Intelligent customer service method and device, electronic device, and storage medium

Abstract

The present disclosure provides a kind of intelligent customer service method and device, electronic equipment, storage medium;It is related to data processing technical field.The method comprises: identifying entity information sent by user in customer service session;In response to the operation of the control corresponding to target business component, according to the entity information, matching associated content in corresponding association library;The association library is constructed according to the association between each business node in the business process corresponding to business scenario;Send the associated content to the user client in the customer service session.The present disclosure can solve the problem that the service quality and service efficiency are low due to artificial query each business system in the process of artificial customer service in related technology.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more specifically, to an intelligent customer service method and apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of internet technology, more and more e-commerce platforms have emerged. A key objective of e-commerce platform management is to improve the quality and efficiency of customer service.

[0003] In related technologies, customer service personnel need to frequently switch between various business systems to query relevant business information based on the information provided by users. This method is prone to errors, affecting service quality, and has a low service response speed, resulting in low service efficiency.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide an intelligent customer service method and apparatus, electronic device, and storage medium, thereby solving to some extent the problem of low service quality and efficiency caused by manual inquiries into various business systems during the manual customer service process in related technologies.

[0006] According to a first aspect of this disclosure, an intelligent customer service method is provided, the method comprising: identifying entity information sent by a user in a customer service session; responding to an operation on a control corresponding to a target business component on the customer service client, matching related content in a corresponding relational database based on the entity information; the relational database being constructed based on the relational relationships between business nodes in a business process corresponding to a business scenario; and sending the related content to the user client in the customer service session.

[0007] Optionally, the association database includes a business association tree, and the method further includes: configuring corresponding business components according to the business scenario of the customer service session; constructing a business association tree for each business component corresponding to the business scenario; and establishing an association between the association tree and the corresponding control of the business component.

[0008] Optionally, the entity information includes the entity's attribute information and status information. The construction of the business association tree for the business scenario includes: determining the first-level child node of the business association tree based on the entity's attribute information; creating a second-level child node under the first-level child node based on the status information corresponding to the entity; determining the response content corresponding to each status information; and using the response content as the terminal child node of the second-level child node, wherein the terminal child node is the associated content.

[0009] Optionally, matching associated content based on the entity information includes: in response to an operation on the control corresponding to the target business component, matching the target entity information corresponding to the target business component in the entity information; matching nodes in the corresponding business association tree according to the business rules corresponding to the nodes based on the target entity information to determine the target path; and taking the content of the terminal child node corresponding to the target path as the associated content.

[0010] Optionally, the associated content includes a response type, and before sending the associated content, the method further includes: rendering the associated content according to the response type.

[0011] Optionally, the method further includes: caching real-time messages of the customer service session, the real-time messages including entity information and response content in the customer service session; and retrieving and displaying the latest content of the customer service session from the cache in response to a switching operation for the customer service session.

[0012] Optionally, the method further includes: statistically analyzing the usage frequency information of the controls corresponding to each of the business components within the target period; determining the priority order of the controls corresponding to each of the business components based on the usage frequency information; and generating and displaying a display list of the controls corresponding to each of the business components based on the priority order.

[0013] Optionally, displaying the list of controls corresponding to the business component includes: displaying the list as a plugin page on the customer service conversation page of the customer service client.

[0014] According to a second aspect of this disclosure, an intelligent customer service device is provided, the device comprising: an identification module, a matching module, and a sending module; the identification module is used to identify entity information sent by a user in a customer service session; the matching module is used to, in response to an operation on a control corresponding to a target business component on the customer service terminal, match related content in a corresponding relational database based on the entity information; the relational database is constructed based on the relational relationships between business nodes in the business process corresponding to the business scenario; and the sending module is used to send the related content to the user client in the customer service session.

[0015] According to a third aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the above embodiments.

[0016] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: one or more processors; and a storage device for one or more programs, which, when executed by the one or more processors, cause the one or more processors to perform the method described in any of the above embodiments.

