Call route matching method and device based on double tags

Abstract

The invention provides a call route matching method based on double tags. The call route matching method can be applied to the technical field of artificial intelligence and big data. The method comprises the following steps: in response to a call request, obtaining at least one user dynamic label of a user and at least one seat dynamic label of each seat in a target seat group corresponding to the call request, the target seat group being determined according to a preset static routing rule; the seat dynamic tag and the user dynamic tag are used for representing feature data of an instant state, short-term behavior preference or a real-time analysis result; determining at least one target matched seat in the target seat group according to a preset label matching rule, the user dynamic label and the seat dynamic label; and routing the call request of the user to the target matching seat. The invention further provides a call route matching device and equipment based on the double tags, a storage medium and a program product.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, specifically to the field of big data technology, and more specifically to a dual-label-based call routing matching method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, call center systems (such as bank customer service hotlines) generally employ static rule-based routing strategies. For example, based on the customer's region, the service type selected through the interactive voice response menu, or the incoming call number's attributes, the incoming circuit is routed to the corresponding agent skill group (i.e., the target agent group). However, after group-level routing is completed, the allocation of agents within the group is usually randomized based solely on agent availability or simple queuing rules. This crude "service → role group" routing completely ignores the individual customer's immediate needs, emotional state, value preferences, and other personalized characteristics. It also fails to fully consider the agent's expertise, experience, and real-time service capabilities, resulting in poor customer experience, inefficient use of agent resources, and difficulty in effectively improving service quality and customer satisfaction. Summary of the Invention

[0003] In view of the above problems, this application provides a method, apparatus, electronic device and storage medium for call routing matching based on dual tags.

[0004] According to a first aspect of this application, a call routing matching method based on dual tags is provided, comprising: in response to a call request, obtaining at least one user dynamic tag of a user and at least one agent dynamic tag of each agent in a target agent group corresponding to the call request, wherein the target agent group is determined according to a preset static routing rule, and the agent dynamic tag and the user dynamic tag are used to characterize feature data representing immediate status, short-term behavioral preferences, or real-time analysis results; determining at least one target matching agent in the target agent group according to a preset tag matching rule, the user dynamic tag, and the agent dynamic tag; and routing the user's call request to the target matching agent.

[0005] According to an embodiment of this application, the preset tag matching rule includes a predefined mapping relationship between user dynamic tag types and agent dynamic tag types, and corresponding priority weights; the step of determining at least one target matching agent in the target agent group based on the preset tag matching rule, the user dynamic tags, and the agent dynamic tags includes: for each agent in the target agent group, identifying the matching status between the agent dynamic tag and the user dynamic tag; calculating the comprehensive matching degree between each agent and the user based on the matching status and the corresponding priority weights; sorting the agents in the target agent skill group based on the comprehensive matching degree, and determining the agents whose sorting meets preset conditions as the target matching agents.

[0006] According to an embodiment of this application, identifying the matching status of the agent dynamic tag and the user dynamic tag includes: filtering out agents who satisfy the mapping relationship with all the user dynamic tags as a priority candidate set; and if the priority candidate set is empty, filtering out agents who satisfy the mapping relationship with at least one of the user dynamic tags as a secondary candidate set. Calculating the overall matching degree between each agent and the user based on the matching status and the corresponding priority weight includes: if the priority candidate set is determined to be non-empty, calculating the overall matching degree between the agent and the user for each agent in the priority candidate set based on the matching status of the agent dynamic tag and the user dynamic tag and the corresponding priority weight; if the priority candidate set is determined to be empty, calculating the overall matching degree between the agent and the user for each agent in the secondary candidate set based on the matching status of the agent dynamic tag and the user dynamic tag and the corresponding priority weight.

[0007] According to an embodiment of this application, the preset tag matching rule is implemented through a configurable rule engine; the method further includes: in response to a configuration operation, establishing, modifying or deleting a matching mapping relationship between user dynamic tag types and agent dynamic tag types.

[0008] According to an embodiment of this application, the method further includes: if it is determined that all the target matching agents are in a non-idle state, assigning the call request to any currently idle available agent within the target agent group.

[0009] According to an embodiment of this application, obtaining at least one user dynamic tag for a user includes: with the user's authorization, collecting multi-dimensional source data of the user, the multi-dimensional source data including at least one of records in the user's historical behavior database, real-time interaction data stream, and pre-configured preference settings information; performing at least one analysis and processing operation on the multi-dimensional source data, the analysis and processing operation including: mining and analysis of historical behavior records, voice sentiment analysis or semantic intent recognition of the real-time interaction data stream; and determining the user dynamic tag based on the result output by the analysis and processing operation.

[0010] According to an embodiment of this application, obtaining agent dynamic tags includes: periodically collecting agent service quality data within a preset time period, wherein the service quality data includes at least one of: call recording quality inspection scores, user feedback satisfaction evaluations, average session processing time, and skill certification results; and determining the agent dynamic tags based on the service quality data.

