An advertisement delivery method and system based on big data

Abstract

The application provides an advertisement putting method and system based on big data, and relates to the technical field of advertisement putting.The method comprises the following steps: obtaining text description information of a plurality of advertisements to be put; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be put by using a text processing model; clustering the text description information of the plurality of advertisements to be put based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target putting advertisements based on the K clusters; and putting the target putting advertisements to users, so that the method can accurately screen out advertisements that are interesting to users.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of advertisement delivery, and particularly relates to an advertisement delivery method and system based on big data. BACKGROUND

[0002] With the rapid development of Internet technology, advertisement delivery has become an important means for enterprises to promote products and services. Traditional advertisement delivery is usually based on simple attributes of users (such as age, gender, geographic location, etc.) for rough classification and delivery, which cannot accurately capture the interests and preferences of users, resulting in poor advertisement effect. The advertisement content does not match the actual needs and interests of users, and users may feel disturbed, even disgusted, affecting user experience. Invalid advertisement delivery not only wastes the advertisement budget of enterprises, but also occupies network bandwidth and user's time, reducing the overall return on investment of advertisements. Because the advertisement content does not match the actual interests of users, users often feel disturbed, even disgusted, affecting user experience.

[0003] Therefore, how to accurately screen out advertisements that users are interested in is a problem to be solved at present. SUMMARY

[0004] The technical problem solved by the present application is how to accurately screen out advertisements that users are interested in.

[0005] According to a first aspect, the present application provides an advertisement delivery method based on big data, comprising: obtaining text description information of a plurality of advertisements to be delivered; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be delivered using a text processing model; clustering the text description information of the plurality of advertisements to be delivered based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target delivery advertisements based on the K clusters; and delivering users based on the target delivery advertisements.

[0006] In a possible implementation manner, the determining of the target delivery advertisements based on the K clusters comprises:

[0007] inputting the K clusters into a screening model to screen one preselected advertisement from each cluster; generating a promoted picture of the preselected advertisement in each cluster based on text description information of the preselected advertisement in each cluster using a diffusion model; displaying the promoted picture of the preselected advertisement in each cluster, and obtaining a selected picture selected by a user from the promoted picture of the preselected advertisement in each cluster and a cluster where the selected picture is located; constructing an advertisement graph structure based on the cluster where the selected picture is located, the advertisement graph structure including a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes including one selected picture node and a plurality of to-be-launched advertisement nodes, the selected picture node being a center node, and the plurality of to-be-launched advertisement nodes each establishing an edge with the one selected picture node; and determining a plurality of target launched advertisements based on graph attention network processing of the advertisement graph structure.

[0008] In a possible implementation, the node feature of the one selected picture node includes text description information of an advertisement corresponding to the selected picture, the node feature of each to-be-launched advertisement node includes text description information of a to-be-launched advertisement, and the feature of the edge established between the one selected picture node and each to-be-launched advertisement node includes a Euclidean distance between the one selected picture node and the to-be-launched advertisement node.

[0009] In a possible implementation, the input of the diffusion model is text description information of the preselected advertisement in each cluster, and the output of the diffusion model is the promoted picture of the preselected advertisement in each cluster.

[0010] According to a second aspect, the present application provides an advertisement launching system based on big data, comprising:

[0011] a first obtaining module configured to obtain text description information of a plurality of to-be-launched advertisements;

[0012] a text processing module configured to determine a K value in a K-means clustering algorithm based on the text description information of the plurality of to-be-launched advertisements using a text processing model;

[0013] a second obtaining module configured to cluster the text description information of the plurality of to-be-launched advertisements based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters;

[0014] a determining module configured to determine a plurality of target launched advertisements based on the K clusters;

[0015] a launching module configured to launch the target launched advertisements to a user.

[0016] In a possible implementation, the determining module is further configured to:

[0017] input the K clusters into a screening model to screen one preselected advertisement from each cluster;

[0018] generate a promotion picture of the pre-selected advertisement in each cluster based on the textual description information of the pre-selected advertisement in each cluster using a diffusion model;

[0019] display the promotion picture of the pre-selected advertisement in each cluster, and obtain a selected picture selected by a user from the promotion picture of the pre-selected advertisement in each cluster and a cluster where the selected picture is located;

[0020] construct an advertisement graph structure based on the cluster where the selected picture is located, the advertisement graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a selected picture node and a plurality of to-be-launched advertisement nodes, the selected picture node being a center node, and the plurality of to-be-launched advertisement nodes each establishing an edge with the selected picture node;

[0021] determine a plurality of target launched advertisements based on processing the advertisement graph structure using a graph attention network.

