METHOD AND SYSTEM TO PROTECT A USER OF ONE OR MORE SOCIAL NETWORKS OR VIDEO GAMES AGAINST CYBERBULLYING RISKS

Description

1 / 13 “METHOD AND SYSTEM TO PROTECT A USER OF ONE OR MORE SOCIAL NETWORKS OR VIDEO GAMES AGAINST CYBERBULLYING RISKS” DESCRIPTION FIELD OF THE INVENTION

[0001] The present invention relates to a method for protecting a user of one or more social networks or video games against the risks of cyberbullying and toxic content. It also relates to a processing system that employs this method.

[0002] The field of the invention is more particularly that of preventing cyberbullying and online toxicity on social networks. TECHNOLOGICAL BACKGROUND

[0003] Since the emergence and widespread deployment of social networks around the world, there has been a growing number of cases of cyberbullying and online toxicity, and parents of children with access to these social networks are powerless against the serious risks their children may face.

[0004] Software tools already exist to detect toxic or cyberbullying messages in the flow of information passing through messaging systems and social networks.

[0005] US patent application US11,138,237 B2 (IBM) Social Media Toxicity Analysis discloses a method for analyzing the toxicity of social media content, including constructing a class model that is representative of a type and level of toxicity associated with the content. A first social media message is analyzed, using a processor and memory, to calculate a first toxicity score associated with the first social media message and assign the first social media message to a first class in the class model. A second social media message is analyzed, using a processor and memory, to calculate a second toxicity score associated with the second social media message and assign the second social media message to a second class in the class model. A toxicity trend is predicted based on the first Petition 870250092015, dated 08 / 10 / 2025, pp. 68 / 93 2 / 13 toxicity score, in the first class, in the second toxicity score and in the second class. In response to the predicted increase in the toxicity trend, a corrective measure is applied to reduce the toxicity trend.

[0006] US patent 10,915,789 B2 discloses a method and a device for detecting offensive content on a portable electronic device by monitoring communications sent, received, or stored on the portable electronic device, wherein the monitoring comprises collecting content data, classifying content data by calculating an alert score for content data wherein an alert score corresponds to detected offensive content, and sending an alert notification to a second portable electronic device to alert it of the detection of offensive content on the first portable electronic device.

[0007] Document US2019 / 0266242 A1 discloses a method for mitigating cyberbullying by accurately intercepting and analyzing the sentiment of social media messages before presenting them to the intended recipient device. Based on message sentiment and sender category, abusive messages can be sent to an administrator for review and appropriate action. As a result, such messages can be blocked from the intended recipient device. The system can analyze message sentiment using a machine learning approach, for example, employing a Naive Bayes algorithm. An inference model can be generated through machine learning. The inference model can produce a metric that is used when evaluating message sentiment.

[0008] Document US2021 / 0042830 A1 discloses a digital multimedia system that uses a decentralized communication system to transfer digital data. In some embodiments, the digital data comprises digital property, currency, and instructions for executing financial transactions. In some embodiments, the digital multimedia system controls the storage and flow of digital data through specified nodes located in specified jurisdictions. Petition 870250092015, dated 08 / 10 / 2025, pp. 69 / 93 3 / 13

[0009] Document US2018 / 349502 A1 discloses a method and a system for filtering content from a computing device's graphical display, content which may have an object associated with content identifiers. This method comprises determining, by the computing device and based on an indication of selected filter criteria, a respective weighted probability for the object and determining a graphical element for an application based on the weighted probability.

[0010] Document WO2015 / 095597 A1 discloses a method and a system that allows parents to view and track their children's smartphone activities, which may comprise one or more software modules for children. The module, which can be installed on each child's smartphone, can access and extract data about several other smartphone software applications, including at least two of the following applications: a text messaging application, a social media application, an image application that facilitates the transmission or reception of images, and a web browser application.

[0011] Document US2015 / 095014 A1 discloses a method for selecting and evaluating content. A content rating platform processes content directed to or originating from a user to determine one or more elements in the content. The content rating platform calculates a content rating for the content by comparing the one or more elements with at least one user-configurable dictionary and then selects an operation to process the content based on the content rating.

[0012] Document WO2022 / 055546 A1 discloses a method, a system, and a product for filtering unwanted social multimedia content in real time. The system comprises sets of machine learning classifiers to filter unwanted content across various media. The classifiers are trained with labeled data. Once trained, the models filter the incoming data in real time, either on a server or on a mobile device. Petition 870250092015, dated 08 / 10 / 2025, pp. 70 / 93 4 / 13

[0013] However, it should be noted that the tools currently available are neither effective nor easy to use for social media users and parents of minors who access these networks.

