CN111950902A - Intelligent outbound call processing method and device - Google Patents

Intelligent outbound call processing method and device Download PDF

Info

Publication number
CN111950902A
CN111950902A CN202010807563.7A CN202010807563A CN111950902A CN 111950902 A CN111950902 A CN 111950902A CN 202010807563 A CN202010807563 A CN 202010807563A CN 111950902 A CN111950902 A CN 111950902A
Authority
CN
China
Prior art keywords
node
flow
tree
user
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010807563.7A
Other languages
Chinese (zh)
Other versions
CN111950902B (en
Inventor
宋雨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202010807563.7A priority Critical patent/CN111950902B/en
Publication of CN111950902A publication Critical patent/CN111950902A/en
Application granted granted Critical
Publication of CN111950902B publication Critical patent/CN111950902B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/527—Centralised call answering arrangements not requiring operator intervention
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Administration (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Signal Processing (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Telephonic Communication Services (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an intelligent outbound processing method and a device, wherein the method comprises the following steps: determining the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound; determining the user interest degree of each process node in the process tree; determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree; and adjusting the process nodes of the process tree according to the importance degree of each process node. The invention can determine the importance degree of the process node based on the user reach rate and the user interest degree of the process node, further adjust the process node according to the importance degree of the process node, overcome the defect that business personnel subjectively and randomly adjust the process node, and realize the purposes of interactive feedback adjustment based on customers and optimization of the process node of the intelligent outbound process tree.

Description

Intelligent outbound call processing method and device
Technical Field
The invention relates to the technical field of intelligent outbound, in particular to an intelligent outbound processing method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The intelligent outbound refers to actively making a call to a user through the intelligent robot, and providing intelligent calling services such as marketing notification and the like. The intelligent outbound call can complete a continuous multi-round of voice interaction with the customer by analyzing the customer response by means of semantic understanding of the intelligent robot.
At present, the intelligent outbound service needs to rely on subjective judgment of service personnel, and the service personnel configure an intelligent outbound flow tree suitable for a certain service scene in advance under the service scene, wherein each flow node needing to communicate and interact with a client under the service scene is included in the intelligent outbound flow tree. However, the subjective factors and judgment of the business personnel play a crucial role in the adjustment of the process nodes. That is, when each flow node in the intelligent outbound flow tree needs to be adjusted and optimized, a service person generally adjusts the flow node subjectively and randomly based on experience and knowledge, resulting in strong subjectivity in adjusting the flow node.
Therefore, the existing intelligent outbound service has the problem that the configuration and adjustment of the process nodes excessively depend on subjective judgment of service personnel.
Disclosure of Invention
The embodiment of the invention provides an intelligent outbound processing method, which is used for adjusting and optimizing process nodes of an intelligent outbound process tree based on interactive feedback of a client, and comprises the following steps:
determining the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound;
determining the user interest degree of each process node in the process tree;
determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree;
and adjusting the process nodes of the process tree according to the importance degree of each process node.
The embodiment of the invention also provides an intelligent outbound processing device, which is used for adjusting and optimizing the process nodes of the intelligent outbound process tree based on the interactive feedback of the client, and the intelligent outbound processing device comprises:
the reach rate determining module is used for determining the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound;
the interest degree determining module is used for determining the user interest degree of each process node in the process tree;
the importance degree determining module is used for determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree;
and the node adjusting module is used for adjusting the process nodes of the process tree according to the importance degree of each process node.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the intelligent outbound processing method when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the intelligent outbound processing method is stored in the computer-readable storage medium.
