CN115470867A - Agent matching method, device, equipment and storage medium based on knowledge graph - Google Patents
Agent matching method, device, equipment and storage medium based on knowledge graph Download PDFInfo
- Publication number
- CN115470867A CN115470867A CN202211276675.XA CN202211276675A CN115470867A CN 115470867 A CN115470867 A CN 115470867A CN 202211276675 A CN202211276675 A CN 202211276675A CN 115470867 A CN115470867 A CN 115470867A
- Authority
- CN
- China
- Prior art keywords
- customer
- agent
- client
- seat
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
The application relates to a knowledge graph-based agent matching method, a knowledge graph-based agent matching device, knowledge graph-based agent matching equipment and a storage medium, wherein the method comprises the following steps: acquiring incoming call information of a client, and acquiring service category information determined by the client through interactive voice response; determining the current available agents in the agent list according to the service category information; the currently available agents are online and in a ready state; determining a target seat matched with a client in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent; and establishing a call between the target seat and the client. According to the method, the target seat matched with the customer can be determined from the current available seats determined based on the service class information through the incoming call information and the preset knowledge graph, so that the problems of randomness and inaccuracy of seat matching are solved, the matching degree of the seat and the customer is improved, and the satisfaction degree of the customer is improved.
Description
Technical Field
The present application relates to the technical field of customer service, and in particular, to a method, an apparatus, a device, and a storage medium for agent matching based on a knowledge graph.
Background
In an electric Internet Technology (Internet Technology, abbreviated as IT) operation and maintenance service, a voice call platform is an important channel, a user reports daily problems, requirements and faults through the voice call platform, and operation and maintenance personnel track and process the problems.
In a traditional IT calling system, after a customer makes a call and selects a service skill set, a calling platform selects an agent according to the queuing condition of the agent, so that the communication between the agent and a customer service is realized. The traditional seat matching method only matches the seat condition, the contact degree between the seats distributed by the system and the clients is low, and the problem solution of the clients is influenced, so that the service quality is reduced, and the satisfaction degree and the experience degree of the clients are influenced.
Disclosure of Invention
In order to solve the technical problems of randomness and inaccuracy of seat matching of an electric power IT operation and maintenance call center, the application provides a seat matching method, a device, equipment and a storage medium based on a knowledge graph.
In a first aspect, the present application provides a knowledge-graph-based agent matching method, including:
acquiring incoming call information of a client, and acquiring service class information determined by the client through interactive voice response;
determining the current available seat in a seat list according to the service category information; the currently available agents are online and in a ready state;
determining a target seat matched with the customer in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
establishing a call between the target agent and the client;
optionally, before determining a target agent matching the customer from the currently available agents according to the incoming call information and a preset knowledge graph, the method further includes:
acquiring the knowledge graph;
wherein the construction process of the knowledge graph comprises the following steps:
acquiring customer data and historical customer service records; the historical customer service record comprises at least one of historical telephone traffic data, historical service work order data, seat service capability evaluation data and call service classification data;
respectively extracting at least one ternary group data of the client according to the client data and the historical client service record; the triple data comprises data composed of the client, child nodes of the client and attributes of the child nodes; the child nodes at least comprise an incoming call information child node and a customer seat association parameter child node; the incoming call information sub-node represents the corresponding relation between the client and the incoming call information; the customer seat association parameter child node represents the association relationship between a customer and a seat;
constructing the knowledge graph according to the triple data;
optionally, determining a currently available agent in an agent list according to the service category information includes:
acquiring an agent list, wherein the agent list comprises at least one target classification agent list;
acquiring a preset mapping relation; the mapping relation is the mapping relation between the target classification agent list and the service class information;
determining a target classification agent list from the agent list according to the service category information and the mapping relation, and taking an agent which is online and in a ready state in the target classification agent list as the current available agent;
optionally, the incoming call information includes at least an incoming call number and an incoming call area;
determining a target agent matched with the customer in the current available agents according to the incoming call information and a preset knowledge graph, wherein the method comprises the following steps:
