Seat outbound method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, is applied to a seat call-out distribution scene, and relates to a seat call-out method, device and equipment and a storage medium thereof. Obtaining an outbound call answering behavior representation value of the user; obtaining a user grade classification result based on the historical service transaction information; obtaining an outbound evaluation value according to the outbound answering behavior representation value and the grade classification result; based on the outbound evaluation value and an outbound distribution strategy, an outbound intelligent assistant is distributed to the user, outbound is carried out, and an outbound feedback result is obtained; and screening out a target intention user and transferring the target intention user to a manual service agent. According to the method, intelligent outbound assistant allocation is performed on the user in combination with the outbound answering behavior characterization value and the user level classification result, high-value customers who answer quickly can be screened out to perform outbound service preferentially, the outbound service conversion rate is improved, meanwhile, a layer of outbound intelligent assistant is arranged in front of the manual service agent to perform service intention filtering treatment, and the user experience is improved. And the workload of manual service seats is reduced.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and is applied to an agent outbound call allocation scenario, and in particular to an agent outbound call method, device, equipment, and storage medium thereof. Background Art

[0002] Outbound calls refer to: the phone automatically dials the user's phone through the computer, and the recorded voice is played to the user through the computer. It is an indispensable part of the modern customer service center system of computer and telephone telephony integration. Outbound calls for business promotion are an indispensable and important part of many product services, such as insurance sales services, financial services, financial services, real estate sales services, event invitations and other services. Many banks, insurance companies, securities companies, etc. have established their own telephone marketing platforms, and use the telephone marketing platforms to achieve marketing promotion such as applying for loans, credit cards or purchasing insurance and financial products, thereby expanding and maintaining customers and increasing corporate benefits.

[0003] However, taking the insurance business of insurance companies as an example, the seats mainly use the method of centralized outbound calls during popular time periods, which fails to reasonably allocate seat resources, resulting in low outbound call efficiency and business conversion rate. Therefore, how to improve outbound call efficiency and business conversion rate has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose an agent outbound calling method, device, equipment and storage medium thereof to solve the problem that the existing outbound calling method cannot reasonably allocate seat resources, resulting in low outbound calling efficiency and business conversion rate.

[0005] In order to solve the above technical problems, the embodiment of the present application provides an agent outbound calling method, which adopts the following technical solution:

[0006] A seat outbound calling method comprises the following steps:

[0007] Get the outbound user list;

[0008] According to the outbound call user list, outbound call answering behavior information and historical service transaction information of all users in the outbound call user list are filtered out from the big data;

[0009] Analyzing the outbound call answering behaviors of all the users through the outbound call answering behavior information, and obtaining outbound call answering behavior representation values ​​corresponding to all the users in a preset representation form;

[0010] Classify all users by user level based on the historical service transaction information to obtain the level classification results of all users;

[0011] Inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively;

[0012] Based on the outbound call evaluation value and the preset outbound call allocation strategy, the target type of users are screened out from the outbound call user list and allocated to the preset cluster type outbound call intelligent assistant to make the outbound call and obtain the outbound call feedback result;

[0013] According to the outbound call feedback result, target intended users are screened out, and the target intended users are transferred to manual seats for business services.

[0014] Furthermore, the outbound call answering behavior information includes answering waiting time information and actual call time information. The step of analyzing the outbound call answering behavior of all users through the outbound call answering behavior information and obtaining the outbound call answering behavior characterization values ​​corresponding to all users in a preset characterization form specifically includes:

[0015] Obtain the answering waiting time information and actual call duration information corresponding to each outbound call answering of all the user's history;

[0016] According to the answering waiting time information and the actual call duration information corresponding to each outbound call answering in the history of all users, the average answering waiting time information and the average actual call duration information are obtained;

[0017] The characterization value is calculated by the preset formula:

[0018] C i =a i ×α1+b i ×α2,

[0019] Calculate the outbound call answering behavior characterization values ​​corresponding to all the users, where C i represents the characterization value, a i Indicates the average waiting time for answering calls, b i represents the average actual call duration information, α1 represents the preset first weight coefficient, α2 represents the preset second weight coefficient, and α1+α2=1, and i represents the user number information.

[0020] Furthermore, the step of classifying all users by user level based on the historical service transaction information specifically includes:

[0021] Inputting the historical service transaction information into a preset customer classification model, wherein the historical service transaction information includes user binary classification features of N dimensions, wherein N is a positive integer;

[0022] All the users are divided into user levels based on the user binary classification features of the N dimensions.

[0023] Furthermore, before executing the step of classifying all the users according to the user binary classification features in the N dimensions, the method further includes:

[0024] Using the preset algorithm formula:

[0025] M=2 N ,

[0026] Set M user levels, where M represents the number of user level categories, N represents the number of dimensions, and 2 N Represents the power of 2, where N is a positive integer.

