An artificial intelligence-based semantic clustering conversation intelligent scheduling system and method

Abstract

The application discloses an intelligent scheduling system and method for semantic clustering conversation based on artificial intelligence, relates to the technical field of semantic analysis, and synchronously acquires voice call data and online customer service text flow, adopts an attention mechanism to fuse a joint semantic vector and a user value mapping vector, and generates a context coding vector in combination with a decay factor; an initial topic node is constructed based on the context coding vector, a node weight is dynamically updated through a conversation frequency decay factor, and a topic correlation graph with a weighted edge is generated; for a historical conversation associated with a graph node, a three-dimensional performance model is constructed, a performance score of a customer service reply technique is analyzed, and a knowledge base sorting update is triggered; a value index change rate of a topic node is monitored in real time, when a sudden increase of a high net worth user group associated conversation is detected, a fuse mechanism is automatically triggered and a dedicated agent is dynamically allocated. The application improves the customer service response quality and improves the service experience of users.

Description

Technical Field

[0001] This invention relates to the field of semantic analysis technology, specifically to an artificial intelligence-based semantic clustering conversation intelligent scheduling system and method. Background Technology

[0002] In today's information-saturated world, text data has become a primary means for people to communicate and disseminate information. However, simply relying on keyword matching or surface feature analysis is no longer sufficient to meet the requirements of text understanding. To better understand the deeper meaning of text, semantic analysis technology has emerged.

[0003] Traditional session scheduling and knowledge management rely heavily on static rules and manual maintenance, which cannot effectively cope with business fluctuations and dynamic changes in user groups. Script library updates suffer from long cycles and slow response times. The optimization of high-quality scripts heavily depends on manual analysis, making it impossible to capture the best response strategies in real time. In scenarios of sudden traffic surges or concentrated interactions by high-value users, existing systems struggle to expand dedicated service resources in a timely manner, leading to excessively long user wait times, decreased satisfaction, and increased complaint rates.

[0004] Therefore, this invention discloses an artificial intelligence-based semantic clustering session intelligent scheduling system and method to solve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide an artificial intelligence-based semantic clustering session intelligent scheduling system and method to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent scheduling method for semantic clustering sessions based on artificial intelligence, the method comprising the following steps:

[0007] S1: Simultaneously acquire voice call data and online customer service text stream, use attention mechanism to fuse joint semantic vector and user value mapping vector, and combine with decay factor to generate context encoding vector;

[0008] S2: Construct initial topic nodes based on context encoding vectors, dynamically update node weights through conversation frequency decay factors, calculate the comprehensive value index of topics by combining user level and consumption amount, and generate a topic association graph with weighted edges;

[0009] S3: Based on the historical conversations associated with the graph nodes, a three-dimensional performance model is constructed by integrating the resolution time reduction rate, satisfaction improvement rate, and complaint rate. The performance score of customer service response scripts is analyzed and knowledge base sorting is updated.

[0010] S4: Real-time monitoring of the value index change rate of topic nodes. When a sudden increase in the number of sessions associated with high-net-worth users is detected, the circuit breaker mechanism is automatically triggered and dedicated seats are dynamically allocated.

[0011] According to the above scheme, S1 includes the following:

[0012] S101: After user authorization, collect the user's voice call data and online customer service text data; the voice call data is transcribed into a text sequence in real time using an automatic speech recognition algorithm to obtain a voice-text dialogue sequence with confidence parameters; the customer service text data is a sequence of text messages sent by the user through the online platform; the voice call data and online customer service text data are synchronized and aligned based on timestamps to form a fused text sequence;

[0013] S102: Encode the fused text using a lightweight BERT model to generate a joint semantic vector; extract the user value vector for each user, which includes the normalized values ​​of user level and historical spending amount; perform a sigmoid transformation on the confidence parameter to obtain weight coefficients, and generate a user value mapping vector by weighting the user value vector based on these weight coefficients; input the joint semantic vector as a query and the user value mapping vector as a key and value into a multi-head attention mechanism to output a fused vector; perform a decay transformation on the fused vector using a time decay factor to obtain the final context encoding vector; the time decay factor γ at time t... t =1-exp(-at), where a is the attenuation coefficient, which is a preset constant, and exp() represents an exponential function with the natural number base.