The embodiment of the invention determines the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound; determining the user interest degree of each process node in the process tree; determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree; and adjusting the process nodes of the process tree according to the importance degree of each process node. The embodiment of the invention can determine the importance degree of the process node based on the user reach rate and the user interest degree of the process node, further adjust the process node according to the importance degree of the process node, overcome the defect that business personnel subjectively and randomly adjust the process node, and realize the purposes of interactive feedback adjustment based on customers and optimization of the process node of the intelligent outbound process tree.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart of an implementation of an intelligent outbound processing method according to an embodiment of the present invention;
fig. 2 is a flowchart of implementing step 101 in the intelligent outbound processing method according to the embodiment of the present invention;
fig. 3 is a flowchart illustrating the implementation of step 102 in the intelligent outbound processing method according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating implementation of step 302 in the intelligent outbound processing method according to the embodiment of the present invention;
fig. 5 is a flowchart illustrating the implementation of step 103 in the intelligent outbound processing method according to the embodiment of the present invention;
fig. 6 is a flowchart illustrating the implementation of step 104 in the intelligent outbound processing method according to the embodiment of the present invention;
fig. 7 is a functional block diagram of an intelligent outbound processing device according to an embodiment of the present invention;
fig. 8 is a block diagram illustrating a structure of a reach rate determining module 701 in an intelligent outbound processing apparatus according to an embodiment of the present invention;
fig. 9 is a block diagram illustrating a structure of an interest level determining module 702 in the intelligent outbound processing apparatus according to an embodiment of the present invention;
fig. 10 is a block diagram of a structure of an interest level determining unit 902 in the intelligent outbound processing apparatus according to the embodiment of the present invention;
fig. 11 is a block diagram of an importance level determining module 703 in the intelligent outbound processing apparatus according to the embodiment of the present invention;
fig. 12 is a block diagram illustrating a structure of a node adjustment module 704 in the intelligent outbound processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
Fig. 1 shows an implementation flow of the intelligent outbound processing method provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
as shown in fig. 1, the intelligent outbound processing method includes:
step 101, determining a user reach rate of each flow node in the flow tree according to an execution result of the intelligent outbound;
step 102, determining the user interest degree of each process node in the process tree;
103, determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree;
and 104, adjusting the process nodes of the process tree according to the importance degree of each process node.
When the intelligent outbound is carried out, the intelligent outbound can be executed in sequence according to the sequence of the flow nodes in the initially created flow tree, and the execution result of the intelligent outbound is obtained after the execution of the intelligent outbound is finished. Assuming that the number of target users of the intelligent outbound service is M, intelligent outbound is required to be performed on the M users according to each flow node in the flow tree. And after the intelligent outbound execution is finished, determining the user reaching rate of each flow node based on the execution result of the intelligent outbound.
Although a certain flow node in the intelligent outbound service is played, the user is not effectively touched. The concept of reach rate is generated. The user reach rate is originally a term of an advertisement boundary, and means that the percentage of the number of reach users contacting the flow node in the target user number M is determined to be the target user number M.
After the user reach rate of each process node in the process tree is determined, the user interest degree of each process node in the process tree is further determined. The user interest degree of the process node refers to an interest score or an interest value, or a divided interest level and the like quantized through objective criteria and fed back to the process node by a user. For example, the user interest level of a certain process node may be pre-divided into multiple levels, such as "very active", "more active", "general", "not active", and "very not active", etc.; the interest score or interest score for a flow node may also be determined by some quantitative criteria. Or dividing the user interest degree of the process node into a plurality of levels in advance by taking the interest score or the interest score as a quantization standard, and determining the corresponding interest level according to the interest score or the interest score of a certain process node. In embodiments of the present invention, a quantified interest score or interest value may be employed to represent a degree of user interest of a process node.
Furthermore, after the user reach rate and the user interest level of each process node are determined, the importance level of the process node may be determined based on the user reach rate and the user interest level of the process node. Wherein the importance degree of the process node is similar to the user interest degree of the process node. For example, a quantified importance score or a quantified importance value may also be used to represent the importance of a flow node.
In addition, the importance degree score or the importance degree score can be used as a quantification standard to divide the importance degree of the flow node into a plurality of importance degree grades in advance, and the importance degree of the flow node can be represented by the divided different importance degree grades. For example, the importance level of a flow node is previously divided into "important", "general", "unimportant", and "very unimportant", etc. When determining the importance degree of a certain process node, determining the corresponding importance degree grade based on the importance degree score or the importance degree score of the process node.
And finally, after determining the importance degree of each process node based on the user reach rate and the user interest degree of the process nodes, adjusting the positions, the number and the like of the process nodes in the process tree based on the importance degree of the process nodes. For example, a flow node with a high degree of importance is placed in a flow node with a low degree of importance, or a flow node with a high degree of importance and a flow node with a low degree of importance are alternately arranged, or a flow node with a low degree of importance is alternately arranged among flow nodes with a high degree of importance, and the like. In addition, the number of the flow nodes in the flow tree can be deleted and adjusted according to the importance degree of the flow nodes.
In the embodiment of the invention, the user reach rate of each flow node in the flow tree is determined according to the execution result of the intelligent outbound; determining the user interest degree of each process node in the process tree; determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree; and adjusting the process nodes of the process tree according to the importance degree of each process node. The embodiment of the invention can determine the importance degree of the process node based on the user reach rate and the user interest degree of the process node, further adjust the process node according to the importance degree of the process node, overcome the defect that business personnel subjectively and randomly adjust the process node, and realize the purposes of interactive feedback adjustment based on customers and optimization of the process node of the intelligent outbound process tree.