[0011] According to an embodiment of this application, the method further includes: collecting performance evaluation data associated with the call service when the target matched agent completes the current call service; and adjusting the corresponding weights in the mapping relationship between user dynamic tag types and agent dynamic tag types based on the performance evaluation data.

[0012] A second aspect of this application provides a call routing matching device based on dual tags. The device includes: an acquisition module, configured to acquire, in response to a call request, at least one user dynamic tag of a user and at least one agent dynamic tag of each agent in a target agent group corresponding to the call request, wherein the target agent group is determined according to preset static routing rules, and the agent dynamic tags and the user dynamic tags are used to characterize feature data representing immediate status, short-term behavioral preferences, or real-time analysis results; a matching module, configured to determine at least one target matching agent in the target agent group according to preset tag matching rules, the user dynamic tags, and the agent dynamic tags; and a call routing module, configured to route the user's call request to the target matching agent. According to an embodiment of this application, the resource scheduling module includes a conversion submodule and a first generation submodule.

[0013] According to an embodiment of this application, the matching module includes: a matching submodule, a calculation submodule, and a first determination submodule.

[0014] The matching submodule is used to identify the matching status between the agent's dynamic tag and the user's dynamic tag for each agent in the target agent group; the calculation submodule is used to calculate the comprehensive matching degree between each agent and the user based on the matching status and the corresponding priority weight; the determination submodule is used to sort the agents in the target agent skill group according to the comprehensive matching degree, and determine the agents whose sorting meets the preset conditions as the target matched agents.

[0015] According to an embodiment of this application, the matching module further includes: a first filtering submodule and a second filtering submodule.

[0016] The first filtering submodule is used to filter out agents that satisfy the mapping relationship with all of the user dynamic tags as a priority candidate set; the second filtering submodule is used to filter out agents that satisfy the mapping relationship with at least one of the user dynamic tags as a secondary candidate set if the priority candidate set is empty.

[0017] According to an embodiment of this application, the apparatus further includes: a configuration module, configured to establish, modify, or delete a mapping relationship between user dynamic tag types and agent dynamic tag types in response to a configuration operation.

[0018] According to an embodiment of this application, the apparatus further includes: a rerouting module, configured to, if it is determined that all the target matching agents are in a non-idle state, assign the call request to any currently idle available agent within the target agent group.

[0019] According to an embodiment of this application, the acquisition module is further configured to collect multi-dimensional source data of the user with the user's authorization, wherein the multi-dimensional source data includes at least one of records in the user's historical behavior database, real-time interactive data stream, and pre-configured preference settings information; perform at least one analysis and processing operation on the multi-dimensional source data, wherein the analysis and processing operation includes: mining and analysis of historical behavior records, voice sentiment analysis or semantic intent recognition of the real-time interactive data stream; and determine the user's dynamic tag based on the result output by the analysis and processing operation.

[0020] According to an embodiment of this application, the acquisition module is further configured to periodically collect service quality data of agents within a preset time period, the service quality data including at least one of: call recording quality inspection score, user feedback satisfaction evaluation, average session processing time, and skill certification results; and determine the agent's dynamic tag based on the service quality data.

[0021] According to an embodiment of this application, the device further includes a collection module and an adjustment module.

[0022] The collection module is used to collect performance evaluation data associated with the call service when the target matched agent completes the call service; the adjustment module is used to adjust the priority weights in the mapping relationship between user dynamic tag types and agent dynamic tag types based on the performance evaluation data.

[0023] A third aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0024] A fourth aspect of this application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0025] The fifth aspect of this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method. Attached Figure Description

[0026] The above-mentioned contents, other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0027] Figure 1 This illustration schematically depicts an application scenario of a dual-label-based call routing matching method according to an embodiment of this application.

[0028] Figure 2 A flowchart illustrating a dual-label-based call routing matching method according to an embodiment of this application is shown schematically.

[0029] Figure 3 A flowchart illustrating a dual-label-based call routing matching method according to another embodiment of this application is shown schematically;

[0030] Figure 4 A schematic diagram illustrates a structural block diagram of a dual-tag-based call routing matching device according to an embodiment of this application; and

[0031] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a dual-tag-based call routing matching method according to an embodiment of this application. Detailed Implementation

[0032] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0033] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0034] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0035] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0036] In the technical solution of this application, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0037] In scenarios involving automated decision-making using personal information, the methods, devices, and systems provided in this application all offer users corresponding entry points for choosing to agree to or reject the automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making stage. Here, "automated decision-making" refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests, or economic, health, and credit status through computer programs, and then making a decision. Here, "expert decision-making" refers to the activity of making decisions by personnel who specialize in a particular field, possess specialized experience, knowledge, and skills, and have reached a certain level of professional expertise.

