Interaction method and device based on large model, terminal equipment and storage medium

By obtaining and processing data to be interacted, establishing interactive relationships, realizing interaction between users and users, users and private big models, solving the problem of single interaction methods of large models, improving interaction efficiency and accuracy, and Protect the security and privacy of user data.

CN118965329APending Publication Date: 2024-11-15深圳市健成星云科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410872260.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-01
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The interaction modes of large models in natural language processing, computer vision, speech recognition and other fields are single and lack diversity.

Method used

By obtaining the data to be interacted, extracting the information of designated interaction objects, judging and establishing interactive relationships, the interaction between users and users, users and private big models and private big models is realized, and a variety of interaction methods based on big models are provided.

Benefits of technology

It realizes secure and diversified interactions between users and users, users and private big models, and private big models, improves interaction efficiency and accuracy, and protects the security and privacy of user data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118965329A_ABST
    Figure CN118965329A_ABST
Patent Text Reader

Abstract

The invention is suitable for the technical field of artificial intelligence, and provides an interaction method and device based on a large model, terminal equipment and a storage medium. The interaction method based on the large model comprises the steps of obtaining to-be-interacted data; specified interaction object information in the to-be-interacted data is extracted, and a specified interaction object is determined as a target interaction object; judging whether an interaction relationship with the target interaction object is established or not; and if the interaction relationship with the target interaction object is not established, establishing the interaction relationship with the target interaction object, interacting with the target interaction object based on the to-be-interacted data, and obtaining interaction data returned by the target interaction object. According to the embodiment of the invention, interaction between users, interaction between users and own large models, interaction between users and other users and interaction between large models can be realized, namely, multiple interaction modes based on the large models are provided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and in particular, relates to an interaction method, apparatus, terminal device and storage medium based on a large model. Background Art

[0002] Large models are widely used in various fields such as natural language processing, computer vision, speech recognition, and recommendation systems. For example, large models can be used to handle more complex natural language processing tasks, such as machine translation, speech recognition, text summarization, sentiment analysis, etc. In related technologies, although large models can interact with users in a conversational manner, the interaction method is still limited to the conversational interaction between large models and users, and the interaction method is relatively simple. Summary of the invention

[0003] The embodiments of the present application provide a large-model-based interaction method, apparatus, terminal device, and storage medium, which can solve the problem of a single large-model interaction method in related technologies.

[0004] In a first aspect, an embodiment of the present application provides an interaction method based on a large model, comprising:

[0005] Get the data to be interacted with;

[0006] Extracting designated interaction object information from the to-be-interacted data, and determining the designated interaction object as a target interaction object, wherein the designated interaction object includes one or more of a user and a private big model, and each user corresponds to one private big model;

[0007] Determining whether an interactive relationship has been established with the target interactive object;

[0008] If no interaction relationship is established with the target interaction object, an interaction relationship is established with the target interaction object, and interaction is performed with the target interaction object based on the data to be interacted with, and interaction data returned by the target interaction object is acquired.

[0009] In a second aspect, an embodiment of the present application provides an interactive device based on a large model, including:

[0010] An acquisition module is used to acquire data to be interacted with;

[0011] A determination module, used to extract the designated interaction object information in the to-be-interacted data, and determine the designated interaction object as a target interaction object, wherein the designated interaction object includes one or more of a user and a private big model, and each user corresponds to one private big model;

[0012] A judgment module, used to judge whether an interaction relationship has been established with the target interaction object;

[0013] The interaction module is used to establish an interaction relationship with the target interaction object if no interaction relationship has been established with the target interaction object, and to interact with the target interaction object based on the data to be interacted with, and to obtain the interaction data returned by the target interaction object.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned large model-based interaction method when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned large model-based interaction method are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute the above-mentioned large model-based interaction method.

