Information recommendation method, electronic device and storage medium

Abstract

The present application discloses an information recommendation method, an electronic device and a storage medium, comprising: receiving a first request; the first request is used to request to recommend first information of a first service to a first customer service node; the first information represents an operation guide for processing the first service; determining at least one first service node associated with the first service in a first network; the first network represents the correspondence between type nodes, service nodes, customer service nodes and attribute nodes; the type node represents the service type; the attribute node at least represents the attribute corresponding to the customer service node; when the weight of the edge between the first service node in the at least one first service node and the connected second customer service node meets the first set condition, based on the second information of the attribute node corresponding to the corresponding second customer service node, recommending the first information to the first customer service node; the second information represents the operation record generated when processing the first service.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an information recommendation method, electronic device and storage medium. Background Art

[0002] Since customer service personnel generally have a high mobility, in related technologies, courses in the course learning system are used to train new customer service personnel to help them quickly master the skills of communicating with customers in different scenarios.

[0003] However, the course content in the course learning system may not be consistent with the operating procedures and scripts in the actual operation process, causing customer service personnel to learn incorrect knowledge. Summary of the invention

[0004] In view of this, the embodiments of the present application provide an information recommendation method, an electronic device and a storage medium to solve the technical problem in the related art that customer service personnel learn wrong knowledge because the course content in the course learning system is inconsistent with the operating procedures and scripts in the actual operation process.

[0005] To achieve the above purpose, the technical solution of this application is implemented as follows:

[0006] The present application provides an information recommendation method, including:

[0007] receiving a first request; the first request is used to request a first information of a first service to be recommended to a first customer service node; the first information represents an operation guide for processing the first service;

[0008] Determine at least one first service node associated with the first service in a first network; wherein the first network represents a correspondence between a type node, a service node, a customer service node, and an attribute node; the type node represents a service type; and the attribute node at least represents an attribute corresponding to the customer service node;

[0009] When the weight of the edge between the first business node in the at least one first business node and the connected second customer service node meets the first set condition, first information is recommended to the first customer service node based on the second information of the attribute node corresponding to the corresponding second customer service node; wherein the second information represents the operation record generated when processing the first business.

[0010] In the above solution, the first network is constructed in the following manner:

[0011] Based on the set business type and all corresponding businesses, create type nodes and connected business nodes;

[0012] Based on the attribute information of the business, create an attribute node connected to the corresponding business node;

[0013] Based on the attribute information of the customer service that processes each business, a customer service node connected to the corresponding business node is created, and an attribute node connected to the corresponding customer service node is created.

[0014] In the above solution, before recommending the first information to the first customer service node, the method further includes:

[0015] Determining a first weight of an edge between a type node and a corresponding service node in the first network based on a value of a set service indicator corresponding to the service;

[0016] Based on the value of the set capability indicator corresponding to the customer service, a second weight of the edge between the service node and the corresponding customer service node in the first network is determined.

[0017] In the above solution, the first request carries a first customer service identifier and a first service identifier; after receiving the first request, the method further includes:

[0018] Creating a first customer service node based on the first customer service identifier;

[0019] Connecting the first customer service node to all first service nodes corresponding to the first service identifier;

[0020] The average weight of the edge between the first service node and the connected second customer service node is determined as the weight of the edge between the first service node and the first customer service node.

[0021] In the above solution, after recommending the first information to the first customer service node, the method further includes:

[0022] In the first network, a first attribute node connected to the first customer service node is created, and attribute information of the first attribute node is updated based on an operation record corresponding to the first customer service node.

[0023] In the above scheme, the method further includes:

[0024] When a third customer service node in the first network triggers a new operation instruction, determining the aggregation degree of the second service nodes based on the first number and the second number corresponding to the second service nodes;

[0025] When the aggregation degree of the second service node is less than the first set threshold, splitting out a third service corresponding to the new operation instruction;

[0026] In the first network, create a third service node corresponding to the third service, and connect the third service node to a type node corresponding to the corresponding second service node and the third customer service node;

[0027] Among them, the second business node is a business node in the first network that represents the emergency event; the first number represents the total number of edges connected to the second business node; the second number represents the total number of triangles with the second business node as the vertex, and the vertices of the triangles do not include type nodes.

[0028] In the above scheme, the method further includes:

[0029] When the number of times any two customer service nodes process the same type of service is greater than a second set threshold or the duration is greater than a third set threshold, establishing an association relationship between the two customer service nodes in the first network;

[0030] In the case where the topology of the first network changes, based on the attribute node corresponding to the fourth customer service node, recommending third information to a fifth customer service node associated with the fourth customer service node; wherein,

[0031] The fourth customer service node represents a customer service node connected to a service node related to the topology structure change, and the second weight of the fourth customer service node satisfies a second set condition.

