DTMF transmission mode management method and cloud call platform

Abstract

The invention discloses a DTMF transmission mode management method and a cloud call platform. The method comprises the following steps: after a session is established between a calling terminal and a called terminal, obtaining a first voice sent by the called terminal to the calling terminal; a first DTMF key event transmitted by the calling terminal to the called terminal through a pre-negotiated DTMF transmission mode is obtained, second voice and first voice feedback time fed back by the called terminal to the calling terminal according to the first DTMF key event are obtained, and the first DTMF key event at least comprises first key triggering time; and executing corresponding management operation on the DTMF transmission mode according to the size relationship between the first key triggering time and the first voice feedback time and the consistency relationship between the first voice and the second voice. The technical problem that the recognition accuracy of the DTMF key event is low due to the fact that the DTMF transmission mode negotiated between the calling terminal and the called terminal is inconsistent with the line transmission mode actually provided by an operator is solved.

Description

Technical Field

[0001] The present application relates to the field of voice communication technology, and in particular to a DTMF transmission mode management method and a cloud call platform. Background Art

[0002] In the cloud call platform built on Free SWITCH, Interactive Voice Response (IVR) plays a pivotal role. Its working principle is: through a highly intuitive graphical configuration interface, users are allowed to set up multi-level dialogue nodes (covering various types such as playing audio nodes and transferring skill group nodes) without restrictions, so as to flexibly respond to the personalized customization needs of various complex business processes. Therefore, in the scenario where both parties of the call are connected to the cloud call platform, when the called party is a robot customer service system, and the robot customer service system presets a set of interactive voice response processes that require the caller to interact through keystrokes, the caller can interact with the system by making calls and triggering keys, so that the system can intelligently navigate to the corresponding business processing node or customer service team based on the user's voice answer or keystroke input, which not only significantly improves the user experience satisfaction, but also effectively enhances the enterprise's operational efficiency and service quality.

[0003] However, in a real call environment, although the caller and the called party have already determined the transmission method of DTMF (Dual-tone Multi-Frequency) key signals through signaling negotiation before the communication is started, due to the differences in design and implementation between different communication product manufacturers and the complexity of the operator network environment they rely on, it often happens that the DTMF transmission method determined by the two parties through negotiation is inconsistent with the line transmission method actually provided by the operator, resulting in the DTMF key events being unable to be correctly identified during the transmission process, which in turn affects the smooth progress of the call.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a DTMF transmission mode management method and a cloud call platform to at least solve the technical problem of low recognition accuracy of DTMF key events due to the inconsistency between the DTMF transmission mode negotiated between the calling end and the called end and the line transmission mode actually provided by the operator.

[0006] According to one aspect of an embodiment of the present application, a DTMF transmission mode management method is provided, comprising: after a communication session is successfully established between a calling end and a called end, obtaining a first voice sent by the called end to the calling end, wherein the first voice is used to prompt the calling end with key information to be triggered; obtaining a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission mode, and obtaining a second voice and a first voice feedback time fed back by the called end to the calling end based on the first DTMF key event, wherein the first DTMF key event at least includes: a first key trigger time; according to the size relationship between the first key trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, performing corresponding management operations on the DTMF transmission mode, wherein the management operations include: changing or keeping unchanged.

[0007] Optionally, before obtaining the first voice information sent by the called end to the calling end, the method also includes: obtaining a call request message initiated by the calling end, wherein the call request message includes at least: the telephone number or address of the called end, and the DTMF transmission method supported by the calling end; routing the call request message to the called end according to the number or address of the called end; obtaining a call response message fed back by the called end to the calling end, wherein the call response message is used to indicate that the call request message is in a pending state; after the called end receives the call request message, obtaining a call reception message replied by the called end to the calling end, wherein the call reception message includes at least: the DTMF transmission method supported by the called end; obtaining a confirmation message sent by the calling end to the called end, wherein the confirmation message is used to indicate that the calling end has confirmed that it has received and accepted the call reception message sent by the called end, and the confirmation message includes at least: the DTMF transmission method negotiated by the calling end and the called end.

