Quick sensitive content filtering method and system based on dynamic multi-rule matching

Abstract

The invention discloses a quick sensitive content filtering method and system based on dynamic multi-rule matching. The method comprises the following steps: acquiring a current application scene of to-be-filtered content; obtaining filtering rule application condition information, wherein the filtering rule application condition information comprises a preset application scene and a preset filtering rule corresponding to the preset application scene; based on the current application scene and the filtering condition application rule, determining a preset filtering rule corresponding to the current application scene as a current application rule; and processing the to-be-filtered content based on the current application rule to obtain a content processing result. Different filtering rules can be selected according to different scenes, sensitive content can be filtered as much as possible, the probability that normal content is filtered is reduced, normal communication of users can be guaranteed, and user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and system for rapid filtering of sensitive content based on dynamic multi-rule matching. Background Art

[0002] With the development and progress of Internet technology, various online platforms have gradually emerged, and more and more people have joined these online platforms. Through these platforms, users can share their daily lives and popularize scientific knowledge, etc. However, there will also be some low-quality people who will post some bad information, so the relevant platforms will use all kinds of filtering methods to filter out these bad and sensitive content.

[0003] When filtering these sensitive contents, relevant platforms usually filter them by screening keywords or key words. Although this method can block some sensitive contents, it will also block some normal contents containing these keywords, affecting users' normal communication and usage experience. Summary of the invention

[0004] The embodiments of the present application provide a method and system for quickly filtering sensitive content based on dynamic multi-rule matching, which can filter sensitive content as much as possible while reducing the probability of normal content being filtered, thereby ensuring normal communication among users and improving user experience.

[0005] The present application provides a method for rapid filtering of sensitive content based on dynamic multi-rule matching, including: Get the current application scenario of the content to be filtered; Acquire filtering rule application condition information, wherein the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; Based on the current application scenario and the filtering condition application rule, determining the preset filtering rule corresponding to the current application scenario as the current application rule; The to-be-filtered content is processed based on the current application rule to obtain a content processing result.

[0006] Optionally, in some embodiments, the preset filtering rule includes a keyword filtering rule and a semantic filtering rule, and the applying rule based on the current application scenario and the filtering condition determines the preset filtering rule corresponding to the current application scenario as the current application rule, including: When the current application scenario is a structured scenario, the preset filtering rule corresponding to the structured scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0007] Optionally, in some embodiments, when the current application scenario is a structured scenario, before determining that the preset filtering rule corresponding to the structured scenario is the keyword filtering rule and using the keyword filtering rule as the current application rule, the method further includes: Obtaining preset keywords in the keyword filtering rule; Based on the preset keyword, obtaining a substitute keyword of the preset keyword according to a preset search frequency; The keyword filtering rule is updated based on the alternative keyword.

[0008] Optionally, in some embodiments, the determining, based on the current application scenario and the filtering condition application rule, the preset filtering rule corresponding to the current application scenario as the current application rule further includes: When the current application scenario is a content-based scenario, it is determined that the preset filtering rule corresponding to the content-based scenario is the semantic filtering rule, and the semantic filtering rule is used as the current application rule.

[0009] Optionally, in some embodiments, when the current application scenario is a content scenario, before determining that the preset filtering rule corresponding to the content scenario is the semantic filtering rule and using the semantic filtering rule as the current application rule, the method further includes: Obtaining the number of online users in the content scenario; When the number of online users exceeds the preset number of users, the preset filtering rule corresponding to the content scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0010] Optionally, in some embodiments, after obtaining the number of online users in the content scenario, the method further includes: When the number of online users does not exceed the preset number of users, the preset filtering rule corresponding to the content scenario is determined to be the semantic filtering rule, and the semantic filtering rule is used as the current application rule.

[0011] Optionally, in some embodiments, when the number of online users exceeds a preset number of users, before determining that the preset filtering rule corresponding to the content scenario is the semantic filtering rule and using the semantic filtering rule as the current application rule, the method further includes: Obtaining the content update frequency corresponding to the number of online users; When the content update frequency does not exceed the preset update frequency, determining that the preset filtering rule corresponding to the content scenario is the semantic filtering rule, and using the semantic filtering rule as the current application rule; When the content update frequency exceeds the preset update frequency, the preset filtering rule corresponding to the content scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0012] Optionally, in some embodiments, after obtaining the current application rule, the method further includes: Determining whether the content-based scene is a real-time live broadcast scene; If the content-based scene is a real-time live broadcast scene, obtaining a live broadcast tag of the content-based scene; The semantic filtering rule corresponding to the live broadcast tag is shielded based on the live broadcast tag.

