Voice response anomaly detection method and device, equipment and storage medium

Abstract

The invention provides a voice response anomaly detection method, device and equipment and a storage medium, and the voice response anomaly detection method comprises the steps: carrying out the first call of a telephone terminal and an interactive voice response system under the condition that the interactive voice response system is normal, determining the interaction content of the telephone terminal and the interactive voice response system, and carrying out the first call of the telephone terminal and the interactive voice response system; storing the interactive content as a dial testing template, ending the first call, after a specified time interval, performing a second call on the current interactive voice response system, performing anomaly detection on the current interactive voice response system according to the dial testing template, determining an anomaly detection result, and sending the anomaly detection result to the user. Compared with the prior art, anomaly detection can be automatically carried out on the current interactive voice response system based on the dial test template, the accuracy and timeliness of anomaly detection can be improved, and better experience can be provided for customers.

Description

Technical Field

[0001] The present application relates to the field of voice, and particularly to a method, apparatus, device, and storage medium for detecting abnormal voice responses. Background Art

[0002] IVR (Interactive Voice Response) is an interactive voice response system used to provide automatic response services for customers. IVR generally configures various processes (such as key menus and intelligent voice), etc. Currently, IVR is widely used in call centers. At present, anomalies in the IVR system, such as being unable to make a call, having no voice response after the call is connected, or abnormal interaction, etc., are generally detected by manual detection or customer complaints and other means of feedback, with low detection efficiency, poor timeliness, and affecting the customer experience. Summary of the Invention

[0003] Embodiments of the present application provide a method, apparatus, device, and storage medium for detecting abnormal voice responses to solve at least one problem existing in the related art. The technical solutions are as follows:

[0004] In a first aspect, an embodiment of the present application provides a method for detecting abnormal voice responses, including:

[0005] When the interactive voice response system is normal, make a first call to the telephone terminal and the interactive voice response system;

[0006] Determine the interaction content between the telephone terminal and the interactive voice response system, save the interaction content as a test template, and end the first call;

[0007] After a specified time interval, make a second call to the current interactive voice response system;

[0008] Perform abnormal detection on the current interactive voice response system according to the test template to determine the abnormal detection result.

[0009] In one implementation, the determining the interaction content between the telephone terminal and the interactive voice response system includes:

[0010] Obtain the first content of the telephone terminal;

[0011] Obtain the second content of the interactive voice response system for answering based on the first content;

[0012] Based on the first content and the second content, obtain the interaction content.

[0013] In one implementation, the anomaly detection of the interactive voice response system according to the probing template determines that the anomaly detection result includes:

[0014] Extract the first content in the probing template;

[0015] Play the first content to the interactive voice response system to obtain the response content of the interactive voice response system;

[0016] Extract the second content in the probing template, compare the response content with the second content, and obtain a comparison result;

[0017] Determine the anomaly detection result according to the comparison result.

[0018] In one implementation, the determination of the anomaly detection result according to the comparison result includes:

[0019] When the comparison result indicates that the similarity is greater than or equal to the similarity threshold, determine the anomaly detection result indicating normal;

[0020] Or,

[0021] When the comparison result indicates that the similarity is less than the similarity threshold, determine the anomaly detection result indicating anomaly;

[0022] Or,

[0023] When the comparison result indicates that the similarity is less than the similarity threshold, return to the step of playing the first content to the interactive voice response system, and determine the comparison results for a specified number of times;

[0024] When the comparison results for a specified number of times are all such that the similarity is less than the similarity threshold for a continuous preset number of times, determine the anomaly detection result indicating anomaly, or, within a preset time interval, the number of comparison results indicating that the similarity is less than the similarity threshold is greater than the number threshold, determine the anomaly detection result indicating anomaly, otherwise, determine the anomaly detection result indicating normal.

[0025] In one implementation, the obtaining of the first content of the telephone terminal includes:

[0026] Enable key detection for the telephone terminal to obtain key text content;

[0027] Enable automatic speech recognition for the telephone terminal to obtain the speech text content of the telephone terminal;

[0028] Obtain the first content according to the key text content and the speech text content.

[0029] In one implementation, the obtaining of the second content for which the interactive voice response system responds based on the first content includes:

[0030] When the interactive voice response system receives the first content, obtain the voice content of the interactive voice response system;

[0031] Perform automatic speech recognition on the voice content to obtain the second content.

[0032] In one implementation, the method further includes:

[0033] When the anomaly detection result indicates an anomaly, issue an alarm according to the alarm policy.

