Man-machine conversation method and device

Abstract

The invention discloses a man-machine conversation method and device, and relates to the technical field of artificial intelligence. A specific embodiment of the method comprises the steps of monitoring whether user global session information in a process meets a preset bypass trigger condition or not in the process of performing a conversation with a user based on a pre-established main session tree; wherein the bypass triggering condition corresponds to a preset system action; when it is monitored that the user global session information meets the bypass triggering condition, bypass return information is determined based on a system action corresponding to the bypass triggering condition; and determining a current session node of the main session tree, and replacing the information in the current session node with the bypass return information and outputting the bypass return information to a user. According to the embodiment, the main dialogue tree can be prevented from being changed when the demand is changed through bypass logic configuration for the main dialogue tree, and the reusability between the main dialogue trees is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a human-computer dialogue method and device. Background Art

[0002] Human-computer dialogue refers to the interaction between machines and people through understanding and using natural language. In the current human-computer dialogue process, the machine side can communicate with people based on a pre-established dialogue tree. The dialogue tree structure is relatively complex and contains intent processing logic to deal with various user intentions. When the demand changes or adjusts, the existing technology generally needs to adjust the dialogue tree. In actual applications, some intent processing logic is frequently used, or has customized requirements, or has temporary characteristics. If all these intent processing logics are reflected in the dialogue tree, it is necessary to make a full change to the dialogue tree for each application scenario, which is labor-intensive and costly, and the reusability between the dialogue trees is poor. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a human-computer dialogue method and device, which can avoid changes to the main dialogue tree when requirements change by configuring bypass logic for the main dialogue tree, and improve the reusability between main dialogue trees.

[0004] To achieve the above objective, according to one aspect of the present invention, a human-computer dialogue method is provided.

[0005] The human-computer dialogue method of the embodiment of the present invention includes: in the process of dialogue with the user based on the pre-established main dialogue tree, whether the user's global conversation information in the process meets the preset bypass trigger condition; wherein the bypass trigger condition corresponds to the preset system action; when it is monitored that the user's global conversation information meets the bypass trigger condition, the bypass return information is determined based on the system action corresponding to the bypass trigger condition; the current conversation node of the main dialogue tree is determined, and the bypass return information is output to the user instead of the information in the current conversation node.

[0006] Optionally, the bypass triggering condition includes: the user demonstrates a specific intention in N rounds of conversation; N is an integer not less than 1; and whether the user's global conversation information during the monitoring process meets the preset bypass triggering condition, including: using a pre-trained natural language processing model to determine the user's intention in each round of conversation; in response to the intention including a specific intention, accumulating the number of conversation rounds corresponding to the specific intention; in response to the number of conversation rounds reaching N, determining that the user's global conversation information meets the bypass triggering condition.

[0007] Optionally, the bypass trigger condition includes: a conditional expression containing at least one specific word; and whether the user global session information in the monitoring process meets the preset bypass trigger condition includes: determining whether the text information converted from the user session information of the current round matches the conditional expression.

[0008] Optionally, the system action includes: broadcasting specific voice information to the user; and determining the bypass return information based on the system action corresponding to the bypass trigger condition, including: determining the specific voice information as the bypass return information.

[0009] Optionally, the method further includes: after outputting to the user instead of the information in the current conversation node with the bypass return information, continuing the conversation with the user based on the current conversation node and the main conversation tree.

[0010] Optionally, bypass trigger conditions and system actions are pre-configured for the main dialog tree.

[0011] To achieve the above objective, according to another aspect of the present invention, a human-computer dialogue device is provided.

[0012] The human-machine dialogue device of the embodiment of the present invention may include: a monitoring unit, an information determination unit and an output unit.

[0013] The monitoring unit is used to monitor whether the user's global session information meets the preset bypass trigger condition during the process of communicating with the user based on the pre-established main dialogue tree; the bypass trigger condition corresponds to the preset system action; the information determination unit is used to determine the bypass return information based on the system action corresponding to the bypass trigger condition when it is monitored that the user's global session information meets the bypass trigger condition; the output unit is used to determine the current session node of the main dialogue tree, and output the bypass return information to the user instead of the information in the current session node.

