Telephone banking navigation method, device, electronic device and storage medium
By building a telephone banking business knowledge base and automatically adjusting navigation nodes, the problem of low efficiency of telephone banking services in the existing technology is solved, fast and efficient customer navigation and service provision are achieved, and overall service efficiency and customer experience are improved.
Patent Information
- Application Number
- CN202110961465.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-20
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2041-08-20
AI Technical Summary
The existing telephone banking services are time-consuming and can only be selected for single nodes due to the progressive navigation method of step by step, resulting in low service efficiency and cannot provide services to customers quickly and efficiently, which affects the overall efficiency of the banking system.
Build a knowledge base for telephone banking business, and by determining the customer's current navigation node and navigation intention, searching matching navigation nodes from the knowledge base, realizing automatic adjustment of navigation nodes, and providing fast matching and response to voice interaction.
It improves the customer's knowledge hit rate, reduces the telephone banking service time, quickly provides customers with services in the business field, and improves service efficiency and customer experience.
Smart Images

Figure CN113657913B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and more specifically, to a telephone banking navigation method, device, electronic equipment and storage medium. Background Art
[0002] Telephone banking is an important part of customer service, and existing telephone banking services often require customers to select relevant questions step by step according to the multi-level navigation nodes set by the system.
[0003] This step-by-step approach is time-consuming and can only perform single-node selection during the service process. Ultimately, it cannot provide customers with fast, efficient, and reliable services, and also affects the overall service efficiency of the banking system. Summary of the invention
[0004] In view of this, in order to solve the above problems, the present invention provides a telephone banking navigation method, device, electronic device and storage medium, and the technical solution is as follows:
[0005] A telephone banking navigation method, the method comprising:
[0006] Constructing a knowledge base for telephone banking services, wherein the nodes of the knowledge base are navigation nodes under the telephone banking services, and the navigation nodes belonging to leaf nodes are linked to corresponding business knowledge;
[0007] Determine a first navigation node where the incoming customer is currently located, and the customer's navigation intention;
[0008] According to the child nodes of the first navigation node in the knowledge base, a second navigation node matching the navigation intention is retrieved from the knowledge base to output business knowledge of a target navigation node, which is a leaf node of the second navigation node.
[0009] Preferably, the method for determining the navigation intention includes:
[0010] Acquire confirmation information input by the customer, wherein the confirmation information includes a node identifier that can uniquely mark a navigation node, and the node identifier may be one or more; or
[0011] The question information input by the customer is obtained, and semantic detection is performed on the question information to determine keywords that can indicate navigation nodes.
[0012] Preferably, the retrieving a second navigation node matching the navigation intention from the knowledge base according to the child nodes of the first navigation node in the knowledge base comprises:
[0013] Determine candidate navigation nodes that are leaf nodes of the first navigation node in the knowledge base;
[0014] Calculating the similarity between the navigation intention and the business knowledge linked to the candidate navigation node;
[0015] If there are candidate navigation nodes with a similarity higher than the corresponding threshold, the candidate navigation node with the highest similarity is used as the second navigation node, and the second navigation node is the target navigation node.
[0016] Preferably, the retrieving a second navigation node matching the navigation intention from the knowledge base according to the subnodes of the first navigation node in the knowledge base further includes:
[0017] If there is no candidate navigation node with a similarity higher than the corresponding threshold, obtaining the number of hits of different navigation nodes in the knowledge base in the historical navigation records, where the number of hits of a navigation node is the maximum number of hits of the child nodes of the navigation node;
[0018] A plurality of navigation nodes with the largest number of hits are selected from the first level child nodes of the first navigation node as the second navigation nodes.
[0019] Preferably, the method further comprises:
[0020] Obtaining feedback information from the customer regarding the multiple outputs of business knowledge to determine the number of misses from the customer;
[0021] In a case where the number of misses is greater than a corresponding threshold, an agent is allocated to the customer, so as to provide navigation service to the customer through the allocated agent.
