Large model interaction method and device, storage medium and program product

Abstract

The invention discloses a large model interaction method and device, a storage medium and a program product, relates to the technical field of artificial intelligence, and aims to solve the problem that a text-based dialogue mode is too single, which may cause relatively low dialogue efficiency. The large model interaction method comprises the steps that a front-end server responds to an interaction request operation of a user and sends a first interaction request to a back-end server, and the first interaction request comprises request content; the back-end server sends a second interaction request to the artificial intelligence large model based on the first interaction request, and the second interaction request comprises request content and a request format; the artificial intelligence large model sends an interaction response to the back-end server based on the second interaction request, the interaction response comprises response content corresponding to the request content, and the format of the response content is a request format; the format of the interactive response is a lightweight data exchange format; and the back-end server sends an interaction response to the front-end server.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a large-scale model interaction method, device, storage medium, and program product. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, more and more popular AI models (also called large models) have emerged, such as large language models (LLMs). Users can interact with large models to answer their questions. Currently, users interact with large models through text-based dialogue.

[0003] However, when users interact with large models through text-based conversations, the monotony of the conversational approach may not fully meet user needs and may result in low conversation efficiency. Therefore, finding ways to enrich conversational methods and improve efficiency has become a pressing issue. Summary of the Invention

[0004] The purpose of this application is to provide a large model interaction method, device, storage medium and program product, aiming to solve the problem that the text-based dialogue method is too single and may lead to low dialogue efficiency.

[0005] To achieve the above objectives, this application adopts the following technical solutions:

[0006] In the first aspect, the present application provides a large model interaction method, including: the front-end server sends a first interaction request to the back-end server in response to the user's request for interaction operation, the first interaction request including: request content; the back-end server sends a second interaction request to the artificial intelligence large model based on the first interaction request, the second interaction request including: request content and request format; the artificial intelligence large model sends an interaction response to the back-end server based on the second interaction request, the interaction response including: response content corresponding to the request content, the format of the response content is the request format; the format of the interaction response is a lightweight data exchange format; the back-end server sends the interaction response to the front-end server.

[0007] The large model interaction method provided in the embodiment of the present application allows users to send an interaction request to the back-end server through the front-end server when they need to interact with the artificial intelligence large model. Furthermore, the back-end server can send the request content and request format to the artificial intelligence large model. In this way, the artificial intelligence large model can return the response content in the corresponding request format to the front-end server through the back-end server to display the response content in the request format to the user. In other words, the request format can be in multiple formats, including text format, and the artificial intelligence large model can return and display the response content in multiple formats to the front-end server. In this way, users can interact with the artificial intelligence large model in multiple ways, enriching the dialogue mode of the artificial intelligence large model and thus improving the dialogue efficiency. Thus, it solves the problem in the related art that users only use text dialogue mode to interact with the large model, which is too simple and may lead to low dialogue efficiency.

[0008] In some embodiments, the request format includes at least one of: an interaction type, a question, an option.

[0009] In some embodiments, the interaction type includes at least one of the following: single selection, multiple selection, link, text, drop-down box, and date selection.

[0010] In some embodiments, it also includes: the artificial intelligence big model sends an interaction response to the back-end server based on the second interaction request, including: the artificial intelligence big model determines the target type from all types included in the interaction type based on the request content; and sends the interaction response to the back-end server, and the format of the response content included in the interaction response is the request format of the target type.

[0011] In some embodiments, when the target type is a link, the question is the name of the link and the options are the content of the link; or, when the target type is text, the question is the title and the options are empty; or, when the target type is any one of single choice, multiple choice, and drop-down box, the question is the title.

[0012] In some embodiments, after the back-end server sends the interactive response to the front-end server, the method further includes: the front-end server displays the response content according to the format of the response content.

[0013] In some embodiments, after the front-end server displays the response content in the format of the response content, the method also includes: the front-end server sends a first response message to the back-end server in response to the user's operation of selecting an answer, the first response message including at least one of the following: a question, an answer, and the format of the first response message is a lightweight data exchange format; the back-end server converts the format of the first response message into a text format to obtain a second response message; the back-end server sends the second response message to the artificial intelligence large model.