[0014] Optionally, the bypass trigger condition includes: the user demonstrates a specific intention in N rounds of conversation; N is an integer not less than 1; and the monitoring unit can be further used to: determine the user's intention in each round of conversation using a pre-trained natural language processing model; in response to the intention including a specific intention, accumulate the number of conversation rounds corresponding to the specific intention; in response to the number of conversation rounds reaching N, determine that the user's global session information meets the bypass trigger condition.

[0015] Optionally, the bypass triggering condition includes: a conditional expression containing at least one specific word; and the monitoring unit may be further configured to: determine whether the text information converted from the user session information of the current round matches the conditional expression.

[0016] Optionally, the system action includes: broadcasting specific voice information to the user; and the information determination unit may be further used to: determine the specific voice information as bypass return information.

[0017] Optionally, the device further includes a recovery unit for continuing the dialogue with the user based on the current conversation node and the main dialogue tree after outputting the bypass return information to the user instead of the information in the current conversation node.

[0018] Optionally, bypass trigger conditions and system actions are pre-configured for the main dialog tree.

[0019] To achieve the above objective, according to another aspect of the present invention, an electronic device is provided.

[0020] An electronic device of the present invention includes: one or more processors; a storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the human-computer dialogue method provided by the present invention.

[0021] To achieve the above objective, according to yet another aspect of the present invention, a computer-readable storage medium is provided.

[0022] A computer-readable storage medium of the present invention stores a computer program, and when the program is executed by a processor, the human-computer dialogue method provided by the present invention is implemented.

[0023] To achieve the above objective, according to yet another aspect of the present invention, a computer program product is provided.

[0024] A computer program product of the present invention includes a computer program, and when the computer program is executed by a processor, the human-computer dialogue method provided by the present invention is implemented.

[0025] According to the technical solution of the present invention, the embodiments of the above invention have the following advantages or beneficial effects: Pre-configure bypass trigger conditions and corresponding system actions for the main dialog tree. Bypass trigger conditions and system actions can be used to represent intent processing logic that is frequently used, customized, or temporary. The intent processing logic is executed independently of the main dialog tree logic, and the main dialog tree is not modified. When the user's global session information is detected to meet the bypass trigger conditions, the server can determine the bypass return information to output to the user based on the system action corresponding to the bypass trigger conditions. By configuring bypass logic for the main dialog tree, various intent processing logics are implemented, forming a beneficial supplement to the main dialog tree, avoiding changes to the main dialog tree when demand adjustments are made, and reducing operation and maintenance costs. The bypass logic can be reused between the required main dialog trees, and can also reflect customized logic, thereby taking into account the customization and reusability requirements of human-computer dialogue.

[0026] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention. Figure 1 Schematic diagram of the main steps of the human-computer dialogue method in an embodiment of the present invention; Figure 2 Schematic diagram of the human-computer dialogue method in an embodiment of the present invention; Figure 3 is a schematic diagram of specific execution steps of the human-computer dialogue method in an embodiment of the present invention; Figure 4 is a schematic diagram of the main dialogue tree structure of an embodiment of the present invention; Figure 5 It is a schematic diagram of components of a human-machine dialogue device in an embodiment of the present invention; Figure 6 is an exemplary system architecture diagram in which embodiments of the present invention may be applied; Figure 7 It is a schematic diagram of the structure of an electronic device used to implement the human-computer dialogue method in the embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0029] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0030] Figure 1 It is a schematic diagram of the main steps of the human-computer dialogue method in an embodiment of the present invention.

[0031] like Figure 1 As shown, the human-machine dialogue method of the embodiment of the present invention can be executed by a server supporting the machine end, and the specific execution steps are as follows: Step S101: In the process of communicating with the user based on the pre-established main dialogue tree, monitor whether the user's global conversation information in the process meets the preset bypass trigger condition. The bypass trigger condition is configured to correspond to the preset system action. In actual application, the bypass logic (including bypass trigger conditions and system actions) can be configured for the main dialogue tree of the specific human-computer dialogue scene as needed, and the bypass logic can be used between multiple main dialogue trees.