[0013] Optionally, in some embodiments, after determining whether the contentized scene is a real-time live scene, the method further includes: If the content-based scene is a non-real-time live scene, the shielded semantic filtering rule is restored.

[0014] Accordingly, the embodiment of the present application provides a system for rapid filtering of sensitive content based on dynamic multi-rule matching, including: A scene acquisition module is used to obtain the current application scene of the content to be filtered; A condition information acquisition module, used to acquire filtering rule application condition information, wherein the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; A rule determination module, configured to determine, based on the current application scenario and the filtering condition application rule, the preset filtering rule corresponding to the current application scenario as the current application rule; The content processing module is used to process the content to be filtered based on the current application rule to obtain a content processing result.

[0015] The embodiment of the present application provides a method and system for rapid filtering of sensitive content based on dynamic multi-rule matching, which can obtain the current application scenario of the content to be filtered; obtain the application condition information of the filtering rule, which includes the preset application scenario and the preset filtering rule corresponding to the preset application scenario; based on the current application scenario and the filtering condition application rule, determine the preset filtering rule corresponding to the current application scenario as the current application rule; process the content to be filtered based on the current application rule to obtain the content processing result. The present application can select different filtering rules according to different scenarios, can filter sensitive content as much as possible, and reduce the probability of normal content being filtered, can ensure the normal communication of users and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a scenario diagram of a method for rapid filtering of sensitive content based on dynamic multi-rule matching provided in an embodiment of the present application; Figure 2 It is a flow chart of a method for rapid filtering of sensitive content based on dynamic multi-rule matching provided in an embodiment of the present application; Figure 3 is a structural schematic diagram of a model configuration device provided in an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0019] An embodiment of the present application provides a method and system for rapid filtering of sensitive content based on dynamic multi-rule matching. The system for rapid filtering of sensitive content based on dynamic multi-rule matching can be specifically integrated in an electronic device, which can be a terminal, a server or other device.

[0020] It is understandable that the method for rapid filtering of sensitive content based on dynamic multi-rule matching of this embodiment can be executed on a terminal, on a server, or jointly by a terminal and a server. The above examples should not be construed as limiting the present application.

[0021] like Figure 1 As shown, a terminal and a server jointly perform a method for rapid filtering of sensitive content based on dynamic multi-rule matching as an example. The model training system provided in the embodiment of the present application includes a terminal 10 and a server 11, etc. The terminal 10 and the server 11 are connected via a network, such as a wired or wireless network connection, etc., wherein the model configuration device can be integrated in the terminal.

[0022] The terminal 10 may include a mobile phone, an intelligent voice interaction device, an intelligent home appliance, a vehicle terminal, an aircraft, a tablet computer, a notebook computer, or a personal computer (PC), etc. The terminal 10 may also be provided with a client, which may be an application client or a browser client, etc.

[0023] The server 11 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or 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, CDN, and big data and artificial intelligence platforms. The method or device for rapid filtering of sensitive content based on dynamic multi-rule matching disclosed in this application, wherein multiple servers can be composed into a blockchain, and the server is a node on the blockchain.

[0024] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0025] This embodiment will be described from the perspective of a model configuration device, which may be integrated into an electronic device, such as a server or a terminal.

[0026] This embodiment can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and assisted driving.

[0027] like Figure 2 As shown, the specific process of the method for rapid filtering of sensitive content based on dynamic multi-rule matching can be as follows: 110. Obtain the current application scenario of the content to be filtered.

[0028] To-be-filtered content refers to content uploaded by users to the platform and ready to be published, or content that has been published but has not been allowed to be made public by the platform. If the platform's filtering rules allow publishing, the content published by the user will be published publicly on the platform. If publishing is not allowed, other users on the platform will not be able to view the content published by the user.

[0029] The current application scenario can be determined by the platform system based on the current section of the platform. The current application scenario includes structured scenarios and content scenarios. Among them, the structured scenario refers to the content with a fixed structural pattern. Compared with the content scenario, the frequency and real-time of its interaction are lower, and the content is updated slowly. For example, an online forum is a structured scenario. Its structure has a fixed pattern and exists in the form of posts and replies. The discussion of its topics often focuses on specific topics.