[0032] The present application also provides an electronic device, including:

[0033] A receiving unit, configured to receive a first request; the first request is used to request a first information of a first service to be recommended to a first customer service node; the first information represents an operation guide for processing the first service;

[0034] A first determination unit is used to determine at least one first service node associated with the first service in a first network; wherein the first network represents a correspondence between a type node, a service node, a customer service node and an attribute node; the type node represents a service type; and the attribute node at least represents an attribute corresponding to the customer service node;

[0035] A first recommendation unit is used to recommend first information to the first customer service node based on second information of an attribute node corresponding to the corresponding second customer service node when the weight of the edge between the first business node in the at least one first business node and the connected second customer service node meets the first set condition; wherein the second information represents an operation record generated when processing the first business.

[0036] An embodiment of the present application further provides an electronic device, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the above-mentioned information recommendation method when running the computer program.

[0037] An embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned information display recommendation step is implemented.

[0038] In an embodiment of the present application, when a first request is received, a first service node associated with a first service is determined in a first network, and when the weight of the edge between the first service node and the connected second customer service node meets a first set condition, the first information is recommended to the first customer service node based on the second information of the attribute node corresponding to the corresponding second customer service node. Since the first network is dynamically updated, the weight of the edge between the first service node and the connected second customer service node represents the business capability of the customer service corresponding to the customer service node. Therefore, based on the operation record of the customer service node corresponding to the weight that meets the first set condition, the first information is recommended to the first customer service node, so that the customer service personnel can obtain the corresponding latest operation instructions for learning, which can avoid the situation where the customer service personnel learn the wrong relevant knowledge. In addition, the above scheme does not require manual training of customer service personnel, nor does it require manual updating of the course content of the course learning system, and can also improve the efficiency of training customer service personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of an implementation flow of an information recommendation method provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of a first network provided for an application embodiment of the present application;

[0041] Figure 3 A schematic diagram of an implementation flow of an information recommendation method provided in another embodiment of the present application;

[0042] Figure 4 A schematic diagram of an implementation flow of an information recommendation method provided in an application embodiment of the present application;

[0043] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of the hardware composition structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] Customer service staff generally have a high turnover rate, and new and old customer service staff have different work experiences in handling emergency issues, responding to customers, and assisting customers in applying for after-sales services. How to effectively train customer service staff and help them quickly master the skills of responding to customers and handling emergencies has become a more important topic.

[0046] In the related art, when training customer service personnel using courses in a course learning system, there may be a situation where the course content in the course learning system is inconsistent with the operation process and speech in the actual operation process. On the one hand, manually updating the course content in the course learning system takes a lot of time; on the other hand, if the course content is not updated in time, customer service personnel may learn wrong knowledge and the training effect is poor. The course content may include: system process operation, unified speech to deal with customer problems, and emergency strategies for handling emergencies.

[0047] Based on this, in various embodiments of the present application, by constructing a first network that represents the correspondence between type nodes, business nodes, customer service nodes, and attribute nodes, when a first request for recommending first information of a first business to a first customer service node is received, a first business node associated with the first business is determined in the first network, and when the weight of the edge between the first business node and the connected second customer service node meets the first set condition, the first information is recommended to the first customer service node based on the second information of the attribute node corresponding to the corresponding second customer service node. Among them, the first information represents the operation guide for processing the first business, and the second information represents the operation record generated when processing the first business. Since the first network is dynamically updated, the weight of the edge between the first business node and the connected second customer service node represents the business capability of the customer service node. Therefore, based on the operation record of the customer service node corresponding to the weight that meets the first set condition, the first information is recommended to the first customer service node, so that the customer service personnel can obtain the corresponding latest operation guide for learning, which can avoid the situation that the operation guide learned by the customer service personnel is inconsistent with the actual operation guide. In addition, the above scheme does not require manual training of customer service personnel, does not rely on the course learning system, does not require manual update of the course content of the course learning system, and can also improve the efficiency of training customer service personnel.

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] Figure 1The following is a schematic diagram of the implementation process of the information recommendation method provided in the embodiment of the present application, wherein the execution subject of the process is an electronic device such as a terminal device and a server. Figure 1 As shown, the information recommendation method includes:

[0050] Step 101: Receive a first request; the first request is used to request a recommendation of first information of a first service for a first customer service node; the first information represents an operation guide for processing the first service.

[0051] Here, the first request carries a first customer service identifier and a first service identifier. The first customer service identifier is used by the electronic device to create a first customer service node in the first network; the first service identifier is used by the electronic device to find a service node associated with the first service in the first network. In actual application, the first information includes the words for dealing with customers related to the first service, the operation procedures and precautions related to the first service, etc. The operation procedures include the operation procedures for assisting customers to apply for after-sales service.