[0008] Optionally, a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission method is obtained, and a second voice and a first voice feedback time that the called end feeds back to the calling end based on the first DTMF key event are obtained, including: after the calling end performs a corresponding key operation based on the first voice information, the first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission method is obtained, wherein the above-mentioned first DTMF key event also includes: key information triggered by the called end; after the called end receives the first DTMF key event, the second voice and the first voice feedback time that the called end feeds back to the calling end are obtained.

[0009] Optionally, the DTMF transmission mode is managed based on the size relationship between the first button trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, including: determining the time difference between the first button trigger time and the first voice feedback time, and judging the size relationship between the time difference and a preset time threshold; when the time difference is greater than the time threshold, changing the DTMF transmission mode; when the time difference is not greater than the time threshold, judging whether the first voice is consistent with the second voice; when the first voice is consistent with the second voice, changing the DTMF transmission mode; when the first voice is inconsistent with the second voice, keeping the DTMF transmission mode unchanged.

[0010] Optionally, determining whether the first voice and the second voice are consistent includes: using automatic speech recognition technology to perform text recognition on the first voice and the second voice respectively to obtain corresponding first text information and second text information, and determining whether the first text information is consistent with the second text information.

[0011] Optionally, the DTMF transmission mode includes: RFC2833, SIP INFO or INBAND.

[0012] Optionally, after the DTMF transmission mode is changed, the method also includes: re-obtaining a second DTMF key event transmitted by the calling end to the called end through the changed DTMF transmission mode, and obtaining the third voice information and the second voice feedback time fed back by the called end to the calling end based on the second DTMF key event, wherein the second DTMF key event at least includes: the second key trigger time; based on the relationship between the second key trigger time and the second voice feedback time and the consistency relationship between the second voice and the third voice, performing corresponding management operations on the changed DTMF transmission mode; when the management operation is changed, looping the above steps until the management operation remains unchanged.

[0013] According to another aspect of an embodiment of the present application, a cloud call platform is also provided, including: a first acquisition module, used to acquire a first voice sent by the called end to the calling end after a communication session is successfully established between the calling end and the called end, wherein the first voice is used to prompt the calling end with key information to be triggered; a second acquisition module, used to acquire a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission method, and to acquire a second voice and a first voice feedback time fed back by the called end to the calling end based on the first DTMF key event, wherein the first DTMF key event at least includes: a first key trigger time; a management module, used to perform corresponding management operations on the DTMF transmission method based on the size relationship between the first key trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, wherein the management operation includes: changing or keeping unchanged.

[0014] According to another aspect of the embodiments of the present application, a computer program product is further provided. The computer program product includes: a computer program, wherein when the computer program is executed by a processor, the above-mentioned DTMF transmission mode management method is implemented.

[0015] According to another aspect of the embodiments of the present application, an electronic device is provided, which includes: a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-mentioned DTMF transmission mode management method through the computer program.

[0016] In an embodiment of the present application, after a communication session is successfully established between the calling end and the called end, the call cloud platform obtains the first voice sent by the called end to the calling end; obtains the first DTMF key event transmitted by the calling end to the called end through the pre-negotiated dual-tone multi-frequency DTMF transmission mode, and obtains the second voice and the first voice feedback time fed back by the called end to the calling end based on the first DTMF key event, wherein the first DTMF key event at least includes: the first key trigger time; according to the size relationship between the first key trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, the corresponding management operation is performed on the DTMF transmission mode. In other words, the call cloud platform monitors the DTMF key events and voice data transmitted by both the calling and called parties, and determines whether the DTMF transmission mode pre-negotiated by the calling and called ends is consistent with the transmission mode of the actual line of the operator according to the called voice monitoring timeout mechanism and the called voice monitoring timeout mechanism, so as to manage the DTMF transmission mode, ensure that the DTMF key events transmitted by the calling end according to the DTMF transmission mode can be correctly recognized by the called end, and significantly improve the recognition success rate of the DTMF key events. This solves the technical problem of low recognition accuracy of DTMF key events due to the inconsistency between the DTMF transmission mode negotiated between the calling end and the called end and the line transmission mode actually provided by the operator. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 It is a flowchart of an optional DTMF transmission mode management method according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of the structure of an optional cloud call puzzle according to an embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0022] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] In order to better understand the embodiments of the present application, some nouns or terms that appear in the description of the embodiments of the present application are first translated and explained as follows:

[0024] FreeSWITCH: is an open source soft switch platform that aims to provide a high-performance, flexible and scalable communication solution. It supports multiple communication protocols, including SIP (Session Initiation Protocol), RTP (Real-time Transport Protocol) and WebRTC (Web Real-time Transport Communications), making it an ideal choice for building voice, video and messaging applications. FreeSWITCH can be applied to VoIP (Voice over Internet Protocol) systems, call centers, conference systems, WebRTC applications and other scenarios.