[0030] The content of content-based scenarios does not have a fixed structure pattern, and its content is diverse, including text, pictures, videos, audio, etc. At the same time, the content often contains more implicit meanings and complex expressions, such as humor, irony, metaphors, etc. For example, live broadcast and short video sections have frequent user interactions, fast content updates, and strong real-time performance, which may involve instant messaging, comments, sharing, and other forms.

[0031] 120. Obtain filtering rule application condition information, where the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario.

[0032] The system pre-stores filtering rule application condition information, and when a user publishes information, the system can directly call these rules to process the content to be filtered. The filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario.

[0033] Specifically, the preset filtering rules include keyword filtering rules and semantic filtering rules, wherein the keyword filtering rules correspond to structured scenarios, and the semantic filtering rules correspond to content scenarios. It should be understood that the keyword filtering model includes not only keywords, but also key words.

[0034] 130. Based on the current application scenario and the filtering condition application rule, determine a preset filtering rule corresponding to the current application scenario as the current application rule.

[0035] That is, the current application scenario is matched with the structured scenario and the content scenario in the filter condition application rules. For example, if the current application scenario is an online forum or BBS, it is determined to correspond to the structured scenario. If the current application scenario is a live broadcast or short video, it is determined to correspond to the content scenario.

[0036] Then, according to the correspondence between the preset filtering rules and the application scenarios, if it is a structured scenario, the keyword filtering rule is selected, and if it is a content scenario, the semantic filtering rule is selected. It should be understood that both the semantic filtering rule and the keyword filtering rule can be obtained through the trained filtering model. The application of the current semantic filtering model and the keyword filtering model is quite mature, and this embodiment will not be repeated here.

[0037] Further, in some embodiments, based on the current application scenario and the filtering condition application rule, a preset filtering rule corresponding to the current application scenario is determined as the current application rule, including: When the current application scenario is a structured scenario, it is determined that the preset filtering rule corresponding to the structured scenario is a keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0038] That is, when it is determined that the current application scenario is a structured scenario, it can be determined that the preset filtering rule is a keyword filtering rule at this time. At this time, the platform can use the keyword filtering rule as the current application rule and filter the content to be filtered according to the current application rule.

[0039] Further, in some embodiments, due to the continuous progress of culture, the languages used by users are becoming less and less conventional, and more and more other words containing sensitive content are emerging. Therefore, in order to filter these sensitive contents more accurately, before determining that the preset filtering rule corresponding to the structured scenario is a keyword filtering rule and using the keyword filtering rule as the current application rule when the current application scenario is a structured scenario, it further includes: Obtain the preset keywords in the keyword filtering rule; Obtain the substitute keywords of the preset keywords according to the preset search frequency based on the preset keywords; Update the keyword filtering rule based on the substitute keywords.

[0040] Specifically, the keyword filtering rule filters according to keywords. Among them, there is at least one keyword in the keyword filtering rule in the initial state, and the keywords existing in the keyword filtering rule are the preset keywords.

[0041] Then, according to the preset keywords, obtain the substitute keywords of the preset keywords according to the preset search frequency. The preset search frequency can be set according to the actual situation. For example, it can be set to search once a month, once a year, or once an hour, and can be set according to the actual situation. Of course, in some embodiments, the search frequency can also be to search when new words appear on the Internet. For example, the once-popular Internet keywords such as "blue thin mushroom" and "YYDS". When new words emerge on the Internet are detected by means such as web crawlers, the search can be carried out.

[0042] The substitute keywords of the preset keywords refer to those keywords that can represent the meaning of the preset keywords. For example, the meaning represented by "blue thin mushroom" in the example is "unhappy and want to cry". Therefore, if the preset keyword is "unhappy and want to cry", the substitute keyword is "blue thin mushroom".

[0043] Finally, after obtaining the substitute keywords, add the substitute keywords to the corresponding keyword filtering rules, and the substitute keywords added to the keyword filtering rules can be used as the initial keywords for the next update and combined with the initial keywords of the previous time for subsequent updates. For example, the initial keyword is "feeling uncomfortable and wanting to cry", then when "blue and thin mushrooms" is added to the keyword filtering rules, the current "blue and thin mushrooms" and the previous "feeling uncomfortable and wanting to cry" will be used as new initial keywords for subsequent updates. Of course, if there is no corresponding substitute keyword after the search, there is no need to update the keyword filtering rules. Therefore, through the above method, the newly appeared vocabulary content corresponding to these sensitive contents can be filtered more accurately, and the accuracy of filtering the content to be filtered can be guaranteed as much as possible.

