User-Generated Content Anti-Addiction Method and System

Abstract

The present invention provides a method and system for preventing addiction to user-generated content, belonging to the technical field of data analysis. A first tag of the current page content at the current time t and multiple second tags corresponding to multiple historical page contents within a time period T before the current time t are established; the first tag is compared with each of the multiple second tags one by one. If the similarity or distance value between the first tag and the second tag is greater than a preset threshold, it is determined that the user has entered an addictive state; if the user has entered an addictive state, an alarm signal is issued. The present invention can perform personalized intervention according to the actual situations such as the interest preferences and behavior patterns of different users, making the anti-addiction measures more accurate and effective, improving the security of the user-generated content platform, and improving the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular, to a method and system for preventing addiction to user-generated content. Background Art

[0002] Currently, UGC (User-generated-Content) has become the mainstream Internet service. Some Internet companies combine UGC and recommendation algorithms to push a large amount of content to users, which leads to users being easily addicted while using UGC. Users' addiction to UGC content platforms may result in continuous browsing, creation, or interaction for a long time, thus neglecting important affairs in real life such as study, work, and social interaction. Prolonged use may not only have a negative impact on users' physical health, such as decreased vision and cervical pain, but also cause psychological problems, such as anxiety, loneliness, and distraction of attention. Therefore, how to effectively prevent users from being addicted to UGC content platforms has become an urgent problem to be solved.

[0003] To solve this problem, various anti-addiction methods have been proposed and applied currently. For example, by setting usage time limits, forced rest mechanisms, real-name authentication, and age verification, etc., to limit users' online duration and content access rights. However, most of these methods simply control based on users' online duration or behavior patterns, lacking in-depth analysis and accurate identification of users' content preferences. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for preventing addiction to user-generated content, which determines whether a user enters an addicted state by analyzing and comparing the feature information of the current page content and the historical page content at multiple different historical moments within a period T before the current time t. This method can capture users' interest preferences and behavior patterns, thereby providing more personalized and accurate anti-addiction prompts and measures to solve at least one of the technical problems existing in the above background art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present invention provides a method for preventing addiction to user-generated content, including:

[0007] Obtaining the current page content at the current time t, and the historical page content at multiple different historical moments within a period T before the current time t;

[0008] Based on the current page content, a corresponding first third-order tensor is established, and the first third-order tensor includes current time information, a current page image sample, and a current page image color depth; based on the historical page contents at multiple different historical moments, multiple second third-order tensors corresponding to the historical pages at multiple different historical moments are established, and each of the second third-order tensors includes historical moment information, a page image sample at that historical moment, and a page image color depth at that historical moment;

[0009] Perform character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtain a first label according to the first feature vector; perform character set conversion and vectorization on the multiple second third-order tensors to obtain multiple second feature vectors, and obtain multiple second labels according to the multiple second feature vectors;

[0010] Compare the first label and the multiple second labels one by one. If the similarity or distance value between the first label and the second label is greater than a preset threshold, it is determined that the user has entered an addictive state;

[0011] If the user enters an addictive state, an alarm signal is issued.

[0012] As a further limitation of the first aspect of the present invention, the page content includes one or two different types of modal data, and the modal data is text data, image data, or video data.

[0013] As a further limitation of the first aspect of the present invention, performing character set conversion and vectorization on the first third-order tensor to obtain a first feature vector and obtaining a first label according to the first feature vector includes: converting the first third-order tensor into a first character set, vectorizing the first character set to obtain the first feature vector; extracting the feature information of the first feature vector; calculating the conditional probabilities of different independent features, and performing clustering analysis on the first feature information according to the conditional probability values to obtain the first label.

[0014] As a further limitation of the first aspect of the present invention, performing character set conversion and vectorization on the multiple second third-order tensors to obtain multiple second feature vectors and obtaining multiple second labels according to the multiple second feature vectors includes: converting each of the second third-order tensors into a second character set, vectorizing each of the second character sets to obtain a second feature vector; extracting the feature information of the second feature vector, calculating the conditional probabilities of different independent features, and performing clustering analysis according to the conditional probability values to obtain the second label.