Fig. 2 shows an implementation flow of step 101 in the intelligent outbound processing method provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to accurately determine the user reach rate of a flow node, as shown in fig. 2, step 101, determining the user reach rate of each flow node in a flow tree according to an execution result of an intelligent outbound, includes:
step 201, respectively determining the broadcast number and the reach number of each flow node in the flow tree according to the execution result of the intelligent outbound call;
step 202, determining the user reach rate of each flow node according to the broadcast number and reach number of each flow node in the flow tree.
The execution result of the intelligent outbound at least comprises the broadcast number and the reach number of each flow node. The broadcast number of the process node refers to the number of times that the process node broadcasts (generally, the number of target users corresponding to executing the intelligent outbound), and the reach number of the process node refers to the number of times that the process node reaches the user (the number of reach users, that is, the number of users who contact the process node in the target users is determined).
And after the broadcast number and the reach number of each flow node in the flow tree are determined, determining the percentage of the reach number of the flow node in the broadcast number as the user reach rate of the flow node. And obtaining the user reach rate of each flow node in the flow tree.
In the embodiment of the invention, the broadcast number and the reach number of each flow node in the flow tree are respectively determined according to the execution result of the intelligent outbound, and then the user reach rate of each flow node is determined according to the broadcast number and the reach number of each flow node in the flow tree, so that the user reach rate of the flow node can be accurately determined.
Fig. 3 illustrates an implementation flow of step 102 in the intelligent outbound processing method provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are illustrated, and the details are as follows:
in an embodiment of the present invention, in order to accurately determine the user interest level of a process node, as shown in fig. 3, step 102, determining the user interest level of each process node in a process tree, includes:
step 301, determining user emotional tendency information of each flow node in the flow tree through natural language processing analysis;
step 302, determining the user interest degree of each process node according to the user emotional tendency information and the node depth of each process node and whether the current process node is an end node.
In analyzing the emotional tendency information of the user at the flow node, semantic information and emotional information analysis can be performed on interaction feedback of the user at the flow node in the intelligent outbound through a Natural Language Processing (NLP), and the emotional information may include emotional information of a text and user voice emotional information in the intelligent outbound interaction. The emotion tendency information of the user of the process node can be represented by quantized emotion scores, and the value range of the emotion tendency information is a normalized value range (0, 1).
Specifically, the emotion score corresponding to the text keyword or the emotion score corresponding to the speech emotion can be determined through the emotion correlation comparison table. The emotion correlation comparison table comprises specific text keywords and corresponding emotion scores thereof, and also comprises voice emotion and corresponding emotion scores thereof. Accordingly, when the emotion tendency information of the user of a certain process node is determined, the emotion scores corresponding to the text keywords and the emotion scores corresponding to the speech emotions are determined from the emotion association comparison table respectively by analyzing the text keywords and the speech emotions in the interactive feedback, and the emotion tendency information of the user can be represented by the average value of the emotion scores corresponding to the text keywords and the emotion scores corresponding to the speech emotions.
Or determining the emotional tendency information of the user of the flow node by the following formula:
L＝A×L1+B×L2；
A+B＝1
wherein, L represents the user emotion tendency information of the process node, A represents the text keyword score coefficient, L1 represents the emotion score corresponding to the text keyword, B represents the voice emotion score coefficient, and L2 represents the emotion score corresponding to the voice emotion.
The text keyword score coefficient A and the speech emotion score coefficient B can be flexibly set according to actual conditions and requirements, for example, A is 0.6 and B is 0.4; or a is 0.4 and B is 0.6, etc. In addition, the value intervals of the emotion score L1 corresponding to the text keyword and the emotion score corresponding to the speech emotion are both [ 0, 1 ].
After the emotional tendency information of the user of each process node is determined, the user interest degree of the process node can be comprehensively determined further based on the node depth of the process node and whether the current node is an end node. Generally, the deeper the node depth of a flow node, the worse the patience of the user, that is, the lower the interest level of the flow node having the deeper depth, and whether or not the current node is an end node also become important factors affecting the interest level of the user.
In the embodiment of the invention, the emotion tendency information of the user of each flow node in the flow tree is determined through natural language processing analysis, and the user interest degree of each flow node is determined according to the emotion tendency information and the node depth of the user of each flow node and whether the current flow node is an end node, so that the user interest degree of the flow node can be accurately determined.
Fig. 4 shows an implementation flow of step 302 in the intelligent outbound processing method provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, to improve flexibility of determining a user interest level of a process node, as shown in fig. 4, step 302, determining the user interest level of each process node according to the user emotional tendency information and the node depth of each process node and whether the current process node is an end node, includes:
step 401, determining an emotional tendency coefficient, a node depth coefficient and an end node coefficient based on a received coefficient configuration instruction;
step 402, determining the user interest degree of each process node according to the user emotional tendency information and emotional tendency coefficient, the node depth and the node depth coefficient of each process node, and whether the current process node is an end node or an end node coefficient.