[0014] The attention fusion of lightweight BERT and user value vector in this invention balances semantic understanding efficiency with the need for lightweight models, while introducing user value weights to enable personalized services for high-value users. The time decay factor ensures that the model's dialogue context retains both recent information and historical accumulation, improving the timeliness and accuracy of dialogue responses.

[0015] According to the above scheme, S2 includes the following:

[0016] S201: Analyze the similarity between existing node vectors in the graph and the current context encoding vector. The similarity is equal to the vector product of the node vector and the current context encoding vector divided by the vector length product of the node vector and the current context encoding vector. If the similarity between the current context encoding vector and any node vector is less than the similarity threshold, execute the creation of a new node. Use the current context encoding vector as the initial value of the new node vector. Initialize the attribute information of the new node. The attribute information includes session count, cumulative consumption amount, and average session duration. If the similarity between the current context encoding vector and one of the node vectors is greater than or equal to the similarity threshold, update the attribute information of the current context encoding vector to the node vector with the highest similarity.

[0017] S202: Analyze the value index of nodes based on the attribute information of the updated node vectors, and assign the value index of the i-th node V to... i The value index is denoted as Val i ;

[0018] Update the edge weights of nodes appearing in cross-node sessions. Calculate the edge weights based on the number of cross-node session interactions and the node value index, and then assign the weights to node V. i and V j The edge weight between them is denoted as W. （i，j） :

[0019] ;

[0020] Among them, CSC （i，j） This indicates that node V appears sequentially in the same cross-node session. i and V j The number of times; N j This indicates the presence of node V. j Total number of sessions, Val i V represents j The value index.

[0021] Online incremental construction of conversation graphs enables automatic clustering of conversations with different intent topics without manual intervention; consumption scale and conversation efficiency are jointly incorporated into the indicator system to enhance the ability of graph nodes to characterize real business needs.

[0022] According to the above scheme, S3 includes the following:

[0023] S301: Analyze customer service response scripts at each node, obtain historical session statistics and corresponding baseline values ​​for each script at its respective node. These historical session statistics include average resolution time, average user satisfaction, and complaint rate. Resolution time is the duration from the start of the session to its marked resolution. User satisfaction is determined by a point-based rating system provided to the user after each session. The complaint rate represents the percentage of user complaints arising from customer service response scripts out of the total number of scripts used. A three-dimensional performance model is constructed based on the historical session statistics and baseline values ​​for each customer service response script.

[0024] ;

[0025] Among them, S m TT represents the performance score of the m-th customer service response script within the same node. m csat represents the average resolution time for the m-th customer service response. m R represents the average user satisfaction with the m-th customer service response.m TT represents the complaint rate of the m-th customer service response script; base CSAT base and R base α1, α2, and α3 represent the baseline values ​​for the average resolution time, average user satisfaction, and complaint rate of the m-th customer service response script, respectively; α1, α2, and α3 represent the efficiency coefficients, which are preset constants of the system.

[0026] S302: Integrate the set of performance scores of all historical customer service response scripts under the integrated node; if the performance score of a customer service response script is greater than the product of the maximum performance score of other customer service response scripts and the quality coefficient, mark the customer service response script as a gold script and promote the ranking of the customer service response script to the first position in the knowledge base.

[0027] The automatic evaluation and knowledge base ranking update mechanism for top-performing sales scripts in this invention can automatically promote the best scripts, forming a closed-loop optimization that continuously improves the overall customer service response quality and user satisfaction.

[0028] According to the above scheme, S4 includes the following:

[0029] S401: Real-time monitoring of the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume in each node. If the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume all meet the corresponding thresholds, the dedicated seat allocation mechanism is activated. The threshold for the rate of change of value index is obtained by weighting the peak value of the previous monitoring period with the historical average value. The thresholds for the session ratio and the acceleration of session volume are preset by the system.

[0030] High-net-worth users are those whose total historical spending exceeds a threshold; the session volume acceleration represents the derivative of the rate of change in session volume.

[0031] S402: Assign dedicated seats N based on the normalized value of the node's value index mutation. agent , ;in This represents the floor function, where β1 and β2 are the agent coefficients, which are preset system constants, and ΔVal. norm This represents the normalized value of the node's value index mutation.