[0027] Furthermore, the user binary classification features of the N dimensions include transaction product information, transaction amount information, and transaction promotion rate information. Before executing the step of classifying all users according to the user binary classification features of the N dimensions, the method further includes:

[0028] Obtaining a pre-sorted list of hot products, wherein the list of hot products includes information on the names of the hot products;

[0029] Obtaining a preset binary index value of the transaction amount, wherein the binary index value of the transaction amount is a preset unique transaction amount value. If the current transaction amount is higher than the unique transaction amount value, it indicates that the current transaction amount meets the standard, otherwise the current transaction amount does not meet the standard;

[0030] Obtaining a preset binary index value of the transaction facilitation rate, wherein the binary index value of the transaction facilitation rate is a preset unique probability value, and if the current transaction facilitation rate is higher than the unique probability value, it indicates that the current transaction facilitation rate meets the standard, otherwise the current transaction facilitation rate does not meet the standard;

[0031] The step of classifying all the users into user levels based on the user binary classification features of the N dimensions includes:

[0032] Calculate the proportion of hot products in the transaction product information corresponding to the current user;

[0033] Summarize the total transaction amount information corresponding to the current user, and identify whether the transaction amount information corresponding to the current user meets the requirements based on the total transaction amount information and the preset unique transaction amount value;

[0034] According to the transaction facilitation rate information corresponding to the current user and the preset unique probability value, identifying whether the transaction facilitation rate corresponding to the current user meets the standard;

[0035] The user level of the current user is determined based on the ratio value, whether the transaction amount information meets the standard, and whether the transaction facilitation rate meets the standard.

[0036] Furthermore, before executing the step of inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively, the method further includes:

[0037] Pre-set numerical level values ​​that decrease in sequence according to the user level from high to low;

[0038] Obtaining an evaluation method pre-constructed according to the outbound call answering behavior characterization value and the user level, wherein the evaluation method follows that the larger the outbound call answering behavior characterization value and the higher the user level, the higher the outbound call evaluation value, and the evaluation method includes summing the outbound call answering behavior characterization value and the numerical level value corresponding to the same user;

[0039] Deploying the evaluation method as reference knowledge into the outbound call evaluation model;

[0040] The step of inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively comprises:

[0041] Select different users in turn as the current target user;

[0042] Identifying the user level of the current target user from the level classification results of all users;

[0043] According to the user level, obtaining a numerical level value corresponding to the current target user;

[0044] Filtering the outbound call answering behavior representation value of the current target user from the outbound call answering behavior representation values ​​corresponding to all the users;

[0045] The numerical grade value corresponding to the current target user and the outbound call answering behavior representation value of the current target user are summed to obtain the outbound call evaluation value corresponding to the current target user.

[0046] Further, the step of screening out users of the target type from the outbound call user list and assigning them to the preset cluster type outbound call intelligent assistant based on the outbound call evaluation value and the preset outbound call allocation strategy, making the outbound call, and obtaining the outbound call feedback result specifically includes:

[0047] According to the outbound call evaluation values ​​corresponding to all users in the outbound call user list, all the users are sorted in descending order to obtain a descending sequence;

[0048] Filtering out the top I users from the descending sequence as users of the target type, where I is a positive integer;

[0049] Identify the current outbound call task volume of all outbound call intelligent assistants in the clustered outbound call intelligent assistant and the outbound call service types handled by all outbound call intelligent assistants respectively through the previous work allocation log;

[0050] According to the current outbound call task volume of all the outbound call intelligent assistants in the cluster-type outbound call intelligent assistant and the outbound call service types handled by all the outbound call intelligent assistants respectively, the users of the target type are assigned to the corresponding outbound call intelligent assistants.

[0051] Furthermore, the step of allocating the target type of users to corresponding outbound intelligent assistants according to the current outbound call task volume of all outbound intelligent assistants in the clustered outbound intelligent assistants and the outbound call service types respectively processed by all outbound intelligent assistants specifically includes:

[0052] Identify the outbound call service types corresponding to all target types of users;

[0053] According to the outbound call service type, all outbound call intelligent assistants that process the outbound call service type are screened out from the cluster-type outbound call intelligent assistants;

[0054] From all the outbound call intelligent assistants that process the outbound call service type, select the outbound call intelligent assistant with the least current outbound call task volume as the outbound call intelligent assistant to be assigned;

[0055] According to the preset outbound call real-time monitoring component, all outbound call intelligent assistants that process the outbound call business type are monitored in real time to obtain the outbound call task progress of all outbound call intelligent assistants that process the outbound call business type;

[0056] Based on the progress of the outbound call task, outbound call tasks are allocated among all the outbound call intelligent assistants.

[0057] In order to solve the above technical problems, the embodiment of the present application also provides an agent outbound calling device, which adopts the following technical solution:

[0058] A seat outbound calling device, comprising:

[0059] An outbound user list acquisition module is used to acquire an outbound user list;

[0060] A user-related information screening module is used to screen out the outbound call answering behavior information and historical service transaction information of all users in the outbound call user list from the big data according to the outbound call user list;

[0061] An outbound call answering behavior characterization module, used to analyze the outbound call answering behavior of all the users through the outbound call answering behavior information, and obtain the outbound call answering behavior characterization values ​​corresponding to all the users in a preset characterization form;

[0062] A user grade classification module, used to classify all users by user grade based on the historical service transaction information, and obtain the grade classification results of all users;

[0063] An outbound call evaluation value obtaining module, used to input the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively;

[0064] An outbound call assistant allocation module is used to screen out target type users from the outbound call user list and assign them to a preset cluster type outbound call intelligent assistant based on the outbound call evaluation value and the preset outbound call allocation strategy, make the outbound call, and obtain the outbound call feedback result;

[0065] The target intended user transfer module is used to screen out the target intended users according to the outbound call feedback result, and transfer the target intended users to the manual seat for business service.