[0038] In the technical solution of this application, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0039] In scenarios involving automated decision-making using personal information, the methods, devices, and systems provided in this application all offer users corresponding entry points for choosing to agree to or reject the automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making stage. Here, "automated decision-making" refers to activities that automatically analyze and evaluate an individual's behavioral habits, interests, or economic, health, and credit status through computer programs, and then make decisions. Here, "expert decision-making" refers to activities where individuals specializing in a particular field, possessing specialized experience, knowledge, and skills, and reaching a certain level of professional expertise make decisions.

[0040] This application provides a dual-label-based call routing matching method, comprising: in response to a call request, obtaining at least one user dynamic label of a user and at least one agent dynamic label of each agent in a target agent group corresponding to the call request, wherein the target agent group is determined according to a preset static routing rule, and the agent dynamic label and the user dynamic label are used to characterize feature data representing immediate status, short-term behavioral preferences, or real-time analysis results; determining at least one target matching agent in the target agent group according to the preset label matching rule, the user dynamic label, and the agent dynamic label; and routing the user's call request to the target matching agent.

[0041] Figure 1 The diagram illustrates an application scenario of a dual-label-based call routing matching method according to an embodiment of this application.

[0042] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0043] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as web browser applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0044] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0045] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0046] It should be noted that the dual-label-based call routing matching method provided in this disclosure embodiment can generally be executed by server 105. Correspondingly, the dual-label-based call routing matching device provided in this disclosure embodiment can generally be located in server 105. The dual-label-based call routing matching method provided in this disclosure embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the dual-label-based call routing matching device provided in this disclosure embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0047] It should be understood that Figure 1The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0048] The following will be based on Figure 1 The described scene, through Figures 2-4 The dual-label-based call routing matching method according to embodiments of this application will be described in detail.

[0049] Figure 2 A flowchart illustrating a dual-label-based call routing matching method according to an embodiment of this application is shown.

[0050] like Figure 2 As shown, the dual-label-based call routing matching method of this embodiment includes operations S210 to S260, which can be executed by a server or a terminal device.

[0051] In operation S210, in response to a call request, at least one user dynamic tag of the user and at least one agent dynamic tag of each agent in the target agent group corresponding to the call request are obtained.

[0052] According to an embodiment of this application, the target agent group is determined based on a preset static routing rule, and the agent dynamic tag and the user dynamic tag are used to characterize feature data representing immediate status, short-term behavioral preferences, or real-time analysis results.

[0053] In operation S220, at least one target matching agent is determined in the target agent group according to the preset tag matching rules, the user dynamic tags, and the agent dynamic tags.

[0054] In operation S230, the user's call request is routed to the target matching agent.

[0055] In one example, taking a banking scenario, a customer calls the customer service hotline to conduct business and selects "credit card business consultation" through the Interactive Voice Response (IVR) system. The system then executes preset static routing rules. These rules are typically based on a combination of the following objective, static parameters:

[0056] Customer's location: The system identifies the customer as being located in "Shanghai" based on the origin of the caller ID number.

[0057] The IVR selected the following service type: "Credit Card Business Consultation".

[0058] Incoming number attribute: The customer dialed a regular customer hotline.

[0059] Based on the above parameters, the system's static routing engine determines that this call should be assigned to the "Shanghai Branch - Credit Card Consultation Skills Group." This skills group is the target agent group in this application. This step fully inherits the existing mature and stable routing framework, ensuring that the call is first correctly guided to a professional team capable of handling this type of business.

[0060] In one example, after identifying the target agent group, the system initiates an intelligent matching process, the core of which is obtaining dynamic user tags and agent tags. To obtain user tags, the system queries the customer's tag library in real time. These tags are not fixed but rather feature data representing immediate status, short-term behavioral preferences, or real-time analysis results. For example, the system obtains user tags by linking to the customer profiling system: "Has a card delinquency record within the past week (short-term behavior)," "Voice sentiment analysis during this IVR interaction shows a high anxiety index (immediate status)," and "Historical average transaction value indicates a high-potential customer (analysis results based on recent transactions)." The system then queries the personal ability tag library of all currently available agents within the target agent group. These tags are also time-sensitive, dynamically reflecting their latest expertise and status. For example, Agent A has the tags: "Proficient in handling credit card delinquencies and negotiation (expertise)" and "Strong communication and reassurance skills (based on recent customer reviews)"; Agent B's tags are: "New credit card promotion expert" and "High processing efficiency."

[0061] In one example, the system inputs the aforementioned dynamic tag data into preset tag matching rules for calculation. The rules identify that the customer's "emotional anxiety" and involvement in "overdue payments" highly match the tags of Agent A's "skilled in handling overdue payments" and "strong communication and reassurance abilities," resulting in the highest match score. Therefore, the system identifies Agent A as the target matching agent. Ultimately, the system routes the customer's call request directly to Agent A, rather than randomly assigning it within the group.