[0022] In a possible implementation, the node feature of the selected picture node comprises the textual description information of the advertisement corresponding to the selected picture, the node feature of each to-be-launched advertisement node comprises the textual description information of the to-be-launched advertisement, and the feature of the edge established between the selected picture node and each to-be-launched advertisement node comprises the Euclidean distance between the selected picture node and the to-be-launched advertisement node.

[0023] In a possible implementation, the input of the diffusion model is the textual description information of the pre-selected advertisement in each cluster, and the output of the diffusion model is the promotion picture of the pre-selected advertisement in each cluster.

[0024] According to a third aspect, embodiments of the present application provide 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 the method as described above, the method comprising: obtaining textual description information of a plurality of to-be-launched advertisements; determining a K value in a K-means clustering algorithm based on the textual description information of the plurality of to-be-launched advertisements using a text processing model; clustering the textual description information of the plurality of to-be-launched advertisements based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target launched advertisements based on the K clusters; and launching the target launched advertisements to a user.

[0025] According to a fourth aspect, the embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the foregoing provided big data-based advertisement delivery method, and the method comprises the following steps: obtaining text description information of a plurality of advertisements to be delivered; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be delivered by using a text processing model; clustering the text description information of the plurality of advertisements to be delivered based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target delivery advertisements based on the K clusters; and delivering users based on the target delivery advertisements.

[0026] The application provides a big data-based advertisement delivery method and system, which comprises the following steps: obtaining text description information of a plurality of advertisements to be delivered; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be delivered by using a text processing model; clustering the text description information of the plurality of advertisements to be delivered based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target delivery advertisements based on the K clusters; and delivering users based on the target delivery advertisements, so that the advertisements interested by the users can be accurately screened out. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 An application scenario diagram of the big data-based advertisement delivery method provided by the embodiment of the application is shown in the figure.

[0028] Figure 2 A flowchart of the big data-based advertisement delivery method provided by the embodiment of the application is shown in the figure.

[0029] Figure 3 A flowchart of determining a plurality of target delivery advertisements provided by the embodiment of the application is shown in the figure.

[0030] Figure 4 A schematic diagram of the big data-based advertisement delivery system provided by the embodiment of the application is shown in the figure.

[0031] Figure 5 A schematic diagram of the electronic device provided by the embodiment of the application is shown in the figure.

[0032] Figure 6 A structural schematic diagram of the electronic device provided by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0033] The application will be described in further detail below with specific reference being made to the drawings. Like elements are referenced with like numerals throughout the several figures of the drawings. In the following description, numerous specific details are described to provide a thorough understanding of the application. However, it will be apparent to one skilled in the art that the application can be practiced without many of these specific details. In some instances, well-known structures have not been described in detail in order to avoid obscuring the application. Also, some terminology can be used in the description for the sake of clarity.

[0034] Figure 1 An application scenario of the advertisement putting method based on big data provided in the embodiments of the application is shown in FIG. 1. Figure 1 The application scenario of the advertisement putting method based on big data can include a server 11, a network 12, a terminal 13 and a storage device 14.

[0035] In some embodiments, the server 11 can be a single server or a group of servers. The server 11 can 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 can be configured to perform the advertisement putting method based on big data shown in FIG. 1. Figure 2

[0036] The network 12 can facilitate the exchange of information and / or data. In some embodiments, the network 12 can be any form of wired or wireless network, or any combination thereof.

[0037] The terminal 13 can refer to one or more terminal devices used by a user. In some embodiments, the terminal 13 can include one or more combinations of a mobile device, a tablet computer, a laptop computer, etc.

[0038] The storage device 14 can store data and / or instructions, for example, the storage device 14 can store data instructions of the advertisement putting method based on big data.

[0039] In the embodiments of the application, an advertisement putting method based on big data is provided, as shown in FIG. 1. The advertisement putting method based on big data includes steps S1-S5. Figure 2

[0040] Step S1, obtaining text description information of a plurality of advertisements to be put.

[0041] ​​The textual description information includes the title, text content, and the like of each advertisement, and is used to describe the main information of the advertisement, such as product characteristics, promotional activities, and the like. In some embodiments, the textual description information of the advertisement can be directly read from the database of the advertisement platform.

[0042] In step S2, a value K in a K-means clustering algorithm is determined based on the textual description information of the plurality of advertisements to be delivered, by using a text processing model.

