Call hang-up method and device and computer readable storage medium

By obtaining user input information of the ASR layer and determining its intention, and hanging up the call directly when the intention is to end the conversation, the problem of low call hang-up efficiency in the prior art is solved, and more efficient call management is achieved.

CN119940530APending Publication Date: 2025-05-06SHENZHEN WORKEC TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411900549.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-23
Publication Date
2025-05-06

AI Technical Summary

Technical Problem

The existing calling system needs to hang up the call through a complex process when ending the call, resulting in low hangup efficiency.

Method used

By obtaining user input information from the ASR layer, the intent of the information is determined. If the intention is to end the conversation, the call will be hung up directly without performing other steps, which simplifies the hangup process.

Benefits of technology

It improves the efficiency of hang-up calls, reduces operation steps, and improves call satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119940530A_ABST
    Figure CN119940530A_ABST
Patent Text Reader

Abstract

The invention provides a call hanging-up method and device and a computer readable storage medium, relates to the technical field of computers, and can improve the call hanging-up efficiency. The method is applied to a call hanging-up device in a call system, the call system further comprises a large model layer and an ASR layer, the large model layer is used for determining reply information of information input by a user, and the method comprises the steps of obtaining first information from the ASR layer; the first information comprises information input by a user, and the first information is further sent to the large model layer by the ASR layer; determining intention information of the first information; the intention information is used for indicating dialogue ending or dialogue continuing; and when the intention information of the first information indicates that the conversation is ended, hanging up the conversation with the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a call hanging up method, device and computer-readable storage medium. Background Art

[0002] A call system is a system that can communicate with users.

[0003] When ending a call with a user, the call system usually needs to go through a relatively complicated process to hang up the call, and the efficiency of hanging up the call is low. Summary of the invention

[0004] The present application provides a call hanging up method, device and computer-readable storage medium, which can improve the efficiency of hanging up a call.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a call hanging up method is provided, and the method is applied to a call hanging up device in a call system, the call system also includes a large model layer and an ASR layer, the large model layer is used to determine reply information of information input by a user, and the method includes: obtaining first information from the ASR layer; the first information includes information input by the user, and the first information is also sent to the large model layer by the ASR layer; determining intent information of the first information; the intent information is used to indicate the end of the conversation or the continuation of the conversation; when the intent information of the first information indicates the end of the conversation, hanging up the call with the user.

[0007] Based on this solution, by obtaining the first information including the information input by the user from the ASR layer, thereafter, determining the intention information of the first information for indicating the end of the conversation or the continuation of the conversation, thereafter, when the intention information of the first information indicates the end of the conversation, the call with the user is hung up. Since the first information is also sent by the ASR layer to the large model layer for determining the reply information of the information input by the user, compared with the existing solution that performs a series of steps before hanging up the call with the user, the solution of the present application decouples the determination of the reply information of the information input by the user and the determination of the intention information of the first information in parallel. After determining that the intention information of the first information indicates the end of the call, it means that the user wants to end the conversation, and the call with the user can be hung up without performing other steps, thereby improving the efficiency of hanging up the call.

[0008] In combination with the first aspect, in certain embodiments of the first aspect, hanging up the call with the user includes: obtaining second information from the big model layer; the second information includes reply information of the first information; determining intent information of the second information; and hanging up the call with the user when the intent information of the second information indicates to end the conversation.

[0009] Based on this solution, when the intent information of the first message indicates to end the conversation, the second message including the reply information of the first message is obtained from the large model layer, and then the intent information of the second message is determined. Then, when the intent information of the second message indicates to end the conversation, the call with the user is hung up. The call with the user is hung up only when the intention of both parties on the call is to end the conversation, which can improve the satisfaction with the call.

[0010] In combination with the first aspect, in certain implementations of the first aspect, when the intention information of the second information indicates to continue the conversation, the call with the user is maintained.