[0032] Step S102: when it is detected that the user global session information meets the bypass triggering condition, the bypass return information is determined based on the system action corresponding to the bypass triggering condition.

[0033] Step S103: Determine the current conversation node of the main dialog tree, and output the bypass return information to the user instead of the information in the current conversation node. In this step, when the bypass logic is satisfied, the bypass return information determined by the bypass logic can be output to the user first.

[0034] In this way, by configuring bypass logic for the main dialogue tree, various intent processing logics can be implemented, forming a beneficial supplement to the main dialogue tree, avoiding changes to the main dialogue tree when requirements are adjusted, and reducing operation and maintenance costs. The bypass logic can be reused between the required main dialogue trees, and can also reflect customized logic, thus taking into account the customization and reusability requirements of human-computer dialogue.

[0035] The following specifically describes the human-computer dialogue method of the embodiment of the present invention. Figure 2-4 .

[0036] Step S301: Pre-configure bypass trigger conditions and system actions for the main dialog tree. In this step, the bypass logic is pre-configured for the main dialog tree that needs to be bypassed. The above main dialog tree, in contrast to the bypass logic, refers to the tree structure that the human-computer dialog depends on. Generally, the main dialog tree that is suitable can be pre-specified according to the business type, application scenario and user category. A main dialog tree can be constructed based on the preset session information on the machine side and the intention reflected in the session information that the user may enter, such as Figure 4 shown.

[0037] exist Figure 4 In the main dialog tree, each possible conversation between the user and the machine is a node, and a conversation between the user and the machine is called a round. Figure 4There are three rounds in total. The session information of the machine side is pre-configured. The machine side enters the corresponding branch according to the session information of the user side and the intention embodied therein, and returns the preset session content of the corresponding branch. In practical applications, the machine side can implement the main human-computer dialogue process based on the main dialogue tree. However, the dialogue tree structure in the specific scenario is relatively complex, with a large number of nodes. If it is changed or adjusted to meet diverse needs, the workload is large and the cost is high. In particular, for the intention processing logic with high frequency of use, customization requirements, or temporary characteristics, the way to adjust the main dialogue tree is very inflexible. In response to the above problems, the embodiment of the present invention configures bypass logic for the main dialogue tree, forms a main dialogue tree to determine the main dialogue process, and the bypass logic determines the auxiliary process. In particular, for the intention processing logic with high frequency of use, customization requirements, or temporary characteristics, the bypass logic provides convenient support in the form of flexible recording and customized configuration, thereby improving the maintainability and component reusability of the human-computer dialogue system.

[0038] In this step, bypass trigger conditions and system actions can be configured in advance for the main dialogue tree. The trigger conditions can support various applicable forms. In one embodiment, the bypass trigger condition includes: the user reflects a specific intention in N rounds of dialogue; N is an integer not less than 1. In this case, the user emphasizes the specific intention in multiple rounds of dialogue, and a corresponding reply can be made based on the bypass logic. In another embodiment, the bypass trigger condition includes: a conditional expression containing at least one specific word, such as a regular expression. In this case, the text information converted from the user session information can be matched with the conditional expression. If the match is successful, the bypass trigger condition is satisfied. In another embodiment, the bypass trigger condition includes: the user reflects a certain number of first intentions and a certain number of second intentions in multiple rounds of dialogue, that is, the first intention is x times and the second intention is y times, x and y are both integers not less than 1, and both represent the number of dialogue rounds. In this case, the user emphasizes a certain number of intentions and a certain number of second intentions in multiple rounds of dialogue, and a corresponding reply can be made based on the bypass logic.

[0039] System actions can be configured according to actual needs, for example, may include: broadcasting predetermined specific voice information to the user, querying results based on keywords and feeding back to the user, etc.

[0040] Step S302: The server performs a human-computer dialogue based on the main dialogue tree. In this step, the server dialogues with the user based on the main dialogue tree and determines the next node according to the current node and the intention of the user's conversation.

[0041] Step S303: The server monitors whether the bypass trigger condition is met. After receiving the user's voice, the server performs voice recognition and intent recognition, and executes the main dialogue process according to the main dialogue tree. For the pre-configured bypass logic, the server can perform corresponding monitoring according to the bypass trigger condition. For example, if the bypass trigger condition is: the user shows a specific intention in N rounds of dialogue, the server monitoring method is: first use the pre-trained natural language processing model to determine the user's intention in each round of dialogue, and in response to the intention including a specific intention, accumulate the number of dialogue rounds corresponding to the specific intention; in response to the number of dialogue rounds reaching N, determine that the user's global conversation information meets the bypass trigger condition. If the bypass trigger condition includes: a conditional expression containing at least one specific word, the server monitoring method is: determine whether the text information converted from the user conversation information of the current round matches the conditional expression, and if it matches, it meets the bypass trigger condition.

[0042] If the bypass triggering condition includes: the user expresses the first intention x times and the second intention y times in multiple rounds of conversations, the server monitors the first intention and the second intention separately and accumulates the corresponding times. When the first intention is monitored to reach x times and the second intention is monitored to reach y times, the bypass triggering condition is met. If the server determines that the bypass triggering condition is met, step S304 is executed. If the server determines that the bypass triggering condition is not met, the process returns to step S303.

[0043] Step S304: The server determines the bypass return information according to the system action. In this step, the server may return information to the user according to the system action corresponding to the bypass trigger condition, that is, output the bypass return information to the user. In the case where the system action is to broadcast a predetermined specific voice information to the user, the server may determine the specific voice information as the bypass return information. In the case where the system action is to query the results based on keywords and feed back to the user, the server may query based on the keywords in the historical rounds, and then determine the bypass return information based on the query results.

[0044] For example, in a scenario involving repayment, the bypass logic pre-configured for the main dialogue tree is: the bypass trigger condition is that the user expresses repayment difficulty (intention) three times, and the system action is to output to the user "I understand your situation, can you ask a friend for help and pay off the overdue portion first?" The server will output the above content when it detects that the user's intention is to have repayment difficulty in three rounds.

[0045] Step S305: The server determines the current conversation node of the main conversation tree. In this step, the server determines the current conversation node according to the execution logic of the main conversation tree.

[0046] Step S306: The server outputs the bypass return information to the user instead of the information in the current conversation node. In this step, the server outputs the bypass return information first, that is, outputs the bypass return information to the user instead of the information in the current conversation node. It can be understood that the server can synthesize the text information into voice and broadcast it to the user.

[0047] Step S307: The server returns to the current session node and continues to execute the conversation based on the main conversation tree. In this step, when executing the bypass logic, the server maintains the session state in the main conversation tree. After the bypass logic is executed, the server continues to execute the conversation with the user based on the current session node and the main conversation tree, and continues to monitor the timing when the bypass trigger condition is met.

[0048] In the technical solution of the embodiment of the present invention, a bypass dialogue process that can be triggered globally is defined outside the main dialogue tree, wherein the user intention and the number of triggers are combined to form a trigger condition configuration that runs through the global context, the processing result is shared with the main dialogue tree context, and the information on the triggering of the bypass dialogue process is broadcasted preferentially, thereby facilitating the operator to perform refined configuration of the bypass dialogue process.

[0049] It should be noted that the collection, collection, update, analysis, processing, use, transmission, storage and other aspects of user personal information that may be involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0050] For the above-mentioned method embodiments, for the convenience of description, they are expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, and some steps can actually be performed in other orders or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the present invention.

[0051] In order to better implement the above-mentioned solution of the embodiment of the present invention, relevant devices for implementing the above-mentioned solution are also provided below.

[0052] See also Figure 5 As shown, the human-machine dialogue device 500 provided by the embodiment of the present invention may include: a monitoring unit 501 , an information determining unit 502 , and an output unit 503 .

[0053] Among them, the monitoring unit 501 is used to monitor whether the user's global session information in the process meets the preset bypass trigger condition during the dialogue with the user based on the pre-established main dialogue tree; wherein the bypass trigger condition corresponds to the preset system action; the information determination unit 502 is used to determine the bypass return information based on the system action corresponding to the bypass trigger condition when it is monitored that the user's global session information meets the bypass trigger condition; the output unit 503 is used to determine the current session node of the main dialogue tree, and output the bypass return information to the user instead of the information in the current session node.

[0054] In an embodiment of the present invention, the bypass triggering condition includes: the user demonstrates a specific intention in N rounds of conversation; N is an integer not less than 1; and the monitoring unit 501 can be further used to: determine the user's intention in each round of conversation using a pre-trained natural language processing model; in response to the intention including a specific intention, accumulate the number of conversation rounds corresponding to the specific intention; in response to the number of conversation rounds reaching N, determine that the user's global session information meets the bypass triggering condition.

[0055] As a preferred solution, the bypass trigger condition includes: a conditional expression containing at least one specific word; and the monitoring unit 501 can be further used to: determine whether the text information converted from the user session information of the current round matches the conditional expression.

[0056] Preferably, the system action includes: broadcasting the specific voice information to the user; and the information determination unit 502 can be further used to: determine the specific voice information as bypass return information.

[0057] In one embodiment, the apparatus 500 further comprises a recovery unit for continuing the dialogue with the user based on the current dialogue node and the main dialogue tree after outputting the bypass return information to the user instead of the information in the current dialogue node.

[0058] Furthermore, in the embodiment of the present invention, the bypass triggering conditions and system actions are pre-configured for the main dialog tree.

[0059] According to the technical solution of the embodiment of the present invention, bypass trigger conditions and corresponding system actions are configured for the main dialogue tree in advance. The bypass trigger conditions and system actions can be used to represent the intention processing logic with high frequency of use, customized requirements, or temporary characteristics. The intention processing logic is executed independently from the main dialogue tree logic, and the main dialogue tree is not changed. When it is monitored that the user's global session information meets the bypass trigger condition, the server can determine the bypass return information to output to the user based on the system action corresponding to the bypass trigger condition, thereby realizing various intention processing logics by configuring bypass logic for the main dialogue tree, forming a beneficial supplement to the main dialogue tree, avoiding changes to the main dialogue tree when the demand is adjusted, and reducing operation and maintenance costs. The bypass logic can be reused between the required main dialogue trees, and can also reflect customized logic, thereby taking into account the customization and reusability requirements of human-computer dialogue.

[0060] Figure 6 An exemplary system architecture 600 is shown to which the human-machine dialogue method or human-machine dialogue device according to the embodiment of the present invention can be applied.

[0061] like Figure 6 As shown, the system architecture 600 may include terminal devices 601, 602, 603, a network 604 and a server 606 (this architecture is only an example, and the components included in the specific architecture may be adjusted according to the specific application). The network 604 is used to provide a medium for a communication link between the terminal devices 601, 602, 603 and the server 605. The network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0062] Users can use terminal devices 601, 602, 603 to interact with server 605 through network 604 to receive or send messages, etc. Various client applications can be installed on terminal devices 601, 602, 603, such as applications with human-computer dialogue functions, etc. (only as an example).

[0063] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0064] The server 605 may be a server that provides various services, such as a background server (only an example) that supports applications with human-computer dialogue functions operated by users using the terminal devices 601, 602, and 603. The background server may process the received session request and feed back the processing result (such as the return information output to the user - only an example) to the terminal devices 601, 602, and 603.

[0065] It should be noted that the human-computer dialogue method provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the human-computer dialogue device is generally disposed in the server 605 .

[0066] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0067] The present invention also provides an electronic device. The electronic device of the embodiment of the present invention comprises: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the human-computer dialogue method provided by the present invention.

[0068] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of an electronic device suitable for implementing an embodiment of the present invention. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0069] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the computer system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0070] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0071] In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the main step diagram. In the above embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit 701, the above functions defined in the system of the present invention are executed.

[0072] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may 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 may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0073] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0074] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes: a monitoring unit, an information determination unit and an output unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the information determination unit may also be described as a "unit that provides bypass return information to the output unit".

[0075] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the steps executed by the device include: in the process of communicating with the user based on the pre-established main dialogue tree, monitoring whether the user's global conversation information in the process meets the preset bypass trigger condition; wherein the bypass trigger condition corresponds to the preset system action; in the case of monitoring that the user's global conversation information meets the bypass trigger condition, determining the bypass return information based on the system action corresponding to the bypass trigger condition; determining the current conversation node of the main dialogue tree, and outputting the bypass return information to the user instead of the information in the current conversation node.

[0076] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the human-computer dialogue method provided by the present invention is implemented.

[0077] In the technical solution of the embodiment of the present invention, bypass trigger conditions and corresponding system actions are configured for the main dialogue tree in advance. The bypass trigger conditions and system actions can be used to represent the intention processing logic with high frequency of use, customized requirements, or temporary characteristics. The intention processing logic is executed independently from the main dialogue tree logic, and the main dialogue tree is not changed. When it is monitored that the user's global session information meets the bypass trigger condition, the server can determine the bypass return information to output to the user based on the system action corresponding to the bypass trigger condition, thereby realizing various intention processing logics by configuring bypass logic for the main dialogue tree, forming a beneficial supplement to the main dialogue tree, avoiding changes to the main dialogue tree when the demand is adjusted, and reducing operation and maintenance costs. The bypass logic can be reused between the required main dialogue trees, and can also reflect customized logic, thereby taking into account the customization and reusability requirements of human-computer dialogue.

[0078] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A human-computer dialogue method, characterized in that: include: In the process of communicating with the user based on the pre-established main dialogue tree, monitoring whether the user's global session information in the process meets the preset bypass triggering condition; wherein the bypass triggering condition corresponds to the preset system action; In the case where it is monitored that the user global session information meets the bypass triggering condition, determining the bypass return information based on the system action corresponding to the bypass triggering condition; The current conversation node of the main dialog tree is determined, and the bypass return information is used to replace the information in the current conversation node and output to the user.

2. The method according to claim 1, characterized in that The bypass triggering condition includes: the user shows a specific intention in N rounds of conversation; N is an integer not less than 1; and the monitoring of whether the user global session information in the process meets the preset bypass triggering condition includes: Leverage pre-trained natural language processing models to determine the user’s intent at each turn of conversation; In response to the intent including the specific intent, accumulating the number of dialogue turns corresponding to the specific intent; In response to the number of dialogue turns reaching N, it is determined that the user global session information meets the bypass triggering condition.

3. The method according to claim 1, characterized in that The bypass triggering condition includes: a conditional expression containing at least one specific word; and the monitoring of whether the user global session information in the process meets the preset bypass triggering condition includes: It is determined whether the text information converted from the user session information of the current round matches the conditional expression.

4. The method according to claim 1, characterized in that: The system action includes: broadcasting specific voice information to the user; and the system action corresponding to the bypass trigger condition determines the bypass return information, including: The specific voice information is determined as the bypass return information.

5. The method according to claim 1, characterized in that The method further comprises: After the bypass return information is output to the user instead of the information in the current conversation node, the conversation with the user is continued based on the current conversation node and the main conversation tree.

6. The method according to claim 1, characterized in that The bypass trigger conditions and the system actions are pre-configured for the main dialog tree.

7. A human-computer dialogue device, characterized in that: include: A monitoring unit, used to monitor whether the user's global session information in the process of communicating with the user based on the pre-established main dialogue tree meets a preset bypass triggering condition; wherein the bypass triggering condition corresponds to a preset system action; an information determining unit, configured to determine bypass return information based on a system action corresponding to the bypass triggering condition when monitoring that the user global session information meets the bypass triggering condition; The output unit is used to determine the current conversation node of the main dialogue tree, and output the bypass return information to the user instead of the information in the current conversation node.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images