[0015] As a further limitation of the first aspect of the present invention, the similarity or distance value between the first label and the second label is calculated one by one; if the similarity between the first label and the second label corresponding to a certain historical moment is higher than the set similarity threshold or the distance value is lower than the set distance threshold, it indicates that there is consistency or similarity between the current page content and the historical page content at that historical moment, and then it is determined that the user has entered the addictive state.

[0016] As a further limitation of the first aspect of the present invention, a Naive Bayes classifier is used to calculate the prior probability and conditional probability of each category according to the training data set, calculate the posterior probability of the input first feature information belonging to each category, and select the category with the largest probability as the prediction result, that is, the first label.

[0017] In a second aspect, the present invention provides a user-generated content anti-addiction system, including:

[0018] An acquisition module, configured to acquire the current page content at the current time t, and the historical page contents at a plurality of different historical moments within a time period T before the current time t;

[0019] A processing module, configured to establish a corresponding first third-order tensor according to the current page content, where the first third-order tensor includes current time information, a current page image sample, and a current page image color depth; establish a plurality of second third-order tensors corresponding to the historical pages at a plurality of different historical moments according to the historical page contents at a plurality of different historical moments, and each of the second third-order tensors includes historical moment information, a page image sample at that historical moment, and a page image color depth at that historical moment;

[0020] A conversion module, configured to perform character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtain a first label according to the first feature vector; perform character set conversion and vectorization on the plurality of second third-order tensors to obtain a plurality of second feature vectors, and obtain a plurality of second labels according to the plurality of second feature vectors;

[0021] A comparison module, configured to compare the first label and the plurality of second labels one by one, and if the similarity or distance value between the first label and the second label is greater than a preset threshold, it is determined that the user has entered the addictive state;

[0022] An alarm module, configured to send an alarm signal if the user enters the addictive state.

[0023] In a third aspect, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium; the processor is adapted to execute a computer program; the computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the user-generated content anti-addiction method as described in the first aspect is implemented.

[0024] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program is adapted to be loaded and executed by a processor to implement the user-generated content anti-addiction method as described in the first aspect.

[0025] In a fifth aspect, the present invention provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the user-generated content anti-addiction method as described in the first aspect is implemented.

[0026] Advantages of the present invention: First, obtain the current page content of the user and the page content within a previously set time, then extract the feature information of these contents and perform clustering analysis to obtain corresponding labels. Next, compare the similarity or distance value between the label of the current page content and the label of the previous page content. If the similarity is higher than the set threshold (or the distance value is lower than the set threshold), it is determined that the user may enter an addictive state. Finally, trigger an alarm signal or other preset anti-addiction measures to remind the user to pay attention to the usage duration and content selection. It can perform personalized intervention according to the actual situations such as the interest preferences and behavior patterns of different users, making the anti-addiction measures more accurate and effective, improving the security of the UGC content platform, and improving the user experience. Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings according to these drawings without creative efforts.

[0028] Figure 1 It is a functional framework diagram of the user-generated content anti-addiction system according to the embodiment of the present invention.

[0029] Figure 2 It is a principle block diagram of the computer device according to the embodiment of the present invention. Detailed Embodiments

[0030] To facilitate the understanding of the present invention, the present invention will be further explained below with specific embodiments in conjunction with the drawings, and the specific embodiments do not constitute a limitation to the embodiments of the present invention.

[0031] Those skilled in the art should understand that the accompanying drawings are only schematic diagrams of the embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0032] Embodiment 1

[0033] In this Embodiment 1, a method for preventing addiction to user-generated content is provided, including the following steps:

[0034] Obtain the current page content at the current time t, and the historical page contents at multiple different historical moments within a period T before the current time t;

[0035] According to the current page content, establish its corresponding first third-order tensor, which includes current time information, current page image samples, and current page image color depth; according to the historical page contents at multiple different historical moments, establish multiple second third-order tensors corresponding to the historical pages at multiple different historical moments, and each of the second third-order tensors includes historical moment information, page image samples at that historical moment, and page image color depth at that historical moment;

[0036] Perform character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtain a first label according to the first feature vector; perform character set conversion and vectorization on the multiple second third-order tensors to obtain multiple second feature vectors, and obtain multiple second labels according to the multiple second feature vectors;

[0037] Compare the first label with the multiple second labels one by one. If the similarity or distance value between the first label and the second label is greater than a preset threshold, it is determined that the user has entered an addicted state;

[0038] If the user enters an addicted state, an alarm signal is issued.