determining a target client corresponding to the incoming number in the knowledge graph, and acquiring client seat association parameters of the target client in the knowledge graph;
determining an agent list corresponding to the call-in area from the current available agents;
according to the customer seat association parameters, determining a seat matched with the target customer in the seat list as the target seat;
optionally, the customer seat association parameters include: at least one of a customer name, a unit to which the customer belongs, a customer post rating, customer sensitivity, customer complaint rate, customer satisfaction, and customer preferred seating data;
according to the customer seat association parameters, determining a seat matched with the target customer in the seat list as the target seat, including:
acquiring a integrating degree weight corresponding to each customer seat association parameter;
calculating the score of each agent in the agent list according to the customer agent association parameters and the integrating degree weight;
sorting the agents in the agent list according to the score of each agent to obtain a sorting result, and taking the agent with the highest score in the sorting result as the target agent;
optionally, after establishing the call between the target agent and the client, the method further includes:
acquiring a customer service record of the target agent to the customer;
updating the knowledge-graph based on the customer service record;
optionally, determining a target agent matched with the customer from the currently available agents according to the incoming call information and a preset knowledge graph, including:
according to the incoming call information and the preset knowledge graph, when the customer is determined to be a new customer, an agent satisfaction ranking list is obtained;
and determining the highest current satisfaction seat in an online and ready state from the seat satisfaction ranking table, and taking the highest current satisfaction seat as the target seat matched with the new customer.
In a second aspect, the present application provides a knowledge-graph based agent matching apparatus, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring the incoming call information of a client and acquiring the service category information determined by the client through an interactive voice response;
the determining module is used for determining the current available seat in the seat list according to the service category information; the currently available agents are online and in a ready state;
the matching module is used for determining a target seat matched with the client in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
and the answering module is used for establishing the conversation between the target seat and the client.
In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the steps of the agent matching method based on the knowledge-graph according to any embodiment of the first aspect when executing the program stored in the memory.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of a knowledge-graph based agent matching method as described in any one of the embodiments of the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
the method provided by the embodiment of the application can be used for carrying out deep analysis by combining with the customer requirements to obtain the service category information determined by the customer through interactive voice response; and determining the current available seat in the seat list according to the service category information, and determining a target seat matched with the customer in the current available seat according to the incoming call information and a preset knowledge map so as to solve the problems of randomness and inaccuracy of seat matching and improve the matching degree of the seat and the customer, thereby improving the satisfaction degree and experience degree of the customer on the seat and enabling the operation and maintenance service to better serve the customer.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a system architecture diagram of a knowledge-graph based agent matching method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a knowledge-graph-based agent matching method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart diagram of a knowledge graph construction method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an agent matching apparatus based on a knowledge-graph according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The first embodiment of the present application provides a knowledge-graph-based agent matching method, which can be applied to a system architecture as shown in fig. 1, where the system architecture includes at least an agent matching system 101 and a client 100, and the client 100 can establish a voice call with the agent matching system 101 through a cellular network, and the number of the clients 100 is not limited.
The method can be applied to the agent matching system 101 in the system architecture, and is used for matching an agent with any customer 100 calling into the agent matching system 101, for example, the agent matching system 101 may be an electric power IT operation and maintenance call center, or may be configured in the electric power IT operation and maintenance call center, and performs agent matching on the customer 100 calling in through a call platform.
Next, a knowledge-graph-based agent matching method is described in detail based on the system architecture. A knowledge-graph-based agent matching method, as shown in fig. 2, the method comprising:
The incoming call information of the client may include information such as an incoming call number, incoming call time, and an incoming call area corresponding to the incoming call number.
Interactive Voice Response, or IVR (Interactive Voice Response), also called intelligent IVR service, can guide the customer to determine the service type information to be acquired through touch-tone Voice navigation.
