Short message interception processing method, short message interception processing system and server

Abstract

The invention relates to the technical field of communication, and discloses a short message interception processing method, a short message interception processing system and a server, and the method comprises the steps: obtaining first short message data, inputting the first short message data into a classification model to generate an interception strategy, judging whether a real-time short message is a junk short message or not based on the interception strategy, and if the real-time short message is the junk short message, sending the junk short message to the server; if the short messages are not spam short messages, the real-time short messages are added to the blacklist, and if the short messages are not spam short messages, the real-time short messages are pushed to the user, the corresponding interception strategy can be generated for the user based on the historical short message data of the user, so that the spam short message interception effect is improved, and the satisfaction degree of the user to short message communication is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and in particular to a text message interception processing method, a text message interception processing system and a server. Background Art

[0002] With the rapid development of mobile communication technology and the popularization of smart phones, the frequency of users communicating and exchanging information through text messages has increased significantly. However, this is also accompanied by the generation of a large number of spam text messages, which affects the user experience.

[0003] At present, spam SMS blocking systems usually rely on static rules to identify and block spam SMS, such as keyword filtering, fixed blacklists, etc. Since the senders of spam SMS often change their methods and words to evade detection, thereby avoiding triggering keyword filtering rules, and when new senders of spam SMS appear, the use of fixed blacklists cannot effectively block spam SMS. In addition, with the continuous evolution and development of spam SMS sending strategies, the use of static rules cannot adapt to changes in spam SMS sending strategies, resulting in poor interception results. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present application provide a text message interception processing method, a text message interception processing system and a server to solve the problem that static rules cannot adapt to changes in spam text message sending strategies, resulting in poor interception effect. It can improve the interception effect of spam text messages and improve user satisfaction with text message communications.

[0005] In order to solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for intercepting and processing short messages, the method comprising:

[0007] Acquire first SMS data, wherein the first SMS data includes junk SMS and non-junk SMS;

[0008] Inputting the first SMS data into a classification model to generate an interception strategy, wherein the interception strategy is used to intercept spam SMS;

[0009] Acquire second SMS data, wherein the second SMS data is real-time SMS data;

[0010] Based on the interception strategy, determining whether the second SMS data is a spam SMS;

[0011] If the second SMS data is junk SMS, adding the second SMS data to a blacklist;

[0012] If the second SMS data is not a spam SMS, the second SMS data is pushed to the user.

[0013] In some embodiments, inputting the first SMS data into a classification model to generate an interception strategy includes:

[0014] Extracting features from the first SMS data to obtain a first key feature;

[0015] Analyze the first key feature through the classification model to obtain an analysis result;

[0016] Based on the analysis results, an interception strategy is generated.

[0017] In some embodiments, the first key feature includes a keyword and a sender, and the first key feature is analyzed by a classification model to obtain an analysis result, including:

[0018] Analyze the keywords and senders respectively to obtain the analysis results, including:

[0019] Counting the frequency of the keyword being marked by the user to obtain a first statistical result, and using the first statistical result as the analysis result, wherein the first statistical result includes the frequency;

[0020] The number of times the sender is marked by the user is counted to obtain a second statistical result, and the second statistical result is used as the analysis result, wherein the second statistical result includes the number of times.

[0021] In some embodiments, based on the analysis results, an interception strategy is generated, including:

[0022] Add keywords with a frequency greater than the frequency threshold to the blacklist;

[0023] Add senders whose times exceed the threshold to the blacklist;

[0024] Based on the blacklist, an interception strategy is generated, wherein the interception strategy includes intercepting specific senders and filtering specific keywords.

[0025] In some embodiments, based on the interception strategy, determining whether the second SMS data is a spam SMS includes:

[0026] Extracting a keyword from the second SMS data, and determining whether the keyword exists in a blacklist, if the keyword exists in the blacklist, determining that the second SMS data is a spam message, and if the keyword does not exist in the blacklist, determining that the second SMS data is a non-spam message;

[0027] and / or,

[0028] It is detected whether the sender corresponding to the second SMS data exists in the blacklist. If the sender exists in the blacklist, it is determined that the second SMS data is a spam SMS. If the sender does not exist in the blacklist, it is determined that the second SMS data is not a spam SMS.

[0029] In some embodiments, the method further comprises:

[0030] Retrain the classification model to update the interception strategy, including:

[0031] Obtain user feedback data at preset time intervals;

[0032] The classification model is retrained based on the feedback data to update the interception strategy.

[0033] In some embodiments, retraining the classification model based on the feedback data includes:

[0034] Extracting features from the feedback data to obtain a second key feature, wherein the second key feature includes a keyword and a sender;

[0035] Based on the second key feature, the classification model is retrained to obtain a trained classification model.