[0062] The dual-label-based call routing matching method provided in this application transforms traditional coarse-grained routing into intelligent and refined services by constructing a hierarchical routing decision-making process. First, the method directs call requests to the correct target agent group based on preset static routing rules, ensuring basic routing accuracy and business professionalism. Then, within that group, dynamic dual labels representing immediate status and short-term characteristics are acquired and utilized to digitally map the customer's specific real-time needs to the agent's latest adaptability. Precise matching and routing within the group are then completed based on preset label matching rules. This process systematically solves the problems of randomized allocation within groups and neglect of individual real-time status and demand differences in existing technologies. Therefore, while ensuring routing reliability, it significantly improves service personalization, first-time problem resolution rate, and agent resource allocation efficiency.

[0063] Figure 3A flowchart illustrating a dual-label-based call routing matching method according to another embodiment of this application is shown. Figure 3 As shown, this includes operations S310 to S330.

[0064] In operation S310, for each agent in the target agent group, the matching status of the agent dynamic tag and the user dynamic tag is identified.

[0065] The preset tag matching rules include a predefined mapping relationship between user dynamic tag types and agent dynamic tag types, and the corresponding priority weights;

[0066] In operation S320, the overall matching degree between each agent and the user is calculated based on the matching situation and the corresponding priority weight.

[0067] In operation S330, the seats in the target seat skill group are sorted according to the comprehensive matching degree, and the seats that meet the preset conditions are determined as the target matching seats.

[0068] In one example, the system has identified the target agent group as "Shanghai Branch - Credit Card Consultation Skills Group" and obtained the customer's dynamic user tag set as {"Has a card delinquency record within the past week", "High emotional anxiety index", "High potential customer"}. Simultaneously, there are three available agents (A, B, and C) within the target group, with the following dynamic tags: Agent A: {"Skilled in handling credit card delinquencies and negotiations", "Strong communication and reassurance skills"}; Agent B: {"New credit card promotion expert", "High processing efficiency"}; Agent C: {"Familiar with high-end customer service processes", "Skilled in handling credit card delinquencies and negotiations"}. The system executes the following weighted, fine-grained matching process:

[0069] The system uses a predefined tag matching rule, the core of which is a predefined "tag type mapping relationship and weight table". For example, mapping relationship R1: User tag "Has a card overdue record within the past week" → Agent tag "Skilled in handling credit card overdue payments and negotiation", weight W1=0.5. Mapping relationship R2: User tag "High emotional anxiety index" → Agent tag "Strong communication and reassurance skills", weight W2=0.3. Mapping relationship R3: User tag "High-potential customer" → Agent tag "Familiar with high-end customer service processes", weight W3=0.2. The system compares the customer tags with the tags of each agent to identify valid mapping relationships: For Agent A: both R1 and R2 are matched.

[0070] For Agent B: No pre-defined mapping was matched. For Agent C: R1 and R3 were matched.

[0071] Calculate the overall matching score: Based on the identified matching relationships and their weights, calculate the overall matching score between each agent and the customer. Agent A's overall matching score = W1 + W2 = 0.5 + 0.3 = 0.8. Agent B's overall matching score = 0. Agent C's overall matching score = W1 + W3 = 0.5 + 0.2 = 0.7. The system sorts Agents A, B, and C in descending order of their overall matching scores, resulting in: Agent A (0.8) > Agent C (0.7) > Agent B (0). Assuming the "preset condition" is to select the agent ranked first, the system determines Agent A as the target matching agent for this call.

[0072] By using predefined mapping relationships and priority weights, the system not only determines the presence or absence of tags but also assesses the relative importance of different matching dimensions. The comprehensive matching score provides a precise quantitative indicator, giving a clear basis for decision-making when selecting the optimal candidate seats from among multiple candidates. Finally, the ranking and filtering based on this metric ensures that each routing is based on the most scientific evaluation results under the current conditions, improving the rationality and consistency of resource allocation decisions.

[0073] According to an embodiment of this application, identifying the matching status of the agent dynamic tag and the user dynamic tag includes: filtering out agents who satisfy the mapping relationship with all the user dynamic tags as a priority candidate set; if the priority candidate set is empty, filtering out agents who satisfy the mapping relationship with at least one of the user dynamic tags as a secondary candidate set.

[0074] In one example, the user's dynamic tag set is identified as: {"Preference for Cantonese services", "Inquiry about overseas credit card fraud", "Stable mood"}. The preset tag matching rules define the following mapping relationships and weights:

[0075] Customer tag "Prefers Cantonese service" → Agent tag "Proficient in Cantonese", weight = 0.4; Customer tag "Consults about overseas credit card fraud" → Agent tag "Credit card fraud handling expert", weight = 0.4; Customer tag "Emotionally stable" → Agent tag "Good service attitude", weight = 0.2.