When the user interest degree of the process node is determined, three factors of the emotion tendency information of the user, the node depth and whether the current process node is an end node are mainly considered. Specifically, the coefficient of each factor, that is, the emotional tendency coefficient, the node depth coefficient, and the end node coefficient, is determined first. In a preferred embodiment, the sum of the emotional tendency coefficient, the node depth coefficient and the end node coefficient is 1. Or in other embodiments, the sum of the emotional tendency coefficient, the node depth coefficient and the end node coefficient is not less than 0.8 or 0.9, and the like.
In embodiments of the present invention, the node depth may be determined based on the location of the flow node in the flow tree. Specifically, the percentage of the number of layers of the node where the flow node is located to the total number of layers of the nodes included in the flow tree may be used as the node depth, and it can be seen that the node depth value range of the flow node is also [ 0, 1 ]. Assuming that the flow tree includes multiple node levels, the node depth can be determined by the location of the node level at which the flow node is located. Specifically, a certain flow tree includes 12 node layers, and the node layer where the flow node is located is the 5 th node layer. Accordingly, the node depth of the flow node can be determined to be 5/12.
In addition, the position of the flow node in the node layer of the flow tree can be directly determined as the node depth of the flow node in the flow tree. At this time, the range of the node depth of the flow node is a positive integer. For example, the flow tree has 12 node levels, and assuming that the node level of the flow node in the flow tree is the 5 th level, the node level (value 5) of the flow node in the flow tree is determined as the node depth of the flow node in the flow tree.
In addition, the user interest level of the process node is also related to whether the current process node is an end node. Assuming that the current process node is an end node, setting the value of whether the end node is 1; and (4) assuming that the current process node is not an end node, setting the value of whether the end node is set to be-1. Therefore, the value range of whether to finish the node is (1, 1).
Specifically, when determining the emotional tendency coefficient, the node depth coefficient, and the end node coefficient, the emotional tendency coefficient, the node depth coefficient, and the end node coefficient may be determined based on the received configuration instruction. Preferably, the configured emotional tendency coefficient, the node depth coefficient and the end node coefficient can be modified and the like.
When determining the user interest degree of the process node, the user interest degree may be specifically determined by the following formula:
In＝a×L+b×S+c×E；
wherein In represents the user interest degree of the process node, a represents the emotional tendency coefficient, L represents the user emotional tendency information of the process node, b represents the node depth coefficient, S represents the node depth, c represents the end node coefficient, and E represents the value of whether the end node is taken, which can only be-1 or 1. In a preferred embodiment, the emotion tendency coefficient, the node depth coefficient, and the end node coefficient satisfy: a + b + c is 1.
For example, assuming that the emotion tendency coefficient a, the node depth coefficient b, and the end node coefficient c are 0.8, 0.1, and.01, respectively, the user interest level In of the flow node is 0.8L +0.1S + 0.1E.
In the embodiment of the invention, the emotion tendency coefficient, the node depth coefficient and the end node coefficient are determined based on the received coefficient configuration instruction, and then the user interest degree of each process node is determined according to the user emotion tendency information and emotion tendency coefficient of each process node, the node depth and the node depth coefficient, and whether the current process node is the end node or the end node coefficient, so that the flexibility of determining the user interest degree of the process node can be improved.
Fig. 5 shows an implementation flow of step 103 in the intelligent outbound processing method provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to accurately determine the importance degree of the process node, as shown in fig. 5, step 103 determines the importance degree of each process node according to the user reach and the user interest degree of each process node in the process tree, including:
step 501, determining a reach coefficient and an interest coefficient of each flow node in a flow tree;
step 502, determining the importance degree of each process node according to the user reach rate and reach rate coefficient of each process node in the process tree, and the user interest degree and interest coefficient of each process node in the process tree.
When determining the importance degree of the process node, the importance degree is mainly related to two factors, namely the user reach rate and the user interest degree of the process node. First, the reach coefficient of a process node and the interest coefficient of the process node may be determined. In a preferred embodiment, the sum of the reach coefficient of the process node and the interest coefficient of the process node is 1. Or the sum of the reach coefficient of the process node and the interesting coefficient of the process node is not less than 0.8 or 0.9, and the like.
In addition, the reach coefficient of the process node and the interesting coefficient of the process node can be adjusted and modified respectively based on the actual situation and the specific requirements.
When determining the importance degree of a flow node, the importance degree may be specifically determined by the following formula:
TS＝p×TR+q×In；
wherein TS represents the importance degree of the process node, p represents the reach rate coefficient of the process node, TR represents the user reach rate of the process node, q represents the user interest coefficient of the process node, and In represents the user interest degree of the process node.