[0036] In some embodiments, updating the interception policy includes:

[0037] Based on the trained classification model, the keywords and senders in the blacklist are updated to obtain an updated blacklist;

[0038] Generate a new interception strategy based on the updated blacklist.

[0039] In a second aspect, an embodiment of the present application provides a server, including:

[0040] A processor and a memory, the processor is used to execute the executable program code in the memory, and when the executable program code is executed, the processor executes the instructions of the SMS interception processing method of the first aspect.

[0041] In a third aspect, an embodiment of the present application provides a short message interception processing system, the system comprising:

[0042] The server of the second aspect is used to generate an interception strategy and to regularly update the interception strategy;

[0043] An electronic device is used to obtain an interception strategy, identify spam text messages based on the interception strategy, and intercept the spam text messages.

[0044] The beneficial effect of the implementation of the present application is that, different from the prior art, the implementation of the present application provides a method for intercepting and processing short messages, the method comprising: obtaining first short message data, wherein the first short message data includes junk short messages and non-junk short messages, inputting the first short message data into a classification model to generate an interception strategy, wherein the interception strategy is used to intercept junk short messages, obtaining second short message data, wherein the second short message data is real-time short message data, judging whether the second short message data is a junk short message based on the interception strategy, if the second short message data is a junk short message, adding the second short message data to a blacklist, and if the second short message data is non-junk short messages, pushing the second short message data to the user. The present application can generate a corresponding interception strategy for the user based on the user's historical short message data, so as to improve the interception effect of junk short messages and improve the user's satisfaction with short message communications. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] One or more embodiments are exemplarily described by corresponding drawings, which do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and the figures in the drawings do not constitute proportional limitations unless otherwise stated.

[0046] Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

[0047] Figure 2 It is a flowchart of a method for intercepting and processing short messages provided in an embodiment of the present application;

[0048] Figure 3 yes Figure 2 A detailed flow chart of step S202 in FIG.

[0049] Figure 4 yes Figure 3 A detailed flow chart of step S2022 in FIG.

[0050] Figure 5 yes Figure 3 A detailed flow chart of step S2023 in FIG.

[0051] Figure 6 yes Figure 2 A detailed flow chart of step S204 in FIG.

[0052] Figure 7 It is a flowchart of an update interception strategy provided by an embodiment of the present application;

[0053] Figure 8 yes Figure 7 A detailed flow chart of step S702 in FIG.

[0054] Fig. 9It is a structural schematic diagram of a text message interception and processing system provided in an embodiment of the present application;

[0055] Fig.10 It is a structural schematic diagram of a text message interception processing device provided in an embodiment of the present application;

[0056] Fig.11 It is a structural diagram of a server provided in an embodiment of the present application.

[0057] Description of Figure Numbers:

[0058]

[0059] DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0061] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, and all are within the scope of protection of the present application. In addition, the words "first", "second", etc. used in the present application do not limit the data, but only divide the same or similar items with basically the same functions and effects.

[0062] Before introducing the embodiments of the present application, a short message interception processing method known to the inventor of the present application is briefly introduced to facilitate subsequent understanding of the embodiments of the present application.

[0063] Currently, SMS interception usually adopts static rules, such as fixed blacklists and keywords. The above solutions have the following disadvantages:

[0064] (1) Static rules cannot adapt to changes in spam SMS sending strategies, resulting in certain limitations in intercepting information. For example, important information may be intercepted by mistake, or spam SMS may be missed.

[0065] (2) Due to the lack of adaptive capabilities, static rules cannot be adjusted in a timely manner, resulting in poor spam blocking effects and reduced user experience.

[0066] In response to the above problems, the present application obtains historical SMS data, inputs the historical SMS data into a classification model to generate an interception strategy, and determines whether the real-time SMS is a spam SMS based on the interception strategy. If it is a spam SMS, the real-time SMS is added to a blacklist; if it is a non-spam SMS, the real-time SMS is pushed to the user. The present application can generate a corresponding interception strategy for the user based on the user's historical SMS data to improve the interception effect of spam SMS and improve the user's satisfaction with SMS communication.

[0067] Before introducing the present application in detail, a brief introduction to the prior art known to the present application is given to facilitate subsequent understanding of the embodiments of the present application.

[0068] Personalized Learning Algorithm: A machine learning algorithm used to customize and optimize software services based on the user's historical behavior data (such as deleting, ignoring, or marking text messages as spam). This algorithm enables the system to learn individual preferences and automatically adjust its functions. Personalized learning algorithms include decision tree ensemble learning algorithms and random forest algorithms.