[0017] The exemplary embodiments disclosed herein may have some or all of the following beneficial effects:

[0018] In the intelligent customer service method provided by the exemplary embodiments of this disclosure, on the one hand, entity information sent by the user in the customer service session can be identified; in response to the operation of the control corresponding to the target business component on the customer service terminal, related content can be matched in the corresponding relational database based on the entity information; one-click query of related content can be realized, avoiding frequent switching between different business systems, with high query accuracy and improved service response speed and service efficiency. On the other hand, a relational database can be constructed based on the relationship between each business node in the business process. After the business process is divided according to the business nodes, the relationship between different business nodes can be established, and the business process can be transformed into a relational database. Thus, the response result (related content) corresponding to the business process can be quickly matched based on the relational database for different entity information, realizing rapid relational query of different businesses and improving service response speed and service efficiency. In addition, with business scenarios as the dimension, a relational database is constructed for each business scenario, which can be applied to different business scenarios and new business scenarios, and has a wide range of applications.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0021] Figure 1 The illustration shows a schematic diagram of the system architecture of an intelligent customer service method and apparatus according to an embodiment of the present disclosure.

[0022] Figure 2The diagram illustrates one of the flowcharts of an intelligent customer service method according to an embodiment of the present disclosure.

[0023] Figure 3 A schematic diagram of a business association tree structure is shown in one embodiment of the present disclosure.

[0024] Figure 4 The illustration shows a business component display page and a configuration page according to one embodiment of the present disclosure.

[0025] Figure 5 The flowchart of a smart customer service method according to one embodiment of the present disclosure is illustrated in the schematic diagram.

[0026] Figure 6 The diagram illustrates a front-end design architecture of a client according to an embodiment of the present disclosure.

[0027] Figure 7 The diagram illustrates a structural block diagram of an intelligent customer service device according to an embodiment of the present disclosure.

[0028] Figure 8 A block diagram of an electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0029] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0030] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0031] This disclosure addresses situations in the logistics industry where the sender is not present at the drop-off point, and an order is placed online with a courier picking it up at a designated location. The intelligent customer service method disclosed in this specification is described below with reference to specific embodiments.

[0032] Figure 1 A schematic diagram of a system architecture 100 for an exemplary application environment in which an intelligent customer service method and apparatus according to embodiments of this disclosure can be applied is shown. Figure 1 As shown, system architecture 100 may include user terminal 101 and server 102. A network provides a communication link between user terminal 101 and server 102. The network may include various connection types, such as wired, wireless communication links, or fiber optic cables. User terminal 101 may be various electronic devices with a display screen, including but not limited to desktop computers, portable computers, smartphones, and tablets. It should be understood that... Figure 1 The number of terminals, networks, and servers shown is merely illustrative. Depending on implementation needs, there can be any number of terminals, networks, and servers. For example, user terminal 101 could be tens of thousands of terminals using an e-commerce platform.

[0033] For example, a user client is installed on a user terminal, and the server can be a backend server for the customer service client. The server can also be connected to the customer service terminal, and the customer service client is installed on the customer service terminal. The server and the customer service terminal together form the customer service client. When a user initiates a customer service session on the user client, the server identifies the entity information sent by the user in the customer service session. In response to operations on the corresponding controls of the target business component in the customer service client, the server matches the associated content in the corresponding relationship database based on the entity information. The relationship database is constructed according to the relationship between various business nodes in the business process corresponding to the business scenario, with one relationship database corresponding to one business scenario. The associated content is then sent to the user client in the customer service session.

[0034] The intelligent customer service method provided in this embodiment can be executed by server 102, and correspondingly, the intelligent customer service device can also be set in server 102.

[0035] refer to Figure 2 As shown, an example embodiment of the intelligent customer service method provided in this disclosure may include the following steps S210 to S230.

[0036] Step S210: Identify entity information sent by the user in the customer service session.

[0037] Step S220: In response to the operation of the control corresponding to the target business component on the client side, the associated content is matched in the corresponding relationship database according to the entity information; the relationship database is constructed according to the relationship between each business node in the business process corresponding to the business scenario.

[0038] Step S230: Send the associated content to the user client in the customer service session.