[0039] In this embodiment, first, the user's current page content and the page content within the previously set time are obtained. Then, the feature information of these contents is extracted and cluster analysis is performed to obtain corresponding labels. Next, the similarity or distance value between the label of the current page content and the labels of the previous page contents is compared. If the similarity is higher than the set threshold (or the distance value is lower than the set threshold), it is determined that the user may have entered an addicted state. Finally, an alarm signal or other preset anti-addiction measures are triggered to remind the user to pay attention to the usage duration and content selection. This personalized analysis method makes the anti-addiction measures more accurate and can be customized for different users' actual situations. It helps to improve the user experience and security of the UGC content platform and promote the health of users.

[0040] In this embodiment, in the information collection step of the above page content, in practical applications, with the server as the implementation entity, it includes the following steps:

[0041] Through the API interface or web crawler technology of the UGC content platform, the content of the current page browsed by the user at the current time t is captured in real time. A time window T (i.e., the time period T before time t) is set, and through the platform's historical records or database, the historical page content at multiple different historical moments browsed by the user within this time window is extracted. The above-mentioned page content includes, but is not limited to, multimedia data such as text, images, and videos. Although the page content collected in this step includes, but is not limited to, various modal multimedia data such as text, images, and videos, in the subsequent stages after this step, both the current page content and the historical page content only include one or two types of modal information, such as only including one of text, images, and videos, or only including any two of text, images, and videos.

[0042] In practical applications, taking the user side as the implementation entity, the content of the page browsed by the user at the current time t is captured in real time through screenshots. A time window T is set, and through screenshots, the page content at multiple different historical moments browsed by the user within this time window is extracted and retained.

[0043] It can be understood that when implementing the above steps for collecting page content information, conventional methods can be used to obtain the content of the current page. The current page refers to the page displayed on the current terminal, usually the terminal is a monitor and / or a speaker and / or a touch display device. The content of the current page refers to the content of various media such as text and images on the current page. In this embodiment, regardless of the form of obtaining the current page content and historical page content, time is the main basis, and each page content is assigned a timestamp, so that the collected page content can be sorted according to the timestamp, thus ensuring the correctness and consistency of the data source sorting and providing support for subsequent time series analysis.

[0044] In this embodiment, it can be understood that the current time t is obtained, and a first third-order tensor including the current time t is established. The first third-order tensor is a vector containing three elements. In addition to the current time t information, the elements included in the first third-order tensor also include the image sample of the current page and the color depth of the current page image. A time period T is set, and multiple second third-order tensors including historical moment information within the time period T before the current time t are established. The second third-order tensor also includes the historical moment image sample and the color depth. The image sample and color depth information are applicable to pages containing image content.

[0045] In this embodiment, multiple historical moments are set within the time period T, denoted as T1, T2, …, Tn respectively. Third-order tensors including historical time information at moments T1, T2, …, Tn are obtained respectively, that is, the content of the second page is obtained at moments T1, T2, …, Tn. It can also be understood that this embodiment also includes deleting duplicate page content, and only keeping one of multiple identical screenshots. For the most widely used mobile devices currently, deleting duplicate content helps to control the storage size and reduce the storage requirements. For UGC content, it can also reduce the deviation of the analysis results.

[0046] In this embodiment, for the current page content, natural language processing (NLP) and computer vision (CV) technologies are used for in-depth analysis to extract first feature information such as keywords, image features, and sentiment tendencies. Specifically, for the text content in the page content, after text recognition, the TF-IDF method, N-gram model, or bag-of-words model is used to convert the content into a first character set, and then the first character set is vectorized to extract the text data feature vector; and / or for the audio content in the page content, the speech conversion method is used to convert the audio content into text content, and then the TF-IDF method, N-gram model, or bag-of-words model is used to extract the text data feature vector; and / or for the image content in the page, traditional image feature extraction methods are used to extract the feature vector of the image. Traditional image feature extraction methods include the SIFT method, SURF method, HOG method, ORB method, etc. This is common knowledge in the art and will not be listed one by one here. It can be understood that this kind of step depends on the computing module deployed on the server side or the computing module deployed on the client side.

