CN114979346A - Call data processing method, system, device and storage medium - Google Patents

Abstract

The present invention provides a call data processing method, system, equipment and storage medium. The method includes the steps of: establishing a call between the caller and an IP phone in response to an incoming call request from the caller; and receiving the call by the user-level switch PBX the information flow in the process, convert the information flow into a network data flow, and forward the network data flow to the mirror switch; the mirror switch performs mirror processing on the network data flow to generate a voice mirror file; and The mirror switch sends the network data stream to the IP phone, and sends the voice mirror file to a cloud analysis platform; the cloud analysis platform is used to generate early warning information associated with the call according to the voice mirror file and output; the present application not only realizes the call recording for the IP telephone system, but also reduces the implementation cost of analyzing the recording.

Description

Call data processing method, system, device and storage medium

technical field

The present invention relates to the field of communication technologies, and in particular, to a method, system, device and storage medium for processing call data.

Background technique

Traditional IP phone systems and softphone systems cannot directly use functions such as recording and recording analysis, that is, they cannot use call recordings for recording analysis in real time. Among them, even if the softphone system implements recording, it cannot obtain some information in the data stream of the call network, such as calling and called information, and perform recording analysis. In order to use the recording to analyze the recording in the IP telephone system, it is generally necessary to build a recording server, which leads to a high implementation cost and a complex system. How to use the call recording for real-time recording analysis and reduce the implementation cost of the IP telephone system is a problem currently faced.

SUMMARY OF THE INVENTION

In view of the problems in the prior art, the purpose of the present invention is to provide a call data processing method, system, device and storage medium, which are used to reduce the implementation cost of recording and analysis for the IP telephone system.

In order to achieve the above object, the present invention provides a method for processing call data, which is used to record and analyze the call data of a telephone system, wherein the telephone system includes a user-level switch PBX and an IP phone; the method includes the following steps:

S110, establishing a call between the calling party and the IP phone in response to the calling party's incoming request;

S120, the user-level switch PBX receives the information flow during the call, converts the information flow into a network data flow, and forwards the network data flow to the mirror switch;

S130, the mirroring switch performs mirroring processing on the network data stream to generate a voice mirroring file; and

S140, the mirror switch sends the network data stream to the IP phone, and sends the voice mirror file to a cloud analysis platform; the cloud analysis platform is configured to generate and associate the call according to the voice mirror file warning information and output.

Optionally, the mirror switch and the IP phone are located in the same local area network.

Optionally, step S130 includes:

S131: Obtain multiple ports of the user-level switch PBX that need to be recorded as target switch ports;

S132, obtaining a mirroring port that is mirrored by the mirroring switch on the target switch port, as a target mirroring port; and

S133: Map the data of the target switch port to the target mirroring port.

Optionally, step S132 includes:

Obtain the load capacity and current load of each mirrored port of the mirrored switch;

Obtain the load margin of each mirrored port according to the load capacity and current load of each of the mirrored ports; and

Use the mirror port with the largest load margin as the target mirror port.

Optionally, the method further includes the steps:

S150, the cloud analysis platform converts the voice image file into a voice stream;

S160, the cloud analysis platform performs text recognition on the voice stream to obtain corresponding text data and pinyin information; and

S170, the cloud analysis platform generates and outputs early warning information associated with the call according to the pinyin information and the text data.

Optionally, step S170 includes:

When the pinyin information is the same as the first preset information and the text data is the same as the second preset information, early warning information is generated and output according to the text data.

Optionally, step S170 includes:

According to the text data, obtain the appeal category corresponding to the early warning information;

Based on the appeal category and the preset database, obtain the on-duty agent matching the appeal category; the preset database stores the on-duty agents corresponding to different appeal categories;

Allocate the warning information to the on-duty agent for processing.

Optionally, after each call ends, the cloud analysis platform generates and outputs early warning information associated with the call based on a voice image file corresponding to the call.

Optionally, step S110 includes:

When an incoming call from an external phone is detected, the operator base station sends the incoming call request to the user-level switch PBX;

The user-level switch PBX sends the incoming call request to the IP phone;

The user-level switch PBX receives the response information of the IP phone to the incoming request, and forwards the response information to the operator base station.