[0034] In a second aspect, an embodiment of the present application provides a voice response anomaly detection device, including:

[0035] A first call module, configured to perform a first call between a telephone terminal and the interactive voice response system when the interactive voice response system is normal;

[0036] A determination module, configured to determine the interaction content between the telephone terminal and the interactive voice response system, save the interaction content as a dial test template, and end the first call;

[0037] A second call module, configured to perform a second call on the current interactive voice response system after a specified time interval;

[0038] A detection module, configured to perform anomaly detection on the current interactive voice response system according to the dial test template, and determine an anomaly detection result.

[0039] In one implementation, the detection module is further configured to:

[0040] When the anomaly detection result indicates an anomaly, issue an alarm according to the alarm policy.

[0041] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory, where instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the method in any one of the above aspects.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed, the method in any one of the above aspects is implemented.

[0043] The beneficial effects in the above technical solutions at least include:

[0044] By making a first call to a telephone terminal and an interactive voice response system when the interactive voice response system is normal, determining the interaction content between the telephone terminal and the interactive voice response system, saving the interaction content as a test call template, ending the first call, and after a specified time interval, making a second call to the current interactive voice response system, performing anomaly detection on the current interactive voice response system according to the test call template, and determining the anomaly detection result, it is possible to automatically perform anomaly detection on the current interactive voice response system based on the test call template. Compared with the prior art, the accuracy and timeliness of anomaly detection can be improved, which is beneficial to providing a better experience for customers.

[0045] The above summary is for the purpose of the specification only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present application will become readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In the drawings, unless otherwise specified, the same reference numerals throughout the several views denote the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in accordance with the present application and should not be regarded as limiting the scope of the present application.

[0047] Figure 1 It is a schematic flowchart of the steps of a method for detecting voice response anomalies according to an embodiment of the present application;

[0048] Figure 2 It is a schematic diagram of interaction content according to an embodiment of the present application;

[0049] Figure 3 It is a structural block diagram of a device for detecting voice response anomalies according to an embodiment of the present application;

[0050] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] In the following, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present application. Therefore, the drawings and the description are considered to be exemplary in nature rather than restrictive.

[0052] Referring to Figure 1 , a flowchart of a method for detecting voice response anomalies according to an embodiment of the present application is shown. The method for detecting voice response anomalies can at least include steps S100 - S400:

[0053] S100. When the interactive voice response system is normal, make a first call to the telephone terminal and the interactive voice response system.

[0054] S200. Determine the interaction content between the telephone terminal and the interactive voice response system, save the interaction content as a test call template, and end the first call.

[0055] S300. After a specified time interval, make a second call to the current interactive voice response system.

[0056] S400. Perform anomaly detection on the current interactive voice response system according to the test call template, and determine the anomaly detection result.

[0057] The voice response anomaly detection method in the embodiments of the present application can be executed by an electronic control unit, a controller, a processor, etc. of terminals such as a computer, a mobile phone, a tablet, and a vehicle-mounted terminal, or can be executed by a cloud server, for example, the system in the cloud server.

[0058] The technical solution of the embodiments of the present application, by making a first call to the telephone terminal and the interactive voice response system when the interactive voice response system is normal, determining the interaction content between the telephone terminal and the interactive voice response system, saving the interaction content as a test call template, ending the first call, making a second call to the current interactive voice response system after a specified time interval, and performing anomaly detection on the current interactive voice response system according to the test call template to determine the anomaly detection result, can automatically perform anomaly detection on the current interactive voice response system based on the test call template. Compared with the prior art, it can improve the accuracy and timeliness of anomaly detection, which is beneficial to providing a better experience for customers.

[0059] In one implementation, the system includes an outbound call module, a recording module, a test call module, and an alarm module. Optionally, the outbound call module has functions of initiating a call, bridging a call, key detection, ASR / TTS, and communicates with the recording module and the test call module through an interface; the recording module communicates with the outbound call module through an interface, receives the keys and ASR recognition content during the entire interaction process between the telephone terminal and the IVR, and saves them as a test call template; the test call module communicates with the outbound call module through an interface. After the outbound call module calls the IVR, it receives the ASR recognition content at the IVR end, and at the same time controls the outbound call module to play TTS or send keys to the IVR according to the test call template content; the alarm module compares the test call interaction record with the test call template content to determine whether the IVR system is normal. If it is not normal, corresponding alarms are generated according to the alarm policy.

[0060] Among them, in step S100, when the interactive voice response system is normal, the outbound call module is used to initiate a call to make a first call to the telephone terminal and the interactive voice response system.

[0061] In one embodiment, in step S200, the recording module determines the interaction content between the telephone terminal and the interactive voice response system, and saves the interaction content as a test call template. After the test call template is saved, the outbound call module ends the first call.