[0047] For the historical page content, first, the features are extracted by the method described in the above first feature information extraction, and then unsupervised learning algorithms (such as K-means, DBSCAN, etc.) are used for clustering analysis to form multiple different content category labels, that is, the second labels.

[0048] It can be understood that in one or more embodiments, the first feature is extracted currently, and the second feature is extracted and retained at historical moments. There is a time difference between the two. For the first page content, since it represents the latest data, simple feature extraction can meet the basic analysis requirements. For the historical page content, since it contains historical data, more in-depth data mining and analysis are required. Therefore, clustering analysis is used to discover hidden patterns or trends in the data.

[0049] In this embodiment, the following steps can also be used to extract feature vectors: for the text content in the page content, after text recognition, a convolutional neural network or a recurrent neural network is used to extract the feature vectors of the text data; and / or for the audio content in the page content, a speech conversion method is used to convert the audio content into text content, and then a convolutional neural network or a recurrent neural network is used to extract the feature vectors of the text data; and / or for the image content in the page, a convolutional neural network or a recurrent neural network is used to extract the feature vectors of the image. It can be understood that such steps rely on the computing module deployed on the server side.

[0050] In this embodiment, a label generation algorithm is adopted to map the first feature information into a predefined label system to obtain the label of the current page content, that is, the first label. In one embodiment, a Naive Bayes classifier can be used to generate the first label, calculate the conditional probabilities of different independent features, classify the first feature information according to the conditional probability values, and obtain the first label according to the classification. More specifically, when using the Naive Bayes classifier, first calculate the prior probability and conditional probability of each category according to the training data set, then calculate the posterior probability of the input first feature information belonging to each category according to the input first feature information, and select the category with the largest probability as the prediction result, that is, the first label. It can be understood that the above training data set can be a customized picture data set or text data set, which is a common technology in this field and will not be elaborated here. In one embodiment, a support vector machine can also be used. First, train the support vector machine model on the training data set to find the optimal hyperplane parameters, then input the first feature information into the trained support vector machine model, and determine the category to which it belongs according to the output value, that is, the first label. In one embodiment, unsupervised or semi-supervised deep learning algorithms such as the K-means clustering algorithm, DBSCAN clustering algorithm, or label propagation algorithm can also be used, which will not be elaborated here.

[0051] In this embodiment, an empty data structure (i.e., a similarity list) is created in advance. Different data structures can be selected according to different programming languages and data volumes. Lists or arrays are the most common choices because they can store multiple values in order and can be accessed quickly through indexes. Set the similarity list to be empty so that similarity values can be added later. After initialization, the program will traverse each second label, calculate the similarity or distance value between the first label and each second label, and add the results to the similarity or distance value list. The similarity or distance value list will be used in subsequent steps to determine whether there is a situation where a certain similarity value exceeds the preset threshold or the distance value is lower than the preset threshold, so as to determine whether the user is repeatedly browsing similar content and has a risk of addiction.

[0052] It can be understood that in the above steps, the core is to compare the first tags with the second tags one by one, and then for each pair of compared tags, calculate the similarity between them. According to the calculated similarity or distance value and a preset threshold, it is determined whether the user enters an addictive state; if the similarity of a pair of tags is higher than the threshold or the distance value is lower than the threshold, it may indicate that there is a high degree of consistency or similarity between the current page content and the previous page content, and then it is determined that the user enters an addictive state.

[0053] In this embodiment, it is necessary to ensure that each first tag is compared with the corresponding second tag (based on chronological order or other association rules). For each pair of compared tags, calculate the similarity or distance value between them. The calculation method of the similarity or distance value can be selected according to the actual application scenario, such as cosine similarity, Euclidean distance, Manhattan distance, etc. According to the calculated similarity or distance value and the preset threshold, it is determined whether the user enters an addictive state. If the similarity of a pair of tags is higher than the threshold (or the distance value is lower than the threshold, depending on the selected calculation method and threshold setting method), it may indicate that there is a high degree of consistency or similarity between the current page content and the previous page content, and then it may be determined that the user enters an addictive state. After determining that the user enters an addictive state, an alarm signal or other preset anti-addiction measures can be further triggered to remind the user to pay attention to the usage duration and content selection, or to limit the user's further access.