[0044] Furthermore, in some embodiments, different filtering rules are applied to different application scenarios, which can prevent a one-size-fits-all situation as much as possible, that is, it can prevent the situation where all content is filtered regardless of whether it is correct or not as long as the corresponding keywords exist. Therefore, based on the current application scenario and the filtering condition application rules, the preset filtering rule corresponding to the current application scenario is determined as the current application rule, which also includes: When the current application scenario is a content-based scenario, it is determined that the preset filtering rule corresponding to the content-based scenario is a semantic filtering rule, and the semantic filtering rule is used as the current application rule.

[0045] The method of obtaining semantic filtering rules is the same as the method of obtaining keyword filtering rules, and the only difference is the current application scenario. When the current application rule is a semantic filtering rule, it can be judged in combination with the contextual semantics of the content to be filtered to determine whether the content to be filtered is sensitive content. For example, if only keywords are used for filtering, if the preset keywords are "money", "politics", "country", "discrimination" and other words, all content containing the above keywords will be filtered. If semantic filtering rules are used, the relevant filtering rule model will parse whether the content is sensitive or not. For example: if the content to be filtered is "the state issues corresponding policies to increase farmers' monetary income", the semantic filtering rule will consider this sentence to be non-sensitive content and does not need to be filtered.

[0046] Furthermore, in the content-based scenario, different filtering rules will be considered due to the number of people, because when there are too many people, the semantic filtering rule has high computational complexity and requires more computing resources and time. Therefore, in order to solve the above problem, when the current application scenario is a content-based scenario, before determining that the preset filtering rule corresponding to the content-based scenario is a semantic filtering rule and using the semantic filtering rule as the current application rule, it also includes: Get the number of online users in the content scenario; When the number of online users exceeds the preset number of users, it is determined that the preset filtering rule corresponding to the content-based scenario is a keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0047] First, the platform obtains the number of online users in the content scenario where the content to be filtered is located. The more online users there are, the more content to be filtered is generated, because the interactions in the content scenario are frequent and fast.

[0048] Therefore, if the number of online users exceeds the preset number of users, it proves that the semantic filtering rules used for the content to be filtered at this time will cause the system to be overloaded, the filtering speed will be slow, and the system may freeze. Therefore, at this time, the preset filtering rule corresponding to the content scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule. Compared with the semantic filtering rule, the keyword filtering rule does not need to understand the contextual semantics of the content, can occupy less computing resources, and has a faster computing speed, so the filtering speed is faster.

[0049] Correspondingly, if the number of online users does not exceed the preset number of users, it is determined that the preset filtering rule corresponding to the content-based scenario is a semantic filtering rule, and the semantic filtering rule is used as the current application rule.

[0050] At this time, due to the small number of online users, the largest content to be filtered that can be generated will not affect the normal operation of the system. Therefore, in order to improve the accuracy, the semantic filtering rules are continued to be used to filter the content to be filtered.

[0051] Furthermore, in some embodiments, when there are many online users, sometimes too much content to be filtered may not be generated, so the accuracy of determining the filtering rule based only on the number of online users needs to be improved. Therefore, when the number of online users exceeds the preset number of users, before determining that the preset filtering rule corresponding to the content scenario is a semantic filtering rule and using the semantic filtering rule as the current application rule, it also includes: Get the content update frequency corresponding to the number of online users; When the content update frequency does not exceed the preset update frequency, determining that the preset filtering rule corresponding to the content scenario is a semantic filtering rule, and using the semantic filtering rule as the current application rule; When the content update frequency exceeds the preset update frequency, the preset filtering rule corresponding to the content scenario is determined to be a keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0052] First, the content update frequency of the number of online users in the current application scenario is obtained. The content update frequency refers to the number of contents to be filtered generated per unit time in the current application scenario and the number of online users, such as the number of contents to be filtered generated per second, or the number of contents to be filtered generated per minute. This unit time can be set according to actual conditions, and this embodiment does not limit this.