[0025] Dual-Tone Multi-Frequency (DTMF) signal: is a signaling technology used in telephone systems. It is mainly used to transmit numbers or control commands through audio signals. When the user presses a button on the telephone keypad, the phone will simultaneously generate two audio signals of specific frequencies, one from the high-frequency group and the other from the low-frequency group. Different frequency combinations are used to represent different numbers or function keys.

[0026] Event Socket Library (ESL): It is a library provided by FreeSWITCH for interacting with FreeSWITCH. It controls FreeSWITCH and monitors events through TCP socket connections, and provides a high-performance event transmission mechanism that allows external applications to interact directly with FreeSWITCH through TCP (Transmission Control Protocol) or SSL (Secure Sockets Layer) connections, obtain real-time notifications of call events (such as DTMF key presses, call status changes, etc.), and can send control commands to dynamically manage or manipulate ongoing call sessions.

[0027] Automatic Speech Recognition (ASR): is a technology that can convert human speech into text or commands that can be understood by computers. It enables computers to "understand" human speech and accurately convert speech information into text output. It mainly consists of preprocessing, feature extraction, language model, acoustic model and recognition coding.

[0028] Example 1

[0029] According to an embodiment of the present application, a DTMF transmission mode management method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 is a flow chart of a DTMF transmission mode management method provided according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps S102-S106, wherein:

[0031] Step S102: after a communication session is successfully established between the calling end and the called end, a first voice sent by the called end to the calling end is obtained.

[0032] In the technical solution provided in the above step S102, a communication session is pre-established between the calling end (the party initiating the call) and the called end (the party receiving the call, such as a robot customer service system) to ensure that both parties can transmit voice data through the network. When the calling end and the called end start two-way voice communication, the cloud call platform can manage the entire call session, including: call routing, media processing (such as voice encoding and decoding, audio mixing), call control (such as establishing, maintaining, and terminating sessions) and additional services (such as IVR, call records, call quality monitoring), etc.

[0033] Specifically, when a communication session is successfully established between the calling end and the called end, when the calling end initiates a call request, the cloud call platform can route the call request to the called end. Then the calling end can first feedback the first voice to the calling end according to the preset interactive voice response process, where the first voice is a voice message used to guide or prompt the calling end to perform key operations, such as an IVR voice prompt such as "Please press 1 to continue, press 2 to return to the main menu".

[0034] Step S104, obtaining a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission mode, and obtaining a second voice and a first voice feedback time fed back by the called end to the calling end according to the first DTMF key event.

[0035] In the technical solution provided in the above step S104, after receiving the first voice sent by the called end, the calling end can perform corresponding key operations according to the prompt information of the first voice, and the first DTMF key event generated by the key operation can be encoded and sent to the called end through the DTMF transmission method pre-negotiated by the calling end and the called end. In this process, the cloud call platform can monitor the first DTMF key event sent by the calling end through the ESL (Event Socket Library) mechanism to obtain the first key trigger time of the calling end performing the key operation.

[0036] When the called end receives the first DTMF key event from the calling end, it can identify the signal according to the negotiated DTMF transmission method, wherein the identification process may involve signal decoding, noise filtering, spectrum analysis, etc. Then, the called end can again feedback the second voice to the calling end based on the recognition result and the preset interactive voice response process, wherein the second voice is also a voice message used to guide or prompt the calling end to perform key operations. At the same time, the cloud call platform can record the first voice feedback time when the called end feeds back the second voice to the calling end, that is, the start time when the called end sends the second voice.

[0037] Step S106, performing corresponding management operations on the DTMF transmission mode according to the relationship between the first button triggering time and the first voice feedback time and the consistency relationship between the first voice and the second voice, wherein the management operations include: changing or maintaining.