[0043] The text processing model is a deep neural network model, the input of the text processing model is the textual description information of the plurality of advertisements to be delivered, and the output of the text processing model is the value K in the K-means clustering algorithm. The deep neural network model includes a deep neural network (DNN). The deep neural network can include a plurality of processing layers, each processing layer is composed of a plurality of neurons, and each neuron performs matrix transformation on data. The K-means clustering algorithm is an unsupervised learning algorithm, and the K-means clustering algorithm is used to divide a data set into K clusters, and the data points in each cluster have similar features. The value K is the number of clusters in the K-means clustering algorithm. By using the deep neural network model to extract features from the textual description information of the advertisement and automatically determining the value K in the K-means clustering algorithm, the accuracy and effect of clustering can be improved. The traditional K value determination method (such as elbow method, contour coefficient method) depends on artificial setting or simple statistical method, and the use of deep neural network model can more scientifically determine the value K, avoiding the subjectivity and uncertainty of artificial setting, and improving the accuracy and effect of clustering.

[0044] In step S3, the textual description information of the plurality of advertisements to be delivered is clustered based on the K-means clustering algorithm and the value K in the K-means clustering algorithm to obtain K clusters.

[0045] Each of the K clusters includes a type of advertisements to be delivered. For example, advertisements A, B, C, and D are clustered, and assuming that the value K is 3, three clusters can be obtained, cluster 1 [advertisements A and B], cluster 2 [advertisement C], and cluster 3 [advertisement D].

[0046] In some embodiments, the textual description information of the advertisement can be converted into a vector representation by a BERT model, and then clustered by a K-means clustering algorithm to obtain K clusters.

[0047] In step S4, a plurality of target delivery advertisements are determined based on the K clusters.

[0048] In some embodiments, Figure 3 A flowchart for determining a plurality of target delivery advertisements is provided for an embodiment of the present application, and the determination of the plurality of target delivery advertisements includes steps S21-S25.

[0049] Step S21, input the K clusters to a screening model to screen one pre-selected advertisement from each cluster.

[0050] The screening model is a deep neural network model, the input of the screening model is the K clusters, and the output of the screening model is one pre-selected advertisement screened from each cluster. As an example, assuming that the value of K is 3, there are 3 clusters, then the screening model screens one pre-selected advertisement from each cluster, and 3 pre-selected advertisements are obtained.

[0051] The screening model selects the most representative and attractive advertisement from each cluster, providing a basis for subsequent generation of promotion pictures and user selection.

[0052] Step S22, generating a promotion picture of the pre-selected advertisement in each cluster based on the textual description information of the pre-selected advertisement in each cluster using a diffusion model.

[0053] The input of the diffusion model is the textual description information of the pre-selected advertisement in each cluster, and the output of the diffusion model is the promotion picture of the pre-selected advertisement in each cluster.

[0054] The diffusion model is a generative model, and the diffusion model is used to generate a corresponding image according to a given text. In some embodiments, the diffusion model includes DALL-E, Stable Diffusion, etc. For example, input the textual description information "the latest smart phone, super long endurance, high-definition camera" of the advertisement A to the diffusion model, and the diffusion model generates a high-definition picture showing the latest smart phone. The diffusion model can generate personalized promotion pictures according to the textual description information of the advertisement, ensuring that the picture of each advertisement is highly related to the content of the advertisement, improving the relevance and attractiveness of the advertisement. The diffusion model can generate new samples from a given data distribution. The diffusion model generates high-quality images through a process of gradually adding noise and gradually removing noise.

[0055] Step S23, displaying the promotion picture of the pre-selected advertisement in each cluster, and obtaining the selected picture selected by the user from the promotion picture of the pre-selected advertisement in each cluster and the cluster where the selected picture is located.

[0056] In some embodiments, the promotion picture of the pre-selected advertisement in each cluster can be displayed on the user's screen, and the picture selected by the user from the promotion picture can be obtained.

[0057] The cluster where the selected picture is located is the cluster to which the selected picture belongs.

[0058] Step S23 understands the interests and preferences of the user through the actual selection of the user, providing a basis for subsequent advertisement placement.

[0059] Compared with pure text description, images are more intuitive and easy to understand, users can quickly understand the content and characteristics of the advertisement, and improve the browsing efficiency of users. Users can select the interested advertisement by clicking the picture, enhance the interactivity and participation of users, and improve the user experience.

[0060] Step S24, constructing an advertisement graph structure based on the cluster where the selected picture is located, the advertisement graph structure including a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes including a selected picture node and a plurality of to-be-launched advertisement nodes, the selected picture node being a central node, and the plurality of to-be-launched advertisement nodes respectively establishing edges with the selected picture node.