[0022] A telephone banking navigation device, comprising:
[0023] A knowledge base construction module is used to construct a knowledge base for telephone banking services, wherein the nodes of the knowledge base are navigation nodes under the telephone banking services, and the navigation nodes belonging to leaf nodes are linked to corresponding business knowledge;
[0024] A navigation service module is used to determine the first navigation node where the incoming customer is currently located and the customer's navigation intention; based on the child nodes of the first navigation node in the knowledge base, a second navigation node matching the navigation intention is retrieved from the knowledge base to output the business knowledge of the target navigation node, where the target navigation node is a leaf node of the second navigation node.
[0025] Preferably, the navigation service module determines the navigation intention in a manner including:
[0026] Acquire confirmation information input by the customer, wherein the confirmation information includes a node identifier that can uniquely mark a navigation node, and the node identifier may be one or more; or
[0027] The question information input by the customer is obtained, and semantic detection is performed on the question information to determine keywords that can indicate navigation nodes.
[0028] Preferably, the navigation service module for retrieving a second navigation node matching the navigation intention from the knowledge base according to the subnodes of the first navigation node in the knowledge base to output the business knowledge of the target navigation node is specifically used for:
[0029] Determine candidate navigation nodes that are leaf nodes of the first navigation node in the knowledge base; calculate the similarity between the navigation intention and the business knowledge linked to the candidate navigation nodes; if there are candidate navigation nodes with a similarity higher than a corresponding threshold, use the candidate navigation node with the highest similarity as the second navigation node, and the second navigation node is the target navigation node.
[0030] An electronic device comprises: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement the telephone banking navigation method.
[0031] A storage medium stores computer executable instructions, and the computer executable instructions are used to execute the telephone banking navigation method.
[0032] Compared with the prior art, the present invention has the following beneficial effects:
[0033] The present invention provides a telephone banking navigation method, device, electronic device and storage medium. By constructing a knowledge base of telephone banking services, the current navigation node of the incoming customer can be located, and another matching navigation node can be retrieved from the child nodes of the knowledge base from the located navigation node according to the navigation intention, so as to provide the customer with telephone banking navigation services and finally output business knowledge. Based on the present invention, the automatic adjustment of navigation nodes can be realized, the knowledge hit rate of customers can be improved, the overall service time of telephone banking can be reduced, and services in corresponding business fields can be quickly provided to customers. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0035] Figure 1 A method flow chart of a telephone banking navigation method provided by an embodiment of the present invention;
[0036] Figure 2 A schematic diagram of a navigation node provided by an embodiment of the present invention;
[0037] Figure 3 A partial method flow chart of the telephone banking navigation method provided by an embodiment of the present invention;
[0038] Figure 4 A schematic diagram of the structure of a telephone banking navigation device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0041] The embodiment of the present invention provides a telephone banking navigation method, which records the navigation nodes of the customer based on the knowledge base, and supports the customer to quickly match and respond to business problems at various levels of navigation nodes through voice interaction. The method flow chart of the method is as follows: Figure 1 As shown, the following steps are included:
[0042] S10, constructing a knowledge base for telephone banking services, wherein the nodes of the knowledge base are navigation nodes under the telephone banking services, and the navigation node links belonging to leaf nodes have corresponding business knowledge.
[0043] In the embodiment of the present invention, the knowledge manager maintains the navigation knowledge of the telephone banking service, and maintains, counts and adjusts the navigation nodes under the telephone banking service in the knowledge base. Specifically, the nodes at all levels in the knowledge base are synchronized with the navigation nodes of the telephone banking service, and the terminal nodes of the knowledge base, i.e., the leaf nodes, are linked to the specific business knowledge, i.e., the detailed knowledge of each business type.
[0044] Knowledge administrators can add or update the knowledge base by batch uploading or maintaining it one by one. They can also count the application frequency of each navigation node in the knowledge base and intelligently adjust the order of navigation nodes.
[0045] S20, determining the first navigation node where the incoming customer is currently located, and the customer's navigation intention.
[0046] In the embodiment of the present invention, the location of the navigation node currently located by the customer, that is, the first navigation node, can be updated in real time. Under the first navigation node, the customer can input relevant information representing the navigation intention. In the embodiment of the present invention, the customer can choose to directly input a question to make a request, or specify the navigation node to be entered through the telephone banking service.
