A promotional content processing method, device, equipment, medium and product

Through segmentation and combination of promotional content and evaluation of user interest characteristics, selecting the highest-rated content to be delivered, the problems of insufficient merchant motivation and dissatisfaction with user needs are solved, and the enrichment and effective delivery of personalized promotional content is achieved.

CN114708008BActive Publication Date: 2024-12-03BEIJING YOUZHUJU NETWORK TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111661810.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-30
Publication Date
2024-12-03
Estimated Expiration
2041-12-30

AI Technical Summary

Technical Problem

Due to uncertain revenue when promoting content production, merchants have insufficient motivation. Only a small amount of promotional content is produced and repeated delivery is unable to meet the personalized needs of different users.

Method used

By obtaining the promotional content to be processed, dividing and combining it, evaluating and selecting the highest-rated content for delivery based on user interest characteristics, personalized processing is achieved.

Benefits of technology

It enriches the number of promotional content, meets the personalized needs of different users, and improves the effectiveness and user conversion rate of promotional content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114708008B_ABST
    Figure CN114708008B_ABST
Patent Text Reader

Abstract

The present disclosure provides a promotional content processing method, device, equipment, medium and product, which relates to the field of computer technology. The method includes obtaining the promotional content to be processed, segmenting the promotional content to obtain multiple content segments, and then combining the multiple content segments to obtain multiple candidate contents; evaluating the scores of the multiple candidate contents according to the multiple candidate contents and the user's interest characteristics, and finally selecting the target content with the highest score from the multiple candidate contents, and delivering the target content to the user. It can be seen that the method realizes personalized processing of the promotional content, and only requires a small amount of promotional content to meet the personalized needs of different users.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a promotion content processing method, apparatus, device, computer-readable storage medium, and computer program product. Background Art

[0002] With the continuous development of computer technology, especially mobile Internet technology, merchants usually publish promotional content (such as advertisements) to promote related products or services. The promotional content usually exists in the form of multimedia data, and the form of multimedia data includes but is not limited to video, voice and image.

[0003] Since it is difficult to produce promotional content and the benefits that promotional content brings to merchants are uncertain, merchants have a weaker motivation to produce promotional content, which in turn leads to merchants only producing one piece of promotional content and then delivering the same promotional content to different users.

[0004] However, different users have different interests in promotional content. It is difficult to meet the personalized needs of different users by delivering the same promotional content to different users. Summary of the invention

[0005] The purpose of the present disclosure is to provide a promotion content processing method, device, equipment, computer-readable storage medium and computer program product, which can personalize the promotion content and meet the personalized needs of different users.

[0006] In a first aspect, the present disclosure provides a promotion content processing method, the method comprising:

[0007] Get the promotional content to be processed;

[0008] Segmenting the promotional content to obtain multiple content segments;

[0009] Combining the multiple content segments to obtain multiple candidate contents;

[0010] Evaluating scores of the plurality of candidate contents according to the plurality of candidate contents and the interest characteristics of the user;

[0011] The target content with the highest score among the multiple candidate contents is delivered to the user.

[0012] In a second aspect, the present disclosure provides a promotion content processing device, including:

[0013] An acquisition module is used to acquire promotional content to be processed;

[0014] A segmentation module, used to segment the promotional content to obtain multiple content segments;

[0015] A combining module, used for combining the multiple content segments to obtain multiple candidate contents;

[0016] An evaluation module, configured to evaluate the scores of the plurality of candidate contents according to the plurality of candidate contents and the interest characteristics of the user;

[0017] The processing module is used to deliver the target content with the highest score among the multiple candidate contents to the user.

[0018] In a third aspect, the present disclosure provides an electronic device, including:

[0019] a storage device having a computer program stored thereon;

[0020] A processing device is used to execute the computer program in the storage device to implement the steps of any one of the methods described in the first aspect of the present disclosure.

[0021] In a fourth aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of any one of the methods described in the first aspect of the present disclosure.