The present invention also provides a call data processing system for implementing the above call data processing method, the call data processing system includes a telephone system, a mirror switch and a cloud analysis platform, and the telephone system includes a user-level switch PBX and an IP phone ;

The user-level switch PBX is used to establish a call between the caller and the IP phone in response to the caller's incoming request; and to receive the information flow during the call, convert the information flow into a network data flow, and convert the information flow into a network data flow. the network data stream is forwarded to the mirror switch;

The mirror switch is configured to perform mirror processing on the network data stream, generate a voice mirror file, send the network data stream to the IP phone, and send the voice mirror file to a cloud analysis platform;

The cloud analysis platform is configured to generate and output early warning information associated with the call according to the voice image file.

The present invention also provides a call data processing device, comprising:

processor;

a memory in which an executable program of the processor is stored;

Wherein, the processor is configured to execute the steps of any one of the above call data processing methods by executing the executable program.

The present invention also provides a computer-readable storage medium for storing a program, and when the program is executed by a processor, the steps of any one of the above call data processing methods are implemented.

Compared with the prior art, the present invention has the following advantages and outstanding effects:

The call data processing method, system, device and storage medium provided by the present invention mirror the network data stream by using a mirror switch, then continue to forward the original network data stream to the IP phone, and use the mirror file for recording and analysis, so that no construction is required. The recording server reduces the implementation cost and the complexity of system implementation; and can use the call recording data for recording analysis while recording in real time, with higher timeliness, and can quickly analyze early warning information, which is conducive to improving the efficiency of telephone agent management.

Description of drawings

Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings.

FIG. 1 is a schematic structural diagram of a call data processing system disclosed in an embodiment of the present invention;

FIG. 2 is a schematic diagram of a method for processing call data disclosed in an embodiment of the present invention;

3 is a schematic diagram of a method for processing call data disclosed by another embodiment of the present invention;

FIG. 4 is a schematic flowchart of step S130 in a call data processing method disclosed in another embodiment of the present invention;

5 is a schematic diagram of a method for processing call data disclosed by another embodiment of the present invention;

FIG. 6 is a schematic flowchart of step S170 in a call data processing method disclosed by another embodiment of the present invention;

7 is a schematic structural diagram of a call data processing device disclosed in an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a computer-readable storage medium disclosed in an embodiment of the present invention.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their repeated descriptions will be omitted.

An embodiment of the present invention discloses a method and system for processing call data. As shown in FIG. 1 , the system includes a telephone system, a mirror switch 11 and a cloud analysis platform 12 . The above-mentioned telephone system includes a subscriber-level exchange PBX 13 and an IP telephone 14 . It should be noted that the number of IP phones shown in FIG. 1 does not represent the actual number of IP phones in actual implementation, and is only used for exemplary illustration. In specific implementation, when the party answering the call is a customer service agent or an agent on duty, different phone ports can be allocated to different agents on duty, that is, there is a one-to-one correspondence between agents and ports. The port of the IP phone used by each agent is different.

As shown in Figure 2, the above-mentioned call data processing method includes the steps:

S110, in response to the caller's incoming request, establish a call between the caller and the IP phone. Specifically, in this step, when an incoming call from an external phone is detected, the base station of the operator sends an incoming call request to the user-level switch PBX. User-level switches PBX (Private Branch Exchange), also known as program-controlled switches, are used to complete the telephone exchange between enterprises and with the public telecommunication network, and combine functions such as telephone, fax, and modem.

The above-mentioned user-level switch sends the incoming call request to the IP phone. The above-mentioned user-level switch PBX receives the response information of the above-mentioned IP phone to the above-mentioned incoming call request, and forwards the above-mentioned response information to the above-mentioned operator base station. In specific implementation, when the above-mentioned response information is to answer the external call, a call can be established between the caller and the IP phone through the operator base station and the user-level switch PBX in response to the caller's incoming request.

S120, the user-level switch PBX receives the information flow during the call, converts the above information flow into a network data flow, and forwards the above network data flow to the mirror switch. Specifically, after the phone call between the caller and the IP phone is established, the call signal sent by the caller is transmitted to the user-level switch PBX through the operator's base station, and the user-level switch PBX converts the call signal into a network data stream. Only by converting it into the form of network data stream can the call signal be received and recognized by the IP phone.

S130: The mirror switch performs mirror processing on the network data stream to generate a voice mirror file. In this way, the voice recording of the call is realized. The recording is a real-time recording and can be sent to the cloud analysis platform in real time. In this way, after each call ends, each call can be analyzed in real time, and there is no need to store a large number of voice files, avoiding the need for Mass storage requirements.

In this embodiment, the above-mentioned mirror switch and the above-mentioned IP phone are located in the same local area network. This is beneficial to ensure the success rate of each mirrored voice call and reduce the probability of mirroring failure; and is beneficial to improve the efficiency of mirrored voice and the transmission efficiency.