[0011] In combination with the first aspect, in certain embodiments of the first aspect, when the intent information of the first message indicates to continue the conversation, the method also includes: obtaining second information from the big model layer; the second information includes reply information of the first message; determining the intent information of the second message; and hanging up the call with the user when the intent information of the second message indicates to end the conversation.

[0012] Based on this solution, when the intention information of the first message indicates to continue the conversation, the second message including the reply information of the first message is obtained from the large model layer, and then the intention information of the second message is determined. Then, when the intention information of the second message indicates to end the conversation, it means that the call system wants to end the conversation with the user. At this time, the call with the user can be hung up without performing other steps, thereby improving the efficiency of hanging up the call.

[0013] In combination with the first aspect, in certain embodiments of the first aspect, after hanging up the call with the user, the method further includes: sending third information to the large model layer; the third information is used to instruct the large model layer to stop determining reply information of the first information.

[0014] Based on this solution, the user will not receive a reply message to the first message after the call is hung up. After hanging up the call with the user, the third message is sent to the big model layer to instruct the big model layer to stop determining the reply message to the first message. Since the big model needs to pay a usage cost, such as time cost and economic cost, the usage cost of the call system can be reduced by making the big model layer stop determining the reply message to the first message.

[0015] In a second aspect, a call hanging device is provided for implementing the call hanging method of the first aspect. The call hanging device is included in a call system, and the call system also includes a large model layer and an ASR layer. The large model layer is used to determine the reply information of the information input by the user. The call hanging device includes a module, unit, or means corresponding to the above method, and the module, unit, or means can be implemented by hardware, software, or by hardware executing the corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions.

[0016] In combination with the second aspect, in certain embodiments of the second aspect, the device includes: an acquisition module and a processing module; the acquisition module is used to acquire first information from the ASR layer; the first information includes information input by the user, and the first information is also sent to the large model layer by the ASR layer; the processing module is used to determine the intention information of the first information; the intention information is used to indicate the end of the conversation or the continuation of the conversation; the processing module is also used to hang up the call with the user when the intention information of the first information indicates the end of the conversation.

[0017] In combination with the second aspect, in certain embodiments of the second aspect, the processing module is also used to hang up the call with the user, including: obtaining second information from the large model layer; the second information includes reply information of the first information; determining the intention information of the second information; and hanging up the call with the user when the intention information of the second information indicates to end the conversation.

[0018] In combination with the second aspect, in certain embodiments of the second aspect, when the intention information of the second information indicates to continue the conversation, the processing module is further used to maintain the call with the user.

[0019] In combination with the second aspect, in certain embodiments of the second aspect, when the intent information of the first message indicates to continue the conversation, the processing module is also used to: obtain second information from the large model layer; the second information includes reply information of the first message; determine the intent information of the second message; and hang up the call with the user when the intent information of the second message indicates to end the conversation.

[0020] In combination with the second aspect, in certain embodiments of the second aspect, after hanging up the call with the user, the processing module is also used to: send a third message to the large model layer; the third information is used to instruct the large model layer to stop determining the reply information of the first message.

[0021] According to a third aspect, a call hanging device is provided, comprising: at least one processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement the method provided in the first aspect and any possible implementation manner thereof.

[0022] In a fourth aspect, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of a call hanging device, the call hanging device is enabled to execute the method provided in the first aspect and any possible implementation manner thereof.

[0023] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method provided in the first aspect and any possible implementation manner thereof.

[0024] Among them, the technical effects brought about by any implementation of the second to fifth aspects can refer to the technical effects brought about by different implementations of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of the architecture of a call system provided for this application;

[0026] Figure 2 A schematic diagram of the architecture of another call system provided by the present application;

[0027] Figure 3 A flowchart of a call hanging up method provided by this application;

[0028] Figure 4 A flowchart of another call hanging up method provided by the present application;

[0029] Figure 5 A schematic diagram of the structure of a call hanging device provided in this application;

[0030] Figure 6 A structural schematic diagram of another call hanging up device provided in the present application. DETAILED DESCRIPTION

[0031] In the description of this application, unless otherwise specified, "plurality" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0032] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0033] Meanwhile, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0034] It is understood that the "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments in the entire specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It is understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0035] It can be understood that in the present application, "when", "if" and "if" all mean that corresponding processing will be carried out under certain objective circumstances, but do not limit the time, nor do they require judgment actions when implementing them, nor do they mean the existence of other limitations.

