Intelligent voice outbound method and system, computer equipment and readable storage medium

Abstract

The invention provides an intelligent voice outbound method and system, computer equipment and a readable storage medium. The intelligent voice outbound method comprises the steps that outbound configuration information is acquired according to an outbound task, outbound content is determined, the outbound configuration information comprises dynamic variable information and an outbound template, and the dynamic variable information comprises client identity information and express delivery information; converting the outbound content into outbound voice based on a voice synthesis model, and sending the outbound voice to a client according to a configured outbound line resource; if the client answers the outbound voice, feedback information of the client is obtained based on the DTMF key recognition model and / or the voice recognition model, and an outbound task is ended.

Description

Technical Field

[0001] The present application relates to the technical field of electrical equipment, and in particular to an intelligent voice outbound calling method and system, a computer device and a readable storage medium. Background Art

[0002] In the express delivery industry, outbound call systems are widely used to communicate with customers, such as notifying customers to pick up parcels, confirming delivery addresses, etc. Traditional outbound call systems usually rely on manual operations, which are inefficient and prone to errors. In recent years, with the development of speech recognition technology (ASR), text-to-speech technology (TTS), and robot outbound call technology, automated outbound call systems have gradually become an industry trend. However, existing automated outbound call systems still have many problems in outbound call template configuration and customer intent recognition.

[0003] For example: Complex outbound call template configuration: Outbound call templates are usually static and cannot dynamically fill in variables according to different scenarios, resulting in single and inflexible outbound call content. Inaccurate customer intent recognition: Existing outbound call systems usually rely on simple key input (DTMF) when identifying customer intent, which cannot accurately capture the customer's true intent. Summary of the invention

[0004] Based on this, it is necessary to provide an intelligent voice outbound calling method and system, computer equipment and readable storage medium to address the above technical problems.

[0005] An intelligent voice outbound calling method, comprising:

[0006] Acquire outbound call configuration information according to the outbound call task, and determine the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information;

[0007] Convert the outbound call content into outbound call voice based on the speech synthesis model, and send the outbound call voice to the customer according to the configured outbound call line resources;

[0008] If the customer answers the outbound voice, customer feedback information is obtained based on the DTMF key recognition model and / or the voice recognition model, and the outbound call task is terminated.

[0009] In one embodiment, the step of obtaining outbound call configuration information according to the outbound call task and determining the outbound call content includes:

[0010] Acquire the outbound call template and the dynamic variable information according to the outbound call task;

[0011] The dynamic variable information is filled into the outbound call template, and the outbound call content is determined.

[0012] In one embodiment, the step of converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources includes:

[0013] Converting the outbound call content into an outbound call voice based on a speech synthesis model;

[0014] Acquire a preset outbound call line resource, and send the outbound call voice to the customer through the outbound call line resource; or,

[0015] Obtain outbound call line resource list information, determine current outbound call line resources according to the outbound call line resource list information, and send the outbound call voice to the customer through the current outbound call line resources.

[0016] In one embodiment, if the customer answers the outbound voice, the steps of obtaining the customer's feedback information based on the DTMF key recognition model and / or the voice recognition model and ending the outbound call task include:

[0017] If the customer answers the outbound voice, feedback information from the customer is obtained based on the DTMF key recognition model and / or the voice recognition model;

[0018] The feedback information is sent to the queue of messages to be pushed, and the outbound call task is terminated.

[0019] In one embodiment, the intelligent voice outbound calling method further includes:

[0020] If the customer does not answer the outbound voice, the reason for not answering the call is determined based on the voice recognition model, and the reason for not answering the call is sent to the queue of messages to be pushed; or,

[0021] If the customer does not answer the outbound voice, the outbound voice is resent to the customer within a preset period.

[0022] In one of the embodiments, the method further includes: obtaining the customer's historical express delivery data according to the outbound call task, and determining the outbound call content based on a natural language processing model and the customer's historical express delivery data.

[0023] In one embodiment, the intelligent voice outbound calling method further includes:

[0024] According to the execution status of the outbound call task, outbound call data information is counted and a visual data report is output to facilitate data analysis and decision-making by operators, wherein the outbound call data information includes outbound call success rate information and customer answering rate information.