[0017] The beneficial effect of the embodiment of the present application compared with the prior art is: the embodiment of the present application obtains the data to be interacted, extracts the information of the designated interactive object in the data to be interacted, and determines that the designated interactive object is the target interactive object, and determines whether an interactive relationship has been established with the target interactive object. If an interactive relationship has not been established with the target interactive object, an interactive relationship is established with the target interactive object, and based on the data to be interacted, the target interactive object is interacted with to obtain the interactive data returned by the target interactive object. The embodiment of the present application can realize the interaction between users, users and their own large models, users and large models of other users, and large models and large models, that is, it provides a variety of interaction methods based on large models. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 It is a schematic diagram of an implementation flow of an interaction method based on a large model provided in an embodiment of the present application;

[0020] Figure 2 It is a structural schematic diagram of an interactive device based on a large model provided in an embodiment of the present application;

[0021] Figure 3 It is a structural diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are protected by the present application.

[0023] It should be noted that the terms "include", "comprises" and "have" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, terminal, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices. In the claims, specification and drawings of the present application, relational terms such as "first" and "second" are merely used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such real-time relationship or order between these entities / operations / objects.

[0024] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] Large models are widely used in various fields such as natural language processing, computer vision, speech recognition, and recommendation systems. For example, large models can be used to handle more complex natural language processing tasks, such as machine translation, speech recognition, text summarization, sentiment analysis, etc. In related technologies, although large models can interact with users in a conversational manner, the interaction method is still limited to the conversational interaction between large models and users, and the interaction method is relatively simple.

[0026] In view of this, the embodiments of the present application can realize the interaction between users, users and their own big models, users and other users' big models, and big models and big models, that is, it provides a variety of interaction methods based on big models.

[0027] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0028] Figure 1 The present invention provides a schematic diagram of a large model-based interactive method for implementing the flow chart, which can be applied to a terminal device, which can be a mobile phone, a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, etc.

[0029] Specifically, the above-mentioned large model-based interaction method may include the following steps S101 to S104.

[0030] It is important to understand that in the usage scenario of this application, users can have their own private big model, which is highly customized and personalized, so as to provide users with more accurate and personalized services. Unlike the big models on the current market, which mostly provide standardized and integrated solutions, the private big model in this application allows users to adjust various aspects of the model according to specific needs, including algorithm selection, data processing methods and user interface.

[0031] Step S101, obtaining data to be interacted with.

[0032] The data to be interacted with may be data generated by a user or a big model that needs to interact with other users or big models, and may include text, voice, image, and other forms. It should be understood that in some usage scenarios, a user may issue an interaction instruction to his or her big model, and the big model may interact with other users or big models according to the interaction instruction. Therefore, the data to be interacted with may be generated by a big model.

[0033] In the implementation of the present application, the terminal device can receive data to be interacted from the user or the private model. These data can be transmitted through various interfaces (such as API, web page, mobile application, etc.). The data format may include text, voice, image, etc.

[0034] Step S102: extracting information of a designated interactive object from the to-be-interacted data, and determining the designated interactive object as a target interactive object.

[0035] The designated interaction objects include one or more of users and private big models, and each user corresponds to a private big model.

[0036] In the implementation of the present application, the terminal device can parse the specified interaction object information from the data to be interacted, such as user ID, private model ID, etc., or parse and identify the text data in the data to be interacted, and identify the specified interaction object information in the data to be interacted. Then, according to the parsed information, the target interaction object of this interaction is determined.

[0037] Step S103: determine whether an interactive relationship has been established with the target interactive object.

[0038] It should be understood that this application is different from the existing public big model. In the prior art, all users can interact with the public big model, which can be understood as there is only one big model, and there is no need to establish an interactive relationship between the user and the public big model to start human-computer interaction. However, in this application, the private big model can only interact with other users or other private big models through a specific interface, that is, the private big model needs to establish an interactive relationship with other users or other users' private big models before interaction can begin.

[0039] In the implementation manner of the present application, the terminal device may check whether a necessary interaction relationship or connection has been established between the sender of the data to be interacted with (which may be a user or a private model) and the target interaction object.

[0040] Step S104: if no interaction relationship is established with the target interaction object, then an interaction relationship is established with the target interaction object, and interaction is performed with the target interaction object based on the data to be interacted with, and interaction data returned by the target interaction object is obtained.