[0052] In some embodiments, before step 102 or step 101, the electronic device builds a first network based on all services corresponding to each set service type in at least one set service type, attribute information of each service, and attribute information of customer service that processes each service. The first network represents the correspondence between type nodes, service nodes, customer service nodes, and attribute nodes; the type node represents the service type. In the first network, a service node represents a type or a service under the corresponding type node. The customer service node represents the customer service.

[0053] In actual application, the business type includes at least one of: activities, emergencies, processes and agency applications. Among them, activities generally refer to promotional activities, such as full-reduction activities, shopping allowances, etc. Processes generally refer to the processing procedures related to after-sales service. Agency applications refer to the general term for customer service to assist customers in applying for or processing projects. Agency applications include at least one of after-sales, compensation and disputes.

[0054] In actual application, the attribute nodes in the first network include a first attribute node and a second attribute node. The first attribute node is connected to the customer service node, and the second attribute node is connected to the business node. The first attribute node represents the attributes corresponding to the customer service node, and the second attribute node represents the attributes corresponding to the business node. In other words, the first attribute node includes attribute information corresponding to the customer service, and the second attribute node includes attribute information corresponding to the business. Among them, the attribute information of the business includes the business identifier and business information, etc., and the business information may include information for setting business indicators in different dimensions. The attribute information of the customer service includes the operation records generated by the customer service when processing the corresponding business and the information for setting the capability indicators, such as chat information when solving user problems, form information filled in when processing forms, etc.

[0055] In some embodiments, the first network is constructed in the following manner:

[0056] Based on the set business type and all corresponding businesses, create type nodes and connected business nodes;

[0057] Based on the attribute information of the business, create an attribute node connected to the corresponding business node;

[0058] Based on the attribute information of the customer service that processes each business, a customer service node connected to the corresponding business node is created, and an attribute node connected to the corresponding customer service node is created.

[0059] Here, the electronic device creates a type node in the first network based on the set business type, and creates a business node connected to the set business type in the first network based on all businesses corresponding to the set business type, and the business node corresponds to the business one-to-one; based on the attribute information of the business, creates an attribute node connected to the corresponding business node, and the attribute node includes the attribute information of the business; based on the attribute information of the customer service that handles each business, creates a customer service node connected to the corresponding business node, and creates an attribute node connected to the corresponding customer service node, and the attribute node includes the attribute information of the customer service.

[0060] Exemplarily, the first network constructed is as follows Figure 2 As shown, Figure 2 In the figure, the hollow circle represents the type node, the triangle represents the business node, and the black solid circle represents the customer service node. Figure 2 Type node 1 represents activities, type node 2 represents emergencies, type node 3 represents processes, and type node 4 represents speech.

[0061] In some embodiments, when constructing the first network, the method further includes:

[0062] Determining a first weight of an edge between a type node and a corresponding service node in the first network based on a value of a set service indicator corresponding to the service;

[0063] Based on the value of the set capability indicator corresponding to the customer service, a second weight of the edge between the service node and the corresponding customer service node in the first network is determined.

[0064] Here, the electronic device determines the value of the set business indicator corresponding to the business from the attribute information corresponding to the business, and determines the first weight of the edge between the type node and the corresponding business node in the first network based on the value of the set business indicator corresponding to the business. The electronic device determines the value of the set capability indicator corresponding to the customer service from the attribute information corresponding to the customer service, and determines the second weight of the edge between the business node and the corresponding customer service node in the first network based on the value of the set capability indicator corresponding to the customer service.

[0065] In the case where there is only one set business indicator, the electronic device determines the corresponding first weight based on the correspondence between the value of the set business indicator and the weight; in the case where the number of set business indicators is at least two, the values ​​of at least two set business indicators are weighted and summed to obtain the corresponding first weight. It should be noted that for a business with a validity period, when the first business fails, the first weight corresponding to the first business is reduced. In actual application, the first weight corresponding to the first business can be set to 0.

[0066] When there is only one set capability indicator, the electronic device determines the corresponding second weight based on the correspondence between the value of the set capability indicator and the weight; when the number of set capability indicators is at least two, the values ​​of at least two set capability indicators are weighted and summed to obtain the corresponding second weight.

[0067] In actual application, when the business type is activity, the business indicators are set to include at least one of the consultation volume, processing volume and favorable comment rate. When the business type is application on behalf of others, the business indicators are set to include the order opening rate and the order closing rate. The order opening rate is calculated based on the consultation volume and the total number of application forms created, and the order closing rate is calculated based on the total number of application forms processed and the total number of application forms created.

[0068] When the business type is application on behalf of others and the business is a dispute, the capability indicators are set to include at least one of the dispute form review volume, resolution rate, and favorable comment rate.

[0069] In this embodiment, corresponding first weights and second weights are set in the first network, and the popularity or importance of the service can be identified by the first weight, and the service capability of the corresponding customer service can be identified by the second weight.