[0066] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0067] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned agent outbound calling method when executing the computer-readable instructions.

[0068] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0069] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the agent outbound calling method described above are implemented.

[0070] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0071] The agent outbound call method described in the embodiment of the present application obtains a list of outbound call users; screens outbound call answering behavior information and historical service transaction information of users; obtains the outbound call answering behavior characterization value of users; obtains the user grade classification result based on the historical service transaction information; obtains the outbound call evaluation value according to the outbound call answering behavior characterization value and the grade classification result; based on the outbound call evaluation value and the outbound call allocation strategy, screens out the target type of users and assigns them to the outbound call intelligent assistant, makes the outbound call, and obtains the outbound call feedback result; screens out the target intended users and transfers them to the manual agent. The present application combines the outbound call answering behavior characterization value and the user grade classification result to allocate intelligent outbound call assistants to users, and can screen out high-value customers who answer quickly and give priority to outbound call services, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistant before the manual agent to perform business intention filtering and disposal, the workload of the manual agent is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0073] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0074] Figure 2 is a flow chart of an embodiment of an agent outbound calling method according to the present application;

[0075] Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 203 is shown;

[0076] Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 204 is shown;

[0077] Figure 5 yes Figure 2 A flowchart of a specific embodiment of deploying the evaluation method to the outbound call evaluation model before step 205 is shown;

[0078] Figure 6 yes Figure 2 A flowchart of a specific embodiment of step 205 is shown;

[0079] Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 206 is shown;

[0080] Figure 8 yes Figure 7 A flowchart of a specific embodiment of step 704 is shown;

[0081] Fig. 9 It is a structural schematic diagram of an embodiment of a seat outbound calling device according to the present application;

[0082] Fig.10 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0083] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0084] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0085] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0086] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0087] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0088] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0089] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0090] It should be noted that the agent outbound calling method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the agent outbound calling device is generally arranged in the terminal device.

[0091] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0092] Continue to refer Figure 2 , shows a flow chart of an embodiment of an agent outbound calling method according to the present application. The agent outbound calling method comprises the following steps:

[0093] Step 201, obtaining a list of outbound users;

[0094] Specifically, the outbound user list may be a customer list uploaded from a customer management system for service maintenance or service recommendation, which at least includes the customer's outbound contact information. The outbound user list may be, for example, a customer list to be contacted in a financial service scenario.

[0095] By obtaining the list of outbound users, it is convenient for the company's business management or marketing party to market the company's business.

[0096] Step 202, based on the outbound user list, filter out the outbound call answering behavior information and historical service transaction information of all users in the outbound user list from the big data;

[0097] In this embodiment, the outbound call answering behavior information and historical service transaction information of all users in the outbound call user list are filtered out from big data. The specific implementation method is to obtain the outbound call answering behavior information and historical service transaction information of all users in the outbound call user list from multiple authoritative data platforms.

[0098] By obtaining the outbound call answering behavior information and historical service transaction information of all users in the outbound call user list from multiple authoritative data platforms, it is convenient to allocate an intelligent outbound call assistant to the user in combination with the outbound call answering behavior information and historical service transaction information.

[0099] Step 203, analyzing the outbound call answering behaviors of all the users through the outbound call answering behavior information, and obtaining outbound call answering behavior characterization values ​​corresponding to all the users using a preset characterization form;

[0100] Specifically, the outbound call answering behavior information includes answering waiting time information and actual call time information.

[0101] In this embodiment, a preset representation form is adopted to obtain the representation value of the outbound call answering behavior corresponding to all the users, which is essentially to digitize the outbound call answering behavior corresponding to the user, so as to facilitate the subsequent allocation of intelligent outbound call assistants using the digitized processing results, facilitate the execution and processing of the computer, and at the same time, improve the interpretability of the outbound call behavior.

[0102] Step 204, classifying all the users into user grades based on the historical service transaction information to obtain grade classification results for all the users;

[0103] In this embodiment, all the users are classified into user levels based on the historical service transaction information. First, the multidimensional feature data in the historical service transaction information is screened out, and the multidimensional feature data is classified by binary classification according to a preset binary classification index value. Then, the level classification results of all the users are set and obtained according to the binary classification results. The purpose of the processing here is to classify the users according to their corresponding historical service transaction information, so that when the intelligent outbound call assistant is subsequently allocated, the company's high-value customers are allocated first according to the user level to avoid the loss of high-value customers.

[0104] Step 205, inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively;

[0105] Specifically, the outbound call evaluation values ​​corresponding to all the users are obtained by inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model. The outbound call evaluation values ​​corresponding to all the users are obtained from a comprehensive analysis perspective by combining the outbound call answering behavior characterization values ​​and the grade classification results. This enables priority calls to be made to customers with high grades and good outbound call answering behaviors. This can not only give priority to serving high-quality customers, but also save outbound call resource consumption and improve business facilitation efficiency.

