Method, device and equipment for switching operation process based on large model and storage medium
By judging the human-computer dialogue nodes and automatically switching or jumping the operation process, the problem of business limitations of a single operation process is solved, intelligent switching of the operation process is realized, and business efficiency is improved.
Patent Information
- Application Number
- CN202510129862.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-05
- Publication Date
- 2025-05-30
AI Technical Summary
In the prior art, a single operation process has business limitations, resulting in users needing to manually switch between multiple processes, which is cumbersome.
By determining whether the current human-computer dialogue node is the first node, identifying the first node information or the second node information of the target user, automatically switch the default operation process or jump to the target operation node.
It realizes automatic switching operation process through human-computer dialogue, simplifies the user's operation process in multiple processes, and improves the operation efficiency of the business.
Smart Images
Figure CN120068921A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent switching processes. Specifically, it relates to a method, device, equipment, and storage medium for switching operation processes based on a large model. Background Art
[0002] Currently, during the conversation between a large model and a user, there are usually multiple operation processes, and each operation process has its own operation content for interaction with the large model. Generally, there is only one main process. Common processes include, for example, when a robot communicates with a user by phone, sending a text message to the user and then guiding the user to open the text message link to purchase a product; when the robot communicates with the user, guiding the user to open the official account to purchase a product; when the robot communicates with the user, adding the user's WeChat and sending a link through WeChat for the user to purchase a product. In the sales tasks of the above processes, usually, there is a main operation process to output the current node, such as currently guiding the user to check if they have received a text message, or currently guiding the user to open the link in the text message.
[0003] However, a single process has great limitations in business. For example, if the user does not receive the text message and then needs to purchase the product through the official account, and after the user purchases the product, they need to be guided to add WeChat. In multiple processes, using a single main process for processing is rather cumbersome.
[0004] Therefore, how to achieve intelligent switching of operation processes through human-machine dialogue is a technical problem that needs to be solved. Summary of the Invention
[0005] The purpose of the embodiments of this application is to provide a method for switching operation processes based on a large model. Through the technical solutions of the embodiments of this application, the effect of intelligent switching of operation processes through human-machine dialogue can be achieved.
[0006] In a first aspect, the embodiments of this application provide a method for switching operation processes based on a large model, including determining whether the current human-machine dialogue node is the first dialogue node: when it is determined that the current human-machine dialogue node is the first dialogue node, identifying the first node information of the target user under the current human-machine dialogue node and switching the default operation process, where the first node information includes: the current conversation record and the current user's doubts; when it is determined that the current human-machine dialogue node is not the first dialogue node, identifying the second node information of the target user under the current human-machine dialogue node and jumping to the target operation node according to the second node information, where the second node information includes: the current conversation record, the current user's doubts, the user's historical doubts, and the user's historical operation status.
[0007] In the above embodiments of the present application, by determining whether the current node is the first node, the default operation process can be switched according to the current node or the target node can be jumped to according to the node information of the current node, so as to achieve the effect of intelligent switching of the operation process through human-computer dialogue.
[0008] In some embodiments, determining whether the current human-computer dialogue node is the first dialogue node includes: determining whether the memory stores the historical dialogue information or the historical operation status of the target user; when it is determined that the memory stores the historical dialogue information or the historical operation status of the target user, the current human-computer dialogue node is the first dialogue node; when it is determined that the memory does not store the historical dialogue information and the historical operation status of the target user, the current human-computer dialogue node is not the first dialogue node.
[0009] In the above embodiments of the present application, it is possible to accurately determine whether the current node is the first node through the historical dialogue information and historical operation information in the memory.
[0010] In some embodiments, when it is determined that the current human-computer dialogue node is the first dialogue node, identifying the first node information of the target user under the current human-computer dialogue node and switching the default operation process includes: when it is determined that the current human-computer dialogue node is the first dialogue node, identifying the first node information through the underlying model and switching the current operation process to the default operation process.
[0011] In the above embodiments of the present application, when the current human-computer dialogue node is the first dialogue node, the current operation process can be switched to the default operation process to realize the automatic execution function of the default process.