[0076] There are currently five available seats in the target agent group (e.g., "Shenzhen Branch - Credit Card Anti-Fraud Group"), with the following labels: Seat W: {"Fluent in Cantonese", "Credit Card Fraud Handling Expert", "Good Service Attitude"}; Seat X: {"Fluent in Cantonese", "New Credit Card Promotion Expert"}; Seat Y: {"Credit Card Fraud Handling Expert", "Good Service Attitude"}; Seat Z: {"New Credit Card Promotion Expert", "Good Service Attitude"}; Seat V: {"Fluent in English", "Credit Card Fraud Handling Expert"}.

[0077] According to an embodiment of this application, if it is determined that the priority candidate set is not empty, then for each agent in the priority candidate set, the comprehensive matching degree between the agent and the user is calculated based on the matching situation of the agent's dynamic tag and the user's dynamic tag and the corresponding priority weight; if it is determined that the priority candidate set is empty, then for each agent in the secondary candidate set, the comprehensive matching degree between the agent and the user is calculated based on the matching situation of the agent's dynamic tag and the user's dynamic tag and the corresponding priority weight.

[0078] In one example, the system first attempts to filter agents whose mapping relationships are satisfied with all user dynamic tags. The check reveals that only agent W simultaneously satisfies the three mapping conditions: "fluent in Cantonese," "credit card fraud handling expert," and "good service attitude." Therefore, the system includes agent W in the priority candidate set. Since the priority candidate set is not empty (containing agent W), the system directly determines the target matching agent based on the overall matching score. Constructing a secondary candidate set: This path is not executed in this example. However, for illustration, it is assumed that agent W is currently busy (unavailable), so the priority candidate set is actually empty. At this point, the system executes degradation logic: filtering agents who satisfy at least one mapping relationship as the secondary candidate set. Agents X, Y, Z, and V all satisfy at least one condition (e.g., X satisfies "fluent in Cantonese," Y satisfies "credit card fraud handling expert" and "good service attitude"), and they will constitute the secondary candidate set. From the currently valid candidate set (the priority candidate set in this example), the final target is determined based on the overall matching score. For seat W, its overall matching degree is 0.4 + 0.4 + 0.2 = 1.0. Therefore, the system determines seat W as the target matching seat. If selecting from the secondary candidate set, the overall matching degree of each seat needs to be calculated (e.g., seat Y is 0.4 + 0.2 = 0.6) and sorted, and the one with the highest matching degree is selected.

[0079] According to an embodiment of this application, the method further includes: in response to a configuration operation, establishing, modifying, or deleting a mapping relationship between user dynamic tag types and agent dynamic tag types.

[0080] In one example, the system provides a rule configuration management interface. Administrators use this interface to dynamically manage preset tag matching rules. When routing policies need adjustment, administrators can visually manipulate the mapping network composed of dynamic customer tag types and dynamic agent tag types within the interface. Specifically, administrators select specified types from the preset customer and agent tag type libraries and establish a new association for them, while setting parameters such as priority weight and activation conditions for this relationship. Administrators can locate an existing mapping relationship and modify its associated tag types, weight values, or activation status. For policies that are no longer applicable, administrators can directly select and delete the corresponding mapping relationship. All these configuration operations are submitted through the interface and received and loaded by the system's rule engine in real time. The new rule set takes effect immediately, and subsequent call routing matching will be executed according to the updated rule logic, without interrupting ongoing services or deploying underlying code.

[0081] According to an embodiment of this application, the method further includes: if it is determined that all the target matching agents are in a non-idle state, assigning the call request to any currently idle available agent within the target agent group.

[0082] In one example, after determining the target matching agent, for instance, based on the aforementioned matching rules, the system calculates that Agent P (labeled "high anxiety index" and "consulting on complex business") has the highest overall match score for the target customer (labeled "strong communication and reassurance skills" and "expert in handling complex business"), followed by Agent Q (labeled "strong communication and reassurance skills"). Therefore, the system identifies Agent P and Agent Q as the target matching agents for this call and sorts them according to their match score (P takes precedence over Q). The system then performs an agent status check and fallback routing process, querying the current working status of Agent P and Agent Q in real time. The query reveals that Agent P is currently on a call and is in a "busy" state; Agent Q is also handling follow-up matters for another customer and is in a "post-processing (not idle)" state. Since all the identified target matching agents (P and Q) are in a non-idle state, the system determines that it cannot immediately provide the optimal matching service. The system immediately ignores the label-based matching result as a fault tolerance and guarantee mechanism. It then employs a pre-defined standard queuing strategy (e.g., an algorithm based on "longest idle time" or "round-robin") to quickly retrieve a list of currently "idle" agents within the same target agent group (i.e., the skill group to which the customer was initially statically routed). If agent R is currently idle, the system directly assigns the customer's call request to agent R.

[0083] According to an embodiment of this application, obtaining at least one user dynamic tag for a user includes: with the user's authorization, collecting multi-dimensional source data of the user, wherein the multi-dimensional source data includes at least one of records in a user's historical behavior database, real-time interaction data stream, and pre-configured preference settings information; performing at least one analysis and processing operation on the multi-dimensional source data, wherein the analysis and processing operation includes: mining and analysis of historical behavior records, voice sentiment analysis or semantic intent recognition of the real-time interaction data stream; and determining the user dynamic tag based on the result output by the analysis and processing operation.

