AI outbound-based conciliation willingness analysis and case priority management method

Abstract

The invention relates to the technical field of intelligent dispute handling, and discloses an AI outbound-based conciliation willingness analysis and case priority management method, which comprises the following steps: (a) a robot AI is used for carrying out batch outbound and automatically communicating with a called person, and the robot AI can carry out real-time dialogue management according to a preset rule and algorithm; (b) collecting the mediation willingness information of the called person through a customized verbal skill template, the verbal skill template including but not limited to an open question and a closed question, and a preset situational guide dialogue; (c) dividing the called persons into different categories according to the call connection condition; through AI robot batch outbound and automatic dialogue management, the manpower cost is greatly reduced, and the information collection speed and efficiency are improved. By using the voice recognition technology and the semantic understanding technology, the mediation willingness and the related information of the demodulated person can be accurately recognized, the information distortion is reduced, and the accuracy of information collection is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent dispute resolution, and specifically to a method for mediation willingness analysis and case priority management based on AI outbound calls. Background Art

[0002] At present, in the field of judicial mediation, traditional mediation intention collection and case management mainly rely on manual operations, which have problems such as low efficiency, incomplete information collection, and long case processing cycle. Especially when dealing with a large number of mediation requests, the method of manually contacting the mediators one by one and collecting information is not only time-consuming and labor-intensive, but also prone to information omissions or misunderstandings. In addition, the lack of an effective case priority management system often results in cases that need to be resolved urgently not being handled in a timely manner.

[0003] Although some AI-based outbound call systems have been used in customer service and other fields, they usually only have simple question-and-answer functions and lack the ability to deeply analyze mediation intentions and effective handling mechanisms for complex cases. In addition, existing systems often do not fully consider the emotional state and personal preferences of the mediators, making it difficult to implement personalized communication strategies. Therefore, how to efficiently and accurately analyze the mediation intentions of the mediators and manage the priority of cases accordingly has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a mediation willingness analysis and case priority management method based on AI outbound calls to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The mediation willingness analysis and case priority management method based on AI outbound calls includes the following steps:

[0007] (a) Using robot AI to make batch outbound calls and automatically communicate with the mediators, and the robot AI can manage real-time conversations according to pre-set rules and algorithms;

[0008] (b) collecting the mediation willingness information of the mediator through customized speech templates, which include but are not limited to open-ended questions and closed-ended questions, as well as preset scenarios to guide the dialogue;

[0009] (c) Classify the mediated party into different categories according to the call connection status, including but not limited to: not answering the call in person, answering the call in person, answering the call by a relative or friend, answering the call by an unconfirmed user, forwarded by a relative or friend, and not forwarded by a relative or friend, as well as the subsequent handling strategy for each category;

[0010] (d) Generate a corresponding portrait of the person being mediated for subsequent follow-up and communication, including but not limited to basic personal information, call records, and willingness to mediate;

[0011] (e) The voice response is converted into text through voice recognition technology, and semantic understanding technology is used to identify the mediation willingness and key information of the mediator, where the mediation willingness includes but is not limited to willingness to mediate, clear refusal to mediate, and unknown mediation willingness, and key information such as case details and dispute focus is also identified.

[0012] Preferably, it also includes:

[0013] Using emotion recognition technology to assess the emotional state of the person being mediated, including but not limited to positive, negative, and neutral;

[0014] Adjust conversational strategies based on emotional state, including but not limited to adopting a gentler or more direct conversational style.

[0015] Preferably, it also includes screening out high-quality mediation cases with or without willingness based on the mediation willingness profile of the mediator, and sorting and processing the cases according to their priorities. The sorting criteria include but are not limited to the urgency of the case and the mediation willingness strength of the mediator;

[0016] Mediation resources are allocated based on the sorting results, including but not limited to manual intervention and further automated processing.

[0017] Preferably, further comprising:

[0018] Optimizing outbound calling strategies through a personalized recommendation algorithm that takes into account the historical behavior and preferences of the mediator;

[0019] Adjust outbound call time, frequency, and content based on personalized recommendation results.

[0020] Preferably, further comprising:

[0021] ① Use intelligent decision-making algorithms to determine the priority of cases, which may be based on machine learning models;

[0022] ② Dynamically adjust case priorities to adapt to mediation progress and changes in the external environment;

[0023] ③ Use deep learning models for intent recognition and prediction, which can be sequence-to-sequence models based on natural language processing technology or other related technologies;

[0024] ④ Use deep learning models to conduct a comprehensive analysis of the verbal and non-verbal behaviors of the mediator.