[0022] In a fifth aspect, the present disclosure provides a computer program product comprising instructions, which, when executed on a device, enables the device to execute the method described in any one of the implementations of the first aspect.

[0023] It can be seen from the above technical solutions that the present disclosure has the following advantages:

[0024] On the one hand, after processing the promotional content to obtain multiple candidate contents, the method scores the multiple candidate contents based on the user's interest characteristics, and then obtains scores for the multiple candidate contents, and delivers the target content with the highest score to the user, thereby meeting the personalized needs of different users; on the other hand, the method only requires a small amount of promotional content, and by splitting and combining a small amount of promotional content, a large amount of candidate contents can be obtained, thereby enriching the number of promotional contents and making it easier to meet the personalized needs of different users.

[0025] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical method of the embodiments of the present disclosure, the drawings required for use in the embodiments are briefly introduced below.

[0027] Figure 1 A schematic diagram of a promotion content processing system provided by an embodiment of the present disclosure;

[0028] Figure 2 A schematic diagram of a promotional content upload interface provided by an embodiment of the present disclosure;

[0029] Figure 3 A flowchart of a promotion content processing method provided by an embodiment of the present disclosure;

[0030] Figure 4 A schematic diagram of a double tower model provided in an embodiment of the present disclosure;

[0031] Figure 5 A schematic diagram of a promotion content processing device provided by an embodiment of the present disclosure;

[0032] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The terms "first" and "second" in the embodiments of the present disclosure are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0034] First, some technical terms involved in the embodiments of the present disclosure are introduced.

[0035] Promotional content refers to content used to promote or publicize a target object. For example, promotional content can be an advertisement. By publishing an advertisement, users can pay more attention to the target object promoted or publicized in the advertisement. In some examples, advertisements can be used to call on users to save water resources, or to guide users to consume digital products in the advertisement.

[0036] Promotional content usually exists in the form of multimedia data, including but not limited to video, voice and image. It is difficult to produce promotional content, and merchants usually only produce and publish a small amount of promotional content. In addition, the benefits brought to merchants by promotional content are often uncertain. For example, the conversion rate of promotional content is unstable, which will discourage merchants from creating new promotional content. As a result, merchants will only use a small amount of or even the same promotional content to deliver to different users.

[0037] However, in actual scenarios, different users have different interests in promotional content. Using the same promotional content to deliver it to different users is difficult to meet the personalized needs of different users and it is difficult to convert users.

[0038] In view of this, an embodiment of the present disclosure provides a promotional content processing method, which includes: obtaining the promotional content to be processed, segmenting the promotional content to obtain multiple content segments, and then combining the multiple content segments to obtain multiple candidate content, thereby enriching the number of promotional content and making it easier to meet the personalized needs of different users; then, the method evaluates the scores of the multiple candidate content based on the multiple candidate content and the user's interest characteristics, and then selects the target content with the highest score from the multiple candidate content to deliver to the user, thereby achieving the delivery of different target content to the user's users, thereby meeting the personalized needs of different users.

[0039] The method can be applied to a promotion content processing system. When the method is applied to a promotion content processing system, it is specifically implemented in the form of a computer program. In some embodiments, the computer program can be independent, for example, it can be an independent application with corresponding functions. In other embodiments, the computer program can be a functional module or plug-in, etc., which is attached to an existing application and runs.

[0040] For example, taking the case where a promotional content processing system is attached to a shopping application, the promotional content processing system can obtain the promotional content of the target object (such as a product), and then process the promotional content to obtain multiple candidate contents. Different candidate contents are delivered to different users (the candidate contents are the target contents with the highest scores for the user), thereby meeting the personalized needs of different users.

[0041] The promotion content processing method provided in the embodiment of the present disclosure can be executed by the client alone, by the server alone, or by the client and the server in collaboration. When the promotion content processing method is executed by the client alone, it indicates that the promotion content processing system can be operated offline. For ease of understanding, the following takes the promotion content processing method executed by the client and the server in collaboration as an example for explanation.