[0012] In some embodiments, when it is determined that the current human-computer dialogue node is not the first dialogue node, identifying the second node information of the target user under the current human-computer dialogue node and jumping to the target operation node according to the second node information includes: when it is determined that the current human-computer dialogue node is not the first dialogue node, identifying the second node information through the underlying model to obtain the user response information, where the response information includes a reply message and / or an operation message; jumping to the target operation node according to the user response information.
[0013] In the above embodiments of the present application, when the current human-computer dialogue node is not the first dialogue node, it can automatically jump to the target operation node according to the user's response information to realize the intelligent switching of the operation process.
[0014] In a second aspect, an embodiment of the present application provides a device for switching an operation process based on a large model, including:
[0015] A determination module for determining whether the current human-computer dialogue node is the first dialogue node:
[0016] A switching module, configured to, when determining that the current human-machine dialogue node is the first dialogue node, identify first node information of a target user under the current human-machine dialogue node, and switch the default operation process, where the first node information includes: the current conversation record and the current user's doubts;
[0017] A jumping module, configured to, when determining that the current human-machine dialogue node is not the first dialogue node, identify second node information of the target user under the current human-machine dialogue node, and jump to a target operation node according to the second node information, where the second node information includes: the current conversation record, the current user's doubts, the user's historical doubts, and the user's historical operation status.
[0018] Optionally, the determining module is specifically configured to:
[0019] Determine whether the memory stores the historical conversation information of the target user or the user's historical operation status;
[0020] When determining that the memory stores the historical conversation information of the target user or the user's historical operation status, the current human-machine dialogue node is the first dialogue node;
[0021] When determining that the memory does not store the historical conversation information of the target user and the user's historical operation status, the current human-machine dialogue node is not the first dialogue node.
[0022] Optionally, the switching module is specifically configured to:
[0023] When determining that the current human-machine dialogue node is the first dialogue node, identify the first node information through the underlying model, and switch the current operation process to the default operation process.
[0024] Optionally, the jumping module is specifically configured to:
[0025] When determining that the current human-machine dialogue node is not the first dialogue node, identify the second node information through the underlying model to obtain user response information, where the response information includes reply information and / or operation information;
[0026] Jump to the target operation node according to the user response information.
[0027] In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect above are run.
[0028] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method provided in the first aspect above are run.
[0029] Other features and advantages of the present application will be described in the subsequent specification, and in part will be obvious from the specification, or can be understood by implementing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures specifically pointed out in the written specification, claims, and drawings. Description of the Drawings
[0030] To more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.
[0031] Figure 1 It is a flowchart of a method based on the large model switching operation process provided by an embodiment of the present application;
[0032] Figure 2 It is a flowchart of an implementation method based on the large model switching operation process provided by an embodiment of the present application;
[0033] Figure 3 It is a schematic block diagram of a device based on the large model switching operation process provided by an embodiment of the present application;
[0034] Figure 4 It is a structural schematic diagram of a device based on the large model switching operation process provided by an embodiment of the present application. Detailed Embodiments
[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.
[0036] It should be noted that: similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions, and cannot be understood as indicating or implying relative importance.
[0037] This application is applied to the scenario of realizing automatic switching of operation processes in human-machine dialogue. The specific scenario is to analyze the relevant information of the current node through a newly added controller to realize the automatic switching of the default operation process or the target operation process.
[0038] Currently, during the dialogue between the large model and the user, there are usually multiple operation processes, and each operation process has its own operation content for interaction with the large model. Generally, there is only one main process. Common processes are, for example, when the robot communicates with the user by phone, sending a text message to the user and then guiding the user to open the text message link to purchase a product; when the robot communicates with the user, guiding the user to open the official account to purchase a product; when the robot communicates with the user, adding the user's WeChat and sending a link through WeChat for the user to purchase a product. In the sales tasks of the above processes, usually there is a main operation process to output the current node, such as currently guiding the user to check if they have received a text message, currently guiding the user to open the link in the text message, etc. However, a single process has great limitations in business. For example, if the user does not receive the text message and then needs to purchase the product through the official account, and after the user purchases the product, they need to be guided to add WeChat. In multiple processes, it is rather cumbersome to handle with a single main process.
