AI assistant interaction method and device, electronic equipment and storage medium

Abstract

The invention provides an AI assistant interaction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an interaction operation triggered by a user; determining a target AI assistant and a target information base called by the target AI assistant according to the operation type of the interaction operation; the target AI assistant is any one of two preset AI assistants, and each preset AI assistant corresponds to a target information base of different information; in response to a query instruction triggered based on a user, the target AI assistant performs model reasoning by referring to the target information base to determine a target query result; and displaying the target query result. According to the method and the device, the AI assistant can be controlled to call different information bases according to different interactive operations, so that the technical effect of arousing different AI assistant functions is achieved, and the technical problem of arousing a single AI assistant function in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an AI assistant interaction method and device, an electronic device, and a storage medium. Background Art

[0002] With the advent of the AIGC (Artificial Intelligence Generated Content) era, AI can greatly improve people's life and work efficiency, and AIPC (artificial intelligence personal computer) and AI mobile phones have become the clear direction of market consensus.

[0003] In the related art, some products have realized functions such as waking up AI assistants, taking photos or other functions. However, when the AI ​​assistant is invoked in the related art, only a single AI function can be realized, and different AI functions cannot be invoked based on different needs.

[0004] Therefore, there is a technical problem in the related technology that it can only evoke a single AI assistant function. Summary of the invention

[0005] The present application provides an AI assistant interaction method and device, an electronic device and a storage medium to at least solve the technical problem in the related art that only a single AI assistant function can be evoked.

[0006] According to one aspect of an embodiment of the present application, there is provided an AI assistant interaction method, including:

[0007] Get interactive operations triggered by the user;

[0008] Determine a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of two preset AI assistants, and each of the preset AI assistants corresponds to a target information library of different information;

[0009] In response to the query instruction triggered by the user, the target AI assistant performs model reasoning with reference to the target information library to determine the target query result;

[0010] The target query result is displayed.

[0011] Optionally, as in the aforementioned method, the preset AI assistant includes a first AI assistant and a second AI assistant, and determining the target AI assistant and the target information library called by the target AI assistant according to the operation type of the interactive operation includes:

[0012] In a case where the operation type of the interactive operation is the first type, determining the first AI assistant as the target AI assistant, wherein the first AI assistant is an AI assistant that can perform model reasoning based on the user's private information and Internet public information, and the target information library called by the first AI assistant includes the private information and the Internet public information;

[0013] When the operation type of the interactive operation is the second type, the second AI assistant is determined as the target AI assistant, and the target information library called by the target AI assistant includes Internet public information, wherein the second AI assistant is an AI assistant that can perform model reasoning based on Internet public information, and the target information library called by the second AI assistant includes the Internet public information.

[0014] Optionally, as in the aforementioned method, when the operation type of the interactive operation is the first type, determining that the target AI assistant is the first AI assistant, and the information library called by the target AI assistant includes the privacy information of the user, includes:

[0015] When the operation type of the interactive operation is the first type, privacy prompt information is generated and displayed, wherein the privacy prompt information is used to indicate that the target information library to be called by the target AI assistant contains the user's private information;

[0016] Upon receiving a confirmation operation on the privacy prompt information, the target AI assistant is determined to be the first AI assistant.

[0017] Optionally, as in the aforementioned method, the query instruction includes a first query instruction and a second query instruction, and in response to the query instruction triggered by the user, the target AI assistant performs model reasoning with reference to the target information library, and determining the target query result includes:

[0018] In response to the first query instruction triggered by the user, the target AI assistant performs model reasoning with reference to the target information library to determine a first query result;

[0019] In response to a second query instruction triggered by the user, obtaining a second query result corresponding to the second query instruction based on the second query result and referring to the target information database;

[0020] The second query result is determined as the target query result.