[0041] In an embodiment of the present application, if an interactive relationship is not established between the sender of the data to be interacted and the target interactive object, the terminal device may perform necessary operations to establish an interactive relationship. For example, a request may be sent to establish a network connection, verify the user identity, or start a session. Once an interactive relationship is established, the terminal device may perform interactive operations with the target interactive object based on the data to be interacted. The specific interaction process may include multiple steps such as sending a request, receiving a response, and processing data. During the interaction process, the terminal device may receive a response or feedback data from the target interactive object. The interactive data may contain various information, such as text response, voice output, image display, etc. The terminal device may parse and process the interactive data for subsequent use or display to the user.

[0042] The beneficial effect of the embodiment of the present application compared with the prior art is: the embodiment of the present application obtains the data to be interacted, extracts the information of the designated interactive object in the data to be interacted, and determines that the designated interactive object is the target interactive object, and determines whether an interactive relationship has been established with the target interactive object. If an interactive relationship has not been established with the target interactive object, an interactive relationship is established with the target interactive object, and based on the data to be interacted, the target interactive object is interacted with to obtain the interactive data returned by the target interactive object. The embodiment of the present application can realize the interaction between users, users and their own large models, users and large models of other users, and large models and large models, that is, it provides a variety of interaction methods based on large models.

[0043] In some embodiments of the present application, if no interaction relationship is established with the target interaction object, an interaction relationship is established with the target interaction object, and interaction is performed with the target interaction object based on the data to be interacted with, and interaction data returned by the target interaction object is obtained, which may specifically include steps S401 to S405.

[0044] It is understandable that in some scenarios, the big model can send data to be interacted with to other private big models in order to obtain the interaction data returned by the private big model. For example, the user can set his own big model to randomly access the big models of other users in a completely open or limited manner. For example, the user can let his big model obtain specific information or perform some tasks, such as collecting the latest research results in a certain field. You can also randomly let your big model ask any questions to obtain some interesting information. At this time, the user's private big model can send data to be interacted with to other private big models to request the latest research results in certain fields. If the authority permits, other private big models can feedback the latest research results in the field to the private big model.

[0045] Step S401, when the sender of the data to be interacted is the first private model and the target interaction object is the second private model, if there is no interaction relationship established between the first private model and the second private model, identity authentication is performed through a key or a digital certificate.

[0046] The first private macro model and the second private macro model are different private macro models.

[0047] In an implementation manner of the present application, when the sender of the data to be interacted is a first private big model, and the target interaction object is a second private big model, that is, when one private big model sends the data to be interacted to another private big model, if no interaction relationship is established between the first private big model and the second private big model, then the terminal device can perform identity authentication through a key or a digital certificate, and specifically, one or more encryption and decryption processes can be used to ensure the communication security between the two private big models.

[0048] Step S402: If the verification is successful, an interactive relationship between the first private macro model and the second private macro model is established.

[0049] In the implementation manner of the present application, if the identity authentication is successful, that is, it is confirmed that the first private model and the second private model are both legal and authorized entities, then the terminal device can establish an interactive relationship between the two private models. It can be understood that the interactive relationship between the two can be a temporary connection or a long-term cooperative relationship, which can depend on business needs and security policies.

[0050] Step S403: sending the data to be interacted to the second private big model through the first private big model.

[0051] In the implementation manner of the present application, after the interactive relationship is established, the first private macro model may send the data to be interacted to the second private macro model.

[0052] Step S404, after the second private big model determines that the data to be interacted meets the legality requirement, the interaction data returned by the second private big model according to the data to be interacted and the pre-set privacy settings is obtained.

[0053] In the implementation mode of the present application, after receiving the data to be interacted, the second private big model can first determine whether the data to be interacted meets the legality requirements. Specifically, it can include checking whether the format, content, source, etc. of the data comply with the preset rules and restrictions, or verifying whether the first private big model has the interaction authority. Then the second private big model can return the interaction data based on the data to be interacted and the pre-set privacy settings. Specifically, the second private big model can check whether its own privacy settings are allowed. If it is allowed, the second private big model can generate corresponding interaction data based on the data to be interacted, and send the interaction data to the first private big model.