[0032] This invention more accurately identifies the sudden needs of high-value user groups, enabling early warning; it calculates trigger thresholds based on weighted historical peak values ​​and average values, adaptively adjusts monitoring standards, and improves the system's sensitivity and robustness to fluctuations in user behavior; based on dedicated agent allocation rules after normalization of value index mutations, it achieves dynamic and flexible management of resource allocation, enabling rapid mobilization of service resources during high-demand periods, significantly reducing user waiting time, and improving the service experience for high-value users.

[0033] Another aspect of this application is an artificial intelligence-based semantic clustering conversation intelligent scheduling system, which is applied to the above-mentioned artificial intelligence-based semantic clustering conversation intelligent scheduling method. The system includes a feature analysis module, a graph update module, a speech ranking optimization module, and an early warning scheduling module.

[0034] The feature analysis module is used to simultaneously acquire voice call data and online customer service text stream, and uses an attention mechanism to fuse joint semantic vectors and user value mapping vectors, and combines a decay factor to generate context encoding vectors.

[0035] The graph update module is used to construct initial topic nodes based on context encoding vectors, dynamically update node weights through session frequency decay factors, calculate the comprehensive value index of topics by combining user level and consumption amount, and generate a topic association graph with weighted edges.

[0036] The script ranking optimization module is used to construct a three-dimensional performance model by integrating the resolution duration reduction rate, satisfaction improvement rate and complaint rate of historical conversations associated with graph nodes, analyze the performance score of customer service response scripts, and trigger knowledge base ranking updates.

[0037] The early warning and scheduling module is used to monitor the change rate of the value index of topic nodes in real time. When a sudden increase in the number of sessions associated with high-net-worth users is detected, the circuit breaker mechanism is automatically triggered and dedicated seats are dynamically allocated.

[0038] According to the above scheme, the feature analysis module includes a text fusion unit and a value fusion unit;

[0039] The text fusion unit is used to collect users' voice call data and online customer service text data, and synchronize the voice call data and online customer service text data based on timestamps to form a fused text sequence.

[0040] The value fusion unit is used to encode the fused text based on the lightweight BERT model, generate a joint semantic vector, extract the user value vector of the corresponding user, generate a user value mapping vector by weighting the user value vector based on the weight coefficient, use the joint semantic vector as a query and the user value mapping vector as a key and value input to a multi-head attention mechanism, and output a fused vector; the fused vector is then subjected to a decay transformation by combining a time decay factor to obtain the final context encoding vector.

[0041] According to the above scheme, the map update module includes a similarity analysis unit and a weight analysis unit;

[0042] The similarity analysis unit is used to analyze the similarity between existing node vectors in the graph and the current context encoding vector. If the similarity between the current context encoding vector and any node vector is less than the similarity threshold, a new node is created. If the similarity between the current context encoding vector and one of the node vectors is greater than or equal to the similarity threshold, the attribute information of the current context encoding vector is updated to the node vector with the highest similarity.

[0043] The weight analysis unit is used to analyze the value index of nodes based on the attribute information of the updated node vectors, update the edge weights of nodes appearing in cross-node sessions, and calculate the edge weights based on the number of cross-node session interactions and the node value index.

[0044] According to the above scheme, the script sorting optimization module includes an efficiency analysis unit and a script optimization unit;

[0045] The performance analysis unit is used to statistically analyze customer service response scripts in each node, obtain historical conversation statistics indicators and corresponding historical conversation statistics indicator benchmark values ​​for each customer service response script in its respective node, construct a three-dimensional performance model based on the historical conversation statistics indicators and historical conversation statistics indicator benchmark values ​​for each customer service response script, and analyze the performance score of the customer service response script based on the three-dimensional performance model.

[0046] The script optimization unit is used to integrate the performance scores of all historical customer service response scripts under the node; if the performance score of a customer service response script is greater than the product of the maximum performance score of other customer service response scripts and the quality coefficient, the customer service response script is marked as a gold script and the ranking of the customer service response script is promoted to the first position in the knowledge base.

[0047] According to the above scheme, the early warning and dispatch module includes a real-time monitoring unit and a seat allocation unit;

[0048] The real-time monitoring unit is used to monitor in real time the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume in each node. If the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume all meet the corresponding threshold, the dedicated seat allocation mechanism is activated.