[0084] In one example, when a customer initiates a call request, the system, provided it complies with relevant specifications and has obtained customer authorization, initiates the process of generating and updating the customer's dynamic tags. This process is not simply retrieving a static customer profile, but rather performing a dynamic data collection, analysis, and tag calculation operation. Specifically, this includes: the system collecting raw information related to the customer from multiple heterogeneous data sources in real-time or near real-time. These data sources at least cover: a user history behavior database: querying the customer's recent transaction history, product holding changes, service interaction history, etc.; real-time interactive data stream: capturing the real-time voice stream and keystroke sequence during the customer's dialogue with the IVR system after the call enters the IVR system; and pre-configured preference settings: reading information such as language preferences and communication channel preferences actively set by the customer on online platforms (such as mobile banking apps). The system inputs the collected raw data into the corresponding analysis engine for real-time processing: mining and analyzing historical behavior records, identifying short-term behavioral patterns through models, such as "recently frequently checking foreign exchange rates." The system performs voice sentiment analysis on real-time interactive data streams, using acoustic models to assess the emotional state (e.g., calm, anxious, dissatisfied) implied in the customer's current speech. Simultaneously, it performs semantic intent recognition, parsing keywords expressed by the customer in the IVR to preliminarily determine their core needs (e.g., "reporting a lost item" or "complaining"). The system updates user dynamic tags: the analysis engine's output (e.g., "behavioral pattern: recently interested in forex," "emotional state: anxious," "potential intent: reporting a lost item") is transformed into structured feature data. This feature data is matched against a tag definition library to generate or update the dynamic tag set for the customer's current session. For example, the above results are updated to tags: {"potential recent forex trading needs," "anxious," "business intent may involve account security"}. If the customer already has old tags (e.g., yesterday's tag was "stable"), they will be overwritten by the new tag derived from this analysis ("anxious"), ensuring that the tags always reflect the latest status.

[0085] According to an embodiment of this application, obtaining agent dynamic tags includes: periodically collecting agent service quality data within a preset time period, wherein the service quality data includes at least one of: call recording quality inspection scores, user feedback satisfaction evaluations, average session processing time, and skill certification results; and determining the agent dynamic tags based on the service quality data.

[0086] In one example, the generation and maintenance of agent dynamic tags is a continuous, periodic background process, rather than a one-time static assignment. The system automatically performs the following tag update tasks according to a preset cycle (e.g., daily or weekly): At the end of each cycle, the system automatically collects service quality data generated by the target agent within that cycle from multiple operations and quality inspection platforms. This data is objective and quantifiable, primarily including: Call recording quality inspection scores: Based on a preset quality inspection model (covering dimensions such as service standards, business accuracy, and communication skills), the system automatically or manually scores sampled calls of the agent. User satisfaction ratings: Summarizing customer satisfaction ratings (e.g., 1-5 points) or evaluation texts submitted by customers via SMS, IVR, or online channels after the agent's service is completed. Average session processing time: Calculating the average processing time for similar business sessions by the agent as an indicator of their efficiency. Skill certification results: Synchronizing the latest data from the human resources or training system, recording newly acquired or renewed professional skill certifications for the agent (e.g., "Advanced Anti-Fraud Certification," "Advanced Sales Qualification for Financial Products"). The system inputs the collected multi-dimensional data into a tag calculation engine. The engine dynamically updates the agent's tag set based on predefined rules and algorithm models (e.g., activating the "Service Star" tag if satisfaction scores are above X points for N consecutive times; activating the "Highly Efficient" tag if the processing time for a certain type of service is significantly lower than the group average and quality inspection is passed; automatically adding the corresponding tag when a new skill certification is added). For example:

[0087] Agent A achieved an average quality inspection score of 98 this week and received 5 "Very Satisfactory" ratings. The system has updated its label, adding or strengthening the "Excellent Service Quality" label. Agent B recently passed the "Cross-border Business Expert" certification; the system has updated its label, adding the "Cross-border Business Expert" label. Agent C's recent average processing time for "Loan Business" has risen to the bottom 20% of the group; the system may weaken or remove its original "Efficient Loan Business Processing" label.

[0088] According to an embodiment of this application, the method further includes: collecting performance evaluation data associated with the call service when the target matched agent completes the current call service; and adjusting the corresponding weights in the mapping relationship between user dynamic tag types and agent dynamic tag types based on the performance evaluation data.