[0106] Step 206, based on the outbound call evaluation value and the preset outbound call allocation strategy, select the target type of users from the outbound call user list and assign them to the preset cluster type outbound call intelligent assistant, make the outbound call, and obtain the outbound call feedback result;

[0107] In this embodiment, the target type of users can be understood as users whose outbound call evaluation values ​​are greater than a preset evaluation threshold. Such users are preferentially assigned outbound call intelligent assistants and given priority in outbound calls to ensure that as many outbound calls as possible are made to high-quality and high-value customers in the same amount of time, thereby improving the business promotion rate.

[0108] Step 207: Screen out target potential users according to the outbound call feedback result, and transfer the target potential users to a human agent for business service.

[0109] Specifically, after the robot, i.e., the outbound intelligent assistant, makes an outbound call, it screens out target potential users, i.e., users who are satisfied with the service, based on the outbound call feedback results, and transfers the service to manual seats for subsequent business services. By setting up a layer of outbound intelligent assistant before the manual seats to perform business intention filtering and processing, it can not only reduce the workload of the manual seats, but also improve the efficiency of outbound business calls.

[0110] In this embodiment, by obtaining a list of outbound call users; filtering out the outbound call answering behavior information and historical service transaction information of the users; obtaining the outbound call answering behavior characterization value of the users; obtaining the user level classification result based on the historical service transaction information; obtaining the outbound call evaluation value according to the outbound call answering behavior characterization value and the level classification result; based on the outbound call evaluation value and the outbound call allocation strategy, filter out the target type of users and assign them to the outbound call intelligent assistant, make the outbound call, and obtain the outbound call feedback result; filter out the target intended users and transfer them to the manual seat. This application combines the outbound call answering behavior characterization value and the user level classification result to allocate intelligent outbound call assistants to users, and can filter out high-value customers who answer quickly and give priority to outbound call services, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistant before the manual seat to perform business intention filtering and disposal, the workload of the manual seat is reduced.

[0111] Continue to refer Figure 3 , Figure 3yes Figure 2 The flowchart of a specific embodiment of step 203 shown includes the following steps:

[0112] Step 301, obtaining the answering waiting time information and the actual call time information corresponding to each outbound call answering of all the users in history;

[0113] Step 302, obtaining average call waiting time information and average actual call time information according to the call waiting time information and actual call time information corresponding to each outbound call answering of all the users in history;

[0114] Step 303, using a preset characterization value calculation formula:

[0115] C i =a i ×α1+b i ×α2,

[0116] Calculate the outbound call answering behavior characterization values ​​corresponding to all the users, where C i represents the characterization value, a i Indicates the average waiting time for answering calls, b i represents the average actual call duration information, α1 represents the preset first weight coefficient, α2 represents the preset second weight coefficient, and α1+α2=1, and i represents the user number information.

[0117] By using the answering waiting time information and actual call duration information corresponding to each outbound call answering by the user as feature dimensions, we can obtain the user's corresponding outbound call answering behavior representation value, which makes it easier to allocate outbound smart assistants to customers who answer calls quickly and have more efficient call communication, thereby improving the efficiency of outbound call business.

[0118] Continue to refer Figure 4 , Figure 4 yes Figure 2 The flowchart of a specific embodiment of step 204 shown includes the following steps:

[0119] Step 401, inputting the historical service transaction information into a preset customer classification model, wherein the historical service transaction information includes user binary classification features of N dimensions, wherein N is a positive integer;

[0120] Step 402: classify all the users into user levels based on the user binary classification features of the N dimensions.

[0121] Through historical service transaction information, all users are divided into user levels, which fully combines the users' historical service transaction data to facilitate the screening of relatively high-value customers from the outbound user list, give priority to the allocation of outbound smart assistants, and improve the promotion rate and conversion rate of outbound business.

[0122] In this embodiment, before executing the step of classifying all the users into user levels based on the user binary classification features in the N dimensions, the method further includes:

[0123] Using the preset algorithm formula:

[0124] M=2 N ,

[0125] Set M user levels, where M represents the number of user level categories, N represents the number of dimensions, and 2 N Represents the power of 2, where N is a positive integer.

[0126] Specifically, the N-dimensional user binary classification features include transaction product information, transaction amount information and transaction success rate information.

[0127] In this embodiment, before executing the step of classifying all the users into user levels based on the user binary classification features of the N dimensions, the method also includes: obtaining a pre-sorted list of hot products, wherein the hot product list contains hot product name information; obtaining a pre-set transaction amount binary classification indicator value, wherein the transaction amount binary classification indicator value is a preset unique transaction amount value, and if the current transaction amount is higher than the unique transaction amount value, it indicates that the current transaction amount meets the standard, otherwise the current transaction amount does not meet the standard; obtaining a pre-set transaction facilitation rate binary classification indicator value, wherein the transaction facilitation rate binary classification indicator value is a preset unique probability value, and if the current transaction facilitation rate is higher than the unique probability value, it indicates that the current transaction facilitation rate meets the standard, otherwise the current transaction facilitation rate does not meet the standard.

[0128] By pre-setting a list of hot products, binary indicators of transaction amount and binary indicator values ​​of transaction success rate, and then combining the user's actual transaction product information, transaction amount information and transaction success rate information, users can be classified into different levels to facilitate the screening of high-value and high-quality customers.