[0061] The node features of the selected picture node include the text description information of the advertisement corresponding to the selected picture, the node features of each to-be-launched advertisement node include the text description information of the to-be-launched advertisement, and the features of the edge established between each to-be-launched advertisement node and the selected picture node include the Euclidean distance between the selected picture node and the to-be-launched advertisement node.

[0062] The advertisement graph structure is a graph structure for representing the relationship between advertisements, wherein the nodes represent the advertisements and the edges represent the relationship between the advertisements. As an example, the advertisement graph structure is constructed, the selected picture node is advertisement 1, the to-be-launched advertisement nodes are advertisement 2 and advertisement 3, and the features of the edges between the selected picture node and the to-be-launched advertisement nodes are the Euclidean distance.

[0063] As an example, assuming that the user selects the promotion picture of advertisement A from the promotion pictures of advertisement A, advertisement C and advertisement D, the cluster where the selected picture is located is cluster 1, and the other advertisements in cluster 1 are taken as to-be-launched advertisement nodes, for example, cluster 1 also includes advertisement 2 and advertisement 3, and advertisement 2 and advertisement 3 are taken as to-be-launched advertisement nodes.

[0064] The selected picture node represents the advertisement actually selected by the user, which is a direct feedback of the user's interest. Taking the selected advertisement as the central node can ensure that the recommended advertisements are highly related to the user's interest. By taking the selected picture node as the center, advertisements related to the user's interest can be more accurately recommended, and the click rate and conversion rate of the advertisements can be improved. Since the selected picture node and the to-be-launched advertisement node are both points in the cluster, the Euclidean distance between the selected picture node and the to-be-launched advertisement node can be calculated to obtain the features of the edges between the selected picture node and the to-be-launched advertisement node.

[0065] Step S25, processing the advertisement graph structure based on a graph attention network to determine a plurality of target launched advertisements.

[0066] The graph attention network is a deep learning model for processing graph structured data. The graph attention network captures the relationships between nodes through an attention mechanism. The input of the graph attention network is the advertisement graph structure, and the output of the graph attention network is a plurality of target advertising.

[0067] The pictures selected by the user are a direct reflection of the user's interests. By constructing a graph structure only based on the cluster where the selected pictures are located, it can be ensured that the recommended advertisements are highly relevant to the user's interests. The number of advertisements is very large, and if all advertisements are considered for graph structure construction, the computational complexity will be very high. By only considering the cluster where the selected pictures are located, the number of advertisements that the graph attention network needs to process can be greatly reduced, and the computational complexity can be reduced.

[0068] The graph attention network can generate personalized recommendations based on the relationship between the pictures selected by the user (selected picture nodes) and other advertisements (to-be-launched advertisement nodes). Through the attention mechanism, the graph attention network can more accurately identify which advertisements are most likely to interest the user. The graph attention network can efficiently process large-scale graph structured data and is suitable for large amounts of advertising data in the advertising recommendation scenario. By only considering the cluster where the selected pictures are located, the number of nodes that need to be processed is further reduced, and the computational efficiency is improved.

[0069] Step S5, launching the target advertising to the user based on the target advertising.

[0070] When the target advertising is determined, the target advertising is launched to the user based on the target advertising. In some embodiments, the target advertising can be recommended to the user through a pop-up window.

[0071] Based on the same inventive concept, Figure 4 A schematic diagram of an advertisement launching system based on big data is provided for an embodiment of the present application. The advertisement launching system based on big data comprises:

[0072] The first acquisition module 41 is configured to acquire text description information of a plurality of to-be-launched advertisements.

[0073] The text processing module 42 is configured to determine a K value in a K-means clustering algorithm based on the text description information of the plurality of to-be-launched advertisements using a text processing model.

[0074] The second acquisition module 43 is configured to cluster the text description information of the plurality of to-be-launched advertisements based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters.

[0075] The determination module 44 is configured to determine a plurality of target advertisements based on the K clusters.

[0076] The putting module 45 is configured to put the target advertisement to the user based on the target advertisement.

[0077] Based on the same inventive concept, the embodiment of the present application provides an electronic device, such as Figure 5 as shown in the figure, comprising:

[0078] comprising: 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 realize the big data-based advertisement putting method provided in the foregoing, the method comprising: obtaining text description information of a plurality of advertisements to be put; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be put using a text processing model; clustering the text description information of the plurality of advertisements to be put based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target advertisements based on the K clusters; and putting the target advertisements to the user.