[0053] The content update frequency can be obtained through real-time calculation, for example, by presetting multiple unit times for recording the number of contents to be filtered. Of course, the unit times here can be the same or different. For example, the first interception is the number of contents to be filtered in one second, the second interception is the number of contents to be filtered in one second, and the third interception is the number of contents to be filtered in one minute. Then, the average of these three intercepted numbers is calculated to obtain the content update frequency. Of course, the time unit in the mean calculation process needs to be converted into the same unit, such as seconds. The interval of each interception can be the same or different, and can be set according to the actual situation.

[0054] When the content update frequency does not exceed the preset update frequency, it proves that even if the number of online users exceeds the preset number of users, not too much content to be filtered will be generated. The content to be filtered can be one word, multiple words, one sentence or multiple sentences, etc. The multiple content to be filtered can be at least one of these cases.

[0055] When there is not too much content to be filtered, the resource usage will not be overloaded, and the filtering time of sensitive content is sufficient. At this time, the accuracy of filtering is the main concern, so the preset filtering rule corresponding to the content scenario is determined to be the semantic filtering rule, and the semantic filtering rule is used as the current application rule. On the contrary, if the content update frequency exceeds the preset update frequency, it proves that even if the number of online users exceeds the preset number of users, too much content to be filtered will be generated. At this time, if semantic filtering is continued, the system will be overloaded, occupying too many computing resources, and may cause the filtering speed of sensitive content to slow down. Therefore, the filtering speed is the main concern at this time, so the preset filtering rule corresponding to the content scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

[0056] Through the above-mentioned manner, the filtering rules can be selected in combination with the number of online users and the content update frequency, which can further improve the accuracy and speed of filtering the content to be filtered by the filtering rules.

[0057] Furthermore, in some embodiments, due to different application scenarios, some of the to-be-filtered content that may be sensitive content is allowed in certain specific application scenarios, and it is not necessary to filter these contents at this time. Therefore, after obtaining the current application rules, the following is also included: Determine whether the content scene is a real-time live broadcast scene; If the content-based scene is a real-time live broadcast scene, obtain the live broadcast tag of the content-based scene; Based on the live broadcast tag, the semantic filtering rules corresponding to the live broadcast tag are shielded.

[0058] There are some sensitive contents that are allowed in the live broadcast scene, but not allowed in the non-live broadcast scene. Therefore, it is necessary to determine whether the content scene is a live broadcast scene. If the content scene is a live broadcast scene, obtain the live broadcast tag of the content scene. Among them, the live broadcast tag is pre-set in the platform background. Users can only select the corresponding tag, but cannot change the tag content.

[0059] For example, in a live broadcast scenario, the live broadcast tags may be "games", "making friends", "telling stories", and under the "telling stories" tag, there may be detailed live broadcast tags such as "ghosts", "history", "online games", etc. Therefore, if the live broadcast tag obtained is "telling stories", you can also obtain its corresponding detailed tags, such as "ghosts", "history", "online games". These tags are selected when the user creates a live broadcast. When other users enter the corresponding live broadcast room, all users in the live broadcast room will carry the live broadcast tag of this live broadcast room. If they leave the live broadcast room, they will lose the live broadcast tag.

[0060] At this time, the semantic filtering rules corresponding to the live broadcast tags are blocked. For example, "ghosts and gods" are not allowed under the current semantics, that is, the relevant semantics of ghosts and gods exist in the filtering rules. If the live broadcast tags of the current real-time live broadcast scene are "storytelling" and "ghosts and gods", the relevant semantics of ghosts and gods in the filtering rules will be blocked. In other words, if there is "ghosts and gods" related content in the content to be filtered at this time, it is allowed. At this time, it can be guaranteed that the content related to the live broadcast tag posted by users in the real-time live broadcast scene can be discovered by other users, which is convenient for communication.

[0061] Of course, if after determining whether the content scene is a real-time live scene, if the content scene is a non-real-time live scene, the shielded semantic filtering rules are restored. That is, if the real-time live scene ends and becomes a non-real-time live scene, it is not allowed to continue to publish the content corresponding to the live tag at this time, so the shielded semantic filtering rules are restored at this time, that is, the sensitive content corresponding to the live tag published by the user at this time cannot be discovered by other users. In this way, it can ensure that users can publish corresponding content under specific circumstances, and prevent users from arbitrarily publishing content under specific circumstances, and can ensure the security of content publishing.

[0062] 140. Process the content to be filtered based on the current application rule to obtain a content processing result.