[0025] An intelligent voice outbound calling system, comprising:

[0026] A processing module, used for obtaining outbound call configuration information according to the outbound call task and determining the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information;

[0027] A conversion module connected to the processing module, the conversion module is used to convert the outbound call content into an outbound call voice based on a speech synthesis model, and send the outbound call voice to the customer according to the configured outbound call line resources;

[0028] The recognition module is connected to the conversion module. If the customer answers the outbound voice, the recognition module is used to obtain the customer's feedback information based on the DTMF key recognition model and / or the voice recognition model, and end the outbound call task.

[0029] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the above embodiments when executing the computer program.

[0030] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described in any one of the above embodiments.

[0031] Compared with the prior art, the above-mentioned intelligent voice outbound call method and system, computer equipment and readable storage medium. The intelligent voice outbound call method includes: obtaining outbound call configuration information according to the outbound call task, and determining the outbound call content, wherein the outbound call configuration information includes dynamic variable information and outbound call templates, and the dynamic variable information includes customer identity information and express information; converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources; if the customer answers the outbound call voice, the customer's feedback information is obtained based on the DTMF button recognition model and / or the speech recognition model, and the outbound call task is terminated. The present application adopts the above-mentioned method to determine the outbound call content by combining dynamic variable information and outbound call templates, which solves the problem of complex outbound call template configuration in traditional outbound call systems and improves the flexibility and personalization of outbound call content. At the same time, the customer's feedback information is obtained through the DTMF button recognition model and / or the speech recognition model, which solves the problem of inaccurate customer intention recognition in traditional outbound call systems and improves the accuracy of customer intention recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A flowchart of an intelligent voice outbound calling method provided in one embodiment of the present application;

[0034] Figure 2 A structural block diagram of an intelligent voice outbound calling system provided in one embodiment of the present application;

[0035] Figure 3 This is a diagram of the internal structure of a computer device provided in one embodiment of the present application.

[0036] Description of reference numerals:

[0037] 10. Intelligent voice outbound call system; 100. Processing module; 200. Conversion module; 300. Recognition module. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0039] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings). In the description of this application, it should be understood that the orientation or position relationship indicated by the terms "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", etc. are based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to this application.

[0040] In the present application, unless otherwise clearly specified and limited, a first feature being “above” or “below” a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being “above”, “above”, and “above” a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being “below”, “below”, and “below” a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0041] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0043] See also Figure 1 , an embodiment of the present application provides an intelligent voice outbound calling method. The intelligent voice outbound calling method comprises:

[0044] S102: Obtain outbound call configuration information according to the outbound call task, and determine the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information.

[0045] In some embodiments, the processor or controller can obtain the outbound call configuration information according to the outbound call task, and determine the outbound call content. Specifically, the outbound call configuration information may include dynamic variable information and outbound call templates. Among them, the dynamic variable information may include customer identity information (such as name, etc.), express information (such as express number, pickup address), etc. The outbound call template can be set in advance, and can be set specifically according to business needs. After selecting the outbound call template, the dynamic variable information can be automatically filled into the outbound call template, and the final outbound call content can be generated. This ensures the personalization and accuracy of the outbound call content. In some embodiments, the business party can initiate an outbound call task request based on the APP ID, and specify the external display number and outbound call template. It can be set specifically according to actual needs. The outbound call template supports multi-language and multi-scenario configuration, and can be flexibly adjusted according to business needs.

[0046] S104: converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources.

[0047] In some embodiments, the outbound call content can be converted into an outbound call voice based on a speech synthesis model by a processor or a controller, and the outbound call voice can be sent to the customer according to the configured outbound call line resources. Specifically, the TTS technical model (speech synthesis model) can be used to synthesize the outbound call content into voice, and ensure the natural and smooth voice notification. In some embodiments, the speech synthesis model supports a variety of voice styles and speech speed adjustments, which can be personalized according to customer preferences.

[0048] In some embodiments, the system may be initialized before starting an outbound call task. Specifically, the outbound call task may be initialized and outbound call line resources may be allocated based on the request parameters. Outbound call line resources may be pre-configured, such as configuring outbound call line resources such as "YTO Express" and "Mom's Station", and supporting the business party to specify an external number when executing an automatic outbound call task of a voice robot based on the ID of the APP. Among them, the external number is marked and authenticated by a third-party platform to ensure the legitimacy and security of the number. In some embodiments, in addition to pre-configuration of outbound call line resources, dynamic application for outbound call line resources may also be adopted, which can be adjusted in real time according to business needs. By pre-configuring outbound call line resources, the problem of inflexible number management in traditional outbound call systems is solved, and the customer experience is improved.