[0079] Based on the same inventive concept, the embodiment of the present application provides a computer readable storage medium having a computer program stored thereon, the program being executed by a processor 51 to realize the big data-based advertisement putting method provided in the foregoing, the method comprising: obtaining text description information of a plurality of advertisements to be put; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be put using a text processing model; clustering the text description information of the plurality of advertisements to be put based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target advertisements based on the K clusters; and putting the target advertisements to the user.

[0080] The big data-based advertisement putting method provided by the embodiment of the present application can be applied to terminal equipment (such as a mobile phone), a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable device (such as a smart watch, smart glasses, or a smart helmet), an augmented reality (AR) \ virtual reality (VR) device, a smart home device, a vehicle-mounted computer, and other electronic devices, and the embodiment of the present application does not make any limitation in this regard.

[0081] Taking the mobile phone 100 as an example of the above-mentioned electronic device, Figure 6 a structural schematic diagram of the mobile phone 100 is shown.

[0082] As shown in the figure, Figure 6As shown, the mobile phone 100 can 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 loudspeaker 170A, a receiver 170B, a microphone 170C, a headset interface 170D, a sensor module 180, a key 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0083] The processing module 110 can include one or more processing units, for example: the processing module 110 can include an application processor (AP), a modem processor, a graphics processing unit (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. Among them, different processing units can be independent devices, or can be integrated in one or more processors.

[0084] Among them, the controller can be the nerve center and command center of the mobile phone 100, and is the decision maker that coordinates the work of each component of the mobile phone 100 according to the instruction. The controller can generate operation control signals according to instruction operation codes and timing signals to complete the control of fetching and executing instructions.

[0085] The application processor can be installed with an operating system of the mobile phone 100, which is used to manage hardware and software resources of the mobile phone 100. For example, to manage and configure memory, to determine the priority order of system resource supply and demand, to manage the file system, to manage the driver, etc. The operating system can also be used to provide an operation interface for user to interact with the system. Among them, various software can be installed in the operating system, such as drivers, application programs (Apps), etc. For example, the operating system of the mobile phone 100 can be an Android system, a Linux system, etc.

[0086] The processing module 110 can also include a memory for storing instructions and data. In some embodiments, the memory in the processing module 110 is a cache memory. The memory can hold instructions or data that the processing module 110 has just used or is reusing. If the processing module 110 needs to use the instructions or data again, it can call them directly from the memory. This avoids repeated access and reduces the waiting time of the processing module 110, thus improving the efficiency of the system.

[0087] In some embodiments, the processing module 110 can include one or more interfaces. The interfaces can include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0088] The processing module 110 can be configured to: obtain text description information of a plurality of advertisements to be launched; determine a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be launched using a text processing model; cluster the text description information of the plurality of advertisements to be launched based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determine a plurality of target launched advertisements based on the K clusters; and launch the target launched advertisements to a user.

[0089] The charging management module 140 is configured to receive charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 can receive charging input from a wired charger through the USB interface 130. In some wireless charging embodiments, the charging management module 140 can receive wireless charging input through a wireless charging coil of the mobile phone 100. The charging management module 140 can charge the battery 142 while also supplying power to the electronic device through the power management module 141.

[0090] The power management module 141 is configured to connect the battery 142 and the charging management module 140 to the processing module 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140 to power the processing module 110, the internal memory 121, the external memory, the display 194, the camera 193, the wireless communication module 160, and the like. The power management module 141 can also be configured to monitor parameters such as the battery capacity, the number of battery cycles, the battery health status (leakage, impedance), and the like. In some embodiments, the power management module 141 can also be disposed in the processing module 110. In some other embodiments, the power management module 141 and the charging management module 140 can be disposed in the same device.

[0091] The wireless communication functions of the mobile phone 100 can be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor, and the baseband processor, and the like.

[0092] The antenna 1 and the antenna 2 are configured to transmit and receive electromagnetic wave signals. Each antenna in the mobile phone 100 can be configured to cover a single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example, the antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in combination with a tuning switch.

[0093] The mobile communication module 150 can provide a solution for wireless communication including 2G / 3G / 4G / 5G and the like applied to the mobile phone 100. The mobile communication module 150 can include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), and the like. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, filter, amplify, and the like the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation. The mobile communication module 150 can also amplify signals modulated by the modem processor and convert the signals into electromagnetic waves radiated by the antenna 1. In some embodiments, at least part of the functional modules of the mobile communication module 150 can be disposed in the processing module 110. In some embodiments, at least part of the functional modules of the mobile communication module 150 and at least part of the modules of the processing module 110 can be disposed in the same device.