[0069] Decision Tree Ensemble Learning Algorithm: It is a machine learning algorithm used to complete learning tasks by building and combining multiple learners. Decision tree is a common prediction model. In ensemble learning, multiple decision trees are combined to combine the prediction results of each decision tree to complement each other, thereby obtaining more accurate prediction results, improving the accuracy of predictions and preventing overfitting.

[0070] Random Forest Algorithm: A decision tree ensemble learning algorithm that improves overall prediction accuracy by building multiple decision trees and integrating their prediction results. The random forest algorithm works well when processing a large number of input variables and is highly robust to outliers and nonlinear data.

[0071] Incremental Learning: is a learning method that allows the model to be updated as new data arrives without retraining the entire model from scratch, saving resources and enabling the model to adapt to new data patterns.

[0072] Whitelist: In the field of information security, a whitelist is a list of allowed elements (such as email addresses, software, IP addresses, etc.). In the SMS receiving preprocessing system, users can add trusted senders to the whitelist to ensure that their SMS messages will not be intercepted.

[0073] Blacklist: Corresponding to the whitelist, the blacklist is a list of elements that are not allowed or rejected. In this system, spam senders will be automatically added to the blacklist and dynamically updated based on user feedback and model predictions.

[0074] Dynamic Updating Mechanism: refers to the system's ability to automatically adjust parameters or lists (such as black and white lists) based on real-time data and user feedback data. This mechanism enables the system to continuously adapt to changes and improve system accuracy and user satisfaction.

[0075] The technical solution of the present application is described in detail below in conjunction with the accompanying drawings:

[0076] See also Figure 1 , Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

[0077] like Figure 1 As shown, the application environment 100 includes a server 10 and an electronic device 20. The server 10 and the electronic device 20 are connected via a wireless network or a wired network. The wireless network includes wireless networks such as 2G, 3G, 4G, 5G, wireless LAN, and Bluetooth, and the wired network includes wired networks such as serial cables and network cables.

[0078] The server 10 is used to generate an interception strategy and send the interception strategy to the electronic device 20, wherein the interception strategy includes intercepting a specific sender and filtering specific keywords.

[0079] Among them, server 10 is an independent physical server, or it can be a server cluster or distributed system composed of multiple physical servers, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0080] The electronic device 20 is used to receive the interception strategy sent by the server 10 and deploy the interception strategy on the electronic device 20. When communicating with other electronic devices via SMS, the electronic device 20 identifies junk SMS based on the interception strategy and intercepts the junk SMS.

[0081] The electronic device 20 includes mobile phones, tablet computers, smart wearable devices (such as smart watches) and other devices capable of SMS communication.

[0082] See also Figure 2 , Figure 2 It is a flowchart of a method for intercepting and processing short messages provided in an embodiment of the present application;

[0083] The SMS interception processing method is applied to a server. Specifically, the execution subject of the SMS interception processing method is one or at least two processors of the server.

[0084] like Figure 2 As shown, the SMS interception processing method includes:

[0085] Step S201: Acquire first SMS data, wherein the first SMS data includes junk SMS and non-junk SMS;

[0086] In an embodiment of the present application, the first SMS data is historical SMS data, which includes spam SMS and non-spam SMS, wherein spam SMS refers to SMS messages sent to a user without the user's consent and which the user does not want to receive, or SMS messages that the user cannot refuse to receive according to his or her own wishes, and non-spam SMS refers to SMS messages that the user agrees to receive, which are valuable to the user or which the user does not consider to constitute harassment.

[0087] Specifically, first SMS data is obtained from the electronic device.

[0088] In the embodiment of the present application, the first SMS data is used to perform preliminary training on the classification model so that the classification model can distinguish between junk SMS and non-junk SMS.

[0089] Step S202: inputting the first SMS data into a classification model to generate an interception strategy, wherein the interception strategy is used to intercept junk SMS;

[0090] In an embodiment of the present application, the first SMS data includes SMS reception records and SMS sending records, wherein the SMS reception records include the content of the SMS received by the user, the sender, the receiving time, the user behavior, etc. The user behavior is the user's reaction to the received SMS, such as opening, replying, deleting, and marking. The SMS sending records include the content of the SMS sent by the user, the recipient, the sending time, the frequency of SMS exchanges with the recipient, etc.

[0091] In an embodiment of the present application, the first SMS data is a training data set, and the training data set is used to train the classification model.