[0025] Preferably, further comprising:

[0026] Ensure data security and integrity through blockchain technology, which is used in the process of data storage, transmission and verification;

[0027] Implement blockchain-based distributed ledger technology to record key data during the mediation process.

[0028] Preferably, it also includes regular backup and security audit of the data in the mediation process, and the audit includes but is not limited to data integrity check and access permission review.

[0029] Preferably, it also includes implementing an automatic redial mechanism for calls that are not connected or hung up, and repeating the call according to a preset time interval;

[0030] When encountering complex cases, the system automatically marks and transfers them to human mediators with corresponding professional backgrounds for processing.

[0031] Preferably, it also includes adopting a multi-language support function so that the robot AI can automatically switch the conversation language according to the language habits of the mediator;

[0032] Make appropriate adjustments to the language based on cultural differences in different language environments.

[0033] Preferably, further comprising:

[0034] Implement a feedback loop mechanism to allow mediators or mediated parties to evaluate the AI ​​outbound call process and service quality;

[0035] Update the AI ​​dialogue strategy in real time based on feedback information.

[0036] The present invention has at least the following beneficial effects:

[0037] (1) This solution greatly reduces labor costs and improves the speed and efficiency of information collection through AI robot batch outbound calls and automatic dialogue management. By using speech recognition technology and semantic understanding technology, it can accurately identify the mediation intention and related information of the mediator, reduce information distortion, and enhance the accuracy of information collection.

[0038] (2) Through emotion recognition technology and personalized recommendation algorithms, this solution can adjust communication strategies based on the emotional state and historical behavior of the mediator, enhance the affinity and effectiveness of the dialogue, and achieve personalized communication. By prioritizing cases, it can ensure that urgent cases and high-willing cases are handled in a timely manner, thereby improving the overall success rate of mediation.

[0039] (3) This solution uses blockchain technology to ensure data security and integrity, increase the credibility of the system, facilitate regular security audits, and improve data security and transparency. By supporting multi-language and cultural differences, it can better serve mediators from different regions and cultural backgrounds and expand the scope of services.

[0040] (4) By implementing a feedback loop mechanism, this solution can continuously optimize AI dialogue strategies and service quality, ensuring continuous improvement in system performance and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0042] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1

[0045] See also Figure 1 The present invention provides a technical solution: a mediation willingness analysis and case priority management method based on AI outbound calls, comprising the following steps:

[0046] (a) Using robot AI to make batch outbound calls and automatically communicate with the mediators, and the robot AI can manage real-time conversations according to pre-set rules and algorithms;

[0047] (b) collecting the mediation willingness information of the mediator through customized speech templates, which include but are not limited to open-ended questions and closed-ended questions, as well as preset scenarios to guide the dialogue;

[0048] (c) Classify the mediated party into different categories according to the call connection status, including but not limited to: not answering the call in person, answering the call in person, answering the call by a relative or friend, answering the call by an unconfirmed user, forwarded by a relative or friend, and not forwarded by a relative or friend, as well as the subsequent handling strategy for each category;

[0049] (d) Generate a corresponding portrait of the person being mediated for subsequent follow-up and communication, including but not limited to basic personal information, call records, and willingness to mediate;

[0050] (e) The voice response is converted into text through voice recognition technology, and semantic understanding technology is used to identify the mediation willingness and key information of the mediator, where the mediation willingness includes but is not limited to willingness to mediate, clear refusal to mediate, and unknown mediation willingness, and key information such as case details and dispute focus is also identified.

[0051] It should be noted that the development of AI dialogue robots is to set up AI robots that can manage real-time dialogues according to preset rules and algorithms. The robot should have the ability to understand natural language and be able to flexibly adjust dialogue strategies according to different dialogue scenarios.

[0052] Develop a set of dialogue templates that include open-ended questions, closed-ended questions, and situation-guided dialogues to collect information about the mediator's willingness to mediate.

[0053] The mediators are divided into multiple categories according to the call connection situation, and specific follow-up strategies are formulated for each category. The basic information of the mediators, such as name, contact information, etc., is collected. The key information of each call, such as the time, duration and main content of the call, is recorded. The mediators' willingness to mediate and case-related information are identified through voice recognition technology and semantic understanding technology.

[0054] Automated processing: For simple cases, we will continue to use the AI ​​outbound call system for automated processing.

[0055] Human intervention: Complex cases or those requiring professional mediation will be assigned to human mediators.