[0054] Embodiment 2

[0055] As Figure 1 shown, Embodiment 2 of the present invention provides a user-generated content anti-addiction system, including:

[0056] An acquisition module, configured to acquire the current page content at the current time t and the historical page contents at multiple different historical moments within a previous time period T before the current time t;

[0057] A processing module, configured to establish a corresponding first third-order tensor according to the current page content, where the first third-order tensor includes current time information, a current page image sample, and a current page image color depth; and establish multiple second third-order tensors corresponding to the historical pages at multiple different historical moments according to the historical page contents at multiple different historical moments, and each of the second third-order tensors includes historical moment information, a page image sample at that historical moment, and a page image color depth at that historical moment;

[0058] A conversion module for performing character set conversion and vectorization on the first third-order tensor to obtain a first eigenvector, and obtaining a first label based on the first eigenvector; performing character set conversion and vectorization on a plurality of the second third-order tensors to obtain a plurality of second eigenvectors, and obtaining a plurality of second labels based on the plurality of second eigenvectors;

[0059] A comparison module for comparing the first label and the plurality of second labels one by one. If the similarity or distance value between the first label and the second label is greater than a preset threshold, it is determined that the user is in an addicted state;

[0060] An alarm module for sending an alarm signal if the user is in an addicted state.

[0061] It can be understood that the above-mentioned various modules can be respectively or all combined into one or several other modules to form, or some of them can be further split into multiple smaller units with functions to form, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present invention. The above modules are divided based on logical functions. In actual applications, the function of one module can also be realized by multiple modules, or the functions of multiple modules can be realized by one module. In other embodiments of the present invention, the system may also include other modules. In actual applications, these functions can also be assisted by other modules and can be realized by the cooperation of multiple modules.

[0062] According to another embodiment of the present invention, a system according to this embodiment can be constructed by running a computer program (including program code) capable of executing the respective steps involved in the corresponding method described in Embodiment 1 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), a random access memory (RAM), and a read-only memory (ROM), and the method of Embodiment 1 of the present invention can be realized. The computer program can be recorded on a computer-readable recording medium, loaded into the above computing device through the computer-readable recording medium, and run therein.

[0063] This embodiment is based on the background of a UGC content platform (such as a short video platform). This platform has a large number of users, and there is a problem that some users are overly addicted to UGC content. To solve this problem, the platform plans to apply the above system to deeply analyze the user page content through artificial intelligence technology, judge the addicted state of the user, and perform personalized intervention.

[0064] The platform collects page data of users browsing UGC content, including text, images, etc., and preprocesses the collected data, such as denoising, standardization, etc., to improve the accuracy of subsequent analysis. It uses artificial intelligence technology to extract feature information of the page content, such as keywords, image features, etc., and performs clustering analysis on the extracted feature information to obtain corresponding labels, such as entertainment, education, technology, etc. Calculate the similarity or distance value between the current page content label and the previous page content label, which can be achieved through algorithms such as cosine similarity and Euclidean distance. Set a threshold value. When the similarity or distance value exceeds this threshold, it is considered that the user may be repeatedly browsing similar content and there is a risk of addiction. Determine whether the user is in an addicted state according to the similarity or distance value and the preset threshold. When the user is judged to be in an addicted state, trigger an alarm signal, such as sending a reminder message to the user or popping up a warning window. In addition, time limits and rest reminders can also be set. When the user continuously browses UGC content for more than a certain period of time, the content playback is automatically paused and the user is reminded to rest.

[0065] Embodiment 3

[0066] As Figure 2 shown, this implementation provides an electronic device, which includes a processor, a communication interface, and a computer-readable storage medium. Among them, the processor, the communication interface, and the computer-readable storage medium can be connected through a bus or other means.

[0067] Among them, the communication interface is used to receive and send data. The computer-readable storage medium can be stored in the memory of the electronic device. The computer-readable storage medium is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer-readable storage medium.

[0068] The processor (or CPU (Central Processing Unit, central processing unit)) is the computing core and control core of the electronic device, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method process or corresponding function.