[0049] The seat allocation unit is used to allocate dedicated seats based on the normalized value of the node's value index mutation.

[0050] Compared with existing technologies, the beneficial effects of this invention are as follows: The attention fusion of lightweight BERT and user value vectors in this invention balances semantic understanding efficiency with the need for lightweight models, while introducing user value weights to enable personalized services for high-value users. The time decay factor ensures that the model's dialogue context retains both recent information and historical accumulation, improving the timeliness and accuracy of dialogue responses. Online incremental construction of the conversation graph enables automatic clustering of conversations with different intent topics without manual intervention. Integrating consumption scale and conversation efficiency into the indicator system enhances the graph nodes' ability to characterize real business needs. The automatic evaluation of top-performing scripts and the knowledge base ranking update mechanism in this invention automatically promotes optimal scripts, forming a closed-loop optimization that continuously improves the overall customer service response quality and user satisfaction. This invention more accurately identifies the sudden needs of high-value user groups, enabling early warning; it calculates trigger thresholds based on weighted historical peak values ​​and average values, adaptively adjusts monitoring standards, and improves the system's sensitivity and robustness to fluctuations in user behavior; based on dedicated agent allocation rules after normalization of value index mutations, it achieves dynamic and flexible management of resource allocation, enabling rapid mobilization of service resources during high-demand periods, significantly reducing user waiting time, and improving the service experience for high-value users. Attached Figure Description

[0051] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0052] Figure 1 This is a flowchart illustrating an artificial intelligence-based semantic clustering session intelligent scheduling method according to the present invention.

[0053] Figure 2 This is a schematic diagram of the structure of an artificial intelligence-based semantic clustering session intelligent scheduling system according to the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Please see Figure 1 This invention provides a technical solution: an intelligent scheduling method for semantic clustering sessions based on artificial intelligence, which includes the following steps:

[0056] S1: Simultaneously acquire voice call data and online customer service text stream, use attention mechanism to fuse joint semantic vector and user value mapping vector, and combine with decay factor to generate context encoding vector;

[0057] S1 includes the following:

[0058] S101: After user authorization, collect user's voice call data and online customer service text data; the voice call data is transcribed into a text sequence in real time using an automatic speech recognition algorithm to obtain a voice-text dialogue sequence with confidence parameters; the customer service text data is a sequence of text messages sent by the user through the online platform; the voice call data and online customer service text data are synchronized and aligned based on timestamps to form a fused text sequence;

[0059] S102: Encode the fused text using a lightweight BERT model to generate a joint semantic vector; extract the user value vector for each user, which includes the normalized values ​​of user level and historical spending amount; perform a sigmoid transformation on the confidence parameter to obtain weight coefficients, and generate a user value mapping vector by weighting the user value vector based on these weight coefficients; input the joint semantic vector as the query and the user value mapping vector as the key and value into a multi-head attention mechanism to output a fused vector; perform a decay transformation on the fused vector using a time decay factor to obtain the final context encoding vector; the time decay factor γ at time t... t =1-exp(-at), where a is the attenuation coefficient, which is a preset constant, and exp() represents an exponential function with the natural number base.

[0060] S2: Construct initial topic nodes based on context encoding vectors, dynamically update node weights through conversation frequency decay factors, calculate the comprehensive value index of topics by combining user level and consumption amount, and generate a topic association graph with weighted edges;

[0061] S2 includes the following:

[0062] S201: Analyze the similarity between existing node vectors in the graph and the current context encoding vector. The similarity is equal to the vector product of the node vector and the current context encoding vector divided by the vector length product of the node vector and the current context encoding vector. If the similarity between the current context encoding vector and any node vector is less than the similarity threshold, execute the creation of a new node. Use the current context encoding vector as the initial value of the new node vector. Initialize the attribute information of the new node. The attribute information includes session count, cumulative consumption amount, and average session duration. If the similarity between the current context encoding vector and one of the node vectors is greater than or equal to the similarity threshold, update the attribute information of the current context encoding vector to the node vector with the highest similarity.

