Customer return visit system control method and device and computer readable storage medium

Abstract

The invention discloses a control method and device of a client return visit system and a computer readable storage medium, and relates to the technical field of data processing, the control method of the client return visit system comprises the following steps: establishing a communication session with a voice communication terminal, reducing waiting time, ensuring real-time performance and stability of communication, and improving user experience. The corresponding questionnaire audio is accurately obtained according to the customer information and is sent to the voice communication terminal of the customer through the communication session, the traditional return visit operation process is simplified, the reply audio sent by the customer through the voice communication terminal is converted into the text form through the voice recognition technology, the accuracy of data collection is improved, and the user experience is improved. And the return visit question and answer pair is generated according to the reply audio and the questionnaire audio, and the return visit question and answer pair and the customer information are stored in an associated manner, so that automatic processing of the return visit process is realized, manual intervention is reduced, and the return visit efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a control method, device and computer-readable storage medium for a customer return visit system. Background Art

[0002] Customer feedback systems are widely used to collect customer feedback on services or products in order to optimize and improve them in a timely manner. In the current customer feedback system, manual customer service initiates a feedback to the customer and asks the customer questions based on the feedback questionnaire. The manual customer service needs to listen carefully or read the customer's answer, and then select the answer that best suits the customer's answer from the preset answer options. Since manual customer service needs to spend time to understand the customer's answer, the customer needs to wait for the manual customer service's selection and confirmation. The feedback process is long, resulting in low feedback efficiency.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a control method, device and computer-readable storage medium for a customer return visit system, aiming to solve the technical problem of how to improve the efficiency of customer return visits.

[0005] To achieve the above purpose, the present application proposes a control method for a customer return visit system, the control method for the customer return visit system comprising: Establishing a communication session with a voice call terminal corresponding to the customer based on the customer information; Acquire a questionnaire audio according to the customer information, and send the questionnaire audio to the voice call terminal based on the communication session; receiving a reply audio sent by the voice call terminal, and generating a reply-answer pair according to the reply audio and the questionnaire audio; The question-answer pair is associated with the customer information and stored.

[0006] In one embodiment, the step of establishing a communication session with a voice call terminal corresponding to the customer based on the customer information includes: Determine the corresponding customer information according to the customer return visit process; Identify the type of voice call terminal corresponding to the customer information to obtain the communication address of the customer; A session connection with the voice call terminal is established according to the communication address.

[0007] In one embodiment, the step of obtaining the questionnaire audio according to the customer information and sending the questionnaire audio to the voice call terminal based on the communication session includes: Based on the customer information, the corresponding questionnaire is sent to the client terminal to control the client terminal to render the questionnaire; Receiving the questionnaire audio recorded by the customer service of the customer service end according to the questionnaire; The questionnaire audio is sent to the voice call terminal through the communication session.

[0008] In one embodiment, the step of obtaining the questionnaire audio according to the customer information and sending the questionnaire audio to the voice call terminal based on the communication session further includes: Based on the customer information, determine the corresponding questionnaire and identify the content of the questions in the questionnaire; Convert the question content into the questionnaire audio through text-to-speech technology; The questionnaire audio is sent to the voice call terminal through the communication session.

[0009] In one embodiment, the step of receiving the reply audio sent by the voice call terminal and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio includes: Recording the audio of the voice call terminal in real time and identifying pause points in the audio; Determining whether the customer has finished answering based on the customer's pause time and the semantic recognition result; If the customer has finished answering, the time point at which the answer is completed is recorded, and the next audio segment of the questionnaire is played; The reply audio is determined according to the customer's reply, and a questionnaire-answer pair is generated according to the reply audio and the questionnaire audio.

[0010] In one embodiment, the step of determining the reply audio according to the customer's reply, and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio comprises: According to the time point when the questionnaire audio playback ends and the time point when the answer is completed, the audio between the time point when the playback ends and the time point when the answer is completed is intercepted as the reply audio of the questionnaire audio; Generate a questionnaire-answer pair audio from each group of the questionnaire audio and the corresponding answer audio; Each group of the question-answer pair audio is converted into the question-answer pair in text form by using a speech recognition algorithm.