[0039] In the intelligent customer service method provided in this example implementation, on the one hand, it can identify entity information sent by the user in the customer service session; respond to the operation of the corresponding control of the target business component, and match the related content in the corresponding relationship database according to the entity information; realize one-click query of related content, avoid frequent switching between different business systems, achieve high query accuracy, and improve service response speed and service efficiency. On the other hand, it can construct a relationship database based on the relationship between each business node in the business process. After dividing the business process according to the business nodes, it can establish relationship between different business nodes, transform the business process into a relationship database, so that different entity information can be quickly matched with the results (related content) corresponding to the business process based on the relationship database, realize fast related query of different businesses, and improve service response speed and service efficiency. In addition, taking business scenarios as the dimension, a relationship database is constructed for each business scenario, which can be applied to different business scenarios and new business scenarios, and has a wide range of applications.

[0040] The steps of this disclosure are described in more detail below.

[0041] In step S210, entity information sent by the user in the customer service session is identified.

[0042] In this example implementation, a customer service session refers to a conversation message initiated by a user to the platform's customer service regarding objects within the e-commerce platform. For example, when browsing or shopping on an e-commerce platform, a user may initiate a conversation message to inquire about products, orders, or service requests within the platform. Entity information refers to entity-related information associated with objects within the platform. For example, an entity can be a brand, category, product, product attributes, such as product identifiers, codes, order numbers, tracking numbers, return / exchange tracking numbers, service request numbers, product categories, etc., related to the product; the recipient information of the order containing the product (such as address, contact information, name, etc.); the store identifier of the ordered product, etc. It may also include various attribute information of the entity (such as order number or product identifier) ​​(such as whether the entity information exists, entity attribute values, etc.) and status information (such as the order status, logistics status, or after-sales status corresponding to the order number, etc.), but this example does not limit this.

[0043] In this example implementation, artificial intelligence recognition technology can be used to extract entity information from customer service conversations. For instance, entity information recognition can be based on regular expressions or machine learning. Based on regular expressions, the word formation patterns of entity words and high-frequency context words are utilized. For example, product attribute words include: "number + brand" describing the product brand, "number + category" describing the product category, etc. These types of words can be matched using regular expressions. Based on machine learning, for example, BiLSTM (Bidirectional Long Short-Term Memory Network) + CRF (Conditional Random Field) can be used for entity recognition.

[0044] In step S220, in response to the operation of the control corresponding to the target business component of the client, the associated content is matched in the corresponding relationship database according to the entity information.

[0045] In this example implementation, business components can be configured for each business scenario, and a corresponding relationship database can be built for each business component. This allows for the matching of response content corresponding to entity information within the business scenario from the relationship database. The relationship database can be built based on the relationships between business nodes in the business process. For example, a business process within a business scenario can be divided into multiple business steps, and corresponding business rules can be set for each step. Different combinations of business rules can then be used to determine the corresponding response content.

[0046] For example, the relationship database is a business relationship tree, and the method may further include the following steps:

[0047] Configure the corresponding business components based on the business scenario of the customer service session.

[0048] In this example implementation, the business scenario corresponds to the user's conversation content in the customer service session. Taking an e-commerce platform as an example, business scenarios may include orders (such as order inquiry, order restoration, order splitting, order expediting, etc.), compensation (product compensation or price difference adjustment), logistics (logistics inquiry), price protection, invoices (invoice application), warranty (repair application), work order consultation, balance withdrawal, tracking services (order tracking, logistics tracking), etc. The granularity of the business scenario can be determined according to the actual situation.

[0049] In this example implementation, a business component refers to a functional component configured on the client side for each business scenario. Operation controls and editing pages can be configured for each business component. The editing page can include basic information about the business component (such as name, description, display icon, etc.), associated entity information, and associated business relationship tree information, such as... Figure 4 The lower half shows the editing page corresponding to the order query business component.

[0050] For each business component, construct a business association tree corresponding to the business scenario.

[0051] In this example implementation, each business component corresponds one-to-one with a business association tree, which means each component corresponds one-to-one with a business scenario, such as... Figure 4 As shown in the upper part.

[0052] For example, entity information may include the entity's attribute information and status information, and a business association tree can be constructed through the following steps.

