing module 110 can be used to: obtain the user's historical chat records and multiple video files to be received in the chat records; generate multiple user interest pictures based on the user's historical chat records using a variational autoencoder; display the multiple user interest pictures on the user software interface, and obtain multiple target interest pictures selected by the user; determine multiple video files that need to be reminded of messages based on the multiple video files to be received in the chat records and the multiple target interest pictures selected by the user; receive and store the video files that need to be reminded of messages and make message reminders to the user.

[0064] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0065] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0066] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0067] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0068] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A message reminder method based on big data, characterized in that: include: Obtain the user's historical chat records and multiple video files to be received in the chat records; Generate multiple user interest pictures using a variational autoencoder based on the user's historical chat records; Displaying the plurality of user interest pictures on the user software interface, and obtaining the plurality of target interest pictures selected by the user; Determine multiple video files that need to be reminded of messages based on multiple video files to be received in the chat record and multiple target interest pictures selected by the user; Receive and store the video file that needs to be reminded by a message and remind the user by a message.

2. The message reminder method based on big data as claimed in claim 1, characterized in that: The determining of the multiple video files that need to be message reminded based on the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user includes: Based on the interest determination model, the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user are processed to determine multiple key frames of each video file to be received and the user interest of each video file to be received; Constructing a message reminder graph structure, the message reminder graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a user node and a plurality of video file nodes, each video file node respectively establishing an edge with the user node, the node feature of the user node comprising a plurality of target interest pictures selected by the user, the node feature of each video file node comprising a plurality of key frames of each video file to be received, and the feature of each video file node respectively establishing an edge with the user node comprising the user interest level of each video file to be received; The message reminder graph structure is processed based on a graph convolutional network to determine multiple video files that require message reminders.

3. The message reminder method based on big data as claimed in claim 1, characterized in that: The input of the variational autoencoder is the user's historical chat records, and the output of the variational autoencoder is a plurality of user interest pictures.

4. The message reminder method based on big data as claimed in claim 2, characterized in that: The interest determination model is a recurrent neural network model, the input of the interest determination model is multiple video files to be received in the chat record and multiple target interest pictures selected by the user, and the output of the interest determination model is multiple key frames of each video file to be received and the user interest of each video file to be received.

5. A message reminder system based on big data, characterized in that: include: An acquisition module is used to acquire a user's historical chat records and multiple video files to be received in the chat records; A generation module, used to generate a plurality of user interest pictures based on the user's historical chat records using a variational autoencoder; A display module, used to display the plurality of user interest pictures on the user software interface, and obtain a plurality of target interest pictures selected by the user; A determination module, used to determine a plurality of video files that need to be reminded of messages based on a plurality of video files to be received in the chat record and a plurality of target interest pictures selected by the user; The reminder module is used to receive and store the video file that needs message reminder and to send message reminder to the user.

6. The message reminder system based on big data as claimed in claim 5, characterized in that: The determining module is also used for: Based on the interest determination model, the multiple video files to be received in the chat record and the multiple target interest pictures selected by the user are processed to determine multiple key frames of each video file to be received and the user interest of each video file to be received; Constructing a message reminder graph structure, the message reminder graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a user node and a plurality of video file nodes, each video file node respectively establishing an edge with the user node, the node feature of the user node comprising a plurality of target interest pictures selected by the user, the node feature of each video file node comprising a plurality of key frames of each video file to be received, and the feature of each video file node respectively establishing an edge with the user node comprising the user interest level of each video file to be received; The message reminder graph structure is processed based on a graph convolutional network to determine multiple video files that require message reminders.

7. The message reminder system based on big data as claimed in claim 5, characterized in that: The input of the variational autoencoder is the user's historical chat records, and the output of the variational autoencoder is a plurality of user interest pictures.

8. The message reminder system based on big data as claimed in claim 6, characterized in that: The interest determination model is a recurrent neural network model, the input of the interest determination model is multiple video files to be received in the chat record and multiple target interest pictures selected by the user, and the output of the interest determination model is multiple key frames of each video file to be received and the user interest of each video file to be received.

9. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the big data-based message reminder method as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the message reminder method based on big data as described in any one of claims 1 to 4 is implemented.

Images