[0063] That is, the content to be filtered is filtered according to the determined filtering rules, for example, the content to be filtered can be filtered by keyword filtering rules, or by semantic filtering rules. If there is content in the content to be filtered that conflicts with the filtering rules, the content to be filtered will be filtered and cannot be published. That is, the content processing results include that the content to be filtered is qualified and can be published, and that the content to be filtered is not qualified and cannot be published, and the user can be notified through the platform to remind the user to re-edit the content to be filtered according to the content processing results, or directly delete it.

[0064] As can be seen from the above, this embodiment can obtain the current application scenario of the content to be filtered; obtain the filtering rule application condition information, the filtering rule application condition information includes the preset application scenario and the preset filtering rule corresponding to the preset application scenario; based on the current application scenario and the filtering condition application rule, determine the preset filtering rule corresponding to the current application scenario as the current application rule; process the content to be filtered based on the current application rule to obtain the content processing result. This application can select different filtering rules according to different scenarios, can filter sensitive content as much as possible, and reduce the probability of normal content being filtered, can ensure the normal communication of users and improve user experience.

[0065] According to the method described in the previous embodiment, the following will be further described in detail by taking the example of the model configuration device being specifically integrated in the terminal.

[0066] In order to better implement the above method, the present application embodiment also provides a model configuration device, such as Figure 3 As shown, the model configuration device may include a scene acquisition module 310, a condition information acquisition module 320, a rule determination module 330, and a content processing module 340, as follows: A scene acquisition module 310 is used to acquire the current application scene of the content to be filtered; The condition information acquisition module 320 is used to acquire the filtering rule application condition information, where the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; A rule determination module 330 is used to determine a preset filtering rule corresponding to the current application scenario as the current application rule based on the current application scenario and the filtering condition application rule; The content processing module 340 is used to process the content to be filtered based on the current application rules to obtain a content processing result.

[0067] As can be seen from the above, in this embodiment, the scene acquisition module can acquire the current application scene of the content to be filtered; the condition information acquisition module acquires the filtering rule application condition information, and the filtering rule application condition information includes the preset application scene and the preset filtering rule corresponding to the preset application scene; the rule determination module determines the preset filtering rule corresponding to the current application scene as the current application rule based on the current application scene and the filtering condition application rule; the content processing module processes the content to be filtered based on the current application rule to obtain the content processing result. The present application can select different filtering rules according to different scenes, and can filter sensitive content as much as possible while reducing the probability of normal content being filtered, which can ensure the normal communication of users and improve the user experience.

[0068] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0069] The present application also provides an electronic device, such as Figure 4 As shown, it shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, and the electronic device may be a terminal or a server, etc. Specifically: The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; preferably, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0070] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 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 volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0071] The electronic device also includes a power supply 103 for supplying power to various components. Preferably, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply 103 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0072] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0073] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 101 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 102 according to the following instructions, and the processor 101 will run the application programs stored in the memory 102, thereby realizing various functions, as follows: Obtain the current application scenario of the content to be filtered; obtain the filtering rule application condition information, the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; based on the current application scenario and the filtering condition application rule, determine the preset filtering rule corresponding to the current application scenario as the current application rule; process the content to be filtered based on the current application rule to obtain a content processing result.

[0074] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0075] As can be seen from the above, this embodiment can obtain the current application scenario of the content to be filtered; obtain the filtering rule application condition information, the filtering rule application condition information includes the preset application scenario and the preset filtering rule corresponding to the preset application scenario; based on the current application scenario and the filtering condition application rule, determine the preset filtering rule corresponding to the current application scenario as the current application rule; process the content to be filtered based on the current application rule to obtain the content processing result. This application can select different filtering rules according to different scenarios, can filter sensitive content as much as possible, and reduce the probability of normal content being filtered, can ensure the normal communication of users and improve user experience.

[0076] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0077] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the methods for rapid filtering of sensitive content based on dynamic multi-rule matching provided in the embodiments of the present application. For example, the instructions can execute the following steps: Obtain the current application scenario of the content to be filtered; obtain the filtering rule application condition information, the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; based on the current application scenario and the filtering condition application rule, determine the preset filtering rule corresponding to the current application scenario as the current application rule; process the content to be filtered based on the current application rule to obtain a content processing result.