[0054] Step S405: Process the interaction data and output the processed interaction data.

[0055] In the implementation manner of the present application, after the first private big model receives the interactive data returned by the second private big model, the terminal device may further process the data so as to display it to the user, which may specifically include data analysis, conversion, storage and other operations.

[0056] In the implementation mode of the present application, a secure interactive relationship can be established between private large models, and complex data exchange and processing tasks can be realized, which not only improves the efficiency and accuracy of the interaction, but also protects the security and privacy of user data.

[0057] In some specific embodiments of the present application, if no interaction relationship is established with the target interaction object, an interaction relationship is established with the target interaction object, and interaction is performed with the target interaction object based on the data to be interacted with, and interaction data returned by the target interaction object is obtained, which may further include steps S501 to S505.

[0058] It is understandable that in some scenarios, users can send data to be interacted with to other users' private big models to obtain interaction data returned by the private big models. For example, user A can send a request to user B's big model to ask whether user B is free to attend a meeting tomorrow. User B's big model can answer user A based on the schedule information uploaded by user B in advance, such as user B is free tomorrow, or user B is not free tomorrow.

[0059] Step S501, when the sender of the data to be interacted is the first user and the target interaction object is the third private macro model, if there is no interaction relationship established between the first user and the third private macro model, identity authentication is performed through a key or a digital certificate.

[0060] There is no subordinate relationship between the first user and the third private big model, that is, the third private big model is not the private big model of the first user.

[0061] In an implementation manner of the present application, when the sender of the data to be interacted is the first user and the target interaction object is the third private big model, that is, when one user sends the data to be interacted to the private big model of another user, if there is no interaction relationship established between the first user and the third private big model, then the terminal device can perform identity authentication through a key or a digital certificate, and specifically, one or more encryption and decryption processes can be used to ensure the communication security between the user and the private big model.

[0062] Step S502: If the verification is successful, an interactive relationship between the first user and the third private macro model is established.

[0063] In the implementation of the present application, if the identity authentication is successful, that is, it is confirmed that the first user and the third private model are both legal and authorized entities, then the terminal device can establish an interactive relationship between the two private models. It can be understood that the interactive relationship between the two can be a temporary connection or a long-term cooperative relationship, which can depend on business needs and security policies.

[0064] Step S503: sending the data to be interacted to the third private macro model through the first user.

[0065] In the implementation manner of the present application, after the interactive relationship is established, the first user may send the data to be interacted with to the third private macro model.

[0066] Step S504, after the third private big model determines that the data to be interacted meets the legality requirement, the interaction data returned by the third private big model according to the data to be interacted and the pre-set privacy settings is obtained.

[0067] In the implementation mode of the present application, after receiving the data to be interacted, the third private big model can first determine whether the data to be interacted meets the legality requirements. Specifically, it can include checking whether the format, content, source, etc. of the data comply with the preset rules and restrictions, or verifying whether the first user has the interaction authority. Then the third private big model can return the interaction data based on the data to be interacted and the pre-set privacy settings. Specifically, the third private big model can check whether its own privacy settings are allowed. If it is allowed, the third private big model can generate corresponding interaction data based on the data to be interacted, and send the interaction data to the first user.

[0068] Step S505: Process the interaction data and output the processed interaction data.

[0069] In the implementation manner of the present application, after the first user receives the interaction data returned by the third private model, the terminal device may further process the data so as to display it to the user, which may specifically include data analysis, conversion, storage and other operations.

[0070] In the implementation mode of the present application, a user can establish a secure interactive relationship with other users' private big models and realize complex data exchange and processing tasks, which not only improves the efficiency and accuracy of the interaction, but also protects the security and privacy of user data.

[0071] In some specific embodiments of the present application, if no interaction relationship is established with the target interaction object, an interaction relationship is established with the target interaction object, and interaction is performed with the target interaction object based on the data to be interacted with, and interaction data returned by the target interaction object is obtained, which may further include steps S601 to S605.