[0014] The present invention aims to remedy these disadvantages and limitations by proposing a new method for processing online cyberbullying or toxic content that is more efficient and easier to use than existing tools.

[0015] In the present invention, the brain is understood to be a computational model, based on the simulation of the activity of populations of neurons, which possesses or develops cognitive faculties similar to biological brains.

[0016] Blockchain is understood as a ledger, a large database that has the specific feature of being shared simultaneously with all its users, all of whom are also holders of this ledger, and all of whom also have the ability to record data in it, according to specific rules defined by a computer protocol that is highly secure by virtue of cryptography, referring to the definition given in the Log of the joint information mission on blockchain and its uses: a sovereignty issue.

[0017] [https: / www2.assembleenationale.fr / static / 15 / commissions / CFinances / blockchain-synthese.pdf?v=1692355067]. DESCRIPTION OF THE INVENTION

[0018] This objective is achieved with a method to protect a user of one or more social networks or video games against the risks of cyberbullying, wherein this user has a device connected to a communication network to access digital content from said one or more social networks or video games or to receive digital content from one or more other users of said one or more social networks or video games, which comprises: - To perform semantic and contextual analysis on said digital content accessed or received, employing artificial intelligence techniques, Petition 870250092015, dated 08 / 10 / 2025, pp. 71 / 93 5 / 13 - To process the results of semantic and contextual analysis in order to detect a situation of cyberbullying or toxicity in all or part of said content, using a database of predetermined situations, - if a situation of cyberbullying or toxicity of digital content is detected, masking the display of toxic digital content on the screen of the connected device, characterized by it being implemented on a dedicated server suitable for connection, through said communication network, to said social networks or said video games, and by it additionally comprising, if a situation of cyberbullying or toxicity of digital content is detected, recording, in a blockchain, a set of data that describes this cyberbullying, and by the semantic and contextual analysis implementing a plurality of brains, each dedicated to a specific cyberbullying theme and operating simultaneously, each of said brains being intended to detect, after analysis, a word, a transcript of a voice message, an expression or an Emoji belonging to the theme associated with it.

[0019] Data describing cyberbullying or content toxicity may be issued in the form of a record.

[0020] The protection method according to the invention may further comprise a prior verification of the identity of the user to be protected, employing encryption of the identity data entered by that user from the connected device and employing decentralized software tools on Web3.

[0021] The protection method according to the invention may further comprise a step for accessing, from a second connected device, digital content received and detected as constituting cyberbullying or toxic content on a first connected device, as well as a step for Petition 870250092015, dated 08 / 10 / 2025, pp. 72 / 93 6 / 13 insert, from the connected device, a mention of one or more social networks or video game networks where protection is sought.

[0022] When the protection method according to the invention is applied to participation in an online video game, the semantic and contextual analysis steps are additionally configured to detect a toxicity situation in that video game.

[0023] According to another aspect of the invention, a system is proposed to protect a user of one or more social networks or video games against the risks of cyberbullying, wherein this user has a device connected to a communication network to access digital content from said one or more social networks or video games or to receive digital content from one or more other users of said one or more social networks or video games, employing the protection method according to the invention, wherein this system comprises: - means to perform semantic and contextual analysis on said digital content accessed or received, employing artificial intelligence techniques, - means to process the results of semantic and contextual analysis in order to detect a situation of cyberbullying or toxicity in all or part of said content, using a database of predetermined situations, - if a situation of cyberbullying or toxicity of digital content is detected, means to mask the display of toxic or cyberbullying digital content on the screen of the connected device, characterized by being implemented on a dedicated server suitable for connection, through said communication network, to said video game social networks, and by additionally comprising means to record, in a blockchain, a set of data describing such cyberbullying, and by the means to perform semantic and contextual analysis comprising a plurality of brains, each dedicated to a specific cyberbullying theme and operating simultaneously, each of said brains being intended to detect, Petition 870250092015, dated 08 / 10 / 2025, pp. 73 / 93 7 / 13 after analysis, a word, a transcript of a voice message, an expression, or an emoji belonging to the associated theme.

[0024] The protection system according to the invention can be advantageously implemented within a dedicated server that communicates through one or more communication networks, on the one hand, with one or more platforms that operate social networking services and, on the other hand, with a plurality of connected devices that access these social networking services and for which protection against cyberbullying is sought.