[0063] Example 1: S202: Analyze the value index of the node based on the attribute information of the updated node vector, and set the value index of the i-th node V. i The value index is denoted as Val i In this embodiment, the value index Val i The calculation formula is as follows:

[0064] ;

[0065] Where, N i This indicates the presence of node V. i The total number of sessions, n∈[1,N] i ], where n is a positive integer; c n This indicates the presence of node V. i The user's spending amount in the nth session, T i This indicates the presence of node V. i The average session duration; session duration is the time from the initiation of a session to its formal closure. Session duration includes the time spent on reviewing, quality checking, and user confirmation for session records marked as resolved; the review stage refers to the review process triggered automatically by reviewers with customer service management authority or by the system; the quality checking stage is the stage where, after the review is passed, the quality checking system or quality checking personnel conduct a metric-based evaluation of the session quality; the user confirmation stage is the stage where, after the quality checking is passed, the system initiates a second confirmation with the user to solicit the user's final approval of the problem resolution.

[0066] Update the edge weights of nodes appearing in cross-node sessions. Calculate the edge weights based on the number of cross-node session interactions and the node value index, and then assign the weights to node V. i and V j The edge weight between them is denoted as W. （i，j） :

[0067] ;

[0068] Among them, CSC （i，j）This indicates that node V appears sequentially in the same cross-node session. i and V j The number of times; N j This indicates the presence of node V. j Total number of sessions, Val i V represents j The value index.

[0069] S3: Based on the historical conversations associated with the graph nodes, a three-dimensional performance model is constructed by integrating the resolution time reduction rate, satisfaction improvement rate, and complaint rate. The performance score of customer service response scripts is analyzed and knowledge base sorting is updated.

[0070] S3 includes the following:

[0071] S301: Analyze customer service response scripts at each node, obtain historical session statistics and corresponding baseline values ​​for each script at its respective node. Historical session statistics include average resolution time, average user satisfaction, and complaint rate. Resolution time is the duration from the start of the session to its marked resolution. User satisfaction is determined by the system pushing a satisfaction rating interface to the user after each session, where the user provides a point-based rating. The complaint rate is the percentage of user complaints arising from customer service response scripts out of the total number of times those scripts are used. Based on the historical session statistics and baseline values ​​for each customer service response script, construct a three-dimensional performance model:

[0072] ;

[0073] Among them, S m TT represents the performance score of the m-th customer service response script within the same node. m csat represents the average resolution time for the m-th customer service response. m R represents the average user satisfaction with the m-th customer service response. m TT represents the complaint rate of the m-th customer service response script; base CSAT base and R base α1, α2, and α3 represent the baseline values ​​for the average resolution time, average user satisfaction, and complaint rate of the m-th customer service response script, respectively; α1, α2, and α3 represent the efficiency coefficients, which are system preset constants.

[0074] Example 2: In this example, the average resolution time benchmark is obtained through the P90 quantile, the average user satisfaction benchmark is a system preset constant, and the complaint rate benchmark is equal to the complaint rate multiplied by the total consumption amount of users associated with the current topic divided by the regional benchmark consumption amount.

[0075] S302: Integrate the set of performance scores of all historical customer service response scripts under the integrated node; if the performance score of a customer service response script is greater than the product of the maximum performance score of other customer service response scripts and the quality coefficient, mark the customer service response script as a gold script and promote the customer service response script to the first position in the knowledge base.

[0076] S4: Real-time monitoring of the value index change rate of topic nodes. When a sudden increase in the number of sessions associated with high-net-worth users is detected, the circuit breaker mechanism is automatically triggered and dedicated seats are dynamically allocated.

[0077] S4 includes the following:

[0078] S401: Real-time monitoring of the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume in each node. If the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume all meet the corresponding thresholds, the dedicated seat allocation mechanism is activated. The threshold for the rate of change of value index is obtained by weighting the peak value of the previous monitoring period with the historical average value. The thresholds for the session ratio and the acceleration of session volume are preset by the system.

[0079] S402: Assign dedicated seats N based on the normalized value of the node's value index mutation. agent , ;in This represents the floor function, where β1 and β2 are the agent coefficients, which are preset system constants, and ΔVal. norm This represents the normalized value of the node's value index mutation.