[0062] Optionally, in step S200, determining the interaction content between the telephone terminal and the interactive voice response system by the recording module includes S210 - S230:

[0063] S210. Obtain the first content of the telephone terminal.

[0064] Optionally, S210 includes steps S2101 - S2103:

[0065] S2101. Enable key detection for the telephone terminal to obtain key text content.

[0066] S2102. Enable automatic speech recognition for the telephone terminal to obtain the voice text content of the telephone terminal.

[0067] It should be noted that the execution order of S2101 and S2102 is not limited. The user can issue voice or click a key on the telephone terminal, so that the key text content can be obtained through key detection, and the voice text content of the telephone terminal can be obtained by performing automatic speech recognition ASR (Automatic Speech Recognition) on the voice issued by the user. For example, as Figure 2 shown, during the first call, the interactive voice response system (IVR, Interactive Voice Response) issues the voice "Hello! Welcome to call XX. What can I do for you? Please speak", and then the user responds with "key menu" by voice. After automatic speech recognition, the voice text content "key menu" can be recorded. Then the interactive voice response system issues the voice "Okay, now transferring you to the key menu. Please press 1 for XX service, please press 2 for XX service...", and the user enters "1" by pressing a key. The key text content "1" is obtained through key detection, and the interactive voice response system responds with "Okay, now performing XX for you". In this process, the key text content and the voice text content can be extracted.

[0068] S2103. Obtain the first content according to the key text content and the voice text content.

[0069] Specifically, after determining the key text content and the voice text content, the first content is formed. As in the above example, the first content can include "key menu" and "1".

[0070] S220. Obtain a second piece of content for which the interactive voice response system responds based on the first piece of content.

[0071] Optionally, when the interactive voice response system receives the first piece of content, it will respond by voice. Therefore, the recording module obtains the voice content of the interactive voice response system, and then uses automatic speech recognition (ASR) to recognize the voice content to obtain the second piece of content. As Figure 2 In the example shown, the second piece of content in the form of text content can be obtained: "Hello! Welcome to call XX. How can I help you? Please speak.", "Okay, now transferring you to the key menu. Press 1 for XX service, press 2 for XX service...", "Okay, now performing XX for you", etc.

[0072] S230. Obtain the interaction content based on the first piece of content and the second piece of content.

[0073] Specifically, when obtaining the first piece of content and the second piece of content, combine the first piece of content and the second piece of content, and the interaction content of the entire interaction process can be obtained.

[0074] In one implementation, the specified time interval in step S300 is not specifically limited. After saving the call test template, when it is necessary to perform anomaly detection on the current interactive voice response system, the outbound call module can make a second call to the current interactive voice response system, and then the call test module controls the outbound call module to play the first piece of content of the call test template to the interactive voice response system for anomaly detection.

[0075] Optionally, in step S300, anomaly detection is performed on the current interactive voice response system according to the call test template to determine the anomaly detection result, including steps S310 - S340:

[0076] S310. Extract the first piece of content in the call test template.

[0077] S320. Play the first piece of content to the interactive voice response system to obtain the response content of the interactive voice response system.

[0078] Among them, the call test module can extract the first piece of content in the call test template, and then use TTS (Text To Speech) for speech synthesis and send keys. In the above example, convert the "key menu" in the first piece of content into voice and play it to the interactive voice response system by the outbound call module, and convert "1" into a key and play / send it to the interactive voice response system by the outbound call module to obtain the response content of the interactive voice response system. It should be noted that the response content can be converted into text content based on automatic speech recognition.

[0079] S330. Extract the second content in the dial test template, compare the answer content with the second content, and obtain the comparison result.

[0080] Optionally, the dial test module can extract the second content in the dial test template, and compare the answer content with the second content through the alarm module to obtain the comparison result. It should be noted that the comparison method can be the calculation of similarity.

[0081] S340. Determine the anomaly detection result according to the comparison result.

[0082] Optionally, S340 includes one of steps S3401, S3402, or S3403:

[0083] S3401. When the comparison result indicates that the similarity is greater than or equal to the similarity threshold, determine the anomaly detection result indicating normal.

[0084] It should be noted that the similarity threshold is set based on the actual situation. When the comparison result indicates that the similarity is greater than or equal to the similarity threshold, determine the anomaly detection result indicating normal.

[0085] S3402. When the comparison result indicates that the similarity is less than the similarity threshold, determine the anomaly detection result indicating anomaly.

[0086] Specifically, when the comparison result indicates that the similarity is less than the similarity threshold, determine the anomaly detection result indicating anomaly, indicating that the interactive voice response system is abnormal.