[0014] According to a second aspect, a large model interaction device is provided, comprising: a communication unit; a communication unit for a front-end server to send a first interaction request to a back-end server in response to a user request for interaction, the first interaction request including request content; the communication unit is also used for the back-end server to send a second interaction request to the artificial intelligence large model based on the first interaction request, the second interaction request including request content and request format; the communication unit is also used for the artificial intelligence large model to send an interaction response to the back-end server based on the second interaction request, the interaction response including response content corresponding to the request content, the format of the response content being the request format; the format of the interaction response is a lightweight data exchange format; the communication unit is also used for the back-end server to send an interaction response to the front-end server.

[0015] In a third aspect, an electronic device is provided, comprising a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory via a bus; when the large model interaction device is running, the processor executes the computer execution instructions stored in the memory, so that the large model interaction device executes the large model interaction method of the first aspect.

[0016] The large-scale model interaction device may be a network device, or a portion of a network device, such as a chip system within the network device. The chip system is configured to support the network device in implementing the functions described in the first aspect and any possible implementation thereof, such as acquiring, determining, and transmitting data and / or information involved in the large-scale model interaction method. The chip system includes a chip, and may also include other discrete devices or circuit structures.

[0017] In a fourth aspect, a computer-readable storage medium is provided, the computer-readable storage medium comprising computer execution instructions, which, when executed on a computer, enable the computer to execute the large model interaction method of the first aspect.

[0018] In a fifth aspect, a computer program product is also provided, which includes computer instructions. When the computer instructions are run on a large model interaction device, the large model interaction device executes the large model interaction method as described in the first aspect above.

[0019] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the large-scale model interaction device, or may be packaged separately from the processor of the large-scale model interaction device, and this embodiment of the application is not limited to this.

[0020] The description of the second, third, fourth and fifth aspects of this application can refer to the detailed description of the first aspect.

[0021] In the embodiments of this application, the names of the large-scale model interaction devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear with other names. For example, the receiving unit may also be called a receiving module, a receiver, etc. As long as the functions of each device or functional module are similar to those of this application, they are within the scope of the claims of this application and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A schematic diagram of the structure of a large model interaction system provided in an embodiment of the present application;

[0024] Figure 2 A flowchart of a large model interaction method provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of a dialog box provided by a front-end server according to an embodiment of the present application;

[0026] Figure 4 A flowchart of another large model interaction method provided in an embodiment of the present application;

[0027] Figure 5 A flowchart of another large model interaction method provided in an embodiment of the present application;

[0028] Figure 6 A flowchart of another large model interaction method provided in an embodiment of the present application;

[0029] Figure 7 A schematic structural diagram of a large model interaction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0032] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connected," and "connected" should be understood broadly. For example, they may refer to fixed connections, detachable connections, or integral connections. They may be directly connected, indirectly connected through an intermediary, or internally connected between two components. Those skilled in the art will understand the specific meanings of these terms in this application based on the specific circumstances.

[0033] In the embodiments of the present application, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of other identical elements in the process, article, or device comprising the element.

[0034] In the embodiments of this 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 this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0035] In related technologies, when using popular large models, the web-based experience is primarily interactive through text-based conversations. This simplistic interaction method may not fully meet user needs and may result in low conversation efficiency. For example, if a user requests a large model to return some quiz questions, the large model will only return text content such as the question, options, and answers, without providing an interface for users to answer the questions, thus failing to fully meet user interaction needs.

[0036] To address the above issues, this application provides a large model interaction method that can communicate with the large model in a rich interactive way, including the following methods: single selection, multiple selection, text input box, link, drop-down menu (also called drop-down box), date selection, etc., thereby reducing ambiguity and achieving efficient communication.

[0037] The above large model interaction method can be applied to a large model interaction system. Figure 1 This is a schematic diagram of the structure of a large model interaction system provided in an embodiment of the present application. Figure 1 As shown, the large model interaction system includes: a front-end server 101, a back-end server 102 and an artificial intelligence large model 103.

[0038] The front-end server 101 is used to interact with users, exchange information with the back-end server 102, and dynamically display rich components based on the specific format returned by the back-end server 102. The back-end server 102 is used to communicate with the front-end server 101 and interact with the artificial intelligence model 103. The artificial intelligence model 103 is used to respond based on the prompt word sent by the user through the back-end server 102.

[0039] Specifically, the front-end server 101 is configured to respond to a user's interaction request by sending a first interaction request including request content to the back-end server 102. Based on the first interaction request, the back-end server 102 is configured to send a second interaction request including request content and a request format to the artificial intelligence model 103, and to send an interaction response to the front-end server 101. Based on the second interaction request, the artificial intelligence model 103 is configured to send an interaction response including response content corresponding to the request content, and the response content is formatted in the requested format, to the back-end server 102, thereby enabling rich interaction between the user and the artificial intelligence model.

[0040] In the embodiment of the present application, the front-end server 101, the back-end server 102 and the device for deploying the artificial intelligence large model 103 can all be physical machines, such as desktop computers, servers, or a server group composed of multiple servers. The embodiment of the present application is not limited to this.

[0041] The front-end server 101 is commonly referred to as a static server or web server. It is primarily used to store and distribute static files, such as Hypertext Markup Language (HTML), Cascading Style Sheets (CSS), JavaScript, images, and other static resources. The front-end server 101 provides users with a fast and stable access experience and reduces the load on the back-end server 102. Common front-end servers 101 include Apache HTTP Server and Nginx.

[0042] Backend server 102 is used to run applications and process business logic. It processes user requests, interacts with the database, and generates dynamic content. Different backend frameworks can choose different servers, with common ones including Apache Tomcat and Node.js. These servers provide an environment and support for processing requests, while also offering a wealth of features and tools to help backend developers build efficient and secure applications.

[0043] It should be pointed out that Figure 1 The structure shown in the does not constitute a limitation of the large model interactive system, except Figure 1 In addition to the components shown, the large model interactive system may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0044] The large model interaction method provided in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0045] The large model interaction method provided in the embodiment of the present application is applied to Figure 1 The large model interactive system shown in Figure 1 is shown in Figure 2. Figure 2 As shown, the large model interaction method includes S201-S204:

[0046] S201: In response to a user's operation requesting interaction, the front-end server sends a first interaction request to the back-end server.

[0047] The first interaction request includes: request content.

[0048] Optionally, when a user requests to interact with the large AI model, they can click the "Rich Interaction" button in a dialog box provided by the front-end server and enter the desired question, i.e., the request content, in the dialog box. Furthermore, in response to the user's request for interaction, the front-end server sends a first interaction request to the back-end server. In other words, when the front-end server interacts with the back-end server, each session instructs the back-end server to use a rich interaction method. Thus, when a user interacts with the large AI model, the large AI model responds using a rich interaction method.

[0049] For example, the question entered by the user is "Please give me two multiple-choice questions about addition." For another example, the question entered by the user is "What is the address of website A?" For another example, the question entered by the user is "What cities and counties are there in province A?"

[0050] like Figure 3 As shown, the user can enter "Please give me two multiple-choice questions about addition." in the dialog box provided by the front-end server and click the "Enrich Interaction" button.

[0051] S202. The backend server sends a second interaction request to the artificial intelligence model based on the first interaction request.

[0052] The second interaction request includes: request content and request format.

[0053] Optionally, the request format may be in a variety of formats including a text format. For an introduction to specific formats included in the request format, please refer to the following embodiments.

[0054] When the backend server learns from the first interaction request that the user desires a rich interactive conversation, it can add the desired response format (i.e., the request format) before sending the corresponding information (i.e., the request content) to the AI model. This facilitates the AI model to subsequently return the response content in the requested format. In other words, the backend server can receive the content transmitted by the frontend server, concatenate the desired parameters, and then invoke the AI model to return the response.

[0055] It should be noted that the return effects of different artificial intelligence models may be different, and the request format sent to the artificial intelligence model can be fine-tuned individually as needed.

[0056] S203. The artificial intelligence big model sends an interactive response to the backend server based on the second interactive request.

[0057] The interactive response includes: response content corresponding to the request content, and the format of the response content is the request format; the format of the interactive response is a lightweight data exchange format.

[0058] Optionally, the artificial intelligence big model can obtain response content corresponding to the request content based on the request content in the second interactive request, and generate an interactive response in a lightweight data exchange format based on the response content, and the format of the response content in the interactive response is the request format, so as to display the response content in the corresponding format to the user.

[0059] Exemplarily, the lightweight data exchange format may be a JSON array, an Extensible Markup Language (XML) format, or the like.

[0060] For example, assuming the request content is "Please give me two multiple-choice questions about addition.", the response content corresponding to the request content may be "Question 1: What is the result of calculating 15+23? A. 36; B. 38; C. 40; D. 42. Question 2: What is the sum of 57+31? A. 86; B. 87; C. 88; D. 89."

[0061] For example, assuming the request content is "What is the address of website A?", the response content corresponding to the request content may be "https: / / www.A.com".

[0062] S204: The back-end server sends an interactive response to the front-end server.

[0063] Optionally, the back-end server returns an interactive response to the front-end server, so that the front-end server displays the response content in a corresponding format to the user.

[0064] In an embodiment of the present application, a user's interaction request can be sent to a back-end server via a front-end server. Furthermore, the back-end server can send the request content and the request format to the artificial intelligence model. In this way, the artificial intelligence model can return the response content in the corresponding request format to the front-end server via the back-end server to display the response content in the request format to the user. In other words, the request format can be in a variety of formats including text format, and the artificial intelligence model can return and display the response content in a variety of formats to the front-end server. In this way, the user can interact with the artificial intelligence model in a variety of ways, enriching the dialogue mode of the artificial intelligence model and thus improving the dialogue efficiency. Thus, the problem in the related art that the user only uses the text dialogue mode to interact with the model is solved, which is too single and may lead to low dialogue efficiency.

[0065] In some embodiments of the present application, the request format includes at least one of the following: interaction type, question, and option.

[0066] Optionally, the interaction type can also be called interaction_type, the question can also be called question, and the option can also be called option or options. Questions can be questions you want to ask me, and options can be choices you want me to make. Each option can be separated by an English comma.

[0067] For example, when the interactive response format is a lightweight data exchange format of a JSON array, and the request format includes interaction_type, question, and option, the specific content included in the request format in the second interactive request may be as follows:

[0068]

[0069] It should be noted that when the artificial intelligence large model responds to an interaction request, it must strictly follow the above format and only return a JSON array, and not return content other than the JSON array.

[0070] In some embodiments of the present application, the interaction type includes at least one of the following: single selection, multiple selection, link, text, drop-down box, and date selection.

[0071] Optionally, single selection can also be called singleSelect, multiple selection can also be called multiSelect, link can also be called link, text can also be called text, drop-down box can also be called dropdown, and date selection can also be called timeSelect.

[0072] In some of the embodiments of this application, Figure 2 ,like Figure 4 As shown, the above S203 specifically includes S301-S302:

[0073] S301. The artificial intelligence big model determines the target type from all types included in the interaction type based on the request content.

[0074] S302: Send an interactive response to the backend server.

[0075] The format of the response content included in the interactive response is the request format of the target type.

[0076] Optionally, the AI model can identify the specific type of interaction that requires a response based on the request content. Furthermore, the AI model can return a corresponding type of interaction response to the backend server, thereby improving the accuracy of the interaction method provided by the backend server to the user and avoiding situations where the interaction method provided to the user does not match the user's expectations.

[0077] For example, assume that the interaction types include: single choice, multiple choice, link, text, drop-down box, and date selection. If the request content is "Please give me two multiple-choice questions about addition," the artificial intelligence model can determine that the target type is single choice among all the types included in the interaction type. If the request content is "What is the address of website A?", the artificial intelligence model can determine that the target type is link among all the types included in the interaction type. If the request content is "What cities and counties are there in province a?", the artificial intelligence model can determine that the target type is drop-down box among all the types included in the interaction type.

[0078] In some embodiments of the present application, when the target type is a link, the question is the name of the link and the options are the content of the link. Alternatively, when the target type is text, the question is the title and the options are blank. Alternatively, when the target type is any of single-choice, multiple-choice, and drop-down boxes, the question is the title.

[0079] For example, when the request content is "What is the address of website A?" and the target type is a link, the specific content included in the interactive response may be as follows:

[0080]

[0081] For example, when the request content is "What is the temperature today?" and the target type is text, the specific content included in the interactive response may be as follows:

[0082]

[0083] For example, when the request content is "Please give me two multiple-choice questions about addition," and the target type is single-choice, the specific content included in the interactive response may be as follows:

[0084]

[0085]

[0086] It should be noted that when there is only one question, you also need to return to the outermost brackets.

[0087] For example, when the request content is "What cities and counties are there in province a?" and the target type is a drop-down box, the specific content included in the interactive response may be as follows:

[0088]

[0089] In some of the embodiments of this application, Figure 2 ,like Figure 5 As shown, after the above S204, the process further includes S401:

[0090] S401. The front-end server displays the response content according to the format of the response content.

[0091] Optionally, the front-end server can display the response content in a component manner according to the interaction type (i.e., interaction_type) in the format of the response content returned by the back-end server, thereby realizing the user's expected interaction method and facilitating subsequent user interactions.

[0092] For example, assuming that the interaction_type in the interactive response is single choice, the front-end server displays the response content as a single choice, and displays a submit button at the bottom of the single choice.

[0093] In some of the embodiments of this application, Figure 5 ,like Figure 6As shown, after the above S401, S501-S503 are also included:

[0094] S501: In response to the user selecting an answer, the front-end server sends a first response message to the back-end server.

[0095] The first response message includes at least one of the following: a question and an answer, and the format of the first response message is a lightweight data exchange format.

[0096] Optionally, the user can select an answer based on the response content displayed by the front-end server and click the submit button. Furthermore, in response to the user's selection of the answer, the front-end server sends a first response message to the back-end server to complete the user-side interaction and facilitate subsequent interactions with the artificial intelligence model.

[0097] The format of the first response message may be json, XML, etc. The answer may also be called answer.

[0098] For example, when the format of the first response message is JSON format, the specific content included in the first response message may be as follows:

[0099]

[0100] For example, the response content in the above interactive response includes the following specific content:

[0101]

[0102] S502: The backend server converts the format of the first response message into a text format to obtain a second response message.

[0103] S503. The backend server sends a second response message to the artificial intelligence large model.

[0104] Optionally, the back-end server converts the format of the first response message into text format, and then sends it to the artificial intelligence big model, so that the artificial intelligence big model can recognize the user's response message and understand the user's intention, so as to judge whether the user's response is correct, or infer the user's next intention.

[0105] Exemplarily, the specific content of the first response message includes:

[0106]

[0107]

[0108] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily appreciate that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, 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 a hardware or computer software driven hardware manner 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 be beyond the scope of this application.

[0109] The embodiment of the present application can divide the functional modules of the large model interaction device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0110] like Figure 7 , which is a structural diagram of a large model interaction device provided in an embodiment of the present application. Figure 7 The large model interaction device shown includes: a communication unit 1001;

[0111] The communication unit 1001 is used for the front-end server to send a first interaction request to the back-end server in response to the user's operation of requesting interaction. The first interaction request includes: request content.

[0112] The communication unit 1001 is also used for the back-end server to send a second interaction request to the artificial intelligence model based on the first interaction request. The second interaction request includes: request content and request format.

[0113] The communication unit 1001 is also used for the artificial intelligence large model to send an interactive response to the back-end server based on the second interactive request. The interactive response includes: response content corresponding to the request content, and the format of the response content is the request format; the format of the interactive response is a lightweight data exchange format.

[0114] The communication unit 1001 is also used for the back-end server to send an interactive response to the front-end server.

[0115] In some embodiments, the request format includes at least one of: an interaction type, a question, an option.

[0116] In some embodiments, the interaction type includes at least one of the following: single selection, multiple selection, link, text, drop-down box, and date selection.

[0117] In some embodiments, the large model interaction device also includes: a processing unit 1002, which is used by the artificial intelligence large model to determine the target type from all types included in the interaction type based on the request content; a communication unit 1001, which is also used to send an interaction response to the back-end server, and the format of the response content included in the interaction response is the request format of the target type.

[0118] In some embodiments, when the target type is a link, the question is the name of the link and the options are the content of the link; or, when the target type is text, the question is the title and the options are empty; or, when the target type is any one of single choice, multiple choice, and drop-down box, the question is the title.

[0119] In some embodiments, the processing unit 1002 is further configured to cause the front-end server to display the response content according to the format of the response content.

[0120] In some embodiments, communication unit 1001 is further configured to cause the front-end server to send a first response message to the back-end server in response to the user selecting an answer. The first response message includes at least one of the following: a question and an answer, and the first response message is formatted in a lightweight data exchange format. Processing unit 1002 is further configured to cause the back-end server to convert the first response message into text format to obtain a second response message. Communication unit 1001 is further configured to cause the back-end server to send the second response message to the large artificial intelligence model.

[0121] An embodiment of the present application also provides a computer-readable storage medium, which includes computer-executable instructions. When the computer-executable instructions are run on a computer, the computer executes the large model interaction method provided in the above embodiment.

[0122] The embodiments of the present application also provide a computer program product that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement the large model interaction method provided in the above embodiments. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

[0123] The system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiment can be combined into one module or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps and are not to be regarded as improper limitations of the present invention.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A large model interaction method, characterized in that: include: The front-end server sends a first interaction request to the back-end server in response to the user's operation of requesting interaction, wherein the first interaction request includes: request content; The backend server sends a second interaction request to the artificial intelligence model based on the first interaction request, where the second interaction request includes: the request content and the request format; The artificial intelligence model sends an interactive response to the backend server based on the second interactive request, wherein the interactive response includes: response content corresponding to the request content, the format of the response content is the request format; and the format of the interactive response is a lightweight data exchange format; The back-end server sends the interactive response to the front-end server.

2. The large model interaction method according to claim 1, characterized in that: The request format includes at least one of the following: interaction type, question, and option.

3. The large model interaction method according to claim 2, characterized in that: The interaction type includes at least one of the following: single selection, multiple selection, link, text, drop-down box, and date selection.

4. The large model interaction method according to claim 3, characterized in that: The artificial intelligence big model sends an interactive response to the backend server based on the second interactive request, including: The artificial intelligence big model determines the target type from all types included in the interaction type based on the request content; The interactive response is sent to the backend server, where the format of the response content included in the interactive response is the request format of the target type.

5. The large model interaction method according to claim 4, characterized in that: In the case where the target type is the link, the question is the name of the link, and the option is the content of the link; or In the case where the target type is the text, the question is a title and the option is empty; or, When the target type is any one of the single choice, the multiple choice and the drop-down box, the question is a title.

6. The large model interaction method according to claim 1, characterized in that: After the back-end server sends the interactive response to the front-end server, the method further includes: The front-end server displays the response content according to the format of the response content.

7. The large model interaction method according to claim 6, characterized in that: After the front-end server displays the response content according to the format of the response content, the method further includes: In response to the user selecting an answer, the front-end server sends a first response message to the back-end server, where the first response message includes at least one of the following: a question and an answer, and the format of the first response message is a lightweight data exchange format; The backend server converts the format of the first response message into a text format to obtain a second response message; The backend server sends the second response message to the artificial intelligence large model.

8. An electronic device, characterized in that: include: A processor and a memory; wherein the memory is used to store one or more programs, and the one or more programs include computer-executable instructions. When the device is running, the processor executes the computer-executable instructions stored in the memory to enable the device to perform the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program or instructions, which, when executed on a computer, causes the computer to perform the method according to any one of claims 1 to 7 .

Images