During specific implementation, as shown in Figure 3, this step may include:

S131: Acquire multiple ports of the user-level switch PBX to be recorded as target switch ports. That is, it is determined which ports of the user-level switch PBX output network data streams that need to be recorded, and then mirroring is performed accordingly.

S132: Acquire a mirroring port on which the mirroring switch performs mirroring processing on the target switch port, as a target mirroring port. as well as

S133, the mirror switch maps the data of the target switch port to the target mirror port. In this way, the network data flow output from the target switch port is mirrored.

And S140, the mirror switch sends the network data stream to the IP phone, and sends the voice mirror file to a cloud analysis platform. The above-mentioned cloud analysis platform is configured to generate and output early warning information associated with the above-mentioned call according to the above-mentioned voice image file.

In this embodiment, after each call ends, the cloud analysis platform generates and outputs early warning information associated with the call based on the voice image file corresponding to the call. That is, the cloud analysis platform performs recording analysis according to the recording file corresponding to each complete call. Since the voice image file is also in the form of a network data stream, during the specific implementation, the cloud analysis platform can convert the voice image file into a voice stream, and then perform text recognition to obtain text data. When the above voice stream and text data conform to the preset When the conditions are met, it indicates that certain keywords have been mentioned in the call content of the calling party, and then an early warning is triggered.

For example, an application scenario is that a guest staying in a hotel calls the hotel customer service agent to complain about poor hygiene. Then, when the keyword "poor hygiene" is identified according to the above voice stream and text data, and the "poor hygiene" is also a preset condition, that is, a trigger condition, then the word "poor hygiene" is extracted. Keywords corresponding to other trigger conditions are then extracted together, and the extracted words are combined to form early warning information. Then push each early warning keyword in the early warning information to the on-duty staff of the corresponding responsible department for processing, for example, push the early warning information corresponding to "poor hygiene" to the department responsible for handling hotel hygiene, such as timely return visits from guests, Soothe your guests. This can help improve the guest experience of staying at the hotel. Therefore, the application can also intelligently identify and analyze recordings in real time, and quickly and accurately analyze customer sentiment and evaluation, which is beneficial to improve the management efficiency and response efficiency of seat responders such as hotels.

Optionally, as shown in FIG. 4 , in an embodiment, on the basis of the embodiment corresponding to the foregoing FIG. 2 , the foregoing step S132 may include:

S1321: Obtain the load capacity and current load of each mirrored port of the mirrored switch.

S1322: Obtain the load margin of each mirrored port according to the load capacity and current load of each mirrored port. as well as

S1323, the mirroring port with the largest load margin is used as the target mirroring port.

This is beneficial to reduce the phenomenon of interference by the computing performance of the mirror switch during the mirroring process, and reduce the probability of mirroring failure; it is beneficial to ensure the success of mirroring; on the other hand, it is beneficial to improve the transmission efficiency of mirrored files, thereby improving the efficiency of mirrored voice.

In another embodiment of the present application, another method for processing call data is disclosed. As shown in Figure 5, on the basis of the above-mentioned embodiment corresponding to Figure 2, the method also includes the steps:

S150, the cloud analysis platform converts the voice image file into a voice stream.

S160, the cloud analysis platform performs text recognition on the voice stream to obtain corresponding text data and pinyin information. as well as

S170, the cloud analysis platform generates and outputs early warning information associated with the call according to the pinyin information and the text data.

In specific implementation, for example, when the text data is the same as a preset text, the warning information corresponding to the preset text is triggered, and then the warning information is sent to the corresponding management personnel.

Optionally, in an embodiment, the foregoing step S170 includes:

S171, when the above-mentioned pinyin information is the same as the first preset information, and the above-mentioned text data is the same as the second preset information, generate early warning information according to the above-mentioned text data.

That is, according to the data extracted from the call recording of the calling party, it is determined that the recorded data has the same sound and the same word as the preset information. In this case, it means that the preset warning trigger condition is met, then the warning is triggered; this can ensure that Accuracy of alert triggering. At this time, the corresponding short paragraph of words with the same pronunciation and the same character, such as the word "poor hygiene" in the above example, is used as early warning information and pushed to the corresponding department in charge of processing or the agent on duty, which can help improve the caller's confidence. Problem solving efficiency; it is also beneficial to improve the management efficiency and response efficiency of the agent responder, and help them quickly solve the problem of the caller.

Optionally, in an embodiment, as shown in FIG. 6 , in addition to step S171, step S170 further includes steps:

S172, according to the above text data, obtain the appeal category corresponding to the above warning information.