In an embodiment, determining a currently available agent in the agent list according to the service category information may specifically include: acquiring an agent list, wherein the agent list comprises at least one target classification agent list; acquiring a preset mapping relation; the mapping relation is the mapping relation between the target classification agent list and the service class information; and determining a target classification agent list from the agent list according to the service class information and the mapping relation, and taking the agent which is online and in a ready state in the target classification agent list as the current available agent.
In this embodiment, the agent lists may be grouped according to service categories in advance, that is, the agent lists are divided into one or more target classification agent lists, each target classification agent list corresponds to one piece of service category information, and an agent in the target classification agent list is adept at handling and solving various problems corresponding to the service category. Of course, some of the agents in the target categorized agent list may be offline or in a listening state, or one agent may be grouped into a plurality of target categorized agent lists and be listening to calls of other service categories during grouping, so that when determining the currently available agents, the online and ready agents need to be screened from the determined target categorized agent lists.
In the embodiment, the seats can be classified by grouping the seat lists, so that the services which are good at the authorities are processed, the service level is improved, the operation and maintenance service can better serve customers, and the satisfaction degree and the experience degree of the customers to the seats are further improved.
In the embodiment, the IT service categories can be classified and the seats can be grouped according to the service categories according to the responsibility of the power IT call center and the IT service range, and the intelligent IVR button type voice navigation service can be built between the customer and the seats based on the intelligent IVR service. The mapping relation between the key data of the client and the IT service classification can be set through the intelligent IVR key type voice navigation service, the client completes the traffic distribution of the client after interactively selecting the service type to be obtained through the intelligent IVR key, meanwhile, the screening and filtering of the seats are completed according to the selected service type, and a seat list which is in a ready state and has the functions of responding and processing the client appeal is generated at present.
The method comprises the steps of determining a client corresponding to incoming call information through the corresponding relation between the client and the incoming call information in a preset knowledge graph, and determining a target seat matched with the client according to the association relation between the client and the seat in the knowledge graph.
And step 204, establishing a call between the target seat and the client.
In the embodiment, deep analysis can be performed by combining with the customer requirements to acquire service category information determined by the customer through interactive voice response; and determining the current available seat in the seat list according to the service category information, and determining a target seat matched with the customer in the current available seat according to the incoming call information and a preset knowledge map so as to solve the problems of randomness and inaccuracy in seat matching and improve the matching degree of the seat and the customer, thereby improving the satisfaction degree and experience degree of the customer on the seat and enabling the operation and maintenance service to better serve the customer.
In one embodiment, before determining a target agent matching the customer among currently available agents according to the incoming call information and the preset knowledge graph, the method further comprises: and acquiring a knowledge graph.
The process of constructing the knowledge graph, as shown in fig. 3, at least includes:
In the embodiment, the knowledge graph generation model and the knowledge graph generation algorithm are derived and applied based on the current mature knowledge graph generation model, and the whole process of knowledge extraction, knowledge fusion, knowledge inference and knowledge storage is covered comprehensively.
The data extracted when the knowledge graph is generated may include customer data, historical traffic data, historical service work order data, agent service capability evaluation data, call service classification data, and the like, based on the acquired data, the customer is focused, and extraction of triple data such as entities, relationships, attributes (which may also be referred to as nodes, sub-nodes, and attributes) and the like is completed based on a deep learning method, where an entity refers to the customer and may also be referred to as a node, a sub-node refers to a relationship with the customer, and an attribute refers to an attribute of a relationship between the sub-node and the customer, as illustrated below:
the triple data format may be used as: (zhang, incoming call time, 22 months 6 and 22 days 22 hours 23 minutes 23 seconds 2022), (zhang, post, responsibility), (zhang, business team, assets team), (zhang, post level, VIP/important/common), (zhang, sensitivity, 10-1), (zhang, complaint rate, 10-1), (zhang, satisfaction, 10-1). The call-in time, the service group, the post level, the complaint rate, the satisfaction degree and the like are child nodes of the third node, and the special responsibility, the asset group and the like are attributes of the corresponding child nodes.