[0087] S3403. When the comparison result indicates that the similarity is less than the similarity threshold, return to the step of playing the first content to the interactive voice response system, determine the comparison results for a specified number of times. When the comparison results for a continuous preset number of times among the specified number of comparison results all indicate that the similarity is less than the similarity threshold, determine the anomaly detection result indicating anomaly. Or, within a preset time interval, the number of comparison results indicating that the similarity is less than the similarity threshold is greater than the number threshold, determine the anomaly detection result indicating anomaly. Otherwise, determine the anomaly detection result indicating normal.

[0088] It should be noted that in one implementation, in order to more accurately determine that the interactive voice response system is abnormal without causing misjudgment, when the comparison result indicates that the similarity is less than the similarity threshold, return to the step of playing the first content to the interactive voice response system and determine the comparison results for a specified number of times; the specified number of times is set based on the actual situation and is not specifically limited.

[0089] In the embodiments of the present application, 1) when the comparison results of a specified number of times and the comparison results of a continuous preset number of times all indicate that the similarity is less than the similarity threshold, an abnormal detection result indicating abnormality is determined; or 2) within a preset time interval, the number of comparison results indicating that the similarity is less than the similarity threshold is greater than the number threshold, and an abnormal detection result indicating abnormality is determined; when the above two situations are not satisfied, a normal abnormal detection result is determined, indicating that the interactive voice response system is normal.

[0090] In one implementation manner, the voice response abnormal detection method of the embodiments of the present application may further include: when the abnormal detection result indicates abnormality, an alarm is made according to the alarm policy. For example, the alarm policy may be to notify through forms such as emails, text messages, official accounts, applets, web pages, etc., so that maintenance personnel can maintain the interactive voice response system in a timely manner, improving the real-time performance and efficiency of abnormal handling.

[0091] Through the method of the embodiments of the present application, problems in the related art that monitoring of the IVR system such as resource status, signaling testing, etc. cannot detect that the IVR is silent or abnormal content is broadcasted are solved. First, the IVR system is called, the user communicates with the IVR, and the entire interaction process is recorded as a testing template. Then, the user call to the IVR is simulated, and the interaction is carried out with the IVR according to the template content. Verifying whether the IVR process is normal through this strategy will be more accurate. The voice interaction process is converted into a visual testing template by using ASR, and then TTS is used to simulate the interaction between the user and the IVR according to the template. In principle, it has the same effect as the user actually dialing the IVR, so as to achieve the purpose of verifying the IVR process to determine whether the IVR is abnormal.

[0092] Refer to Figure 3 , which shows the structural block diagram of the voice response abnormal detection device according to an embodiment of the present application. The device may include:

[0093] The first call module is used to make a first call to the telephone terminal and the interactive voice response system when the interactive voice response system is normal;

[0094] The determination module is used to determine the interaction content between the telephone terminal and the interactive voice response system, save the interaction content as a testing template, and end the first call;

[0095] The second call module is used to make a second call to the current interactive voice response system after a specified time interval;

[0096] The detection module is used to perform abnormal detection on the current interactive voice response system according to the testing template and determine the abnormal detection result.

[0097] In one implementation manner, the detection module is further used for:

[0098] When the anomaly detection result indicates an anomaly, an alarm is issued according to the alarm policy.

[0099] For the functions of the modules in each device in the embodiments of the present application, reference may be made to the corresponding descriptions in the above methods, which will not be elaborated herein.

[0100] Refer to Figure 4 , which shows a structural block diagram of an electronic device according to an embodiment of the present application. The electronic device includes: a memory 310 and a processor 320. The memory 310 stores instructions that can run on the processor 320. The processor 320 loads and executes the instructions to implement the voice response anomaly detection method in the above embodiments. Among them, the number of the memory 310 and the processor 320 can be one or more.

[0101] In one implementation, the electronic device further includes a communication interface 330 for communicating with external devices and performing data interaction and transmission. If the memory 310, the processor 320, and the communication interface 330 are implemented independently, the memory 310, the processor 320, and the communication interface 330 can be interconnected through a bus and complete communication with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 4 only a thick line is shown in [reference], but it does not mean that there is only one bus or one type of bus.

[0102] Optionally, in a specific implementation, if the memory 310, the processor 320, and the communication interface 330 are integrated on a chip, the memory 310, the processor 320, and the communication interface 330 can complete communication with each other through an internal interface.

[0103] The embodiments of the present application provide a computer-readable storage medium that stores a computer program. When the computer program is executed by a processor, it implements the voice response anomaly detection method provided in the above embodiments.