S173, based on the above-mentioned appeal category and the preset database, obtain an on-duty agent matching the above-mentioned appeal category. The above-mentioned preset database stores on-duty agents corresponding to different appeal categories.

S174: Allocate the above-mentioned early warning information to the above-mentioned on-duty agent for processing.

During specific implementation, the above step S172 may be implemented by a trained neural network model, and the above text data and/or the above pinyin information are used as the input of the neural network model to output the corresponding appeal category. Wherein, the above-mentioned neural network model may be an existing sentiment analysis recognition model or the like.

For example, the above-mentioned appeal category can be a complaint or a compliment, etc. This application pushes the above-mentioned warning information to the corresponding department responsible for processing or the agent on duty, which can help improve the problem solving efficiency of the calling party and improve the management efficiency of the agent responding party. and answering efficiency, helping it resolve caller problems quickly.

It should be noted that all the above-mentioned embodiments disclosed in this application can be freely combined, and the technical solutions obtained after the combination are also within the protection scope of this application.

An embodiment of the present invention also discloses a call data processing system, which includes:

The telephone call establishment module, in response to the caller's incoming request, establishes a call between the caller and the IP phone.

The call signal conversion module, the user-level switch PBX receives the information flow during the call, converts the above information flow into a network data flow, and forwards the above network data flow to the mirror switch.

In the voice mirroring module, the mirroring switch performs mirroring processing on the network data stream to generate a voice mirroring file. as well as

In the image file transmission module, the image switch sends the network data stream to the IP phone, and sends the voice image file to a cloud analysis platform. The above-mentioned cloud analysis platform is configured to generate and output early warning information associated with the above-mentioned call according to the above-mentioned voice image file.

It can be understood that the call data processing system of the present invention also includes other existing functional modules that support the operation of the call data processing system. The above-mentioned call data processing system is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present invention.

The call data processing system in this embodiment is used to implement the above call data processing method. Therefore, for the specific implementation steps of the call data processing system, reference may be made to the above description of the call data processing method, which will not be repeated here.

An embodiment of the present invention further discloses a call data processing device, including a processor and a memory, wherein the memory stores an executable program of the processor; the processor is configured to execute the above call data processing method by executing the executable program steps in . FIG. 7 is a schematic structural diagram of a call data processing device disclosed in the present invention. An electronic device 600 according to this embodiment of the present invention is described below with reference to FIG. 7 . The electronic device 600 shown in FIG. 7 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in FIG. 7, electronic device 600 takes the form of a general-purpose computing device. Components of the electronic device 600 may include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.

The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the above-mentioned part of the call data processing method of this specification. For example, the processing unit 610 may perform the steps shown in FIG. 2 .

The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and/or a cache storage unit 6202 , and may further include a read only storage unit (ROM) 6203 .

The storage unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, An implementation of a network environment may be included in each or some combination of these examples.

The bus 630 may be representative of one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any of a variety of bus structures bus.

The electronic device 600 may also communicate with one or more external devices 700 (eg, keyboards, pointing devices, Bluetooth devices, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with Any device (eg, router, modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 650 . Also, the electronic device 600 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 660 . Network adapter 660 may communicate with other modules of electronic device 600 through bus 630 . It should be appreciated that, although not shown, other hardware and/or software modules may be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage platform, etc.

The invention also discloses a computer-readable storage medium for storing a program, when the program is executed, the steps in the above call data processing method are implemented. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes program code, when the program product runs on a terminal device, the program code is used to cause the terminal device to execute the above-mentioned description in this specification. The steps according to various exemplary embodiments of the present invention are described in the call data processing method.

As shown above, when the program of the computer-readable storage medium of this embodiment is executed, the mirroring switch is used to perform mirroring processing on the network data stream, and then the original network data stream is continuously forwarded to the IP phone, and the mirror file is used for recording analysis, In this way, there is no need to build a recording server, which reduces the implementation cost and the complexity of system implementation; it is more adaptable to different telephone systems.

FIG. 8 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to FIG. 8, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read only memory (CD-ROM) and include program codes, and can be used in a terminal device, For example running on a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

A computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable storage medium can also be any readable medium other than a readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming Language - such as the "C" language or similar programming language. The program code may execute entirely on the user computing device, partly on the user device, as a stand-alone software package, partly on the user computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (eg, using an Internet service provider business via an Internet connection).