[0092] In an embodiment of the present application, before the first SMS data is input into the classification model, the first SMS data is preprocessed to remove special characters, punctuation marks, numbers, etc. in the SMS content of the first SMS data, and to remove meaningless words in the SMS content, such as meaningless words including ", ", etc. The SMS content is divided into multiple words, and core words are further extracted. The words expressing the same or similar meanings are restored to a basic form to convert the first SMS data from unstructured data into structured data, so that the model can more easily understand the first SMS data.

[0093] Specifically, the first SMS data is input into a classification model, the first SMS data is converted into a feature vector, the first SMS data is classified through the classification model to distinguish between spam SMS and non-spam SMS, and an interception strategy is generated based on the spam SMS and non-spam SMS, wherein the interception strategy is used to intercept spam SMS, and the interception strategy includes intercepting spam SMS, moving spam SMS to a blacklist, sending a warning notification, etc.

[0094] Please refer to Figure 3 , Figure 3 yes Figure 2 A detailed flow chart of step S202 in FIG.

[0095] like Figure 3 As shown, step S202 includes:

[0096] Step S2021: extracting features from the first SMS data to obtain a first key feature;

[0097] Specifically, feature extraction is performed on the first SMS data to obtain first key features, wherein the first key features include features such as SMS length, keywords, whether a link is included, and sender reputation.

[0098] Step S2022: Analyze the first key feature through the classification model to obtain an analysis result;

[0099] Specifically, the first key feature is analyzed through a classification algorithm to count the frequency of keywords being marked by users and the number of times the sender is marked by users, to obtain an analysis result, wherein the analysis result includes the frequency of keywords being marked by users and the number of times the sender is marked by users.

[0100] Among them, classification algorithms include logistic regression, support vector machine (SVM), random forest, gradient boosting tree, and deep learning model.

[0101] Please refer to Figure 4 , Figure 4 yes Figure 3 A detailed flow chart of step S2022 in FIG.

[0102] like Figure 4 As shown, step S2022 includes:

[0103] Step S2221: Count the frequency of the keyword being marked by the user to obtain a first statistical result, and use the first statistical result as the analysis result, wherein the first statistical result includes the frequency;

[0104] Specifically, the frequency of keywords being marked by users is counted. For example, within a time period, 10 spam messages are marked, and 8 of them contain keywords (such as winning, free, etc.), which means that winning, free and spam messages are highly correlated. The number of times the keyword appears in the spam messages can be used to obtain the frequency of the keyword being marked by the user, and the first statistical result is obtained. The first statistical result includes the frequency of the keyword being marked by the user, and the first statistical result is also the analysis result.

[0105] In an embodiment of the present application, after counting the frequency of keywords marked by users, it is also necessary to calculate the frequency of the keywords appearing in the corpus to obtain the importance of the keywords in the text messages, wherein the corpus includes known spam text messages and non-spam text messages. By calculating the frequency of the keywords appearing in the corpus, the recognition rate of the classification model can be improved to identify which keywords are more relevant to spam text messages and which keywords are more relevant to non-spam text messages.

[0106] Specifically, a weighted technique is used to calculate the frequency of occurrence of a keyword in a corpus. Commonly used weighted techniques include TF-IDF (Term Frequency-Inverse Document Frequency). TF-IDF refers to term frequency-inverse document frequency. TF-IDF evaluates the importance of a keyword to a specific document (such as spam text messages) by calculating the frequency of the keyword appearing in a document (such as text messages) and the rarity of the keyword in the entire document collection (such as a corpus).

[0107] Step S2222: Count the number of times the sender is marked by the user to obtain a second statistical result, and use the second statistical result as the analysis result, wherein the second statistical result includes the number of times;

[0108] Specifically, the number of times the sender appears in the blacklist within a specific period of time is counted to obtain the number of times the sender is marked by the user, and a second statistical result is obtained. The second statistical result is used as the analysis result. The second statistical result includes the number of times the sender is marked by the user. For example, within 30 days, a number (i.e., the sender) appears in the blacklist 100 times (i.e., marked by 100 users), then the number of times the sender is marked by the user is 100.

[0109] In an embodiment of the present application, the probability of text messages received within a specific time being marked as spam can also be counted as an analysis result, for example, the probability of text messages received between 22:00 in the evening and 7:00 in the morning of the next day being marked as spam can be counted.

[0110] Step S2023: Generate an interception strategy based on the analysis result;

[0111] Specifically, based on the analysis results, an interception strategy is generated, that is, based on the frequency of keywords marked by users, if keywords greater than a frequency threshold are identified as related to spam text messages, text messages containing keywords greater than the frequency threshold are determined to be spam text messages and are intercepted; or, based on the number of times a sender is marked by users, when the number of times a sender is marked by users is greater than a threshold, the sender is determined to be the sender of spam text messages, and text messages related to the sender are marked as spam text messages and are intercepted; or, based on the probability of text messages received within a specific time being marked as spam text messages, when the probability of text messages received within a specific time being marked as spam text messages is greater than a threshold, text messages received from unfamiliar senders within a specific time are marked as spam text messages and are intercepted.