[0025] It may also include means to send a notification of detection of a cyberbullying situation to a dedicated platform.

[0026] The processing method according to the invention is advantageously carried out in the form of an application to combat cyberbullying and online toxicity, which can be downloaded on any device (mobile phone / tablet computer / PC / console).

[0027] With the help of its Artificial Intelligence, the method masks the toxicity on social networks added by its users and the hate messages they may receive. It analyzes conversations semantically and contextually to obtain results that match the user's wishes.

[0028] If a user encounters real cyberbullying problems, the application that implements the method according to the invention supports the user in their legal processes and certifies their data to establish a file for filing a complaint with the competent authorities. The application also helps the victim find an association specialized in combating online toxicity.

[0029] The application is also suitable for online gamers, for whom toxicity is a recurring problem, integrating with the platforms they are connected to, as well as with the video games that allow the solution to act.

[0030] The app also allows users and their designated guardians to be notified if they send inappropriate contextual elements that may be considered toxic by their recipients. Petition 870250092015, dated 08 / 10 / 2025, pp. 74 / 93 8 / 13

[0031] This application is built using software tools available in the AWS universe, according to the architecture below.

[0032] The processing method according to the invention employs: - an application fully designed for deployment on Web3, across multiple media and social networks, - an AI that employs a plurality of brains, each assigned to detecting a specific type of cyberbullying content, as opposed to the usual practice of using a single brain, - Assistance with the automatic output of records and recording of all types of content reports (image / text / video / file) to a blockchain. DESCRIPTION OF THE FIGURES - [Figure 1] Figure 1 is a block diagram of an exemplary embodiment of a system for protection against cyberbullying according to the invention; - [Figure 2] Figure 2 illustrates the main steps of an exemplary embodiment of the protection method according to the invention; - [Figure 3] Figure 3 illustrates an example of software architecture employed in a protection system according to the invention; - [Figure 4] Figure 4 shows an example of a user interface that provides a protected user with a summary of the operations for detecting cyberbullying and toxic content; - [Figure 5] Figure 5 shows an example of a user interface that provides a supervisor user with a summary of operations for detecting situations of cyberbullying and toxic content to which one or more family members, especially minors, may have been exposed; - [Figure 6] Figure 6 shows an example of a user interface that provides a protected user with blocking and reporting functions in response to the detection of cyberbullying or toxic content; Petition 870250092015, dated 08 / 10 / 2025, pp. 75 / 93 9 / 13 [Figure 7] Figure 7 shows an example of a user interface that provides a video game user with a panel of the detection operations performed by the protection method according to the invention. DETAILED DESCRIPTION OF A MODALITY

[0033] With reference to Figures 1 and 2, a system 1 for protection against cyberbullying according to the invention is employed on a server 13 to which a database 14 is associated and is connected via a common network to a digital cloud 2 (generally called the Cloud) that links a set of social networking platforms 5 (or social media), including, for example, but not limited to, Discord®, Twitter®, Instagram®, TikTok® or Facebook®, and video game platforms 4, such as the Steam® platform.

[0034] The method for protection against cyberbullying according to the invention is used in a set of digital communication devices connected to the Cloud 2, such as smartphones 6 to 9,12 or tablet-type computers 10, on which a dedicated application has been installed. Some of these smartphones 8,9 can be connected to Cloud 2 resources via a router 11.

[0035] The mission of the cyberbullying protection system 1, according to the invention, will be to protect users of smartphones or tablet-type computers 6 to 10, equipped with the protection application, against the malicious actions of people or server organizations 5 connected to the Cloud 2 and who seek to harm these users through one or more social networks or one or more video game platforms.

[0036] A description will now be given, still with reference to [Figure 2], of an embodiment of the method for protection against cyberbullying according to the invention. It is assumed that a dedicated application has been downloaded by a smartphone user 7 from a protection server 1 that implements the protection method according to the invention.

[0037] This application, which provides a graphical interface on the screen of a user's smartphone 7 or on the screen of a smartphone 12 belonging to a user who is a parent or member. Petition 870250092015, dated 08 / 10 / 2025, pp. 76 / 93 10 / 13 of a minor user's family requests access to the user's account on a social network, for example, the Discord network, to the server that manages that network.

[0038] Once server 13 managing the protection method has gained access to the protected user's Discord social network account, a semantic and functional analysis 101 of the content received in that user account will be performed, permanently or periodically at a predetermined frequency. This analysis is performed directly on the protection server, before the analyzed content can be viewed on the user's smartphone 7.