[0069] The processor is configured to execute the following process:

[0070] Obtain the current page content at the current time t, and the historical page content at multiple different historical moments within a previous time period T before the current time t;

[0071] Based on the current page content, a corresponding first third-order tensor is established, and the first third-order tensor includes current time information, a current page image sample, and a current page image color depth; based on the historical page contents at multiple different historical moments, multiple second third-order tensors corresponding to the historical pages at multiple different historical moments are established, and each of the second third-order tensors includes historical moment information, a page image sample at that historical moment, and a page image color depth at that historical moment;

[0072] Perform character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtain a first label according to the first feature vector; perform character set conversion and vectorization on the multiple second third-order tensors to obtain multiple second feature vectors, and obtain multiple second labels according to the multiple second feature vectors;

[0073] Compare the first label with the multiple second labels one by one. If the similarity or distance value between the first label and the second label is greater than a preset threshold, it is determined that the user has entered an addictive state;

[0074] If the user enters an addictive state, an alarm signal is issued.

[0075] Embodiment 4

[0076] This implementation provides a computer-readable storage medium (Memory). A computer-readable storage medium is a memory device in an electronic device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the electronic device and, of course, the extended storage medium supported by the electronic device. The computer-readable storage medium provides a storage space, and this storage space stores the processing system of the electronic device.

[0077] Moreover, one or more instructions suitable for being loaded and executed by a processor are also stored in this storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory; optionally, it can also be at least one computer-readable storage medium located far from the aforementioned processor.

[0078] In one embodiment, one or more instructions are stored in the computer-readable storage medium; the one or more instructions stored in the computer-readable storage medium are loaded and executed by a processor to implement the following process:

[0079] Obtain the current page content at the current time t, and the historical page contents at multiple different historical moments within a period T before the current time t;

[0080] Based on the current page content, a corresponding first third-order tensor is established. The first third-order tensor includes current time information, a current page image sample, and the current page image color depth. Based on the historical page contents at multiple different historical moments, multiple second third-order tensors corresponding to the historical pages at multiple different historical moments are established. Each of the second third-order tensors includes historical moment information, the page image sample at that historical moment, and the page image color depth at that historical moment.

[0081] Perform character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtain a first label based on the first feature vector. Perform character set conversion and vectorization on the multiple second third-order tensors to obtain multiple second feature vectors, and obtain multiple second labels based on the multiple second feature vectors.

[0082] Compare the first label with the multiple second labels one by one. If the similarity or distance value between the first label and the second label is greater than a pre-set threshold, it is determined that the user has entered an addictive state.

[0083] If the user enters an addictive state, an alarm signal is issued.

[0084] Embodiment 5

[0085] This implementation provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the electronic device to perform the following processes:

[0086] Obtain the current page content at the current time t, and the historical page contents at multiple different historical moments within a period T before the current time t.

[0087] Based on the current page content, a corresponding first third-order tensor is established. The first third-order tensor includes current time information, a current page image sample, and the current page image color depth. Based on the historical page contents at multiple different historical moments, multiple second third-order tensors corresponding to the historical pages at multiple different historical moments are established. Each of the second third-order tensors includes historical moment information, the page image sample at that historical moment, and the page image color depth at that historical moment.

[0088] Perform character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtain a first label based on the first feature vector. Perform character set conversion and vectorization on the multiple second third-order tensors to obtain multiple second feature vectors, and obtain multiple second labels based on the multiple second feature vectors.

[0089] Compare the first tag and the multiple second tags one by one. If the similarity or distance value between the first tag and the second tag is greater than a pre-set threshold, it is determined that the user is in an addictive state;

[0090] If the user is in an addictive state, an alarm signal is issued.

[0091] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0092] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data processing device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0093] Although the specific implementation manners of the present invention are described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that based on the technical solutions disclosed in the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts should be covered within the protection scope of the present invention.

