Device and method for predicting behaviors based on multi-platform data for interaction and self-adjustment

Abstract

A device and method for predicting behavior based on multi-platform data and enabling interaction and self-adjustment, which analyzes user interaction behavior data on multiple platforms, uses an artificial intelligence model to predict user behavior types based on the analysis results, generates personalized response messages to interact with users based on the predicted behavior types, and adjusts the artificial intelligence model based on user interaction behavior, can accurately grasp user intentions across platforms and enable the model to adapt and adjust, thereby achieving the technical effect of precise and personalized interaction with users and improving service efficiency.

Claims

1. A method for predicting and self-adjusting user behavior based on multi-platform data, applied to a device, the method comprising at least the following steps: obtaining user interaction behavior data from multiple data sources; integrating the interaction behavior data; analyzing the interaction behavior data to generate a user feature vector and an emotional tendency index; inputting the user feature vector and the emotional tendency index as parameters into an artificial intelligence model, causing the artificial intelligence model to generate a predicted behavior type for the user on each of the target platforms; generating a personalized response message for each user on each target platform based on the predicted behavior type; monitoring the user's user interaction behavior after the personalized response message is provided to the user to generate a monitoring result; when the monitoring result detects that the user's interaction behavior includes a specific combination of behaviors with negative experiences, executing a service recovery strategy, the service recovery strategy including reducing or stopping marketing activities for the user, marking the user as a high-priority user, providing compensatory coupons, prompting live customer service to proactively contact the user; and adjusting the parameters in the artificial intelligence model related to generating the predicted behavior type based on the monitoring result.

2. The method for predicting behavior and self-adjusting based on multi-platform data as described in claim 1, wherein before the step of monitoring the user's interaction behavior after the personalized response message is provided to the user, the method further includes the step of selecting an optimal interaction channel based on the predicted behavior type, the current context, and the user's user preferences, and using the optimal interaction channel to provide the personalized response message to the user.

3. The method for predicting behavior and self-adjusting based on multi-platform data as described in claim 1, wherein the step of adjusting the parameters in the artificial intelligence model that generate the predicted behavior type based on the monitoring results is to perform attribution analysis on the monitoring results to determine a key feature affecting the user's interactive behavior, and update the weights in the artificial intelligence model corresponding to the key feature.

4. The method for predicting behavior and self-adjusting based on multi-platform data as described in claim 1, wherein the step of adjusting the parameters in the artificial intelligence model for generating the predicted behavior type based on the monitoring results further includes the steps of calculating an emotional volatility index or a contrarian psychological index based on the historical sequence of the emotional tendency index, measuring the user's sensitivity to and reaction tendency to the personalized response message based on the emotional volatility index or the contrarian psychological index, correcting the predicted behavior type based on the sensitivity and the reaction tendency, and adjusting the generation strategy of the personalized response message based on the sensitivity and the reaction tendency.

5. The method for predicting behavior and self-adjusting based on multi-platform data as described in claim 1, wherein the step of generating the personalized response message for the user based on the predicted behavior type and the user's historical interaction data further includes the steps of determining the user's current situation based on the user's intent determined from the context of the interaction behavior data and / or the user's behavior on the platform, analyzing the user's public posts on social media in the interaction behavior data through natural language processing (NLP) technology to generate a mirror communication style, and generating the personalized response message that conforms to the mirror communication style by using corresponding interaction strategies based on the sentiment tendency index, the current situation, the predicted behavior type and the historical interaction data.

6. An apparatus for predicting and self-adjusting user behavior based on multi-platform data, the apparatus comprising at least: a data transmission module for acquiring user interaction behavior data from multiple data sources; a data integration module for integrating the interaction behavior data; a feature analysis module for analyzing the interaction behavior data to generate a user feature vector and a sentiment tendency index; a behavior prediction module for inputting the user feature vector and the sentiment tendency index as parameters into an artificial intelligence model, so that the artificial intelligence model generates a predicted behavior type for the user corresponding to one of the target platforms; and a response generation module for generating responses based on the predicted behavior type. The system generates a personalized response message for each user on each target platform; a response monitoring module monitors the user's interaction behavior after the personalized response message is provided to the user to generate a monitoring result, and executes a service recovery strategy when the monitoring result detects that the user's interaction behavior includes a specific combination of behaviors, including reducing or stopping marketing activities for the user, marking the user as a high priority, providing compensatory coupons, and prompting a live customer service representative to proactively contact the user; and a model adjustment module adjusts the parameters in the artificial intelligence model related to the generation of the predicted behavior type based on the monitoring result.

7. The device for interaction and self-adjustment based on multi-platform data prediction behavior as described in claim 6, wherein the behavior prediction module is further used to select an optimal interaction channel based on the predicted behavior type, the current context, and the user preferences obtained by the data transmission module, and the data transmission module is further used to use the optimal interaction channel to provide the personalized response message to the user.

8. The device for predicting and self-adjusting behavior based on multi-platform data as described in claim 6, wherein the model adjustment module performs attribution analysis on the monitoring results to determine a key feature affecting the user's interactive behavior and updates the weights in the artificial intelligence model corresponding to the key feature.

9. The device for predicting behavior and self-adjusting based on multi-platform data as described in claim 6, wherein the feature analysis module is further used to calculate an emotional fluctuation index or a contrarian psychological index based on the historical sequence of the emotional tendency index, and to measure the user's sensitivity to and reaction tendency to the personalized response message based on the emotional fluctuation index or the contrarian psychological index; the behavior prediction module is further used to modify the predicted behavior type based on the sensitivity and the reaction tendency; and the response generation module is further used to adjust the generation strategy of the personalized response message based on the sensitivity and the reaction tendency.

10. The device for interaction and self-adjustment based on multi-platform data prediction behavior as described in claim 6, wherein the response generation module is further used to determine the user's current situation based on the user's intent and / or the user's behavior on the platform as determined by the behavior prediction module based on the context of the interaction behavior data, and to generate a mirror communication style by analyzing the user's public posts on social media in the interaction behavior data through natural language processing technology, and to generate a personalized response message that conforms to the mirror communication style by using the corresponding interaction strategy based on the emotion tendency index, the current situation, the predicted behavior type and the historical interaction data.

Images