[0080] Please see Figure 2 The present invention provides a technical solution: an artificial intelligence-based semantic clustering conversation intelligent scheduling system, which includes a feature analysis module, a graph update module, a speech sorting optimization module, and an early warning scheduling module;

[0081] The feature analysis module is used to simultaneously acquire voice call data and online customer service text streams. It uses an attention mechanism to fuse joint semantic vectors and user value mapping vectors, and combines a decay factor to generate context encoding vectors.

[0082] The graph update module is used to construct initial topic nodes based on context encoding vectors, dynamically update node weights through session frequency decay factors, calculate the comprehensive value index of topics by combining user level and consumption amount, and generate a topic association graph with weighted edges.

[0083] The script ranking optimization module is used to construct a three-dimensional performance model by integrating the resolution duration reduction rate, satisfaction improvement rate and complaint rate of historical conversations associated with graph nodes, analyze the performance score of customer service response scripts, and trigger knowledge base ranking updates.

[0084] The early warning and scheduling module is used to monitor the change rate of the value index of topic nodes in real time. When a sudden increase in the number of sessions associated with high-net-worth users is detected, the circuit breaker mechanism is automatically triggered and dedicated seats are dynamically allocated.

[0085] The feature analysis module includes a text fusion unit and a value fusion unit;

[0086] The text fusion unit is used to collect users’ voice call data and online customer service text data, and synchronizes the voice call data and online customer service text data based on timestamps to form a fused text sequence.

[0087] The value fusion unit is used to encode the fused text based on the lightweight BERT model, generate a joint semantic vector, extract the user value vector of the corresponding user, generate a user value mapping vector by weighting the user value vector based on the weight coefficient, use the joint semantic vector as the query and the user value mapping vector as the key and value input to the multi-head attention mechanism, and output the fused vector; the fused vector is then subjected to a decay transformation by combining a time decay factor to obtain the final context encoding vector.

[0088] The map update module includes a similarity analysis unit and a weight analysis unit;

[0089] The similarity analysis unit is used to analyze the similarity between existing node vectors in the graph and the current context encoding vector. If the similarity between the current context encoding vector and any node vector is less than the similarity threshold, a new node is created. If the similarity between the current context encoding vector and one of the node vectors is greater than or equal to the similarity threshold, the attribute information of the current context encoding vector is updated to the node vector with the highest similarity.

[0090] The weight analysis unit is used to analyze the value index of nodes based on the attribute information of the updated node vectors, update the edge weights of nodes appearing in cross-node sessions, and calculate the edge weights based on the number of cross-node session interactions and the node value index.

[0091] The script ranking optimization module includes a performance analysis unit and a script optimization unit;

[0092] The performance analysis unit is used to statistically analyze customer service response scripts at each node, obtain historical conversation statistics indicators and corresponding historical conversation statistics benchmark values ​​for each customer service response script at its respective node, construct a three-dimensional performance model based on the historical conversation statistics indicators and historical conversation statistics benchmark values ​​for each customer service response script, and analyze the performance score of the customer service response script based on the three-dimensional performance model.

[0093] The script optimization unit is used to integrate the performance scores of all historical customer service response scripts under a node. If the performance score of a customer service response script is greater than the product of the maximum performance score of other customer service response scripts and the quality coefficient, the customer service response script is marked as a gold script and its ranking is promoted to the first position in the knowledge base.

[0094] The early warning and dispatch module includes a real-time monitoring unit and a seat allocation unit;

[0095] The real-time monitoring unit is used to monitor in real time the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume in each node. If the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume all meet the corresponding threshold, the dedicated seat allocation mechanism is activated.

[0096] The seat allocation unit is used to allocate dedicated seats based on the normalized value of the node's value index mutation.