[0011] In one embodiment, the step of determining the reply audio according to the customer's reply, and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio further includes: Using the complete audio recorded from the voice call terminal as the reply audio; According to the question-and-answer start time point recorded in the questionnaire audio and the question-and-answer start time point recorded in the answer audio, the questionnaire audio and the answer audio are spliced ​​to generate a questionnaire-answer pair audio; The audio of the question-answer pair is converted into the question-answer pair in text form by a speech recognition algorithm.

[0012] In one embodiment, after the step of receiving the reply audio sent by the voice call terminal and generating a reply-answer pair according to the reply audio and the questionnaire audio, the following steps are included: Traversing and checking each set of question-answer pairs in the reply-answer pairs, and marking the questions that have not been answered as missing questions; Determine the corresponding questionnaire audio according to the marked missing question, and send the questionnaire audio of the missing question to the voice call terminal based on the communication session; Receive the missing question purpose reply audio sent by the voice call terminal, and update the questionnaire-answer pair according to the missing question purpose questionnaire audio and the missing question purpose reply audio.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a control device for a customer return visit system, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the control method for the customer return visit system as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the control method of the customer return visit system as described above are implemented.

[0015] The present application provides a control method for a customer return visit system. The present application first establishes a communication session with a voice call terminal to reduce waiting time and ensure the real-time and stability of communication. The application accurately obtains the corresponding questionnaire audio according to the customer information and sends it to the customer's voice call terminal through the communication session, thereby simplifying the operation process of the traditional return visit. The reply audio sent by the customer through the voice call terminal is converted into text form through voice recognition technology, thereby improving the accuracy of data collection. A return visit-answer pair is generated according to the reply audio and the questionnaire audio, and the return visit-answer pair is associated with the customer information and saved, thereby realizing the automated processing of the return visit process, reducing manual intervention, and improving the efficiency of the return visit. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A flowchart diagram of a control method for a customer return visit system according to an embodiment of the present invention; Figure 2 A flow chart of the second embodiment of the control method of the customer return visit system of the present application; Figure 3 A flowchart diagram of the third embodiment of the control method of the customer return visit system of the present application; Figure 4 A flowchart diagram of a fourth embodiment of the control method of the customer return visit system of the present application; Figure 5 A flowchart diagram of a fifth embodiment of the control method of the customer return visit system of the present application; Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the control method of the customer return visit system in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] The main solutions of the embodiments of this application are: At present, customer feedback systems are widely used to collect customer feedback on services or products in order to optimize and improve them in a timely manner. In the current customer feedback system, manual customer service initiates a feedback to the customer and asks the customer questions based on the feedback questionnaire. The manual customer service needs to listen carefully or read the customer's answer, and then select the answer that best suits the customer's answer from the preset answer options. Since manual customer service needs to spend time to understand the customer's answer, the customer needs to wait for the manual customer service's selection and confirmation. The feedback process is long, resulting in low feedback efficiency.

[0023] The present application reduces waiting time and ensures the real-time and stability of communication by establishing a communication session with a voice call terminal, accurately obtains the corresponding questionnaire audio according to customer information, and sends it to the customer's voice call terminal through the communication session, thereby simplifying the operational process of traditional return visits. The reply audio sent by the customer through the voice call terminal is converted into text form through voice recognition technology, thereby improving the accuracy of data collection. A reply-answer pair is generated based on the reply audio and the questionnaire audio, and the reply-answer pair is associated with the customer information and saved, thereby realizing the automated processing of the return visit process, reducing manual intervention, and improving the efficiency of return visits.

[0024] It should be noted that the execution subject of this embodiment can be a control device of the customer return visit system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., and this embodiment does not specifically limit this. The following takes the control device of the customer return visit system as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0025] Embodiment 1 Based on this, the present application proposes a control method for a customer return visit system of the first embodiment, please refer to Figure 1 , the control method of the customer return visit system includes: Step S100: establishing a communication session with a voice call terminal corresponding to the customer based on the customer information.