[0038] In the technical solution provided in the above step S106, the cloud call management platform can dynamically adjust the DTMF transmission mode used by the calling end to transmit the DTMF key event based on the relationship between the monitored first button trigger time and the first voice feedback time, and the consistency relationship between the first voice and the second voice, so as to avoid the DTMF transmission mode negotiated and determined by the calling and called ends being inconsistent with the DTMF transmission mode of the line actually provided by the operator, thereby causing the DTMF key event to be unable to be correctly identified.

[0039] In the technical solution provided by the above steps S102-S106, it can be learned that in the embodiment of the present application, the call cloud platform monitors the DTMF key events and voice data transmitted by the calling and called parties, and judges whether the DTMF transmission mode pre-negotiated by the calling and called parties is consistent with the transmission mode of the operator's actual line according to the called voice monitoring timeout mechanism and the called voice monitoring timeout mechanism, so as to manage the DTMF transmission mode, ensure that the DTMF key events transmitted by the calling end according to the DTMF transmission mode can be correctly recognized by the called end, and significantly improve the recognition success rate of the DTMF key events. In addition, the technical problem of low recognition accuracy of DTMF key events caused by the inconsistency between the DTMF transmission mode negotiated between the calling end and the called end and the line transmission mode actually provided by the operator is solved.

[0040] The specific implementation steps of the DTMF transmission mode management method are described in detail below in conjunction with the specific implementation process.

[0041] As a cloud-based service, the cloud call platform can be an operator's cloud communication service, an enterprise-level contact center solution, or any other cloud-based telephone system.

[0042] Therefore, when the calling party (such as an individual user, enterprise user or other entity) uses a telephone, a VoIP client or any other telephone communication device to initiate a call to request communication with a specific called party, the cloud call platform can provide functions such as call routing, media processing (such as voice encoding and decoding, audio mixing), call control (such as establishing, maintaining, and terminating sessions) and additional services (such as IVR, call recording, and call quality monitoring).

[0043] The called party (such as an individual user, an enterprise IVR system, a customer service representative, or other entity) can choose to answer or reject the call after receiving the call request. Specifically, in an enterprise scenario, the called party may be a complex IVR system that is responsible for processing automated voice services, including speech synthesis, speech recognition, key processing, etc.

[0044] It should be noted that in some scenarios, the cloud call platform includes all the functions of the called party, that is, the cloud call platform and the called party are actually the same system, and no additional signaling or media interaction is required through the network. For example, when the called party is a cloud-based IVR system or customer service robot, the cloud call platform itself has the capabilities of IVR logic processing, speech synthesis, speech recognition, key signal recognition and processing. In some scenarios, the cloud call platform only includes some functions of the called party, such as IVR process management and simple voice processing, but more complex business logic or specific voice interaction functions may be provided by external called party services. For example, the cloud call platform directly handles basic call routing and DTMF signal recognition, but the IVR voice response and the execution of complex business processes are completed by the integrated third-party applications or services. In this mode, the cloud call platform and the called party service interact through API (Application Programming Interface) or specific protocols. In addition, the cloud call platform and the called party can also be completely independent systems, where the cloud call platform is responsible for call establishment, control and media transmission; while the called party may be a locally deployed IVR system, a customer service representative's telephone terminal or other communication terminal. In this case, the cloud call platform needs to interact with the called party through the network for signaling and media to ensure the smooth progress of the call.

[0045] Therefore, in the technical solution provided in the above step S102, the cloud call platform can monitor the establishment of a communication session between the calling end and the called end according to the following process, including:

[0046] Step 1: Get the call request message initiated by the calling party. The call request message may be an INVITE message of SIP, and the call request message includes at least: the address of the calling party, the address or number of the called party, and an SDP description, and the SDP description includes not only the media type and codec supported by the calling party, but also the DTMF transmission mode supported by the calling party.

[0047] Step 2: Route the call request message to the called party according to the called party's number or address. That is, the cloud call platform can route the call request to the called party through the corresponding network (such as the public switched telephone network PSTN, VoIP network) according to the called party's address or phone number in the call request.

[0048] Step 3: Obtain a call response message fed back by the called end to the calling end, wherein the call response message may be a message such as SIP 180Ringing, and the call response message is used to indicate that the call request message is in a pending state (the phone has rung or is processing a call).