[0089] In one example, after a specific service call is completed, the system initiates a closed-loop feedback optimization process. Assume that in this service, the system assigned the customer to Agent A based on matching rules (e.g., mapping the customer tag "high-risk investment intention" to the agent tag "senior financial advisor," with a weight of 0.5). After the service, the system automatically collects performance evaluation data related to this service call through multiple channels, such as the customer's satisfaction rating (e.g., 4 out of 5) given via IVR voice feedback or SMS reply after the call; whether the customer completed related business operations (e.g., subscribing to high-risk financial products) in the short term; and the quality control team's score for the call recording (e.g., scores on business accuracy, compliance, and service skills). The system inputs the collected multi-dimensional performance data into a weighted optimization algorithm model. This model comprehensively evaluates the service performance of this matching instance ("high-risk investment intention" -> "senior financial advisor"). For example, if the evaluation results show that the match achieved excellent results (high customer satisfaction, successful conversion, excellent quality control), the model will increase the weight of that mapping relationship (e.g., from 0.5 to 0.55). This means that in the future, customers with similar tags will be more likely to be matched with agents labeled "Senior Financial Advisor." Conversely, if historical data from multiple matches shows that matching customers with "high-risk investment intentions" with "Senior Financial Advisors" is generally ineffective (e.g., high complaint rate, low conversion rate), the model will decrease the weight, thereby reducing the priority of such matches and prompting the system to explore other potentially more effective matching rules (e.g., trying to match with agents labeled "Risk Communication Expert").

[0090] Based on the above-described dual-label-based call routing matching method, this application also provides a dual-label-based call routing matching device. The following will combine... Figure 4 The device is described in detail.

[0091] Figure 4 A schematic block diagram of a dual-tag-based call routing matching device according to an embodiment of this application is shown. Figure 4 As shown, the dual-tag-based call routing matching device 400 of this embodiment includes an acquisition module 410, a matching module 420, and a call routing module 430.

[0092] The acquisition module 410 is used to acquire, in response to a call request, at least one user dynamic tag of the user and at least one agent dynamic tag of each agent in the target agent group corresponding to the call request. The target agent group is determined according to preset static routing rules. The agent dynamic tags and the user dynamic tags are used to characterize features such as immediate status, short-term behavioral preferences, or real-time analysis results. In one embodiment, the acquisition module 410 can be used to perform the operation S210 described above, which will not be repeated here.

[0093] The matching module 420 is used to determine at least one target matching agent in the target agent group according to preset tag matching rules, the user dynamic tags, and the agent dynamic tags. In one embodiment, the matching module 420 can be used to perform the operation S220 described above, which will not be repeated here.

[0094] The matching module 430 is used to determine at least one target matching agent in the target agent group according to preset tag matching rules, the user dynamic tags, and the agent dynamic tags. In one embodiment, the matching module 430 can be used to perform the operation S230 described above, which will not be repeated here.

[0095] According to an embodiment of this application, the matching module includes: a matching submodule, a calculation submodule, and a first determination submodule.

[0096] The matching submodule is used to identify the matching status between the agent's dynamic tag and the user's dynamic tag for each agent in the target agent group; the calculation submodule is used to calculate the comprehensive matching degree between each agent and the user based on the matching status and the corresponding priority weight; the determination submodule is used to sort the agents in the target agent skill group according to the comprehensive matching degree, and determine the agents whose sorting meets the preset conditions as the target matched agents.

[0097] According to an embodiment of this application, the matching module further includes: a first filtering submodule and a second filtering submodule.

[0098] The first filtering submodule is used to filter out agents that satisfy the mapping relationship with all of the user dynamic tags as a priority candidate set; the second filtering submodule is used to filter out agents that satisfy the mapping relationship with at least one of the user dynamic tags as a secondary candidate set if the priority candidate set is empty.

[0099] According to an embodiment of this application, the apparatus further includes: a configuration module, configured to establish, modify, or delete a mapping relationship between user dynamic tag types and agent dynamic tag types in response to a configuration operation.

[0100] According to an embodiment of this application, the device further includes: a rerouting module, configured to determine the current status of all target matching agents after determining the target matching agent; if it is determined that all target matching agents are in a non-idle state, then ignore the tag matching result and assign the call request to any currently idle available agent within the target agent group.

[0101] According to an embodiment of this application, the acquisition module is further configured to collect multi-dimensional source data of the user with the user's authorization, wherein the multi-dimensional source data includes at least one of records in the user's historical behavior database, real-time interactive data stream, and pre-configured preference settings information; perform at least one analysis and processing operation on the multi-dimensional source data, wherein the analysis and processing operation includes: mining and analysis of historical behavior records, voice sentiment analysis or semantic intent recognition of the real-time interactive data stream; and determine the user's dynamic tag based on the result output by the analysis and processing operation.

[0102] According to an embodiment of this application, the acquisition module is further configured to periodically collect service quality data of agents within a preset time period, the service quality data including at least one of: call recording quality inspection score, user feedback satisfaction evaluation, average session processing time, and skill certification results; and determine the agent's dynamic tag based on the service quality data.

[0103] According to an embodiment of this application, the device further includes a collection module and an adjustment module.