[0026] In the customer return visit system, the purpose of establishing a communication session based on customer information and the customer's corresponding voice call terminal is to establish contact with the customer instantly and effectively, ensure that the return visit information can be accurately conveyed to the customer, and receive customer feedback. This step is the beginning of the return visit process and the basis for ensuring the smooth progress of subsequent steps. Through the communication session, the system can capture customer needs and feedback in real time, and improve the timeliness and accuracy of the return visit.

[0027] In this embodiment, customer information refers to various information related to customers, including but not limited to the customer's name, telephone number, address, purchase history, etc. This information is used to identify the customer and ensure the targeted return visit. Voice call terminal refers to the device used by customers for voice calls, such as mobile phones, landlines, etc. These devices can receive and send voice information and are important tools for establishing communication sessions with customers.

[0028] Optionally, according to the customer's preference and actual situation, select a suitable communication method to establish a conversation with the customer.

[0029] For example, when a mobile phone number is provided in the customer information, a voice call is established with the customer by dialing the number; when the customer provides contact information of other communication software, a voice call can also be established with the customer through other communication software.

[0030] Optionally, step S100 includes: Step S110, determining the corresponding customer information according to the customer return visit process.

[0031] Exemplarily, according to a preset return visit process, customer information related to the return visit is retrieved from a database.

[0032] Step S120: Identify the voice call terminal type corresponding to the customer information to obtain the communication address of the customer.

[0033] In this embodiment, the voice call terminal type refers to the type of device used by the customer to make voice calls, including mobile phones, landline phones, etc. Different types of terminals require different communication protocols and methods. The communication address is the address used to establish a communication connection, including a telephone number and a network address, etc.

[0034] Exemplarily, the format of the telephone number in the customer information is checked, and based on the format, it is determined whether it is a mobile phone or a landline, and the communication address is determined.

[0035] Exemplarily, based on the email address in the customer information, a voice call reservation is made via a video conference link via email.

[0036] Step S130: establishing a session connection with the voice call terminal according to the communication address.

[0037] Exemplarily, a voice call is made according to the customer's phone number through the dialing module to establish a session connection.

[0038] Exemplarily, based on VoIP (Voice over IP) technology, voice signals are transmitted through an IP network. According to the acquired communication address, the network location such as the IP address and port number of the VoIP device is determined, a session request is initiated using the VoIP protocol, and a connection is established with the target VoIP device.

[0039] Step S200: obtaining a questionnaire audio according to the customer information, and sending the questionnaire audio to the voice call terminal based on the communication session.

[0040] Based on the established customer communication session, according to the customer's specific information, select and obtain the questionnaire audio content that is most suitable for the customer, and send these questionnaire audios to the customer's voice call terminal through the communication session to ensure that the customer can receive personalized and relevant follow-up questionnaires, thereby improving the participation of the follow-up and the effectiveness of data collection.

[0041] In this embodiment, the questionnaire audio refers to an audio file in which the questions of the follow-up questionnaire are recorded in voice form, or a questionnaire audio generated by text-to-speech technology based on the questions of the questionnaire.

[0042] Optionally, use data analysis tools to perform cluster analysis on customer information, divide customers into different groups based on factors such as their purchasing behavior, geographic location, demographic information, etc., select or design appropriate questionnaire audio content for each group, and ensure that the questions match the characteristics and needs of the customer group.

[0043] Optionally, design a questionnaire template based on business needs, including questions, options, and formats, select the most appropriate questionnaire template based on the collected customer information, and then adjust it as needed.

[0044] Exemplarily, in a communication session established with a customer, when it is confirmed that the customer is ready to receive the questionnaire, the questionnaire audio starts to be played.

[0045] Optionally, if the customer raises the question of "did not hear clearly" or "did not understand" during the listening process, these keywords are identified and the questionnaire audio of the question is played again.

[0046] Step S300, receiving the reply audio sent by the voice call terminal, and generating a questionnaire-answer pair based on the reply audio and the questionnaire audio.

[0047] In this embodiment, the reply audio is recorded by a voice call terminal, and the customer's answer to the questions in the questionnaire audio exists in the form of audio and needs to be converted or recognized as analyzable data. The questionnaire question-answer pair is structured data formed by matching the customer's answer with the specific questions in the questionnaire. Each question-answer pair contains two parts: the question from the questionnaire audio and the answer from the reply audio.