[0094] The modem processor can include a modulator and a demodulator. The modulator is configured to modulate a low frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is configured to demodulate a received electromagnetic wave signal into a low frequency baseband signal. The demodulator then transmits the demodulated low frequency baseband signal to the baseband processor for processing. The low frequency baseband signal is processed by the baseband processor and then transmitted to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 170A, a microphone 170B, etc.), or displays an image or a video through the display screen 194. In some embodiments, the modem processor can be a separate device. In other embodiments, the modem processor can be independent of the processing module 110 and disposed in the same device as the mobile communication module 150 or other functional modules.

[0095] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (e.g., wireless fidelity (Wi-Fi) network), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc. The wireless communication module 160 can be one or more devices that integrate at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates and filters the electromagnetic wave signal, and transmits the processed signal to the processing module 110. The wireless communication module 160 can also receive a signal to be transmitted from the processing module 110, modulate it, amplify it, and convert it into electromagnetic wave radiation via the antenna 2.

[0096] In some embodiments, the antennas 1 and the mobile communication module 150 of the mobile phone 100 are coupled, and the antennas 2 and the wireless communication module 160 are coupled, so that the mobile phone 100 can communicate with a network and other devices through wireless communication technologies. The wireless communication technologies can include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technologies, etc. The GNSS can include global positioning system (GPS), global navigation satellite system (GLONASS), beidu navigation satellite system (BDS), quasi-zenith satellite system (QZSS), and / or satellite based augmentation systems (SBAS).

[0097] The mobile phone 100 implements display functions through a GPU, a display screen 194, and an application processor, etc. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processing module 110 can include one or more GPUs that execute program instructions to generate or change display information.

[0098] The display screen 194 is configured to display images, videos, and the like. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flex light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light emitting diodes (QLED), or the like. In some embodiments, the mobile phone 100 can include one or N display screens 194, where N is a positive integer greater than 1.

[0099] The mobile phone 100 can implement the photographing function through the ISP, the camera 193, the video codec, the GPU, the display screen 194, and the application processor. In some embodiments, the mobile phone 100 can implement the video communication function through the ISP, the camera 193, the video codec, the GPU, and the application processor.

[0100] The ISP is configured to process the data fed back by the camera 193. For example, when taking a photo, the shutter is opened, the light is transmitted to the camera photosensitive element through the lens, the light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing to convert it into an image visible to the naked eye. The ISP can also optimize the algorithm for the noise, brightness, and skin color of the image. The ISP can also optimize the exposure, color temperature, and other parameters of the shooting scene. In some embodiments, the ISP can be arranged in the camera 193.

[0101] The camera 193 is configured to capture still images or videos. An object generates an optical image through a lens and projects it onto a photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV, or the like format. In some embodiments, the mobile phone 100 can include one or N cameras 193, where N is a positive integer greater than 1.

[0102] The digital signal processor is used to process digital signals, in addition to being able to process digital image signals, it can also process other digital signals. For example, when the mobile phone 100 is in frequency point selection, the digital signal processor is used to perform Fourier transform on the frequency point energy, etc.

[0103] The video codec is used to compress or decompress digital video. The mobile phone 100 can support one or more video codecs. In this way, the mobile phone 100 can play or record videos in multiple encoding formats, such as: moving picture experts group (MPEG) 1, MPEG 2, MPEG 3, MPEG 4, etc.

[0104] The NPU is a neural-network (NN) calculation processor, which can quickly process input information by drawing on the structure of biological neural networks, such as drawing on the transmission mode between human brain neurons, and can also continuously self-learn. Through the NPU, the mobile phone 100 can realize intelligent cognitive applications such as image recognition, face recognition, voice recognition, text understanding, etc.

[0105] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the mobile phone 100. The external memory card communicates with the processing module 110 through the external memory interface 120 to realize data storage functions. For example, music, video, etc. Files are saved in the external memory card.

[0106] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processing module 110 executes various functional applications and data processing of the mobile phone 100 by running the instructions stored in the internal memory 121. The internal memory 121 can include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc. The data storage area can store data created during use of the mobile phone 100 (such as audio data, a phonebook, etc.), etc. In addition, the internal memory 121 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0107] The mobile phone 100 can realize audio functions through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the earphone interface 170D, and the application processor, etc. For example, music playing, recording, etc.

[0108] The audio module 170 is configured to convert digital audio information into analog audio signals for output, and to convert analog audio input into digital audio signals. The audio module 170 can also be configured to encode and decode audio signals. In some embodiments, the audio module 170 can be disposed in the processing module 110, or some of the functions of the audio module 170 can be disposed in the processing module 110.