In a preferred embodiment, the reach coefficient of the flow node and the user interest coefficient of the flow node satisfy p + q ═ 1. For example, p is 0.5 and q is 0.5; or p is 0.6 and q is 0.4.
In the embodiment of the invention, the reach rate coefficient and the interest coefficient of each process node in the process tree are determined, the importance degree of each process node is determined according to the user reach rate and the reach rate coefficient of each process node in the process tree and the user interest degree and the interest coefficient of each process node in the process tree, and the importance degree of the process node can be accurately determined.
Fig. 6 shows an implementation flow of step 104 in the intelligent outbound processing method provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to optimize the process nodes of the process tree based on the user feedback, as shown in fig. 6, step 104, adjusting the process nodes of the process tree according to the importance level of each process node includes:
step 601, ranking the flow nodes with high importance degree in the flow tree in front of the flow nodes with low importance degree according to the sequence from high to low, and obtaining the flow tree after the flow nodes are adjusted.
After the importance degree of each process node is determined, optimizing and adjusting the process nodes of the process tree according to the sequence of the importance degrees of the process nodes from high to low, namely, arranging the process nodes with high importance degrees in front of the process nodes and arranging the process nodes with low importance degrees in back of the process nodes to obtain the final process tree after the process nodes are optimized.
In the embodiment of the invention, the flow nodes with high importance degree in the flow tree are arranged in front of the flow nodes with low importance degree according to the sequence from high to low, so that the flow tree after the flow nodes are adjusted is obtained, and the flow nodes of the flow tree can be optimized based on user feedback.
In an embodiment of the present invention, in order to further optimize the process nodes in the process tree, as shown in fig. 6, step 104, adjusting the process nodes in the process tree according to the importance level of each process node includes:
step 602, deleting the process nodes with the importance degree lower than the preset importance degree threshold from the process tree.
The higher the importance degree of the process node is, the greater the influence degree of the process node on the user is, the lower the importance degree of the process node is, and the smaller or no influence of the process node on the user is. At this time, the process nodes may be divided by setting a preset importance threshold.
Specifically, the process nodes with the importance degree lower than the preset importance degree threshold are deleted from the process tree, the operation does not affect other process nodes with higher importance degree in the process tree, and the deleted process nodes have little or no influence on the user, so that the purpose of further optimizing the process nodes in the process tree is achieved.
In the embodiment of the invention, the process nodes with the importance degree lower than the preset importance degree threshold value are deleted from the process tree, so that the process nodes in the process tree can be further optimized.
The embodiment of the invention also provides an intelligent outbound processing device, which is described in the following embodiment. Because the principle of solving the problems of the devices is similar to that of the intelligent outbound processing method, the implementation of the devices can be referred to the implementation of the method, and repeated details are not repeated.
Fig. 7 shows functional modules of the intelligent outbound processing apparatus provided in the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
referring to fig. 7, each module included in the intelligent outbound processing apparatus is used to execute each step in the embodiment corresponding to fig. 1, and specific reference is made to fig. 1 and the related description in the embodiment corresponding to fig. 1, which is not repeated herein. In the embodiment of the present invention, the intelligent outbound processing apparatus includes a reach rate determining module 701, an interest level determining module 702, an importance level determining module 703, and a node adjusting module 704.
And a reach rate determining module 701, configured to determine a user reach rate of each flow node in the flow tree according to an execution result of the intelligent outbound.
An interest level determining module 702 is configured to determine a user interest level of each flow node in the flow tree.
The importance determining module 703 is configured to determine the importance of each process node according to the user reach and the user interest of each process node in the process tree.
A node adjusting module 704, configured to adjust the flow nodes of the flow tree according to the importance degree of each flow node.
In the embodiment of the present invention, the reach rate determining module 701 determines the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound; the interest level determining module 702 determines the user interest level of each flow node in the flow tree; the importance degree determining module 703 determines the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree; the node adjusting module 704 adjusts the flow nodes of the flow tree according to the importance degree of each flow node. The embodiment of the invention can determine the importance degree of the process node based on the user reach rate and the user interest degree of the process node, further adjust the process node according to the importance degree of the process node, overcome the defect that business personnel subjectively and randomly adjust the process node, and realize the purposes of interactive feedback adjustment based on customers and optimization of the process node of the intelligent outbound process tree.
