Voice message processing method and device, storage medium, and electronic device

Abstract

The present invention provides a method and device for processing voice messages, a storage medium, and an electronic device. The method includes: obtaining a voice message on a soft switch platform; determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message; matching a voice processing channel of complexity from a preset channel list, and sending the voice message to a corresponding target business platform for processing through the voice processing channel. That is, the intelligent distribution platform classifies and processes the voice messages through interaction and cooperation with the target device terminal, the basic service platform, and the business platform, and determines a suitable voice processing channel for the voice message according to the complexity corresponding to the voice message, and divides and manages the voice messages. Therefore, the problems in the prior art that voice messages cannot be effectively distinguished and processed, and the processing method is single and cannot be adjusted can be solved.

Description

Technical Field

[0001] The present invention relates to the field of communications, and in particular to a method and device for processing voice messages, a storage medium, and an electronic device. Background Art

[0002] Traditional customer service solutions are overall packaged solutions. When processing voice messages, they are all processed in the same way. They cannot determine the type of user terminal that initiates the customer service request, actively push information to the user, and cannot select the appropriate customer service terminal to respond to the customer service request based on the user's own information and the type of customer service terminal used by the user, so as to achieve accurate customer service request processing. For example, mature solutions on the market generally identify the source of users and distribute user routes to designated seats, such as robots provided by suppliers or a skill group of the seat system. They cannot flexibly process customer service requests in accordance with the corresponding actual situation, and may result in complex processing of simple customer service requests.

[0003] In view of the problems in the related technologies such as the inability to effectively distinguish and process voice messages, the single processing method and the inability to adjust the same, no effective technical solution has been proposed. Summary of the invention

[0004] The embodiments of the present invention provide a method and device for processing voice messages, a storage medium, and an electronic device, so as to at least solve the problems in the related art that voice messages cannot be effectively distinguished and processed, and the processing method is single and cannot be adjusted.

[0005] According to one embodiment of the present invention, a method for processing voice messages is provided, comprising: obtaining a voice message on a soft switch platform; determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message; matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel.

[0006] In an exemplary embodiment, a voice processing channel of varying complexity is matched from a preset channel list, and a voice message is sent to a corresponding target business platform for processing through the voice processing channel, including: when it is determined that the complexity is less than or equal to a first preset threshold, determining that the voice processing channel corresponding to the voice message is an interactive voice response; when it is determined that the complexity is greater than the first preset threshold and less than or equal to a second preset threshold, determining that the voice processing channel corresponding to the voice message is a manual agent response.

[0007] In an exemplary embodiment, after matching a voice processing channel of varying complexity from a preset channel list and sending the voice message to the corresponding target business platform for processing through the voice processing channel, the method further includes: obtaining the processing result of the target business platform for the voice message; determining whether the voice message is successfully processed based on the processing result, and generating a processing record of the voice message, wherein the processing record includes: platform information of the target business platform that processes the voice message, and a processing cycle of the voice message.

[0008] In an exemplary embodiment, whether the voice message is successfully processed is determined based on the processing result, and a processing record of the voice message is generated, including: when the processing result indicates that the voice message needs to be forwarded to other service platforms for processing, it is determined that the voice message is not successfully processed, and the voice message is added to a queue of messages to be forwarded, wherein the queue of messages to be forwarded is used to store voice messages that have not been successfully processed and forward them to other service platforms other than the target service platform for reprocessing; when the processing result indicates that the voice message sender is called, it is determined that the voice message is successfully processed, and all processing processes corresponding to the voice message are terminated.

[0009] In an exemplary embodiment, after adding the voice message to the queue of messages to be forwarded, the method further includes: when it is determined that the number of messages in the queue of messages to be forwarded is greater than a preset threshold, making a forwarding call request; and starting the forwarding operation of the messages in the queue of messages to be forwarded based on the forwarding call request.

[0010] In an exemplary embodiment, after obtaining the voice message on the soft switch platform, the above method also includes: querying the identification code carried by each voice message, wherein the identification code is used to identify the basic information of the target object that initiates the voice message; querying the identification code through the information database connected to the application interface; when it is determined that the identification code exists in the information database, determining that the target object corresponding to the voice message is a registered object, and adding a target identifier to the voice message, wherein the target identifier is used to indicate that the voice message is an after-sales service message.

[0011] In an exemplary embodiment, obtaining a voice message on a soft switch platform includes: determining the device type of a target device that sends a voice message; and establishing a voice message sending channel with the target device if the device type has call authority to obtain the voice message sent by the target device.

[0012] According to another embodiment of the present invention, a voice message processing device is provided, including: an acquisition module for acquiring voice messages on a soft switch platform; a determination module for determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message; and a processing module for matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel.

[0013] In an exemplary embodiment, the above-mentioned processing module is also used to determine that the voice processing channel corresponding to the voice message is an interactive voice response when it is determined that the complexity is less than or equal to a first preset threshold; and to determine that the voice processing channel corresponding to the voice message is a manual agent response when it is determined that the complexity is greater than the first preset threshold and less than or equal to a second preset threshold.

[0014] In an exemplary embodiment, the above-mentioned device also includes: a recording module, which is used to obtain the processing results of the target business platform for the voice message; determine whether the voice message is successfully processed based on the processing results, and generate a processing record of the voice message, wherein the processing record includes: platform information of the target business platform that processes the voice message, and the processing cycle of the voice message.

[0015] In an exemplary embodiment, the above-mentioned recording module is also used to determine that the voice message has not been successfully processed and add the voice message to a queue of messages to be forwarded when the processing result indicates that the voice message needs to be forwarded to other business platforms for processing, wherein the queue of messages to be forwarded is used to store voice messages that have not been successfully processed and forward them to other business platforms other than the target business platform for reprocessing; when the processing result indicates that the voice message sender is called, it is determined that the voice message has been successfully processed and all processing processes corresponding to the voice message are terminated.

[0016] In an exemplary embodiment, the recording module further includes: a forwarding unit, configured to make a forwarding call request when it is determined that the number of messages in the message queue to be forwarded is greater than a preset threshold; and to start the forwarding operation of the messages in the message queue to be forwarded based on the forwarding call request.

[0017] In an exemplary embodiment, the above-mentioned device also includes: a query module, used to query the identification code carried by each voice message, wherein the identification code is used to identify the basic information of the target object that initiates the voice message; query the identification code through the information database connected to the application interface; when it is determined that the identification code exists in the information database, determine that the target object corresponding to the voice message is a registered object, and add a target identifier to the voice message, wherein the target identifier is used to indicate that the voice message is an after-sales service message.

[0018] In an exemplary embodiment, the acquisition module is further used to determine the device type of the target device that sends the voice message; if the device type has call authority, establish a voice message sending channel with the target device to obtain the voice message sent by the target device.

[0019] According to yet another embodiment of the present invention, a storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

[0020] According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0021] Through the present invention, voice messages on the soft switch platform are obtained; the complexity corresponding to the voice message is determined, wherein the complexity is used to indicate the difficulty of processing the voice message; a voice processing channel of the complexity is matched from a preset channel list, and the voice message is sent to the corresponding target business platform for processing through the voice processing channel. That is to say, the intelligent distribution platform classifies and processes the voice messages through interaction and cooperation with the target device terminal, the basic service platform, and the business platform, and determines a suitable voice processing channel for the voice message according to the complexity corresponding to the voice message, and divides and manages the voice messages. Therefore, the problems in the prior art that voice messages cannot be effectively distinguished and processed, and the processing method is single and cannot be adjusted, etc., can be solved, so that the processing methods for voice messages become diverse, the processing efficiency of voice messages is improved, and the slowness of a single method is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 It is a hardware structure block diagram of an intelligent distribution platform of a voice message processing method according to an embodiment of the present invention;

[0024] Figure 2 is a flow chart of a method for processing a voice message according to an embodiment of the present invention;

[0025] Figure 3 is a structural diagram of an intelligent business distribution platform system according to an optional embodiment of the present invention;

[0026] Figure 4is a network topology diagram of an intelligent service distribution platform system according to an optional embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of a network architecture of an intelligent business distribution platform system according to an optional embodiment of the present invention;

[0028] Figure 6 is a schematic diagram of a flow chart of a voice message being processed by an intelligent service distribution platform system according to an optional embodiment of the present invention;

[0029] Figure 7 It is a structural block diagram of voice message processing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0032] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or a similar computing device in the cloud. Taking running on an intelligent distribution platform as an example, Figure 1 FIG. 1 is a hardware structure block diagram of an intelligent distribution platform of a method for processing voice messages according to an embodiment of the present invention. Figure 1 As shown, the intelligent distribution platform may include one or more ( Figure 1 Only one is shown in the figure) processor 102 (processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. In an exemplary embodiment, the above-mentioned intelligent distribution platform may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above-mentioned intelligent distribution platform. Figure 1 More or fewer components as shown, or with Figure 1 Equivalent functions or comparisons shown Figure 1 A different configuration with more features is shown.

[0033] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for processing voice messages in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the intelligent distribution platform via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the intelligent distribution platform. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0035] In this embodiment, a method for processing a voice message is provided. Figure 2 1 is a flow chart of a method for processing a voice message according to an embodiment of the present invention, the flow chart comprising the following steps:

[0036] Step S202, obtaining a voice message on the soft switch platform;

[0037] Step S204, determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message;

[0038] Step S208, matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel.

[0039] It should be noted that the above-mentioned preset channel list may simultaneously contain one or more sets of correspondence between complexity and voice processing channels, and the correspondence can be flexibly set according to actual usage requirements, so that the scalability and flexibility of voice message processing are greatly enhanced.

[0040] Through the above steps, the voice message on the soft switch platform is obtained; the complexity corresponding to the voice message is determined, wherein the complexity is used to indicate the difficulty of processing the voice message; the voice processing channel of the complexity is matched from the preset channel list, and the voice message is sent to the corresponding target business platform for processing through the voice processing channel. That is to say, the intelligent distribution platform classifies and processes the voice messages through the interaction and cooperation with the target device terminal, the basic service platform, and the business platform, and determines the appropriate voice processing channel for the voice message according to the complexity corresponding to the voice message, and divides and manages the voice messages. Therefore, it can solve the problems in the prior art that voice messages cannot be effectively distinguished and processed, and the processing method is single and cannot be adjusted, so that the processing methods for voice messages become diverse, the processing efficiency of voice messages is improved, and the slowness of a single method is avoided.

[0041] In an exemplary embodiment, a voice processing channel of varying complexity is matched from a preset channel list, and a voice message is sent to a corresponding target business platform for processing through the voice processing channel, including: when it is determined that the complexity is less than or equal to a first preset threshold, determining that the voice processing channel corresponding to the voice message is an interactive voice response; when it is determined that the complexity is greater than the first preset threshold and less than or equal to a second preset threshold, determining that the voice processing channel corresponding to the voice message is a manual agent response.

[0042] Simply put, by setting a threshold range, voice messages within a certain complexity range are processed through the same voice processing channel, avoiding the tediousness of confirming channels when the complexity is too high. As long as it is within the threshold range, the corresponding voice processing channel will be used, so that no matter what the circumstances, the corresponding processing channel for the voice message can be quickly determined.

[0043] In an exemplary embodiment, after matching a voice processing channel of varying complexity from a preset channel list and sending the voice message to the corresponding target business platform for processing through the voice processing channel, the method further includes: obtaining the processing result of the target business platform for the voice message; determining whether the voice message is successfully processed based on the processing result, and generating a processing record of the voice message, wherein the processing record includes: platform information of the target business platform that processes the voice message, and a processing cycle of the voice message.

[0044] That is to say, after the voice message is sent to the corresponding target business platform for processing through the voice processing channel, in order to facilitate the subsequent search for the processing results of the voice message and ensure the processing effect of the voice message, the processing results can be analyzed to determine the corresponding processing status of each voice message, and the processing cycle of voice messages on different business platforms can be counted, so that the voice messages can be sent to the target business platform with a short processing cycle through big data analysis, thereby improving the feedback efficiency of voice messages.

[0045] In an exemplary embodiment, whether the voice message is successfully processed is determined based on the processing result, and a processing record of the voice message is generated, including: when the processing result indicates that the voice message needs to be forwarded to other service platforms for processing, it is determined that the voice message is not successfully processed, and the voice message is added to a queue of messages to be forwarded, wherein the queue of messages to be forwarded is used to store voice messages that have not been successfully processed and forward them to other service platforms other than the target service platform for reprocessing; when the processing result indicates that the voice message sender is called, it is determined that the voice message is successfully processed, and all processing processes corresponding to the voice message are terminated.

[0046] In an exemplary embodiment, after adding the voice message to the queue of messages to be forwarded, the method further includes: when it is determined that the number of messages in the queue of messages to be forwarded is greater than a preset threshold, making a forwarding call request; and starting the forwarding operation of the messages in the queue of messages to be forwarded based on the forwarding call request.

[0047] For example, the client first connects to the call control module. The call control module calls the intelligent distribution platform interface to obtain the default call channel (such as the intelligent IVR). After the call control module obtains the default channel, it calls the intelligent IVR. After the intelligent IVR processes, it needs to be forwarded to other platforms for processing, and then sends an MQ message to the MQ platform. After the intelligent distribution platform detects that the call request needs to be forwarded in the MQ, it notifies the call control module to perform the call transfer operation. After receiving the request, the call control module calls the channel informed by the intelligent distribution platform. After the call is connected, it hangs up the call with the intelligent IVR.

[0048] In an exemplary embodiment, after obtaining the voice message on the soft switch platform, the above method also includes: querying the identification code carried by each voice message, wherein the identification code is used to identify the basic information of the target object that initiates the voice message; querying the identification code through the information database connected to the application interface; when it is determined that the identification code exists in the information database, determining that the target object corresponding to the voice message is a registered object, and adding a target identifier to the voice message, wherein the target identifier is used to indicate that the voice message is an after-sales service message.

[0049] In an exemplary embodiment, obtaining a voice message on a soft switch platform includes: determining the device type of a target device that sends a voice message; and establishing a voice message sending channel with the target device if the device type has call authority to obtain the voice message sent by the target device.

[0050] In order to better understand the process of the above-mentioned voice message processing method, the process of the above-mentioned voice message processing method is described below in combination with two optional embodiments.

[0051] In an optional embodiment of the present invention, an intelligent service distribution platform system is mainly provided, such as Figure 3 As shown, the above system includes: a client 32, a basic service platform 34, an intelligent distribution platform DBS 36, and a business platform 38;

[0052] Optionally, the basic service platform 34 may include: IM platform, media platform, SS soft switch platform (DBS-ss), remote control module (DBS-remote); SS soft switch, ss means softswitch, is a functional entity that provides call control and connection control functions for services with real-time requirements for the next generation network NGN, and is the core of next generation network call and control. SS soft switch platform is used to deploy services before the call control module, and is a network communication module used to meet communication needs; IM platform is an instant messaging platform that provides basic text, voice, picture and other types of message content, and can send text, images, voice, and files. Media platform provides an audio platform for voice calls, which is the main business module responsible for audio calls, and an audio and video call platform that can make voice and video calls.

[0053] Optionally, the components of the intelligent distribution platform DBS 36 may include: Rest API module, business rule processing module, MQ (Message Queue, message queue, MQ for short) message queue module (DBS-MQ), call control module (DBS-call), background management module (DBS-Web), remote control module (DBS-remote); wherein, the Rest API module provides background interface services for the intelligent distribution platform, which is mainly used to provide background interfaces for H5 online customer service and background management websites, and also provides interfaces such as hic customer service center call interface to obtain historical forwarding communication records. The MQ message queue module is used to process MQ messages and reply messages to MQ, provide a unified MQ docking specification, and provide it to third-party applications for docking, so as to achieve access to the intelligent distribution platform service function. The background management module is mainly the background management website (DBS-H5-Admin) of the intelligent distribution platform, which provides forwarding rule configuration for page sessions and query and monitoring of text and audio sessions, and also provides statistical report functions to facilitate data statistics and monitoring. The session forwarding log can also be viewed on the background management website. It is an interface-based background management module. The call control module is mainly used to control audio calls. It connects with the DBS-REST module. After obtaining the forwarding channel, it calls the designated platform through SIP signaling to complete the voice online consultation function of the network device or smart speaker. The call control module can complete the connection with the intelligent IVR and the HIC customer service center voice agent to complete the forwarding of call signaling. The remote control module and the call control module include two parts: one is the SDK function integrated in the network device, and the other is the desktop program for the agents of the hic customer service center. When the user of the network device uses the device for voice communication, the manual agent is required to provide remote support. The customer can click the remote assistance button. At this time, a 6-digit connection code will be displayed on the network device. Tell the manual agent this connection code. The manual agent can enter the connection code through the desktop client and directly remotely control the network device.

[0054] Optionally, the business platform 38 may include: a user center system, a cloud text robot, an intelligent IVR, a HIC customer service platform, and a network customer service center.

[0055] Optionally, the user center system includes: integrated scenarios and integrated data, wherein the integrated scenario is to obtain user information, including user unique ID and user role information, based on the user's unique account. The integrated data is based on user ID and user role, and the user ID is used by the HIC customer service center to obtain this user information. The user role is used by the intelligent distribution platform to determine which default channel to use based on the user role.

[0056] Optionally, the integration scenario of the Cloud Question text robot is that the IM client sends a voice message to the IM platform through the SDK, the IM platform forwards the message to the intelligent distribution platform, the intelligent distribution platform sends the IM message to MQ according to business rules, the Cloud Question robot consumes the data in the MQ message, and then answers the question. The answer message is also sent to MQ, the intelligent distribution platform consumes the message stored by the Cloud Question robot on the intelligent distribution platform, and determines whether the Cloud Question robot forwards the message to other channels. If it is forwarded to the HIC customer service center for processing, if not, the message is pushed to the IM client through the REST interface.

[0057] It should be noted that the above integrated data is composed of the following in different interaction stages:

[0058] Step 1: The IM platform forwards the message to the intelligent distribution platform. The IM is the producer and the intelligent distribution platform consumes it. Optionally, the corresponding field types are shown in Table 1:

[0059]

[0060]

[0061] Step 2: The intelligent distribution platform consumes IM_to_robot, queries the user center interface based on userId to obtain user information, and determines which channel the user should be forwarded to based on business rules. The default robot channel calls the robot interface / MQ.

[0062] Step 3: The intelligent distribution platform determines that manual work is required, sends a production message, and consumes it at the hic customer service center. At this time, the corresponding field types are shown in Table 2:

[0063]

[0064] Optionally, the integration scenario of the HIC customer service platform is: enter the online customer service page of the Zhijia APP, click the [Transfer to Manual] button or the top custom menu, and you can forward the consultation to the HIC customer service text processing center. The HIC customer service center can handle text and image consultations. Process: The online customer service sends an IM message to the IM platform, and the IM platform forwards the message to the intelligent distribution platform. The intelligent distribution platform determines that it is to be sent to the manual customer service, and then calls the manual customer service rest interface to send the question out. After the hic customer service center receives the question, the customer service writes the corresponding answer, and then calls the reply interface provided by the intelligent distribution platform. After receiving the reply, the intelligent distribution platform pushes this message to the online customer service, and the whole process ends. The integrated data of the HIC customer service platform is: after transferring to manual, the deal_type field in the ke_text_session_info table needs to be modified. deal_type is 1, which means that the robot is processing, and 2, which means that the manual customer service is processing. The HIC customer service center and the manual agent platform can intervene in text and voice consultations.

[0065] Optional, intelligent IVR (voice call), intelligent question and answer voice platform, can guide users intelligently based on knowledge training. The integration scenario of intelligent IVR is that the user uses the smart speaker through the SS soft switch module to the call processing module, the call processing module DBS-Call calls the intelligent distribution platform interface, obtains the default call to the channel intelligent IVR, and the speaker and intelligent IVR establish communication. When the intelligent IVR cannot handle it, it calls the intelligent distribution platform interface, obtains the forwarding channel information, and then forwards the call to the forwarding channel.

[0066] The integrated data of intelligent IVR includes:

[0067] 1) Get the default channel information of voice calls, request URL: POST http: / / {hostname} / v1 / voice / defaultModule. The request parameters are shown in Table 3. The return parameters are shown in Table 4, and the info object parameters are shown in Table 5;

[0068] Table 3, request parameters:

[0069]

[0070] Table 4, return parameters:

[0071]

[0072] Table 5. info object parameters

[0073]

[0074] 2) Get the voice forwarding manual channel information. Specifically, request URL: POST http: / / {hostname} / v1 / voice / customerModule. The request parameters are shown in Table 6. The return parameters are shown in Table 7. The info object parameters are shown in Table 8.

[0075] Table 6, request parameters:

[0076]

[0077] Table 7, return parameters:

[0078]

[0079] Table 8. info object parameters

[0080]

[0081]

[0082] After the above intelligent business distribution platform system is built, it is also divided in terms of organization and authority. For example, the roles of the intelligent distribution platform backend management website are divided into: super administrator, ordinary administrator, and operation and maintenance engineer. The super administrator has all system permissions, including role management, administrator management, etc. The ordinary administrator has all permissions except role management, user management, and menu management. The operation and maintenance engineer has the abnormal forwarding data menu.

[0083] As an optional implementation, Figure 4 is a network topology diagram of an intelligent service distribution platform system according to an optional embodiment of the present invention; Figure 5 : is a schematic diagram of the network architecture of the intelligent business distribution platform system according to an optional embodiment of the present invention. A user can access the cloud server where the intelligent business distribution platform and online customer service exist through the Internet. The cloud server is directly connected to the information server including the user center and the membership system. The cloud server can also be connected to the internal system server. The internal system server may include sensitive information such as the order system, CDK, work order system, OMS, etc.;

[0084] Optionally, when executing the above network architecture, you need to pay attention to the following points:

[0085] 1. Each functional module establishes an elastic expansion group to cope with business peaks;

[0086] 2. The database security group only allows the corresponding application to access, the application security group only allows the front-end access, and other groups are also required to only open necessary access permissions;

[0087] 3. The business is placed in another VPC in the same area as the distribution platform for necessary isolation.

[0088] 4. Publish Internet services through the load balancer, and disable Internet addresses for other resources.

[0089] Optionally, for the data structure, use the existing user center's unified login solution, and record the non-logged-in users separately. Customer information comes from the user center, including user tags, names, user IDs, mobile phone numbers, addresses, etc.; member and rights information comes from the member center, such as member rights level, etc.; points information comes from the points center, such as member points, etc.; user service order information comes from the HCC system; user product and order information comes from the existing Zhijia Mall order system. User logistics information comes from the existing CDK logistics system. This will form a unified information management.

[0090] As an optional implementation, Figure 6 1 is a flow chart of a process of processing a voice message by an intelligent service distribution platform system according to an optional embodiment of the present invention, which specifically includes the following steps:

[0091] Step 1: Register the target device on the basic service platform so that the voice message of the target device can be uploaded to the soft switch platform included in the basic service platform.

[0092] Step 2: When a voice message call is initiated from the target device, the voice message is sent to the soft switch platform;

[0093] Step 3: The soft switch platform calls the call control module in the intelligent distribution platform to complete the process of the client first connecting to the call control module.

[0094] Step 4: The call control module calls the intelligent distribution platform interface to obtain the default call channel (eg, intelligent IVR).

[0095] Step 5: The call control module calls the default channel to determine how the default channel handles the voice message;

[0096] Step 6: When the default channel fails to process the voice message successfully, it is determined that the voice message needs to be forwarded for processing, and the forwarding channel information is obtained and sent to the business rule processing module in the intelligent distribution platform for confirmation;

[0097] Step 7: The call control module forwards the voice message according to the forwarding channel information corresponding to the forwarding call initiated by the default channel;

[0098] Step 8: After receiving the forwarding request, call the new channel according to the forwarding channel information to process the voice message, and hang up the call on the old channel.

[0099] In summary, through the optional embodiments of the present invention, the intelligent business distribution platform provides the ability to distribute user consultation customer service information based on a variety of business scenarios, and realizes the distribution of upper-level logic, such as distributing consulting users to different robots or different reception groups of different seat reception systems. In addition, the intelligent business distribution platform provides a unified docking specification to facilitate the access configuration of modular products. The entire intelligent customer service system can be modularly replaced or upgraded, and multiple suppliers can be selected for bidding cooperation, which can not only improve product strength but also save a lot of costs.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, 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, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to perform the processing of voice messages described in each embodiment of the present invention.

[0101] In this embodiment, a voice message processing device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made are omitted. Although the devices described in the following embodiments are preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0102] Figure 7 is a structural block diagram of a voice message processing device according to an embodiment of the present invention, such as Figure 7 As shown, the device comprises:

[0103] An acquisition module 72 is used to acquire a voice message on a soft switch platform;

[0104] A determination module 74, configured to determine the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message;

[0105] The processing module 76 is used to match a voice processing channel of the complexity from a preset channel list, and send the voice message to a corresponding target service platform for processing through the voice processing channel.

[0106] Through the above-mentioned device, voice messages on the soft switch platform are obtained; the complexity corresponding to the voice message is determined, wherein the complexity is used to indicate the difficulty of processing the voice message; a voice processing channel of the complexity is matched from a preset channel list, and the voice message is sent to the corresponding target business platform for processing through the voice processing channel. In other words, the intelligent distribution platform classifies and processes the voice messages through interaction and cooperation with the target device terminal, the basic service platform, and the business platform, and determines a suitable voice processing channel for the voice message according to the complexity corresponding to the voice message, and divides and manages the voice messages. Therefore, the problems in the prior art that voice messages cannot be effectively distinguished and processed, and the processing method is single and cannot be adjusted, etc., can be solved, so that the processing methods for voice messages become diverse, the processing efficiency of voice messages is improved, and the slowness of a single method is avoided.

[0107] In an exemplary embodiment, the processing module is also used to determine that the voice processing channel corresponding to the voice message is an interactive voice response when the complexity is determined to be less than or equal to a first preset threshold; and to determine that the voice processing channel corresponding to the voice message is a manual agent response when the complexity is determined to be greater than the first preset threshold and less than or equal to a second preset threshold. In simple terms, by setting a threshold interval, voice messages within a certain complexity range are processed through the same voice processing channel, thus avoiding the tediousness of confirming channels when the complexity is too high. As long as it is within the threshold range, the corresponding voice processing channel is used, so that no matter what the situation is, the processing channel corresponding to the voice message can be quickly determined.

[0108] In an exemplary embodiment, the above-mentioned device also includes: a recording module, which is used to obtain the processing result of the target business platform for the voice message; determine whether the voice message is successfully processed according to the processing result, and generate a processing record of the voice message, wherein the processing record includes: platform information of the target business platform that processes the voice message, and the processing cycle of the voice message. That is to say, after the voice message is sent to the corresponding target business platform for processing through the voice processing channel, in order to facilitate the subsequent search for the processing result of the voice message and ensure the processing effect of the voice message, the processing result can be analyzed to determine the corresponding processing situation of each voice message, and the processing cycle of the voice message by different business platforms can be counted, so that the voice message can be sent to the target business platform with a short processing cycle in priority through big data analysis, thereby improving the feedback efficiency of the voice message.

[0109] In an exemplary embodiment, the above-mentioned recording module is also used to determine that the voice message has not been successfully processed and add the voice message to a queue of messages to be forwarded when the processing result indicates that the voice message needs to be forwarded to other business platforms for processing, wherein the queue of messages to be forwarded is used to store voice messages that have not been successfully processed and forward them to other business platforms other than the target business platform for reprocessing; when the processing result indicates that the voice message sender is called, it is determined that the voice message has been successfully processed and all processing processes corresponding to the voice message are terminated.

[0110] In an exemplary embodiment, the recording module further includes: a forwarding unit, configured to make a forwarding call request when it is determined that the number of messages in the message queue to be forwarded is greater than a preset threshold; and to start the forwarding operation of the messages in the message queue to be forwarded based on the forwarding call request.

[0111] For example, the client first connects to the call control module. The call control module calls the intelligent distribution platform interface to obtain the default call channel (such as intelligent IVR, interactive Vocie Response, interactive voice response, abbreviated as IVR). After the call control module obtains the default channel, it calls the intelligent IVR. After the intelligent IVR processes, it needs to be forwarded to other platforms for processing, and then sends an MQ message to the MQ platform. After the intelligent distribution platform detects that the call request needs to be forwarded in MQ, it notifies the call control module to perform the call transfer operation. After receiving the request, the call control module calls the channel informed by the intelligent distribution platform. After the call is connected, it hangs up the call with the intelligent IVR.

[0112] In an exemplary embodiment, the above-mentioned device also includes: a query module, used to query the identification code carried by each voice message, wherein the identification code is used to identify the basic information of the target object that initiates the voice message; query the identification code through the information database connected to the application interface; when it is determined that the identification code exists in the information database, determine that the target object corresponding to the voice message is a registered object, and add a target identifier to the voice message, wherein the target identifier is used to indicate that the voice message is an after-sales service message.

[0113] In an exemplary embodiment, the acquisition module is further used to determine the device type of the target device that sends the voice message; if the device type has call authority, establish a voice message sending channel with the target device to obtain the voice message sent by the target device.

[0114] In the description of the present invention, it should be understood that the orientations or positional relationships indicated by the terms "center", "upper", "lower", "front", "back", "left", "right", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0115] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two components. When a component is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other component or there can also be a central component. When a component is considered to be "connected" to another element, it can be directly connected to the other element or there can be a central element at the same time. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0116] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0117] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0118] In an exemplary embodiment, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0119] S1, obtain the voice message on the soft switch platform;

[0120] S2, determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message;

[0121] S3, matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel.

[0122] In an exemplary embodiment, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0123] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0124] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0125] In an exemplary embodiment, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0126] S1, obtain the voice message on the soft switch platform;

[0127] S2, determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message;

[0128] S3, matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel.

[0129] In an exemplary embodiment, the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0130] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices. In an exemplary embodiment, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing a voice message, characterized in that: include: Get voice messages on the soft switch platform; Determining the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message; Matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel; Wherein, the preset channel list simultaneously contains one or more sets of corresponding relationships between complexity and speech processing channels; After acquiring the voice message on the soft switch platform, the method further includes: Querying the identification code carried by each of the voice messages, wherein the identification code is used to identify basic information of the target object that initiated the voice message; Querying the identification code through an application program interface connected to an information database; When it is determined that the identification code exists in the information database, it is determined that the target object corresponding to the voice message is a registered object, and a target identification is added to the voice message, wherein the target identification is used to indicate that the voice message is an after-sales service message.

2. The method for processing voice messages according to claim 1, characterized in that: Matching a voice processing channel of the complexity from a preset channel list, and sending the voice message to a corresponding target service platform for processing through the voice processing channel, including: In the case where it is determined that the complexity is less than or equal to a first preset threshold, determining that the voice processing channel corresponding to the voice message is an interactive voice response; When it is determined that the complexity is greater than the first preset threshold and less than or equal to the second preset threshold, it is determined that the voice processing channel corresponding to the voice message is a manual agent answer.

3. The method for processing voice messages according to claim 1, characterized in that: After matching a voice processing channel of the complexity from a preset channel list and sending the voice message to a corresponding target service platform for processing through the voice processing channel, the method further includes: Obtaining a processing result of the target service platform on the voice message; Determine whether the voice message is successfully processed according to the processing result, and generate a processing record of the voice message, wherein the processing record includes: platform information of a target service platform for processing the voice message and a processing cycle of the voice message.

4. The method for processing voice messages according to claim 3, characterized in that: Determining whether the voice message is successfully processed according to the processing result, and generating a processing record of the voice message, including: If the processing result indicates that the voice message needs to be forwarded to other service platforms for processing, determining that the voice message has not been successfully processed, and adding the voice message to a queue of messages to be forwarded, wherein the queue of messages to be forwarded is used to store voice messages that have not been successfully processed and forward them to other service platforms other than the target service platform for reprocessing; In the case where the processing result indicates that the voice message sender is called, it is determined that the voice message is successfully processed, and all processing flows corresponding to the voice message are terminated.

5. The method for processing voice messages according to claim 4, characterized in that: After adding the voice message to the queue of messages to be forwarded, the method further includes: When it is determined that the number of messages in the to-be-forwarded message queue is greater than a preset threshold, a forwarding call request is made; The forwarding operation of the messages in the to-be-forwarded message queue is started based on the forwarding call request.

6. The method for processing voice messages according to claim 1, characterized in that: Get voice messages on the soft switch platform, including: Determining the device type of the target device that sent the voice message; In the case that the device type has the calling authority, a voice message sending channel is established with the target device to obtain the voice message sent by the target device.

7. A voice message processing device, characterized in that: include: An acquisition module is used to acquire voice messages on the soft switch platform; A determination module, configured to determine the complexity corresponding to the voice message, wherein the complexity is used to indicate the difficulty of processing the voice message; A processing module, used to match a voice processing channel of the complexity from a preset channel list, and send the voice message to a corresponding target service platform for processing through the voice processing channel; Wherein, the preset channel list simultaneously contains one or more sets of corresponding relationships between complexity and speech processing channels; The device also includes: a query module, which is used to query the identification code carried by each voice message after obtaining the voice message on the soft switch platform, wherein the identification code is used to identify the basic information of the target object that initiated the voice message; query the identification code through the information database connected to the application program interface; when it is determined that the identification code exists in the information database, determine that the target object corresponding to the voice message is a registered object, and add a target identifier in the voice message, wherein the target identifier is used to indicate that the voice message is an after-sales service message.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method for processing a voice message according to any one of claims 1 to 6 when running.

9. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the voice message processing method according to any one of claims 1 to 6.

Images