[0112] Please refer to Figure 5 , Figure 5 yes Figure 3 A detailed flow chart of step S2023 in FIG.

[0113] like Figure 5 As shown, step S2023 includes:

[0114] Step S2231: adding keywords with a frequency greater than a frequency threshold to a blacklist;

[0115] Specifically, keywords whose frequency of being marked by users is greater than a frequency threshold are added to the blacklist. For example, if the frequency threshold is set to 0.9, keywords whose frequency of being marked by users is greater than 0.9 are added to the blacklist.

[0116] Step S2232: add the sender whose number of times is greater than the number threshold to the blacklist;

[0117] Specifically, a sender whose number of times marked by the user within a specific period is greater than a threshold number is added to the blacklist.

[0118] In the embodiment of the present application, if the number of times a sender is marked within a certain period of time is greater than a threshold number, it also indicates that the sender has a low reputation.

[0119] Step S2233: Generate an interception strategy based on the blacklist, wherein the interception strategy includes intercepting specific senders and filtering specific keywords;

[0120] Specifically, based on the blacklist, an interception strategy is generated, wherein the interception strategy includes intercepting specific senders and filtering specific keywords, that is, determining that senders appearing in the blacklist need to be intercepted, and determining that text messages related to the keywords appearing in the blacklist need to be intercepted.

[0121] In an embodiment of the present application, after the classification model is trained by the training data set, an interception strategy is initially generated, and the classification model needs to be further evaluated to determine whether the performance of the model meets the expected requirements. Specifically: a test data set is obtained, wherein the test data set is historical SMS data, and the test data set includes spam SMS and non-spam SMS. The test data set is input into the trained classification model, and the test data set is predicted by the classification model to obtain a prediction result. According to the prediction result and the true label of the test set, the evaluation index of the classification model is calculated, and the evaluation index includes accuracy, precision, recall and other indicators. The probability score of the sample belonging to a certain category is further calculated. The larger the probability value, the higher the possibility that the sample is a spam SMS. For example, when using the logistic regression algorithm, the probability value output by the classification model is between 0 and 1. The probability value indicates the possibility that the SMS is a spam SMS. When the probability value is 0.8, it means that the classification model believes that the current SMS has an 80% probability of being a spam SMS. By setting a threshold, it is decided when to classify the SMS as a spam SMS. For example, the threshold is 0.5, and SMS with a probability value lower than 0.5 is regarded as a non-spam SMS, and SMS with a probability value equal to or greater than 0.5 is regarded as a spam SMS.

[0122] Step S203: obtaining second SMS data, wherein the second SMS data is real-time SMS data;

[0123] Specifically, second SMS data is obtained from the electronic device, wherein the second SMS data is real-time SMS data.

[0124] Step S204: determining whether the second SMS data is junk SMS;

[0125] Specifically, the second SMS data is input into the trained classification model, and whether the second SMS data is spam is determined based on the interception strategy. If the second SMS data is not spam, jump to step S205; if the second SMS data is spam, jump to step S206.

[0126] Please refer to Figure 6 , Figure 6 yes Figure 2 A detailed flow chart of step S204 in FIG.

[0127] like Figure 6 As shown, step S204 includes:

[0128] Step S241: Detect whether the sender corresponding to the second SMS data exists in the blacklist;

[0129] Specifically, traverse the blacklist to detect whether the sender corresponding to the second SMS data exists in the blacklist. If the sender corresponding to the second SMS data does not exist in the blacklist, jump to step S242; if the sender corresponding to the second SMS data exists in the blacklist, jump to step S243.

[0130] Step S242: Determine whether the keyword exists in the blacklist;

[0131] Specifically, when the sender corresponding to the second SMS data does not exist in the blacklist, and the sender corresponding to the currently received SMS is an unfamiliar phone number, it is necessary to further determine whether the keywords in the SMS content in the second SMS data exist in the blacklist. If so, jump to step S243; if not, jump to step S244.

[0132] Step S243: Determine that the second SMS data is junk SMS;

[0133] Specifically, when the sender corresponding to the second SMS data is in the blacklist, or the keywords in the SMS content of the second SMS data are in the blacklist, the second SMS data is determined to be spam, and the second SMS data is intercepted based on the interception strategy.