The call data processing method, system, device, and storage medium provided by the embodiments of the present invention mirror the network data stream by using a mirror switch, then continue to forward the original network data stream to the IP phone, and use the mirror file for recording analysis. There is no need to build a recording server, which reduces the implementation cost and the complexity of system implementation; it is more adaptable to different telephone systems. In addition, the call recording data can be used for recording analysis while recording in real time, which has higher timeliness, and can quickly analyze early warning information, which is conducive to improving the efficiency of telephone agent management.

The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and it cannot be considered that the specific implementation of the present invention is limited to these descriptions. For those of ordinary skill in the technical field of the present invention, without departing from the concept of the present invention, some simple deductions or substitutions can be made, which should be regarded as belonging to the protection scope of the present invention.

Claims (12)

1. A call data processing method is characterized in that the method is used for recording and analyzing call data of a telephone system, wherein the telephone system comprises a PBX (private branch exchange) and an IP (Internet protocol) phone; the method comprises the following steps:

s110, responding to the incoming call request of the calling party, and establishing a conversation between the calling party and the IP phone;

s120, a PBX (private Branch exchange) receives an information stream in a call process, converts the information stream into a network data stream, and forwards the network data stream to a mirror image switch;

s130, the mirror image switch carries out mirror image processing on the network data stream to generate a voice mirror image file; and

s140, the mirror image switch sends the network data stream to an IP phone and sends the voice mirror image file to a cloud analysis platform; and the cloud analysis platform is used for generating and outputting early warning information related to the call according to the voice mirror image file.

2. The call data processing method according to claim 1, wherein the mirror switch and the IP telephone are located in the same lan.

3. The call data processing method according to claim 1, wherein step S130 comprises:

s131, acquiring a plurality of ports of the PBX of the user-level switch needing to record as ports of a target switch;

s132, acquiring a mirror image port of the mirror image switch for performing mirror image processing on the target switch port as a target mirror image port; and

s133, mapping the data of the target switch port to the target mirror image port.

4. The call data processing method according to claim 3, wherein step S132 includes:

acquiring the load capacity and the current load of each mirror image port of the mirror image switch;

acquiring the load allowance of each mirror image port according to the load capacity and the current load of each mirror image port; and

and taking the mirror port with the maximum load margin as a target mirror port.

5. The call data processing method according to claim 1, wherein said method further comprises the steps of:

s150, the cloud analysis platform converts the voice image file into a voice stream;

s160, the cloud analysis platform performs text recognition on the voice stream to obtain corresponding text data and pinyin information; and

and S170, generating and outputting early warning information related to the call by the cloud analysis platform according to the pinyin information and the text data.

6. The call data processing method according to claim 5, wherein step S170 comprises:

and when the pinyin information is the same as the first preset information and the text data is the same as the second preset information, generating early warning information according to the text data and outputting the early warning information.

7. The call data processing method according to claim 5, wherein step S170 comprises:

acquiring an appeal category corresponding to the early warning information according to the text data;

acquiring an on-duty seat matched with the appeal category based on the appeal category and a preset database; the preset database stores on-duty seats corresponding to different appeal categories;

and distributing the early warning information to the on-duty seat for processing.

8. The call data processing method of claim 1, wherein after each call, the cloud analysis platform generates and outputs warning information associated with the call based on a voice image file corresponding to the call.

9. The call data processing method according to claim 1, wherein step S110 comprises:

when an external telephone incoming call is detected, the operator base station sends an incoming call request to a PBX (private Branch exchange);

the PBX sends the incoming call request to an IP phone;

and the PBX receives response information of the IP phone for the incoming call request and forwards the response information to the operator base station.

10. A call data processing system for implementing the call data processing method according to claim 1, wherein the call data processing system comprises a telephone system, a mirror switch and a cloud analysis platform, the telephone system comprises a private branch exchange (PBX) and an IP phone;

the PBX is used for responding to an incoming call request of a calling party and establishing a call between the calling party and the IP phone; receiving an information flow in a call process, converting the information flow into a network data flow, and forwarding the network data flow to a mirror image switch;

the mirror image switch is used for carrying out mirror image processing on the network data stream, generating a voice mirror image file, sending the network data stream to an IP phone and sending the voice mirror image file to a cloud analysis platform;

and the cloud analysis platform is used for generating and outputting early warning information related to the call according to the voice image file.

11. A call data processing apparatus, comprising:

a processor;

a memory having stored therein an executable program of the processor;

wherein the processor is configured to perform the steps of the call data processing method of any one of claims 1 to 9 via execution of the executable program.

12. A computer-readable storage medium storing a program for implementing the steps of the call data processing method according to any one of claims 1 to 9 when the program is executed by a processor.

Images