[0104] The collection module is used to collect performance evaluation data associated with the call service when the target matched agent completes the call service; the adjustment module is used to adjust the priority weights in the mapping relationship between user dynamic tag types and agent dynamic tag types based on the performance evaluation data.

[0105] According to embodiments of this application, any plurality of modules among the acquisition module 410, matching module 420, and call routing module 430 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this application, at least one of the acquisition module 410, matching module 420, and call routing module 430 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the acquisition module 410, matching module 420, and call routing module 430 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0106] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a dual-tag-based call routing matching method according to an embodiment of this application. Figure 5 As shown, an electronic device 500 according to an embodiment of this application includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0107] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0108] According to embodiments of this application, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0109] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0110] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the dual-label-based call routing matching method provided in the embodiments of this application.

[0111] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0112] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this application embodiment. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0114] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

Claims

1. A call routing matching method based on dual tags, characterized in that, include: In response to a call request, at least one user dynamic tag of the user and at least one agent dynamic tag of each agent in the target agent group corresponding to the call request are obtained, wherein the target agent group is determined according to a preset static routing rule, and the agent dynamic tag and the user dynamic tag are used to characterize feature data representing immediate status, short-term behavioral preferences or real-time analysis results. Based on the preset tag matching rules, the user dynamic tags, and the agent dynamic tags, at least one target matching agent is determined in the target agent group; The user's call request is routed to the target matching agent.

2. The method according to claim 1, characterized in that, The preset tag matching rules include a predefined mapping relationship between user dynamic tag types and agent dynamic tag types, and the corresponding priority weights; The step of determining at least one target matching agent in the target agent group based on preset tag matching rules, the user dynamic tags, and the agent dynamic tags includes: For each agent in the target agent group, identify the matching status between the agent's dynamic tag and the user's dynamic tag; Based on the matching results and corresponding priority weights, the overall matching degree between each seat and the user is calculated; The seats in the target seat skill group are sorted according to the overall matching degree, and the seats that meet the preset conditions are determined as the target matching seats.

3. The method according to claim 2, characterized in that, The process of identifying the matching between the agent's dynamic tag and the user's dynamic tag includes: Select agents whose mapping relationship with all the user dynamic tags satisfies the given criteria, and use this as a priority candidate set; and If the priority candidate set is empty, then the seats that satisfy the mapping relationship with at least one of the user dynamic tags are selected as the secondary candidate set; The step of calculating the overall match degree between each seat and the user based on the matching results and corresponding priority weights includes: If it is determined that the priority candidate set is not empty, then for each agent in the priority candidate set, the comprehensive matching degree between the agent and the user is calculated based on the matching situation between the agent's dynamic tag and the user's dynamic tag and the corresponding priority weight. If the priority candidate set is determined to be empty, then for each agent in the secondary candidate set, the overall matching degree between the agent and the user is calculated based on the matching of the agent's dynamic tag and the user's dynamic tag and the corresponding priority weight.

4. The method according to claim 2, characterized in that, The preset tag matching rules are implemented through a configurable rule engine; the method further includes: In response to configuration operations, establish, modify, or delete the mapping relationship between user dynamic tag types and agent dynamic tag types.

5. The method according to claim 1, characterized in that, The method further includes: If it is determined that all the target matching agents are not idle, the call request is assigned to any currently idle available agent within the target agent group.

6. The method according to claim 1, characterized in that, Obtain at least one user dynamic tag from the user, including: With user authorization, multi-dimensional source data of the user is collected, including at least one of the following: records in the user's historical behavior database, real-time interaction data streams, and pre-configured preference settings information; Perform at least one analysis and processing operation on the multidimensional source data, the analysis and processing operation including: mining and analysis of historical behavior records, voice sentiment analysis or semantic intent recognition of the real-time interactive data stream; The user's dynamic tags are determined based on the results of the analysis and processing operation.

7. The method according to claim 1, characterized in that, The dynamic tags for agents include: Service quality data of agents is collected periodically within a preset time period. The service quality data includes at least one of the following: quality inspection score of call recordings, satisfaction evaluation of user feedback, average session processing time, and skill certification results. The agent's dynamic tag is determined based on the service quality data.

8. The method according to claim 2, characterized in that, The method further includes: If the target matched agent completes the call service, collect the performance evaluation data associated with the call service; Based on the performance evaluation data, adjust the priority weights in the mapping relationship between user dynamic tag types and agent dynamic tag types.

9. A call routing matching device based on dual tags, characterized in that, The device includes: The acquisition module is used to acquire at least one user dynamic tag of the user and at least one agent dynamic tag of each agent in the target agent group corresponding to the call request in response to a call request. The target agent group is determined according to a preset static routing rule. The agent dynamic tag and the user dynamic tag are used to characterize feature data representing immediate status, short-term behavioral preferences or real-time analysis results. The matching module is used to determine at least one target matching agent in the target agent group according to the preset tag matching rules, the user dynamic tags and the agent dynamic tags; The call routing module is used to route the user's call request to the target matching agent.

10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 8.

Images