[0129] Specifically, in the case that the user binary classification features in the N dimensions include the transaction product information, transaction amount information and transaction success rate information, the step of dividing the user levels of all the users according to the user binary classification features in the N dimensions includes: calculating the proportion of hot products in the transaction product information corresponding to the current user; summarizing the total transaction amount information corresponding to the current user, and identifying whether the transaction amount information corresponding to the current user meets the requirements based on the total transaction amount information and the preset unique transaction amount value; identifying whether the transaction success rate corresponding to the current user meets the requirements based on the transaction success rate information corresponding to the current user and the preset unique probability value; and determining the user level of the current user in combination with the proportion value, whether the transaction amount information meets the requirements and whether the transaction success rate meets the requirements.

[0130] By dividing all the users into user levels, it is convenient to subsequently allocate outbound intelligent assistants according to different user levels.

[0131] Continue to refer Figure 5 In some optional implementations, before step 205, a step of deploying the evaluation method to the outbound call evaluation model is also included. Figure 5 yes Figure 2 The flowchart of a specific embodiment of deploying the evaluation method to the outbound call evaluation model before step 205 includes the following steps:

[0132] Step 501, pre-set numerical level values ​​that decrease in sequence according to the user level from high to low;

[0133] Step 502, obtaining an evaluation method pre-constructed according to the outbound call answering behavior characterization value and the user level, wherein the evaluation method follows that the larger the outbound call answering behavior characterization value and the higher the user level, the higher the outbound call evaluation value, and the evaluation method includes summing the outbound call answering behavior characterization value and the numerical level value corresponding to the same user;

[0134] Step 503: deploy the evaluation method as reference knowledge into the outbound call evaluation model.

[0135] By pre-deploying the evaluation method to the outbound evaluation model, it is convenient to evaluate users later.

[0136] Continue to refer Figure 6 , Figure 6 yes Figure 2 The flowchart of a specific embodiment of step 205 shown includes the following steps:

[0137] Step 601, selecting different users in turn as current target users;

[0138] Step 602, identifying the user level of the current target user from the level classification results of all users;

[0139] Step 603, obtaining a numerical level value corresponding to the current target user according to the user level;

[0140] Step 604, filtering out the outbound call answering behavior characterization value of the current target user from the outbound call answering behavior characterization values ​​corresponding to all the users;

[0141] Step 605: sum the numerical grade value corresponding to the current target user and the outbound call answering behavior representation value of the current target user to obtain the outbound call evaluation value corresponding to the current target user.

[0142] By summing the numerical grade value corresponding to the current target user and the outbound call answering behavior representation value of the current target user, the outbound call evaluation value corresponding to the current target user is obtained, which is convenient for combining the outbound call evaluation value corresponding to the user to subsequently allocate an intelligent outbound call assistant to the user.

[0143] Continue to refer Figure 7 , Figure 7 yes Figure 2 The flowchart of a specific embodiment of step 206 shown includes the following steps:

[0144] Step 701, sorting all users in the outbound call user list in descending order according to the outbound call evaluation values ​​corresponding to all users in the outbound call user list to obtain a descending sequence;

[0145] Step 702, selecting the top I users from the descending sequence as users of the target type, where I is a positive integer;

[0146] Step 703, identifying the current outbound call task volume of all outbound call intelligent assistants in the clustered outbound call intelligent assistant and the outbound call service types processed by all outbound call intelligent assistants respectively through the previous work allocation log;

[0147] Step 704, according to the current outbound call task volume of all the outbound call intelligent assistants in the clustered outbound call intelligent assistants and the outbound call service types handled by all the outbound call intelligent assistants respectively, the users of the target type are allocated to the corresponding outbound call intelligent assistants.

[0148] By giving priority to users with higher outbound call evaluation values ​​in the allocation of outbound call intelligent assistants, business conversion can be completed more efficiently.

[0149] Continue to refer Figure 8 , Figure 8 yes Figure 7 The flowchart of a specific embodiment of step 704 shown includes the following steps:

[0150] Step 801, identifying the outbound call service types corresponding to all target types of users;

[0151] Step 802, according to the outbound call service type, filter out all outbound call intelligent assistants that process the outbound call service type from the cluster type outbound call intelligent assistants;

[0152] Step 803, from all the outbound call intelligent assistants that process the outbound call service type, screen out the outbound call intelligent assistant with the least current outbound call task volume as the outbound call intelligent assistant to be assigned;

[0153] Step 804, according to the preset outbound call real-time monitoring component, all outbound call intelligent assistants processing the outbound call service type are monitored in real time to obtain the outbound call task progress of all outbound call intelligent assistants processing the outbound call service type;

[0154] Step 805: Based on the progress of the outbound call task, the outbound call task is allocated among all the outbound call intelligent assistants.

[0155] Through the outbound call real-time monitoring component, all the outbound call intelligent assistants that handle the outbound call business type are monitored in real time, and the outbound call task progress of all the outbound call intelligent assistants that handle the outbound call business type is obtained, thereby achieving timely scheduling of outbound call dynamics during the entire outbound call process and avoiding excessive task load for a single outbound call intelligent assistant.

[0156] In this embodiment, the step of screening out target intended users based on the outbound call feedback results, and transferring the target intended users to a manual agent for business services, specifically includes: screening out business intended users based on the outbound call feedback results; transferring to a manual agent through the communication connection information of the business intended users; and transferring the business intended users to a manual agent for business services.