[0134] Step S244: Determine that the second SMS data is not a spam SMS;

[0135] Specifically, when the sender corresponding to the second SMS data does not exist in the blacklist, and the keyword in the SMS content of the second SMS data does not exist in the blacklist, it is determined that the second SMS data is not a spam SMS.

[0136] Step S205: Push the second SMS data to the user;

[0137] Specifically, when it is determined that the second SMS data is not a junk SMS, the second SMS data is pushed to the user, and the user is notified to check.

[0138] Step S206: adding the second SMS data to the blacklist;

[0139] Specifically, when it is determined that the second SMS data is a spam SMS, the second SMS data is added to a blacklist.

[0140] Please refer to Figure 7 , Figure 7 It is a flowchart of an update interception strategy provided by an embodiment of the present application;

[0141] like Figure 7 As shown, update the interception strategy, including:

[0142] Step S701: obtaining user feedback data at intervals of a preset time period;

[0143] In an embodiment of the present application, when SMS communications are being conducted, the way a user handles certain SMS messages may change. For example, a number previously added to a blacklist is removed from the blacklist by the user. In order to adapt to these changes and meet user needs, it is necessary to regularly obtain user feedback data to readjust the interception strategy.

[0144] Specifically, user feedback data is obtained at intervals of a preset time period, for example, at intervals of one month or three months, from the electronic device, wherein the user feedback data includes user behavior.

[0145] In an embodiment of the present application, obtaining user feedback data from an electronic device requires the user's consent and compliance with relevant laws and regulations, such as the General Data Protection Regulation (GDPR), to protect the user's privacy, and uploading the data to the server via the Hypertext Transfer Protocol Secure (HTTPS) to ensure the security and integrity of the data transmission process.

[0146] In an embodiment of the present application, user feedback data is processed to a minimum, for example, by using short text or selection boxes to collect data, without the need to collect specific SMS content.

[0147] Step S702: retraining the classification model based on the feedback data to update the interception strategy;

[0148] Specifically, the trained classification model is retrained based on user feedback data to update the interception strategy.

[0149] In an embodiment of the present application, by retraining the trained classification model, the classification model can re-update the model parameters according to the latest user behavior data to optimize the interception strategy, which can avoid the problem that static interception rules cannot adapt to user needs and can improve the accuracy of spam SMS interception.

[0150] Please refer to Figure 8 , Figure 8 yes Figure 7 A detailed flow chart of step S702 in FIG.

[0151] like Figure 8 As shown, step S702 includes:

[0152] Step S721: extracting features from the feedback data to obtain a second key feature;

[0153] Specifically, feature extraction is performed on the feedback data to obtain second key features, wherein the second key features include features such as user behavior, sender, and keywords.

[0154] Step S722: retraining the classification model based on the second key feature to obtain a trained classification model;

[0155] Specifically, the second key feature is input into the classification model to retrain the classification model to obtain a trained classification model.

[0156] In an embodiment of the present application, the classification model is retrained so that the classification model can learn user behavior to more accurately distinguish spam text messages from non-spam text messages, thereby avoiding the problem of false interception or missed interception, ensuring that users will not miss important information and will not be harassed by spam text messages.

[0157] Step S723: Based on the trained classification model, the keywords and senders in the blacklist are updated to obtain an updated blacklist;

[0158] Specifically, based on the trained classification model, senders trusted by the user or keywords of interest are removed from the blacklist, etc. and added to the whitelist, and senders not trusted by the user or keywords of no interest to the user are removed from the whitelist, etc. and added to the blacklist, and the blacklist and whitelist are updated.

[0159] In the embodiment of the present application, user behavior is analyzed to relearn which types of text messages are more likely to be marked as spam text messages, so as to learn the user's blocking preferences.

[0160] Step S724: Generate a new interception strategy based on the updated blacklist;

[0161] Specifically, based on the updated blacklist, a new interception policy is regenerated, for example, the senders newly added to the blacklist are intercepted, and the interception policy corresponding to the senders removed from the blacklist is deleted.

[0162] In an embodiment of the present application, user feedback data is periodically obtained to automatically update the interception rules to improve the accuracy of spam text message interception. At the same time, it is possible to learn different users' preferences for spam text message interception and provide corresponding interception strategies for different users to improve user satisfaction.

[0163] See also Fig. 9 , Fig. 9 It is a structural schematic diagram of a text message interception and processing system provided in an embodiment of the present application;

[0164] like Fig. 9 As shown, the SMS interception processing system 900 includes a server 10 and an electronic device 20. The server 10 and the electronic device 20 are connected to each other through WebSocket, which is a two-way communication protocol that allows a persistent connection to be established between the electronic device 20 and the server 10, and can support applications that require real-time data transmission (such as instant messaging, notification push, etc.).