Claims

1. A method for preventing user-generated content addiction, characterized in that: include: Get the current page content at the current time, as well as the historical page content at multiple different historical moments within a period of time before the current time; According to the current page content, a first third-order tensor corresponding to the current page content is established, wherein the first third-order tensor includes current time information, current page image samples, and current page image color depth; according to the historical page contents at multiple different historical moments, multiple second third-order tensors corresponding to historical pages at multiple different historical moments are established, wherein each of the second third-order tensors includes historical moment information, page image samples at the historical moment, and page image color depth at the historical moment; The first third-order tensor is subjected to character set conversion and vectorization to obtain a first feature vector, and a first label is obtained according to the first feature vector, specifically including: converting the first third-order tensor into a first character set, vectorizing the first character set, and obtaining the first feature vector; extracting feature information of the first feature vector; calculating the conditional probabilities of different independent features, and performing cluster analysis on the first feature information according to the conditional probability values ​​to obtain a first label; the plurality of second third-order tensors are subjected to character set conversion and vectorization to obtain a plurality of second feature vectors, and a plurality of second labels are obtained according to the plurality of second feature vectors, specifically including: converting each of the second third-order tensors into a second character set, vectorizing each of the second character sets, and obtaining a second feature vector; extracting feature information of the second feature vector, calculating the conditional probabilities of different independent features, and performing cluster analysis according to the conditional probability values ​​to obtain the second label; Comparing the first tag with the plurality of the second tags one by one, and if the similarity or distance value between the first tag and the second tag is greater than a preset threshold, it is determined that the user has entered an addicted state; specifically comprising: calculating the similarity or distance value between the first tag and the second tag one by one; if the similarity between the first tag and the second tag corresponding to a certain historical moment is higher than a set similarity threshold or the distance value is lower than a set distance threshold, it indicates that there is consistency or similarity between the current page content and the historical page content at the historical moment, and then determining that the user has entered an addicted state; If the user enters an addicted state, an alarm signal will be issued.

2. The user-generated content anti-addiction method according to claim 1, characterized in that: The page content includes one or two different modal data, and the modal data is text data, image data or video data.

3. The user-generated content anti-addiction method according to claim 1, characterized in that: Using the naive Bayes classifier, the prior probability and conditional probability of each category are calculated according to the training data set. According to the input first feature information, the posterior probability of it belonging to each category is calculated, and the category with the largest probability is selected as the prediction result, that is, the first label.

4. A user-generated content anti-addiction system, characterized in that: include: The acquisition module is used to acquire the current page content at the current time t, and the historical page content at multiple different historical moments within a time period T before the current time t; A processing module is used to establish a first third-order tensor corresponding to the current page content according to the current page content, wherein the first third-order tensor includes current time information, current page image samples, and current page image color depth; and to establish a plurality of second third-order tensors corresponding to historical pages at a plurality of different historical moments according to the historical page contents at a plurality of different historical moments, wherein each of the second third-order tensors includes historical moment information, page image samples at the historical moment, and page image color depth at the historical moment; A conversion module, for performing character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtaining a first label according to the first feature vector; and for performing character set conversion and vectorization on multiple second third-order tensors to obtain multiple second feature vectors, and obtaining multiple second labels according to the multiple second feature vectors; performing character set conversion and vectorization on the first third-order tensor to obtain a first feature vector, and obtaining a first label according to the first feature vector; specifically including: converting the first third-order tensor into a first character set, vectorizing the first character set, and obtaining the first feature vector; extracting feature information of the first feature vector; calculating the conditional probabilities of different independent features, and performing cluster analysis on the first feature information according to the conditional probability values ​​to obtain the first label; performing character set conversion and vectorization on multiple second third-order tensors to obtain multiple second feature vectors, and obtaining multiple second labels according to the multiple second feature vectors, specifically including: converting each of the second third-order tensors into a second character set, vectorizing each of the second character sets, and obtaining a second feature vector; extracting feature information of the second feature vector, calculating the conditional probabilities of different independent features, and performing cluster analysis according to the conditional probability values ​​to obtain the second label; A comparison module, used for comparing the first tag with the plurality of the second tags one by one, and if the similarity or distance value between the first tag and the second tag is greater than a preset threshold, it is judged that the user has entered an addicted state; specifically comprising: calculating the similarity or distance value between the first tag and the second tag one by one; if the similarity between the first tag and the second tag corresponding to a certain historical moment is higher than a set similarity threshold or the distance value is lower than a set distance threshold, it indicates that there is consistency or similarity between the current page content and the historical page content at the historical moment, and then judging that the user has entered an addicted state; The alarm module is used to send out an alarm signal if the user enters an addicted state.

5. A computer device, characterized in that: include: a processor and a computer readable storage medium; A processor, suitable for executing a computer program; the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the user-generated content anti-addiction method as described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which is suitable for being loaded by a processor and executing the user-generated content anti-addiction method as described in any one of claims 1 to 3.

7. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the user-generated content anti-addiction method as described in any one of claims 1 to 3.

Images