[0048] As an optional implementation method, the reply audio sent by the customer through the voice call terminal is received in real time, the reply audio is converted into text format using voice recognition technology, the recognized reply text is matched with the original questionnaire audio by comparing question numbers, keywords or semantic content, and based on the matching results, each question and the corresponding reply are combined into a question-answer pair.

[0049] Step S400: associate the question-answer pair with the customer information and save it.

[0050] The collected questionnaire pairs are associated with the corresponding customer information and saved. This ensures that each customer's feedback can be accurately tracked, their needs and preferences can be understood, and the differences between different customer groups can be analyzed. By associating and saving, customer feedback data can be used more effectively and more precise strategies can be formulated.

[0051] In this embodiment, the association preservation refers to establishing a link between the access-answer pair and the corresponding customer information in the database to ensure that the two can be matched and queried with each other. This association can be achieved based on other unique identifiers such as customer ID, telephone number, etc.

[0052] As an optional implementation, a unique identifier in the customer information is determined, and after collecting the question-answer pairs, the question-answer pairs are associated with the corresponding customer information according to the identifier, and the associated data is saved in a database.

[0053] The present embodiment provides a control method for a customer return visit system. The present embodiment first reduces waiting time and ensures the real-time and stability of communication by establishing a communication session with a voice call terminal. The corresponding questionnaire audio is accurately obtained according to the customer information, and is sent to the customer's voice call terminal through the communication session, thereby simplifying the operation process of the traditional return visit. The reply audio sent by the customer through the voice call terminal is converted into text form through voice recognition technology, thereby improving the accuracy of data collection. A return visit-answer pair is generated according to the reply audio and the questionnaire audio, and the return visit-answer pair is associated with the customer information and saved, thereby realizing the automated processing of the return visit process, reducing manual intervention, and improving the efficiency of the return visit.

[0054] Based on the first embodiment, the second embodiment of the present application proposes a control method for a customer return visit system, referring to Figure 2 , step S200 includes: Step S210: Based on the customer information, the corresponding questionnaire is sent to the client end to control the client end to render the questionnaire.

[0055] Based on the collected customer information, the corresponding questionnaire is sent to the customer service end, and the customer service end is instructed to display the questionnaire so that the customer service end can ask questions based on the content of the questionnaire.

[0056] In this embodiment, the customer service end refers to a software interface or tool used by human customer service to communicate with customers, receive customer requests, view customer information, handle customer issues, and send and receive questionnaires and other tasks.

[0057] As an optional implementation, a corresponding questionnaire template is selected based on the collected customer information, and the questionnaire is sent to the customer service end, and the customer service end is controlled to display the questionnaire so that the customer service can ask questions to the customer based on the content of the questionnaire.

[0058] Step S220, receiving the questionnaire audio recorded by the customer service of the customer service end according to the questionnaire.

[0059] In this embodiment, the questionnaire audio refers to an audio file recorded by the customer service staff asking questions to the customer based on the content of the questionnaire.

[0060] As an optional implementation, the client receives the questionnaire audio recorded by the customer service according to the order and questions of the questionnaire, and checks the audio quality to ensure that the audio is clear. If the audio is not clear, the client is notified to re-record.

[0061] Step S230: sending the questionnaire audio to the voice call terminal through the communication session.

[0062] The recorded questionnaire audio is sent directly to the customer at the voice call terminal through the ongoing communication session, ensuring that the audio content of the questionnaire can be conveyed to the customer instantly and accurately, thereby improving communication efficiency.

[0063] Exemplarily, the questionnaire audio is sent to the client at the voice call terminal through the audio transmission function of the communication session.

[0064] The present embodiment provides a control method for a customer return visit system. The present embodiment first screens and matches the questionnaire that best suits the customer through customer information to ensure the pertinence and effectiveness of the questionnaire, sends the questionnaire to the customer service end, controls the customer service end to render the questionnaire, enables the customer service personnel to intuitively see the content of the questionnaire, prepares for subsequent recording work, and instantly sends the recorded questionnaire audio to the customer at the voice call terminal through a communication session, thereby improving the efficiency of communication.