[0056] In some embodiments, it also includes:

[0057] Use emotion recognition technology to assess the emotional state of the mediator, including but not limited to positive, negative, and neutral, in order to improve the success rate of mediation and optimize dialogue strategies;

[0058] Adjust conversational strategies based on emotional state, including but not limited to adopting a gentler or more direct conversational style.

[0059] It should be noted that sentiment analysis: integrates emotion recognition technology to evaluate the emotional state of the person being mediated (positive, negative, neutral).

[0060] Strategy adjustment: Adjust the dialogue strategy according to the emotional state of the mediator and adopt a more appropriate way to communicate.

[0061] In some embodiments, it also includes screening out high-quality mediation cases with or without willingness based on the mediation willingness profile of the mediator, and sorting and processing the cases according to their priorities. The sorting criteria include but are not limited to the urgency of the case and the mediation willingness strength of the mediator;

[0062] Mediation resources are allocated based on the sorting results, including but not limited to manual intervention and further automated processing.

[0063] It should be noted that cases with mediation willingness or unknown mediation willingness are screened out based on the mediation willingness profile of the mediated party.

[0064] Priority sorting: Cases are sorted according to factors such as the urgency of the case and the willingness of the mediator to mediate.

[0065] In some embodiments, further comprising:

[0066] Optimize outbound call strategies through personalized recommendation algorithms to improve mediation efficiency and user satisfaction, and the personalized recommendation algorithms take into account the historical behavior and preference factors of the mediator;

[0067] Adjust outbound call time, frequency, and content based on personalized recommendation results to increase response rate and mediation success rate.

[0068] It should be noted that personalized recommendations: use personalized recommendation algorithms to optimize outbound call strategies, improve mediation efficiency and user satisfaction.

[0069] Behavioral analysis: Considers the historical behavior and preferences of the mediator, such as optimal outbound call time, frequency, and content.

[0070] In some embodiments, further comprising:

[0071] ① Use intelligent decision-making algorithms to determine the priority of cases. The intelligent decision-making algorithms can be based on machine learning models and take into account multiple factors such as case complexity and party background;

[0072] ② Dynamically adjust case priorities to adapt to mediation progress and changes in the external environment;

[0073] ③ Use deep learning models to identify and predict intentions and improve the accuracy of mediation intention identification. The model can be a sequence-to-sequence model based on natural language processing technology or other related technologies;

[0074] ④ Use deep learning models to conduct a comprehensive analysis of the verbal and non-verbal behaviors of the mediator in order to more accurately infer his or her true intentions.

[0075] It should be noted that priorities are dynamically adjusted: intelligent decision-making algorithms are used to dynamically adjust case priorities to adapt to changes in mediation progress and the external environment.

[0076] Deep learning model: Use deep learning models to identify and predict intentions and improve the accuracy of mediation intention identification.

[0077] Non-verbal behavior analysis: Use deep learning models to conduct a comprehensive analysis of the verbal and non-verbal behaviors of the mediator to more accurately infer his or her true intentions.

[0078] In some embodiments, further comprising:

[0079] Ensure data security and integrity and improve system credibility through blockchain technology, which is applied in data storage, transmission and verification;

[0080] Implement blockchain-based distributed ledger technology to record key data in the mediation process and ensure that the data cannot be tampered with.

[0081] It should be noted that blockchain technology: blockchain technology is used to ensure the security and integrity of data and improve the credibility of the system.

[0082] Distributed ledger: Use blockchain-based distributed ledger technology to record key data in the mediation process to ensure that the data cannot be tampered with.

[0083] In some embodiments, it also includes regular backup and security audit of the data in the mediation process to ensure the reliability and traceability of the data. The audit includes but is not limited to data integrity check and access permission review.

[0084] It should be noted that data backup and auditing: regular backup and security audits are carried out on data during the mediation process to ensure the reliability and traceability of the data.

[0085] In some embodiments, it also includes implementing an automatic redial mechanism for calls that are not connected or hung up, and repeating the call according to a preset time interval to increase the probability of successful contact;

[0086] When encountering complex cases, the system automatically marks and transfers them to human mediators with relevant professional backgrounds for processing, so as to improve the professionalism and success rate of mediation.

[0087] It should be noted that the missed call processing is: for calls that are not answered or hung up, an automatic redial mechanism is implemented to repeat the call according to a preset time interval.

[0088] Professional mediator intervention: When encountering complex cases, the system automatically marks and transfers these cases to human mediators with corresponding professional backgrounds for processing.