[0072] It is understood that in some scenarios, multiple users and their corresponding private big models can form a big model group. In this group environment, private big models can communicate with each other to help group members coordinate activities and share information more effectively. For example, user A can initiate an event invitation through his big model, asking who in the group is free tomorrow. The big models of each member can automatically check the schedule and preferences of their owner, determine whether they are free to attend the event, and reply to A's big model.

[0073] Step S601, when the sender of the data to be interacted is the fourth private big model and the target interaction object is the fifth private big model in the private big model group, if there is no interaction relationship established between the fourth private big model and the fifth private big model, identity authentication is performed through a key or a digital certificate.

[0074] The fourth private macro model and the fifth private macro model are different private macro models, the private macro model group includes one or more fifth private macro models, and the fifth private macro models are different from each other.

[0075] Step S602: If the verification is successful, an interactive relationship between the fourth private macro model and the fifth private macro model is established.

[0076] Step S603: Send the data to be interacted to the fifth private big model through the fourth private big model.

[0077] Step S604, after the fifth private big model determines that the data to be interacted meets the legality requirements, the interaction data returned by the fifth private big model according to the data to be interacted and the pre-set privacy settings is obtained.

[0078] Step S605: Process the interaction data and output the processed interaction data.

[0079] In the implementation of the present application, when the sender of the data to be interacted is the fourth private big model, and the target interaction object is the fifth private big model in the private big model group, the fourth private big model can initiate an interaction request to all the fifth private big models in the private big model group. The specific interaction process can refer to the above steps S401 to S405, or steps S501 to S505, which will not be repeated here.

[0080] In some implementations of the present application, the above method may further include steps S701 to S706.

[0081] Step S701, obtaining personal data uploaded by the user to the private macro model.

[0082] Among them, personal data can be any data related to the user uploaded to the private big model, and can be knowledge data such as notes.

[0083] In the implementation manner of the present application, users can upload new knowledge data in real time through a designated interface or API.

[0084] Step S702: organize and save personal data.

[0085] In the implementation mode of the present application, the terminal device can clean and pre-process the received personal data to ensure the uniformity of data quality and format, and store the processed data in a knowledge base according to a certain structure (such as key-value pairs, tables, etc.).

[0086] Step S703, when receiving a query instruction from the user, parsing the query instruction, and retrieving corresponding personal data according to the query instruction.

[0087] In the implementation of the present application, the user can input a query instruction through the interactive interface. When receiving the query instruction of the user, the terminal device can parse the query instruction through the private big model, determine the type and range of the data that the user needs to query, and retrieve the corresponding personal data from the knowledge base according to the parsing result. Exemplarily, if the user wants to query the knowledge data previously uploaded to the private big model, the user can send the corresponding query instruction to his own private big model, and the private big model can retrieve the corresponding personal data from the knowledge base according to the query instruction, and can also perform information retrieval based on the query instruction to feedback more comprehensive information.

[0088] Step S704, obtaining the user's user preferences and historical behaviors.

[0089] In an implementation manner of the present application, the terminal device may analyze and extract the user's preferences and historical behaviors from the user's historical interaction records through data mining, machine learning and other technologies.

[0090] Step S705: Generate prompt information based on user preferences, historical behaviors and corresponding personal data.

[0091] In an implementation manner of the present application, after obtaining user preferences and historical behaviors, the terminal device may expand personal data according to the user preferences and historical behaviors to generate more accurate and personalized data (and prompt information).

[0092] Step S704: output prompt information to the user.

[0093] In an implementation manner of the present application, after obtaining the prompt information, the terminal device can output the prompt information according to a preset output format (such as text, picture, etc.).

[0094] The implementation methods of the present application can enable the private big model to have continuous learning and adaptation capabilities, thereby providing more accurate personalized feedback and suggestions, thereby improving the user experience.

[0095] In some specific implementations of the present application, the above-mentioned organizing and saving of personal data may specifically include steps S801 to S803.

[0096] Step S801, upload personal data to the knowledge base.