Fig. 8 shows a schematic structure of the module 701 for determining a reach rate in the intelligent outbound processing apparatus according to the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, which is detailed as follows:
in an embodiment of the present invention, in order to accurately determine the user reach rate of the flow node, referring to fig. 8, each unit included in the reach rate determining module 701 is configured to execute each step in the embodiment corresponding to fig. 2, specifically please refer to fig. 2 and the related description in the embodiment corresponding to fig. 2, which is not described herein again. In the embodiment of the present invention, the reach rate determining module 701 includes a broadcast reach determining unit 801 and a reach rate determining unit 802.
And the broadcast reach determining unit 801 is configured to determine the broadcast number and the reach number of each flow node in the flow tree according to the execution result of the intelligent outbound.
The reach rate determining unit 802 is configured to determine a user reach rate of each flow node according to the broadcast number and the reach number of each flow node in the flow tree.
In the embodiment of the present invention, the broadcast reach determining unit 801 determines the broadcast number and the reach number of each flow node in the flow tree according to the execution result of the intelligent outbound, and the reach determining unit 802 determines the user reach rate of each flow node according to the broadcast number and the reach number of each flow node in the flow tree, so that the user reach rate of the flow node can be accurately determined.
Fig. 9 shows a structural schematic diagram of the interest level determining module 702 in the intelligent outbound processing device provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the detailed description is as follows:
in an embodiment of the present invention, in order to accurately determine the user interest level of a process node, referring to fig. 9, each unit included in the interest level determining module 702 is configured to execute each step in the embodiment corresponding to fig. 3, specifically refer to fig. 3 and the related description in the embodiment corresponding to fig. 3, and details are not repeated here. In this embodiment of the present invention, the interest level determining module 702 includes an emotion analyzing unit 901 and an interest level determining unit 902.
An emotion analyzing unit 901, configured to determine, through natural language processing analysis, user emotional tendency information of each flow node in the flow tree.
An interest level determining unit 902, configured to determine a user interest level of each process node according to the user emotional tendency information and the node depth of each process node, and whether the current process node is an end node.
In the embodiment of the present invention, the emotion analysis unit 901 determines the user emotion tendency information of each flow node in the flow tree through natural language processing analysis, and then the interest level determination unit 902 determines the user interest level of each flow node according to the user emotion tendency information and the node depth of each flow node, and whether the current flow node is an end node, so that the user interest level of the flow node can be accurately determined.
Fig. 10 shows a schematic structural diagram of the interest level determining unit 902 in the intelligent outbound processing device provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, which are detailed as follows:
in an embodiment of the present invention, in order to improve flexibility of determining a user interest level of a process node, referring to fig. 10, each sub-unit included in the interest level determining unit 902 is configured to perform each step in the embodiment corresponding to fig. 4, specifically please refer to fig. 4 and the related description in the embodiment corresponding to fig. 4, which is not repeated herein. In this embodiment of the present invention, the interest level determining unit 902 includes a coefficient determining subunit 1001 and an interest level determining subunit 1002.
A coefficient determination subunit 1001 configured to determine an emotional tendency coefficient, a node depth coefficient, and an end node coefficient based on the received coefficient configuration instruction.
The interest level determining subunit 1002 is configured to determine a user interest level of each process node according to the emotional tendency information and the emotional tendency coefficient of the user of each process node, the node depth and the node depth coefficient, and whether the current process node is an end node or an end node coefficient.
In the embodiment of the present invention, the coefficient determination subunit 1001 determines the emotion tendency coefficient, the node depth coefficient, and the end node coefficient based on the received coefficient configuration instruction, and then the interest degree determination subunit 1002 determines the user interest degree of each process node according to the user emotion tendency information and emotion tendency coefficient of each process node, the node depth and node depth coefficient, and whether the current process node is an end node and an end node coefficient, so that flexibility of determining the user interest degree of the process node can be improved.
Fig. 11 shows a schematic structure of the importance level determining module 703 in the intelligent outbound call processing apparatus provided in the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to accurately determine the importance level of the flow node, referring to fig. 11, each unit included in the importance level determining module 703 is configured to execute each step in the embodiment corresponding to fig. 5, specifically please refer to fig. 5 and the related description in the embodiment corresponding to fig. 5, which is not described herein again. In this embodiment of the present invention, the importance level determining module 703 includes a coefficient determining unit 1101 and an importance level determining unit 1102.
A coefficient determining unit 1101, configured to determine a reach coefficient and an interest coefficient of each flow node in the flow tree.
The importance determining unit 1102 is configured to determine the importance of each process node according to the user reach rate and reach rate coefficient of each process node in the process tree, and the user interest and interest coefficient of each process node in the process tree.
In the embodiment of the present invention, the coefficient determining unit 1101 determines the reach rate coefficient and the interest coefficient of each process node in the process tree, and the importance determining unit 1102 determines the importance of each process node according to the user reach rate and the reach rate coefficient of each process node in the process tree and the user interest and the interest coefficient of each process node in the process tree, so as to accurately determine the importance of the process node.