[0157] It is achieved that according to the outbound call feedback results, target potential users are screened out, that is, users who are satisfied with the business are screened out, and subsequent business services are transferred to manual seats. By setting up a layer of outbound call intelligent assistant before the manual agent to perform business intention filtering and processing, it can not only reduce the workload of the manual agent, but also improve the efficiency of business outbound calls.

[0158] This application obtains a list of outbound call users; screens outbound call answering behavior information and historical service transaction information of users; obtains the characterization value of users' outbound call answering behavior; obtains user grade classification results based on historical service transaction information; obtains outbound call evaluation values ​​based on the outbound call answering behavior characterization values ​​and grade classification results; based on the outbound call evaluation values ​​and outbound call allocation strategies, screens out target type of users and assigns them to outbound call intelligent assistants to make the outbound call and obtain outbound call feedback results; screens out target intended users and transfers them to manual seats. This application combines the outbound call answering behavior characterization values ​​and user grade classification results to assign intelligent outbound call assistants to users, and can screen out high-value customers who answer quickly and give priority to outbound call services, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistants before manual seats to filter and process business intentions, the workload of manual seats can be reduced.

[0159] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0160] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0161] In the embodiment of the present application, by obtaining a list of outbound call users; filtering out the outbound call answering behavior information and historical service transaction information of the users; obtaining the outbound call answering behavior characterization value of the users; obtaining the user level classification result based on the historical service transaction information; obtaining the outbound call evaluation value according to the outbound call answering behavior characterization value and the level classification result; based on the outbound call evaluation value and the outbound call allocation strategy, the target type of users are filtered out and assigned to the outbound call intelligent assistant, the outbound call is made, and the outbound call feedback result is obtained; the target intended users are filtered out and transferred to the manual seat. The present application combines the outbound call answering behavior characterization value and the user level classification result to allocate the intelligent outbound call assistant to the users, and can filter out high-value customers who answer quickly and give priority to outbound call service, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistant before the manual seat to filter and handle the business intention, the workload of the manual seat is reduced.

[0162] Further references Fig. 9 , as a response to the above Figure 2The present application provides an embodiment of a seat outbound calling device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0163] like Fig. 9 As shown, the seat outbound calling device 900 described in this embodiment includes: an outbound calling user list acquisition module 901, a user related information screening module 902, an outbound calling answering behavior characterization module 903, a user level classification module 904, an outbound calling evaluation value acquisition module 905, an outbound calling assistant allocation module 906 and a target intended user transfer module 907. Among them:

[0164] An outbound user list acquisition module 901 is used to acquire an outbound user list;

[0165] The user-related information screening module 902 is used to screen the outbound call answering behavior information and historical service transaction information of all users in the outbound call user list from the big data according to the outbound call user list;

[0166] The outbound call answering behavior characterization module 903 is used to analyze the outbound call answering behavior of all the users through the outbound call answering behavior information, and obtain the outbound call answering behavior characterization values ​​corresponding to all the users in a preset characterization form;

[0167] A user level classification module 904 is used to classify all users based on the historical service transaction information to obtain the level classification results of all users;

[0168] The outbound call evaluation value obtaining module 905 is used to input the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively;

[0169] The outbound call assistant allocation module 906 is used to screen out target type users from the outbound call user list and allocate them to the preset cluster type outbound call intelligent assistant based on the outbound call evaluation value and the preset outbound call allocation strategy, make the outbound call, and obtain the outbound call feedback result;

[0170] The target intended user transfer module 907 is used to screen out target intended users according to the outbound call feedback result, and transfer the target intended users to manual seats for business services.

[0171] This application obtains a list of outbound call users; screens outbound call answering behavior information and historical service transaction information of users; obtains the characterization value of users' outbound call answering behavior; obtains user grade classification results based on historical service transaction information; obtains outbound call evaluation values ​​based on the outbound call answering behavior characterization values ​​and grade classification results; based on the outbound call evaluation values ​​and outbound call allocation strategies, screens out target type of users and assigns them to outbound call intelligent assistants to make the outbound call and obtain outbound call feedback results; screens out target intended users and transfers them to manual seats. This application combines the outbound call answering behavior characterization values ​​and user grade classification results to assign intelligent outbound call assistants to users, and can screen out high-value customers who answer quickly and give priority to outbound call services, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistants before manual seats to filter and process business intentions, the workload of manual seats can be reduced.

[0172] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0173] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0174] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0175] The computer device 10 includes a memory 10a, a processor 10b, and a network interface 10c which are interconnected and communicated via a system bus. It should be noted that: Fig.10Only a computer device 10 having a component memory 10a, a processor 10b, and a network interface 10c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0176] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0177] The memory 10a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10a can be an internal storage unit of the computer device 10, such as a hard disk or memory of the computer device 10. In other embodiments, the memory 10a can also be an external storage device of the computer device 10, such as a plug-in hard disk equipped on the computer device 10, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10a can also include both the internal storage unit of the computer device 10 and its external storage device. In this embodiment, the memory 10a is generally used to store an operating system and various application software installed on the computer device 10, such as a computer-readable instruction of an agent outbound calling method, etc. In addition, the memory 10a can also be used to temporarily store various data that have been output or will be output.

[0178] The processor 10b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 10b is generally used to control the overall operation of the computer device 10. In this embodiment, the processor 10b is used to run the computer-readable instructions stored in the memory 10a or process data, such as running the computer-readable instructions of the agent outbound calling method.