[0049] S106: If the customer answers the outbound voice, feedback information from the customer is obtained based on the DTMF key recognition model and / or the voice recognition model, and the outbound call task is terminated.

[0050] In some embodiments, after the outbound voice is sent to the customer, if the customer answers the outbound voice, the customer's intention can be identified based on the DTMF key recognition model and / or the voice recognition model to obtain the customer's real feedback. Among them, the DTMF key recognition model supports multi-level menu selection, and can perform logical judgment based on the customer's key input to achieve complex intention recognition. The voice recognition model can perform logical judgment based on the customer's voice input to obtain the customer's intention. During the outbound call process, the system can monitor the outbound call status in real time and record the outbound call results. After obtaining the customer's feedback information, the outbound call task can be ended.

[0051] This embodiment adopts the above method to determine the outbound call content through the cooperation of dynamic variable information and outbound call template, which solves the problem of complex outbound call template configuration in the traditional outbound call system and improves the flexibility and personalization of the outbound call content. At the same time, the customer's feedback information is obtained through the DTMF key recognition model and / or the voice recognition model, which solves the problem of inaccurate customer intention recognition in the traditional outbound call system and improves the accuracy of customer intention recognition.

[0052] In some embodiments, the step of obtaining the outbound call configuration information according to the outbound call task and determining the outbound call content includes: obtaining the outbound call template and the dynamic variable information according to the outbound call task; filling the dynamic variable information into the outbound call template, and determining the outbound call content. The outbound call template can automatically fill in the dynamic variable information according to different scenarios, such as customer name, express number, pickup address, etc.

[0053] In some embodiments, the step of converting the outbound call content into an outbound voice based on a speech synthesis model, and sending the outbound voice to the customer according to the configured outbound line resources includes: converting the outbound call content into an outbound voice based on a speech synthesis model; obtaining preset configured outbound line resources, and sending the outbound voice to the customer through the outbound line resources; or, obtaining outbound line resource list information, determining the current outbound line resources according to the outbound line resource list information, and sending the outbound voice to the customer through the current outbound line resources.

[0054] In some embodiments, the outbound call line resource list information can be a real-time display list information, and the business party can dynamically apply for the current outbound call line resources from the list information according to actual needs. Then the outbound voice is sent to the customer through the current outbound call line resources. This makes it convenient for the business party to make real-time adjustments according to actual business needs. The use of message queue processing can improve the throughput and reliability of message processing.

[0055] In some embodiments, if the customer answers the outbound voice, the step of obtaining the customer's feedback information based on the DTMF key recognition model and / or the voice recognition model, and ending the outbound call task includes: if the customer answers the outbound voice, the customer's feedback information is obtained based on the DTMF key recognition model and / or the voice recognition model; the feedback information is sent to the queue of messages to be pushed, and the outbound call task is ended. In some embodiments, the queue of messages to be pushed may include multiple outbound call results to be pushed. The system can push the outbound call results to the business party in a loop according to the queue of messages to be pushed, so as to remind the business party in time, thereby avoiding the corresponding outbound call tasks not being processed or forgotten to be processed.

[0056] In some embodiments, after the outbound call task is completed, the outbound call result can be transmitted back to the business system through asynchronous MQ to reduce system coupling and improve system response speed. Among them, asynchronous transmission supports multiple message formats, which can be customized according to business needs and are not specifically limited here.

[0057] In some embodiments, the intelligent voice outbound calling method also includes: if the customer does not answer the outbound voice, determining the reason for not answering based on the voice recognition model, and sending the reason for not answering to the message queue to be pushed; or, if the customer does not answer the outbound voice, resending the outbound voice to the customer within a preset period.