And based on the extracted and generated triple data, the homography and reasoning of knowledge are completed by combining a deep learning algorithm, the content, the relation and the attribute elements of each node in the knowledge graph are formed, and finally, the knowledge data storage can be completed by using a database based on Neo4j and the visual construction of the knowledge graph can be completed.
The generated knowledge graph embodies the correlation and attribute information of clients, agents and service categories.
Specifically, the call-in information sub-node of the client, such as the mobile phone number of the client, the area where the client is located, and the like, can be extracted from the client data.
The customer agent association parameter child node for the customer may be extracted from the historical customer service record. The customer seat association parameters may include: one or more of a customer name, a unit to which the customer belongs, a customer post rating, customer sensitivity, customer complaint rate, customer satisfaction, and customer preferred seating data. The customer seat association parameters are parameters that the customer has a certain degree of association with the seat, for example, if the customer post level is higher, a seat with stronger service capability needs to be allocated for processing, or if the customer complaint rate is higher, a seat with strong service capability and high service level needs to be allocated for processing. Of course, to improve the accuracy of the agent matching, the customer agent association parameters may include all of the above parameters.
It should be noted that the child nodes and attributes in the specific triple data may be set as needed, and the specific selected graph database may also select other graph databases as needed, which are all described above by way of example and do not represent limitations on the graph databases.
It should be noted that the knowledge graph may further include a preset mapping relationship between the target classification agent list and the service category information.
In one embodiment, the incoming call information at least comprises an incoming call number and an incoming call area, and the determining of the target seat matched with the customer from the currently available seats according to the incoming call information and a preset knowledge graph comprises the following steps: determining a target client corresponding to the incoming number in the knowledge graph, and acquiring client seat association parameters of the target client in the knowledge graph; determining an agent list corresponding to the call-in area from the current available agents; and determining an agent matched with the target customer in the agent list as a target agent according to the customer agent association parameters.
In this embodiment, the target client is a client found in the knowledge graph according to the incoming call information, that is, a client corresponding to the incoming call information, and is different from the client in name only and has no substantial difference. Service class information corresponding to different incoming areas may be different, and the seat list may be classified according to the incoming areas, so that accuracy of seat matching is improved.
In one embodiment, determining an agent matching a target customer in an agent list as a target agent according to the customer agent association parameter includes: acquiring a fitness weight corresponding to each customer seat association parameter; calculating the score of each agent in the agent list according to the client agent correlation parameters and the integrating degree weight; and sorting the agents in the agent list according to the score of each agent to obtain a sorting result, and taking the agent with the highest score in the sorting result as a target agent.
In this embodiment, the fitness weight corresponding to the customer seat association parameter is related to the attribute of the child node of the customer seat association parameter, for example, when the customer seat association parameter is a customer complaint rate, the fitness weight is related to a specific numerical value of the customer complaint rate, if the complaint rate of the seat a in the seat list is low, the score of the seat a is high, or the score of the seat is related to the complaint rate data and the like according to the satisfaction of the seat.
Specifically, a customer intention prediction model and an algorithm can be preset in the knowledge graph, the customer intention prediction model is built based on an attention mechanism, and the attention mechanism is combined to analyze and calculate the service capability fitness weight of the seat. The customer name, the unit to which the customer belongs, the customer post level, the sensitivity, the complaint rate and the satisfaction degree, the service category, the satisfaction degree and the complaint rate data related to the seats, the seat data related to the customers and the like are used as input, the service conformity weight of each seat in the seat list which is in a ready state and responds to and processes the customer appeal is calculated respectively, the expected service requirement of the customers is subjected to predictive analysis based on the weight, and the seats are sorted according to the sorting rule from large to small of the weight after the weight calculation is finished.