[0039] This analysis 101 employs a set of artificial brains C1, C2, C3, C4, C5, each assigned to a specific category of cyberbullying or toxicity.

[0040] An artificial brain is understood as a computational model, based on the simulation of the activity of populations of neurons, that possesses or develops cognitive faculties similar to biological brains.

[0041] If a malicious server 5 sends a message with cyberbullying content or a message with toxic content to the protected user, one of the C1 to C5 brains will detect 103, after analysis, a word, a transcript of a voice message, an expression, or an Emoji belonging to one of the categories associated with each of these brains.

[0042] The protection server 13 will then mask 104 the message detected as constituting cyberbullying or toxic content, so that this message or content will not be accessed by the protected user on their smartphone screen 7.

[0043] This is followed by a step 105 of recording data describing this detection of cyberbullying or toxicity on a blockchain 15 that is accessible by the protection server 13 via the Cloud 2 and a step 106 of issuing a record 107 intended to be transmitted to an administrative or official authority responsible for combating cyberbullying.

[0044] Detection data may include, for example, the content of the intercepted message, the date, time and origin (if technically possible) of that message. Petition 870250092015, dated 08 / 10 / 2025, pp. 77 / 93 11 / 13

[0045] In an embodiment of the invention dedicated to protecting minor users under parental supervision, various options may be provided for employing the protection method according to the invention.

[0046] The protection method according to the invention can be constructed from, but not limited to, a software architecture 20, as shown in [Figure 3]. Several basic modules of this software architecture can be taken from the AWS (Amazon Web Services) software offering.

[0047] The software architecture 20 employs a DNS domain name system 21, associated with SSL certificate management 23 and a CDN content delivery network to manage and host 25 the website implementing the protection method according to the invention.

[0048] This website is built on a Web Framework 27 that triggers a consent management module 24 and a personal identity and access management module 29.

[0049] The core of the software architecture 20 comprises an image container module 34, built, for example, from a GraphQL Framework in Python, which is powered by a Docker image registry 28.

[0050] This container 34 triggers a payment service module 35, an image recognition module 30 controlled by the personal identity and access management module 29, a natural language processing (NLP) inference engine 36, a module 31 for managing identities and access to social networks that will be protected, and a NoSQL database 37.

[0051] Module 31 for managing identities and access to social networks controls, through authorization tokens, a serverless computing module 32 that directly addresses each of the social networks 21 (e.g., WhatsApp), 33 (e.g., Messenger) that are the target of the protection method according to the invention. It is understood that these social networks may include, but are not limited to, Discord, Twitter, Instagram, TikTok, or Facebook, as exemplified in [Figure 1]. Petition 870250092015, dated 08 / 10 / 2025, pp. 78 / 93 12 / 13

[0052] The PLN 36 natural language processing inference mechanism triggers a PLN 41 machine learning module, a PLN 42 custom learning module that can be targeted to a graphics processing unit (GPU) learning module on demand, which can be activated by a time scheduling module 45.

[0053] The NoSQL database 37 feeds a data integration mechanism 38, which feeds a data warehouse 39 equipped with a key performance indicator module 40 and an immutable database or a blockchain 15.

[0054] With reference to Figures 4 to 7, several practical examples of graphical user interfaces generated on the screen of protected users or a supervisor, implementing the protection method according to the invention, will now be described.

[0055] The user interface 50 represented by [Figure 4] corresponds to what a protected user can view on their smartphone screen: it contains a graphical summary 51, for example, in circular format, illustrating the percentages of toxic messages 54 and blocked messages 55. The protected user can access summary data for each of the social networks 52 to which they are subscribed, and a list 53 of the latest blocked messages.

[0056] With reference to [Figure 5], the supervisor, for example, a parent or an adult family member, can view a user interface 60 in which they can consult, for each of the protected users 62,63 under their supervision, a summary 61 of the percentages of toxic and blocked messages 64,65.