[0070] It should be noted that the weights corresponding to the nodes, the relevant information of the nodes, and the edges between the nodes in the first network are all dynamically updated. The association between the business node and the customer service node is also dynamically updated. For example, when it is detected that the customer service corresponding to the customer service node A has processed the compensation business, a connection relationship is established between the customer service node A and the business node corresponding to the compensation business in the first network. For example, the information of the attribute node connected to the corresponding customer service node is updated based on the operation record of the customer service personnel.

[0071] In some embodiments, when the first request carries a first customer service identifier and a first service identifier, after the first network is constructed and the first request is received, the method further includes:

[0072] Creating a first customer service node based on the first customer service identifier;

[0073] Connecting the first customer service node to all first service nodes corresponding to the first service identifier;

[0074] The average weight of the edge between the first service node and the connected second customer service node is determined as the weight of the edge between the first service node and the first customer service node.

[0075] The electronic device creates a first customer service node in the first network based on the first customer service identifier; determines all first business nodes corresponding to the first business identifier from the first network, and connects the first customer service node to each first business node respectively; calculates a weight mean based on the weight of the edge between each first business node and the connected second customer service node, and determines the calculated weight mean as the weight of the edge between the first business node and the first customer service node.

[0076] In actual application, when the first service is compensation, the electronic device determines all service nodes representing compensation from the first network, and connects the first customer service node to each service node representing compensation.

[0077] Step 102: Determine at least one first service node associated with the first service in a first network; wherein the first network represents a correspondence between type nodes, service nodes, customer service nodes and attribute nodes; the type node represents a service type; and the attribute node at least represents an attribute corresponding to the customer service node.

[0078] Here, the electronic device determines a service node matching the first service identifier in the first network based on the first service identifier carried in the first request, and obtains the first service node associated with the first service.

[0079] Step 103: When the weight of the edge between the first business node in the at least one first business node and the connected second customer service node meets the first set condition, based on the second information of the attribute node corresponding to the corresponding second customer service node, recommend the first information to the first customer service node; wherein the second information represents the operation record generated when processing the first business.

[0080] Here, the electronic device obtains the weight of the edge between each first service node and the connected second customer service node from the first network; determines the weight that meets the first set condition from the obtained weights, and recommends the first information to the first customer service node based on the second information of the attribute node corresponding to the second customer service node corresponding to the weight that meets the first set condition.

[0081] The first setting condition includes that the weight is maximum, or the weight is greater than or equal to a set threshold.

[0082] In actual application, the electronic device recommends the first information to the first customer service node based on the second information of the attribute node corresponding to the second customer service node corresponding to the largest weight.

[0083] In some embodiments, after step 103, the method further includes: in the first network, creating a first attribute node connected to the first customer service node, and updating attribute information of the first attribute node based on an operation record corresponding to the first customer service node.

[0084] Here, the electronic device obtains the attribute information of the first customer service node, creates a first attribute node connected to the first customer service node in the first network based on the attribute information of the first customer service node, and updates the attribute information of the first attribute node based on the operation record generated by the first customer service node when processing the first service. Thus, the electronic device can dynamically update the attribute information of the first attribute node connected to the first customer service node.

[0085] In this embodiment, when the electronic device receives the first request, it determines the first service node associated with the first service in the first network, and recommends the first information to the first customer service node based on the second information of the attribute node corresponding to the corresponding second customer service node when the weight of the edge between the first service node and the connected second customer service node meets the first set condition. Since the first network is dynamically updated, the weight of the edge between the first service node and the connected second customer service node represents the service capability of the customer service corresponding to the customer service node. Therefore, based on the operation record of the customer service node corresponding to the weight that meets the first set condition, the first information is recommended to the first customer service node, so that the customer service personnel can obtain the latest corresponding operation instructions for learning, which can avoid the situation where the operation instructions learned by the customer service personnel are inconsistent with the actual operation instructions, so as to improve the training effect. In addition, this solution does not require manual training of customer service personnel, nor does it require manual updating of the course content of the course learning system, and can also improve the efficiency of training customer service personnel.

[0086] In order to mine and update the emergent events in the first network, such as Figure 3 As shown, in some examples, the method further includes:

[0087] Step 104: When the third customer service node in the first network triggers a new operation instruction, the aggregation degree of the second service node is determined based on the first quantity and the second quantity corresponding to the second service node. The second service node is a service node representing an emergency event in the first network; the first quantity represents the total number of edges connected to the second service node; the edges connected to the second service node include edges formed by the third customer service node and the second service node; the second quantity represents the total number of triangles with the second service node as a vertex, and the vertices of the triangles do not include type nodes.

[0088] Here, the third customer service node generally refers to any customer service node in the first network, and the first operation instruction is any operation instruction triggered by the third customer service node. Considering that emergencies are usually generated by activities, in actual application, the third customer service node can be a customer service node connected to a business node representing an activity, and / or a customer service node connected to a business node representing an emergencies.