[0089] In some embodiments, a multi-language support function is also adopted, so that the robot AI can automatically switch the conversation language according to the language habits of the mediator to cover a wider audience group;

[0090] Make appropriate adjustments to the language based on cultural differences in different language environments to enhance the affinity and effectiveness of the conversation.

[0091] It should be noted that automatic language switching: the AI ​​robot should have multi-language support capabilities and be able to automatically switch the conversation language according to the language habits of the person being mediated.

[0092] Adjustment for cultural differences: Make appropriate adjustments to the language based on cultural differences in different language environments to enhance the affinity and effectiveness of the conversation.

[0093] In some embodiments, further comprising:

[0094] Implement a feedback loop mechanism to allow mediators or mediated parties to evaluate the AI ​​outbound call process and service quality to continuously improve the system's performance and user experience;

[0095] The AI ​​dialogue strategy is updated in real time based on feedback information to ensure the timeliness and accuracy of the dialogue content.

[0096] It should be noted that service quality evaluation: a feedback loop mechanism is implemented to allow mediators or mediated persons to evaluate the AI ​​outbound call process and service quality.

[0097] System optimization: Update AI dialogue strategies in real time based on feedback information to ensure the timeliness and accuracy of dialogue content.

[0098] Example 2

[0099] The present invention also protects the emotion perception and dialogue strategy adjustment method:

[0100] Assess the emotional state of the mediator through emotion recognition technology to improve the mediation success rate and optimize the dialogue strategy.

[0101] Implementation steps:

[0102] Integrated emotion recognition technology: Advanced natural language processing (NLP) technology is integrated into the AI ​​outbound calling system, which can extract acoustic features from speech and analyze the emotional state of the mediator in combination with text content.

[0103] Sentiment Labeling: Perform real-time sentiment analysis on each call to label the moderated person’s emotional state, such as “positive,” “negative,” or “neutral.”

[0104] Strategy Adjustment:

[0105] For mediators who show "positive" emotions, a more open and friendly dialogue style can be adopted to encourage them to share more details. For mediators with "negative" emotions, a more gentle and supportive communication strategy can be adopted to help alleviate their negative emotions. For mediators with "neutral" emotions, a neutral dialogue style should be maintained to avoid causing unnecessary reactions.

[0106] Expected results:

[0107] A more accurate grasp of the emotional state of the person being mediated can help build a trusting relationship, thereby increasing the success rate of mediation.

[0108] Example 3

[0109] The present invention also provides a personalized outbound call strategy and a method for improving user satisfaction:

[0110] Optimize outbound call strategies through personalized recommendation algorithms to improve mediation efficiency and user satisfaction.

[0111] Implementation steps:

[0112] Data collection and analysis: Collect basic information of the mediator, past communication records, willingness to mediate and other data, and analyze their historical behavior and preferences, such as the time period when they most frequently answer calls.

[0113] Personalized recommendation model construction: Based on the collected data, a personalized recommendation model is trained that can predict when and under what circumstances the mediator is more likely to answer the call, and which type of speech can better promote effective communication.

[0114] Strategy Adjustment and Implementation:

[0115] Adjust outbound call plans based on model predictions, for example, by making outbound calls during the time period when the mediate is most likely to answer the call.

[0116] Adjust the speech template and use language and expressions that are more suitable for the personality characteristics of the person being mediated.

[0117] Expected results:

[0118] Significantly improve call connection rate and mediation efficiency through personalized outbound calling strategies, while also improving overall user satisfaction.

[0119] In summary, the second embodiment and the third embodiment respectively focus on the importance of emotion management and personalized services in the mediation process. Through these specific measures, the quality and efficiency of the mediation work can be further improved.

[0120] Working principle: Start AI robots to make batch outbound calls to the mediators. The AI ​​robots will talk to the mediators according to the pre-designed speech templates, collect the mediators’ basic information, case details, mediation willingness and other related information, classify the mediators according to the call results (such as answered, not answered, refused, etc.), integrate the mediators’ personal information, call records, mediation willingness and other information to form a mediator portrait, convert the call content into text through voice-to-text technology, analyze the mediators’ mediation willingness using semantic understanding technology, and evaluate the mediators’ emotional state using emotion recognition technology. Use personalized recommendation algorithms to adjust outbound call strategies, including outbound call time, frequency and content, adjust the dialogue strategy according to the mediators’ emotional state, and screen out high-quality cases, i.e., those mediators with a stronger willingness to mediate or mediation. For cases where the willingness to mediate is unknown, the cases are sorted according to factors such as the urgency of the case and the strength of the mediation willingness of the mediator. The priority of the cases is determined by intelligent decision-making algorithms. An automatic redial mechanism is implemented for calls that are not answered or hung up. If multiple attempts are still unsuccessful, they may be marked for special handling. When encountering complex cases, the system automatically marks and transfers these cases to manual mediators with corresponding professional backgrounds for processing. Blockchain technology is used to ensure the security and integrity of data, and regular data backup and security audit mechanisms are implemented. Multi-language support functions are provided, so that the robot can automatically switch conversation languages, make appropriate adjustments to the language according to cultural differences in different language environments, allow mediators or mediators to evaluate the AI ​​outbound call process and service quality, and collect feedback information for system optimization and improvement.