[0053] Based on the entity's attribute information, determine the first-level child node of the business association tree.

[0054] In this example implementation, the entity's attribute information may include the presence or absence of entity information, and first-level child nodes can be determined based on the presence or absence of that entity information. For example, two first-level child nodes can be defined based on the presence or absence of an order number: a child node with an order number and a child node without an order number. Figure 3 As shown.

[0055] Based on the status information of the entity, create a second-level child node under the first-level child node.

[0056] In this example implementation, the status information corresponding to an entity can be any of the entity's possible states. For example, the order status information corresponding to an order number can include: order cancelled, order completed, order locked, logistics received, order returned, order awaiting payment, order payment completed, etc. Each state's corresponding business rule can correspond to one or more second-level child nodes. For example, an order cancelled can correspond to one business rule used to determine whether the order has been cancelled. An order locked can correspond to multiple business rules, first determining whether the order has been shipped (corresponding to one business rule), then determining whether the order has been delivered (corresponding to another business rule).

[0057] In this example implementation, business rules can be composed of system components, corresponding regular expressions, and logical operators to form a second-level child node. Each second-level child node is a condition node corresponding to a business logic. Between second-level child nodes with a business logic sequence, the node corresponding to the business logic executed later can be used as the child node of the node corresponding to the business logic executed earlier. That is, an association relationship can be established between second-level child nodes according to the business logic.

[0058] Determine the response content corresponding to each status message.

[0059] In this example implementation, each business scenario will have corresponding response content for its business logic. For example, the response content for "order cancelled" could be tracking information about the order cancellation status. The response content can be configured according to the business scenario and business logic.

[0060] The response content is set as the terminal child node of the second-level child node, and the terminal child node is the associated content.

[0061] In this example implementation, the terminal child node of each business association tree is the response content, thus completing the construction of the association tree. For example, the construction result of the business association tree for the order reminder business scenario is as follows: Figure 3 As shown, the root node can be an empty node. First-level child nodes are created to determine if there are disputed orders. Second-level child nodes are created under each first-level child node, such as "Order Cancelled," "Order Completed," "Logistics Signed For," "Order Locked," and other statuses. Second-level child nodes can also have sub-level child nodes, such as child nodes under the corresponding nodes for other statuses. Each business logic is ultimately configured with response content as the terminal child node (e.g., Answer 1, Answer 2, Answer 2... Answer x... Answer N). In the diagram, "..." indicates an omitted portion of the answer.

[0062] Establish relationships between the relationship tree and the corresponding controls of the business components.

[0063] In this example implementation, a rapid matching process for the response content of the business scenario is achieved by establishing an association between the relationship tree and the corresponding control of the business component.

[0064] For example, entity information can be matched with related content through the following steps.

[0065] In response to operations on the controls corresponding to the target business component, the target entity information corresponding to the target business component is matched in the entity information; based on the target entity information, node matching is performed in the corresponding business association tree according to the business rules corresponding to the node to determine the target path; the content of the terminal child node corresponding to the target path is used as the associated content.

[0066] In this example implementation, entity information may include multiple entities (such as order number, product number, waybill number, etc.). The target entity can be selected from these entities based on the business scenario. For example, in a logistics end-to-end tracking scenario, the target entity could be the waybill number. A mapping table between business scenarios and target entity information can be established, allowing for quick determination of the target entity information.

[0067] In this example implementation, each node has corresponding business rules. By matching business rules between different nodes, the target path is determined, thereby determining the response content of the corresponding terminal child node. Business rules can be rule expressions formed using regular expressions and / or logical operators, and can be implemented in conjunction with system functional components. A regular expression is a logical formula for string manipulation, using predefined specific characters and combinations of these characters to form a "rule string." This "rule string" expresses a filtering logic for the string. For example, a business rule could be to obtain the context order ID from the user parameter service.

[0068] In step S230, the associated content is sent to the user client in the customer service session.

[0069] In this example implementation, the associated content can be sent to the corresponding user client or to the customer service client so that the customer service client can process the associated content before sending it to the user client. This example does not impose any restrictions on this.