[0104] The embodiments of the present application further provide a chip, which includes a processor for calling and running instructions stored in a memory from the memory, so that a communication device equipped with the chip executes the method provided in the embodiments of the present application.

[0105] An embodiment of the present application further provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, the output interface, the processor, and the memory are connected through an internal connection path. The processor is configured to execute the code in the memory. When the code is executed, the processor is configured to execute the method provided by the embodiment of the application.

[0106] It should be understood that the above-mentioned processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the advanced RISC machines (ARM) architecture.

[0107] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may further include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0108] In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0109] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0110] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of these features. In the description of this application, "a plurality of" means two or more unless otherwise specifically defined.

[0111] Any process or method description represented in the flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of this application includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed.

[0112] The logic and / or steps represented in the flowchart or described in other ways herein, for example, may be considered as a sequenced list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in connection with these instruction execution systems, apparatus, or devices.

[0113] It should be understood that the various parts of this application may be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above example methods may be completed by a program instructing relevant hardware, and this program may be stored in a computer-readable storage medium. When this program is executed, it includes one or a combination of the steps of the method embodiments.

[0114] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above integrated module may be implemented in the form of hardware or in the form of a software functional module. If the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, an optical disk, or the like.

[0115] As mentioned above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for detecting abnormal voice responses, characterized in that, Including: When the interactive voice response system is normal, make a first call to the telephone terminal and the interactive voice response system; Determine the interaction content between the telephone terminal and the interactive voice response system, save the interaction content as a test call template, and end the first call; After a specified time interval, make a second call to the current interactive voice response system; Perform anomaly detection on the current interactive voice response system according to the test call template, and determine the anomaly detection result.

2. The voice response anomaly detection method according to claim 1, wherein: The determining the interaction content between the telephone terminal and the interactive voice response system includes: Obtain the first content of the telephone terminal; Obtain the second content of the interactive voice response system's response based on the first content; Based on the first content and the second content, obtain the interaction content.

3. The voice response anomaly detection method according to claim 2, wherein: The performing anomaly detection on the interactive voice response system according to the test call template and determining the anomaly detection result includes: Extract the first content from the test call template; Play the first content to the interactive voice response system to obtain the response content of the interactive voice response system; Extract the second content from the test call template, compare the response content with the second content, and obtain a comparison result; Based on the comparison result, determine the anomaly detection result.

4. The voice response anomaly detection method according to claim 3, wherein: The determining the anomaly detection result based on the comparison result includes: When the comparison result indicates that the similarity is greater than or equal to the similarity threshold, determine the anomaly detection result indicating normal; Or, When the comparison result indicates that the similarity is less than the similarity threshold, determine the anomaly detection result indicating anomaly; Or, When the comparison result indicates that the similarity is less than the similarity threshold, return to the step of playing the first content to the interactive voice response system, and determine the comparison results for a specified number of times; When the comparison results for a continuous preset number of times among the comparison results for the specified number of times all indicate that the similarity is less than the similarity threshold, determine the anomaly detection result indicating anomaly, or, within a preset time interval, the number of comparison results indicating that the similarity is less than the similarity threshold is greater than the number threshold, determine the anomaly detection result indicating anomaly, otherwise, determine the anomaly detection result indicating normal.

5. The voice response anomaly detection method according to claim 2, characterized in that: The obtaining the first content of the telephone terminal includes: Enable key detection for the telephone terminal to obtain key text content; Enable automatic speech recognition for the telephone terminal to obtain the speech text content of the telephone terminal; Based on the key text content and the speech text content, obtain the first content.

6. The voice response anomaly detection method according to claim 2, wherein: The obtaining the second content of the interactive voice response system's response based on the first content includes: When the interactive voice response system receives the first content, obtain the voice content of the interactive voice response system; Perform automatic speech recognition on the voice content to obtain the second content.

7. The voice response anomaly detection method according to any one of claims 1-6, characterized in that: The method further includes: When the anomaly detection result indicates anomaly, perform an alarm according to the alarm strategy.

8. A voice response anomaly detection device, characterized in that, Including: A first call module, configured to make a first call to the telephone terminal and the interactive voice response system when the interactive voice response system is normal; A determination module, configured to determine the interaction content between the telephone terminal and the interactive voice response system, save the interaction content as a call test template, and end the first call; A second call module, configured to make a second call to the current interactive voice response system after a specified time interval; A detection module, configured to perform anomaly detection on the current interactive voice response system according to the call test template, and determine the anomaly detection result.

9. An electronic device, characterized in that, Comprising: A processor and a memory, wherein instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed, the method according to any one of claims 1 - 7 is implemented.

Images