[0097] In an implementation manner of the present application, a user may upload personal data that the user wants the large model to record or learn to the knowledge base via a terminal device.

[0098] Step S802, determining whether the personal data is data to be updated.

[0099] In an implementation manner of the present application, the terminal device may pre-set a data update judgment logic, such as checking whether the timestamp, version number or content of the data has changed, and then determine which data is to be updated based on the judgment logic.

[0100] Step S803: If the personal data is data to be updated, the corresponding data in the knowledge base is updated according to the data to be updated.

[0101] In an implementation manner of the present application, for data to be updated, the terminal device can compare it with the corresponding data in the knowledge base, and update or replace the data in the knowledge base based on the comparison result to ensure that the data in the knowledge base is up-to-date and accurate.

[0102] In some embodiments of the present application, the data type of the data to be interacted includes one or more of text data, voice data, image data, and video data. The acquiring of the data to be interacted may specifically include the following steps:

[0103] Receive data to be interacted with, determine the data type of the data to be interacted with, and determine the target interaction data type of the data to be interacted with.

[0104] The target interaction data type is the data type of the interaction data that is finally output.

[0105] In the implementation mode of the present application, after the user uploads the data to be interacted, the terminal device can identify the data type of the data to be interacted, and identify the data type of the data to be interacted. After identifying the data type of the data to be interacted, the corresponding data analysis technology, such as speech recognition, natural language processing, image recognition and video analysis technology, can be called to allow the user to interact in various ways such as text, voice, image and video. And further extraction analysis is performed to extract the target interaction data type hidden in the data to be interacted, so as to determine the data type of the interaction data finally output.

[0106] Figure 2 The schematic diagram of the structure of a large model-based interactive device provided in an embodiment of the present application is shown. The large model-based interactive device 2 can be configured on a terminal device. Specifically, the large model-based interactive device 2 can include:

[0107] The acquisition module 201 is used to acquire the data to be interacted with;

[0108] The determination module 202 is used to extract the designated interaction object information in the to-be-interacted data, and determine the designated interaction object as the target interaction object, wherein the designated interaction object includes one or more of a user and a private big model, and each user corresponds to one private big model;

[0109] A determination module 203 is used to determine whether an interaction relationship has been established with the target interaction object;

[0110] The interaction module 204 is configured to establish an interaction relationship with the target interaction object if no interaction relationship has been established with the target interaction object, interact with the target interaction object based on the data to be interacted with, and obtain interaction data returned by the target interaction object.

[0111] The beneficial effect of the embodiment of the present application compared with the prior art is: the embodiment of the present application obtains the data to be interacted, extracts the information of the designated interactive object in the data to be interacted, and determines that the designated interactive object is the target interactive object, and determines whether an interactive relationship has been established with the target interactive object. If an interactive relationship has not been established with the target interactive object, an interactive relationship is established with the target interactive object, and based on the data to be interacted, the target interactive object is interacted with to obtain the interactive data returned by the target interactive object. The embodiment of the present application can realize the interaction between users, users and their own large models, users and large models of other users, and large models and large models, that is, it provides a variety of interaction methods based on large models.

[0112] In some embodiments of the present application, the interaction module 204 is also used for: when the sender of the data to be interacted is the first private big model, and the target interaction object is the second private big model, if no interaction relationship is established between the first private big model and the second private big model, identity authentication is performed through a key or a digital certificate, and the first private big model and the second private big model are different private big models; if the verification is successful, an interaction relationship is established between the first private big model and the second private big model; the data to be interacted is sent to the second private big model through the first private big model; after the second private big model determines that the data to be interacted meets the legitimacy requirements, the interaction data returned by the second private big model according to the data to be interacted and the pre-set privacy settings is obtained; the interaction data is processed and the processed interaction data is output.

[0113] In some embodiments of the present application, the interaction module 204 is also used for: when the sender of the data to be interacted is the first user and the target interaction object is the third private big model, if no interaction relationship is established between the first user and the third private big model, identity authentication is performed through a key or a digital certificate, and there is no subordinate relationship between the first user and the third private big model; if the verification is successful, an interaction relationship is established between the first user and the third private big model; the data to be interacted is sent to the third private big model through the first user; after the third private big model determines that the data to be interacted meets the legitimacy requirements, the interaction data returned by the third private big model according to the data to be interacted and the pre-set privacy settings is obtained; the interaction data is processed and the processed interaction data is output.