[0179] The network interface 10c may include a wireless network interface or a wired network interface. The network interface 10c is generally used to establish a communication connection between the computer device 10 and other electronic devices.

[0180] The computer device proposed in this embodiment belongs to the field of artificial intelligence technology and is applied to the outbound call allocation scenario of agents. This application obtains a list of outbound call users; screens outbound call answering behavior information and historical service transaction information of users; obtains the characterization value of the outbound call answering behavior of users; obtains the user level classification result based on the historical service transaction information; obtains the outbound call evaluation value according to the outbound call answering behavior characterization value and the level classification result; based on the outbound call evaluation value and the outbound call allocation strategy, screens out the target type of users and assigns them to the outbound call intelligent assistant, makes the outbound call, and obtains the outbound call feedback result; screens out the target intended users and transfers them to the manual seats. This application combines the outbound call answering behavior characterization value and the user level classification result to allocate intelligent outbound call assistants to users, and can screen out high-value customers who answer quickly and give priority to outbound call services, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistants before the manual seats to filter and handle business intentions, the workload of the manual seats can be reduced.

[0181] The present application also provides another implementation mode, that is, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the above-mentioned agent outbound calling method.

[0182] The computer-readable storage medium proposed in this embodiment belongs to the field of artificial intelligence technology and is applied to the outbound call allocation scenario of agents. This application obtains a list of outbound call users; screens outbound call answering behavior information and historical service transaction information of users; obtains the outbound call answering behavior characterization value of users; obtains the user level classification result based on the historical service transaction information; obtains the outbound call evaluation value according to the outbound call answering behavior characterization value and the level classification result; based on the outbound call evaluation value and the outbound call allocation strategy, screens out the target type of users and assigns them to the outbound call intelligent assistant, makes the outbound call, and obtains the outbound call feedback result; screens out the target intended users and transfers them to the manual seat. This application combines the outbound call answering behavior characterization value and the user level classification result to allocate intelligent outbound call assistants to users, and can screen out high-value customers who answer quickly and give priority to outbound call services, thereby improving the conversion rate of outbound business. At the same time, by setting a layer of outbound call intelligent assistant before the manual seat to perform business intention filtering and disposal, the workload of the manual seat is reduced.

[0183] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0184] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A seat outbound calling method, characterized in that: The steps include: Get the outbound user list; According to the outbound call user list, outbound call answering behavior information and historical service transaction information of all users in the outbound call user list are filtered out from the big data; Analyzing the outbound call answering behaviors of all the users through the outbound call answering behavior information, and obtaining outbound call answering behavior representation values ​​corresponding to all the users in a preset representation form; Classify all users by user level based on the historical service transaction information to obtain the level classification results of all users; Inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively; Based on the outbound call evaluation value and the preset outbound call allocation strategy, the target type of users are screened out from the outbound call user list and allocated to the preset cluster type outbound call intelligent assistant to make the outbound call and obtain the outbound call feedback result; According to the outbound call feedback result, target intended users are screened out, and the target intended users are transferred to manual seats for business services.

2. The agent outbound calling method according to claim 1, characterized in that: The outbound call answering behavior information includes answering waiting time information and actual call time information. The step of analyzing the outbound call answering behaviors of all users through the outbound call answering behavior information and obtaining outbound call answering behavior characterization values ​​corresponding to all users in a preset characterization form specifically includes: Obtain the answering waiting time information and actual call duration information corresponding to each outbound call answering of all the user's history; According to the answering waiting time information and the actual call duration information corresponding to each outbound call answering in the history of all users, the average answering waiting time information and the average actual call duration information are obtained; The characterization value is calculated by the preset formula: C i =a i ×α1+b i ×α2, Calculate the outbound call answering behavior characterization values ​​corresponding to all the users, where C i represents the characterization value, a i Indicates the average waiting time for answering calls, b i represents the average actual call duration information, α1 represents the preset first weight coefficient, α2 represents the preset second weight coefficient, and α1+α2=1, and i represents the user number information.

3. The agent outbound calling method according to claim 1, characterized in that: The step of classifying all users by user level based on the historical service transaction information specifically includes: Inputting the historical service transaction information into a preset customer classification model, wherein the historical service transaction information includes user binary classification features of N dimensions, wherein N is a positive integer; All the users are divided into user levels based on the user binary classification features of the N dimensions.

4. The agent outbound calling method according to claim 3, characterized in that: Before executing the step of classifying all the users by user levels based on the user binary classification features in the N dimensions, the method further includes: Using the preset algorithm formula: M＝2 N ， Set M user levels, where M represents the number of user level categories, N represents the number of dimensions, and 2 N Represents the power of 2, where N is a positive integer.