[0042] In order to make the technical solution of the present disclosure clearer and easier to understand, the architecture of the promotion content processing system provided by the embodiment of the present disclosure is introduced below with reference to the accompanying drawings.

[0043] See also Figure 1The system architecture diagram of the promotion content processing system 100 shown in FIG. 1 includes a terminal 110, a terminal 120 and a server 130. The terminal 110, the terminal 120 and the server 130 are connected via a network. Among them, the terminal 110 can be a merchant's terminal, and the terminal 120 can be a user's terminal, and the terminal includes but is not limited to a smart phone, a tablet computer, a laptop computer, a personal digital assistant (PDA) or a smart wearable device. The server 130 can be a cloud server, for example, a central server in a central cloud computing cluster, or an edge server in an edge cloud computing cluster. Of course, the server 130 can also be a server in a local data center. The local data center refers to a data center directly controlled by the user.

[0044] In some examples, the terminal 110 may present a human-computer interaction interface to the merchant so that the merchant can upload promotional content to promote the target object. Figure 2 As shown in FIG. 1 , this figure is a schematic diagram of a promotion content upload interface provided by an embodiment of the present disclosure, and the promotion content upload interface includes: promotion content 201 to be uploaded and an upload control 202. The merchant can select the promotion content 201 by clicking on it, and then click on the upload control 202. The terminal 110 can send the promotion content 201 selected by the merchant to the server 130 based on the merchant's click operation on the upload control 202. In this way, the server 130 can obtain the promotion content selected by the merchant.

[0045] The server 130 can perform processing such as segmentation and combination on the promotional content to obtain multiple candidate contents, and then evaluate the scores of the multiple candidate contents based on the user's interest characteristics and the multiple candidate contents before delivering them to the user, and select the target content with the highest score from the multiple candidate contents to deliver to the user. Specifically, the server 130 can send the target content to the user's terminal 120, and the terminal 120 can present the promotional content to the user. For users with different interest characteristics, the server 130 can deliver different target contents to users with different interest characteristics. The target content is obtained based on the user's interest characteristics, so the target content can meet the user's personalized needs.

[0046] It can be seen that by processing the promotional content through the promotional content processing system, only a small amount of promotional content is needed to meet the personalized needs of different users.

[0047] In order to make the technical solution of the present disclosure clearer and easier to understand, the promotion content processing method provided by the embodiment of the present disclosure is introduced from the perspectives of the terminal 110 , the terminal 120 and the server 130 .

[0048] like Figure 3As shown in the figure, a promotion content processing method provided by an embodiment of the present disclosure is provided, and the method includes:

[0049] S301: The terminal 110 obtains promotional content selected by the merchant.

[0050] There are many types of promotional content, for example, the promotional content can be voice, video or image. For ease of understanding, this embodiment takes the promotional content as a video as an example for introduction.

[0051] like Figure 2 The schematic diagram of the promotion content upload interface shown is that the merchant can select the promotion content to be released in the promotion content upload interface, and the terminal 110 can obtain the promotion content selected by the merchant based on the user's click operation on the upload control.

[0052] It should be noted that the embodiments of the present disclosure are described by taking the creator of the promotional content as a merchant as an example. Of course, in other embodiments, the creator of the promotional content may also be a blogger, etc.

[0053] S302: The terminal 110 sends the promotion content selected by the merchant to the server 130.

[0054] After acquiring the promotional content selected by the merchant, the terminal 110 may send the promotional content to the server 130 , so that the server 130 acquires the promotional content selected by the user and performs subsequent processing on the promotional content.

[0055] S303: The server 130 segments the promotional content to obtain multiple content segments.

