Rule engine-based intelligent calling seat task allocation and routing system and method

Abstract

The invention discloses an intelligent calling seat task allocation and routing system and method based on a rule engine, and relates to the technical field of communication and computers. The system comprises a task access module, a seat state management module, a rule engine module and a routing decision and execution module. The method comprises the steps of receiving tasks and extracting features; acquiring the real-time state of the seat; intelligent matching and decision making are carried out through a rule engine according to predefined and configurable rules in combination with task features and seat states; and finally, the task is routed to the optimal seat. According to the invention, through a dynamic and flexible rule engine, the defect of stiffness of a traditional routing strategy is overcome, the accuracy, high efficiency and intelligence of call task allocation are realized, and the customer service experience and the seat working efficiency are remarkably improved.

Description

Technical Field

[0001] This invention relates to the fields of communication technology, computer software and artificial intelligence application technology, and in particular to an intelligent task allocation and routing system and method based on a rule engine for call centers. Background Technology

[0002] As enterprise customer service scales continue to expand, call centers have become a vital bridge for communication between businesses and their customers. Traditional call center task allocation often employs static strategies such as simple polling, random selection, or longest idle time based on skill groups. These strategies have the following significant drawbacks: Poor flexibility: It cannot dynamically adjust according to real-time changes in business conditions (such as agent load, customer level, and business urgency).

[0003] Inefficiency: It is difficult to ensure that the most appropriate task is assigned to the most appropriate agent, resulting in increased call duration, reduced problem resolution rate, and decreased customer satisfaction.

[0004] Waste of resources: The inability to optimize the allocation of human resources for agents may result in highly skilled agents handling simple problems, while complex problems are handled by less experienced agents.

[0005] Lack of intelligence: Most existing systems lack the ability to deeply analyze and learn from historical and real-time data, making it impossible to make predictive and adaptive routing decisions.

[0006] Therefore, there is an urgent need in this field for a technical solution that can overcome the above-mentioned defects and achieve intelligent, dynamic, and personalized task allocation and routing. Summary of the Invention

[0007] (a) Purpose of the invention The purpose of this invention is to provide an intelligent call agent task allocation and routing system and method based on a rule engine, to solve the problems of poor flexibility, low efficiency, and resource waste in existing technologies. This invention aims to achieve accurate and efficient allocation of call tasks through a dynamic and configurable rule engine, thereby improving customer satisfaction and agent work efficiency.

[0008] (II) Technical Solution To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides an intelligent call agent task allocation and routing system based on a rule engine, comprising: Task access module: Used to receive customer task requests from various channels (such as telephone, online chat, email, and ticket system) and extract task feature information, including but not limited to: customer identity identifier, customer level, business type, urgency of problem, IVR (Interactive Voice Response) selection result, and historical service records.

[0009] Agent Status Management Module: Used to monitor and maintain the status information of all agents in real time. The status information includes, but is not limited to: agent online / offline status, current call status, skill level, proficiency tag, historical performance data, and current workload (such as the number of tasks processed and the average call duration).

[0010] The rules engine module, as the core of the system, connects to the task access module and the agent status management module, and is used to execute predefined routing rules. This module includes: Rule base: Stores various routing rules configured by administrators through a visual interface. These rules are "condition-action" pairs. For example, a rule could be: "IF Customer level is VIP AND Business type is complaint THEN Prioritize routing to available agents in skill group A with a historical satisfaction rating higher than 4.8 stars."

[0011] Rule executor: Based on task feature information and real-time agent status information, it matches, resolves conflicts, and prioritizes rules in the rule base, and finally calculates the optimal agent matching list or the unique target agent.

[0012] Routing decision and execution module: Connected to the rule engine module, it receives the routing decision results output by the rule engine module and routes the task request to the specified target agent or agent queue.

[0013] Furthermore, the rules engine module also supports the integration of machine learning models. The system can use historical task data and agent performance data as training sets to train predictive models that predict task processing time, customer satisfaction, or success rate. The rules engine can incorporate the model's prediction results as a new "condition" factor into the decision-making process of routing rules, thereby achieving data-driven intelligent routing.

[0014] Secondly, this invention provides a rule engine-based intelligent call agent task allocation and routing method, applied to the aforementioned system, comprising the following steps: S1: Receive customer task requests through the task access module and parse and extract task feature information.