[0089] When the electronic device obtains the first operation instruction triggered by the third customer service node in the first network, the electronic device compares the first operation instruction with the historical operation instruction triggered by the third customer service node, thereby determining whether the first operation instruction is a new operation instruction. When the first operation instruction is a new operation instruction, all second service nodes are determined from the first network; the first quantity and the second quantity corresponding to each second service node are calculated, and the aggregation degree of the corresponding second service node is determined based on the first quantity and the second quantity corresponding to each second service node. Wherein,

[0090] When calculating the first quantity corresponding to each second business node, the electronic device connects the third customer service node to the second business node, calculates the total number of edges connected to the second business node, obtains the corresponding first quantity, and deletes the edge between the third customer service node and the second business node when the first quantity corresponding to the second business node is calculated.

[0091] In practical applications, electronic devices use the formula Calculate the aggregation degree of the second service node. u Characterizes the aggregation degree of the u-th second service node, K u Indicates the first number corresponding to the u-th second service node, R u Indicates the second quantity corresponding to the u-th second service node.

[0092] When the aggregation degree of the second service node is less than the first set threshold, it indicates that a new emergency event has occurred, and step 105 is executed; when the aggregation degree of the second service node is greater than or equal to the first set threshold, it indicates that no new emergency event has occurred, and the processing flow ends.

[0093] Step 105: When the aggregation degree of the second service node is less than the first set threshold, split out the third service corresponding to the new operation instruction.

[0094] Here, when the aggregation degree of any second service node is less than the first set threshold, the electronic device creates a third service corresponding to a new operation instruction, thereby splitting the third service corresponding to the new operation instruction from the service represented by the service node connected to the second customer service node.

[0095] Step 106: In the first network, create a third service node corresponding to the third service, and connect the third service node to the type node corresponding to the corresponding second service node and the third customer service node.

[0096] Here, the electronic device creates a third service node corresponding to the third service in the first network, connects the third service node to a type node corresponding to the corresponding second service node, and connects the third service node to a third customer service node.

[0097] It should be noted that after step 106, the electronic device can also recommend relevant information for handling emergencies to the third customer service node based on the weight of the edge of the customer service node connected to the second service node. The specific implementation method is similar to the timing process of recommending the first information to the first customer service node, which will not be repeated here. In this embodiment, the electronic device can discover new emergencies based on the aggregation degree of the second service node in the first network, create a new service node corresponding to the emergencies in the first network, and recommend relevant information for handling emergencies to the third customer service node. As a result, there is no need for trainers to train customer service personnel on emergencies, nor is there a need to update learning materials corresponding to emergencies in the course learning system.

[0098] In some embodiments, the method further comprises:

[0099] When the number of times any two customer service nodes process the same type of service is greater than a second set threshold or the duration is greater than a third set threshold, establishing an association relationship between the two customer service nodes in the first network;

[0100] In the case where the topology of the first network changes, based on the attribute node corresponding to the fourth customer service node, recommending third information to a fifth customer service node associated with the fourth customer service node; wherein,

[0101] The fourth customer service node represents a customer service node connected to a service node related to the topology structure change, and the second weight of the fourth customer service node satisfies a second set condition.

[0102] Here, when the electronic device detects that any two customer service nodes in the first network handle the same type of business, it calculates the number of times or duration that the two customer service nodes handle the same type of business, and establishes an association relationship between the two customer service nodes in the first network when the calculated number of times is greater than the second set threshold, or the calculated duration is greater than the third set threshold. In practical applications, a dotted line is used in the first network to mark the association relationship between the two customer service nodes. Exemplarily, customer service node A and customer service node B both handle dispute business, and the number of times the dispute business is handled is greater than the second set threshold, or the duration of handling the dispute business is greater than the third set threshold, and the electronic device uses a dotted line to connect customer service node A and customer service node B in the first network.

[0103] Taking into account the occurrence of new emergencies in the first network, or the change in the business, the topology of the first network changes, when the electronic device detects that the topology of the first network has changed, determines from the first network all customer service nodes connected to the fourth business node related to the topology change, and determines the second weight that meets the second set condition based on the second weight of the edge between the fourth business node and each connected customer service node; determines the customer service node corresponding to the second weight that meets the second set condition as the fourth customer service node, and recommends the third information to the fifth customer service node associated with the fourth customer service node based on the attribute information of the attribute node corresponding to the fourth customer service node.

[0104] The setting threshold corresponding to the second setting condition may be the same as or different from the first setting condition. The second setting condition includes the weight being the largest, or the weight being greater than or equal to the setting threshold.

