Live broadcast interaction information identification method and device, live broadcast system, equipment and medium

Abstract

The invention relates to a live broadcast interaction information identification method and device, a live broadcast system, electronic equipment and a computer readable storage medium. The method comprises the following steps: in a live broadcast process, obtaining interaction information input in a live broadcast room in real time, and extracting a target text from the interaction information; matching characters of the target text by using preset roots and derivatives thereof; when the derivative word exists in the target text, respectively calculating the smoothness weight of the derivative word and the root in the target text, and comparing whether the smoothness weight of the derivative word is smaller than the smoothness weight of the root or not; when the smoothness weight of the derivative word is smaller than the smoothness weight of the word root, intercepting the interaction information in real time and preventing the interaction information from being displayed on a live broadcast room interface; according to the technical scheme, more accurate and comprehensive interception of variants appearing in the live broadcast process can be realized, the missed detection risk identification cost is reduced, and mistaken interception of normal live broadcast interaction information can be avoided.

Claims

1. A method for identifying live interactive information, characterized in that: include: During the live broadcast process, the interactive information input in the live broadcast room is obtained in real time, and the target text is extracted from the interactive information; Matching characters of the target text using preset word roots and their derivatives; When there are derived words in the target text, respectively calculating the fluency weights of the derived words and the root words in the target text, and comparing whether the fluency weight of the derived words is less than the fluency weight of the root words; When the fluency weight of the derived word is less than the fluency weight of the root word, the interactive information is intercepted in real time and prevented from being displayed on the live broadcast room interface.

2. The method for identifying live interactive information according to claim 1, characterized in that: Matching characters of the target text using preset root words and their derivatives includes: Perform multi-mode matching on each character of the target text in a preset dictionary tree, and detect whether there are derived words in the target text based on the matching results of each character; wherein the dictionary tree is constructed based on the root word generated by the live broadcast sensitive word and its derived replacement words.

3. The method for identifying live interactive information according to claim 1, characterized in that: Calculating the fluency weights of the derived words and the root words in the target text respectively, and comparing whether the fluency weight of the derived words is less than the fluency weight of the root words, including: Inputting the derived words and sentences of the root words in the target text into a large language model to calculate and obtain fluency weights; The fluency weight of the derived word is compared with the fluency weight of the root word; if the fluency weight of the derived word is less than the fluency weight of the root word, then the fluency weight of the derived word is less than the fluency weight of the root word.

4. The method for identifying live interactive information according to claim 3, characterized in that: Also includes: Dividing the target text into sentence components according to the association weights between different characters in a word and the association weights between words; The weights of the derived words and roots in the sentences of the target text are traversed, from the weight before the word to the fluency weight after the word, and the derived word component is determined according to the fluency weight of the derived word and the fluency weight of the root.

5. The method for identifying live interactive information according to claim 4, characterized in that: Also includes: When the derived word is at the beginning of the sentence in the target text, the weight of the word appearing at the beginning of the sentence in the natural language environment is taken as the pre-word fluency weight; When the derived word is at the end of the target text, the post-word fluency weight is 0.

6. The method for identifying live interactive information according to claim 1, characterized in that: Acquire interactive information input in the live broadcast room in real time, and extract target text from the interactive information, including: When interactive information is input in the live broadcast room, a screenshot image of the live broadcast room interface is obtained in real time through the live broadcast service system; The screenshot image is subjected to text recognition based on OCR technology to obtain the target text.

7. The method for identifying live interactive information according to claim 1, characterized in that: Also includes: Detect sensitive words that appear during live broadcasts on live broadcast platforms; Performing semantic analysis on the sensitive words and generating a certain number of word roots, and constructing a normalized word library based on the word roots; Deriving a plurality of replacement words according to the root word, and constructing a normalized replacement library based on the mapping relationship between the replacement words and the root word; Obtaining a normalized keyword vocabulary according to the normalized vocabulary and the normalized replacement library; Constructing a dictionary tree of all pattern strings of the root word and the replacement word, and setting a failure pointer of each node of the dictionary tree; Initialize the current state to the root node.

8. The method for identifying live interactive information according to claim 1, characterized in that: Also includes: When the sensitive words in the target text meet the manual review conditions, the interactive information is sent to the manual review system for review; Perform corresponding processing operations on the user according to the review results returned by the manual review system.

9. A device for identifying live interactive information, characterized in that: include: An extraction module is used to obtain interactive information input in the live broadcast room in real time during the live broadcast process, and extract the target text from the interactive information; A matching module, used for matching characters of the target text using preset word roots and their derivatives; A comparison module, for respectively calculating the fluency weights of the derived word and the root word in the target text when there are derived words in the target text, and comparing whether the fluency weight of the derived word is less than the fluency weight of the root word; The interception module is used to intercept the interactive information in real time and prevent it from being displayed on the live broadcast room interface when the fluency weight of the derived word is less than the fluency weight of the root word.

10. A live broadcast system, characterized in that: include: Client and live broadcast server; wherein the client includes an anchor terminal and a viewer terminal respectively connected to the live broadcast server through a network; The live broadcast server is used to receive the anchor video uploaded by the anchor end and forward it to the audience end, and use the live broadcast interactive information identification method described in any one of claims 1 to 8 to identify the interactive information uploaded by the client; The anchor terminal is used to collect anchor videos and upload them to the live broadcast server, and upload the interactive information of the anchor side to the live broadcast server for identification processing; The audience terminal is used for audience users accessing the live broadcast room, playing the anchor video sent by the live broadcast server, and uploading the interactive information on the audience side to the live broadcast server for identification processing.

11. An electronic device, characterized in that: The electronic device comprises: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the steps of the method for identifying live interactive information as described in any one of claims 1-8.

12. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded by the processor and executes the steps of the method for identifying live interactive information according to any one of claims 1-8.

Images