[0039] Therefore, this application determines whether the current human-machine dialogue node is the first dialogue node: when it is determined that the current human-machine dialogue node is the first dialogue node, it identifies the first node information of the target user under the current human-machine dialogue node and switches the default operation process, where the first node information includes: the current conversation record and the current user's doubts; when it is determined that the current human-machine dialogue node is not the first dialogue node, it identifies the second node information of the target user under the current human-machine dialogue node and jumps to the target operation node according to the second node information, where the second node information includes: the current conversation record, the current user's doubts, the user's historical doubts, and the user's historical operation status. By judging whether the current node is the first node to switch the default operation process according to the current node or jump to the target node according to the node information of the current node, the effect of realizing intelligent switching of operation processes through human-machine dialogue can be achieved.
[0040] In the embodiments of this application, the execution entity can be the device for switching operation processes based on a large model in the system for switching operation processes based on a large model. In practical applications, the device for switching operation processes based on a large model can be electronic devices such as terminal devices and servers, which are not limited herein.
[0041] The following combines Figure 1 to describe in detail the method for switching operation processes based on a large model in the embodiments of this application. The method for switching operation processes based on a large model can be executed by a newly added controller (control module) in the human-machine dialogue system.
[0042] Please refer to Figure 1, Figure 1 This is a flowchart of a method for the operation process of switching based on a large model provided by an embodiment of the present application. As Figure 1 shown, the method for the operation process of switching based on a large model includes:
[0043] Step 110: Determine whether the current human - machine dialogue node is the first dialogue node.
[0044] Among them, the first dialogue node can represent the first dialogue node of the current dialogue, or the first dialogue node of the current and historical dialogues. Dialogue nodes include communication nodes, operation nodes, etc. The current dialogue node can be a node in different dialogue scenarios. For example, sales scenarios, guidance operation scenarios, service introduction scenarios, etc.
[0045] In some embodiments of the present application, determining whether the current human - machine dialogue node is the first dialogue node includes: determining whether the memory stores the historical dialogue information of the target user or the historical operation status of the user; when it is determined that the memory stores the historical dialogue information of the target user or the historical operation status of the user, the current human - machine dialogue node is the first dialogue node; when it is determined that the memory does not store the historical dialogue information of the target user and the historical operation status of the user, the current human - machine dialogue node is not the first dialogue node.
[0046] In the above process of the present application, it is possible to accurately determine whether the current node is the first node through the historical dialogue information and historical operation information in the memory.
[0047] Among them, the target user can be the user who is currently having a human - machine dialogue, including sales objects, service objects, etc. The historical dialogue information includes historical dialogue content and the user's reply content. The historical operation status includes whether the user has historical operations and the operation content.
[0048] For example, when it is recognized that there is the historical voice dialogue content or operation information of the target user in the memory or the system, it is considered that the current node is the first node, otherwise it is a non - first node.
[0049] Step 120: When it is determined that the current human - machine dialogue node is the first dialogue node, identify the first node information of the target user under the current human - machine dialogue node and switch the default operation process.
[0050] Among them, the first node information includes: the current dialogue record and the current user's doubts. The current user's doubts include the user's reply content and question content. The default process can be a process set by the user himself. For example, the initial process defined by the business, asking the user to look at the text message, or view the content of the official account, etc.
[0051] In some embodiments of the present application, when it is determined that the current human-machine dialogue node is the first dialogue node, the first node information of the target user under the current human-machine dialogue node is recognized, and the default operation process is switched, including: when it is determined that the current human-machine dialogue node is the first dialogue node, the first node information is recognized through the underlying model, and the current operation process is switched to the default operation process.
[0052] In the above process of the present application, when the current human-machine dialogue node is the first dialogue node, the current operation process can be switched to the default operation process to implement the automatic execution function of the default process.
[0053] Among them, the underlying model can be based on the new generation of open-source large model (llama2), and the underlying model is trained through different node information and the corresponding node user response information. The underlying model can learn how to judge the next operation according to the node information, select the default operation process or jump to the target non-operation process.
[0054] For example, when it is recognized that there is no relevant operation instruction in the node information, the default operation process is directly switched. When it is recognized that there is a doubt or an instruction information of the target user in the node information, the user's doubt can be replied or the target operation process can be jumped to according to the instruction information.
[0055] Step 130: When it is determined that the current human-machine dialogue node is not the first dialogue node, the second node information of the target user under the current human-machine dialogue node is recognized, and the target operation node is jumped to according to the second node information.
[0056] Among them, the second node information includes: the current conversation record, the current user doubt, the user's historical doubts, and the user's historical operation status.
[0057] In some embodiments of the present application, when it is determined that the current human-machine dialogue node is not the first dialogue node, the second node information of the target user under the current human-machine dialogue node is recognized, and the target operation node is jumped to according to the second node information, including: when it is determined that the current human-machine dialogue node is not the first dialogue node, the second node information is recognized through the underlying model to obtain the user response information, where the response information includes the reply information and / or the operation information; the target operation node is jumped to according to the user response information.
[0058] In the above process of the present application, when the current human-machine dialogue node is not the first dialogue node, the target operation node can be automatically jumped to according to the user's response information to realize the intelligent switching of the operation process.
[0059] For example, if the user replies three times in a row that they haven't received the text message, the process should jump to the official account process at this time; if the user clicks on the received text message and completes the payment operation, the process should jump to the WeChat link for the operation of adding WeChat.
[0060] Optionally, if the response information or operation information of the target user indicates some instructions, corresponding operations can be performed according to the user's response information or operation information. For example, if the user clicks or makes a voice response to jump to the WeChat official account page, the page can be directly jumped to the official account according to the user's response information or operation information.
[0061] In the above Figure 1 In the process shown above, the present application determines whether the current human-machine dialogue node is the first dialogue node: when it is determined that the current human-machine dialogue node is the first dialogue node, the first node information of the target user under the current human-machine dialogue node is recognized, and the default operation process is switched, where the first node information includes: the current conversation record and the current user's doubts; when it is determined that the current human-machine dialogue node is not the first dialogue node, the second node information of the target user under the current human-machine dialogue node is recognized, and the target operation node is jumped to according to the second node information, where the second node information includes: the current conversation record, the current user's doubts, the user's historical doubts, and the user's historical operation status. By judging whether the current node is the first node to switch the default operation process according to the current node or jump to the target node according to the node information of the current node, the effect of intelligent switching of the operation process through human-machine dialogue can be achieved.
[0062] Next, in combination with Figure 2 The implementation method of switching the operation process based on the large model in the embodiments of the present application will be described in detail.
[0063] Please refer to Figure 2 , Figure 2 FIG. is a flowchart of an implementation method of switching the operation process based on the large model provided by the embodiments of the present application. As Figure 2 shown, the implementation method of switching the operation process based on the large model includes:
[0064] Step 210: Judge the user's doubts.
[0065] Specifically: Through the current conversation and historical conversation content, judge the doubts or operations existing in the current conversation node user.
[0066] Step 220: Read the user's historical status and the user's doubts, and perform node judgment.
[0067] Specifically: According to the doubts or operations existing in the user, combine the historical operations and response content to judge whether the current node is the first node.
[0068] Step 230: Process switching.
[0069] Specifically: When it is determined that the current human-machine dialogue node is the first dialogue node, the first node information of the target user under the current human-machine dialogue node is recognized, and the default operation process is switched. When it is determined that the current human-machine dialogue node is not the first dialogue node, the second node information of the target user under the current human-machine dialogue node is recognized, and the target operation node is jumped to according to the second node information.
[0070] In addition, Figure 2 The specific methods and steps shown can be referred to Figure 1 the method shown, and will not be elaborated here too much.
[0071] Previously, Figure 1 - Figure 2 described the method of switching the operation process based on the large model. Next, in combination with Figure 3 - Figure 4 describe the device for switching the operation process based on the large model.
[0072] Please refer to Figure 3 , which is a schematic block diagram of a device 300 for switching the operation process based on the large model provided in the embodiments of the present application. The device 300 can be a module, a program segment, or code on an electronic device. The device 300 corresponds to the above Figure 1 method embodiment and can execute Figure 1 each step involved in the method embodiment. The specific functions of the device 300 can be seen in the following description. To avoid repetition, the detailed description is appropriately omitted here.
[0073] Optionally, the device 300 includes:
[0074] A determination module 310, configured to determine whether the current human-machine dialogue node is the first dialogue node:
[0075] A switching module 320, configured to, when it is determined that the current human-machine dialogue node is the first dialogue node, recognize the first node information of the target user under the current human-machine dialogue node, and switch the default operation process, where the first node information includes: the current conversation record and the current user's doubts;
[0076] A jump module 330, configured to, when it is determined that the current human-machine dialogue node is not the first dialogue node, recognize the second node information of the target user under the current human-machine dialogue node, and jump to the target operation node according to the second node information, where the second node information includes: the current conversation record, the current user's doubts, the user's historical doubts, and the user's historical operation status.
[0077] Optionally, the determination module is specifically configured to:
[0078] Determine whether the memory stores the historical conversation information of the target user or the historical operation status of the user; when it is determined that the memory stores the historical conversation information of the target user or the historical operation status of the user, the current human-machine conversation node is the first conversation node; when it is determined that the memory does not store the historical conversation information of the target user and the historical operation status of the user, the current human-machine conversation node is not the first conversation node.
[0079] Optionally, the switching module is specifically used for:
[0080] When it is determined that the current human-machine conversation node is the first conversation node, identify the first node information through the underlying model and switch the current operation process to the default operation process.
[0081] Optionally, the jumping module is specifically used for:
[0082] When it is determined that the current human-machine conversation node is not the first conversation node, identify the second node information through the underlying model to obtain the user response information, where the response information includes reply information and / or operation information; jump to the target operation node according to the user response information.
[0083] Please refer to Figure 4 FIG. is a schematic structural diagram of a device for switching an operation process based on a large model provided in an embodiment of the present application. The device may include a memory 410 and a processor 420. Optionally, the device may further include: a communication interface 430 and a communication bus 440. The device corresponds to the above Figure 1 The method embodiment corresponds and can execute Figure 1 Each step involved in the method embodiment. The specific functions of the device can be seen in the following description.
[0084] Specifically, the memory 410 is used to store computer-readable instructions.
[0085] The processor 420 is used to process the readable instructions stored in the memory and can execute Figure 1 Each step in the method.
[0086] The communication interface 430 is used for signaling or data communication with other node devices. For example: used for communication with a server or a terminal, or for communication with other device nodes. The embodiments of the present application are not limited to this.
[0087] The communication bus 440 is used to implement the direct connection communication between the above components.
[0088] Among them, the communication interface 430 of the device in the embodiment of the present application is used to communicate signaling or data with other node devices. The memory 410 can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. Optionally, the memory 410 can also be at least one storage device located far from the aforementioned processor. The memory 410 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 420, the electronic device executes the above Figure 1 method process shown. The processor 420 can be used on the device 300 and is used to execute the functions in the present application. Exemplarily, the above-mentioned processor 420 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The embodiments of the present application are not limited thereto.
[0089] The embodiment of the present application also provides a readable storage medium. When the computer program is executed by the processor, it executes the method process executed by the electronic device in the method embodiment as Figure 1 shown.
[0090] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described device can refer to the corresponding process in the foregoing method, and will not be elaborated herein.
[0091] In summary, the embodiment of the present application provides a method, device, equipment, and readable storage medium based on the operation process switching of a large model. The method includes determining whether the current human-machine dialogue node is the first dialogue node: when it is determined that the current human-machine dialogue node is the first dialogue node, identifying the first node information of the target user under the current human-machine dialogue node and switching the default operation process, where the first node information includes: the current dialogue record and the current user's doubts; when it is determined that the current human-machine dialogue node is not the first dialogue node, identifying the second node information of the target user under the current human-machine dialogue node and jumping to the target operation node according to the second node information, where the second node information includes: the current dialogue record, the current user's doubts, the user's historical doubts, and the user's historical operation status. Through this method, the effect of intelligent switching of the operation process can be achieved through human-machine dialogue.
[0092] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
[0093] In addition, each functional module in various embodiments of the present application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.
[0094] If the described functions are implemented in the form of software functional modules and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.
[0095] The above are only examples of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application. It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.
[0096] As described above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, and all should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.
[0097] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.
Claims
1. A method for switching operation flow based on a large model, characterized in that: include: Determine whether the current human-computer dialogue node is the first dialogue node: When it is determined that the current human-computer dialogue node is the first dialogue node, identifying the first node information of the target user under the current human-computer dialogue node, and switching the default operation process, wherein the first node information includes: the current dialogue record and the current user doubt; When it is determined that the current human-computer dialogue node is not the first dialogue node, the second node information of the target user under the current human-computer dialogue node is identified, and the target operation node is jumped to according to the second node information, wherein the second node information includes: current dialogue record, current user doubt, user historical doubt and user historical operation status.
2. The method according to claim 1, characterized in that: The step of determining whether the current human-computer dialogue node is the first dialogue node includes: Determining whether the memory stores the historical conversation information of the target user or the historical operation status of the user; When it is determined that the memory stores the historical dialogue information of the target user or the historical operation status of the user, the current human-computer dialogue node is the first dialogue node; When it is determined that the memory does not store the historical dialogue information of the target user and the historical operation status of the user, the current human-computer dialogue node is not the first dialogue node.
3. The method according to claim 1 or 2, characterized in that: When it is determined that the current human-computer dialogue node is the first dialogue node, identifying the first node information of the target user under the current human-computer dialogue node and switching the default operation process include: When it is determined that the current human-computer dialogue node is the first dialogue node, the first node information is identified through the underlying model, and the current operation process is switched to the default operation process.
4. The method according to claim 1 or 2, characterized in that: When it is determined that the current human-computer dialogue node is not the first dialogue node, identifying the second node information of the target user under the current human-computer dialogue node, and jumping to the target operation node according to the second node information, includes: When it is determined that the current human-computer dialogue node is not the first dialogue node, identifying the second node information through the underlying model to obtain user response information, wherein the response information includes reply information and / or operation information; Jump to the target operation node according to the user response information.
5. A device for switching operation flow based on a large model, characterized in that: include: The determination module is used to determine whether the current human-computer dialogue node is the first dialogue node: A switching module, for, when determining that the current human-computer dialogue node is the first dialogue node, identifying the first node information of the target user under the current human-computer dialogue node, and switching the default operation process, wherein the first node information includes: the current dialogue record and the current user doubt; A jump module is used to identify the second node information of the target user under the current human-computer dialogue node when it is determined that the current human-computer dialogue node is not the first dialogue node, and jump to the target operation node according to the second node information, wherein the second node information includes: current dialogue record, current user doubt, user historical doubt and user historical operation status.
6. The device according to claim 5, characterized in that The determination module is specifically used for: Determining whether the memory stores the historical conversation information of the target user or the historical operation status of the user; When it is determined that the memory stores the historical dialogue information of the target user or the historical operation status of the user, the current human-computer dialogue node is the first dialogue node; When it is determined that the memory does not store the historical dialogue information of the target user and the historical operation status of the user, the current human-computer dialogue node is not the first dialogue node.
7. The device according to claim 5 or 6, characterized in that The switching module is specifically used for: When it is determined that the current human-computer dialogue node is the first dialogue node, the first node information is identified through the underlying model, and the current operation process is switched to the default operation process.
8. The device according to claim 5 or 6, characterized in that The jump module is specifically used for: When it is determined that the current human-computer dialogue node is not the first dialogue node, identifying the second node information through the underlying model to obtain user response information, wherein the response information includes reply information and / or operation information; Jump to the target operation node according to the user response information.
9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 4 are executed.
10. A computer-readable storage medium, characterized in that: include: A computer program, when the computer program is run on a computer, causes the computer to execute the method according to any one of claims 1 to 4.