[0049] Step 4: After the called party receives the call request message (that is, after the called party answers the call), the called party can parse the SDP content, select one or more compatible DTMF transmission methods according to its own capabilities or configurations, and reply to the called party with a call reception message. Therefore, the cloud call platform can monitor the call reception message replied by the called party to the calling party. Among them, the call reception message can be a 200OK response message of SIP, which is used to indicate that the called party confirms to accept the call. The call reception message will also carry the SDP description of the called party itself, which will also contain information such as the media type, codec, DTMF transmission method, etc. supported by the called party.

[0050] Step 5: After receiving the call reception message from the called party, the calling party parses the SDP description of the called party again, confirms the communication parameters agreed by both parties, and then sends a confirmation message to the called party. Therefore, the cloud call platform can monitor the confirmation message sent by the calling party to the called party. The confirmation message can be an ACK message to confirm the receipt and acceptance of the call reception message sent by the called party, and the confirmation message includes at least the call parameters negotiated by both parties, including but not limited to: media type, codec, DTMF transmission method, etc.

[0051] At this point, the signaling negotiation between the calling party and the called party is completed, and the calling party and the called party can formally establish a communication session based on the negotiation results. During the session, both parties will transmit audio and video data according to the negotiated communication parameters. It should be noted that in the above process, the negotiation of the DTMF transmission method between the calling party and the called party is usually completed in the SDP (Session Description Protocol) of the SIP signaling, where SDP is a part of the SIP signaling, which describes the media type (such as voice, video), codec format, transmission protocol, connection information, etc. of the session, and is an indispensable information exchange mechanism when establishing a multimedia session.

[0052] Specifically, the methods for monitoring DTMF data in SIP include: RFC2833, SIPINFO or INBAND, where:

[0053] (1) SIPINFO is an out-of-band detection method that transmits DTMF data through the SIP signaling channel. There is no unified implementation standard. Currently, Cisco SIPINFO is used as the standard to identify DTMF keys through the Signal field in the SIPINFO packet. Note that when the DTMF key is "*", different standards implement the corresponding "signal = *" or "signal = 10". In addition, the advantage of SIPINFO is that it does not affect the transmission of RTP data packets, but it may cause asynchrony.

[0054] (2) RFC2833 is an in-band detection method that transmits DTMF key events through RTP. The RFC2833 data packet is identified by a special RtpPayloadType, namely TeleponeEvent. The same DTMF key usually corresponds to multiple RTP packets. The timestamps of these RTP packets are the same, which can be used as a basis for identifying the same key. The end flag of the last RTP packet is set to 1 to indicate the end of the DTMF data.

[0055] (3) INBAND is an in-band detection method, and it is mixed with ordinary RTP voice packets for transmission. The only way to perform INBAND DTMF detection is to extract the RTP data packet for spectrum analysis. After spectrum analysis, the high and low frequencies are obtained, and then the corresponding keys are obtained by looking up the table. The algorithm for spectrum analysis is generally the Goertzel algorithm (also known as the Goertzel algorithm).

[0056] Furthermore, after the communication session between the calling party and the called party is established, the cloud call platform monitors the information transmitted between the calling party and the called party according to the ESL (Event Socket Library) mechanism. First, the called party will feedback the first voice to the calling party according to its pre-set interactive voice response process, wherein the first voice is used to prompt the calling party with the key information to be triggered.

[0057] Next, after the calling end performs the corresponding key operation according to the prompt information of the first voice, the cloud call platform can monitor the first DTMF key event transmitted by the calling end to the called end through the pre-negotiated DTMF transmission method, wherein the above-mentioned first DTMF key event includes: the key information triggered by the calling end, the first key trigger time, and the first key trigger time refers to the timestamp detected and recorded by the cloud call platform when the calling party presses a key on the telephone keypad, such as the precise time record of the selection operation made by the calling end in the IVR process or the time when the number is entered.

[0058] After the called end receives the first DTMF key event sent by the calling end, the called end can continue to feedback the second voice to the calling end based on the result of parsing the first DTMF key event. Since the calling and called parties transmit audio packets via RTP, and the transmitted audio packets carry a timestamp, this timestamp is set according to the standard of the RTP protocol, which reflects the sampling time of the audio data. Therefore, the cloud call platform can monitor the RTP packets fed back by the called end to obtain the specific second voice and the timestamp of the RTP packet (i.e., the first voice feedback time).