[0056] In some examples, the server 130 may determine the method of segmenting the promotional content based on the form of the promotional content. When the promotional content is text, the server 130 may segment the promotional content by sentence, thereby obtaining multiple sentences; when the promotional content is voice, the server 130 may segment the promotional content by sentence obtained after voice recognition, thereby obtaining multiple voice segments; when the promotional content is an image, the server 130 may segment the promotional content by sub-image obtained after image recognition, thereby obtaining multiple image segments.

[0057] When the promotional content is a video, the server 130 can segment the promotional content in at least two ways. In some examples, the server 130 can perform voice recognition on the promotional content to obtain a voice recognition result, which includes at least one segmentation point, and then the server 130 segments the promotional content using the segmentation point. After performing voice recognition on the promotional content, the server 130 can obtain the text corresponding to the promotional content, which includes multiple sentences and punctuation marks (such as commas, periods, semicolons, etc.) between sentences. The timestamps corresponding to the punctuation marks on the video can be used as segmentation points. After the server 130 determines the segmentation point, it determines the timestamp, and then segments the video based on the timestamp to obtain multiple video clips.

[0058] In other examples, the server 130 may also perform image recognition on the promotional content to obtain an image recognition result, which includes at least one segmentation point, and then the server 130 segments the promotional content using the segmentation point. After performing image recognition on the promotional content, the server 130 can determine two adjacent frames of images that are farther apart in the video, where the two adjacent frames of images that are farther apart may be two adjacent frames of images whose similarity is lower than a preset similarity, and then select a timestamp corresponding to a frame of image from the two adjacent frames of images as a segmentation point. After determining the segmentation point, the server 130 determines the timestamp, and then segments the video based on the timestamp to obtain multiple video clips.

[0059] It should be noted that the embodiment of the present disclosure does not specifically limit the manner in which the server 130 segments the promotional content. The above is merely an exemplary introduction, and those skilled in the art may select other segmentation manners based on actual needs.

[0060] S304: The server 130 combines the multiple content segments to obtain multiple candidate contents.

[0061] In some embodiments, the server 130 may number each content segment and then fully arrange the numbers to obtain candidate content corresponding to all combinations of the content segments, or may randomly arrange the numbers to obtain candidate content corresponding to some combinations of the content segments.

[0062] In other embodiments, the server 130 may extract segment features of each content segment from a plurality of content segments, and then obtain the identifier of the cluster center corresponding to the segment features of each content segment based on a mapping relationship between the segment features and the identifiers of the cluster centers, and then determine a plurality of candidate sequences of a plurality of candidate contents based on the identifiers of the cluster centers.

[0063] The mapping relationship between the above-mentioned segment features and the identifiers of the cluster centers can be obtained based on the historical promotion content. The historical promotion content may refer to all promotion content of all industries and types. Specifically, the server 130 may pre-segment the historical promotion content based on the segmentation processing method introduced above, and then obtain the historical content segments of the historical promotion content. The server 130 extracts the segment features of the historical content segments, and then clusters the segment features of the historical content segments to obtain the cluster centers. Different cluster centers can be represented by the identifiers of the cluster centers.

[0064] The above segment features may be text features, image features, or fusion features of text features and image features. In some examples, the text features may be BERT (Bidirectional Encoder Representations from Transformers) features, and the image features may be computer vision (CV) features. The above segment features may be represented by embedding.

[0065] It should be noted that the segment features used by the server 130 when pre-establishing the mapping relationship between the segment features and the identifiers of the cluster centers are consistent with the segment features of each content segment extracted by the server 130 from multiple content segments, for example, all are text features, all are image features, or all are fusion features.

[0066] In some examples, the server may first perform speech recognition on the content segment, obtain the text corresponding to the content segment, and then obtain text features based on the text; the server may perform image recognition on the content segment, and then obtain image features. The embodiments of the present disclosure do not specifically limit the method of extracting text features or image features, and those skilled in the art may select an appropriate method to extract text features or image features based on actual needs.

[0067] For ease of understanding, the following takes the fragment feature as an example of text feature.

