阅读说明：本技术 反网络欺凌系统及方法 (Anti-network spoofing system and method ) 是由 A·米龙 V·泽沃尤 A·M·阿弗洛阿雷 E·M·珀特鲁 L·博特扎图 B·布戈尤 L· 于 2020-01-20 设计创作，主要内容包括：一些实施例使用文本及/或图像处理方法确定电子信息传递平台的用户是否受到例如网络欺凌、性诱骗、及身份盗用等的网上威胁。在一些实施例中,电子消息的文本内容经自动采集并聚合成对话。接着,分析对话数据以提取各种威胁指示符。可组合文本分析的结果与作为所述相应对话的部分传输的图像的分析的结果。当检测到威胁时,一些实施例自动发送通知到第三方(例如父母、老师等)。(Some embodiments use text and/or image processing methods to determine whether a user of an electronic messaging platform is subject to an online threat, such as network spoofing, sexual spoofing, and identity theft. In some embodiments, the text content of the electronic message is automatically collected and aggregated into a conversation. The dialogue data is then analyzed to extract various threat indicators. The results of the text analysis may be combined with the results of the analysis of the images transmitted as part of the respective conversation. Some embodiments automatically send a notification to a third party (e.g., parent, teacher, etc.) when a threat is detected.)

1. A parental control method comprising employing at least one hardware processor of a computer system to:

analyzing a conversation to determine an offensiveness score and a friendliness score, wherein the conversation comprises a sequence of electronic messages exchanged between a first user and a second user, the offensiveness score indicating an offensiveness level for the conversation, the friendliness score indicating a friendliness level for the conversation, and wherein at least one of the offensiveness score and the friendliness score is determined from a plurality of messages of the conversation;

determining whether the first user is spoofed by the second user according to the aggressiveness and friendliness scores; and

in response, when the first user is spoofed, transmitting a parental notification to a parental reporting device identified from a plurality of devices according to the first user, the parental notification indicating that the first user is spoofed.

2. The method of claim 1, further comprising:

determining a first sentiment score and a second sentiment score from the conversation, the first sentiment score indicating a presumed sentiment of the first user and the second sentiment score indicating a presumed sentiment of the second user; and

it is further determined whether the first user is being spoofed based on the first and second sentiment scores.

3. The method of claim 1, further comprising:

determining a dialog certainty content score based on the dialog, the certainty content score indicating whether the dialog includes a language for explicit content; and

it is further determined whether the first user is being spoofed based on the sexual content score.

4. The method of claim 1, wherein the offensiveness score indicates whether the first user used offensive language within the conversation.

5. The method of claim 1, comprising determining the offensiveness score according to whether a plurality of messages of the conversation include offensive language.

6. The method of claim 5, comprising determining the offensiveness score from a message count that includes offensive language.

7. The method of claim 5, comprising determining the offensiveness score from a count of consecutive messages separating two messages within the conversation, both of which contain offensive language.

8. The method of claim 1, comprising determining that the first user is not deceived when the offensiveness and friendliness scores indicate that the conversation is both offensive and friendly.

9. The method of claim 1, comprising determining that the first user is spoofed when the offensiveness score indicates that the language of the second user is substantially more offensive than the language of the first user.

10. A computer system comprising at least one hardware processor configured to execute a conversation analyzer and a parental notifications scheduler, wherein:

the dialog analyzer is configured to:

analyzing a conversation to determine an offensiveness score and a friendliness score, wherein the conversation comprises a sequence of electronic messages exchanged between a first user and a second user, the offensiveness score indicating an offensiveness level of the conversation, the friendliness score indicating a friendliness level of the conversation, and wherein at least one of the offensiveness score and the friendliness score is determined from a plurality of messages of the conversation, an

Determining whether the first user is spoofed by the second user according to the aggressiveness and friendliness scores; and is

The parental notification scheduler is configured to, in response to the dialog analyzer determining that the first user is spoofed, transmit a parental notification to a parental reporting device identified from a plurality of devices according to the first user, the notification message indicating that the first user is spoofed.

11. The computer system of claim 10, wherein the conversation analyzer is further configured to:

determining a first sentiment score and a second sentiment score from the conversation, the first sentiment score indicating a presumed sentiment of the first user and the second sentiment score indicating a presumed sentiment of the second user; and

it is further determined whether the first user is being spoofed based on the first and second sentiment scores.

12. The computer system of claim 10, wherein the conversation analyzer is further configured to:

determining a dialog certainty content score based on the dialog, the certainty content score indicating whether the dialog includes a language for explicit content; and

it is further determined whether the first user is being spoofed based on the sexual content score.

13. The computer system of claim 10, wherein the offensiveness score indicates whether the first user used offensive language within the conversation.

14. The computer system of claim 10, wherein the conversation analyzer is configured to determine the offensiveness score according to whether a plurality of messages of the conversation include offensive language.

15. The computer system of claim 14, wherein the conversation analyzer is configured to determine the offensiveness score from a message count that includes offensive language.

16. The computer system of claim 14, wherein the conversation analyzer is configured to determine the offensiveness score according to a count of consecutive messages separating two messages within the conversation, both of which include offensive language.

17. The computer system of claim 10, wherein the conversation analyzer is configured to determine that the first user is not deceived when the offensiveness and friendship scores indicate that the conversation is both offensive and friendship.

18. The computer system of claim 10, wherein the dialog analyzer is configured to determine that the first user is being spoofed when the offensiveness score indicates that the language of the second user is substantially more offensive than the language of the first user.

19. A non-transitory computer-readable medium storing instructions that, when executed by at least one hardware processor of a computer system, cause the computer system to form a conversation analyzer and a parental notification scheduler, wherein: the dialog analyzer is configured to:

analyzing a conversation to determine an offensiveness score and a friendliness score, wherein the conversation comprises a sequence of electronic messages exchanged between a first user and a second user, the offensiveness score indicating an offensiveness level of the conversation, the friendliness score indicating a friendliness level of the conversation, and wherein at least one of the offensiveness score and the friendliness score is determined from a plurality of messages of the conversation, an

Determining whether the first user is spoofed by the second user according to the aggressiveness and friendliness scores; and is

The parental notification scheduler is configured to, in response to the dialog analyzer determining that the first user is spoofed, transmit a parental notification to a parental reporting device identified from a plurality of devices according to the first user, the notification message indicating that the first user is spoofed.