[0070] For example, the processing of related content by the customer service client may include rendering the related content according to the response type.

[0071] In this example implementation, the associated content may include a response type, which can be configured during the business association tree construction process and bound to the corresponding response content. The response type can include text type and template type; text type refers to plain text display, while template type refers to content display according to a corresponding template component. The associated content (response content) can be rendered according to the response type to generate response information, which is then sent from the customer service client to the user client. This enables rapid response to user inquiries and improves user experience.

[0072] In some embodiments, the method further includes caching real-time messages from customer service sessions.

[0073] In this example implementation, real-time messages generated during a customer service session can be cached according to the session dimension. For example, entity information and response content in the real-time messages of a customer service session can be cached.

[0074] In response to switching operations for a customer service session, retrieve and display the latest customer service session content from the cache.

[0075] In this example implementation, when the customer service representative switches to the current customer service session window, the latest customer service session content can be retrieved from the cache to achieve real-time message refresh, making it easier for the customer service representative to understand the user's intent in a timely manner and improve service efficiency.

[0076] In some embodiments, the method further includes: statistically analyzing the usage frequency information of the corresponding controls of the business components within a target period.

[0077] In this example implementation, the target period can be one day or several days, which can be configured according to the implementation situation. The usage frequency information refers to the operation frequency information of the corresponding control of the business component, such as the usage frequency within one day.

[0078] Based on usage frequency information, determine the priority order of controls corresponding to business components.

[0079] In this example implementation, the display order of the controls corresponding to each business component can be adjusted according to their usage frequency, and the priority order can be from high to low according to the usage frequency from high to low.

[0080] Generate and display a list of controls corresponding to the business components according to their priority.

[0081] In this example implementation, the priority order corresponds to the sorting of the controls displayed for each business component. For example, when displayed in a vertical list format, the most frequently used controls can be placed at the front; when displayed in a matrix format, the most frequently used controls can be placed in the first or middle position of the first row, such as... Figure 4 As shown in the upper part, the order query control, being a frequently used feature, is set to the first one in the first row.

[0082] For example, the list can be displayed as a plugin page on the customer service conversation page of the customer service client to facilitate customer service operations. The specific display effect is as follows: Figure 4 As shown in the upper part.

[0083] For example, the implementation process of the intelligent customer service method disclosed herein is as follows: Figure 5 As shown, this can be achieved through the following steps.

[0084] Step S501: The client creates the business components corresponding to the business scenario.

[0085] Step S502: Construct the corresponding business association tree based on the business scenario corresponding to the business component.

[0086] Step S503: The client establishes an association between the association tree and the corresponding controls of the business components.

[0087] Step S504: The user initiates a customer service session with the client.

[0088] Step S505: The client identifies the entity information sent by the user in the customer service session.

[0089] In step S506, the client responds to the operation on the control corresponding to the target business component by matching the associated content in the corresponding relationship database based on the entity information.

[0090] In step S507, the client renders the associated content based on the response type.

[0091] In step S508, the client sends the rendered content to the client.

[0092] In the above embodiments, the customer service client may include a front-end and a back-end, which work together to provide customer service to users. The back-end of the customer service client can be configured with a business association tree and its related business rule nodes, as well as the correspondence between entity information and the business association tree. The front-end configuration of the customer service client is as follows: Figure 6 As shown, the client-side frontend can be configured with a message listening service 610, a business component library service 620, an entity management service 630, a business component rendering service 640, a message push service 650, and a web plugin page 660. The message listening service 610 monitors the client-side session message queue in real time and transmits the monitored messages to the business component library service 620 via a protocol conversion gateway. The business component library service 620 transmits the identified entity information to the entity management service 630 for entity information management in this session. The business component library service 620 sends entity update messages to the web plugin page 660 via the message push service 650, and the web plugin page 660 feeds back to the business component library service 620 via a transmission protocol. During the response process, the business component library service 620 sends the response content to the business component rendering service 640 for rendering.