[0065] Based on the first embodiment, the third embodiment of the present application proposes a control method for a customer return visit system, referring to Figure 3 , step S200 further includes: Step S240, based on the customer information, determine the corresponding questionnaire and identify the content of the questions in the questionnaire.

[0066] Based on the customer information provided, the corresponding questionnaire is accurately matched and determined to ensure the pertinence of the questionnaire, and then all the questions contained in the questionnaire are accurately identified. By identifying the questions in the questionnaire, basic data is provided for subsequent text-to-speech processing.

[0067] For example, a customer profile is constructed based on customer information, including key features such as the customer's age, gender, occupation, and purchase history. A machine learning algorithm is used to match the customer profile with a preset questionnaire library to find the questionnaire that best suits the customer. All questions in the questionnaire are extracted by parsing the questionnaire file, and the questions are classified and organized.

[0068] Step S250, converting the question content into the questionnaire audio through text-to-speech technology.

[0069] By using text-to-speech technology, the questions in the questionnaire are converted from text to audio format, and questionnaire audio is generated so that the questionnaire can be presented to customers via voice.

[0070] In this embodiment, text-to-speech (TTS) technology is an artificial intelligence technology that can convert text information stored, edited and displayed in a computer into audible voice information.

[0071] Optionally, choose a suitable TTS engine according to your needs, including Google Text-to-Speech, Amazon Polly, Microsoft Azure Text-to-Speech, etc. These engines provide different voice styles, speaking speeds, intonations and other parameters, which can be adjusted according to the characteristics of the questionnaire and the target customer group.

[0072] Exemplarily, according to the type of questionnaire, the voice style, speaking speed, intonation, volume and other parameters of the TTS engine are configured, the identified question content is arranged in the order of the questionnaire and input into the TTS engine, and the questionnaire audio is generated according to the configured parameters.

[0073] Step S260: sending the questionnaire audio to the voice call terminal through the communication session.

[0074] The questionnaire audio generated by text-to-speech technology is sent to the user's voice call terminal through an established communication session, ensuring that the user can hear the questionnaire questions and respond immediately, enhancing the real-time nature of voice interaction and improving the efficiency of questionnaire collection and data analysis.

[0075] Exemplarily, the questionnaire audio is sent to the client at the voice call terminal through the audio transmission function of the communication session.

[0076] This embodiment provides a control method for a customer return visit system. This embodiment first uses customer information to screen and match the questionnaire that best suits the customer to ensure the pertinence and effectiveness of the questionnaire. It uses text-to-speech technology to convert the content of the questions in the questionnaire into an audio format, and sends the questionnaire audio to the user's voice call terminal in real time through a communication session, thereby improving the efficiency and accuracy of questionnaire collection.

[0077] Based on the first embodiment, the fourth embodiment of the present application proposes a control method for a customer return visit system, referring to Figure 4 , step S300 includes: Step S310, recording the audio of the voice call terminal in real time, and identifying pause points in the audio.

[0078] In this embodiment, audio recording refers to the process of capturing and saving sound signals through a device, and recording the voice content of the customer's reply at the voice call terminal. The pause point is the time point in the audio signal when the sound intensity suddenly decreases or stops completely, and is used as a mark to segment the continuous voice signal.

[0079] As an optional implementation, the call audio is recorded in real time using the built-in microphone of the voice call terminal, the recorded audio signal is analyzed using an audio processing algorithm, and the pause points in the audio are identified by detecting features such as changes in sound intensity and the length of silent segments.

[0080] Optionally, a large amount of annotated speech data is used to train a machine learning model so that it can accurately identify pauses in speech. Various features, including spectral features, energy features, fundamental frequency features, etc., are extracted from the recorded audio as input to the machine learning model, and a prediction result of whether each time point is a pause point is output.

[0081] Optionally, a threshold value for the length of a silence segment is set according to the characteristics of the speech signal, and when the length of the silence segment exceeds the threshold value, it is identified as a pause point.

[0082] Step S320: Determine whether the customer has finished answering based on the customer's pause time and the semantic recognition result.