[0121] For cases that require human intervention, mediators with relevant professional backgrounds will take over and handle them. After the mediation is completed, the case status will be updated and the case will be closed.

[0122] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0123] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The mediation willingness analysis and case priority management method based on AI outbound calls is characterized by: The following steps are involved: (a) Using robot AI to make batch outbound calls and automatically communicate with the mediators, and the robot AI can manage real-time conversations according to pre-set rules and algorithms; (b) collecting the mediation willingness information of the mediator through customized speech templates, which include but are not limited to open-ended questions and closed-ended questions, as well as preset scenarios to guide the dialogue; (c) Classify the mediated party into different categories according to the call connection status, including but not limited to: not answering the call in person, answering the call in person, answering the call by a relative or friend, answering the call by an unconfirmed user, forwarded by a relative or friend, and not forwarded by a relative or friend, as well as the subsequent handling strategy for each category; (d) Generate a corresponding portrait of the person being mediated for subsequent follow-up and communication, including but not limited to basic personal information, call records, and willingness to mediate; (e) The voice response is converted into text through voice recognition technology, and semantic understanding technology is used to identify the mediation willingness and key information of the mediator, where the mediation willingness includes but is not limited to willingness to mediate, clear refusal to mediate, and unknown mediation willingness, and key information such as case details and dispute focus is also identified.

2. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 1 is characterized by: Also includes: Using emotion recognition technology to assess the emotional state of the person being mediated, including but not limited to positive, negative, and neutral; Adjust conversational strategies based on emotional state, including but not limited to adopting a gentler or more direct conversational style.

3. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 2 is characterized by: It also includes screening out high-quality mediation cases with or without willingness based on the mediation willingness profile of the mediator, and sorting and processing the cases according to their priority. The sorting criteria include but are not limited to the urgency of the case and the mediation willingness of the mediator; Mediation resources are allocated based on the sorting results, including but not limited to manual intervention and further automated processing.

4. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 1 is characterized by: Further including: Optimizing outbound calling strategies through a personalized recommendation algorithm that takes into account the historical behavior and preferences of the mediator; Adjust outbound call time, frequency, and content based on personalized recommendation results.

5. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 3 is characterized by: Further including: ① Use intelligent decision-making algorithms to determine the priority of cases, which may be based on machine learning models; ② Dynamically adjust case priorities to adapt to mediation progress and changes in the external environment; ③ Use deep learning models for intent recognition and prediction, which can be sequence-to-sequence models based on natural language processing technology or other related technologies; ④ Use deep learning models to conduct a comprehensive analysis of the verbal and non-verbal behaviors of the mediator.

6. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 1 is characterized by: Further including: Ensure data security and integrity through blockchain technology, which is used in the process of data storage, transmission and verification; Implement blockchain-based distributed ledger technology to record key data during the mediation process.

7. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 1 is characterized by: It also includes regular backup and security audits of data during the mediation process, including but not limited to data integrity checks and access rights reviews.

8. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 7 is characterized by: It also includes implementing an automatic redial mechanism for unanswered or disconnected calls, and repeating the call at a preset time interval; When encountering complex cases, the system automatically marks and transfers them to human mediators with corresponding professional backgrounds for processing.

9. The method for mediation willingness analysis and case priority management based on AI outbound calling according to claim 1 is characterized by: It also includes the use of multi-language support, which allows the robot AI to automatically switch the conversation language according to the language habits of the mediator; Make appropriate adjustments to the language based on cultural differences in different language environments.

10. The mediation willingness analysis and case priority management method based on AI outbound calling according to claim 1 is characterized by: Further including: Implement a feedback loop mechanism to allow mediators or mediated parties to evaluate the AI ​​outbound call process and service quality; Update AI dialogue strategies in real time based on feedback information.

Images