[0036] It can be understood that some optional features in the embodiments of the present application may be implemented independently in certain scenarios without relying on other features, such as the solution on which they are currently based, to solve corresponding technical problems and achieve corresponding effects, or may be combined with other features according to needs in certain scenarios. Accordingly, the devices provided in the embodiments of the present application may also realize these features or functions accordingly, which will not be elaborated here.

[0037] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments in this application, and the various implementation methods in each embodiment, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments and the various implementation methods in each embodiment are consistent and can be referenced to each other. The technical features in different embodiments and the various implementation methods in each embodiment can be combined to form new embodiments, implementation methods, implementation methods, or implementation methods according to their inherent logical relationships. The following implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0038] The call system is a machine system that can talk with the user. For example, the call system can be a chat robot.

[0039] Figure 1 A schematic diagram of the architecture of a call system provided for this application, such as Figure 1 As shown, the call hanging system 10 includes a telephone system layer 11, an automatic speech recognition (ASR) layer 12, a large model layer 13 and a text-to-speech (TTS) layer 14.

[0040] The telephone system layer 11 is used to handle specific call-related services, such as connecting a call with a user, hanging up a call with a user, distinguishing the types of calls, intercepting calls, persisting call records, etc. After connecting a call with a user, the telephone system layer will perform some services, such as authority verification or record persistence.

[0041] The voice information input by the user can be transmitted to the ASR layer 12 through the telephone system layer 11 .

[0042] The ASR layer 12 is used to convert the voice information input by the user into text information and transmit the text information to the large model layer 13.

[0043] The large model layer 13 is used to determine the reply information of the information input by the user. It can perform in-depth analysis on the text information converted from the voice information input by the user through a large language model (LLM), then generate reply text information, and pass the reply text information to the TTS layer 14. LLM can be, for example, GPT, Wenxinyiyan, etc.

[0044] The TTS layer 14 is used to convert the text information output by the large model layer 13 into voice information, and output the voice information to the user through the telephone system layer 11.

[0045] In this call system, when ending a call with a user, the telephone system layer 11 needs to determine whether the large model layer 13 is generating a reply text message. If the large model layer 13 is generating a reply text message, it is necessary to wait for the large model layer 13 to complete the generation. After that, the telephone system layer 11 also needs to determine whether the reply text message is output to the user through the TTS 14 layer and determine whether the user has not input voice information within a certain period of time. At this time, the call with the user can be hung up.

[0046] Therefore, when ending a call with a user, existing solutions usually require a relatively complicated process to hang up the call. Any lag in any link in the process will result in an inability to hang up the call with the user, and the efficiency of hanging up the call is low.

[0047] To solve the above problems, this application provides a call hanging up method. Figure 2This is a schematic diagram of the architecture of another call hang-up system provided by the present application. The call hang-up method provided by the present application can be applied to Figure 2 The call hanging device in the call hanging system shown in FIG. Figure 2 As shown, the call hanging system 20 includes a call hanging device 21, a telephone system layer 22, an ASR layer 23, a large model layer 24 and a TTS layer 25.

[0048] The detailed description of the telephone system layer 22, the ASR layer 23, the large model layer 24 and the TTS layer 25 can be referred to in Figure 1 The description of the corresponding parts in this application will not be repeated here.

[0049] The call hanging device 21 can receive information from the ASR layer 23 and the large model layer 24, and send instructions to the telephone system layer 22.

[0050] The call hanging up device 21 can execute the call hanging up method provided in this application.

[0051] In practical applications, the call hanging up method provided in the embodiment of the present application can be applied to the call hanging up device 21, and can also be applied to the devices included in the call hanging up device 21.

[0052] The following describes the call hanging up method provided in the embodiment of the present application by taking the call hanging up method applied to the call hanging up device 21 as an example in conjunction with the accompanying drawings.

[0053] Figure 3 A flowchart of a call hanging up method provided by this application, such as Figure 3 As shown, the method comprises the following steps:

[0054] S301. The call hanging device obtains first information from the ASR layer.

[0055] The first information includes information input by the user, and the first information is also sent by the ASR layer to the large model layer.

[0056] It should be noted that the first information is in the form of text.

[0057] As a possible implementation, combining Figure 1 The voice information input by the user is transmitted to the ASR layer through the telephone system layer, and the ASR layer converts the voice information input by the user into text information to obtain the first information.

[0058] The ASR layer sends the first information to the call hanging device and the large model layer.

[0059] Correspondingly, the call hanging device receives the first information from the ASR layer and executes S302. The large model layer receives the first information from the ASR layer and determines the reply information of the first information.

[0060] S302: The call hanging device determines the intention information of the first information.

[0061] The intention information is used to indicate whether to end the conversation or continue the conversation.

[0062] As a possible implementation, the call hanging device detects whether there is a preset keyword in the first message. If the preset keyword exists in the first message, it is determined that the intention information of the first message indicates to end the conversation; if the preset keyword does not exist in the first message, it is determined that the intention information of the first message indicates to continue the conversation.

[0063] Exemplarily, the preset keywords may include goodbye and bye. Of course, the preset keywords may also include other words, and this application does not impose any specific limitation on this.

[0064] As another possible implementation, the call hanging device determines the vector information of the first message, compares the vector information of the first message with the preset vector information, and obtains the vector similarity. If the vector similarity is greater than the preset similarity threshold, it is determined that the intention information of the first message indicates to end the conversation, and if the vector similarity is less than or equal to the preset similarity threshold, it is determined that the intention information of the first message indicates to continue the conversation.

[0065] Exemplarily, the preset similarity threshold may be 90% or 85%. Of course, the preset similarity threshold may also be other values, and the present application does not impose any specific limitation on this.

[0066] As another possible implementation, the call hanging device determines to input the first information and a preset instruction for indicating the determination of the intention information into a preset model, and the preset model outputs the intention information of the first information.

[0067] Exemplarily, the preset model may be GPT or Wenxinyiyan. Of course, the preset model may also be other models, and this application does not impose any specific limitation on this.

[0068] S303: When the intention information in the first message indicates to end the conversation, the call hanging-up device hangs up the call with the user.

[0069] As a possible implementation manner, the call hanging up device determines whether the intention information of the first information indicates to end the conversation.

[0070] When the intention information of the first information indicates to end the conversation, the call hanging-up device sends instruction information for instructing to hang up the call with the user to the telephone system layer.

[0071] Correspondingly, the telephone system layer receives the instruction information for instructing to hang up the call with the user, and hangs up the call with the user.

[0072] Optionally, after the call hanging up device hangs up the call with the user, the call hanging up device sends third information to the big model layer.

[0073] The third information is used to instruct the large model layer to stop determining the reply information of the first information.

[0074] After the call is hung up, the user will not receive a reply message to the first message. After hanging up the call with the user, the third message is sent to the big model layer to instruct the big model layer to stop determining the reply message to the first message. Since the big model needs to pay a usage cost, such as time cost and economic cost, the usage cost of the call system can be reduced by making the big model layer stop determining the reply message to the first message.

[0075] As another possible implementation, the call hanging up device obtains second information from the large model layer; the second information includes reply information of the first information; determines the intention information of the second information; and hangs up the call with the user when the intention information of the second information indicates to end the conversation.

[0076] It should be noted that the specific description of this possible implementation method can refer to the relevant description in the subsequent part of the specific implementation method of this application, and this application will not explain it here.

[0077] Based on S301-S303, by obtaining the first information including the information input by the user from the ASR layer, thereafter, determining the intent information of the first information for indicating the end of the conversation or the continuation of the conversation, thereafter, when the intent information of the first information indicates the end of the conversation, the call with the user is hung up. Since the first information is also sent by the ASR layer to the large model layer for determining the reply information of the information input by the user, compared with the existing solution that performs a series of steps before hanging up the call with the user, the solution of the present application decouples the determination of the reply information of the information input by the user and the determination of the intent information of the first information in parallel. After determining that the intent information of the first information indicates the end of the call, it means that the user wants to end the conversation, and the call with the user can be hung up without performing other steps, thereby improving the efficiency of hanging up the call.

[0078] The above is a general description of the call hanging up method provided by the present application. The call hanging up method provided by the present application will be further described below in conjunction with the accompanying drawings.

[0079] In one design, Figure 4 A flowchart of another call hanging up method provided by this application is as follows: Figure 4As shown, S303 provided in the specific implementation manner of the present application may specifically include the following multiple steps:

[0080] S401. The call hanging device obtains second information from the large model layer.

[0081] The second information includes reply information of the first information.

[0082] It should be noted that the second information is in the form of text.

[0083] As a possible implementation, combining Figure 1 , the call hanging device sends a request message for requesting the second information to the large model layer. Correspondingly, the large model layer receives the request message from the call hanging device.

[0084] After the large model layer generates the second information, it sends a response message including the second information to the call hanging device. Correspondingly, the call hanging device receives the response information from the large model layer and obtains the second information from the response information.

[0085] S402: The call hanging-up device determines the intention information of the second information.

[0086] As a possible implementation method, the call hanging up device detects whether there is a preset keyword in the second information. If the preset keyword exists in the second information, it determines that the intention information of the second information indicates to end the conversation; if the preset keyword does not exist in the second information, it determines that the intention information of the second information indicates to continue the conversation.

[0087] As another possible implementation method, the call hang-up device determines the vector information of the second information, compares the vector information of the second information with the preset vector information, and obtains the vector similarity. If the vector similarity is greater than the preset similarity threshold, it is determined that the intention information of the second information indicates to end the conversation; if the vector similarity is less than or equal to the preset similarity threshold, it is determined that the intention information of the second information indicates to continue the conversation.

[0088] As another possible implementation, the call hanging device determines to input the second information and a preset instruction for indicating the determination of the intention information into a preset model, and the preset model inputs the intention information of the second information.

[0089] S403: When the intention information in the second information indicates to end the conversation, the call hanging-up device hangs up the call with the user.

[0090] As a possible implementation manner, the call hanging up device determines whether the intention information of the second information indicates to end the conversation.

[0091] When the intention information of the second information indicates to end the conversation, the call hanging-up device sends instruction information for instructing to hang up the call with the user to the telephone system layer.

[0092] Correspondingly, the telephone system layer receives the instruction information for instructing to hang up the call with the user, and hangs up the call with the user.

[0093] In the case that the intention information of the second message indicates to continue the conversation, the call hanging device maintains the call with the user.

[0094] Based on S401-S403, when the intent information of the first message indicates to end the conversation, the second message including the reply information of the first message is obtained from the large model layer, and then the intent information of the second message is determined. Then, when the intent information of the second message indicates to end the conversation, the call with the user is hung up. The call with the user is hung up only when the intention of both parties on the call is to end the conversation, which can improve the satisfaction with the call.

[0095] In one design, when the intention information of the first message indicates to continue the conversation, the call hanging up method provided by the present application may further include the following steps:

[0096] S501. The call hanging device obtains second information from the large model layer.

[0097] The second information includes reply information of the first information.

[0098] It should be noted that the specific description of S501 can refer to the relevant description of S401, which will not be repeated here.

[0099] S502: The call hanging device determines the intention information of the second information.

[0100] It should be noted that the specific description of S502 can refer to the relevant description of S402, which will not be repeated here.

[0101] S503: When the intention information in the second information indicates to end the conversation, the call hanging-up device hangs up the call with the user.

[0102] It should be noted that the specific description of S503 can refer to the relevant description of S403, which will not be repeated here.

[0103] Based on S501-S503, when the intention information of the first message indicates to continue the conversation, the second message including the reply information of the first message is obtained from the large model layer, and then the intention information of the second message is determined. Then, when the intention information of the second message indicates to end the conversation, it means that the call system wants to end the conversation with the user. At this time, the call with the user can be hung up without performing other steps, thereby improving the efficiency of hanging up the call.

[0104] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the call hang-up device executing the call hang-up method. In order to achieve the above functions, the call hang-up device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0105] The embodiment of the present application can divide the function modules of the call hang-up device according to the above method example. For example, each function module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software function modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, the "module" here may refer to a specific application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0106] In the case of functional module division, Figure 5 A schematic diagram of the structure of a call hanging device is shown. Figure 5 As shown, the call hanging device 50 includes an acquisition module 501 and a processing module 502 .

[0107] In some embodiments, the call hanging device 50 may further include a storage module ( Figure 5 ), for storing program instructions and data.

[0108] Among them, the acquisition module 501 is used to obtain the first information from the ASR layer; the first information includes information input by the user, and the first information is also sent to the large model layer by the ASR layer; the processing module 502 is used to determine the intention information of the first information; the intention information is used to indicate the end of the conversation or the continuation of the conversation; the processing module 502 is also used to hang up the call with the user when the intention information of the first information indicates the end of the conversation.

[0109] Optionally, the processing module 502 is also used to hang up the call with the user, including: obtaining second information from the large model layer; the second information includes reply information of the first information; determining the intention information of the second information; and hanging up the call with the user when the intention information of the second information indicates to end the conversation.

[0110] Optionally, when the intention information in the second information indicates to continue the conversation, the processing module 502 is further used to maintain the call with the user.

[0111] Optionally, when the intention information of the first message indicates to continue the conversation, the processing module 502 is also used to: obtain second information from the large model layer; the second information includes reply information of the first message; determine the intention information of the second message; and hang up the call with the user when the intention information of the second message indicates to end the conversation.

[0112] Optionally, after hanging up the call with the user, the processing module 502 is further used to: send a third message to the large model layer; the third message is used to instruct the large model layer to stop determining the reply information of the first message.

[0113] All relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0114] When the functions of the above functional modules are implemented in the form of hardware, Figure 6 A structural diagram of another call hanging device is shown. Figure 6 As shown, the call hanging device 60 includes a processor 601, a memory 602 and a bus 603. The processor 601 and the memory 602 may be connected via the bus 603.

[0115] The processor 601 is the control center of the call hanging device 60, which can be a processor or a general term for multiple processing elements. For example, the processor 601 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0116] As an embodiment, the processor 601 may include one or more CPUs, such as Figure 6 CPU0 and CPU1 are shown in the figure.

[0117] The memory 602 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0118] As a possible implementation, the memory 602 may exist independently of the processor 601, and the memory 602 may be connected to the processor 601 via a bus 603, and is used to store instructions or program codes. When the processor 601 calls and executes the instructions or program codes stored in the memory 602, the call hanging method provided in the embodiment of the present application can be implemented.

[0119] In another possible implementation, the memory 602 may also be integrated with the processor 601 .

[0120] The bus 603 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0121] It should be pointed out that Figure 6 The structure shown does not constitute a limitation on the call hanging device 60. Figure 6 In addition to the components shown, the call hang-up device 60 may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0122] As an example, combining Figure 5The functions implemented by the acquisition module 501 and the processing module 502 in the call hanging device 50 are similar to those Figure 6 The function of processor 601 in is the same.

[0123] Optional, such as Figure 6 As shown, the call hanging device 60 provided in the embodiment of the present application may further include a communication interface 604 .

[0124] The communication interface 604 is used to connect with other devices through a communication network. The communication network may be Ethernet, wireless access network, wireless local area network (WLAN), etc. The communication interface 604 may include a receiving unit for receiving data and a sending unit for sending data.

[0125] In a possible implementation, in the call hanging device 60 provided in the embodiment of the present application, the communication interface 604 may also be integrated in the processor 601, which is not specifically limited in the embodiment of the present application.

[0126] As a possible product form, the call hanging device of the embodiment of the present application can also be implemented using the following: one or more field programmable gate arrays (FPGA), programmable logic devices (PLD), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits that can perform the various functions described throughout the present application.

[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0128] An embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed, the computer executes each step in the method flow shown in the above method embodiment.

[0129] An embodiment of the present application provides a computer program product including instructions. When the instructions are executed on a computer, the computer is caused to execute each step in the method flow shown in the above method embodiment.

[0130] An embodiment of the present application provides a chip system, including: a processor and an interface circuit; the interface circuit is used to receive a computer program or instruction and transmit it to the processor; the processor is used to execute the computer program or instruction so that the chip system executes each step in the method flow shown in the above method embodiment.

[0131] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, and a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), registers, hard disks, optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any other form of computer-readable storage media in a suitable combination of the above, or numerical values ​​in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in a specific-purpose ASIC. In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0132] Since the call hang-up device, computer-readable storage medium, and computer program product provided in this embodiment can be applied to the call hang-up method provided in this embodiment, the technical effects that can be obtained can also refer to the above-mentioned method embodiments, and the embodiments of this application will not be repeated here.

[0133] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0134] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for hanging up a call, characterized in that: The method is applied to a call hanging device in a call system, wherein the call system further comprises a large model layer and an ASR layer, wherein the large model layer is used to determine reply information of information input by a user, and the method comprises: Acquire first information from the ASR layer; the first information includes information input by a user, and the first information is also sent by the ASR layer to the large model layer; Determining intention information of the first information; the intention information is used to indicate ending the conversation or continuing the conversation; When the intention information of the first information indicates to end the conversation, hang up the call with the user.

2. The method according to claim 1, characterized in that The hanging up the call with the user comprises: Acquire second information from the large model layer; the second information includes reply information of the first information; determining intent information of the second information; When the intention information of the second information indicates to end the conversation, hang up the call with the user.

3. The method according to claim 2, characterized in that When the intention information of the second information indicates to continue the conversation, maintain the call with the user.

4. The method according to claim 1, characterized in that: In the case where the intention information of the first information indicates to continue the conversation, the method further includes: Acquire second information from the large model layer; the second information includes reply information of the first information; determining intent information of the second information; When the intention information of the second information indicates to end the conversation, hang up the call with the user.

5. The method according to claim 1, characterized in that After hanging up the call with the user, the method further includes: Sending third information to the large model layer; the third information is used to instruct the large model layer to stop determining reply information of the first information.

6. A call hanging device, characterized in that: The call hanging device is included in a call system, the call system also includes a large model layer and an ASR layer, the large model layer is used to determine the reply information of the information input by the user, and the device includes: an acquisition module and a processing module; The acquisition module is used to acquire first information from the ASR layer; the first information includes information input by a user, and the first information is also sent by the ASR layer to the large model layer; The processing module is used to determine the intention information of the first information; the intention information is used to indicate to end the conversation or continue the conversation; The processing module is further configured to hang up the call with the user when the intention information of the first information indicates to end the conversation.

7. The device according to claim 6, characterized in that The processing module is further used to hang up the call with the user, including: Acquire second information from the large model layer; the second information includes reply information of the first information; determining intent information of the second information; When the intention information of the second information indicates to end the conversation, hang up the call with the user.

8. The device according to claim 6, characterized in that When the intention information of the second information indicates to continue the conversation, the processing module is further used to maintain the call with the user.

9. A call hanging device, characterized in that: The call hanging device comprises: a processor, the processor is coupled to a memory, the memory is used to store programs or instructions, when the program or instructions are executed by the processor, the device executes the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instructions are executed, the computer is caused to perform the method according to any one of claims 1 to 5.