[0165] The server 10 is connected to the electronic device 20 . The server 10 is used to collect training data to train the classification model to generate an interception strategy, and store the interception strategy in a database in the server 10 .

[0166] The electronic device 20 is connected to the server 10 , and is used to obtain the interception strategy and run the interception strategy in the electronic device. When a new SMS is received, the interception result of the new SMS is displayed through the display interface of the electronic device 20 .

[0167] In the embodiment of the present application, the electronic device 20 obtains the interception strategy and stores the interception strategy in a local database or cache so as to intercept junk text messages in real time when receiving text messages.

[0168] In an embodiment of the present application, when the server 10 updates the interception policy, the server 10 sends the update notification of the interception policy to the electronic device via a push notification, for example, through Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNs).

[0169] In the embodiment of the present application, the display interface of the electronic device 20 includes a smart interception setting button, a trust list button, and a historical interception record button. By clicking the smart interception setting button, you can set whether to turn on or off the smart interception function, that is, determine whether to run or turn off the interception strategy. By clicking the trust list button, you can view the trust list, which is also a whitelist for storing trusted numbers. By clicking the historical interception record button, you can view the junk text messages that have been intercepted in the past on the display interface.

[0170] See also Fig.10 , Fig.10 It is a structural schematic diagram of a text message interception processing device provided in an embodiment of the present application;

[0171] like Fig.10 As shown, the short message interception processing device 1000 includes:

[0172] A first acquiring unit 1001 is configured to acquire first SMS data, wherein the first SMS data includes junk SMS and non-junk SMS;

[0173] A generating unit 1002, configured to input the first SMS data into a classification model to generate an interception strategy, wherein the interception strategy is used to intercept junk SMS;

[0174] The second acquiring unit 1003 is used to acquire second SMS data, wherein the second SMS data is real-time SMS data;

[0175] The judging unit 1004 is used to judge whether the second SMS data is a spam SMS based on the interception strategy. If the second SMS data is a spam SMS, the second SMS data is added to the blacklist; if the second SMS data is not a spam SMS, the second SMS data is pushed to the user.

[0176] In an embodiment of the present application, the SMS interception processing device can be a software module, which includes a number of instructions stored in a memory. The processor can access the memory and call the instructions for execution to complete the SMS interception processing methods of the above-mentioned embodiments.

[0177] In the embodiments of the present application, the SMS interception processing device can also be constructed by hardware devices. For example, the SMS interception processing device can be constructed by one or more chips, and each chip can work in coordination with each other to complete the SMS interception processing method described in the above embodiments. For another example, the SMS interception processing device can also be constructed by various logic devices, such as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components.

[0178] The SMS interception processing device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0179] The SMS interception processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0180] The SMS interception processing device provided in the embodiment of the present application can achieve Figure 2 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0181] It should be noted that the above device can execute the SMS interception processing method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in the device embodiment, please refer to the SMS interception processing method provided in the embodiment of the present application.

[0182] In the embodiment of the present application, the various units of the SMS interception processing device cooperate with each other to solve the problem that static rules cannot adapt to changes in spam SMS sending strategies, resulting in poor interception effect. This can improve the interception effect of spam SMS and improve user satisfaction with SMS communications.

[0183] See also Fig.11 , Fig.11 It is a structural diagram of a server provided in an embodiment of the present application;

[0184] like Fig.11 As shown, the server 10 includes one or more processors 11 and a memory 12. Fig.11 A processor 11 is taken as an example.

[0185] The processor 11 and the memory 12 may be connected via a bus or other means. Fig.11 The example of connecting through bus is taken in the following.

[0186] A processor, used to execute the SMS interception processing method in any embodiment of the present application, including:

[0187] Acquire first SMS data, wherein the first SMS data includes junk SMS and non-junk SMS;

[0188] Inputting the first SMS data into a classification model to generate an interception strategy, wherein the interception strategy is used to intercept spam SMS;

[0189] Acquire second SMS data, wherein the second SMS data is real-time SMS data;

[0190] Based on the interception strategy, determining whether the second SMS data is a spam SMS;

[0191] If the second SMS data is junk SMS, adding the second SMS data to a blacklist;

[0192] If the second SMS data is not a spam SMS, the second SMS data is pushed to the user.

[0193] The memory 12 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the SMS interception processing method in the embodiment of the present invention. The processor 11 executes various functional applications and data processing of the electronic device by running the non-volatile software programs, instructions and modules stored in the memory 12, that is, the SMS interception processing method of the above method embodiment is implemented.