[0093] This disclosure allows for the creation of corresponding business components for specific business scenarios. All controls corresponding to these components are displayed as plugin pages, enabling customer service personnel to directly manipulate these controls for rapid response to user requests. This avoids frequent switching and querying between different business systems (such as order systems and logistics systems), improving the speed and accuracy of user service responses. Furthermore, this disclosure allows for dynamic configuration and editing of corresponding business components to adapt to frequent changes or upgrades in various business systems, eliminating the need for re-developing code each time.

[0094] This disclosure constructs a corresponding business association tree for each business scenario, thereby transforming the business processes or rules within those scenarios into a node-based structure. This enables rapid determination of response content based on the business scenario, accelerating customer service response time and improving user experience. For new business scenarios, only the corresponding business components need to be developed, without requiring modifications to the system. It offers high configuration flexibility and enables rapid response to new business needs.

[0095] Furthermore, this example embodiment also provides an intelligent customer service device 700. This intelligent customer service device 700 can be applied to a customer service terminal. (See reference...) Figure 7 As shown, the intelligent customer service device 700 may include: an identification module 710, a matching module 720, and a sending module 730. The identification module 710 is used to identify entity information sent by the user in the customer service session; the matching module 720 is used to match related content in the corresponding relationship database based on the entity information in response to the operation of the control corresponding to the target business component on the customer service terminal; the relationship database is constructed according to the relationship between each business node in the business process corresponding to the business scenario; and the sending module 730 is used to send the related content to the user client in the customer service session.

[0096] In one exemplary embodiment of this disclosure, the association library includes a business association tree, and the device 700 further includes: a configuration module, which can be used to configure corresponding business components according to the business scenario of the customer service session; a construction module, which can be used to construct a business association tree for each business component corresponding to the business scenario; and an association module, which can be used to establish an association between the association tree and the corresponding controls of the business components.

[0097] In one exemplary embodiment of this disclosure, the entity information includes the entity's attribute information and status information. The construction module can be used to: determine the first-level child node of the business association tree based on the entity's attribute information; create a second-level child node under the first-level child node based on the status information corresponding to the entity; determine the response content corresponding to each status information; and use the response content as the terminal child node of the second-level child node, where the terminal child node is the associated content.

[0098] In one exemplary embodiment of this disclosure, the matching module 720 may also be used to: in response to an operation on the control corresponding to the target business component, match the target entity information corresponding to the target business component in the entity information; based on the target entity information, perform node matching in the corresponding business association tree according to the business rules corresponding to the node to determine the target path; and take the content of the end child node corresponding to the target path as the associated content.

[0099] In one exemplary embodiment of this disclosure, the associated content includes a response type, and the apparatus 700 further includes a rendering module, which renders the associated content according to the response type before sending the associated content.

[0100] In one exemplary embodiment of this disclosure, the apparatus 700 further includes a caching module, which can be used to: cache real-time messages of a customer service session, the real-time messages including entity information and response content in the customer service session; and in response to a switching operation for a customer service session, retrieve and display the latest content of the customer service session from the cache.

[0101] In one exemplary embodiment of this disclosure, the apparatus 700 further includes a display module, which can be used to: collect usage frequency information of the corresponding controls of each business component within a target period; determine the priority order of the corresponding controls of each business component based on the usage frequency information; and generate and display a display list of the corresponding controls of each business component based on the priority order.

[0102] In one exemplary embodiment of this disclosure, the display module can also be used to display a display list in the form of a plugin page on the customer service session page of the customer service client.

[0103] The specific details of each module or unit in the aforementioned intelligent customer service device have been described in detail in the corresponding intelligent customer service method, so they will not be repeated here.

[0104] On the other hand, this application also provides a computer-readable medium, which may be included in the terminal device described in the above embodiments; or it may exist independently and not assembled into the terminal device. The computer-readable medium carries one or more programs that, when executed by the terminal device, cause the terminal device to implement the methods described in the following embodiments. For example, the terminal device may implement... Figure 2 , Figure 5 The various steps shown are as follows.

[0105] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0106] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0107] like Figure 8 As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0108] The storage unit stores program code, which can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0109] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0110] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0111] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0112] Electronic device 800 can also communicate with one or more external devices 870 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RA identification systems, tape drives, and data backup storage systems.