[0105] In actual application, based on the attribute information of the attribute node corresponding to the fourth customer service node corresponding to the largest second weight, the third information is recommended to the fifth customer service node, and the third information represents the operation guidance for processing the business corresponding to the third business node.

[0106] In actual application, the fifth customer service node is a customer service node connected to the fourth customer service node by a dotted line in the first network.

[0107] In this embodiment, an association relationship is established between customer service nodes that process the same type of service in the first network, and when the topology of the first network changes, the third information is recommended to the associated fifth customer service node based on the attribute node corresponding to the fourth customer service node, so that the fifth customer service node can learn the operation guide for processing the service corresponding to the third service node. When the service corresponding to the fourth service node represents an emergency, the fourth customer service node can provide the fifth customer service node with a sample solution to the emergency problem.

[0108] Test results show that the accuracy of the First Network in discovering new emergencies can reach 74%, the recall rate can reach 86%, and the assistance rate for new customer service can reach 78%, without the need for training personnel to provide special training for customer service or review of emergencies. The recall rate is calculated based on the total number of new emergencies discovered in the First Network and the total number of real emergencies.

[0109] Figure 4 A schematic diagram of an implementation flow of an information recommendation method provided in an application embodiment of the present application is shown in FIG. Figure 4 As shown, the information recommendation method includes:

[0110] Step 401: construct a first network based on all services corresponding to each set service type in at least one set service type, attribute information of each service, and attribute information of a customer service that processes each service.

[0111] The first network is constructed in the following manner:

[0112] Based on the set business type and all corresponding businesses, create type nodes and connected business nodes;

[0113] Based on the attribute information of the business, create an attribute node connected to the corresponding business node;

[0114] Based on the attribute information of the customer service that processes each business, a customer service node connected to the corresponding business node is created, and an attribute node connected to the corresponding customer service node is created.

[0115] Step 402: When the number of times any two customer service nodes process the same type of service is greater than a second set threshold or the duration is greater than a third set threshold, an association relationship between the two customer service nodes is established in the first network.

[0116] Step 403: Based on the value of the set service indicator corresponding to the service, determine the first weight of the edge between the type node and the corresponding service node in the first network.

[0117] Step 404: Based on the value of the set capability indicator corresponding to the customer service, determine the second weight of the edge between the service node and the corresponding customer service node in the first network.

[0118] Step 405: Receive a first request; the first request is used to request a recommendation of first information of a first service for a first customer service node; the first information represents an operation guide for processing the first service.

[0119] Step 406: Determine at least one first service node associated with the first service in the first network; wherein the first network represents the correspondence between type nodes, service nodes, customer service nodes and attribute nodes; the type node represents the service type; and the attribute node at least represents the attribute corresponding to the customer service node.

[0120] Step 407: When the weight of the edge between the first business node in the at least one first business node and the connected second customer service node meets the first set condition, based on the second information of the attribute node corresponding to the corresponding second customer service node, recommend the first information to the first customer service node; wherein the second information represents the operation record generated when processing the first business.

[0121] Step 408: When a new operation instruction is triggered by the third customer service node in the first network, the aggregation degree of the second service node is determined based on the first quantity and the second quantity corresponding to the second service node;

[0122] Step 409: When the aggregation degree of the second service node is less than the first set threshold, split the third service corresponding to the new operation instruction;

[0123] Step 410: In the first network, create a third business node corresponding to the third business, and connect the third business node to the type node corresponding to the corresponding second business node, and the third customer service node; wherein the second business node is a business node representing an emergency event in the first network; the first quantity represents the total number of edges connected to the second business node; the second quantity represents the total number of triangles with the second business node as a vertex, and the vertices of the triangles do not include the type node.

[0124] Step 411: When the topology of the first network changes, based on the attribute node corresponding to the fourth customer service node, recommend third information to the fifth customer service node associated with the fourth customer service node; wherein the fourth customer service node represents a customer service node connected to the business node related to the topology change, and the second weight of the fourth customer service node satisfies the second set condition.

[0125] It should be noted that the implementation process of the above steps can be referred to the relevant description above and will not be repeated here.

[0126] To implement the information recommendation method of the embodiment of the present application, the embodiment of the present application also provides an electronic device, such as Figure 5 As shown, the electronic device includes:

[0127] A receiving unit 51 is configured to receive a first request; the first request is used to request a first information of a first service to be recommended to a first customer service node; the first information represents an operation guide for processing the first service;

[0128] A first determining unit 52 is configured to determine at least one first service node associated with the first service in a first network; wherein the first network represents a correspondence between a type node, a service node, a customer service node, and an attribute node; the type node represents a service type; and the attribute node at least represents an attribute corresponding to the customer service node;

[0129] The first recommendation unit 53 is used to recommend first information to the first customer service node based on second information of an attribute node corresponding to the corresponding second customer service node when the weight of the edge between the first business node in the at least one first business node and the connected second customer service node meets the first set condition; wherein the second information represents the operation record generated when processing the first business.