[0109] The speaker 170A, also referred to as a "loudspeaker", is configured to convert audio electrical signals into sound signals. The mobile phone 100 can listen to music or listen to a hands-free call through the speaker 170A.

[0110] The receiver 170B, also referred to as an "earpiece", is configured to convert audio electrical signals into sound signals. When the mobile phone 100 answers a call or a voice message, the receiver 170B can be held close to the ear of a person to listen to the voice.

[0111] The microphone 170C, also referred to as a "microphone", "sound transducer", is configured to convert sound signals into electrical signals. When making a call or sending a voice message, a user can speak into the microphone 170C through the mouth to input sound signals into the microphone 170C. The mobile phone 100 can be provided with at least one microphone 170C. In other embodiments, the mobile phone 100 can be provided with two microphones 170C, in addition to collecting sound signals, noise reduction functions can also be achieved. In other embodiments, the mobile phone 100 can also be provided with three, four or more microphones 170C, in addition to collecting sound signals, noise reduction, and can also identify the source of the sound, and achieve directional recording functions, etc.

[0112] The earphone interface 170D is configured to connect a wired earphone. The earphone interface 170D can be a USB interface 130, or a 3.5mm open mobile terminal platform (OMTP) standard interface, a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0113] The keys 190 include a power-on key, a volume key, etc. The keys 190 can be mechanical keys. They can also be touch keys. The mobile phone 100 can receive key inputs and generate key signal inputs related to user settings and function control of the mobile phone 100.

[0114] The motor 191 can generate a vibration prompt. The motor 191 can be used for incoming call vibration prompt, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, playing audio, etc.) can correspond to different vibration feedback effects. The motor 191 can also correspond to different vibration feedback effects for touch operations acting on different regions of the display screen 194. Different application scenarios (such as time reminders, received messages, alarms, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0115] The indicator 192 can be an indicator light, which can be used to indicate the charging state, the power change, and can also be used to indicate messages, missed calls, notifications, etc.

[0116] The SIM card interface 195 is used to connect the SIM card. The SIM card can be inserted into or pulled out of the SIM card interface 195 to realize contact and separation with the mobile phone 100. The mobile phone 100 can support one or N SIM card interfaces, and N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, etc. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the multiple cards can be the same or different. The SIM card interface 195 can also be compatible with different types of SIM cards. The SIM card interface 195 can also be compatible with external storage cards. The mobile phone 100 interacts with the network through the SIM card to realize functions such as calling and data communication. In some embodiments, the mobile phone 100 uses an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the mobile phone 100 and cannot be separated from the mobile phone 100.

[0117] The above detailed description has been described for the basic concept, and it is obvious that the above detailed description is only used as an example and does not limit the present description. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and corrections to the present description. Such modifications, improvements and corrections are suggested in the present description, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present description.

[0118] Meanwhile, specific words are used in the present description to describe the embodiments of the present description. For example, “one embodiment”, “an embodiment”, and / or “some embodiments” means a certain feature, structure or characteristic related to at least one embodiment of the present description. Therefore, it should be emphasized and noted that the “one embodiment” or “one embodiment” or “one alternative embodiment” mentioned in different places in the present description does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present description can be properly combined.

[0119] Furthermore, the order of the processing elements and sequence of the steps described in this specification are not intended to be limiting, unless otherwise indicated, and is presented according to the order in which they are believed to be performed, from the view of the applicant, and / or as is practical in light of the functionality provided. Moreover, the use of numbering or letters in the examples, if any, are not intended to limit their application to the narrow set of examples described. Rather, such numbering and / or letters are merely artifacts of a drafting process, and are not intended to be limiting as such. Although the above-disclosed embodiments have shown, described, and pointed out the fundamental and novel features of the applications, it will be understood that various omissions and substitutions, changes of form of the method described herein, can be made by those skilled in the art, without departing from the spirit of the disclosure, and the general scope of the following claims. For example, although the system components described above can be implemented by hardware devices, they can also be implemented by software solutions only, such as installing the described system on an existing server or mobile device.

[0120] Similarly, it is to be noticed that the term "comprising", used in the description, should not be interpreted as being restricted to the means listed thereafter; it does not exclude other elements or steps. It is thus to be interpreted as specifying the presence of the stated features, integers, steps or components as referred to, but does not preclude the presence or addition of one or more other features, integers, steps or components, or groups thereof. Furthermore, the description of the embodiments of the application has been given by way of example only and modifications can be made within the scope of the application as claimed by the following claims.