[0113] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or electronic device, etc.) to execute the methods according to the embodiments of this disclosure.

[0114] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0115] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in this disclosed technical solution all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0116] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps, such as omitting certain steps, combining multiple steps into one step, and / or breaking down one step into multiple steps, should all be considered part of this disclosure.

[0117] It should be understood that this disclosure, as disclosed and defined herein, extends to all alternative combinations of two or more individual features mentioned or apparent in the text and / or figures. All these different combinations constitute multiple alternative aspects of this disclosure. The embodiments described in this specification illustrate the best known mode for implementing this disclosure and will enable those skilled in the art to utilize it.

Claims

1. An intelligent customer service method, characterized in that, The method includes: Identify and extract entity information sent by users in customer service conversations; In response to operations on the corresponding controls of the target business component on the client side, the associated content is matched in the corresponding relationship database based on the entity information; the relationship database is constructed based on the relationship between each business node in the business process corresponding to the business scenario. Send the associated content to the user client in the customer service session; The relationship database includes a business relationship tree, and the entity information includes the entity's attribute information and status information. Based on the entity information, related content is matched, including: In response to the operation of the control corresponding to the target business component, the target entity information corresponding to the target business component is matched in the entity information according to the business scenario, wherein a mapping table between the business scenario and the target entity information is pre-established. Based on the target entity information, node matching is performed in the corresponding business association tree according to the business rules corresponding to the nodes to determine the target path; The content of the terminal child node corresponding to the target path is used as the associated content.

2. The intelligent customer service method according to claim 1, characterized in that, The method further includes: Configure the corresponding business components according to the business scenario of the customer service session; For each of the aforementioned business components, construct a business association tree corresponding to the business scenario; Establish an association between the relationship tree and the corresponding control of the business component.

3. The intelligent customer service method according to claim 2, characterized in that, The construction of the business relationship tree for the business scenario includes: Based on the attribute information of the entity, determine the first-level child node of the business association tree; Based on the status information corresponding to the entity, create a second-level child node under the first-level child node; Determine the response content corresponding to each of the aforementioned status information; The response content is used as the terminal child node of the second-level child node, and the terminal child node is the associated content.

4. The intelligent customer service method according to claim 1, characterized in that, The associated content includes a response type. Before sending the associated content, the method further includes: The associated content is rendered based on the response type.

5. The intelligent customer service method according to claim 1, characterized in that, The method further includes: The real-time messages of the customer service session are cached, and the real-time messages include entity information and response content in the customer service session; In response to a switching operation for the customer service session, the latest content of the customer service session is retrieved from the cache and displayed.

6. The intelligent customer service method according to claim 1, characterized in that, The method further includes: The usage frequency information of the corresponding controls for each of the aforementioned business components is collected within the target period. Based on the usage frequency information, determine the priority order of the controls corresponding to each of the business components; Based on the aforementioned priority order, a list of controls corresponding to each of the aforementioned business components is generated and displayed.

7. The intelligent customer service method according to claim 6, characterized in that, The list of controls corresponding to the business components includes: The display list is shown as a plugin page on the customer service conversation page of the customer service client.

8. An intelligent customer service device, characterized in that, The device includes: The identification module is used to identify and extract entity information sent by users in customer service conversations; The matching module is used to respond to the operation of the control corresponding to the target business component on the client side, and match the associated content in the corresponding relationship library according to the entity information; the relationship library is constructed according to the relationship between each business node in the business process corresponding to the business scenario; The sending module is used to send the associated content to the user client in the customer service session; The relationship database includes a business relationship tree, and the entity information includes the entity's attribute information and status information; the matching module is configured to execute: In response to the operation of the control corresponding to the target business component, the target entity information corresponding to the target business component is matched in the entity information according to the business scenario, wherein a mapping table between the business scenario and the target entity information is pre-established. Based on the target entity information, node matching is performed in the corresponding business association tree according to the business rules corresponding to the nodes to determine the target path; The content of the terminal child node corresponding to the target path is used as the associated content.

9. An electronic device, characterized in that, include: One or more processors; as well as A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images