[0058] In some embodiments, if the customer does not answer the outbound voice call, the recorded text is transcribed based on a speech recognition model (such as an ASR service model or a deep learning speech-to-text model), and the recorded text is identified by keywords to determine the reason for not answering the call, and the reason for not answering the call is sent to the queue of messages to be pushed. In some embodiments, if the customer does not answer the outbound voice call, the customer who did not answer or failed to answer the call can also be automatically re-called according to the retry strategy (such as retrying within a preset period, with no restrictions on the specific period, such as retrying every 20 minutes / 30 minutes) to improve the call reach rate. Among them, the retry mechanism supports multiple policy configurations, such as retrying by time period, retrying by customer type, etc.

[0059] In some embodiments, in the number verification scenario, the system can perform ASR speech-to-text recognition on the recorded text of the outbound call, extract keywords to obtain the number status of the salesperson. Through ASR technology, the salesperson number status is updated in a timely manner to reduce the reduction in customer satisfaction caused by salesperson downtime and number changes. In some embodiments, the system can also support speech-to-text technology based on deep learning, which can improve the accuracy of speech recognition. The specific learning model can be selected according to actual needs.

[0060] In some embodiments, the method further includes: obtaining the customer's historical express delivery data according to the outbound call task, and determining the outbound call content based on the natural language processing model and the customer's historical express delivery data. Specifically, the natural language processing model can automatically generate the outbound call content according to the customer's historical express delivery data. This can improve the outbound call efficiency.

[0061] In some embodiments, the intelligent voice outbound call method further includes: according to the execution of the outbound call task, outbound call data information is counted, and a visual data report is output to facilitate data analysis and decision-making by operators, wherein the outbound call data information includes outbound call success rate information and customer answering rate information. In some embodiments, the outbound call data information may include outbound call success rate, customer answering rate, customer intention recognition rate, etc. In some embodiments, outbound call data analysis based on machine learning can also automatically discover abnormal situations in the outbound call process. This can further help operators to perform data analysis and decision-making.

[0062] See also Figure 2, an embodiment of the present application provides an intelligent voice outbound call system 10. The intelligent voice outbound call system 10 includes: a processing module 100, a conversion module 200 and an identification module 300. The processing module 100 is used to obtain outbound call configuration information according to the outbound call task and determine the outbound call content. Among them, the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and express information. The conversion module 200 is connected to the processing module 100. The conversion module 200 is used to convert the outbound call content into an outbound call voice based on a speech synthesis model, and send the outbound call voice to the customer according to the configured outbound call line resources. The identification module 300 is connected to the conversion module 200. The identification module 300 is used to obtain the customer's feedback information based on the DTMF key recognition model and / or the speech recognition model if the customer answers the outbound call voice, and end the outbound call task.

[0063] In some embodiments, the specific structure of the processing module 100 is not limited, as long as it has the function of obtaining outbound call configuration information according to the outbound call task and determining the outbound call content. Specifically, the processing module 100 can be a microprocessor or an integrated controller. The specific structure of the processing module 100 can be selected according to actual needs and is not specifically limited here.

[0064] In some embodiments, the specific structure of the conversion module 200 is not limited, as long as it has the function of converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources. Specifically, the conversion module 200 can be a voice converter or a processor. The specific structure of the conversion module 200 can be selected according to actual needs and is not specifically limited here.

[0065] In some embodiments, the specific structure of the recognition module 300 is not limited, as long as it has the function of obtaining the customer's feedback information based on the DTMF key recognition model and / or the voice recognition model and ending the outbound call task if the customer answers the outbound call voice. Specifically, the recognition module 300 can be a microprocessor or an integrated controller. The specific structure of the recognition module 300 can be selected according to actual needs and is not specifically limited here.

[0066] This embodiment adopts the above method to determine the outbound call content through the combination of dynamic variable information and outbound call template, which solves the problem of complex outbound call template configuration in the traditional outbound call system and improves the flexibility and personalization of the outbound call content. At the same time, the customer's feedback information is obtained through the DTMF key recognition model and / or the voice recognition model, which solves the problem of inaccurate customer intention recognition in the traditional outbound call system and improves the accuracy of customer intention recognition.

[0067] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent voice outbound calling method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0068] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0069] See also Figure 3 Another embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the intelligent voice outbound calling method described in any one of the above embodiments are implemented.

[0070] In one embodiment, the processor implements the following steps when executing the computer program:

[0071] S102: acquiring outbound call configuration information according to the outbound call task, and determining the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information;

[0072] S104: converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources;

[0073] S106: If the customer answers the outbound voice, feedback information from the customer is obtained based on the DTMF key recognition model and / or the voice recognition model, and the outbound call task is terminated.