[0083] In this embodiment, the semantic recognition result is obtained by converting the customer's voice into text using speech recognition technology and then performing semantic analysis on the text content, including recognized keywords, phrases, sentence structures and the meanings they express.

[0084] Exemplarily, a pause time threshold is set. When the identified pause time exceeds the threshold, the semantic recognition result is analyzed to determine whether the answer content is complete. If the answer content contains all the information required by the question and the semantics are clear, it is considered that the customer has completed the answer.

[0085] Optionally, it is determined whether the customer has finished answering based on the customer's key operation. If the customer pauses and then presses a key to indicate that the customer has finished answering, it can be considered that the customer has completed the answer.

[0086] Step S330: If the customer has finished answering, the time point when the answer is completed is recorded, and the next audio segment of the questionnaire is played.

[0087] After confirming that the customer has finished answering the current questionnaire questions, this time point is recorded and the next questionnaire audio is automatically played, ensuring the continuity and fluency of the questionnaire, helping the system to accurately track the answer time for each question, and providing important information for subsequent data analysis and processing.

[0088] In this embodiment, the time point of completion of answering is the specific moment when the customer completes answering the current questionnaire question, which is recorded in the form of a timestamp.

[0089] Step S340, determining the reply audio according to the customer's reply, and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio.

[0090] After the customer completes the questionnaire, the corresponding response audio is determined based on the customer's response content, and the customer's response audio is combined with the corresponding questionnaire audio to generate a complete questionnaire-answer pair.

[0091] As an optional implementation, the customer's response audio is matched with each question in the questionnaire to ensure that each response corresponds to the correct question, and audio processing technology is used to ensure that the response audio and the questionnaire audio are consistent in time. The matched questionnaire audio and response audio are matched with the matched questionnaire audio and response audio.

[0092] Optionally, audio processing technology is used to extract key features in the questionnaire audio and the reply audio, the similarity between the reply audio and each segment of the questionnaire audio is calculated, similar parts are found for alignment, and based on the similarity calculation results, an optimization algorithm is used to further optimize the alignment results.

[0093] Optionally, the questionnaire audio and the reply audio are converted into text form respectively, and the reply text is aligned with the questionnaire text using a text alignment algorithm based on the text content.

[0094] Optionally, step S340 includes: Step S341, based on the time point when the questionnaire audio playback ends and the time point when the answer is completed, the audio between the time point when the playback ends and the time point when the answer is completed is intercepted as the reply audio to the questionnaire audio.

[0095] In this embodiment, the reply audio is the voice reply issued by the customer between the time when the questionnaire audio playback ends and the time when the answer is completed, which is intercepted as the reply to the question.

[0096] Exemplarily, when the system plays the questionnaire audio, it records the start and end timestamps of each question, monitors and records the start and end timestamps of the customer's answer, and based on the recorded timestamps, captures the audio segment between the end time of the questionnaire audio playback and the completion time of the answer as the reply audio.

[0097] Step S342, generating a questionnaire-answer pair audio from each group of the questionnaire audio and the corresponding answer audio.

[0098] Step S343: converting the audio of each group of the question-answer pairs into text form through a speech recognition algorithm.

[0099] Optionally, step S340 further includes: Step S344: Use the complete audio recorded from the voice call terminal as the reply audio.

[0100] Step S345, according to the question and answer start time point recorded in the questionnaire audio and the question and answer start time point recorded in the answer audio, the questionnaire audio and the answer audio are spliced ​​to generate a questionnaire-answer pair audio.

[0101] In this embodiment, the question-and-answer start time point in the questionnaire audio is the time point when the first question is played and waiting for the customer to answer, and in the reply audio is the time point when the customer starts to answer the first question.

[0102] Exemplarily, when playing the questionnaire audio and recording the answer audio, the timestamp of the start of the question and answer is recorded at the same time, and audio editing software is used to splice them together according to the recorded timestamps as the questionnaire-answer pair audio.

[0103] Step S346: Convert the audio of the question-answer pair into text form through a speech recognition algorithm.