[0015] S2: Obtain real-time status information of all available agents through the agent status management module.

[0016] S3: The rule engine module receives the task feature information and agent status information, loads and executes the routing rules in the rule base.

[0017] S4: The rules engine module generates a sorted list of one or more candidate agents through rule matching, conflict resolution, and priority calculation.

[0018] S5: The routing decision and execution module routes the task request to the highest priority candidate agent according to the sorted list; if the agent is busy or does not answer, it will route the request to the next agent in the list.

[0019] S6: Record the complete process, decision basis, and final result of this routing, for use in subsequent rule optimization and model training.

[0020] (III) Beneficial Effects Compared with the prior art, the present invention has the following significant advantages: Highly flexible and configurable: Through a visual rule configuration interface, business administrators can quickly adjust routing strategies without modifying code, responding to market changes and business needs.

[0021] Precise and efficient allocation: By comprehensively considering multiple dimensions such as task characteristics and agent status, the system achieves optimal matching of "person and task", significantly improving the first call resolution rate and customer satisfaction.

[0022] Maximize resource utilization: Intelligent routing ensures that high-value customers and complex tasks are handled by highly skilled agents, while routine tasks are handled by ordinary agents, thus optimizing human resource allocation.

[0023] Adaptive and intelligent: By integrating machine learning models, the system can learn from historical data and continuously optimize routing strategies, possessing self-learning and adaptive capabilities to continuously improve system performance. Attached Figure Description

[0024] Appendix Figure 1 This is an overall architecture block diagram of the system described in one embodiment of the present invention.

[0025] Appendix Figure 2 This is a flowchart of the method described in one embodiment of the present invention.

[0026] Appendix Figure 3 This is a logical diagram illustrating the rule matching and decision-making process performed by the rule engine in one embodiment of the present invention.

Claims

1. A rule engine based intelligent call agent task assignment and routing system, characterized in that, The application comprises: a task access module for receiving customer task requests and extracting task feature information; a seat state management module for real-time monitoring and maintaining seat state information; a rule engine module connected with the task access module and the seat state management module, the rule engine module comprising a rule base and a rule executor; the rule base is used for storing predefined routing rules; the rule executor is used for executing the routing rules to generate routing decisions according to the task feature information and the seat state information; a routing decision and execution module connected with the rule engine module, for routing the task requests to target seats according to the routing decisions.

2. The system of claim 1, wherein, The task feature information comprises at least one of the following: customer identity, customer level, business type, problem urgency, IVR selection result.

3. The system of claim 1, wherein, The seat state information comprises at least one of the following: seat online / offline state, current call state, skill level, proficiency label, historical performance data, current workload.

4. The system of claim 1, wherein, The rule engine module is further connected with a rule configuration interface for administrators to configure and update the routing rules in the rule base in a visual manner.

5. The system of claim 1, wherein, The rule engine module is further integrated with a machine learning model for predicting task processing results; the rule executor will also use the prediction results of the machine learning model as decision factors when executing routing rules.

6. The system of claim 5, wherein, The prediction results of the machine learning model comprise at least one of the following: predicted task processing time, predicted customer satisfaction, predicted task solution success rate.

7. A rule engine based intelligent call agent task assignment and routing method applied to the system as claimed in any one of claims 1-6, characterized in that, The application comprises the following steps: receiving customer task requests and extracting task feature information; obtaining real-time state information of available seats; inputting the task feature information and seat state information into a rule engine; executing predefined routing rules through the rule engine to generate routing decisions; routing the task requests to target seats according to the routing decisions.

8. The method of claim 7, wherein, The step of "generating routing decisions" comprises: matching routing rules that meet the conditions from the rule base based on the task feature information and seat state information; conflict resolution and priority sorting of the matched routing rules; calculating and outputting a ranking list of one or more candidate seats according to the rule with the highest priority.

9. The method of claim 7, wherein, In the routing decision process, the prediction value of the machine learning model for task processing results is also introduced as a decision basis.

10. The method of claim 7, wherein, The application further comprises the step of recording the task features, seat states, applied rules and routing results of each routing process, and using the recorded data to iteratively optimize the machine learning model or to evaluate and adjust the effect of the rule base.

Images