It should be noted that the attention mechanism means that the client intention prediction model has the ability to focus on its input parameters: a particular input is selected. In the case of limited computing power, an attention mechanism (attention mechanism) is a resource allocation scheme of a main means for solving the information overload problem, and computing resources are allocated to more important tasks.
In one embodiment, after establishing the call between the target agent and the client, the method further comprises: acquiring a customer service record of a target agent to a customer; the knowledge graph is updated based on customer service records.
In the embodiment, the knowledge graph further comprises a knowledge graph complementing model and a knowledge graph complementing algorithm, after customer service is completed, new customer service records are generated, meanwhile, the knowledge graph complementing algorithm is triggered and started, updating and complementing operations of the knowledge graph are completed based on newly generated customer service record data, the knowledge graph is further perfected, and next application is supported.
In the step, a knowledge graph complement model and an algorithm can be built based on a relation inference model of a Recurrent Neural Network (RNN), after a new customer service record is generated, updating and complementing of knowledge graph data related to a customer are completed based on the new customer service record, knowledge graph content is further improved, and continuous optimization of the knowledge graph is completed.
It should be noted that, in the above embodiment, the relevant information of the customer corresponding to the incoming call number is already stored in the knowledge graph, that is, the incoming call customer is an old customer. When the customer who calls in is a new customer, according to the information of calling in and the preset knowledge map, the target seat matched with the customer is determined in the current available seats, and the method comprises the following steps: according to the incoming call information and a preset knowledge graph, when a customer is determined to be a new customer, an agent satisfaction ranking list is obtained; and determining the highest current satisfaction seat in an online ready state from the seat satisfaction ranking table, and taking the highest current satisfaction seat as a target seat matched with the new customer.
In the embodiment, for a new customer, after the seats are ranked from high to low according to the seat satisfaction, the seat with the highest seat satisfaction is preferentially recommended to the customer to provide service for the customer, and the service record is completed. The service quality of the new customer is guaranteed, and after the service record is completed, the information such as the node, the child node, the attribute and the like aiming at the customer is established in the knowledge graph according to the customer service record.
Based on the same technical concept, a second embodiment of the present application provides a knowledge-graph-based agent matching apparatus, as shown in fig. 4, the apparatus includes:
an obtaining module 401, configured to obtain incoming call information of a client, and obtain service category information determined by the client through an interactive voice response;
a determining module 402, configured to determine a currently available agent in an agent list according to the service category information; the currently available agents are online and in a ready state;
a matching module 403, configured to determine, according to the incoming call information and a preset knowledge graph, a target agent that is matched with the customer from among the currently available agents; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
and an answering module 404, configured to establish a call between the target agent and the client.
In this embodiment, the agent matching device can perform deep analysis in combination with the customer requirements to obtain service category information determined by the customer through interactive voice response; and determining the current available seat in the seat list according to the service category information, and determining a target seat matched with the customer in the current available seat according to the incoming call information and a preset knowledge map so as to solve the problems of randomness and inaccuracy of seat matching and improve the matching degree of the seat and the customer, thereby improving the satisfaction degree and experience degree of the customer on the seat and enabling the operation and maintenance service to better serve the customer.