Fig. 12 shows a schematic structure of a node adjustment module 704 in the intelligent outbound processing apparatus according to the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, which is detailed as follows:
in an embodiment of the present invention, in order to optimize a flow node of a flow tree based on user feedback, referring to fig. 12, each unit included in the node adjustment module 704 is configured to execute each step in the embodiment corresponding to fig. 6, and please refer to fig. 6 and the related description in the embodiment corresponding to fig. 6 specifically, which is not described herein again. In this embodiment of the present invention, the node adjusting module 704 includes a node adjusting unit 1201.
The node adjusting unit 1201 is configured to rank, in order from high to low, a process node with a high importance degree in the process tree in front of a process node with a low importance degree, so as to obtain a process tree after the process node is adjusted.
In the embodiment of the present invention, the node adjustment unit 1201 ranks, in order from high to low, the process nodes with a high degree of importance in the process tree in front of the process nodes with a low degree of importance to obtain the process tree after the process nodes are adjusted, and can optimize the process nodes of the process tree based on user feedback.
In an embodiment of the present invention, to further optimize the flow nodes in the flow tree, referring to fig. 12, the node adjustment module 704 includes a node deletion module 1202.
A node deleting module 1202, configured to delete the process node whose importance degree is lower than the preset importance degree threshold from the process tree.
In the embodiment of the present invention, the node deleting module 1202 deletes the process node whose importance degree is lower than the preset importance degree threshold from the process tree, so as to further optimize the process node in the process tree.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the intelligent outbound processing method when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the intelligent outbound processing method is stored in the computer-readable storage medium.
In summary, in the embodiments of the present invention, the user reach rate of each flow node in the flow tree is determined according to the execution result of the intelligent outbound; determining the user interest degree of each process node in the process tree; determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree; and adjusting the process nodes of the process tree according to the importance degree of each process node. The embodiment of the invention can determine the importance degree of the process node based on the user reach rate and the user interest degree of the process node, further adjust the process node according to the importance degree of the process node, overcome the defect that business personnel subjectively and randomly adjust the process node, and realize the purposes of interactive feedback adjustment based on customers and optimization of the process node of the intelligent outbound process tree.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. An intelligent outbound processing method, comprising:
determining the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound;
determining the user interest degree of each process node in the process tree;
determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree;
and adjusting the process nodes of the process tree according to the importance degree of each process node.
2. The intelligent outbound processing method of claim 1 wherein determining the user reach rate for each flow node in the flow tree based on the execution of the intelligent outbound comprises:
respectively determining the broadcast number and the reach number of each flow node in the flow tree according to the execution result of the intelligent outbound call;
and determining the user reach rate of each flow node according to the broadcast number and reach number of each flow node in the flow tree.
3. The intelligent outbound processing method of claim 1 or 2 wherein determining a user's level of interest for each flow node in the flow tree comprises:
determining the emotional tendency information of the user of each flow node in the flow tree through natural language processing analysis;
and determining the user interest degree of each process node according to the user emotional tendency information and the node depth of each process node and whether the current process node is an end node.
4. The intelligent outbound processing method of claim 3 wherein determining the user's interest level of each flow node based on the user emotional tendency information and the node depth of each flow node and whether the current flow node is an end node comprises:
determining an emotional tendency coefficient, a node depth coefficient and an end node coefficient based on the received coefficient configuration instruction;
and determining the user interest degree of each process node according to the user emotional tendency information and emotional tendency coefficient of each process node, the node depth and the node depth coefficient, and whether the current process node is an end node or an end node coefficient.
5. The intelligent outbound processing method of claim 1 wherein determining the importance level of each flow node based on the user reach and the user interest level of each flow node in the flow tree comprises:
determining a reach rate coefficient and an interest coefficient of each process node in the process tree;
and determining the importance degree of each process node according to the user reach rate and reach rate coefficient of each process node in the process tree and the user interest degree and interest coefficient of each process node in the process tree.
6. The intelligent outbound processing method of claim 1 wherein adjusting the flow nodes of the flow tree based on the importance of each flow node comprises:
and according to the sequence from high to low, arranging the flow nodes with high importance degree in the flow tree in front of the flow nodes with low importance degree to obtain the flow tree after the flow nodes are adjusted.
7. The intelligent outbound processing method of claim 1 or 6 wherein adjusting the flow nodes of the flow tree according to the importance of each flow node comprises:
and deleting the process nodes with the importance degrees lower than the preset importance degree threshold value from the process tree.