[0047] Specifically, the methods for determining navigation intent include:
[0048] Obtain confirmation information input by the customer, where the confirmation information includes a node identifier that can uniquely mark a navigation node, and the node identifier can be one or more; or
[0049] Obtain the question information input by the customer, and perform semantic detection on the question information to determine the keywords that can indicate the navigation node.
[0050] In the embodiment of the present invention, the confirmation information input by the client includes the node identifier of the navigation node to be entered, such as the node name, node serial number, etc. When the client determines the navigation node to be entered, the node identifier is one; when the client is not sure which navigation node to select, the client can select multiple navigation nodes at the same time, that is, the node identifiers are multiple.
[0051] In addition, the question information input by the customer contains description information of the navigation node to be entered, which can characterize the customer's needs or purposes. Therefore, semantic detection of the question information can determine the keywords indicating the navigation node, and use the keywords to determine the navigation node to be entered.
[0052] It should be noted that the mapping relationship between different navigation nodes and keywords can be pre-configured, and the embodiment of the present invention does not limit this.
[0053] It should be noted that the above confirmation information and question information may be in text form, voice form, or other body language form, which is not limited in the embodiment of the present invention.
[0054] S30, according to the child nodes of the first navigation node in the knowledge base, retrieving the second navigation node matching the navigation intention from the knowledge base to output the business knowledge of the target navigation node, the target navigation node being the leaf node of the second navigation node.
[0055] In the embodiment of the present invention, in order to facilitate understanding of the logical relationship of the navigation nodes in the knowledge base, Figure 2Take the navigation node diagram shown as an example to illustrate that the customer's incoming line is located at navigation node 1, and the customer can choose to enter one of navigation nodes 2, 3, and 4 under navigation node 1; assuming that the customer chooses to enter navigation node 2 under navigation node 1, then under navigation node 2, he can further choose to enter one of navigation nodes 5, 6, and 7; assuming that the customer chooses navigation node 3 under navigation node 1, then under navigation node 3, he can further choose to enter one of navigation nodes 8 and 9; assuming that the customer chooses navigation node 4 under navigation node 1, the business knowledge linked to navigation node 4 can be output to the customer. Of course, navigation nodes 5, 6, 7, 8, and 9, like navigation node 4, are also terminal nodes of the knowledge base, so when they are selected, the business knowledge they are linked to will also be output to the customer.
[0056] Continue to see Figure 2 , taking navigation node 1 as an example, navigation nodes 2 to 9 are all its child nodes, while navigation nodes 2, 3, and 4 are its first-level child nodes, and navigation nodes 5, 6, 7, 8, and 9 are its second-level child nodes. In addition, navigation nodes 4, 5, 6, 7, 8, and 9 are all leaf nodes of navigation node 1.
[0057] Based on this, after determining the first navigation node, according to its child nodes in the knowledge base, the second navigation node matching the navigation intention can be retrieved therefrom. If the second navigation node is a leaf node, it can be used as the target navigation node to output its business knowledge. Conversely, if the second navigation node is not a leaf node, the customer is guided to enter the second navigation node, and the second navigation node is used as the first navigation node where the customer is currently located, and steps S20 to S30 are continued until the business knowledge is output.
[0058] In the specific implementation process, step S30 "retrieve the second navigation node matching the navigation intention from the knowledge base according to the child nodes of the first navigation node in the knowledge base" can adopt the following steps, and the method flow chart is as follows: Figure 3 As shown:
[0059] S301, determining candidate navigation nodes that are leaf nodes of a first navigation node in a knowledge base.
[0060] In the embodiment of the present invention, continue to refer to Figure 2 , taking the first navigation node as navigation node 1 as an example: the leaf nodes belonging to navigation node 1 in the knowledge base include navigation nodes 4, 5, 6, 7, 8, and 9, so the candidate navigation nodes are navigation nodes 4, 5, 6, 7, 8, and 9.
[0061] S302: Calculate the similarity between the navigation intention and the business knowledge linked to the candidate navigation node.