[0068] Taking multiple content segments including content segment 1, content segment 2, content segment 3, content segment 4, and content segment 5 as an example, the server 130 can extract text feature 1 of content segment 1, text feature 2 of content segment 2, text feature 3 of content segment 3, text feature 4 of content segment 4, and text feature 5 of content segment 5, respectively, and then obtain the identifier 1 of the cluster center corresponding to text feature 1, the identifier 2 of the cluster center corresponding to text feature 2, the identifier 3 of the cluster center corresponding to text feature 3, the identifier 4 of the cluster center corresponding to text feature 4, and the identifier 5 of the cluster center corresponding to text feature 5. Based on this, the server 130 can characterize the promotional content uploaded by the merchant through the original sequence [identifier 1, identifier 2, identifier 3, identifier 4, identifier 5] based on the identifier of the cluster center.

[0069] Then, the server 130 may determine multiple candidate sequences of multiple candidate contents according to the identifiers of the cluster centers. In some examples, the server 130 may perform a full permutation of the above identifiers 1 to 5 to obtain candidate sequences corresponding to all combinations of identifiers 1 to 5, or the server 130 may perform a random permutation to obtain candidate sequences corresponding to some combinations of identifiers 1 to 5.

[0070] In other examples, in order to ensure the semantic coherence of the candidate content corresponding to the candidate sequence, the server 130 may adjust the identifier ranked first in the original sequence of the promotional content to the last to obtain a first candidate sequence, and then adjust the identifier ranked first in the first candidate sequence to the last to obtain a second candidate sequence, until the identifier ranked first in the obtained candidate sequence is the identifier ranked last in the original sequence.

[0071] Taking the above original sequence [identifier 1, identifier 2, identifier 3, identifier 4, identifier 5] as an example, the server can obtain 4 candidate sequences through the above method, as shown in the following Table 1:

[0072] Table 1

[0073] Original sequence Logo 1 Logo 2 Logo 3 Logo 4 Logo 5 First candidate sequence Logo 2 Logo 3 Logo 4 Logo 5 Logo 1 The second candidate sequence Logo 3 Logo 4 Logo 5 Logo 1 Logo 2 The third candidate sequence Logo 4 Logo 5 Logo 1 Logo 2 Logo 3 The fourth candidate sequence Logo 5 Logo 1 Logo 2 Logo 3 Logo 4

[0074] In the multiple candidate sequences shown in Table 1, the order of adjacent identifiers in each candidate sequence is consistent with the order of adjacent identifiers in the original sequence, such as the order of the first four identifiers in the first candidate sequence is consistent with the order of the last four identifiers in the original candidate sequence, and for another example, the order of the last four identifiers in the fourth candidate sequence is consistent with the order of the first four identifiers in the original sequence. In this way, the candidate contents corresponding to the multiple candidate sequences can be semantically coherent to a certain extent.

[0075] S305: The server 130 evaluates the scores of the plurality of candidate contents according to the plurality of candidate contents and the user's interest characteristics.

[0076] In some embodiments, the server 130 may evaluate the scores of multiple candidate contents according to the multiple candidate contents and the user's interest characteristics through a model. The user's interest characteristics may be represented by embedding, and the user's interest characteristics may be obtained based on the user's feedback information on the historical promotion content, and the feedback information may be the user's behavior data on the historical promotion content, such as the user clicking on the historical promotion content, the user watching the promotion content for more than a preset time, etc. Those skilled in the art may select the user's behavior data to be used according to actual needs.

[0077] It should be noted that the user information involved in the embodiments of the present disclosure (such as the user's feedback information mentioned above) requires the user's authorization in advance. Only after obtaining the user's authorization to use the corresponding data can the server 130, terminal 110 or terminal 120 obtain the user's information.

[0078] In some examples, server 130 may perform model training based on user interest features and historical promotion content, wherein the historical promotion content includes multiple historical content segments. Based on this, the historical promotion content may be characterized based on identification features of cluster centers corresponding to the historical content segments and / or position features identified in historical sequences corresponding to the historical promotion content.