[0059] As an optional implementation, in the technical solution provided in the above step S106, the cloud call management platform obtains the size relationship between the first button trigger time and the first voice feedback time, the first voice and the second voice through the above steps, and manages the DTMF transmission mode, including:

[0060] Step S1061, determine the time difference between the first button triggering time and the first voice feedback time, and judge the relationship between the time difference and the preset time threshold. Wherein, the above-mentioned time threshold is set according to the expected DTMF button event recognition and processing time under normal circumstances, which is usually about 1.5 seconds. Therefore, if the time difference is greater than the time threshold, it indicates that the called terminal fails to recognize the first DTMF button event within the normal time, and step S1062 is executed at this time; otherwise, step S1063 is executed.

[0061] Step S1062, changing the DTMF transmission mode.

[0062] Step S1063, determine whether the first voice is consistent with the second voice. This is because the voice information sent by the called end will change according to the DTMF key event fed back by the calling end. Therefore, the cloud call platform can determine whether the called end correctly recognizes the first DTMF key event based on whether the first voice and the second voice are consistent. If they are consistent, it means that the called end did not correctly recognize the first DTMF key event, and the cloud call platform executes step S1062; otherwise, execute step S1064.

[0063] Step S1064, keep the current DTMF transmission mode unchanged.

[0064] Specifically, the above-mentioned change of the DTMF transmission mode is to change the currently used DTMF transmission mode to another DTMF transmission mode other than the current DTMF transmission mode, and the specific DTMF transmission mode to be changed can be set according to the actual application scenario.

[0065] For example, when the DTMF transmission mode currently negotiated by the calling and called parties is RFC2833, if the DTMF transmission mode is inconsistent with the DTMF transmission mode of the line actually provided by the operator, resulting in the called party being unable to parse the DTMF key events within the specified time period or unable to correctly parse the DTMF key events, at this time, the cloud call management platform can trigger a compensation mechanism to dynamically adjust the currently used DTMF transmission mode to SIP INFO or INBAND.

[0066] Optionally, in the technical solution provided in the above step S1063, the cloud call platform can determine whether the first voice and the second voice are consistent according to the following method, including: using automatic speech recognition technology to perform text recognition on the first voice and the second voice respectively, to obtain corresponding first text information and second text information, and to determine whether the first text information and the second text information are consistent.

[0067] Specifically, the process of converting voice information into text information through automatic speech recognition technology is as follows:

[0068] First, the speech information is preprocessed, including but not limited to: noise reduction, pre-emphasis, framing and windowing, so as to reduce the impact of environmental noise, enhance the recognizability of the speech signal, and convert it into a format suitable for subsequent processing.

[0069] Next, the preprocessed speech information is converted into a feature vector sequence. Specifically, this step can use representation methods such as Mel Frequency Cepstral Coefficients (MFCC) or spectrogram to convert the sound waveform into a mathematical representation that describes its sound quality, frequency distribution and time-varying information.

[0070] Then, the pre-trained acoustic model is used to identify the phoneme or small unit of speech corresponding to each feature vector in the feature vector sequence. Among them, the acoustic model is usually a neural network model based on deep learning, such as a recurrent neural network (RNN), a long short-term memory network (LSTM) or a Transformer model, which is trained to identify specific speech units from feature vectors.

[0071] Finally, the speech units (phonemes) corresponding to each feature vector are sequentially integrated into sentence text, and the integrated sentence text is post-processed, such as spelling correction, grammar correction, etc., to improve the accuracy and readability of the final output.

[0072] Furthermore, after the cloud call platform dynamically adjusts the DTMF transmission mode negotiated by the caller and the called party, it can execute steps S104-S106 again, thereby ensuring the accuracy and timeliness of the recognition and response of the DTMF signal and maintaining a high-quality call experience.

[0073] Specifically, the cloud call platform will re-acquire the second DTMF key event transmitted by the calling end to the called end through the changed DTMF transmission mode, and obtain the third voice information and the second voice feedback time fed back by the called end to the calling end based on the second DTMF key event, wherein the second DTMF key event also includes: the second key trigger time; then, the cloud call platform can perform corresponding management operations on the changed DTMF transmission mode based on the relationship between the second key trigger time and the second voice feedback time and the consistency relationship between the second voice and the third voice.