[0062] In the embodiment of the present invention, the first navigation node is continued to be taken as navigation node 1 as an example for explanation. Navigation nodes 4, 5, 6, 7, 8, and 9 are all linked to business knowledge. Therefore, the navigation intention can be converted into text information, and then the text similarity between the navigation intention and the business knowledge can be calculated through a text analysis tool to obtain the similarity between the navigation intention and the business knowledge linked to navigation nodes 4, 5, 6, 7, 8, and 9 respectively.
[0063] S303: If there are candidate navigation nodes with a similarity higher than a corresponding threshold, the candidate navigation node with the highest similarity is used as a second navigation node, and the second navigation node is a target navigation node.
[0064] In the embodiment of the present invention, the first navigation node is taken as navigation node 1 for example, and navigation nodes 4, 5, 6, 7, 8, and 9 have their own corresponding similarity levels, and then candidate navigation nodes with similarity levels higher than the corresponding threshold are selected, and the candidate navigation node with the highest similarity level is used as the second navigation node. For example, navigation node 4 with a similarity level of 100% is used as the second navigation node, so that the business knowledge linked to navigation node 4 is broadcasted.
[0065] In some other embodiments, if there are no candidate navigation nodes with a similarity higher than a corresponding threshold, the hit counts of different navigation nodes in the knowledge base in the historical navigation records are obtained, where the hit count of a navigation node is the maximum hit count of the child nodes of the navigation node; and from the first-level child nodes of the first navigation node, multiple navigation nodes with the largest hit counts are selected as second navigation nodes.
[0066] In the embodiment of the present invention, a counter is set for each navigation node in the knowledge base, and the counter records the hit times of the business knowledge of the corresponding navigation node and its leaf nodes, and the first-level child nodes of the first navigation node are sorted according to the hit times, and the sorting results are synchronized to the voice navigation node of the telephone bank (i.e., the first navigation node), and the k navigation nodes with the largest hit times are selected as the second navigation nodes. Among them, k can be configured in the knowledge base.
[0067] Continue with Figure 2Take an example to illustrate, according to the historical navigation records, each navigation node in the knowledge base has a corresponding number of hits. Continuing to take the first navigation node as navigation node 1 as an example, its first-level child nodes include navigation nodes 2, 3, and 4, and the number of hits of navigation node 2 is the maximum value of the number of hits of navigation nodes 5, 6, and 7, the number of hits of navigation node 3 is the maximum value of the number of hits of navigation nodes 8 and 9, and the number of hits of navigation node 4 is its own number of hits. Therefore, the k navigation nodes with the largest number of hits can be selected from navigation nodes 2, 3, and 4 as the second navigation nodes.
[0068] In some other embodiments, in the process of providing telephone banking navigation services to customers, each time the output of business knowledge is executed, the customer's feedback information on this telephone banking navigation can be obtained, thereby determining whether the business knowledge output this time meets the customer's expectations, that is, whether it hits the customer's navigation intention. Therefore, by obtaining the customer's feedback information on multiple outputs of business knowledge, the number of misses of the customer can be determined, and then when the number of misses is greater than the corresponding threshold, the customer is assigned a seat, and the navigation service for the customer is implemented through the assigned seat.
[0069] That is to say, the embodiment of the present invention can automatically handle customers who have missed multiple times. When they have missed multiple times, they can be directly transferred to a human operator according to their level, and added to the agent waiting queue. Customers can continue to select telephone banking navigation for self-service, and can be immediately transferred to a human operator once the agent is free. This can guide customers to complete the service quickly, reduce the overall waiting time of telephone banking customers, improve the comprehensive experience of customers, and prevent multiple customer interactions from affecting the customer experience.
[0070] The telephone banking navigation method provided by the embodiment of the present invention can locate the current navigation node of the incoming customer by constructing a knowledge base of telephone banking services, and retrieve another matching navigation node from the located navigation node in the subnodes of the knowledge base according to the navigation intention of the customer, thereby providing the customer with telephone banking navigation services and finally outputting business knowledge. Based on the present invention, the automatic adjustment of navigation nodes can be realized, the knowledge hit rate of customers can be improved, the overall service time of telephone banking can be reduced, and services in corresponding business fields can be quickly provided to customers.