[0078] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0079] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0080] Since the instructions stored in the computer-readable storage medium can execute the steps in any one of the methods for quickly filtering sensitive content based on dynamic multi-rule matching provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the methods for quickly filtering sensitive content based on dynamic multi-rule matching provided in the embodiments of the present application can be achieved. Please see the previous embodiments for details and will not be repeated here.

[0081] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementations of the above-mentioned content sorting aspect.

[0082] The above is a detailed introduction to a method and system for rapid filtering of sensitive content based on dynamic multi-rule matching provided in an embodiment of the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0083] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the object needs to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A method for rapid filtering of sensitive content based on dynamic multi-rule matching, characterized in that: include: Get the current application scenario of the content to be filtered; Acquire filtering rule application condition information, wherein the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; Based on the current application scenario and the filtering condition application rule, determining the preset filtering rule corresponding to the current application scenario as the current application rule; The to-be-filtered content is processed based on the current application rule to obtain a content processing result.

2. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 1 is characterized in that: The preset filtering rules include keyword filtering rules and semantic filtering rules, and the application rules based on the current application scenario and the filtering condition determine the preset filtering rules corresponding to the current application scenario as the current application rules, including: When the current application scenario is a structured scenario, the preset filtering rule corresponding to the structured scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

3. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 2 is characterized in that: Before determining that the preset filtering rule corresponding to the structured scenario is the keyword filtering rule when the current application scenario is a structured scenario and using the keyword filtering rule as the current application rule, the method further includes: Obtaining preset keywords in the keyword filtering rule; Based on the preset keyword, obtaining a substitute keyword of the preset keyword according to a preset search frequency; The keyword filtering rule is updated based on the alternative keyword.

4. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 2 is characterized in that: The determining, based on the current application scenario and the filtering condition application rule, the preset filtering rule corresponding to the current application scenario as the current application rule further includes: When the current application scenario is a content-based scenario, it is determined that the preset filtering rule corresponding to the content-based scenario is the semantic filtering rule, and the semantic filtering rule is used as the current application rule.

5. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 4 is characterized in that: When the current application scenario is a content-based scenario, before determining that the preset filtering rule corresponding to the content-based scenario is the semantic filtering rule and using the semantic filtering rule as the current application rule, the method further includes: Obtaining the number of online users in the content scenario; When the number of online users exceeds the preset number of users, the preset filtering rule corresponding to the content scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

6. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 5 is characterized in that: After obtaining the number of online users in the content scenario, the method further includes: When the number of online users does not exceed the preset number of users, the preset filtering rule corresponding to the content scenario is determined to be the semantic filtering rule, and the semantic filtering rule is used as the current application rule.

7. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 5 is characterized in that: When the number of online users exceeds the preset number of users, before determining that the preset filtering rule corresponding to the content scenario is the semantic filtering rule and using the semantic filtering rule as the current application rule, the method further includes: Obtaining the content update frequency corresponding to the number of online users; When the content update frequency does not exceed the preset update frequency, determining that the preset filtering rule corresponding to the content scenario is the semantic filtering rule, and using the semantic filtering rule as the current application rule; When the content update frequency exceeds the preset update frequency, the preset filtering rule corresponding to the content scenario is determined to be the keyword filtering rule, and the keyword filtering rule is used as the current application rule.

8. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to any one of claims 4 to 7, characterized in that: After obtaining the current application rule, the method further includes: Determining whether the content-based scene is a real-time live broadcast scene; If the content-based scene is a real-time live broadcast scene, obtaining a live broadcast tag of the content-based scene; The semantic filtering rule corresponding to the live broadcast tag is shielded based on the live broadcast tag.

9. The method for rapid filtering of sensitive content based on dynamic multi-rule matching according to claim 8, characterized in that: After determining whether the content-based scene is a real-time live broadcast scene, the method further includes: If the content-based scene is a non-real-time live scene, the shielded semantic filtering rule is restored.

10. A system for rapid filtering of sensitive content based on dynamic multi-rule matching, characterized in that: include: A scene acquisition module is used to obtain the current application scene of the content to be filtered; A condition information acquisition module, used to acquire filtering rule application condition information, wherein the filtering rule application condition information includes a preset application scenario and a preset filtering rule corresponding to the preset application scenario; A rule determination module, configured to determine, based on the current application scenario and the filtering condition application rule, the preset filtering rule corresponding to the current application scenario as the current application rule; The content processing module is used to process the content to be filtered based on the current application rule to obtain a content processing result.

Images