[0194] The memory 12 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 12 may optionally include a memory remotely arranged relative to the processor 11. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0195] One or more modules are stored in the memory 12, and when executed by one or more processors 11, the SMS interception processing method in any of the above method embodiments is executed, for example, the above described SMS interception processing method is executed. Figure 2 The steps shown.

[0196] An embodiment of the present application also provides a computer program product, which includes one or more program codes, which are stored in a non-volatile computer-readable storage medium. A processor of an electronic device reads the program code from the non-volatile computer-readable storage medium, and the processor executes the program code to complete the steps of the SMS interception processing method provided in the above embodiment.

[0197] Through the description of the above implementation methods, ordinary technicians in this field can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or by hardware related to program code, and the program can be stored in a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium mentioned above can be a read-only memory, a disk or an optical disk, etc.

[0198] Through the description of the above implementation methods, a person of ordinary skill in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, can also be implemented by hardware. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the non-volatile computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0199] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present application as mentioned above, which are not provided in detail for the sake of simplicity. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intercepting and processing short messages, characterized in that: The method comprises: Acquire first SMS data, wherein the first SMS data includes junk SMS and non-junk SMS; Inputting the first SMS data into a classification model to generate an interception strategy, wherein the interception strategy is used to intercept spam SMS; Acquire second SMS data, wherein the second SMS data is real-time SMS data; Based on the interception strategy, determining whether the second SMS data is a spam SMS; If the second SMS data is a spam SMS, adding the second SMS data to a blacklist; If the second SMS data is not a spam SMS, the second SMS data is pushed to the user.

2. The method according to claim 1, characterized in that The step of inputting the first SMS data into a classification model to generate an interception strategy includes: Extracting features from the first SMS data to obtain a first key feature; Analyze the first key feature by using the classification model to obtain an analysis result; Based on the analysis result, an interception strategy is generated.

3. The method according to claim 2, characterized in that The first key feature includes a keyword and a sender, and the first key feature is analyzed by the classification model to obtain an analysis result, including: Analyze the keywords and senders respectively to obtain the analysis results, which specifically include: Counting the frequency of the keyword being marked by the user to obtain a first statistical result, and using the first statistical result as the analysis result, wherein the first statistical result includes the frequency; The number of times the sender is marked by the user is counted to obtain a second statistical result, and the second statistical result is used as the analysis result, wherein the second statistical result includes the number of times.

4. The method according to claim 3, characterized in that The generating an interception strategy based on the analysis result includes: Adding the keywords whose frequency is greater than the frequency threshold to a blacklist; Adding the sender whose number of times is greater than the number threshold to the blacklist; The interception strategy is generated based on the blacklist, wherein the interception strategy includes intercepting specific senders and filtering specific keywords.

5. The method according to claim 4, characterized in that The determining, based on the interception strategy, whether the second SMS data is a spam SMS includes: Extracting a keyword from the second SMS data, and determining whether the keyword exists in the blacklist, if the keyword exists in the blacklist, determining that the second SMS data is a spam message, and if the keyword does not exist in the blacklist, determining that the second SMS data is a non-spam message; and / or, Detect whether the sender corresponding to the second SMS data exists in the blacklist. If the sender exists in the blacklist, determine that the second SMS data is a spam message. If the sender does not exist in the blacklist, determine that the second SMS data is a non-spam message.

6. The method according to claim 1, characterized in that The method further comprises: Retraining the classification model to update the interception strategy specifically includes: Obtain user feedback data at preset time intervals; The classification model is retrained based on the feedback data to update the interception strategy.

7. The method according to claim 6, characterized in that The retraining of the classification model based on the feedback data comprises: Extracting features from the feedback data to obtain a second key feature, wherein the second key feature includes a keyword and a sender; Based on the second key feature, the classification model is retrained to obtain a trained classification model.

8. The method according to claim 7, characterized in that Updating the interception strategy includes: Based on the trained classification model, updating the keywords and senders in the blacklist to obtain an updated blacklist; Generate a new interception strategy based on the updated blacklist.

9. A server, characterized in that: include: A processor and a memory, wherein the processor is used to execute an executable program code in the memory, and when the executable program code is executed, the processor executes instructions of the SMS interception processing method as described in any one of claims 1 to 8.

10. A short message interception and processing system, characterized in that: The system comprises: The server according to claim 9, configured to generate an interception strategy, and to periodically update the interception strategy; The electronic device is used to obtain the interception strategy, identify junk text messages based on the interception strategy, and intercept the junk text messages.

Images