[0071] Based on the telephone banking navigation method provided in the above embodiment, the present invention provides a device for executing the telephone banking navigation method. The structural diagram of the device is shown in FIG. Figure 4 As shown, including:
[0072] The knowledge base construction module 10 is used to construct a knowledge base for telephone banking services. The nodes of the knowledge base are navigation nodes under telephone banking services, and the navigation nodes belonging to leaf nodes are linked to corresponding business knowledge.
[0073] The navigation service module 20 is used to determine the first navigation node where the incoming customer is currently located and the customer's navigation intention; based on the child nodes of the first navigation node in the knowledge base, retrieve the second navigation node that matches the navigation intention from the knowledge base to output the business knowledge of the target navigation node, and the target navigation node is the leaf node of the second navigation node.
[0074] Optionally, the navigation service module 20 determines the navigation intention in the following manner:
[0075] Obtain confirmation information input by the customer, where the confirmation information includes a node identifier that can uniquely mark a navigation node, and the node identifier can be one or more; or
[0076] Obtain the question information input by the customer, and perform semantic detection on the question information to determine the keywords that can indicate the navigation node.
[0077] Optionally, the navigation service module 20 is used to retrieve a second navigation node matching the navigation intention from the knowledge base according to the child nodes of the first navigation node in the knowledge base, so as to output the business knowledge of the target navigation node, and is specifically used to:
[0078] Determine the candidate navigation nodes that are leaf nodes of the first navigation node in the knowledge base; calculate the similarity between the navigation intention and the business knowledge linked to the candidate navigation nodes; if there are candidate navigation nodes with a similarity higher than a corresponding threshold, use the candidate navigation node with the highest similarity as the second navigation node, and the second navigation node is the target navigation node.
[0079] Optionally, the navigation service module 20 is further used for:
[0080] If there is no candidate navigation node with a similarity higher than the corresponding threshold, obtain the number of hits of different navigation nodes in the knowledge base in the historical navigation records, where the number of hits of a navigation node is the maximum number of hits of the child nodes of the navigation node; from the first-level child nodes of the first navigation node, select multiple navigation nodes with the largest number of hits as the second navigation nodes.
[0081] Optionally, the navigation service module 20 is further used for:
[0082] Obtain feedback information from customers regarding multiple outputs of business knowledge to determine the number of misses of the customer; when the number of misses is greater than a corresponding threshold, assign an agent to the customer to provide navigation services to the customer through the assigned agent.
[0083] It should be noted that the detailed functions of each module in the embodiment of the present invention can be found in the corresponding disclosed part of the above telephone banking navigation method embodiment, which will not be described in detail here.
[0084] Based on the telephone banking navigation method provided in the above embodiment, an embodiment of the present invention provides an electronic device, which includes: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement the telephone banking navigation method.
[0085] Based on the telephone banking navigation method provided in the above embodiment, an embodiment of the present invention provides a storage medium correspondingly. The storage medium stores computer executable instructions, and the computer executable instructions are used to execute the telephone banking navigation method.
[0086] It should be noted that the telephone banking navigation method, device, electronic device and storage medium provided by the present invention can be used in the field of artificial intelligence or finance. The above is only an example and does not limit the application field of the telephone banking navigation method, device, electronic device and storage medium provided by the present invention.
[0087] The above is a detailed introduction to a telephone banking navigation method, device, electronic device and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
[0088] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0089] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device that includes a series of elements is inherent to the elements, or also includes elements inherent to these processes, methods, articles or devices. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.