[0097] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0098] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An intelligent scheduling method for semantic clustering sessions based on artificial intelligence, characterized in that, The method includes the following steps: S1: Simultaneously acquire voice call data and online customer service text stream, use attention mechanism to fuse joint semantic vector and user value mapping vector, and combine with decay factor to generate context encoding vector; S2: Construct initial topic nodes based on context encoding vectors, dynamically update node weights through conversation frequency decay factors, calculate the comprehensive value index of topics by combining user level and consumption amount, and generate a topic association graph with weighted edges; S3: Based on the historical conversations associated with the graph nodes, a three-dimensional performance model is constructed by integrating the resolution time reduction rate, satisfaction improvement rate, and complaint rate. The performance score of customer service response scripts is analyzed and knowledge base sorting is updated. S3 includes the following: S301: Statistically analyze customer service response scripts in each node, obtain historical session statistics indicators and corresponding historical session statistics indicator baseline values ​​for each customer service response script in its respective node. The historical session statistics indicators include average resolution time, average user satisfaction, and complaint rate. The resolution time is the time from the initiation of the session to the point where it is marked as resolved. The user satisfaction rate is determined by the system pushing a satisfaction evaluation interface to the user after each session, where the user provides a point-based rating; the complaint rate is the percentage of user complaints caused by customer service response scripts out of the total number of times customer service response scripts are used; a three-dimensional performance model is constructed based on the historical session statistical indicators and the baseline values ​​of the historical session statistical indicators for each customer service response script. S302: Integrate the set of performance scores of all historical customer service response scripts under the integrated node; if the performance score of a customer service response script is greater than the product of the maximum performance score of other customer service response scripts and the quality coefficient, mark the customer service response script as a gold script and promote the ranking of the customer service response script to the first place in the knowledge base. S4: Real-time monitoring of the value index change rate of topic nodes. When a sudden increase in the number of sessions associated with high-net-worth users is detected, the circuit breaker mechanism is automatically triggered and dedicated seats are dynamically allocated.

2. The method for intelligent scheduling of semantic clustering sessions based on artificial intelligence according to claim 1, characterized in that: S1 includes the following: S101: After user authorization, collect the user's voice call data and online customer service text data; the voice call data is transcribed into a text sequence in real time using an automatic speech recognition algorithm to obtain a voice-text dialogue sequence with confidence parameters; the customer service text data is a sequence of text messages sent by the user through the online platform; the voice call data and online customer service text data are synchronized and aligned based on timestamps to form a fused text sequence; S102: Encode the fused text using a lightweight BERT model to generate a joint semantic vector; extract the user value vector for each user, which includes the normalized values ​​of user level and historical spending amount; perform a sigmoid transformation on the confidence parameter to obtain weight coefficients, and generate a user value mapping vector by weighting the user value vector based on these weight coefficients; input the joint semantic vector as a query and the user value mapping vector as a key and value into a multi-head attention mechanism to output a fused vector; perform a decay transformation on the fused vector using a time decay factor to obtain the final context encoding vector; the time decay factor γ at time t... t =1-exp(-at), where a is the attenuation coefficient, which is a preset constant, and exp() represents an exponential function with the natural number base.

3. The method for intelligent scheduling of semantic clustering sessions based on artificial intelligence according to claim 2, characterized in that: S2 includes the following: S201: Analyze the similarity between existing node vectors in the graph and the current context encoding vector. The similarity is equal to the vector product of the node vector and the current context encoding vector divided by the vector length product of the node vector and the current context encoding vector. If the similarity between the current context encoding vector and any node vector is less than the similarity threshold, execute the creation of a new node. Use the current context encoding vector as the initial value of the new node vector. Initialize the attribute information of the new node. The attribute information includes session count, cumulative consumption amount, and average session duration. If the similarity between the current context encoding vector and one of the node vectors is greater than or equal to the similarity threshold, update the attribute information of the current context encoding vector to the node vector with the highest similarity. S202: Analyze the value index of nodes based on the attribute information of the updated node vectors, and assign the value index of the i-th node V to... i The value index is denoted as Val i ; Update the edge weights of nodes appearing in cross-node sessions, and calculate the edge weights based on the number of cross-node session interactions and the node value index.

4. The semantic clustering session intelligent scheduling method based on artificial intelligence according to claim 3, characterized in that: S4 includes the following: S401: Real-time monitoring of the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume in each node. If the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume all meet the corresponding thresholds, the dedicated seat allocation mechanism is activated. The threshold for the rate of change of value index is obtained by weighting the peak value of the previous monitoring period with the historical average value. The thresholds for the session ratio and the acceleration of session volume are preset by the system. S402: Assign dedicated seats N based on the normalized value of the node's value index mutation. agent , ;in This represents the floor function, where β1 and β2 are the agent coefficients, which are preset system constants, and ΔVal. norm This represents the normalized value of the node's value index mutation.