[0114] In some embodiments of the present application, the interaction module 204 is also used for: when the sender of the data to be interacted is a fourth private big model, and the target interaction object is a fifth private big model in a private big model group, if no interaction relationship is established between the fourth private big model and the fifth private big model, identity authentication is performed through a key or a digital certificate, the fourth private big model and the fifth private big model are different private big models, the private big model group includes one or more fifth private big models, and the fifth private big models are different private big models from each other; if the verification is successful, an interaction relationship is established between the fourth private big model and the fifth private big model; the data to be interacted is sent to the fifth private big model through the fourth private big model; after the fifth private big model determines that the data to be interacted meets the legitimacy requirements, the interaction data returned by the fifth private big model according to the data to be interacted and the pre-set privacy settings is obtained; the interaction data is processed and the processed interaction data is output.

[0115] In some embodiments of the present application, the big model-based interaction device also includes an output module, which is used to: obtain the personal data uploaded by the user to the private big model; organize and save the personal data; when receiving the user's query instruction, parse the query instruction, and retrieve the corresponding personal data according to the query instruction; obtain the user's user preferences and historical behaviors; generate prompt information based on the user preferences, the historical behaviors and the corresponding personal data; and output the prompt information to the user.

[0116] In some embodiments of the present application, the output module is also used to: upload the personal data to a knowledge base; determine whether the personal data is data to be updated; if the personal data is the data to be updated, update the corresponding data in the knowledge base according to the data to be updated.

[0117] In some embodiments of the present application, the data type of the data to be interacted includes one or more of text data, voice data, image data, and video data, and the acquisition module 201 is also used to: receive the data to be interacted, determine the data type of the data to be interacted, and determine the target interaction data type of the data to be interacted.

[0118] like Figure 3 FIG. 3 is a schematic diagram of a terminal device provided in an embodiment of the present application. The terminal device 3 may include: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301, such as an interactive program based on a large model. When the processor 301 executes the computer program 303, the steps in the above-mentioned interactive method embodiments based on a large model are implemented, such as Figure 1 Alternatively, when the processor 301 executes the computer program 303, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 2 The obtained module 201, the determined module 202, the judged module 203 and the interacted module 204 are shown.

[0119] The computer program may be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0120] The terminal device may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of a terminal device and does not constitute a limitation of the terminal device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0121] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0122] The memory 302 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The memory 302 may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device. Further, the memory 302 may also include both an internal storage unit of the terminal device and an external storage device. The memory 302 is used to store the computer program and other programs and data required by the terminal device. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0123] It should be noted that, for the convenience and brevity of description, the structure of the above-mentioned terminal device can also refer to the specific description of the structure in the method embodiment, which will not be repeated here.

[0124] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0125] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned large model-based interaction method can be implemented.

[0126] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned large model-based interaction method when executing the computer program product.

[0127] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0129] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0132] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0133] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An interactive method based on a large model, characterized in that: include: Get the data to be interacted with; Extracting designated interaction object information from the to-be-interacted data, and determining the designated interaction object as a target interaction object, wherein the designated interaction object includes one or more of a user and a private big model, and each user corresponds to one private big model; Determining whether an interactive relationship has been established with the target interactive object; If no interaction relationship is established with the target interaction object, an interaction relationship is established with the target interaction object, and interaction is performed with the target interaction object based on the data to be interacted with, and interaction data returned by the target interaction object is acquired.