[0104] The present embodiment provides a control method for a customer return visit system. The present embodiment firstly performs real-time audio recording of a voice call terminal and identifies pause points in the audio, thereby ensuring instant capture of audio data. Based on the pause time and semantic recognition results, it is determined whether the customer has finished answering, and the customer's answer status is accurately judged. When the customer has finished answering, the time point is recorded and the next questionnaire audio is played, thereby providing an accurate timestamp for generating a questionnaire-answer pair, thereby ensuring the continuity of the question-answer process. The questionnaire audio and the customer's answer audio are accurately intercepted and converted into a text-based questionnaire-answer pair, thereby ensuring the accuracy of the question-answer content.

[0105] Based on the first embodiment, the fifth embodiment of the present application proposes a control method for a customer return visit system, referring to Figure 5 , after step S300, the following steps are included: Step S500, traverse and check each set of question-answer pairs in the reply-answer pairs, and mark the questions that have not been answered as missing questions.

[0106] Exemplarily, each question-answer pair in the response-answer pair is traversed to check whether the answer audio in each question-answer pair exists or is empty. If the answer audio does not exist or is empty, it is considered that the question has not been answered, and the unanswered question is marked as a missing question, and its question number or question content is recorded.

[0107] Step S600: Determine the corresponding questionnaire audio according to the marked missing question, and send the missing question questionnaire audio to the voice call terminal based on the communication session.

[0108] Exemplarily, according to the marked missing questions, the corresponding question audio is retrieved, and the missing question questionnaire audio is resent to the voice call terminal through the communication session.

[0109] Step S700, receiving the missing question purpose reply audio sent by the voice call terminal, and updating the questionnaire-answer pair according to the missing question purpose questionnaire audio and the missing question purpose reply audio.

[0110] Exemplarily, through a communication session, an audio reply to a missing question sent by a voice call terminal is received, and it is checked whether the received reply audio is complete and whether it corresponds to the missing question sent, and the received reply audio is combined with the corresponding missing question questionnaire audio into a new question-answer pair, and updated to the question-answer pair.

[0111] Optionally, for customers who have not yet responded to the questionnaire audio, a call connection is established with an idle customer service end, the customer service end is controlled to display the text corresponding to the unanswered questionnaire audio, and the customer's information is sent to the customer service end through the call connection so that the customer service can communicate further.

[0112] This embodiment provides a control method for a customer follow-up system. This embodiment first traverses and checks the follow-up answer pairs, marks the unanswered questions, resends the questionnaire audio of these missing questions to the voice call terminal to obtain complete replies, and updates the follow-up answer pairs according to the received reply audio to ensure that all questions are answered, thereby improving the integrity of the follow-up answers and the data quality.

[0113] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the control method of the customer return visit system of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0114] The present application provides a control device for a customer return visit system, the control device for the customer return visit system comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the control method for the customer return visit system in the above-mentioned embodiment one.

[0115] Reference below Figure 6 , which shows a schematic diagram of the structure of a control device suitable for implementing a customer return visit system of an embodiment of the present application. The control device of the customer return visit system in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The control device of the customer return visit system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0116] like Figure 6As shown, the control device of the customer return visit system may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in a read-only memory (ROM: Read Only Memory) 1002 or the program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the control device of the customer return visit system are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the control device of the customer return visit system to communicate with other devices wirelessly or by wire to exchange data. Although the control device of the customer return visit system with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0117] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0118] The control device of the customer return visit system provided by the present application adopts the control method of the customer return visit system in the above embodiment, which can solve the technical problem of how to improve the efficiency of customer return visit. Compared with the prior art, the beneficial effects of the control device of the customer return visit system provided by the present application are the same as the beneficial effects of the control method of the customer return visit system provided by the above embodiment, and other technical features in the control device of the customer return visit system are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0119] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0120] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0121] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the control method of the customer return visit system in the above-mentioned embodiment.

[0122] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0123] The computer-readable storage medium may be included in the control device of the customer return visit system; or may exist independently without being assembled into the control device of the customer return visit system.

[0124] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the control device of the customer return visit system, the control device of the customer return visit system can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0125] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0127] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the control method of the above-mentioned customer return visit system, and can solve the technical problem of how to improve the efficiency of customer return visits. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the control method of the customer return visit system provided in the above-mentioned embodiment, and will not be repeated here.