[0130] In some embodiments, the electronic device further includes a construction unit, configured to construct the first network in the following manner:

[0131] Based on the set business type and all corresponding businesses, create type nodes and connected business nodes;

[0132] Based on the attribute information of the business, create an attribute node connected to the corresponding business node;

[0133] Based on the attribute information of the customer service that processes each business, a customer service node connected to the corresponding business node is created, and an attribute node connected to the corresponding customer service node is created.

[0134] In some embodiments, the electronic device further comprises:

[0135] A second determining unit, configured to determine a first weight of an edge between a type node and a corresponding service node in the first network based on a value of a set service indicator corresponding to the service;

[0136] The third determining unit is used to determine a second weight of an edge between a service node and a corresponding customer service node in the first network based on a value of a set capability indicator corresponding to the customer service.

[0137] In some embodiments, the first request carries a first customer service identifier and a first service identifier; and the electronic device further includes a first creation unit, which is used to:

[0138] Creating a first customer service node based on the first customer service identifier;

[0139] Connecting the first customer service node to all first service nodes corresponding to the first service identifier;

[0140] The average weight of the edge between the first service node and the connected second customer service node is determined as the weight of the edge between the first service node and the first customer service node.

[0141] In some embodiments, the electronic device further includes a second creating unit, configured to:

[0142] In the first network, a first attribute node connected to the first customer service node is created, and attribute information of the first attribute node is updated based on an operation record corresponding to the first customer service node.

[0143] In some embodiments, the electronic device further comprises:

[0144] a fourth determining unit, configured to determine, when a third customer service node in the first network triggers a new operation instruction, a degree of aggregation of the second service nodes based on the first number and the second number corresponding to the second service nodes;

[0145] A generating unit, configured to split a third service corresponding to the new operation instruction when the aggregation degree of the second service node is less than a first set threshold;

[0146] The third creation unit creates a third service node corresponding to the third service in the first network, and connects the third service node to the type node corresponding to the corresponding second service node and the third customer service node; wherein,

[0147] The second service node is a service node in the first network that represents an emergency event; the first number represents the total number of edges connected to the second service node; the second number represents the total number of triangles with the second service node as a vertex, and the vertices of the triangles do not include type nodes.

[0148] In some embodiments, the electronic device further comprises:

[0149] an establishing unit, configured to establish an association relationship between any two customer service nodes in the first network when the number of times that any two customer service nodes process the same type of service is greater than a second set threshold or the duration is greater than a third set threshold;

[0150] A second recommendation unit is used to recommend third information to a fifth customer service node associated with the fourth customer service node based on an attribute node corresponding to the fourth customer service node when the topology structure of the first network changes; wherein the fourth customer service node represents a customer service node connected to a business node related to the topology structure change, and the second weight of the fourth customer service node satisfies a second set condition.

[0151] In actual application, each unit included in the electronic device can be implemented by a processor in the electronic device, such as a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU) or a programmable gate array (FPGA), or can be implemented jointly by a processor and a communication interface in the electronic device.

[0152] It should be noted that: when the electronic device provided in the above embodiment performs information recommendation, only the division of the above program modules is used as an example. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the electronic device provided in the above embodiment and the information recommendation method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0153] Based on the hardware implementation of the above program modules, and in order to implement the information recommendation method of the embodiment of the present application, the embodiment of the present application also provides an electronic device. Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the electronic device 6 includes:

[0154] Communication interface 61, capable of exchanging information with other devices such as network devices;

[0155] The processor 62 is connected to the communication interface 61 to implement information interaction with other devices and is used to execute the information recommendation method provided by one or more technical solutions when running a computer program. The computer program is stored in the memory 63.

[0156] Of course, in actual application, the various components in the electronic device 6 are coupled together through the bus system 64. It can be understood that the bus system 64 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 64 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 6 Various buses are labeled as bus system 64.

[0157] The memory 63 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device 6. Examples of such data include: any computer program used to operate on the electronic device 6.

[0158] It can be understood that the memory 63 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 63 described in the embodiments of the present application is intended to include but is not limited to these and any other suitable types of memory.

[0159] The method disclosed in the above embodiment of the present application can be applied to the processor 62, or implemented by the processor 62. The processor 62 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 62 or the instruction in the form of software. The above processor 62 can be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 62 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 63, and the processor 62 reads the program in the memory 63 and completes the steps of the above method in combination with its hardware.

[0160] Optionally, when the processor 62 executes the program, it implements the corresponding processes implemented by the terminal in each method of the embodiments of the present application, which will not be described here for the sake of brevity.