8. An intelligent outbound processing device, comprising:
the reach rate determining module is used for determining the user reach rate of each flow node in the flow tree according to the execution result of the intelligent outbound;
the interest degree determining module is used for determining the user interest degree of each process node in the process tree;
the importance degree determining module is used for determining the importance degree of each process node according to the user reach rate and the user interest degree of each process node in the process tree;
and the node adjusting module is used for adjusting the process nodes of the process tree according to the importance degree of each process node.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the intelligent outbound processing method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program for executing the intelligent outbound processing method according to any one of claims 1 to 7.
CN202010807563.7A 2020-08-12 2020-08-12 Intelligent outbound processing method and device Active CN111950902B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010807563.7A CN111950902B (en) 2020-08-12 2020-08-12 Intelligent outbound processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010807563.7A CN111950902B (en) 2020-08-12 2020-08-12 Intelligent outbound processing method and device

Publications (2)

Publication Number Publication Date
CN111950902A true CN111950902A (en) 2020-11-17
CN111950902B CN111950902B (en) 2023-08-22

Family

ID=73332367

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010807563.7A Active CN111950902B (en) 2020-08-12 2020-08-12 Intelligent outbound processing method and device

Country Status (1)

Country Link
CN (1) CN111950902B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101167103A (en) * 2005-03-11 2008-04-23 法国电信公司 Method of transmitting content display data between a server and at least one client terminal, and corresponding server, terminal and computer program
US20160371271A1 (en) * 2015-06-18 2016-12-22 International Business Machines Corporation Identification of Target Audience for Content Delivery in Social Networks by Quantifying Semantic Relations and Crowdsourcing
CN110636109A (en) * 2019-08-19 2019-12-31 咪咕视讯科技有限公司 Node scheduling optimization method, server and computer readable storage medium
CN111460108A (en) * 2019-01-22 2020-07-28 北京京东尚科信息技术有限公司 Intelligent response method and device
CN111510563A (en) * 2020-04-16 2020-08-07 中国银行股份有限公司 Intelligent outbound method and device, storage medium and electronic equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101167103A (en) * 2005-03-11 2008-04-23 法国电信公司 Method of transmitting content display data between a server and at least one client terminal, and corresponding server, terminal and computer program
US20160371271A1 (en) * 2015-06-18 2016-12-22 International Business Machines Corporation Identification of Target Audience for Content Delivery in Social Networks by Quantifying Semantic Relations and Crowdsourcing
CN111460108A (en) * 2019-01-22 2020-07-28 北京京东尚科信息技术有限公司 Intelligent response method and device
CN110636109A (en) * 2019-08-19 2019-12-31 咪咕视讯科技有限公司 Node scheduling optimization method, server and computer readable storage medium
CN111510563A (en) * 2020-04-16 2020-08-07 中国银行股份有限公司 Intelligent outbound method and device, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN111950902B (en) 2023-08-22

Similar Documents

Publication Publication Date Title
US20180255009A1 (en) Emoji recommendation method and apparatus
US10120955B2 (en) State tracking over machine-learned relational trees in a dialog system
CN110019286B (en) Expression recommendation method and device based on user social relationship
US11176319B2 (en) Leveraging a topic divergence model to generate dynamic sidebar chat conversations based on an emotive analysis
CN111179929B (en) Voice processing method and device
CN113901226B (en) Real-time live broadcast data processing method and computer storage medium
US20150324099A1 (en) Connecting Current User Activities with Related Stored Media Collections
CN110689903B (en) Method, device, equipment and medium for evaluating intelligent sound box
CA3223975A1 (en) Image analysis system
WO2016165414A1 (en) Method and device for push information
CN113343089A (en) User recall method, device and equipment
US20160136526A1 (en) Perpetual Gaming Platform
CN111159382B (en) Method and device for constructing and using session system knowledge model
CN115374266A (en) Interaction method, device, equipment and storage medium based on plot interaction node
KR102171658B1 (en) Crowd transcription apparatus, and control method thereof
US10873662B2 (en) Identifying a media item to present to a user device via a communication session
CN111950902A (en) Intelligent outbound call processing method and device
CN115375808A (en) Behavior control method and device for virtual live character
CN115409585B (en) Information recommendation method based on voice interaction system and related device
CN111443973A (en) Filling method, device and equipment of remark information and storage medium
CN108197189B (en) Active interaction method and device
CN116301329A (en) Intelligent device active interaction method, device, equipment and storage medium
CN113779401A (en) Method for improving hot degree of live broadcast room, electronic equipment and computer readable storage medium
CN110399471A (en) A kind of guiding situational dialogues method and system
CN110580342A (en) public number question-answer response method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant