Intelligent voice call answering method and system based on call transfer
By using intelligent voice-activated call answering technology, the problems of high call volume and poor customer experience for sales staff in the express delivery and logistics industry have been solved. This has enabled intelligent call recording and business processing, improving service quality and efficiency.
Patent Information
- Application Number
- CN202610404919.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-31
- Publication Date
- 2026-07-10
AI Technical Summary
In the express delivery and logistics industry, there are problems such as high pressure on sales staff, poor customer experience, and lack of call record summaries. Traditional call forwarding cannot provide intelligent dialogue services and business processing capabilities.
The intelligent voice call forwarding method enables intelligent interaction with customers through voice-to-text conversion, intent recognition, and business process orchestration, while also recording call content and generating structured feedback.
It alleviated the pressure on sales staff, improved customer experience, ensured service quality and business processing efficiency, reduced customer complaints, and enabled structured feedback of call records.
Smart Images

Figure FT_1
Abstract
Description
Technical Field
[0001] This invention belongs to the fields of communication technology, artificial intelligence and intelligent voice interaction technology, and relates to an intelligent voice call forwarding method and system based on call transfer. Background Technology
[0002] In the express delivery and logistics service industry, couriers or sales representatives are the key link between businesses and customers. Customers typically contact the sales representative by calling their mobile phone number to confirm delivery, change addresses, file complaints, or make inquiries. However, the existing business model faces the following technical problems and challenges: 1. High pressure on sales staff and missed calls: During delivery, sales staff are often driving, carrying goods, or communicating face-to-face with customers, making it difficult to answer customer calls promptly. This not only puts enormous pressure on sales staff but also results in a large number of missed customer calls.
[0003] 2. Customer experience and complaint risks: When customers make calls and no one answers or the line is busy, they are prone to anxiety and dissatisfaction, which can lead to complaints and seriously affect the company's service quality and brand image.
[0004] 3. Lack of call logs and business summaries: Even if salespeople answer the phone, it is difficult for them to accurately record the content of the call and the key business points in their busy work. This leads to a lack of basis for subsequent business processing, which can easily cause information omissions or processing errors.
[0005] 4. Limitations of traditional call forwarding: Traditional call forwarding services can only forward calls to another phone number or voicemail, and cannot provide intelligent dialogue services and business processing capabilities. Summary of the Invention
[0006] The purpose of this invention is to solve the problems in the prior art and provide an intelligent voice call forwarding method and system based on call forwarding, which is used to realize the intelligent call forwarding and call record management system and method for salespersons. To achieve the above objectives, the present invention employs the following technical solution: A method for intelligent voice call answering based on call forwarding includes the following steps: Get incoming customer calls and generate transfer instructions based on them; According to the transfer instruction, conduct voice interaction with the incoming caller and convert the customer's voice into text. The system performs intent recognition based on customer text, executes a preset business process based on the intent recognition results, generates a response text based on the customer's intent, converts the response text into a voice response, and completes the voice call.
[0007] A further improvement of the present invention is that: It also includes recording the interaction content and sending the recorded content to the corresponding salesperson. The recorded content includes the customer's number, the salesperson's number, the call duration, the complete dialogue text, the intent summary, and entity information.
[0008] The transfer instructions include unconditional call transfer, call transfer when the phone is off or out of service area, call transfer when busy, and call transfer when there is no answer.
[0009] The process of recognizing intent based on customer text, executing a preset business process based on the intent recognition result, generating a response text corresponding to the customer's intent according to the preset business process, converting the response text into a response voice, and completing voice call assistance includes: Based on the customer's conversation, the RASA module identifies the customer's intent and the corresponding entity. Input the customer's intent and the corresponding entity into the business process orchestration engine to generate the current dialogue state and the next business process to be executed; Execute the corresponding service query based on the current dialogue status and the next business process to be executed, and select the preset script template based on the service query results.
[0010] The customer's intent includes checking for items, sending items, and filing complaints; The corresponding entities include the waybill number and the relevant address; The service queries include order prohibited items query, address resolution, and waybill query.
[0011] The business process orchestration engine uses the LiteFlow engine.
[0012] An intelligent voice call answering system based on call forwarding includes: The transfer instruction module is used to acquire customer calls and generate transfer instructions based on the customer calls. The voice conversion module is used to interact with the caller via voice according to the transfer instruction, converting the customer's voice into text. The intent recognition module is used to recognize the intent based on the customer's text. Based on the intent recognition result, it executes a preset business process, generates a response text that is tailored to the customer's intent, converts the response text into a response voice, and completes the voice call.
[0013] The system also includes a recording module for recording the interaction content and sending the recorded content to the corresponding salesperson. The recorded content includes the customer's number, the salesperson's number, the call duration, the complete dialogue text, the intent summary, and entity information.
[0014] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of any of the methods described above.
[0015] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the methods described herein.
[0016] Compared with the prior art, the present invention has the following beneficial effects: This invention discloses an intelligent voice call forwarding method, aiming to solve the problems of high call handling pressure, poor customer experience, and lack of call record summaries in the express delivery and logistics service industries. It generates corresponding forwarding instructions based on the customer's voice needs and then proactively engages in understandable voice interaction with the customer, effectively alleviating the pressure on sales staff due to environmental limitations. Furthermore, through intent recognition and business process generation, it generates response texts tailored to the customer's intent, improving the efficiency and accuracy of business processing. This invention effectively alleviates the call handling pressure on sales staff, reduces customer complaints, and improves the efficiency of subsequent processing through structured feedback, ensuring service quality. Attached Figure Description
[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a schematic diagram of the intelligent call forwarding configuration disclosed in an embodiment of the present invention. Detailed Implementation
[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0020] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.
[0021] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0022] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0023] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.
[0024] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.
[0025] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 This invention discloses an intelligent voice call answering method based on call forwarding to solve the problems of high call answering pressure on salespersons, poor customer experience, and lack of call record summarization in the prior art. Its core lies in using the call forwarding function of mobile communication network to seamlessly connect customer calls to the intelligent voice robot platform, and combining dialogue management, business process orchestration and back-end services to achieve intelligent call answering and information summarization throughout the entire process.
[0026] Example 1 This invention discloses an intelligent voice call answering method based on call forwarding, comprising the following steps: Step 1: Obtain customer call information and generate a transfer instruction based on the customer call information; Specifically, it includes: Salespeople can set up call forwarding commands through mobile communication networks to transfer customer calls that meet preset conditions to the voice robot platform.
[0027] The preset conditions include: no conditions, power off / out of service area, busy, and no response.
[0028] Step 2: Based on the transfer instruction, conduct voice interaction with the caller and convert the customer's voice into text. Specifically, it includes: The voice robot platform receives the transferred customer calls via SIP communication service, converts the customer's voice into text via ASR, and converts the robot's reply text into voice via TTS.
[0029] Step 3: Perform intent recognition based on customer text, execute the preset business process according to the intent recognition result, generate a response text based on the customer's intent according to the preset business process, convert the response text into a response voice, and complete the voice call.
[0030] Specifically, it includes: The intelligent dialogue service module receives the text converted from ASR, performs intent recognition, entity extraction, and business process orchestration, and calls the backend query service to assemble the response script: Step 3.1: Determine the current dialogue state by combining the session context information stored in the caching mechanism; Step 3.2: Based on the dialogue status, determine the next business process using the business process orchestration engine; Step 3.3: Call the backend query service according to the business process; Step 3.4: Assemble the reply script based on the query results and the preset script template.
[0031] Furthermore, in this step, the backend query service includes order prohibited items query, address resolution, and waybill query.
[0032] Step 5: Record the interaction content and send the recorded content to the corresponding salesperson.
[0033] Specifically, it includes: After the call ends, the call summary and feedback module automatically pushes the call detail record to the salesperson's client: The call detail records are displayed in a structured and visual manner on the salesperson's client, allowing the salesperson to view the records of calls received on behalf of others.
[0034] Example 2 This invention discloses an intelligent voice call answering method based on call forwarding, comprising the following steps: Step 1: Salesperson sets up call forwarding: Salespeople can set up call forwarding instructions on their mobile phones (e.g., 67 forwarding number#) to forward incoming calls under specific conditions (such as busy) to the voice robot platform.
[0035] Step 2: Customer dials salesperson's number: The customer dials the salesperson's mobile phone number.
[0036] Step 3: Operator triggers call forwarding: When the preset call forwarding conditions are met, the operator will send the call to the technology platform - voice robot platform through the SIP line.
[0037] Step 4: Voice robot platform processing: Upon receiving a call, the customer's voice is converted to text via ASR.
[0038] Send the text to the robot session manager.
[0039] The robot conversation management calls the Xingzhe Zhixiaotong dialogue service interface to obtain the reply text.
[0040] The reply text is converted into speech via TTS and played back to the customer.
[0041] Step 5: End of Call and Push of Record: After the call ends, the system pushes the call detail record to the Xingzhe backend service, and displays it on the salesperson's client through that service.
[0042] Call detail records include audio recordings, dialogue texts, and intent summaries.
[0043] Further, see Figure 1 This is a schematic diagram of the intelligent call forwarding configuration of the present invention, including: The specific process of step 1 includes: (1) Instruction settings: Salespersons can bind their mobile phone number to the voice robot platform's number by dialing a specific call forwarding instruction via their mobile phone.
[0044] (2) Transfer condition settings: The system supports the configuration of various transfer conditions, including: "21" forwarding number #: unconditional call forwarding.
[0045] "62" forwarding number#: Call forwarding is available when the phone is switched off or out of service area.
[0046] "67" forwarding number #: Call forwarding when busy.
[0047] "61" forwarding number #: Call forwarding when there is no answer.
[0048] (3) Platform reception: The voice robot platform receives the call transferred by the operator and identifies which salesperson is calling based on the call information, thereby loading the corresponding business configuration and session context.
[0049] See Figure 1 Furthermore, this embodiment elaborates on the complete execution flow of the intelligent voice call answering system based on call forwarding, and the specific steps are as follows: Step 1: After logging into their account on the terminal, the salesperson enters the "Telephone Assistant" function page of the system. The system automatically verifies whether the salesperson is a registered user of Zhixiaodi. If the salesperson is not a registered user, the salesperson submits a silent registration application containing their employee number, name, mobile phone number, and branch code. The system calls the account registration service to complete the registration and returns the registration information. After registration, both the salesperson and the registered user will enter the call history page.
[0050] The second step involves the system automatically checking on the call log page whether the salesperson's mobile phone number has call forwarding service activated. If not, the salesperson initiates a call forwarding activation request, and the system sends a standardized call forwarding activation command to the telecom service provider. After the telecom service provider executes the activation operation, it synchronizes the service activation / deactivation result to the system, which immediately records the service activation status. If the service is already activated, the system directly proceeds to the call log service stage. Simultaneously, the salesperson can configure multi-condition call forwarding by dialing a dedicated command from their mobile phone.
[0051] The third step is for the customer to dial the mobile phone number linked to the salesperson. The telecom service provider monitors the call status in real time, and when the call forwarding conditions preset by the salesperson are met, the call is automatically forwarded to the system's voice robot platform via SIP line.
[0052] Step 4: After the call ends, generate a structured call detail record and push the call detail record to the Xingzhe backend service.
[0053] Step 5: The backend service of Xingzhe will display the call detail records in a structured and visual form in the "Smart Delivery Call Receipt Records" section of the salesperson's terminal client. The salesperson can view all the call receipt records in this section and perform subsequent business processing operations such as recording playback, calling back customers, and sending text messages to customers based on the record content.
[0054] Furthermore, step 4 specifically includes the following processes: Step 4.1: Receive the session ID and client text.
[0055] Step 4.2, Intent Recognition and Entity Extraction: Call an intent recognition service (such as RASA) to identify the customer's intent from the customer's speech; Furthermore, in this step, the customer's intent includes checking for a package, sending a package, and filing a complaint; Furthermore, in this step, the entity includes the waybill number and the address.
[0056] Step 4.3, Business Process Orchestration: Input the intent and entity into the business process orchestration engine, which uses LiteFlow in this step.
[0057] The LiteFlow engine combines session context information stored in the Redis cache to determine the current conversation state and the next business process.
[0058] It enables the flow of dialogue context and the judgment of complex business logic.
[0059] Step 4.4: Call the query service: Based on the process orchestration results, call the internal services provided by the Xingzhe backend service, such as order prohibited items query, address resolution, and waybill query.
[0060] Step 4.5: Assemble the response script: Based on the query results and preset script templates (stored in the database or configuration), assemble the final response text.
[0061] Step 4.6: Return the reply script to the voice robot platform.
[0062] Furthermore, it also includes the following steps: Step 5.1, Call Detail Record Generation: After the call ends, the voice robot platform generates a call detail record containing the following information: Customer number, salesperson number, call duration, complete conversation text (ASR result and TTS response), intent summary (e.g., "customer inquiring about shipment"), and key entity information (e.g., waybill number).
[0063] Step 5.2, Record the push notification: Call detail records are pushed to the Xingzhe backend service asynchronously (e.g., via message queues).
[0064] Step 5.3, Client Display: Sales representatives can view the "Smart Delivery Call Records" through their client app. The records are displayed in a structured and visual way, allowing sales representatives to clearly understand the purpose of customer calls and the robot's processing results.
[0065] Example 3 This invention discloses an intelligent voice call answering system based on call forwarding, comprising: The system includes the Intelligent Call Forwarding Configuration module, the Voice Robot Platform, the Intelligent Dialogue Service module, and the Call Summary and Feedback module. Specifically: (1) Intelligent Call Forwarding Configuration Module: It allows sales staff to transfer customer calls to the voice robot platform using preset call forwarding commands.
[0066] It supports setting multiple transfer conditions, including unconditional transfer, transfer when the device is off / out of service area, transfer when busy, and transfer when there is no response, ensuring that the transfer can be intelligently handled when the salesperson is in different busy states.
[0067] (2) Voice Robot Platform: Receive transferred customer calls via SIP communication service.
[0068] This invention integrates ASR (Action-Speech Reduction) and TTS (Text-to-Speech) technologies to convert customer voice input into text and synthesize robot text responses into speech. Both ASR and TTS technologies used in this embodiment are existing, publicly available technologies.
[0069] Responsible for managing robot conversations and maintaining call status and context information.
[0070] (3) Intelligent Dialogue Service Module: By employing intent recognition and entity extraction technologies, this system accurately understands customer inquiries. It can also leverage the RASA platform for intent recognition and entity extraction. Through business process orchestration engines (such as LiteFlow) and caching mechanisms (such as Redis), the flow of dialogue context and the processing of complex business logic can be realized.
[0071] We call backend query services to provide standardized services to customers, including order query, address resolution, and waybill query.
[0072] Based on business logic and query results, assemble response scripts to ensure the accuracy and professionalism of the answers.
[0073] (4) Call Summary and Feedback Module: After the call ends, the system automatically pushes the call detail record to the salesperson's client. The call detail record includes the recording, conversation text, intent summary, and key information.
[0074] Sales staff can view the call records handled by Smart Delivery through the client application, quickly understand customer needs and processing results, without the need for manual recording.
[0075] The intelligent call forwarding configuration module supports the setting of various forwarding conditions, including unconditional forwarding, forwarding when the phone is off / out of service area, forwarding when busy, and forwarding when there is no answer.
[0076] This embodiment discloses an intelligent voice call answering method and system based on call forwarding, which includes the following effects: (1) Relieve the pressure on sales staff to answer calls: Through intelligent call forwarding, calls that sales staff cannot answer are automatically transferred to robots to answer, which significantly reduces the burden on sales staff to answer calls.
[0077] (2) Improve customer service experience: When customers make a call, even if the salesperson is busy, they can immediately receive a response and standardized service from the voice robot, which effectively reduces the anxiety and complaints caused by no one answering the phone.
[0078] (3) Ensure service quality and standardization: Voice robots can provide standardized services such as checking and sending packages, ensuring the consistency of service quality and avoiding deviations that may occur with human services.
[0079] (4) Achieve structured feedback of call records: The system automatically generates call summaries and pushes them to the salesperson's client, achieving structured and visual feedback of call records, which improves the efficiency and accuracy of the salesperson's subsequent processing.
[0080] (5) Improve business processing efficiency: Through the integration of intent recognition, business process orchestration and backend query services, the robot can quickly process standardized business, thereby improving the overall business processing efficiency.
[0081] A schematic diagram of a terminal device according to an embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the various method embodiments described above. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the various device embodiments described above.
[0082] The computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention.
[0083] The terminal device can be a desktop computer, laptop computer, cloud server, or other device with strong computing power. The terminal device may include, but is not limited to, a processor and memory.
[0084] The optimal choice for the processor is a multi-core high-speed central processing unit (CPU).
[0085] The memory can be used to store the computer program and / or module. The processor implements various functions of the terminal device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.
[0086] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.
[0087] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for intelligent voice call answering based on call forwarding, characterized in that, Includes the following steps: Get incoming customer calls and generate transfer instructions based on them; According to the transfer instruction, conduct voice interaction with the incoming caller and convert the customer's voice into text. The system performs intent recognition based on customer text, executes a preset business process based on the intent recognition results, generates a response text based on the customer's intent, converts the response text into a voice response, and completes the voice call.
2. The intelligent voice call answering method based on call forwarding according to claim 1, characterized in that, It also includes recording the interaction content and sending the recorded content to the corresponding salesperson. The recorded content includes the customer's number, the salesperson's number, the call duration, the complete dialogue text, the intent summary, and entity information.
3. The intelligent voice call answering method based on call forwarding according to claim 1, characterized in that, The transfer instructions include unconditional call transfer, call transfer when the phone is off or out of service area, call transfer when busy, and call transfer when there is no answer.
4. The intelligent voice call answering method based on call forwarding according to claim 1, characterized in that, The process of recognizing intent based on customer text, executing a preset business process based on the intent recognition result, generating a response text corresponding to the customer's intent according to the preset business process, converting the response text into a response voice, and completing voice call assistance includes: Based on the customer's conversation, the RASA module identifies the customer's intent and the corresponding entity. Input the customer's intent and the corresponding entity into the business process orchestration engine to generate the current dialogue state and the next business process to be executed; Execute the corresponding service query based on the current dialogue status and the next business process to be executed, and select the preset script template based on the service query results.
5. The intelligent voice call answering method based on call forwarding according to claim 4, characterized in that, The customer's intent includes checking for items, sending items, and filing complaints; The corresponding entities include the waybill number and the relevant address; The service queries include order prohibited items query, address resolution, and waybill query.
6. The intelligent voice call answering method based on call forwarding according to claim 4, characterized in that, The business process orchestration engine uses the LiteFlow engine.
7. An intelligent voice call answering system based on call forwarding, characterized in that, include: The transfer instruction module is used to acquire customer calls and generate transfer instructions based on the customer calls. The voice conversion module is used to interact with the caller via voice according to the transfer instruction, converting the customer's voice into text. The intent recognition module is used to recognize the intent based on the customer's text. Based on the intent recognition result, it executes a preset business process, generates a response text that is tailored to the customer's intent, converts the response text into a response voice, and completes the voice call.
8. The intelligent voice call answering system based on call forwarding according to claim 7, characterized in that, The system also includes a recording module for recording the interaction content and sending the recorded content to the corresponding salesperson. The recorded content includes the customer's number, the salesperson's number, the call duration, the complete dialogue text, the intent summary, and entity information.
9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-6.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-6.