2. The interactive method based on a large model as claimed in claim 1, characterized in that: If no interaction relationship is established with the target interaction object, establishing an interaction relationship with the target interaction object, interacting with the target interaction object based on the data to be interacted with, and acquiring interaction data returned by the target interaction object, includes: When the sender of the data to be interacted is a first private model, and the target interaction object is a second private model, if no interaction relationship is established between the first private model and the second private model, identity authentication is performed through a key or a digital certificate, and the first private model and the second private model are different private models; If the verification is successful, establishing an interactive relationship between the first private big model and the second private big model; Sending the data to be interacted to the second private big model through the first private big model; After the second private big model determines that the data to be interacted meets the legality requirement, obtaining the interaction data returned by the second private big model according to the data to be interacted and the pre-set privacy settings; The interaction data is processed and the processed interaction data is output.

3. The interactive method based on a large model as claimed in claim 1, characterized in that: If no interaction relationship is established with the target interaction object, establishing an interaction relationship with the target interaction object, interacting with the target interaction object based on the data to be interacted with, and acquiring interaction data returned by the target interaction object, includes: When the sender of the data to be interacted is the first user, and the target interaction object is the third private macro model, if there is no interaction relationship established between the first user and the third private macro model, identity authentication is performed through a key or a digital certificate, and there is no subordinate relationship between the first user and the third private macro model; If the verification is successful, an interactive relationship between the first user and the third private macro model is established; Sending the data to be interacted to the third private macro model through the first user; After the third private big model determines that the data to be interacted meets the legality requirement, obtaining the interaction data returned by the third private big model according to the data to be interacted and the pre-set privacy settings; The interaction data is processed and the processed interaction data is output.

4. The interactive method based on a large model as claimed in claim 1, characterized in that: If no interaction relationship is established with the target interaction object, establishing an interaction relationship with the target interaction object, interacting with the target interaction object based on the data to be interacted with, and acquiring interaction data returned by the target interaction object, includes: When the sender of the data to be interacted is the fourth private big model, and the target interaction object is the fifth private big model in the private big model group, if no interaction relationship is established between the fourth private big model and the fifth private big model, identity authentication is performed through a key or a digital certificate, the fourth private big model and the fifth private big model are different private big models, the private big model group includes one or more fifth private big models, and the fifth private big models are different private big models from each other; If the verification is successful, then establishing an interactive relationship between the fourth private macro model and the fifth private macro model; Sending the data to be interacted to the fifth private big model through the fourth private big model; After the fifth private big model determines that the data to be interacted meets the legality requirement, obtaining the interaction data returned by the fifth private big model according to the data to be interacted and the pre-set privacy settings; The interaction data is processed and the processed interaction data is output.

5. The interactive method based on a large model as claimed in claim 1, characterized in that: The method further comprises: Obtaining personal data uploaded by the user to the private macro model; Organize and store the personal data; When receiving a query instruction from the user, parsing the query instruction, and retrieving the corresponding personal data according to the query instruction; Obtaining user preferences and historical behaviors of the user; Generate prompt information according to the user preference, the historical behavior and the corresponding personal data; The prompt information is output to the user.

6. The interactive method based on a large model as claimed in claim 5, characterized in that: The personal data is collated and stored, including: upload said personal data to the knowledge base; Determine whether the personal data is data to be updated; If the personal data is the data to be updated, the corresponding data in the knowledge base is updated according to the data to be updated.

7. The interactive method based on a large model as claimed in claim 1, characterized in that: The data type of the data to be interacted includes one or more of text data, voice data, image data, and video data. The acquiring of the data to be interacted includes: The data to be interacted is received, a data type of the data to be interacted is determined, and a target interaction data type of the data to be interacted is determined.

8. An interactive device based on a large model, characterized in that: include: An acquisition module is used to acquire data to be interacted with; A determination module, used to extract the designated interaction object information in the to-be-interacted data, and determine the designated interaction object as a target interaction object, wherein the designated interaction object includes one or more of a user and a private big model, and each user corresponds to one private big model; A judgment module, used to judge whether an interaction relationship has been established with the target interaction object; The interaction module is used to establish an interaction relationship with the target interaction object if no interaction relationship has been established with the target interaction object, and to interact with the target interaction object based on the data to be interacted with, and to obtain the interaction data returned by the target interaction object.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the large model-based interaction method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the large model-based interaction method according to any one of claims 1 to 7 are implemented.