[0074] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the intelligent voice outbound calling method described in any one of the above embodiments are implemented.

[0075] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0076] S102: acquiring outbound call configuration information according to the outbound call task, and determining the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information;

[0077] S104: converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources;

[0078] S106: If the customer answers the outbound voice, feedback information from the customer is obtained based on the DTMF key recognition model and / or the voice recognition model, and the outbound call task is terminated.

[0079] The above-mentioned computer device and computer-readable storage medium determine the outbound call content by cooperating with the dynamic variable information and the outbound call template, thereby solving the problem of complex configuration of the outbound call template in the traditional outbound call system and improving the flexibility and personalization of the outbound call content. At the same time, the customer's feedback information is obtained by the DTMF key recognition model and / or the voice recognition model, thereby solving the problem of inaccurate customer intention recognition in the traditional outbound call system and improving the accuracy of customer intention recognition.

[0080] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0081] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0082] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An intelligent voice outbound calling method, characterized in that: include: Acquire outbound call configuration information according to the outbound call task, and determine the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information; Convert the outbound call content into outbound call voice based on the speech synthesis model, and send the outbound call voice to the customer according to the configured outbound call line resources; If the customer answers the outbound voice, the customer's feedback information is obtained based on the DTMF key recognition model and / or the voice recognition model, and the outbound call task is terminated.

2. The intelligent voice outbound calling method according to claim 1, characterized in that: The step of obtaining outbound call configuration information according to the outbound call task and determining the outbound call content includes: Acquire the outbound call template and the dynamic variable information according to the outbound call task; The dynamic variable information is filled into the outbound call template, and the outbound call content is determined.

3. The intelligent voice outbound calling method according to claim 1, characterized in that: The step of converting the outbound call content into an outbound call voice based on a speech synthesis model, and sending the outbound call voice to the customer according to the configured outbound call line resources comprises: Converting the outbound call content into outbound call voice based on a speech synthesis model; Acquire a preset outbound call line resource, and send the outbound call voice to the customer through the outbound call line resource; or, Obtain outbound call line resource list information, determine current outbound call line resources according to the outbound call line resource list information, and send the outbound call voice to the customer through the current outbound call line resources.

4. The intelligent voice outbound calling method according to claim 1, characterized in that: If the customer answers the outbound voice, the steps of obtaining the customer's feedback information based on the DTMF key recognition model and / or the voice recognition model and ending the outbound call task include: If the customer answers the outbound voice, obtaining customer feedback information based on the DTMF key recognition model and / or the voice recognition model; The feedback information is sent to the queue of messages to be pushed, and the outbound call task is terminated.

5. The intelligent voice outbound calling method according to claim 4, characterized in that: The method further comprises: If the customer does not answer the outbound voice, the reason for not answering the call is determined based on the voice recognition model, and the reason for not answering the call is sent to the queue of messages to be pushed; or, If the customer does not answer the outbound voice, the outbound voice is resent to the customer within a preset period.

6. The intelligent voice outbound calling method according to claim 1, characterized in that: The method further includes: acquiring historical express delivery data of the customer according to the outbound call task, and determining outbound call content based on a natural language processing model and the historical express delivery data of the customer.

7. The intelligent voice outbound calling method according to claim 1, characterized in that: The method further comprises: According to the execution status of the outbound call task, outbound call data information is counted and a visual data report is output to facilitate data analysis and decision-making by operators, wherein the outbound call data information includes outbound call success rate information and customer answering rate information.

8. An intelligent voice outbound calling system, characterized in that: include: A processing module, used for obtaining outbound call configuration information according to the outbound call task and determining the outbound call content, wherein the outbound call configuration information includes dynamic variable information and an outbound call template, and the dynamic variable information includes customer identity information and courier information; A conversion module connected to the processing module, the conversion module is used to convert the outbound call content into an outbound call voice based on a speech synthesis model, and send the outbound call voice to the customer according to the configured outbound call line resources; The recognition module is connected to the conversion module. If the customer answers the outbound voice, the recognition module is used to obtain the customer's feedback information based on the DTMF key recognition model and / or the voice recognition model, and end the outbound call task.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images