[0090] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A telephone banking navigation method, characterized in that: The method comprises: Constructing a knowledge base for telephone banking services, wherein the nodes of the knowledge base are navigation nodes under the telephone banking services, and the navigation nodes belonging to leaf nodes are linked to corresponding business knowledge; Determine a first navigation node where the incoming customer is currently located, and the customer's navigation intention; According to the child nodes of the first navigation node in the knowledge base, retrieving a second navigation node matching the navigation intention from the knowledge base to output business knowledge of a target navigation node, where the target navigation node is a leaf node of the second navigation node; The retrieving a second navigation node matching the navigation intention from the knowledge base according to the child nodes of the first navigation node in the knowledge base comprises: Determine candidate navigation nodes that are leaf nodes of the first navigation node in the knowledge base; Calculating the similarity between the navigation intention and the business knowledge linked to the candidate navigation node; If there are candidate navigation nodes with a similarity higher than the corresponding threshold, the candidate navigation node with the highest similarity is used as the second navigation node, and the second navigation node is the target navigation node; If there is no candidate navigation node with a similarity higher than the corresponding threshold, obtaining the number of hits of different navigation nodes in the knowledge base in the historical navigation records, where the number of hits of a navigation node is the maximum number of hits of the child nodes of the navigation node; A plurality of navigation nodes with the largest number of hits are selected from the first level child nodes of the first navigation node as the second navigation nodes.
2. The method according to claim 1, characterized in that The method for determining the navigation intention includes: Acquire confirmation information input by the customer, wherein the confirmation information includes a node identifier that can uniquely mark a navigation node, and the node identifier may be one or more; or The question information input by the customer is obtained, and semantic detection is performed on the question information to determine keywords that can indicate navigation nodes.
3. The method according to claim 1, characterized in that The method further comprises: Obtaining feedback information from the customer regarding the multiple outputs of business knowledge to determine the number of misses from the customer; In a case where the number of misses is greater than a corresponding threshold, an agent is allocated to the customer, so as to provide navigation service to the customer through the allocated agent.
4. A telephone banking navigation device, characterized in that: The device comprises: A knowledge base construction module is used to construct a knowledge base for telephone banking services, wherein the nodes of the knowledge base are navigation nodes under the telephone banking services, and the navigation nodes belonging to leaf nodes are linked to corresponding business knowledge; A navigation service module, used to determine the first navigation node where the incoming customer is currently located and the navigation intention of the customer; according to the child nodes of the first navigation node in the knowledge base, retrieve the second navigation node matching the navigation intention from the knowledge base to output the business knowledge of the target navigation node, the target navigation node being the leaf node of the second navigation node; The navigation service module is used to retrieve a second navigation node matching the navigation intention from the knowledge base according to the subnodes of the first navigation node in the knowledge base, so as to output the business knowledge of the target navigation node, specifically for: Determine candidate navigation nodes that are leaf nodes of the first navigation node in the knowledge base; calculate the similarity between the navigation intention and the business knowledge linked to the candidate navigation nodes; if there are candidate navigation nodes with a similarity higher than a corresponding threshold, use the candidate navigation node with the highest similarity as the second navigation node, and the second navigation node is the target navigation node; If there is no candidate navigation node with a similarity higher than the corresponding threshold, obtain the number of hits of different navigation nodes in the knowledge base in the historical navigation records, where the hit number of a navigation node is the maximum hit number of the child nodes of the navigation node; and select multiple navigation nodes with the largest hit numbers from the first-level child nodes of the first navigation node as the second navigation nodes.
5. The device according to claim 4, characterized in that The manner in which the navigation service module determines the navigation intention includes: Acquire confirmation information input by the customer, wherein the confirmation information includes a node identifier that can uniquely mark a navigation node, and the node identifier may be one or more; or The question information input by the customer is obtained, and semantic detection is performed on the question information to determine keywords that can indicate navigation nodes.
6. An electronic device, characterized in that: The electronic device comprises: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement the telephone banking navigation method described in any one of claims 1-3.
7. A storage medium, characterized in that: The storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the telephone banking navigation method according to any one of claims 1 to 3 is implemented.
Citation Information
Patent Citations
Artificial intelligent sound navigation data processing method
CN109327629A
Telephone customer service method and device, and readable storage medium
CN109525738A
Self-service equipment navigation method and navigation system thereof
CN111290677A
Transaction node navigation method, device and system
CN111369349A
Transaction node navigation method, device and system
CN111432083A