[0161] In an exemplary embodiment, the present application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, including a first memory 63 storing a computer program, and the computer program can be executed by a processor 62 of the terminal to complete the steps of the aforementioned method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0162] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0163] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0164] In addition, all functional units in the embodiments of the present application may be integrated into one processing module, or each unit may be separately configured as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0165] A person skilled in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, etc. Various media that can store program codes.

[0166] It should be noted that the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0167] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An information recommendation method, characterized in that: include: receiving a first request; The first request is used to request to recommend first information of a first service to the first customer service node; The first information represents an operation guide for processing the first service; Determine at least one first service node associated with the first service in the first network; wherein the first network is constructed based on all services corresponding to each set service type in at least one set service type, attribute information of each service, and attribute information of a customer service that processes each service, and represents a correspondence between a type node, a service node, a customer service node, and an attribute node; the type node represents a service type; and the attribute node at least represents an attribute corresponding to a customer service node; When the weight of the edge between the first business node and the connected second customer service node in the at least one first business node meets the first set condition, the first information is recommended to the first customer service node based on the second information of the attribute node corresponding to the corresponding second customer service node; wherein the weight of the edge between the first business node and the connected second customer service node represents the business capability of the customer service node; and the second information represents the operation record generated when processing the first business.

2. The method according to claim 1, characterized in that The first network is constructed in the following manner: Based on the set business type and all corresponding businesses, create type nodes and connected business nodes; Based on the attribute information of the business, create an attribute node connected to the corresponding business node; Based on the attribute information of the customer service that processes each business, a customer service node connected to the corresponding business node is created, and an attribute node connected to the corresponding customer service node is created.

3. The method according to claim 1, characterized in that Before recommending the first information to the first customer service node, the method further includes: Determining a first weight of an edge between a type node and a corresponding service node in the first network based on a value of a set service indicator corresponding to the service; Based on the value of the set capability indicator corresponding to the customer service, a second weight of the edge between the service node and the corresponding customer service node in the first network is determined.

4. The method according to claim 1, characterized in that: The first request carries a first customer service identifier and a first service identifier; After receiving the first request, the method further includes: Creating a first customer service node based on the first customer service identifier; Connecting the first customer service node to all first service nodes corresponding to the first service identifier; The average weight of the edge between the first service node and the connected second customer service node is determined as the weight of the edge between the first service node and the first customer service node.

5. The method according to claim 1, characterized in that After recommending the first information to the first customer service node, the method further includes: In the first network, a first attribute node connected to the first customer service node is created, and attribute information of the first attribute node is updated based on an operation record corresponding to the first customer service node.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: In the case where a third customer service node in the first network triggers a new operation instruction, determining the aggregation degree of the second service node based on the first number and the second number corresponding to the second service node; the new operation instruction is an operation instruction that does not appear in the historical operation instructions triggered by the third customer service node; When the aggregation degree of the second service node is less than the first set threshold, splitting out a third service corresponding to the new operation instruction; In the first network, create a third service node corresponding to the third service, and connect the third service node to a type node corresponding to the corresponding second service node and the third customer service node; Among them, the second business node is a business node in the first network that represents the emergency event; the first number represents the total number of edges connected to the second business node; the second number represents the total number of triangles with the second business node as the vertex, and the vertices of the triangles do not include type nodes.

7. The method according to claim 6, characterized in that The method further comprises: When the number of times any two customer service nodes process the same type of service is greater than a second set threshold or the duration is greater than a third set threshold, establishing an association relationship between the two customer service nodes in the first network; In the case where the topology of the first network changes, based on the attribute node corresponding to the fourth customer service node, recommending third information to a fifth customer service node associated with the fourth customer service node; wherein, The fourth customer service node represents a customer service node connected to a service node related to the topology structure change, and the second weight of the fourth customer service node satisfies a second set condition.

8. An electronic device, characterized in that: include: A receiving unit, configured to receive a first request; The first request is used to request to recommend first information of a first service to the first customer service node; The first information represents an operation guide for processing the first service; A first determination unit is configured to determine at least one first service node associated with the first service in a first network; wherein the first network is constructed based on all services corresponding to each set service type in at least one set service type, attribute information of each service, and attribute information of a customer service processing each service, and represents a correspondence between a type node, a service node, a customer service node, and an attribute node; the type node represents a service type; and the attribute node at least represents an attribute corresponding to a customer service node; A first recommendation unit is used to recommend first information to the first customer service node based on second information of an attribute node corresponding to the corresponding second customer service node when the weight of the edge between the first business node and the connected second customer service node in the at least one first business node meets the first set condition; wherein the weight of the edge between the first business node and the connected second customer service node represents the business capability of the customer service node; and the second information represents the operation record generated when processing the first business.

9. An electronic device, characterized in that: include: a processor and a memory for storing a computer program capable of being executed on the processor, Wherein, when the processor is used to run the computer program, it executes the steps of the information recommendation method described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the information recommendation method according to any one of claims 1 to 7 are implemented.

Images