[0121] Finally, it should be noted that the embodiments described hereinabove merely represent examples of the principles of the applications. Other variations having essentially the same structure and function are within the scope of the present applications. Accordingly, the embodiments described hereinabove are not to be considered in a limiting sense, as the scope of the present applications is best defined by the appended claims.

Claims

1. A method for advertisement delivery based on big data, characterized in that, The method comprises the following steps: obtaining text description information of a plurality of advertisements to be launched; determining a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be launched using a text processing model, the text processing model being a deep neural network model, an input of the text processing model being the text description information of the plurality of advertisements to be launched, and an output of the text processing model being the K value in the K-means clustering algorithm; clustering the text description information of the plurality of advertisements to be launched based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; determining a plurality of target launched advertisements based on the K clusters, the determination of the target launched advertisements based on the K clusters comprising: inputting the K clusters into a screening model to screen one preliminary advertisement from each cluster; generating a promotion picture of the preliminary advertisement in each cluster based on the text description information of the preliminary advertisement in each cluster using a diffusion model, an input of the diffusion model being the text description information of the preliminary advertisement in each cluster, and an output of the diffusion model being the promotion picture of the preliminary advertisement in each cluster; displaying the promotion picture of the preliminary advertisement in each cluster, and obtaining a selected picture selected by a user from the promotion picture of the preliminary advertisement in each cluster and a cluster in which the selected picture is located; constructing an advertisement graph structure based on the cluster in which the selected picture is located, the advertisement graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising one selected picture node and a plurality of advertisement nodes to be launched, the selected picture node being a central node, the plurality of advertisement nodes to be launched each establishing an edge with the one selected picture node, a node feature of the one selected picture node comprising text description information of an advertisement corresponding to the selected picture, a node feature of each advertisement node to be launched comprising text description information of an advertisement to be launched, and a feature of an edge established between the one selected picture node and each advertisement node to be launched comprising a Euclidean distance between the one selected picture node and the advertisement node to be launched; processing the advertisement graph structure based on a graph attention network to determine the plurality of target launched advertisements; and launching the target launched advertisements to the user.

2. A big data based advertisement delivery system, characterized by, The method comprises the following steps: a first obtaining module is configured to obtain text description information of a plurality of advertisements to be launched; a text processing module is configured to determine a K value in a K-means clustering algorithm based on the text description information of the plurality of advertisements to be launched using a text processing model, the text processing model being a deep neural network model, an input of the text processing model being the text description information of the plurality of advertisements to be launched, and an output of the text processing model being the K value in the K-means clustering algorithm; a second obtaining module is configured to cluster the text description information of the plurality of advertisements to be launched based on the K-means clustering algorithm and the K value in the K-means clustering algorithm to obtain K clusters; a determination module is configured to determine a plurality of target launched advertisements based on the K clusters, and the determination module is further configured to: input the K clusters into a screening model to screen one preliminary advertisement from each cluster; generate a promotion picture of the preliminary advertisement in each cluster based on the text description information of the preliminary advertisement in each cluster using a diffusion model, an input of the diffusion model being the text description information of the preliminary advertisement in each cluster, and an output of the diffusion model being the promotion picture of the preliminary advertisement in each cluster; generate a promotion picture of the pre-selected advertisement in each cluster based on the textual description information of the pre-selected advertisement in each cluster using a diffusion model, an input of the diffusion model being the textual description information of the pre-selected advertisement in each cluster, and an output of the diffusion model being the promotion picture of the pre-selected advertisement in each cluster; display the promotion picture of the pre-selected advertisement in each cluster, and obtain a selected picture selected by a user from the promotion picture of the pre-selected advertisement in each cluster and a cluster in which the selected picture is located; construct an advertisement graph structure based on the cluster in which the selected picture is located, the advertisement graph structure including a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes including one selected picture node and a plurality of to-be-launched advertisement nodes, the selected picture node being a center node, the plurality of to-be-launched advertisement nodes respectively establishing edges with the one selected picture node, a node feature of the one selected picture node including textual description information of an advertisement corresponding to the selected picture, a node feature of each to-be-launched advertisement node including textual description information of a to-be-launched advertisement, and a feature of an edge established between each to-be-launched advertisement node and the one selected picture node including a Euclidean distance between the selected picture node and the to-be-launched advertisement node; determine a plurality of target launched advertisements based on processing of the advertisement graph structure by a graph attention network; a launching module configured to launch the target launched advertisements to a user.

3. An electronic device, comprising: comprise: 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 the big data-based advertisement launching method according to claim 1.

4. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the big data-based advertisement launching method according to claim 1.

Images