5. The agent outbound calling method according to claim 3, characterized in that: The user binary classification features of the N dimensions include transaction product information, transaction amount information and transaction promotion rate information. Before executing the step of classifying all users according to the user binary classification features of the N dimensions, the method further includes: Obtaining a pre-sorted list of hot products, wherein the list of hot products includes information on the names of the hot products; Obtaining a preset binary index value of the transaction amount, wherein the binary index value of the transaction amount is a preset unique transaction amount value. If the current transaction amount is higher than the unique transaction amount value, it indicates that the current transaction amount meets the standard, otherwise the current transaction amount does not meet the standard; Obtaining a preset binary index value of the transaction facilitation rate, wherein the binary index value of the transaction facilitation rate is a preset unique probability value, and if the current transaction facilitation rate is higher than the unique probability value, it indicates that the current transaction facilitation rate meets the standard, otherwise the current transaction facilitation rate does not meet the standard; The step of classifying all the users into user levels based on the user binary classification features of the N dimensions includes: Calculate the proportion of hot products in the transaction product information corresponding to the current user; Summarize the total transaction amount information corresponding to the current user, and identify whether the transaction amount information corresponding to the current user meets the requirements based on the total transaction amount information and the preset unique transaction amount value; According to the transaction facilitation rate information corresponding to the current user and the preset unique probability value, identifying whether the transaction facilitation rate corresponding to the current user meets the standard; The user level of the current user is determined based on the ratio value, whether the transaction amount information meets the standard, and whether the transaction facilitation rate meets the standard.

6. The agent outbound calling method according to claim 1, characterized in that: Before executing the step of inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively, the method further includes: Pre-set numerical level values ​​that decrease in sequence according to the user level from high to low; Obtaining an evaluation method pre-constructed according to the outbound call answering behavior characterization value and the user level, wherein the evaluation method follows that the larger the outbound call answering behavior characterization value and the higher the user level, the higher the outbound call evaluation value, and the evaluation method includes summing the outbound call answering behavior characterization value and the numerical level value corresponding to the same user; Deploying the evaluation method as reference knowledge into the outbound call evaluation model; The step of inputting the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively comprises: Select different users in turn as the current target user; Identifying the user level of the current target user from the level classification results of all users; According to the user level, obtaining a numerical level value corresponding to the current target user; Filtering the outbound call answering behavior representation value of the current target user from the outbound call answering behavior representation values ​​corresponding to all the users; The numerical grade value corresponding to the current target user and the outbound call answering behavior representation value of the current target user are summed to obtain the outbound call evaluation value corresponding to the current target user.

7. The agent outbound calling method according to claim 1, characterized in that: The step of screening out users of a target type from the outbound call user list and assigning them to a preset cluster-type outbound call intelligent assistant based on the outbound call evaluation value and the preset outbound call allocation strategy, making the outbound call, and obtaining the outbound call feedback result specifically includes: According to the outbound call evaluation values ​​corresponding to all users in the outbound call user list, all the users are sorted in descending order to obtain a descending sequence; Filtering out the top I users from the descending sequence as users of the target type, where I is a positive integer; Identify the current outbound call task volume of all outbound call intelligent assistants in the clustered outbound call intelligent assistant and the outbound call service types handled by all outbound call intelligent assistants respectively through the previous work allocation log; According to the current outbound call task volume of all the outbound call intelligent assistants in the cluster-type outbound call intelligent assistant and the outbound call service types handled by all the outbound call intelligent assistants respectively, the users of the target type are assigned to the corresponding outbound call intelligent assistants.

8. The agent outbound calling method according to claim 7, characterized in that: The step of allocating the target type of users to corresponding outbound call intelligent assistants according to the current outbound call task volumes of all outbound call intelligent assistants in the clustered outbound call intelligent assistants and the outbound call service types respectively processed by all outbound call intelligent assistants specifically includes: Identify the outbound call service types corresponding to all target types of users; According to the outbound call service type, all outbound call intelligent assistants that process the outbound call service type are screened out from the cluster-type outbound call intelligent assistants; From all the outbound call intelligent assistants that process the outbound call service type, select the outbound call intelligent assistant with the least current outbound call task volume as the outbound call intelligent assistant to be assigned; According to the preset outbound call real-time monitoring component, all outbound call intelligent assistants that process the outbound call business type are monitored in real time to obtain the outbound call task progress of all outbound call intelligent assistants that process the outbound call business type; Based on the progress of the outbound call task, outbound call tasks are allocated among all the outbound call intelligent assistants.

9. A seat outbound calling device, characterized in that: include: An outbound user list acquisition module is used to acquire an outbound user list; A user-related information screening module is used to screen out the outbound call answering behavior information and historical service transaction information of all users in the outbound call user list from the big data according to the outbound call user list; An outbound call answering behavior characterization module, used to analyze the outbound call answering behavior of all the users through the outbound call answering behavior information, and obtain the outbound call answering behavior characterization values ​​corresponding to all the users in a preset characterization form; A user grade classification module, used to classify all users by user grade based on the historical service transaction information, and obtain the grade classification results of all users; An outbound call evaluation value obtaining module, used to input the outbound call answering behavior characterization values ​​corresponding to all the users and the grade classification results of all the users into a preset outbound call evaluation model to obtain the outbound call evaluation values ​​corresponding to all the users respectively; An outbound call assistant allocation module is used to screen out target type users from the outbound call user list and assign them to a preset cluster type outbound call intelligent assistant based on the outbound call evaluation value and the preset outbound call allocation strategy, make the outbound call, and obtain the outbound call feedback result; The target intended user transfer module is used to screen out the target intended users according to the outbound call feedback result, and transfer the target intended users to the manual seat for business service.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the agent outbound calling method according to any one of claims 1 to 8 when executing the computer-readable instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the agent outbound calling method according to any one of claims 1 to 8 are implemented.

Images