[0057] Each time a cyberbullying situation or toxic content is detected, the protected user - or their supervisor - will be able to view a Defend Me 70 user interface on their smartphone, which offers a Block 71 action allowing the user sending the message to be blocked, and a Pharos 72 Reporting action allowing a legal file to be built and a report to be issued based on the detection information recorded by the protection method according to the invention. Petition 870250092015, dated 08 / 10 / 2025, pp. 79 / 93 13 / 13

[0058] Logically, the present invention is not limited to the embodiment just described, and many other embodiments can be envisioned without departing from the scope of the invention. In particular, the number of artificial brains employed in the protection method according to the invention is not limited to that described above. Furthermore, the structure of the detection data to be recorded on the blockchain can be of any type, depending on the effectiveness of the semantic and contextual analysis techniques employed. The same applies to the structure and practical content of the report issuance records. Petition 870250092015, dated 08 / 10 / 2025, pp. 80 / 93

Claims

1 / 3 CLAIMS 1. A method for protecting a user of one or more social networks (3) or video games (4) against the risks of cyberbullying, wherein that user has a device (6 to 10) connected to a communication network (2) to access digital content from said one or more social networks (3) or said video games (4) or to receive digital content from one or more other users of said one or more social networks (3) or said video games (4), comprising: - performing semantic and contextual analysis (101) on said digital content accessed or received, employing artificial intelligence techniques, - performing the processing (103) of the results of the semantic and contextual analysis in order to detect a situation of cyberbullying or toxicity of all or part of said content, employing a database of predetermined situations, - if a situation of cyberbullying or toxicity of the digital content is detected,masking (104) the display of toxic digital content on the screen of the connected device (6 to 10), characterized by being implemented on a dedicated server suitable for connection, through said communication network (2), to said social networks or said video games, and by further comprising, if a situation of cyberbullying or toxicity of digital content is detected, recording (105), in a blockchain (15), a set of data describing such cyberbullying, and by the semantic and contextual analysis implementing a plurality of brains (C1 to C5), each dedicated to a specific cyberbullying theme and operating simultaneously, each of said brains (C1 to C5) being intended to detect (103), after analysis, a word, a transcript of a voice message, an expression or an Emoji belonging to the theme associated with it.

2. Method, according to claim 1, characterized in that data describing cyberbullying or a toxicity of content are issued (106) in the form of a record (107). Petition 870250092015, dated 08 / 10 / 2025, pp. 81 / 93 2 / 3 3. A protection method, according to any of the preceding claims, characterized by additionally comprising a prior verification of the identity of the user to be protected, employing encryption of the identity data entered by that user from the connected device.

4. A protection method, according to any of the preceding claims, characterized by employing decentralized software tools on the Web3.

5. Protection method, according to any of the preceding claims, characterized by further comprising a step for accessing, from a second connected device (12), digital content received and detected as constituting cyberbullying or toxic content on a first connected device (6 to 10).

6. Protection method, according to any of the preceding claims, characterized by further comprising a step for inserting, from the connected device (6 to 10), a mention of one or more social networks (3) or video game platforms (4) in which protection is sought.

7. Protection method, according to any of the preceding claims, applied to participation in an online video game (4), characterized in that the semantic and contextual analysis and processing steps are additionally configured to detect a cheating situation in that video game.

8. System (1) for protecting a user of one or more social networks (3) or video games (4) against cyberbullying risks, wherein said user has a device (6 to 10) connected to a communication network (2) to access digital content from said one or more social networks (3) or said video games (4) or to receive digital content from one or more other users of said one or more social networks or said video games, employing the protection method as defined in any of the preceding claims, wherein said system comprises: - means (13) for performing semantic and contextual analysis on said digital content accessed or received, employing artificial intelligence techniques, Petition 870250092015, dated 08 / 10 / 2025, p. 82 / 93 3 / 3 - means (13) for processing the results of the semantic and contextual analysis in order to detect a cyberbullying situation or toxicity of all or part of said content,employing a database (14) of predetermined situations, - if a situation of cyberbullying or digital content toxicity is detected, - means to mask the display of toxic digital content on the screen of the connected device (6 to 10), characterized by being implemented on a dedicated server suitable for being connected, through said communication network, to said video game social networks, and by further comprising means to record, in a blockchain (15), a set of data describing such cyberbullying, and by the means to perform semantic and contextual analysis comprising a plurality of brains (C1 to C5), each dedicated to a specific cyberbullying theme and operating simultaneously, each of said brains (C1 to C5) being intended to detect (103), after analysis, a word, a transcript of a voice message, an expression or an Emoji belonging to the theme associated with it.

9. Protection system (1), according to claim 8, characterized by being implemented within a dedicated server that communicates through one or more communication networks (2), on the one hand, with one or more platforms that operate social networking services (3) and, on the other hand, with a plurality of connected devices (6 to 10, 12) that access these social networking services and for which protection against cyberbullying is sought.

10. Protection system (1), according to claim 9, characterized by additionally comprising means for sending a notification of detection of a cyberbullying situation to a dedicated platform. Petition 870250092015, dated 08 / 10 / 2025, pp. 83 / 93

Images