As shown in fig. 5, a third embodiment of the present application provides an electronic device, which includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 complete mutual communication via the communication bus 114,
a memory 113 for storing a computer program;
in one embodiment, the processor 111, when configured to execute the program stored in the memory 113, implements a method for matching an agent based on a knowledge graph according to any one of the foregoing method embodiments, including:
acquiring incoming call information of a client, and acquiring service category information determined by the client through interactive voice response;
determining the current available agents in the agent list according to the service category information; the currently available agents are online and in a ready state;
determining a target seat matched with a client in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
and establishing a call between the target seat and the client.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
The fourth embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of a knowledge-graph-based agent matching method as provided in any one of the method embodiments described above:
acquiring incoming call information of a client, and acquiring service category information determined by the client through interactive voice response;
determining the current available agents in the agent list according to the service category information; the currently available agents are online and in a ready state;
determining a target seat matched with a client in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
and establishing a call between the target seat and the client.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the description, suffixes such as "module", "part", or "unit" used to indicate elements are used only for facilitating the description of the present invention, and have no particular meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A knowledge graph-based agent matching method is characterized by comprising the following steps:
acquiring incoming call information of a client, and acquiring service category information determined by the client through interactive voice response;
determining the current available seat in a seat list according to the service category information; the currently available agents are online and in a ready state;
determining a target seat matched with the customer in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
and establishing the conversation between the target seat and the client.
2. The method of claim 1, wherein before determining a target agent matching the customer among the currently available agents based on the incoming call information and a preset knowledge graph, the method further comprises:
acquiring the knowledge graph;
wherein the construction process of the knowledge graph comprises the following steps:
acquiring customer data and historical customer service records; the historical customer service record comprises at least one of historical telephone traffic data, historical service work order data, seat service capability evaluation data and call service classification data;
respectively extracting at least one ternary group data of the client according to the client data and the historical client service record; the triple data comprises data composed of the client, child nodes of the client and attributes of the child nodes; the child nodes at least comprise an incoming call information child node and a customer seat association parameter child node; the incoming call information sub-node represents the corresponding relation between the client and the incoming call information; the customer seat association parameter child node represents the association relationship between a customer and a seat;
and constructing the knowledge graph according to the triple data.
3. The method of claim 1, wherein determining a currently available agent in an agent list according to the service class information comprises:
acquiring an agent list, wherein the agent list comprises at least one target classification agent list;
acquiring a preset mapping relation; the mapping relation is the mapping relation between the target classification agent list and the service class information;
and determining a target classification agent list from the agent list according to the service class information and the mapping relation, and taking an online agent in a ready state in the target classification agent list as the current available agent.
4. The method according to claim 1, wherein the incoming call information includes at least an incoming call number and an incoming call area;
determining a target agent matched with the customer in the current available agents according to the incoming call information and a preset knowledge graph, wherein the method comprises the following steps:
determining a target client corresponding to the incoming number in the knowledge graph, and acquiring client seat association parameters of the target client in the knowledge graph;
determining an agent list corresponding to the incoming call region in the current available agents;
and determining an agent matched with the target customer in the agent list as the target agent according to the customer agent association parameters.
5. The method of claim 4, wherein the customer agent association parameters comprise: at least one of a customer name, a unit to which the customer belongs, a customer post rating, customer sensitivity, customer complaint rate, customer satisfaction, and customer preferred seating data;
according to the customer seat association parameters, determining a seat matched with the target customer in the seat list as the target seat, including:
acquiring a fitness weight corresponding to each customer seat association parameter;
calculating the score of each agent in the agent list according to the customer agent association parameters and the integrating degree weight;
and sorting the agents in the agent list according to the score of each agent to obtain a sorting result, and taking the agent with the highest score in the sorting result as the target agent.
6. The method of claim 1, wherein after establishing the call between the target agent and the customer, the method further comprises:
acquiring a customer service record of the target seat to the customer;
updating the knowledge-graph based on the customer service record.
7. The method of claim 1, wherein determining a target agent matching the customer among the currently available agents according to the incoming call information and a preset knowledge graph comprises:
according to the incoming call information and the preset knowledge graph, when the client is determined to be a new client, an agent satisfaction ranking list is obtained;
and determining the highest current satisfaction seat in an online ready state from the seat satisfaction ranking table, and taking the highest current satisfaction seat as the target seat matched with the new customer.