5. An artificial intelligence-based semantic clustering session intelligent scheduling system, wherein the system is applied to the implementation of the artificial intelligence-based semantic clustering session intelligent scheduling method according to any one of claims 1-4, characterized in that, The system includes a feature analysis module, a graph update module, a speech sorting optimization module, and an early warning and scheduling module; The feature analysis module is used to simultaneously acquire voice call data and online customer service text stream, and uses an attention mechanism to fuse joint semantic vectors and user value mapping vectors, and combines a decay factor to generate context encoding vectors. The graph update module is used to construct initial topic nodes based on context encoding vectors, dynamically update node weights through session frequency decay factors, calculate the comprehensive value index of topics by combining user level and consumption amount, and generate a topic association graph with weighted edges. The script ranking optimization module is used to construct a three-dimensional performance model by integrating the resolution duration reduction rate, satisfaction improvement rate and complaint rate of historical conversations associated with graph nodes, analyze the performance score of customer service response scripts, and trigger knowledge base ranking updates. The early warning and scheduling module is used to monitor the change rate of the value index of topic nodes in real time. When a sudden increase in the number of sessions associated with high-net-worth users is detected, the circuit breaker mechanism is automatically triggered and dedicated seats are dynamically allocated.

6. The semantic clustering session intelligent scheduling system based on artificial intelligence according to claim 5, characterized in that: The feature analysis module includes a text fusion unit and a value fusion unit; The text fusion unit is used to collect users' voice call data and online customer service text data, and synchronize the voice call data and online customer service text data based on timestamps to form a fused text sequence. The value fusion unit is used to encode the fused text based on the lightweight BERT model, generate a joint semantic vector, extract the user value vector of the corresponding user, generate a user value mapping vector by weighting the user value vector based on the weight coefficient, use the joint semantic vector as a query and the user value mapping vector as a key and value input to a multi-head attention mechanism, and output a fused vector; the fused vector is then subjected to a decay transformation by combining a time decay factor to obtain the final context encoding vector.

7. The semantic clustering session intelligent scheduling system based on artificial intelligence according to claim 5, characterized in that: The map update module includes a similarity analysis unit and a weight analysis unit; The similarity analysis unit is used to analyze the similarity between existing node vectors in the graph and the current context encoding vector. If the similarity between the current context encoding vector and any node vector is less than the similarity threshold, a new node is created. If the similarity between the current context encoding vector and one of the node vectors is greater than or equal to the similarity threshold, the attribute information of the current context encoding vector is updated to the node vector with the highest similarity. The weight analysis unit is used to analyze the value index of nodes based on the attribute information of the updated node vectors, update the edge weights of nodes appearing in cross-node sessions, and calculate the edge weights based on the number of cross-node session interactions and the node value index.

8. The semantic clustering session intelligent scheduling system based on artificial intelligence according to claim 5, characterized in that: The script sorting and optimization module includes a performance analysis unit and a script optimization unit; The performance analysis unit is used to statistically analyze customer service response scripts in each node, obtain historical conversation statistics indicators and corresponding historical conversation statistics indicator benchmark values ​​for each customer service response script in its respective node, construct a three-dimensional performance model based on the historical conversation statistics indicators and historical conversation statistics indicator benchmark values ​​for each customer service response script, and analyze the performance score of the customer service response script based on the three-dimensional performance model. The script optimization unit is used to integrate the performance scores of all historical customer service response scripts under the node; if the performance score of a customer service response script is greater than the product of the maximum performance score of other customer service response scripts and the quality coefficient, the customer service response script is marked as a gold script and the ranking of the customer service response script is promoted to the first position in the knowledge base.

9. The semantic clustering session intelligent scheduling system based on artificial intelligence according to claim 5, characterized in that: The early warning and dispatch module includes a real-time monitoring unit and a seat allocation unit; The real-time monitoring unit is used to monitor in real time the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume in each node. If the ratio of high-net-worth user group sessions to the total sessions of the node, the rate of change of value index, and the acceleration of session volume all meet the corresponding threshold, the dedicated seat allocation mechanism is activated. The seat allocation unit is used to allocate dedicated seats based on the normalized value of the node's value index mutation.

Images