[0079] In some examples, the model used to evaluate the scores of multiple candidate contents may be a dual-tower model or other hybrid models. Figure 4 As shown, this figure is a schematic diagram of a dual-tower model provided by an embodiment of the present disclosure. After completing the training of the dual-tower model, the server 130 can use the dual-tower model to give scores for multiple candidate contents according to the user's interest characteristics and multiple candidate contents.

[0080] Taking the scoring of a candidate content as an example, such as the first candidate content corresponding to the first candidate sequence, the server can obtain the identification feature of each identifier in the first candidate sequence of the first candidate content; it can also obtain the position feature of each identifier in the first candidate sequence of the first candidate content; it can also obtain the identification feature of each identifier and the position feature of each identifier, and fuse the identification feature of each identifier and the position feature of each identifier to obtain the fusion feature of each identifier. In some examples, the score of the candidate content can be determined based on the attention mechanism. Specifically, the server 130 can calculate the score of the candidate content based on the following formula:

[0081]

[0082]

[0083] In formula (1), wij is the weight of each content segment in the candidate content, ui is the user's interest feature, vj can be the identification feature of the jth content segment, or the position feature of the jth content segment, or the fusion feature of the jth content segment obtained by fusing the identification feature of the jth content segment and the position feature of the jth content segment. In formula (2), v is the score of the candidate content.

[0084] Similarly, each candidate content is processed similarly, and then a score for each candidate content can be obtained.

[0085] In some examples, the score can be represented by the click-through rate (CTR). The embodiments of the present disclosure do not specifically limit the way of representing the score. Those skilled in the art can determine the way of representing the score based on actual needs. For example, the score can also be represented by the conversion rate.

[0086] S306 : The server 130 sends the target content with the highest score among the multiple candidate contents to the terminal 120 .

[0087] In some embodiments, the server 130 may send the target content with the highest score among the plurality of candidate contents to the terminal 120 , so that the target content may be delivered to the user through the terminal 120 .

[0088] S307: The terminal 120 obtains user feedback information regarding the target content.

[0089] In some embodiments, after the terminal 120 presents the target content to the user, the terminal 120 may obtain the user's feedback information on the target content, and the feedback information may be represented by the user's behavior data. For example, the terminal 120 may obtain the user's click on the historical promotion content, the user's viewing of the promotion content for more than a preset time, and other behavior data.

[0090] S308 : The terminal 120 sends the feedback information to the server 130 .

[0091] S309: The server 130 updates the user's interest characteristics according to the feedback information.

[0092] After obtaining the feedback information, the terminal 120 may send the feedback information to the server 130 so that the server 130 can update the user's interest features according to the feedback information, for example, it can be an online update, so as to optimize the subsequent model and improve the accuracy of the model prediction.

[0093] S310: The server 130 adjusts the parameters of the model using the target content and the updated interest features.

[0094] In some examples, the server can update the model online to adjust the parameters of the model to improve the accuracy of the model's prediction results.

[0095] It should be noted that the above steps S306 to S310 are optional steps. In some embodiments, the above steps S306 to S310 may not be performed.

[0096] Based on the above content description, the disclosed embodiment provides a promotion content processing method. On the one hand, after the method processes the promotion content to obtain multiple candidate contents, it scores the multiple candidate contents based on the user's interest characteristics, and then obtains the scores of the multiple candidate contents, and delivers the target content with the highest score to the user, thereby meeting the personalized needs of different users; on the other hand, the method only requires a small amount of promotion content, and by dividing and combining a small amount of promotion content, a large amount of candidate content can be obtained, thereby enriching the number of promotion content and making it easier to meet the personalized needs of different users.

[0097] Figure 5 is a schematic diagram of a promotion content processing device according to an exemplary disclosed embodiment. Figure 5 As shown, the promotion content processing device 500 includes:

[0098] An acquisition module 501 is used to acquire promotional content to be processed;

[0099] A segmentation module 502 is used to segment the promotional content to obtain multiple content segments;

[0100] A combining module 503, configured to combine the plurality of content segments to obtain a plurality of candidate contents;

[0101] An evaluation module 504, configured to evaluate the scores of the plurality of candidate contents according to the plurality of candidate contents and the interest characteristics of the user;

[0102] The processing module 505 is used to deliver the target content with the highest score among the multiple candidate contents to the user.

[0103] Optionally, the segmentation module 502 is used to perform voice recognition on the promotion content to obtain a voice recognition result, wherein the voice recognition result includes at least one segmentation point; and segment the promotion content using the at least one segmentation point.

[0104] Optionally, the segmentation module 502 is used to perform image recognition on the promotion content to obtain an image recognition result, wherein the image recognition result includes at least one segmentation point; and segment the promotion content using the at least one segmentation point.

[0105] Optionally, the combination module 503 is used to extract the segment features of each content segment among the multiple content segments; obtain the identifier of the cluster center corresponding to the segment features of each content segment according to the mapping relationship between the segment features and the identifiers of the cluster centers; and determine multiple candidate sequences of multiple candidate contents according to the identifiers of the cluster centers.

[0106] Optionally, the multiple candidate sequences include at least a first candidate sequence and a second candidate sequence; the combination module 503 is used to determine the original sequence of the promotion content according to the identifier of the cluster center; adjust the identifier ranked first in the original sequence to the last to obtain the first candidate sequence; adjust the identifier ranked first in the first candidate sequence to the last to obtain the second candidate sequence.

[0107] Optionally, the segment features include text features and / or image features.

[0108] Optionally, an acquisition module 501 is used to obtain feedback information from the user regarding the target content; a processing module 505 is used to update the user's interest characteristics based on the feedback information; and a model parameter is adjusted using the target content and the updated interest characteristics, wherein the model is used to evaluate the scores of the multiple candidate contents.

[0109] The functions of the above modules have been described in detail in the method steps in the previous embodiment and will not be repeated here.

[0110] Reference below Figure 6 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure, the electronic device may be a server 130, the server 130 is used to implement the following Figure 5 The functions corresponding to the promotion content processing device 500 shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0111] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0112] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0113] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0114] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0115] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0116] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0117] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the promotional content to be processed; segments the promotional content to obtain multiple content segments; combines the multiple content segments to obtain multiple candidate content; evaluates the scores of the multiple candidate content based on the multiple candidate content and the user's interest characteristics; and delivers the target content with the highest score among the multiple candidate content to the user.

[0118] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, the first acquisition module may also be described as a "module for acquiring at least two Internet Protocol addresses".

[0121] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0122] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] According to one or more embodiments of the present disclosure, Example 1 provides a promotion content processing method, the method comprising:

[0124] Get the promotional content to be processed;

[0125] Segmenting the promotional content to obtain multiple content segments;

[0126] Combining the multiple content segments to obtain multiple candidate contents;

[0127] Evaluating scores of the plurality of candidate contents according to the plurality of candidate contents and the interest characteristics of the user;

[0128] The target content with the highest score among the multiple candidate contents is delivered to the user.

[0129] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, wherein the segmentation process of the promotion content includes:

[0130] Performing voice recognition on the promotion content to obtain a voice recognition result, wherein the voice recognition result includes at least one segmentation point;

[0131] The promotion content is segmented using the at least one segmentation point.

[0132] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 1, wherein the segmentation process of the promotion content includes:

[0133] Performing image recognition on the promotional content to obtain an image recognition result, wherein the image recognition result includes at least one segmentation point;

[0134] The promotion content is segmented using the at least one segmentation point.

[0135] According to one or more embodiments of the present disclosure, Example 4 provides the method of Examples 1 to 3, wherein combining the multiple content segments includes:

[0136] Extracting a segment feature of each content segment from the plurality of content segments;

[0137] According to the mapping relationship between the segment features and the identifiers of the cluster centers, the identifier of the cluster center corresponding to the segment features of each content segment is obtained;

[0138] According to the identifier of the cluster center, multiple candidate sequences of multiple candidate contents are determined.

[0139] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 4, wherein the multiple candidate sequences include at least a first candidate sequence and a second candidate sequence; and the determining, according to the identifier of the cluster center, multiple candidate sequences of the multiple candidate contents includes:

[0140] Determining the original sequence of the promotion content according to the identifier of the cluster center;

[0141] Adjust the identifier that is ranked first in the original sequence to the last, to obtain the first candidate sequence;

[0142] The identifier that ranks first in the first candidate sequence is moved to the end to obtain the second candidate sequence.

[0143] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 4 or 5, wherein the segment features include text features and / or image features.

[0144] According to one or more embodiments of the present disclosure, Example 7 provides the method of Examples 1 to 6, wherein the method further includes:

[0145] Obtaining feedback information from the user regarding the target content;

[0146] According to the feedback information, updating the interest characteristics of the user;

[0147] The target content and the updated interest features are used to adjust parameters of a model used to evaluate the scores of the plurality of candidate contents.

[0148] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0149] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0150] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A promotion content processing method, characterized in that: The method comprises: Get the promotional content to be processed; Segmenting the promotional content to obtain multiple content segments; Combining the multiple content segments to obtain multiple candidate contents; Evaluating scores of the plurality of candidate contents according to the plurality of candidate contents and the interest characteristics of the user; Delivering the target content with the highest score among the multiple candidate contents to the user; Among them, combining the multiple content segments includes: extracting segment features of each content segment in the multiple content segments; obtaining the identifier of the cluster center corresponding to the segment features of each content segment according to the mapping relationship between the segment features and the identifiers of the cluster centers; and determining multiple candidate sequences of multiple candidate contents according to the identifiers of the cluster centers.

2. The method according to claim 1, characterized in that The segmentation process of the promotion content includes: Performing voice recognition on the promotion content to obtain a voice recognition result, wherein the voice recognition result includes at least one segmentation point; The promotion content is segmented using the at least one segmentation point.

3. The method according to claim 1, characterized in that: The segmentation process of the promotion content includes: Performing image recognition on the promotional content to obtain an image recognition result, wherein the image recognition result includes at least one segmentation point; The promotion content is segmented using the at least one segmentation point.

4. The method according to claim 1, characterized in that: The multiple candidate sequences include at least a first candidate sequence and a second candidate sequence; and the determining, according to the identifier of the cluster center, multiple candidate sequences of the multiple candidate contents includes: Determining the original sequence of the promotion content according to the identifier of the cluster center; Adjust the identifier that is ranked first in the original sequence to the last, to obtain the first candidate sequence; The identifier that ranks first in the first candidate sequence is moved to the end to obtain the second candidate sequence.

5. The method according to claim 1, characterized in that The segment features include text features and / or image features.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Obtaining feedback information from the user regarding the target content; According to the feedback information, updating the interest characteristics of the user; The target content and the updated interest features are used to adjust parameters of a model used to evaluate the scores of the plurality of candidate contents.

7. A promotion content processing device, characterized in that: include: An acquisition module is used to acquire promotional content to be processed; A segmentation module, used to segment the promotional content to obtain multiple content segments; A combining module, used for combining the multiple content segments to obtain multiple candidate contents; An evaluation module, configured to evaluate the scores of the plurality of candidate contents according to the plurality of candidate contents and the interest characteristics of the user; A processing module, configured to deliver the target content with the highest score among the plurality of candidate contents to the user; Among them, the combination module is specifically used to: extract the segment features of each content segment among the multiple content segments; obtain the identifier of the cluster center corresponding to the segment features of each content segment according to the mapping relationship between the segment features and the identifiers of the cluster centers; and determine multiple candidate sequences of multiple candidate contents according to the identifiers of the cluster centers.

8. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the computer program product is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 6.