8. A knowledge-graph-based agent matching apparatus, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring the incoming call information of a client and acquiring the service category information determined by the client through an interactive voice response;
the determining module is used for determining the current available seat in the seat list according to the service category information; the currently available agents are online and in a ready state;
the matching module is used for determining a target seat matched with the client in the current available seats according to the incoming call information and a preset knowledge graph; the knowledge graph at least comprises a corresponding relation between a client and incoming call information and an association relation between the client and an agent;
and the answering module is used for establishing the conversation between the target seat and the client.
9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the steps of the knowledge-graph based agent matching method of any one of claims 1-7 when executing a program stored on a memory.
10. A computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when being executed by a processor, carries out the steps of the method of knowledge-graph based agent matching according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276675.XA CN115470867A (en) | 2022-10-17 | 2022-10-17 | Agent matching method, device, equipment and storage medium based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276675.XA CN115470867A (en) | 2022-10-17 | 2022-10-17 | Agent matching method, device, equipment and storage medium based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115470867A true CN115470867A (en) | 2022-12-13 |
Family
ID=84336201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211276675.XA Pending CN115470867A (en) | 2022-10-17 | 2022-10-17 | Agent matching method, device, equipment and storage medium based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115470867A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115860436A (en) * | 2023-02-21 | 2023-03-28 | 齐鲁工业大学(山东省科学院) | City hot line dispatching method and system based on knowledge graph |
| CN116108169A (en) * | 2022-12-12 | 2023-05-12 | 长三角信息智能创新研究院 | Hot wire work order intelligent dispatching method based on knowledge graph |
-
2022
- 2022-10-17 CN CN202211276675.XA patent/CN115470867A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116108169A (en) * | 2022-12-12 | 2023-05-12 | 长三角信息智能创新研究院 | Hot wire work order intelligent dispatching method based on knowledge graph |
| CN116108169B (en) * | 2022-12-12 | 2024-02-20 | 长三角信息智能创新研究院 | Hot wire work order intelligent dispatching method based on knowledge graph |
| CN115860436A (en) * | 2023-02-21 | 2023-03-28 | 齐鲁工业大学(山东省科学院) | City hot line dispatching method and system based on knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20100191658A1 (en) | Predictive Engine for Interactive Voice Response System | |
| CN115470867A (en) | Agent matching method, device, equipment and storage medium based on knowledge graph | |
| US20230289702A1 (en) | System and Method of Assigning Customer Service Tickets | |
| CN108076237B (en) | Telephone customer service data processing method and device | |
| CN107786757B (en) | Bank card business parameter regulation means and device | |
| US20150134404A1 (en) | Weighted promoter score analytics system and methods | |
| CN112364035A (en) | Processing method and device for call record big data, electronic equipment and storage medium | |
| CN110147427A (en) | Project case method for pushing and device | |
| CN113206909A (en) | Crank call interception method and device | |
| CN110070392B (en) | User loss early warning method and device | |
| CN112035570A (en) | Merchant evaluation method and system | |
| CN110677269B (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| GB2517358A (en) | Recommendation creation system | |
| CN111050001A (en) | Telephone traffic distribution method and related device | |
| CN110087230B (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN113517990B (en) | Method and device for predicting net recommendation value NPS (network performance indicator) | |
| CN111709472B (en) | Method for dynamically fusing rules to fraud behavior recognition model | |
| CN110909148A (en) | Customer service assisting method and device | |
| Petrovic | Adopting Data Mining Techniques in Telecommunications Industry: Call Center Case Study | |
| EP4203448A1 (en) | Systems and methods for use in blocking of robocall and scam call phone numbers | |
| US20230344933A1 (en) | Systems and methods for use in blocking of robocall and scam call phone numbers | |
| CN116644744A (en) | Customer appeal trend analysis method and system | |
| CN116976716A (en) | Customer satisfaction evaluation method, device, electronic equipment and computer program product | |
| Mandić et al. | Clique comparison and homophily detection in telecom social networks | |
| CN114265505A (en) | Man-machine interaction processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |