Information interaction system and method, and electronic device

Abstract

The embodiments of the present disclosure relate to the fields of large model technology and application development. Disclosed are an information interaction system and method, and an electronic device. The system comprises: a client, which is configured to detect a query request in an interaction interface, wherein the query request at least comprises query content to be replied to; a text processing end, which is configured to retrieve, on the basis of the query content in the query request, text associated with the query content; a guide information processing end, which is configured to generate guide information on the basis of the query content and the retrieved text, wherein the guide information is used for generating reply information corresponding to the query content; and an information reply end, which is configured to call a machine learning model to analyze the guide information, and output the reply information.

Description

Information interaction system, method and electronic device

[0001] Cross-reference

[0002] This disclosure claims priority to the Chinese patent application filed with the China Patent Office on August 28, 2023, with application number 202311093206.9 and invention name “Information Interaction System, Method and Electronic Device,” the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the fields of large-scale model technology and application development, and in particular, to an information interaction system, method, and electronic device. Background Art

[0004] Currently, it is usually possible to schedule some foreign tools in an open source application development framework (for example, Lang Chain) and use computer programming languages ​​(Python or TypeScript) to give the Large Language Model (LLM) data perception and agency capabilities, and generate corresponding large language model applications to interact with the client and provide it with response information.

[0005] However, since the application development is limited to dispatching foreign tools, there will be some limitations and obstacles when such applications are used domestically. When facing the query needs of different application scenarios of the client, it is impossible to provide corresponding response information in a targeted manner. Therefore, there is still a technical problem of low accuracy of information interaction.

[0006] Currently, no effective solutions have been proposed for the above technical problems.

[0007] Summary of the Invention

[0008] The embodiments of the present disclosure provide an information interaction system, method, and electronic device to at least solve the technical problem of low accuracy in information interaction.

[0009] According to one aspect of an embodiment of the present disclosure, an information interaction system is provided. The system may include: a client configured to detect a query request in an interactive interface, wherein the query request includes at least query content to be answered; a text processing terminal configured to retrieve text associated with the query content based on the query content in the query request; a guidance information processing terminal configured to generate guidance information based on the query content and the retrieved text, wherein the guidance information is used to generate reply information corresponding to the query content; and an information reply terminal configured to invoke a machine learning model to analyze the guidance information and output reply information.

[0010] According to another aspect of an embodiment of the present disclosure, an information interaction method is also provided. The method may include: detecting a query request in an interactive interface, wherein the query request includes at least query content to be answered; displaying text associated with the query content on the interactive interface in response to the query request, wherein the text is retrieved based on the query content; displaying guidance information on the interactive interface, wherein the guidance information is generated based on the query content and the retrieved text; and displaying reply information on the interactive interface, wherein the reply information is obtained by analyzing the guidance information based on a machine learning model.

[0011] According to another aspect of an embodiment of the present disclosure, another information interaction method is also provided. The method may include: obtaining a query request from an application platform, wherein the query request includes at least query content to be answered in an application scenario in which the application platform is located; in response to the query request, obtaining text associated with the query content, wherein the text is retrieved based on the query content; generating guidance information based on the retrieved text and the query content, wherein the guidance information is used to generate answer information corresponding to the query content; calling a machine learning model to analyze the guidance information to obtain answer information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario; and outputting the answer information to the application platform.

[0012] According to another aspect of an embodiment of the present disclosure, a method for generating information is provided. The method may include: detecting a query request, wherein the query request includes at least query content to be answered; retrieving text associated with the query content based on the query content in the query request; and generating guidance information based on the retrieved text and the query content, wherein the guidance information is used to enable a machine learning model to analyze the guidance information to obtain response information.

[0013] According to another aspect of an embodiment of the present disclosure, an electronic device is also provided, which may include a memory and a processor: the memory is configured to store computer-executable instructions, and the processor is configured to execute computer-executable instructions. When the above-mentioned computer-executable instructions are executed by the processor, any one of the above-mentioned information interaction methods is implemented.

[0014] According to another aspect of an embodiment of the present disclosure, a processor is further provided, wherein the processor is configured to run a program, wherein any one of the above-mentioned information interaction methods is executed when the program is running.

[0015] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is further provided, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any of the above-mentioned information interaction methods.

[0016] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements any one of the above information interaction methods when executed by a processor.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the above-mentioned information interaction methods is implemented.

[0018] According to another aspect of the present disclosure, a computer program is further provided, which implements any of the above-mentioned information interaction methods when executed by a processor.

[0019] In an embodiment of the present disclosure, the query content in the query request in the user input interactive interface can be detected by the client. The detected query content can be sent to the text processing end, the received query content can be retrieved, and the text associated with the query content can be determined. The query content and the associated text can be sent to the guidance information processing end for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply end, and the guidance information can be analyzed by the machine learning model in the information reply end to determine the reply information corresponding to the query content, and can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process. Considering that there are certain differences in the requirements of different clients for reply information in different application scenarios, the corresponding query requests can be used in a targeted manner to develop an information interaction system for outputting reply information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of the query requests, and then achieving the technical effect of improving the accuracy of information interaction, and solving the technical problem of low accuracy of information interaction.

[0020] It is easy to note that the above general description and the following detailed description are only for the purpose of exemplifying and explaining the present disclosure, and do not constitute a limitation of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0022] FIG1 is a schematic diagram of an information interaction system according to an embodiment of the present disclosure;

[0023] FIG2 is a schematic diagram of an application scenario of an information interaction method according to an embodiment of the present disclosure;

[0024] FIG3 is a flow chart of an information interaction method according to an embodiment of the present disclosure;

[0025] FIG4 is a flow chart of another information interaction method according to an embodiment of the present disclosure;

[0026] FIG5 is a flow chart of an information generating method according to an embodiment of the present disclosure;

[0027] FIG6 is a flow chart of an enterprise-specific big model application method based on a big model as the core according to an embodiment of the present disclosure;

[0028] FIG7( a ) is a schematic diagram of a title chain of a group block according to an embodiment of the present disclosure;

[0029] FIG7( b ) is a schematic diagram of linear chunks obtained by processing a document according to an embodiment of the present disclosure;

[0030] FIG7( c ) is a schematic diagram of a structural block obtained by performing structural processing on scene data of an offline data transmission type according to an embodiment of the present disclosure;

[0031] FIG8 is a schematic diagram of a format for generating query instructions and document fragments according to rules according to an embodiment of the present disclosure;

[0032] FIG9 is a schematic diagram of an information interaction device according to an embodiment of the present disclosure;

[0033] FIG10 is a schematic diagram of another information interaction device according to an embodiment of the present disclosure;

[0034] FIG11 is a schematic diagram of an information generating device according to an embodiment of the present disclosure;

[0035] FIG12 is a structural block diagram of a computer terminal according to an embodiment of the present disclosure;

[0036] FIG13 is a block diagram of an electronic device according to an information interaction method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way are interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or components is not necessarily limited to those steps or components clearly listed, but may include other steps or components that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] The technical solution provided by the present disclosure is mainly implemented using large-scale model technology. The large model here refers to a deep learning model with large-scale model parameters, which can usually contain hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than ten trillion model parameters. The large model can also be called a cornerstone model / foundation model. It is pre-trained by using large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks and has good generalization capabilities, such as large-scale language models (LLMs) and multi-modal pre-training models.

[0040] It should be noted that when the large model is actually applied, the pre-trained model can be fine-tuned through a small number of samples, so that the large model can be applied to different tasks. For example, the large model can be widely used in natural language processing (NLP), computer vision, speech processing and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image description (IC), image generation, etc. It can also be widely used in natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. Therefore, the main application scenarios of the large model include but are not limited to digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc. In the embodiment of the present disclosure, the application generation of the target language processing model obtained by training the generative large model in a dialogue scenario is used as an example for explanation,

[0041] First, some nouns or terms that appear in the description of the embodiments of the present disclosure are subject to the following explanations:

[0042] Large models can be deep learning models that contain a large number of parameters and learning data. Such models require tens of billions of parameters for training and optimization, a large amount of computing resources and data sets to achieve the purpose of improving prediction accuracy, and the ability to follow instructions to output results;

[0043] Generative models (also known as generative text models) refer to a type of natural language processing model based on deep learning that can generate text similar to that expressed in natural human language. These models are typically trained using machine learning algorithms to learn the syntax and semantics of the language and use this knowledge to execute the model when generating text. When generating text, the model receives a piece of text as input, predicts the probability distribution of the next single word or character, generates the next word or character based on this probability distribution, and iterates to generate the next portion of text.

[0044] FIG1 is a schematic diagram of an information interaction system according to an embodiment of the present disclosure. As shown in FIG1 , the information interaction system 100 may include:

[0045] The client 102 is configured to detect a query request in an interactive interface, wherein the query request at least includes query content to be answered.

[0046] In the technical solution provided by the client 102 described above, a query request on an interactive interface can be detected. The client 102 may also be referred to as a user terminal. A query request (e.g., a user-requested query) may include at least query content to be answered, which may be user-entered query content, such as a motor vehicle parking location, a non-motor vehicle parking location, or a route to a corresponding location.

[0047] It should be noted that the query content in the above query request is only an example and is not specifically limited here. It can change according to the application scenario of the information interaction. The query content can be in the form of text, image or audio. The application level corresponding to the interactive interface that processes the query request and generates reply information can be an enterprise-specific application using a large model, that is, a large model application, such as a large language model application. The application scenario can be used to characterize the different usage areas and functional requirements of different enterprises for the application, for example, it can be a navigation map scenario, a translation scenario, a writing assistant scenario, and an emotional information scenario.

[0048] It should be further noted that the above application scenarios are merely examples and are not intended to be limiting. The interactive interface may be a generative dialogue interface, such as a graphical user interface of a Chat Generative Pre-trained Transformer (Chat GPT).

[0049] Optionally, if the user has questions or needs answers, they can perform relevant operations on the interactive interface of the dialogue generation system on the terminal device in the client 102. For example, they can enter the query content corresponding to the question to be queried to generate a corresponding query request. The query request can then be uploaded to the server for processing.

[0050] The text processing terminal 104 is configured to retrieve text associated with the query content based on the query content in the query request.

[0051] In the technical solution provided by the text processing terminal 104 described above, after the client 102 detects a query request in the interactive interface, the client 102 can send the query request to the text processing terminal 104 in the server for processing. The text processing terminal 104 can retrieve text associated with the query content in the query request from pre-stored documents. The text processing terminal 104 can be referred to as a document terminal and can be a document search engine. The text associated with the query content can be a corresponding document or document fragment.

[0052] Considering that if only a single big model application is used to uniformly answer and provide reply information to the user, there will be problems of poor pertinence and low accuracy. However, in the embodiment of the present disclosure, before information interaction, the unified big model application can be pre-processed according to the different application scenarios of the big model application, so that the developed big model application has better adaptability. The big model in the big model application can be trained according to the corresponding scenario data of different application scenarios, and trained into a big model that better meets the application requirements of the corresponding application scenario, and an exclusive big model application after training is obtained. This embodiment can provide the exclusive big model application to the user for use. When the user has relevant needs, the corresponding exclusive big model application can be obtained to interact with information, thereby achieving the purpose of making corresponding exclusive big model applications for different application scenarios, and then achieving the technical effect of improving the accuracy of the reply information provided to the user.

[0053] For example, according to the needs of different companies for their own exclusive big model applications, the scenario data corresponding to the company's application scenario can be input on the corresponding interactive interface to generate the corresponding application generation instructions. Based on the application generation instructions, the scenario data in the application generation instructions can be called to train the unified big model to obtain the trained company's exclusive big model. An exclusive big model application is built based on the exclusive big model, where the unified big model can be a unified language big model, or a language processing model, for example, Tongyi Qianwen. Tongyi Qianwen is an ultra-large-scale language model whose functions can include multi-round dialogue, copywriting, logical reasoning, multimodal understanding, and multi-language support.

[0054] Optionally, after the interactive interface uploads the acquired query request to the server, the text processing terminal 104 in the server can retrieve documents or document fragments associated with the query content in the query request from the documents already created in the exclusive large model application.

[0055] The guidance information processing terminal 106 is configured to generate guidance information based on the query content and the retrieved text, wherein the guidance information is used to generate reply information corresponding to the query content.

[0056] In the technical solution provided by the guidance information processing terminal 106 described above, after the text processing terminal 104 retrieves text associated with the query, the text and query can be sent to the guidance information processing terminal 106 in the calling server for processing. Guidance information processing terminal 106 can generate guidance information (prompt) based on the received text and query. Guidance information processing terminal 106 can be a prompt processing terminal, such as a prompt processor component. The guidance information can be used to generate a response message corresponding to the query, and the guidance information can be a high-quality prompt.

[0057] Optionally, the prompt processor component can perform prompt splicing processing on the retrieved text and the query content to generate spliced ​​guidance information, and can send the guidance information to the large model for processing according to certain rules.

[0058] The information reply terminal 108 is configured to call a machine learning model to analyze the guidance information and output reply information.

[0059] In the technical solution provided by the information reply terminal 108 of the present disclosure, after the guidance information processing terminal 106 processes the text and query content to obtain guidance information, the guidance information can be transmitted to the information reply terminal 108 via the guidance information processing terminal 106. The information reply terminal 108 can call the existing machine learning model Ali to analyze the guidance information, determine the corresponding reply information, and transmit the reply information to the interactive interface of the client 102 for display. The machine learning model can be a trained large model that can meet different application scenarios, for example, it can be a trained language processing model. The application scenario can be the needs of different enterprises for different use areas of the large model. The reply information can be the information to be answered by the query request. The expression of the reply information can be consistent with the expression of the query request, or it can be the expression required by the user, for example, it can be expressed in natural language or in computer language. It should be noted that the expression of the above reply information is only for example and is not specifically limited here. The reply information can also be called a response and can be in the form of text, image, audio, etc. It should be noted that the above reply information is for illustration only and is not subject to any specific limitation.

[0060] Optionally, after the guidance information is input into the machine learning model in the information reply terminal 108, the guidance information can be understood and processed by the machine learning model, thereby continuously generating and obtaining the final reply information, and the reply information can be sent to the interactive interface in the corresponding client 102 for display.

[0061] If only foreign tools are used to develop applications in Lang Chain and generate corresponding information interaction applications, there will be obstacles when the developed applications are put into use in China, and they will not be able to meet the development needs of different application scenarios. As a result, the accuracy of the reply information provided to users through the above applications cannot be guaranteed. Therefore, there is still a technical problem of low accuracy of the reply information provided to the client.

[0062] However, in the disclosed embodiment, since the initial unified machine learning model, such as a big model or a language processing model, can be trained according to different domestic development needs, targeted application development can be achieved, thereby building an exclusive big model application that can meet different application scenarios. The application can include an interactive interface for collecting and uploading query requests, as well as a text processing terminal, a guidance information processing terminal, and an information reply terminal for receiving and processing the query content in the query request. The user's query request is processed by the exclusive big model application, and the related reply information is fed back to the user, thereby achieving the purpose of being able to design exclusive big model applications for different application scenarios, and further achieving the technical effect of improving the accuracy of the reply information provided to the client, wherein the exclusive big model application can be obtained by using a unified language model as a base and training it using the scenario data of the application scenario.

[0063] It should be noted that the various components included in the aforementioned large model application are merely illustrative and are not specifically limited herein. Any process or method for designing an application that conforms to the scenario data by understanding and analyzing the scenario data through a generative model is within the scope of protection of the embodiments of this disclosure.

[0064] Through the above-mentioned information interaction system disclosed in the present invention, the query content in the query request in the user input interactive interface can be detected by the client. The detected query content can be sent to the text processing end, the received query content can be retrieved, and the text associated with the query content can be determined. The query content and the associated text can be sent to the guidance information processing end for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply end, and the guidance information can be analyzed by the machine learning model in the information reply end to determine the reply information corresponding to the query content, and can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process. Considering that there are certain differences in the requirements of different clients for reply information in different application scenarios, the corresponding query requests can be used in a targeted manner to develop an information interaction system for outputting reply information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of the query requests, and then achieving the technical effect of improving the accuracy of information interaction, and solving the technical problem of low accuracy of information interaction.

[0065] The above system of this embodiment is further introduced below.

[0066] As an optional implementation, the client is configured to rewrite the query request in response to the rewrite request in the interactive interface, wherein the amount of information about the query content in the rewritten query request is greater than the amount of information about the query content in the query request before the rewrite; the guidance information processing end is configured to generate guidance information based on the retrieved text and the query content in the rewritten query request.

[0067] In this embodiment, after detecting a query request, a corresponding rewrite request can be triggered. The rewrite component (Rewrite) can rewrite the query request to obtain a rewritten query request. The guidance information processing terminal can generate corresponding guidance information based on the retrieved text associated with the query content in the query request and the rewritten query request. The query content in the rewritten query request can contain more information than the query content in the query request before the rewrite.

[0068] Optionally, a rewriting component can be deployed on the interactive interface. After detecting the presence of a query request written on the interactive interface, the rewriting component can be used to complete the query content in the query request (query). For example, keywords in the query content can be added to complete the query content. By completing the query content, the amount of information in the query content can be increased, resulting in a completed query request (query').

[0069] Optionally, after obtaining the completed query, the document or plugin description can be searched (i.e., retrieved) using a document search engine to retrieve the corresponding text. The text and the rewritten query are then sent to a prompt processor component, which concatenates the retrieved text and the query content in the rewritten query to generate the corresponding prompt information.

[0070] As an optional implementation, the text processing end is configured to perform structured processing on the retrieved text, wherein the structured text is used to represent the hierarchical structure of the text; the guidance information processing end is configured to generate guidance information based on the query content and the structured text.

[0071] In this embodiment, the retrieved text can be structured by the text processing end, and the structured text can be sent to the guidance information processing end. The guidance information processing end can generate corresponding guidance information based on the text obtained after the structured processing and the query content, wherein the structured text can be used to represent the hierarchical structure of the text.

[0072] Optionally, the retrieved text is subjected to structural processing by the text processing end to obtain a text after structural processing, wherein the structural processing can be used to indicate that the text is subjected to structural block processing (chunk). The text after structural processing can be used to represent the hierarchical structure of the text, that is, the structural processing can make the structure of the text more hierarchical. The hierarchical structure can be a hierarchical document representation, which can also be called document hierarchical structure information, and can be represented in the form of a binary tree, etc. This is only for illustration, and no specific limitation is made to the form of expression of the hierarchical structure. Different hierarchies contain different document hierarchical structure information, that is, corresponding features of different hierarchies. For example, the root node of the binary tree contains the global features of the text, and the child nodes contain the internal features of the text.

[0073] In the embodiments of the present disclosure, the provided exclusive large model application may include not only an online end but also an offline end. The online segment can interact with the client in real time when the client needs to answer questions. The offline end can be used for identification and indexing, etc. It should be noted that there are no specific restrictions on the roles and functions contained in the offline end and the online segment. The processing flow of the offline process can be divided into the offline end for processing, and the processing flow of the online process can be divided into the online end for processing. As long as the exclusive large model application is used to interact with the user and provide the user with functions and systems for answering information, they are all within the protection scope of the embodiments of the present disclosure.

[0074] In the embodiments of the present disclosure, since different data have different transmission modes, in order to ensure the efficiency of data transmission, the data can be divided into offline transmission mode data and online transmission mode data according to the different data transmission modes. For offline transmission mode data, corresponding processing can be performed in the offline end. For online transmission mode data, corresponding processing can be performed in the online end. Offline processing processes such as document recognition, application programming interface (API) registration and data vectorization can be performed in the offline end for offline transmission mode data that need to be processed offline. Online processing processes such as question rewriting and related document recall can be performed in the online segment for data obtained by online transmission mode that need to be processed online, so that data with different needs can be accurately processed in a targeted manner, achieving the technical effect of improving the efficiency of data processing.

[0075] For example, a document graph can be used to represent the document offline to fully utilize the structured information of the text.

[0076] Optionally, the offline end can perform the following offline process: the offline end can perform document recognition on the received scenario data of the offline data transmission type, and can use Doc Graph to represent the scenario data after document recognition to obtain text data, and can also identify global features (Global Features) and internal features (Inner Features) in the text data. The text data can be structured, that is, the text data can be divided into hierarchical structured chunks.

[0077] Optionally, in the process of determining the enterprise's exclusive big model based on the initial big model, index information of structured text data can be established through the offline end, and then the structured text and index information can be used to train the model, wherein the index information can be used to query the structured text data, and can be an identifier corresponding to each structured text, for example, the identifier can be represented as chunk_id corresponding to each chunk. The structured document data may include paragraph information (paragraph) of the document data and information such as the title chain (title_chain). The title chain may include the chunk identifier chunk_id, the node relationship of the chunk, and the chunk.

[0078] Optionally, after using DocGraph to represent documents in different formats, an index can be created for each structured chunk. Specifically, each structured chunk can be labeled, for example, by assigning each structured chunk a chunk_id. Each chunk_id can then be annotated with the corresponding document's paragraph and title information. This yields index information for the structured text (chunks / docs), for example, "chunk_id, title_chain, paragraph."

[0079] Optionally, you can also create index information for the tools to be scheduled. That is, you can label each scheduled tool (tool), for example, assign each tool its own tool_id, and each tool_id can be annotated with the corresponding manifest (Manifest) and specification (Spec). This will yield the tool index information (Tool Descs), for example, "tool_id, Manifest, Spec".

[0080] Optionally, after the index information of the document data and the index information of the tool are established, the index information can be embedded (Indexing) to obtain the final exclusive large model output text (file / Docs).

[0081] For example, in the offline end of the information interaction system, offline processes such as data uploading, API registration, and data vectorization can be performed on the first target input text data.

[0082] Alternatively, the text can be represented as a binary tree, divided layer by layer from the root node downwards, to obtain structured chunks. In the disclosed embodiment, considering that global information in the document may be lost through linear chunking, it is proposed to represent text data through structured chunks, thereby achieving the technical effect of being able to reuse document hierarchical structure information and improving the accuracy of document analysis.

[0083] For example, the data (documents) that can be processed in the offline end may include plain text file format (txt), portable document format (pdf), document format (doc), photocopy document, Uniform Resource Locator (URL) web page / website and other formats. In the offline end, for scene data in txt format, the document can be directly represented by Doc Graph. For scene data in pdf format, doc format and photocopy format, the document data in the above multiple formats can be first identified by the document automation processing artificial intelligence cloud service (Document Artificial Intelligence, Doc AI for short), and then represented by Doc Graph. For scene data in url web page / website, the document can be first identified by a parser, and then represented by Doc Graph. The above scene data can be represented by Doc Graph as a document icon structure (Doc Graph Structure) such as text, table or image. It should be noted that this is only an example and does not impose any specific restrictions on the format of offline processed data or the form of document representation.

[0084] As an optional embodiment, the text processing end is configured to segment the retrieved text in response to the text length of the retrieved text being greater than a text length threshold; the guidance information processing end is configured to generate guidance information based on the query content and the segmented text.

[0085] In this embodiment, the text length of the retrieved text can be detected by the text processing terminal. If the text length exceeds the text length threshold, the corresponding text can be segmented and the segmented text can be sent to the guidance information processing terminal. The guidance information processing terminal can generate corresponding guidance information based on the segmented text and the query content, wherein the text length threshold can be a preset value or a value set according to actual conditions. It should be noted that the setting method of the above text length threshold is only an example and is not specifically limited here. Text whose length exceeds the text length threshold can be called long text.

[0086] If a long text is cut into several smaller linear blocks, however, based solely on this cutting method, there is a possibility that semantic information will be lost in the subsequent text, thus still causing the technical problem of low document analysis accuracy. However, in the disclosed embodiment, in order to avoid the situation where semantic information is lost directly in the subsequent text of the long text, the text can be structured and cut into hierarchical structural blocks for document representation. This allows the hierarchical text to achieve the purpose of improving the understanding ability of document question answering under the large model architecture, thereby achieving the technical effect of improving the accuracy of document analysis.

[0087] As an optional embodiment, the plug-in end is configured to register description data of the plug-in, wherein the description data is used to enable the information reply end to identify the plug-in and execute the function corresponding to the plug-in.

[0088] In this embodiment, the description data of the plug-in related to the query request can be registered through the plug-in end in the document search engine, so that when the information reply end recognizes the plug-in, the corresponding function of the plug-in can be executed based on the description data of the plug-in. The description data can be used to enable the information reply end to recognize different plug-ins and execute the respective functions of the corresponding plug-ins. The description data can also be called a plug-in description.

[0089] As an optional embodiment, the text processing end is configured to retrieve descriptive data associated with the query content based on the query content in the query request; the guidance information processing end is configured to generate guidance information based on the query content, the retrieved text and the retrieved descriptive data.

[0090] In this embodiment, the text processing end can retrieve the query content in the received query request, retrieve the description data of the plug-in associated with the query content, and can send the retrieved text, description data, query content and other information to the guidance information processing end, and generate corresponding guidance information based on the above information.

[0091] Optionally, after obtaining the completed query request, a document search engine can be used to search (retrieve) documents corresponding to the query content in the completed query request, thereby searching for description data of the plug-in to be used in the document, and also searching for the corresponding text. The text, the completed query request, and the description data are sent to the prompt processor component for processing to generate the corresponding guidance information.

[0092] As an optional embodiment, the guidance information processing end is configured to splice the retrieved text and the retrieved description data to obtain a first splicing result, and generate guidance information based on the first splicing result and the query content.

[0093] In this embodiment, after the guidance information processing end receives the retrieved text, description data and completed query request, the retrieved text and description data can be spliced ​​to obtain a first splicing result, and corresponding guidance information can be generated based on the first splicing result and the query content, wherein the first splicing result can be used to indicate that both the text and the plug-in description data are spliced ​​together.

[0094] Optionally, if the guidance information processing end receives not only the retrieved text but also the description data of the retrieved plug-in, the prompt processor component can perform prompt splicing on the retrieved text, the description data and the query content in the completed query request to generate guidance information.

[0095] Optionally, the interactive interface can detect whether the user has entered a query request. When a query request is detected, the query request can be uploaded to the text processing end in the server to search for keywords in the plug-in description data. For example, the query request can be processed based on the query context of the query content in the query request. Then, based on the processed query request, the required plug-in description data can be indexed from the pre-established plug-in end. In other words, the plug-in description data (such as document fragments or plug-in descriptions) can be recalled from the document into Doc Cands and transmitted to the prompt processor component via Rank / MRC if too long. The document or plug-in description can be searched through the document search engine to obtain search results, which can be sorted and then sent to the prompt processor in the online end for prompt splicing.

[0096] As an optional embodiment, the guidance information processing end is configured to at least splice the multiple retrieved texts to obtain a second splicing result, and generate guidance information based on the second splicing result and the query content.

[0097] In this embodiment, the guidance information processing end can at least splice the retrieved multiple texts to obtain a second splicing result, and can generate corresponding guidance information based on the second splicing result and the query content, wherein the second splicing result can be used to indicate that it is obtained by splicing only the texts.

[0098] Alternatively, if the guidance information processing terminal only receives the retrieved text, the prompt processor component can perform prompt concatenation on the retrieved text to obtain a second concatenation result, and can generate corresponding guidance information based on the second concatenation result and the query content in the completed query request.

[0099] As an optional embodiment, the text processing end is configured to send the retrieved text to the client; the client is configured to modify the retrieved text in response to a first modification operation performed on the interactive interface; and the guidance information processing end is configured to generate guidance information based on the query content and the modified text.

[0100] In this embodiment, the text processing end can send the retrieved text to the client and display it on the interactive interface of the client. It can determine whether the text displayed on the interactive interface needs to be modified based on the user's needs. If the text needs to be modified, a first modification operation can be performed on the interactive interface to generate corresponding modification instructions to modify the text. The guidance information processing end can be used to generate guidance information based on the modified text and query content, wherein the first modification operation can be used to adjust the retrieved text.

[0101] Optionally, after analyzing and understanding the query content in the query request and retrieving text associated with the query content, the text can be sent to the corresponding user interface on the client for display, allowing the user to confirm whether there is any inaccurate or even erroneous text. The user can confirm and filter the text according to their needs, and can remove or modify some unnecessary or problematic text. In other words, corresponding modification or deletion operations can be performed on the interactive interface to generate corresponding operation instructions to modify or delete the corresponding text, thereby ensuring the accuracy of the text.

[0102] In the disclosed embodiment, since the retrieved text can be fed back to the user in the client, the user is provided with the execution authority of operations such as independently confirming and modifying the text. That is, the user can adjust the retrieved text by operating on the interactive interface according to his own needs, etc., so that the reply information to be fed back to the user is more accurate and more in line with the user's needs, thereby achieving the purpose of improving the interactivity between the exclusive language model application and the user, thereby realizing the technical effect of improving the accuracy of the reply information provided to the client.

[0103] As an optional embodiment, the guidance information processing end is configured to send guidance information to the client; the client is configured to modify the guidance information in response to a second modification operation performed on the interactive interface.

[0104] In this embodiment, the guidance information processing end can send the generated guidance information to the client, and can display it on the interactive interface of the client. It can determine whether the guidance information displayed on the interactive interface needs to be modified based on the user's needs. If it needs to be modified, a second modification operation can be performed on the interactive interface to generate corresponding modification instructions to modify the guidance information, and the final reply information can be generated based on the modified guidance information, wherein the second modification operation can be used to adjust the generated guidance information.

[0105] In an embodiment of the present disclosure, after the guidance information processing end generates corresponding guidance information for the received modified text and other information, it can be sent to the corresponding user interaction interface in the client for display, so that the user can confirm whether there is inaccurate or erroneous guidance information. The user can filter the guidance information according to his or her own needs, and can eliminate or modify the guidance information that has problems or is not needed to modify the guidance information. Considering that the guidance information can be modified and adjusted through interaction with the user, the accuracy of the generated reply information is ensured.

[0106] As an optional embodiment, the information reply end is configured to display the modified guidance information, and call a machine learning model to analyze the modified guidance information and output reply information.

[0107] In this embodiment, after the client modifies the original guidance information received, the modified guidance information can be sent to the information reply end, and the machine learning model can be called to analyze the modified guidance information to output the final reply information.

[0108] In the embodiment of the present disclosure, the text and guidance information are modified through the above-mentioned two interactions with the user, which greatly ensures the accuracy of the text and guidance information, further ensures the accuracy of the reply information provided to the user, and the reply information is more in line with the user's needs, thereby solving the technical problem of low accuracy of the reply information used by the client.

[0109] Optionally, in the process of training the machine learning model to obtain a dedicated large model, after the query, document fragments, etc. enter the prompt-processor, certain rules can be used to organize the query, document fragments, etc. into a certain format and send them to the machine learning model.

[0110] For example, you can combine queries and document fragments into the following format:

[0111] Humans: Please keep the following in mind; they may be helpful in answering certain questions. If you use a specific instruction, please include the number that preceded it in your response:

[0112] [1] “

Title

[0113] [Text] Dear, the non-motorized parking lot is located opposite the Tangqiao Ferry (near the security booth), and there is currently no charging equipment available.

[0114] Warm reminder: The underground parking lot of the park is for motor vehicles only. Motorcycles, electric vehicles, and bicycles are not allowed to park there.

[0115] Virtual Assistant: OK, I've memorized that information. Is there anything I can help you with?

[0116] Human: Can bicycles be parked in the office area?

[0117] Virtual Assistant:.

[0118] It should be noted that humans can also be represented by "Human" and virtual assistants can also be represented by "Assistant." The formats and representations fed into the large model are merely examples and are not intended to be limiting.

[0119] For another example, based on the above method, the virtual assistant can determine the corresponding information to be remembered for learning the application requirements of different application scenarios, so that an exclusive large model can be trained, so that when the user sends relevant questions to the virtual assistant, the virtual assistant can answer the user's related questions based on the pre-learned documents.

[0120] In the disclosed embodiment, considering the need to develop targeted applications according to the development needs of different domestic enterprises, the initial unified large model can be called and used as a base for training. After training, an exclusive large model that meets the needs of the corresponding application scenario can be obtained to develop applications, thereby achieving the purpose of being able to develop corresponding applications for different application scenarios, and further realizing the technical effect of improving the applicability of application development.

[0121] As an optional embodiment, the information reply end is configured to send the reply information and the retrieved text to the client; the client is configured to display the retrieved text on the interactive interface in response to the query operation of the reply information.

[0122] In this embodiment, the information reply terminal processes the modified guidance information using a machine learning model to generate reply information. The client can then send both the text retrieved from the query content of the query request and the generated reply information to the client, and the reply information can be displayed on the corresponding user interface of the client. If the user needs to query the retrieved text corresponding to the reply information, they can perform a query operation on the interface to generate a corresponding query instruction, which will cause the text to be displayed on the interface.

[0123] Optionally, after the information reply end generates the reply information corresponding to the query request, the generated reply information can be fed back to the client and displayed on the interactive interface. If the user needs to view the text used to generate the reply information, the corresponding query operation can be performed on the interactive interface, such as clicking the query control or expressing the query request by voice to generate the corresponding query instruction to query the text corresponding to the reply information. It should be noted that the above-mentioned operation method of querying the text is only for illustration and is not specifically limited here.

[0124] In an embodiment of the present disclosure, the query content in the query request in the user input interactive interface can be detected by the client. The detected query content can be sent to the text processing end, the received query content can be retrieved, and the text associated with the query content can be determined. The query content and the associated text can be sent to the guidance information processing end for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply end. The guidance information is analyzed by the machine learning model in the information reply end to determine the reply information corresponding to the query content, and the reply information can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process.

[0125] Taking into account the differences in the response information requirements of different clients for different application scenarios, we can use the corresponding query requests in a targeted manner to develop an information interaction system for outputting response information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of query requests, and further achieving the technical effect of improving the accuracy of information interaction, and solving the technical problem of low accuracy of information interaction.

[0126] According to an embodiment of the present disclosure, an information interaction method is provided, which is configured to be executed by the information interaction system in the above-described embodiment. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in a different order than that shown.

[0127] Taking into account the huge amount of model parameters of the large model and the limited computing resources of the mobile terminal, the above-mentioned information interaction method provided by the embodiment of the present disclosure can be applied to the application scenario shown in Figure 2, but is not limited thereto. In the application scenario shown in Figure 2, the large model is deployed in the server 10, and the server 10 can be connected to one or more client devices 20 through a local area network connection, a wide area network connection, an Internet connection, or other types of data networks. The client devices 20 here may include but are not limited to: smart phones, tablet computers, laptops, PDAs, personal computers, smart home devices, car-mounted devices, etc. An application platform for detecting and obtaining query requests can be deployed on the graphical user interface of the client device. There is an interactive interface on the application platform for information interaction, and the interactive interface can be a generative dialogue interface. The client device 20 can interact with the user through the graphical user interface to implement the call to the large model, thereby implementing the information interaction method provided by the embodiment of the present disclosure.

[0128] In an embodiment of the present disclosure, a system composed of a client device and a server may perform the following steps: If there is a user in the client who wants to obtain reply information in response to corresponding content from the application platform, a query request corresponding to the corresponding content to be replied (i.e., query content) may be input on the interactive interface on the client device. The client device may obtain the query request and may send the query request to the server via the network. After receiving the query request, the server may execute: step S202, obtaining the query request from the application platform; step S204, obtaining the text associated with the query content in response to the query request; step S206, generating guidance information based on the retrieved text and query content; step S208, calling a machine learning model to analyze the guidance information and obtain reply information in the application scenario; step S210, outputting the reply information to the application platform. The server may send the reply information generated by calling the machine learning model to the corresponding client device via the network.

[0129] It should be noted that, when the operating resources of the client device can meet the deployment and operating conditions of the large model, the embodiments of the present disclosure can be performed in the client device.

[0130] In the above operating environment, the embodiment of the present disclosure further provides a model-based application generation method as shown in FIG3 .

[0131] The embodiments of the present disclosure provide an information interaction method from a client side, wherein the client side can be a user side. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system, such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in a different order than shown here.

[0132] FIG3 is a flow chart of an information interaction method according to an embodiment of the present disclosure. As shown in FIG3 , the method may include the following steps:

[0133] Step S302: Detecting a query request in the interactive interface, wherein the query request at least includes query content to be answered.

[0134] In the technical solution provided in the above step S302 of the present disclosure, it is possible to detect whether there is a query request on the interactive interface, wherein the query request may at least include query content that requires a response from the large model application, and its expression form includes but is not limited to text, image or audio.

[0135] It should be noted that the above query request presentation format is only for illustration and is not specifically limited here.

[0136] Optionally, when a user needs to provide a response using a corresponding large-scale model application, they can click on the corresponding application on the client device to display an interactive interface. The user can enter a query request, including the query content, on the interactive interface. During this process, the client can detect whether a query request exists on the interactive interface. If a query request is detected, it can be sent to the server for processing.

[0137] Step S304 : Displaying text associated with the query content on the interactive interface in response to the query request, wherein the text is retrieved based on the query content.

[0138] In the technical solution provided in the above step S304 of the present disclosure, text associated with the query content in the query request may be displayed on the interactive interface, wherein the text may be retrieved based on the query content.

[0139] Optionally, after detecting that a query request exists on the interactive interface, the query request may be sent to a text processing terminal in the server to process and retrieve the query request to obtain text associated with the query content in the query request.

[0140] Optionally, a rewriting component may be deployed on the interactive interface. After detecting that a query request is written on the interactive interface, the rewriting component may be used to complete the query content in the query request (query) to obtain a completed query request (query').

[0141] Optionally, after obtaining the completed query request, the document or plug-in description may be retrieved through a document search engine to obtain the corresponding text.

[0142] In the disclosed embodiments, to ensure the accuracy of the retrieved text, the text search engine can send all retrieved text to the corresponding user's interactive interface in the client for display, allowing the user to confirm whether there is inaccurate or even erroneous text. The user can confirm and filter the text according to their own needs, and can eliminate or modify some unnecessary or problematic text. In other words, corresponding modification or deletion operations can be performed on the interactive interface to generate corresponding operation instructions to modify or delete the corresponding text, thereby ensuring the accuracy of the text.

[0143] Step S306: displaying guidance information on the interactive interface, wherein the guidance information is generated based on the query content and the retrieved text.

[0144] In the technical solution provided in the above step S306 of the present disclosure, after the retrieved text and query content are processed to obtain guidance information, the guidance information can be fed back to the corresponding interactive interface in the client for display, wherein the guidance information can be generated based on the retrieved text and query content.

[0145] Optionally, the retrieved text and the completed query request or the description information of the plug-in are uniformly sent to the guidance information processing end for processing. For example, prompt splicing can be performed to generate corresponding guidance information.

[0146] In the embodiment of the present disclosure, in order to ensure the accuracy of the generated guidance information, it can be sent to the interactive interface of the corresponding user in the client for display, so that the user can confirm whether there is inaccurate or erroneous guidance information. The user can filter the guidance information according to his or her own needs, and can eliminate or modify the guidance information that has problems or is not needed to modify the guidance information. Considering that the guidance information can be modified and adjusted through interaction with the user, the accuracy of the generated reply information is ensured.

[0147] Step S308: displaying reply information on the interactive interface, wherein the reply information is obtained by analyzing the guidance information based on the machine learning model.

[0148] In the technical solution provided in the above step S308 of the present disclosure, after the guidance information is analyzed based on the machine learning model to obtain the reply information, the reply information can be sent to the interactive interface in the client for display, wherein the reply information can be obtained by analyzing the guidance information based on the machine learning model.

[0149] Optionally, after the guidance information is input into the machine learning model in the information reply end, the guidance information can be understood and processed by the machine learning model, thereby continuously generating and obtaining the final reply information, and the reply information can be sent to the interactive interface in the corresponding client for display.

[0150] Through steps S302 to S308 of the present disclosure, a query request in an interactive interface is detected, wherein the query request includes at least query content to be answered; text associated with the query content is displayed on the interactive interface in response to the query request, wherein the text is retrieved based on the query content; guidance information is displayed on the interactive interface, wherein the guidance information is generated based on the retrieved text and the query content; and response information is displayed on the interactive interface, wherein the response information is obtained by analyzing the guidance information based on a machine learning model. This achieves the technical effect of improving the accuracy of information interaction and solves the technical problem of low accuracy in information interaction.

[0151] The disclosed embodiments also provide an information interaction method from a server side, where the server side can be an enterprise platform. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system, such as a set of computer-executable instructions, and that although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in a different order than shown here.

[0152] FIG4 is a flow chart of another information interaction method according to an embodiment of the present disclosure. As shown in FIG4 , the method may include the following steps:

[0153] Step S402: Obtain a query request from the application platform, wherein the query request at least includes query content to be answered in the application scenario where the application platform is located.

[0154] In the technical solution provided in step S402 above, a query request may be received from an application platform, wherein the query request may include at least query content to be answered within the application scenario in which the application platform resides. The application platform may be an application platform established using a dedicated large model. The application platform may include an interactive interface and a server corresponding to the application.

[0155] Optionally, the interactive interface of the application platform on the user's client device is detected in real time, a query request from the interactive interface is obtained, and the query request can be sent to a server in the application platform for processing.

[0156] Step S404: in response to the query request, obtaining text associated with the query content, wherein the text is retrieved based on the query content.

[0157] In the technical solution provided in the above step S404 of the present disclosure, after the server of the application platform detects the query request, the query content in the query request can be retrieved to retrieve the text associated therewith, wherein the text can be retrieved based on the query content.

[0158] Optionally, a rewriting component can be deployed on the interactive interface of the application platform. After detecting that a query request is written on the interactive interface, the rewriting component can be used to complete the query content in the query. For example, keywords in the query content can be added to complete the query content. By completing the query content, the amount of information in the query content can be increased to obtain a completed query'. The completed query' can be sent to the text processing end in the application platform. The text processing end can be used to search it and obtain the corresponding text.

[0159] Step S406: Generate guidance information based on the retrieved text and the query content, wherein the guidance information is used to generate reply information corresponding to the query content.

[0160] In the technical solution provided in the above step S406 of the present disclosure, the retrieved text and query content can be processed to generate corresponding guidance information, wherein the guidance information can be used to generate the response information required for the query content through processing by a machine learning model.

[0161] Optionally, the retrieved text and the completed query request or the description information of the plug-in are uniformly sent to the guidance information processing terminal in the server of the application platform for processing. For example, prompt splicing can be performed to generate corresponding guidance information.

[0162] Step S408: Calling a machine learning model to analyze the guidance information to obtain response information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario.

[0163] In the technical solution provided in step S408 of the present disclosure, after generating guidance information based on the retrieved text and query content, a machine learning model can be invoked to analyze the guidance information to obtain response information in the application scenario. The machine learning model can be trained based on application data samples in the application scenario. The application scenario can be used to represent the different uses and application requirements of the application platform. The application data samples can be enterprise-specific data samples deployed for the application scenario.

[0164] Optionally, for the initial unified application platform, due to the different application scenarios and application requirements of different enterprises, the big model used in the unified application platform can be pre-trained according to the application data samples corresponding to the application scenarios of each enterprise to obtain the big model exclusive to each enterprise, thereby building an application platform exclusive to each enterprise.

[0165] Optionally, after building an enterprise-specific application platform, the exclusive large model in the application platform can be called to analyze the guidance information to obtain response information that meets the query request in accordance with the corresponding application scenario.

[0166] Step S410: Output reply information to the application platform.

[0167] In the technical solution provided in the above step S410 of the present disclosure, after the guidance information is processed by the machine learning model and the reply information is obtained, it can be sent to and displayed on the interactive interface in the application platform used to interact with the user.

[0168] Through the above steps S402 to S410 of the present disclosure, a query request from the application platform is obtained, wherein the query request at least includes the query content to be answered in the application scenario where the application platform is located; in response to the query request, text associated with the query content is obtained, wherein the text is retrieved based on the query content; guidance information is generated based on the retrieved text and the query content, wherein the guidance information is used to generate reply information corresponding to the query content; a machine learning model is called to analyze the guidance information to obtain reply information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario; and the reply information is output to the application platform, thereby achieving the technical effect of improving the accuracy of information interaction and solving the technical problem of low accuracy of information interaction.

[0169] The present disclosure also provides an information generation method. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in a different order than shown.

[0170] FIG5 is a flow chart of a method for generating information according to an embodiment of the present disclosure. As shown in FIG5 , the method may include the following steps:

[0171] Step S502: Detecting a query request, wherein the query request at least includes query content to be answered.

[0172] In the technical solution provided in the above step S502 of the present disclosure, the query request may be detected, wherein the query request may at least include query content to be answered.

[0173] Optionally, an interactive interface deployed in the client in the exclusive large model application is used to detect whether the user has entered a query request. If a query request is detected, it can be input into the server in the application for processing.

[0174] Optionally, a rewriting component may be deployed on the interactive interface. After detecting that a query request is written on the interactive interface, the rewriting component may be used to complete the query content in the query to obtain a completed query request (query').

[0175] Step S504: based on the query content in the query request, retrieve text associated with the query content.

[0176] In the technical solution provided in the above step S504 of the present disclosure, in the server in the application, a search can be performed according to the query content in the query request to retrieve text associated with the query content.

[0177] Optionally, after obtaining the completed query request, it can be sent to a document search engine in the server, and the document search engine can be used to search for documents or plug-in descriptions to obtain corresponding texts.

[0178] Step S506: Generate guidance information based on the retrieved text and query content, wherein the guidance information is used to enable the machine learning model to analyze the guidance information and obtain response information.

[0179] In the technical solution provided in the above step S506 of the present disclosure, after retrieving the text associated with the query content, corresponding guidance information can be generated based on the retrieved text and the query content, wherein the guidance information can be used to analyze the guidance information using a machine learning model to obtain reply information.

[0180] Optionally, the retrieved text and the completed query request or the description information of the plug-in are uniformly sent to the guidance information processing terminal in the server for processing. For example, prompt splicing can be performed to generate corresponding guidance information.

[0181] Optionally, after the guidance information is input into the machine learning model in the information reply end, the guidance information can be understood and processed by the machine learning model, thereby continuously generating and obtaining the final reply information, and the reply information can be sent to the interactive interface in the corresponding client for display.

[0182] Through steps S502 to S506 of the present disclosure, a query request is detected, wherein the query request includes at least the query content to be answered; based on the query content in the query request, text associated with the query content is retrieved; and guidance information is generated based on the retrieved text and the query content. The guidance information is used to enable a machine learning model to analyze the guidance information and obtain response information. This achieves the technical effect of improving the accuracy of information interaction and solves the technical problem of low information interaction accuracy.

[0183] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0184] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and components involved are not necessarily required by the present disclosure.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0186] Since the advent of Chat GPT, major companies have launched their own exclusive big models. However, there is no clear solution for how to use big models to solve the actual problems of enterprises. In related technologies, it is usually possible to dispatch some foreign tools in Lang Chain and use Python or TypeScript to give LLM data perception and agent capabilities to develop corresponding applications, interact with users based on the corresponding applications, and provide users with the required response information. However, due to the limitation of dispatching foreign tools for application development, there will be some limitations and obstacles when such applications are used domestically, and when faced with the different development needs of different companies, it is impossible to develop the required applications in a targeted manner, which makes the applicability of application development low. Therefore, there is still a technical problem of low accuracy of information interaction.

[0187] Optionally, the present disclosure provides an enterprise-exclusive big model application method based on a big model as the core, which solves the technical problem of low accuracy of reply information provided to the client. Different from traditional solutions that do not target the application development needs of different enterprises, it avoids the limitations and obstacles of using foreign tools for application development, which may cause errors or inaccuracies in the reply information provided to users, resulting in low accuracy of information interaction, and solves the technical problem of low accuracy of information interaction.

[0188] In an embodiment of the present disclosure, the query content in the query request in the user input interactive interface can be detected by the client. The detected query content can be sent to the text processing end, the received query content can be retrieved, and the text associated with the query content can be determined. The query content and the associated text can be sent to the guidance information processing end for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply end, and the guidance information can be analyzed by the machine learning model in the information reply end to determine the reply information corresponding to the query content, and can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process. Considering that there are certain differences in the requirements of different clients for reply information in different application scenarios, the corresponding query requests can be used in a targeted manner to develop an information interaction system for outputting reply information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of the query requests, and then achieving the technical effect of improving the accuracy of information interaction, and solving the technical problem of low accuracy of information interaction.

[0189] The above method of this embodiment is further introduced below.

[0190] In this embodiment, FIG6 is a flow chart of an enterprise-specific big model application method based on a big model as the core according to an embodiment of the present disclosure. As shown in FIG6 , the method may include the following steps:

[0191] Step S601: document recognition scene data to obtain text data.

[0192] In the technical solution provided in the above step S601 of the present disclosure, if a unified large model application needs to be trained, it is necessary to obtain the scene data required for the corresponding application scenario. Document recognition can be performed on the scene data to obtain text data, wherein the scene data can be the data required for the application scenarios of different enterprises.

[0193] Alternatively, if an enterprise needs to develop a proprietary large-scale model application that meets its own application scenarios and other requirements, it can perform relevant operations on the interactive interface of the dialogue generation system on the enterprise's client device. For example, the interactive interface can input the application scenario and scenario data to be used by the application to be generated. When the interactive interface receives the application development requirements, such as scenario data, it can generate corresponding application generation instructions. The application generation instructions can then be uploaded to the server for processing to generate an application that meets the enterprise's application scenario.

[0194] Optionally, the offline end can perform document recognition on the received data and use a Doc Graph to represent the document data, obtaining text data. Global and internal features within the text data can also be identified. The text data can then be structured, that is, divided into hierarchical, structured chunks.

[0195] Optionally, the scene data for offline processing may include formats such as plain text document format, pdf format, doc format, photocopy document, url web page / website, etc. In the offline end, for scene data in plain text document format, the document can be directly represented by a document icon (Doc Graph). For scene data in pdf format, doc format, and photocopy format, Doc AI can be used to perform document recognition on the scene data in the above multiple formats, and then the document can be represented by a document icon. For scene data in url web page / website format, the parser can be used to perform document recognition, and then the document can be represented by a document icon. The above scene data can be represented by a document icon structure such as text form, table form, or image form through a document icon, and the global features and internal features in the scene data can be distinguished.

[0196] Step S602: Create index information of structured text data.

[0197] In the technical solution provided in the above step S602 of the present disclosure, index information of structured text data can be established.

[0198] Optionally, after document representation of scene data of different formats through document icons, an index of each structure chunk after structuring can be established, that is, each structure chunk can be labeled, for example, each structure chunk can be assigned its own chunk_id, and each chunk_id can be annotated with the paragraph information and title information of the corresponding document data. Thus, the index information (chunks / docs) of the structured text data is obtained, for example, it can be "chunk_id, title_chain, paragraph". Index information of the tool to be scheduled can also be established, that is, each scheduled tool (tool) can be labeled, for example, each tool can be assigned its own tool_id, and each tool_id can be annotated with the corresponding manifest (Manifest) and specification (Spec). Thus, the index information of the tool (Tool Descs) is obtained, for example, it can be "tool_id, Manifest, Spec".

[0199] Figure 7(a) is a schematic diagram of a title chain of a chunk according to an embodiment of the present disclosure. As shown in Figure 7(a), the title chain (title_chain) of the chunk may include the chunk identifier (chunk_id) and the connection relationship between each node in the binary tree of the structural chunk, as well as the chunk.

[0200] FIG7(b) is a schematic diagram of linear chunks obtained by processing a document according to an embodiment of the present disclosure. As shown in FIG7(b), linear chunks are a structured method in the prior art. This method can cut a long text into several smaller linear chunks. However, based on the above-mentioned chunking method, the semantic information of the text content will be lost. That is, the linear chunks will lose the document level information. Therefore, there is still a technical problem of low accuracy of document analysis. However, in the embodiment of the present disclosure, in order to avoid the situation where the semantic information of the long text content is lost directly, the scene data can be structured to obtain the structural chunks shown in FIG7(c). The scene data is divided into hierarchical structural chunks to represent the document. The hierarchical scene data can be reused through the document level through the structural chunks under the large model architecture to achieve the purpose of improving the understanding ability of the document question and answer, thereby achieving the technical effect of improving the accuracy of the document analysis.

[0201] Figure 7(c) is a schematic diagram of structural chunks obtained by structuring data for offline data transmission scenarios according to an embodiment of the present disclosure. As shown in Figure 7(c), in this embodiment of the present disclosure, text data can be represented in the form of a binary tree, divided layer by layer from the root node downward, thereby obtaining structural chunks. In this disclosure, considering that global information in a document can be lost through linear chunking, it is proposed that text data can be represented through structural chunks, thereby achieving the technical effect of being able to reuse document hierarchical structure information and improving the accuracy of document analysis.

[0202] Optionally, after the index information of the document data and the index information of the tool are established, the index information may be embedded into the offline language processing model through Indexing (Moss Embedding) to obtain the file Docs.

[0203] For example, in the offline end, offline processes such as data upload, API registration, and data vectorization can also be performed on the first target input text data.

[0204] Step S603: Complete the query request information.

[0205] In the technical solution provided in the above step S603 of the present disclosure, information completion can be performed on the query request to obtain a completed query request.

[0206] Optionally, the context of the query instruction (query context) can be queried through the rewriting component (Rewrite) in the online end, and the information therein can be completed. For example, keywords can be added to the query content in the query request to obtain the completed query request (query').

[0207] Step S604: Recall the document and obtain the plug-in data.

[0208] In the technical solution provided in the above step S604 of the present disclosure, plug-in data can be obtained through document recall.

[0209] Optionally, document recall plugin data is stored in Doc Cands and then transferred to the prompt processor via Rank / MRC if too long. The document or plugin description can be searched using the online document search engine to obtain search results, which can be sorted and then sent to the online prompt processor for prompt splicing.

[0210] Step S605: splicing the plug-in data or documents.

[0211] In the technical solution provided in the above step S605 of the present disclosure, prompt splicing can be performed on the plug-in data or document.

[0212] Optionally, the document or plug-in description is searched through the document search engine in the online end to obtain search results, which can be sorted and then sent to the prompt processor in the online end for prompt splicing.

[0213] Optionally, if the guidance information processing end receives not only the retrieved text but also the description data of the retrieved plug-in, the prompt processor component can perform prompt splicing on the retrieved text, the description data and the query content in the completed query request to generate guidance information.

[0214] Alternatively, if the guidance information processing terminal receives only the retrieved text, the prompt processor component can perform prompt concatenation on the retrieved text to obtain a second concatenation result. The corresponding guidance information can be generated based on the second concatenation result and the query content in the completed query request.

[0215] Optionally, after entering the prompt-processor, the query, document fragments, etc. can be formatted according to certain rules and sent to the large model for training.

[0216] Alternatively, FIG8 is a schematic diagram of a format for generating query instructions and document fragments according to a rule according to an embodiment of the present disclosure. As shown in FIG8 , the query, document fragments, etc. may be combined into the following format:

[0217] Humans: Please keep the following in mind; they may be helpful in answering certain questions. If you use a specific instruction, please include the number that preceded it in your response:

[0218] [1] “

Title

[0219] [Text] Dear, the non-motorized parking lot is located opposite the Tangqiao Ferry (near the security booth), and there is currently no charging equipment available.

[0220] Warm reminder: The underground parking lot of the park is for motor vehicles only. Motorcycles, electric vehicles, and bicycles are not allowed to park there.

[0221] Virtual Assistant: OK, I've memorized that information. Is there anything I can help you with?

[0222] Human: Can bicycles be parked in the office area?

[0223] Virtual Assistant:.

[0224] Step S606: Generate a reply box.

[0225] In the technical solution provided in the above step S606 of the present disclosure, a reply box may be generated.

[0226] Optionally, in the process of inputting the above format into the conversational language model (Moss) for training, if a reply box needs to be generated, the corresponding API can be called, that is, if call API, the corresponding reply box can be generated through the tool application programming interface (Tool API) through the application programming interface response (API Response).

[0227] Optionally, based on the above method, the virtual assistant can determine the corresponding information to be remembered to learn the application requirements of different application scenarios, so that an exclusive large model can be trained, so that when the user sends relevant questions to the virtual assistant, the virtual assistant can answer the user's related questions based on the pre-learned documents.

[0228] In the disclosed embodiment, considering the need to develop targeted applications according to the development needs of different domestic enterprises, the initial unified large model can be called and used as a base for training. After training, an exclusive large model that meets the needs of the corresponding application scenario can be obtained to develop applications, thereby achieving the purpose of being able to develop corresponding applications for different application scenarios, and further realizing the technical effect of improving the applicability of application development.

[0229] It should be noted that the preferred implementation scheme involved in the above embodiments of the present disclosure is the same as the scheme provided in the above embodiments, as well as the application scenario and implementation process, but is not limited to the scheme provided in the above embodiments.

[0230] According to an embodiment of the present disclosure, an information interaction device for implementing the information interaction method shown in FIG. 3 is also provided.

[0231] FIG9 is a schematic diagram of an information interaction device according to an embodiment of the present disclosure. As shown in FIG9 , the information interaction device 900 may include: a first detection component 902 , a first display component 904 , a second display component 906 , and a third display component 908 .

[0232] The first detection component 902 is configured to detect a query request in the interactive interface, wherein the query request at least includes query content to be answered.

[0233] The first display component 904 is configured to display text associated with the query content on the interactive interface in response to the query request, wherein the text is retrieved based on the query content.

[0234] The second display component 906 is configured to display guidance information on the interactive interface, wherein the guidance information is generated based on the retrieved text and the query content.

[0235] The third display component 908 is configured to display reply information on the interactive interface, wherein the reply information is obtained by analyzing the guidance information based on the machine learning model.

[0236] It should be noted that the first detection component 902, the first display component 904, the second display component 906, and the third display component 908 correspond to steps S302 to S308 in the above embodiment. The four components and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above components can be hardware components or software components stored in a memory and processed by one or more processors. The above components can also be part of a device and can be run in a computer terminal provided in the following embodiments.

[0237] According to an embodiment of the present disclosure, there is also provided an information interaction device configured to implement the information interaction method shown in FIG. 4 .

[0238] FIG10 is a schematic diagram of another information interaction device according to an embodiment of the present disclosure. As shown in FIG10 , the information interaction device 1000 may include: a first acquisition component 1002 , a second acquisition component 1004 , a first generation component 1006 , a call component 1008 , and an output component 1010 .

[0239] The first acquisition component 1002 is configured to acquire a query request from the application platform, wherein the query request at least includes query content to be answered in the application scenario where the application platform is located.

[0240] The second acquisition component 1004 is configured to acquire text associated with the query content in response to the query request, wherein the text is retrieved based on the query content.

[0241] The first generating component 1006 is configured to generate guidance information based on the retrieved text and the query content, wherein the guidance information is used to generate reply information corresponding to the query content.

[0242] The calling component 1008 is configured to call a machine learning model to analyze the guidance information and obtain response information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario.

[0243] The output component 1010 is configured to output reply information to the application platform.

[0244] It should be noted that the first acquisition component 1002, the second acquisition component 1004, the first generation component 1006, the call component 1008, and the output component 1010 correspond to steps S402 to S410 in the above embodiment. The examples and application scenarios implemented by the five components and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above components can be hardware components or software components stored in a memory and processed by one or more processors. The above components can also be part of an apparatus and can be run in a computer terminal provided in the following embodiments.

[0245] According to an embodiment of the present disclosure, there is also provided an information generating device configured to implement the information shown in FIG. 5 .

[0246] FIG11 is a schematic diagram of an information generation device according to an embodiment of the present disclosure. As shown in FIG11 , the detailed generation device 1100 may include: a second detection component 1102 , a retrieval component 1104 , and a second generation component 1106 .

[0247] The second detection component 1102 is configured to detect a query request, wherein the query request at least includes query content to be answered.

[0248] The search component 1104 is configured to search for text associated with the query content based on the query content in the query request.

[0249] The second generation component 1106 is configured to generate guidance information based on the retrieved text and query content, wherein the guidance information is used to enable the machine learning model to analyze the guidance information and obtain response information.

[0250] It should be noted that the second detection component 1102, the retrieval component 1104, and the second generation component 1106 correspond to steps S502 to S506 in the above embodiment. The examples and application scenarios implemented by the three components and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above components can be hardware components or software components stored in a memory and processed by one or more processors. The above components can also be part of an apparatus and can be run in a computer terminal provided in the following embodiments.

[0251] In the above-mentioned device, the query content in the query request input by the user in the interactive interface can be detected by the client. The detected query content can be sent to the text processing terminal, and the received query content can be retrieved to determine the text associated with the query content. The query content and the associated text can be sent to the guidance information processing terminal for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply terminal. The guidance information is analyzed by the machine learning model in the information reply terminal to determine the reply information corresponding to the query content. The reply information can be fed back to the interactive interface of the corresponding client for display, completing the information interaction process. Considering that the requirements of different clients for reply information in different application scenarios vary to a certain extent, the corresponding query requests can be used in a targeted manner to develop an information interaction system for outputting reply information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of the query requests, thereby achieving the technical effect of improving the accuracy of information interaction and solving the technical problem of low accuracy of information interaction.

[0252] The embodiment of the present disclosure may provide a computer terminal, which may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced by a terminal device such as a mobile terminal.

[0253] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of a computer network.

[0254] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the model-based application generation method: detecting an application generation instruction acting on the interactive interface, wherein the application generation instruction includes at least: scenario data required for the application to be generated in the corresponding application scenario; in response to the application generation instruction, calling the initial language processing model, wherein the initial language processing model is used to determine the semantics of the initial input data and convert the initial input data into initial output data, and the initial output data is used to describe the natural language that matches the semantics of the initial input data; using the scenario data, training the initial language processing model into a target language processing model in the application scenario; generating an application based on the target language processing model, wherein the target input data of the application is converted via the target language processing model to obtain target output data, the target output data meets the attributes of the application scenario, and the target output data is used to describe the natural language that matches the semantics of the target input data.

[0255] Optionally, Figure 12 is a block diagram of a computer terminal according to an embodiment of the present disclosure. As shown in Figure 12, the computer terminal A may include: one or more (only one is shown in the figure) processors 1202, a memory 1204, a storage controller, and a peripheral interface, wherein the peripheral interface is connected to a radio frequency component, an audio component, and a display.

[0256] Among them, the memory can be configured to store software programs and components, such as the program instructions / components corresponding to the model-based application generation method and device in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and components stored in the memory, that is, implementing the above-mentioned model-based application generation method. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal A via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0257] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: detecting a query request in the interactive interface, wherein the query request includes at least the query content to be answered; displaying text associated with the query content on the interactive interface in response to the query request, wherein the text is retrieved based on the query content; displaying guidance information on the interactive interface, wherein the guidance information is generated based on the query content and the retrieved text; and displaying reply information on the interactive interface, wherein the reply information is obtained by analyzing the guidance information based on a machine learning model.

[0258] As another optional example, the processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain a query request from the application platform, wherein the query request includes at least the query content to be answered in the application scenario in which the application platform is located; in response to the query request, obtain text associated with the query content, wherein the text is retrieved based on the query content; generate guidance information based on the retrieved text and the query content, wherein the guidance information is used to generate reply information corresponding to the query content; call a machine learning model to analyze the guidance information to obtain reply information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario; and output the reply information to the application platform.

[0259] As another optional example, the processor can call the information and application stored in the memory through the transmission device to perform the following steps: detect a query request, wherein the query request includes at least the query content to be answered; based on the query content in the query request, retrieve text associated with the query content; based on the retrieved text and query content, generate guidance information, wherein the guidance information is used to enable the machine learning model to analyze the guidance information to obtain reply information.

[0260] By adopting the embodiment of the present disclosure, the query content in the query request in the user input interactive interface can be detected by the client. The detected query content can be sent to the text processing end, the received query content can be retrieved, and the text associated with the query content can be determined. The query content and the associated text can be sent to the guidance information processing end for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply end, and the guidance information can be analyzed by the machine learning model in the information reply end to determine the reply information corresponding to the query content, and can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process. Considering that there are certain differences in the requirements of different clients for reply information in different application scenarios, the corresponding query requests can be used in a targeted manner to develop an information interaction system for outputting reply information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of the query requests, and then achieving the technical effect of improving the accuracy of information interaction, and solving the technical problem of low accuracy of information interaction.

[0261] Those skilled in the art will appreciate that the structure shown in FIG12 is merely illustrative, and the computer terminal may also be a smartphone (such as an Android phone, iOS phone, etc.), a tablet computer, a PDA, a mobile internet device (MID), a PAD, or other terminal device. FIG12 does not limit the structure of the above-mentioned electronic devices. For example, the computer terminal A may include more or fewer components (such as a network interface, a display device, etc.) than those shown in FIG12, or may have a configuration different from that shown in FIG12.

[0262] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0263] The embodiment of the present disclosure further provides a computer-readable storage medium. Optionally, in this embodiment, the computer-readable storage medium can be configured to store program codes executed by the model-based application generation method provided in the first embodiment.

[0264] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0265] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: detecting a query request in an interactive interface, wherein the query request includes at least query content to be answered; displaying text associated with the query content on the interactive interface in response to the query request, wherein the text is retrieved based on the query content; displaying guidance information on the interactive interface, wherein the guidance information is generated based on the query content and the retrieved text; and displaying reply information on the interactive interface, wherein the reply information is obtained by analyzing the guidance information based on a machine learning model.

[0266] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: obtaining a query request from the application platform, wherein the query request includes at least query content to be answered in the application scenario in which the application platform is located; obtaining text associated with the query content in response to the query request, wherein the text is retrieved based on the query content; generating guidance information based on the retrieved text and the query content, wherein the guidance information is used to generate reply information corresponding to the query content; calling a machine learning model to analyze the guidance information to obtain reply information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario; and outputting the reply information to the application platform.

[0267] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: detecting a query request, wherein the query request includes at least query content to be answered; retrieving text associated with the query content based on the query content in the query request; generating guidance information based on the retrieved text and query content, wherein the guidance information is used to enable a machine learning model to analyze the guidance information to obtain reply information.

[0268] In an embodiment of the present disclosure, the query content in the query request in the user input interactive interface can be detected by the client. The detected query content can be sent to the text processing end, the received query content can be retrieved, and the text associated with the query content can be determined. The query content and the associated text can be sent to the guidance information processing end for processing to generate corresponding guidance information, and the guidance information can be sent to the information reply end, and the guidance information can be analyzed by the machine learning model in the information reply end to determine the reply information corresponding to the query content, and can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process. Considering that there are certain differences in the requirements of different clients for reply information in different application scenarios, the corresponding query requests can be used in a targeted manner to develop an information interaction system for outputting reply information that meets the corresponding application scenarios, thereby achieving the purpose of significantly improving the analysis and processing capabilities of the query requests, and then achieving the technical effect of improving the accuracy of information interaction, and solving the technical problem of low accuracy of information interaction.

[0269] An embodiment of the present disclosure may provide an electronic device that may include a memory and a processor. Figure 13 is a block diagram of an electronic device according to a model-based application generation method of an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0270] As shown in FIG13 , device 1300 includes a computing component 1301 that can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from a storage component 1308 into a random access memory (RAM) 1303. RAM 1303 can also store various programs and data required for the operation of device 1300. Computing component 1301, ROM 1302, and RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to bus 1304.

[0271] Multiple components in device 1300 are connected to I / O interface 1305, including: input component 1306, such as a keyboard, mouse, etc.; output component 1304, such as various types of displays, speakers, etc.; storage component 1308, such as a magnetic disk, optical disk, etc.; and communication component 13010, such as a network card, modem, wireless communication transceiver, etc. Communication component 13010 allows device 1300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0272] The computing component 1301 can be various general and / or special processing components with processing and computing capabilities. Some examples of the computing component 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing components that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing component 1301 performs the various methods and processes described above, such as a model-based application generation method. For example, in some embodiments, the model-based application generation method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage component 1308. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1300 via the ROM 1302 and / or the communication component 13010. When the computer program is loaded into RAM 1303 and executed by computing component 1301, one or more steps of the model-based application generation method described above may be performed. Alternatively, in other embodiments, computing component 1301 may be configured to perform the model-based application generation method in any other appropriate manner (e.g., via firmware).

[0273] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0274] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed on the machine, partially executed on the machine, partially executed on the machine as a stand-alone software package and partially executed on a remote machine, or executed on a remote machine or server.

[0275] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0276] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube or liquid crystal display, monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0277] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks, wide area networks, and the Internet.

[0278] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0279] It should be noted that the serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0280] In the above embodiments of the present disclosure, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0281] In the several embodiments provided in this disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of components is only a logical function division. In actual implementation, there may be other division methods, such as multiple components or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of components can be electrical or other forms.

[0282] Components described as separate parts may or may not be physically separate, and components shown as components may or may not be physical components, that is, they may be located in one place or distributed across multiple network components. Some or all of these components may be selected based on actual needs to achieve the objectives of this embodiment.

[0283] In addition, the functional components in the various embodiments of the present disclosure may be integrated into a single processing component, each component may exist physically separately, or two or more components may be integrated into a single component. The aforementioned integrated components may be implemented in the form of hardware or software functional components.

[0284] If the integrated components are implemented in the form of software functional components and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a read-only memory random access memory, a mobile hard disk, a magnetic disk or an optical disk.

[0285] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as within the scope of protection of the present disclosure. Industrial Applicability

[0286] The solution provided by the embodiment of the present disclosure can be applied to the process in which the user needs the application platform to respond to the query request, and can be implemented by detecting the query content in the query request in the user input interactive interface. The query content can be retrieved to determine the text associated with the query content. The query content and the associated text can be processed to generate corresponding guidance information, and the guidance information can be analyzed by a machine learning model to determine the response information corresponding to the query content, and can be fed back to the interactive interface of the corresponding client for display, thereby completing the information interaction process. Thereby, the purpose of significantly improving the analysis and processing capabilities of the query request is achieved, thereby achieving the technical effect of improving the accuracy of information interaction and solving the technical problem of low accuracy of information interaction.

Claims

1. An information interaction system, comprising: The client is configured to detect a query request in the interactive interface, wherein the query request at least includes query content to be answered; A text processing end, configured to retrieve text associated with the query content based on the query content in the query request; A guidance information processing terminal, configured to generate guidance information based on the query content and the retrieved text, wherein the guidance information is used to generate reply information corresponding to the query content; The information reply end is configured to call a machine learning model to analyze the guidance information and output the reply information.

2. The system according to claim 1, wherein: The client is configured to rewrite the query request in response to the rewrite request in the interactive interface, wherein the amount of information of the query content in the rewritten query request is greater than the amount of information of the query content in the query request before the rewrite; The guidance information processing end is configured to generate the guidance information based on the retrieved text and the rewritten query content in the query request.

3. The system according to claim 1, wherein: The text processing end is configured to perform structural processing on the retrieved text, wherein the text after structural processing is used to represent the hierarchical structure of the text; The guidance information processing end is configured to generate the guidance information based on the query content and the text after structured processing.

4. The system according to claim 1, wherein: The text processing end is configured to perform segmentation processing on the retrieved text in response to the text length of the retrieved text being greater than a text length threshold; The guidance information processing end is configured to generate the guidance information based on the query content and the segmented text.

5. The system according to claim 1, wherein: The system further comprises: The plug-in end is configured to register description data of the plug-in, wherein the description data is used to enable the information reply end to identify the plug-in and execute the function corresponding to the plug-in.

6. The system according to claim 5, wherein: The text processing end is configured to retrieve the description data associated with the query content based on the query content in the query request; The guide information processing end is configured to process the information based on the query content, the retrieved text and the retrieval The description data obtained generates the guidance information.

7. The system according to claim 6, wherein: The guide information processing end is configured to splice the retrieved text and the retrieved description data to obtain a first splicing result, and generate the guide information based on the first splicing result and the query content.

8. The system according to claim 1, wherein: The guidance information processing end is configured to at least splice the multiple retrieved texts to obtain a second splicing result, and generate the guidance information based on the second splicing result and the query content.

9. The system according to claim 1, wherein: The text processing end is configured to send the retrieved text to the client; The client is configured to modify the retrieved text in response to a first modification operation performed on the interactive interface; The guidance information processing end is configured to generate the guidance information based on the query content and the modified text.

10. The system according to claim 1, wherein: The guidance information processing end is configured to send the guidance information to the client; The client is configured to modify the guidance information in response to a second modification operation performed on the interactive interface.

11. The system according to claim 10, wherein: The information reply end is configured to display the modified guidance information, and call the machine learning model to analyze the modified guidance information and output the reply information.

12. The system according to any one of claims 1 to 11, wherein: The information reply end is configured to send the reply information and the retrieved text to the client; The client is configured to respond to a query operation on the reply information and display the retrieved text on the interactive interface.

13. An information interaction method, comprising: Detecting a query request in the interactive interface, wherein the query request at least includes query content to be answered; In response to the query request, displaying text associated with the query content on the interactive interface, wherein the text is retrieved based on the query content; Displaying guidance information on the interactive interface, wherein the guidance information is based on the query content and said retrieved text generating; The reply information is displayed on the interactive interface, wherein the reply information is obtained by analyzing the guidance information based on a machine learning model.

14. An information interaction method, comprising: Obtaining a query request from an application platform, wherein the query request at least includes query content to be answered in an application scenario where the application platform is located; In response to the query request, obtaining text associated with the query content, wherein the text is retrieved based on the query content; Generate guidance information based on the retrieved text and the query content, wherein the guidance information is used to generate reply information corresponding to the query content; Calling a machine learning model to analyze the guidance information to obtain the response information in the application scenario, wherein the machine learning model is trained based on application data samples in the application scenario; The reply information is output to the application platform.

15. The method according to claim 14, wherein: The reply information satisfies the attributes of the application scenario and is used to describe multimodal information that matches the semantics of the query content, and the multimodal information includes at least one of the following: text information containing character information, video frame information containing frame image information, and audio information.

16. A method for generating information, comprising: Detecting a query request, wherein the query request at least includes query content to be answered; Based on the query content in the query request, retrieving text associated with the query content; Based on the retrieved text and the query content, guidance information is generated, wherein the guidance information is used to enable a machine learning model to analyze the guidance information to obtain response information.

17. A computer program product comprising: A computer program which, when executed by a processor, implements the method of any one of claims 13 to 16.

18. A computer program product comprising: A non-volatile computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 13 to 16 when executed by a processor.

19. A computer program, wherein When the computer program is executed by a processor, the method according to any one of claims 13 to 16 is implemented.

20. An electronic device, comprising: A memory storing an executable program; A processor configured to run the program, wherein when the program is run, the execution of claims 13 to 16 is performed Any one of the methods described in .

Images