[0074] When the management operation is change, the cloud call management platform can repeat the above steps until the management operation is maintain.

[0075] Through the above-mentioned DTMF transmission mode management method, the cloud call platform can continuously monitor and quickly identify DTMF signal transmission problems under changeable network conditions, and take corresponding remedial measures, so as to provide stable and reliable DTMF signal recognition services under different network conditions, and provide users with a better communication experience. For example, if it is found that the recognition rate of a certain transmission mode is low under a specific network environment, it can be switched to another mode immediately to avoid continuous communication failures. At the same time, the above-mentioned DTMF transmission mode management method reduces call failures caused by DTMF signal recognition problems, and avoids additional costs and user dissatisfaction caused by redialing, repeated instructions or manual intervention. And the technical problem of low recognition accuracy of DTMF key events due to the inconsistency between the DTMF transmission mode negotiated between the calling end and the called end and the line transmission mode actually provided by the operator is solved.

[0076] Example 2

[0077] According to an embodiment of the present application, a cloud call platform for implementing the DTMF transmission mode management method in Example 1 is also provided. Figure 2 As shown, the cloud call platform at least includes: a first acquisition module 22, a second acquisition module 24 and a management module 26, wherein:

[0078] A first acquisition module 22, configured to acquire a first voice sent by the called end to the calling end after a communication session is successfully established between the calling end and the called end, wherein the first voice is used to prompt the calling end with key information to be triggered;

[0079] The second acquisition module 24 is used to acquire the first DTMF key event transmitted by the calling end to the called end through the pre-negotiated DTMF transmission mode, and acquire the second voice and the first voice feedback time fed back by the called end to the calling end according to the first DTMF key event, wherein the first DTMF key event at least includes: the first key trigger time;

[0080] The management module 26 is used to perform corresponding management operations on the DTMF transmission mode according to the relationship between the first button trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, wherein the management operation includes: changing or keeping unchanged.

[0081] It should be noted that each module in the cloud call platform in the embodiment of the present application corresponds one by one to each implementation step of the DTMF transmission mode management method in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1, and will not be repeated here.

[0082] Example 3

[0083] According to an embodiment of the present application, a computer program product is further provided. The computer program product includes a computer program. When the computer program is executed by a processor, the DTMF transmission mode management method in Embodiment 1 is implemented.

[0084] According to an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the DTMF transmission mode management method in Example 1 by running the computer program.

[0085] According to an embodiment of the present application, a processor is further provided, which is used to run a computer program, wherein the DTMF transmission mode management method in Example 1 is executed when the computer program is running.

[0086] According to an embodiment of the present application, an electronic device is further provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the DTMF transmission mode management method in Example 1 through the computer program.

[0087] Optionally, the computer program executes the following steps when it is running: after a communication session is successfully established between the calling end and the called end, obtain a first voice sent by the called end to the calling end, wherein the first voice is used to prompt the calling end with key information to be triggered; obtain a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission method, and obtain a second voice and a first voice feedback time fed back by the called end to the calling end based on the first DTMF key event, wherein the first DTMF key event at least includes: a first key trigger time; based on the size relationship between the first key trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, perform corresponding management operations on the DTMF transmission method, wherein the management operations include: changing or keeping unchanged.

[0088] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 FIG. 1 shows a hardware structure block diagram of an electronic device for implementing a DTMF transmission mode management method. Figure 3 As shown, the electronic device 30 may include one or more (302a, 302b, ..., 302n are used to illustrate) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.

[0089] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the electronic device 30. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0090] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the DTMF transmission mode management method in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, realizing the vulnerability detection method of the above-mentioned application. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 304 may further include a memory remotely arranged relative to the processor 302, and these remote memories may be connected to the electronic device 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0091] The transmission device 306 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the electronic device 30. In one example, the transmission device 306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 306 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0092] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 30 .

[0093] The serial numbers of the above embodiments are only for description and do not represent the advantages or disadvantages of the embodiments.