[0128] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A control method for a customer return visit system, characterized in that: The control method of the customer return visit system includes: Establishing a communication session with a voice call terminal corresponding to the customer based on the customer information; Acquire a questionnaire audio according to the customer information, and send the questionnaire audio to the voice call terminal based on the communication session; receiving a reply audio sent by the voice call terminal, and generating a reply-answer pair according to the reply audio and the questionnaire audio; The question-answer pair is associated with the customer information and stored.

2. The control method of the customer return visit system according to claim 1, characterized in that: The step of establishing a communication session with a voice call terminal corresponding to the customer based on the customer information includes: Determine the corresponding customer information according to the customer return visit process; Identify the type of voice call terminal corresponding to the customer information to obtain the communication address of the customer; A session connection with the voice call terminal is established according to the communication address.

3. The control method of the customer return visit system according to claim 1, characterized in that: The step of obtaining the questionnaire audio according to the customer information and sending the questionnaire audio to the voice call terminal based on the communication session includes: Based on the customer information, the corresponding questionnaire is sent to the client terminal to control the client terminal to render the questionnaire; Receiving the questionnaire audio recorded by the customer service of the customer service end according to the questionnaire; The questionnaire audio is sent to the voice call terminal through the communication session.

4. The control method of the customer return visit system according to claim 1, characterized in that: The step of obtaining the questionnaire audio according to the customer information and sending the questionnaire audio to the voice call terminal based on the communication session also includes: Based on the customer information, determine the corresponding questionnaire and identify the content of the questions in the questionnaire; Convert the question content into the questionnaire audio through text-to-speech technology; The questionnaire audio is sent to the voice call terminal through the communication session.

5. The control method of the customer return visit system according to claim 1, characterized in that: The step of receiving the reply audio sent by the voice call terminal and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio comprises: Recording the audio of the voice call terminal in real time and identifying pause points in the audio; Determining whether the customer has finished answering based on the customer's pause time and the semantic recognition result; If the customer has finished answering, the time point at which the answer is completed is recorded, and the next audio segment of the questionnaire is played; The reply audio is determined according to the customer's reply, and a questionnaire-answer pair is generated according to the reply audio and the questionnaire audio.

6. The control method of the customer return visit system according to claim 5, characterized in that: The step of determining the reply audio according to the customer's reply, and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio comprises: According to the time point when the questionnaire audio playback ends and the time point when the answer is completed, the audio between the time point when the playback ends and the time point when the answer is completed is intercepted as the reply audio of the questionnaire audio; Generate a questionnaire-answer pair audio from each group of the questionnaire audio and the corresponding answer audio; Each group of the question-answer pair audio is converted into the question-answer pair in text form by using a speech recognition algorithm.

7. The control method of the customer return visit system according to claim 5, characterized in that: The step of determining the reply audio according to the customer's reply, and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio also includes: Using the complete audio recorded from the voice call terminal as the reply audio; According to the question-and-answer start time point recorded in the questionnaire audio and the question-and-answer start time point recorded in the answer audio, the questionnaire audio and the answer audio are spliced ​​to generate a questionnaire-answer pair audio; The audio of the question-answer pair is converted into the question-answer pair in text form by a speech recognition algorithm.

8. The control method of the customer return visit system according to claim 1, characterized in that: After the step of receiving the reply audio sent by the voice call terminal and generating a questionnaire-answer pair according to the reply audio and the questionnaire audio, the method further comprises: Traversing and checking each set of question-answer pairs in the reply-answer pairs, and marking the questions that have not been answered as missing questions; Determine the corresponding questionnaire audio according to the marked missing question, and send the questionnaire audio of the missing question to the voice call terminal based on the communication session; Receive the missing question purpose reply audio sent by the voice call terminal, and update the questionnaire-answer pair according to the missing question purpose questionnaire audio and the missing question purpose reply audio.

9. A control device for a customer return visit system, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the control method of the customer return visit system according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the control method of the customer return visit system according to any one of claims 1 to 8 are implemented.

Images