[0094] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0097] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0099] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A DTMF transmission mode management method, characterized in that: include: After a communication session is successfully established between the calling end and the called end, obtaining a first voice sent by the called end to the calling end, wherein the first voice is used to prompt the calling end with key information to be triggered; Acquire a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated dual-tone multi-frequency DTMF transmission mode, and acquire a second voice and a first voice feedback time fed back by the called end to the calling end according to the first DTMF key event, wherein the first DTMF key event at least includes: a first key trigger time; According to the relationship between the first button triggering time and the first voice feedback time and the consistency relationship between the first voice and the second voice, a corresponding management operation is performed on the DTMF transmission mode, wherein the management operation includes: changing or keeping unchanged.

2. The method according to claim 1, characterized in that Before acquiring the first voice information sent by the called end to the calling end, the method further includes: Acquire a call request message initiated by the calling end, wherein the call request message includes at least: the telephone number or address of the called end, and the DTMF transmission mode supported by the calling end; Routing the call request message to the called party according to the number or address of the called party; Acquire a call response message fed back by the called end to the calling end, wherein the call response message is used to indicate that the call request message is in a pending state; After the called end receives the call request message, a call receiving message replied by the called end to the calling end is obtained, wherein the call receiving message at least includes: a DTMF transmission mode supported by the called end; Acquire a confirmation message sent by the calling end to the called end, wherein the confirmation message is used to indicate that the calling end has confirmed receipt and acceptance of the call reception message sent by the called end, and the confirmation message at least includes: a DTMF transmission mode negotiated by the calling end and the called end.

3. The method according to claim 1, characterized in that Acquiring a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission mode, and acquiring a second voice and a first voice feedback time fed back by the called end to the calling end according to the first DTMF key event, including: After the calling end performs a corresponding key operation according to the first voice information, a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission method is obtained, wherein the first DTMF key event also includes: key information triggered by the called end; After the called end receives the first DTMF key event, the second voice fed back by the called end to the calling end and the first voice feedback time are acquired.

4. The method according to claim 1, characterized in that: The DTMF transmission mode is managed according to the relationship between the first button triggering time and the first voice feedback time and the consistency relationship between the first voice and the second voice, including: Determine the time difference between the first button triggering time and the first voice feedback time, and determine the magnitude relationship between the time difference and a preset time threshold; When the time difference is greater than the time threshold, changing the DTMF transmission mode; When the time difference is not greater than the time threshold, determining whether the first voice is consistent with the second voice; When the first voice is consistent with the second voice, changing the DTMF transmission mode; When the first voice is inconsistent with the second voice, the DTMF transmission mode remains unchanged.

5. The method according to claim 4, characterized in that Determining whether the first voice and the second voice are consistent includes: Automatic speech recognition technology is used to perform text recognition on the first speech and the second speech respectively to obtain corresponding first text information and second text information, and it is determined whether the first text information is consistent with the second text information.

6. The method according to claim 1, characterized in that The DTMF transmission modes include: RFC2833, SIPINFO or INBAND.

7. The method according to claim 1, characterized in that After the DTMF transmission mode is changed, the method further includes: Reacquire the second DTMF key event transmitted by the calling end to the called end through the changed DTMF transmission mode, and acquire the third voice information and the second voice feedback time fed back by the called end to the calling end according to the second DTMF key event, wherein the second DTMF key event at least includes: the second key trigger time; according to the size relationship between the second key trigger time and the second voice feedback time and the consistency relationship between the second voice and the third voice, perform corresponding management operations on the changed DTMF transmission mode; When the management operation is the change, the above steps are executed in a loop until the management operation is the remain unchanged.

8. A cloud call platform, characterized in that: include: A first acquisition module, configured to acquire a first voice sent by the called end to the calling end after a communication session is successfully established between the calling end and the called end, wherein the first voice is used to prompt the calling end with key information to be triggered; The second acquisition module is used to acquire a first DTMF key event transmitted by the calling end to the called end through a pre-negotiated DTMF transmission mode, and acquire a second voice and a first voice feedback time fed back by the called end to the calling end according to the first DTMF key event, wherein the first DTMF key event at least includes: a first key trigger time; A management module is used to perform corresponding management operations on the DTMF transmission mode according to the relationship between the first button trigger time and the first voice feedback time and the consistency relationship between the first voice and the second voice, wherein the management operation includes: changing or keeping unchanged.

9. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the DTMF transmission mode management method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the DTMF transmission mode management method according to any one of claims 1 to 7 through the computer program.

Images