[0021] Optionally, as in the aforementioned method, determining the target information library called by the AI ​​assistant according to the operation type of the interactive operation includes:

[0022] Determining a target application on which the interactive operation acts;

[0023] Determine, according to the information usage rights of the target application, a designated AI assistant and at least one designated information library available to the target application;

[0024] In a case where the designated AI assistant includes the AI ​​assistant indicated by the operation type, the AI ​​assistant indicated by the operation type is determined as the target AI assistant; in a case where the at least one designated information library includes the information library indicated by the operation type, the information library indicated by the operation type is determined as the target information library;

[0025] In a case where the designated AI assistant does not include the AI ​​assistant indicated by the operation type, the designated AI assistant is determined as the target AI assistant; in a case where the at least one designated information library does not include the information library indicated by the operation type, the target information library is determined in the at least one designated information library.

[0026] Optionally, as in the aforementioned method, when the operation type of the interactive operation is the first type, the target AI assistant performs model reasoning with reference to the target information library to determine the target query result, including:

[0027] Obtain a first query result corresponding to the query instruction, which is determined by the target AI assistant in response to the query instruction and after querying the private information repository and the public information repository according to a preset weight, wherein the preset weight is used to indicate the importance of the private information repository and the public information repository when querying.

[0028] Optionally, as in the aforementioned method, the method further comprises:

[0029] Get AI assistant switching information;

[0030] In response to the AI ​​assistant switching information, the target AI assistant is switched, and the information library called by the AI ​​assistant is switched from the first information library to the second information library, wherein the target AI assistant is any one of two preset AI assistants, one of the first information library and the second information library includes private information and Internet public information, and the other only includes the Internet public information, and the first information library and the second information library correspond one-to-one to the two preset AI assistants.

[0031] According to another aspect of the embodiment of the present application, there is also provided an AI assistant interaction device, including:

[0032] An acquisition module, used to acquire the interactive operation triggered by the user;

[0033] An information library determination module, used to determine a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of two preset AI assistants, and each of the preset AI assistants corresponds to a target information library of different information;

[0034] A result determination module, configured to respond to a query instruction triggered by the user, and the target AI assistant refers to the target information library to perform model reasoning and determine a target query result;

[0035] A display module is used to display the target query result.

[0036] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; wherein the memory is used to store a computer program; and the processor is used to execute the method steps in any of the above embodiments by running the computer program stored in the memory.

[0037] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the method steps in any of the above embodiments when executed.

[0038] In an embodiment of the present application, an AI assistant interaction method is adopted, by obtaining an interactive operation triggered by a user; determining a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of two preset AI assistants, and each of the preset AI assistants corresponds to a target information library of different information; in response to a query instruction based on the user trigger, the target AI assistant performs model reasoning with reference to the target information library to determine the target query result; and displays the target query result. Since the target information library can be determined by adopting an operation type based on the interactive operation, and the target query result finally obtained is determined according to the target information library and the query instruction, the AI ​​assistant can be controlled to call different information libraries according to different interactive operations, achieving the technical effect of customizing different AI assistants for users to cope with different user demand scenarios and improve user experience, thereby solving the technical problem of evoking a single AI assistant function existing in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 is a schematic diagram of a hardware environment of an optional AI assistant interaction method according to an embodiment of the present application;

[0042] Figure 2 is a flowchart of an optional AI assistant interaction method according to an embodiment of the present application;

[0043] Figure 3 is a flowchart of an optional AI assistant interaction method according to another embodiment of the present application;

[0044] Figure 4 is a flowchart of an optional AI assistant interaction method according to another embodiment of the present application;

[0045] Figure 5 is a structural block diagram of an optional AI assistant interaction device according to an embodiment of the present application;

[0046] Figure 6 It is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0049] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretation:

[0050] AI assistant is a software or hardware system based on artificial intelligence technology, which is designed to help users complete various tasks and provide multiple functions such as information query, schedule management, smart home control, entertainment, etc. AI assistant interacts with users through natural language processing (NLP), machine learning, speech recognition and synthesis, and provides corresponding services according to user needs.

[0051] According to one aspect of an embodiment of the present application, an AI assistant interaction method is provided. Optionally, in this embodiment, the above-mentioned AI assistant interaction method can be applied to Figure 1 In the hardware environment composed of terminal 1402 and server 1404 shown in FIG. Figure 1 As shown, server 1404 is connected to terminal 1402 via a network, and can be used to provide services (such as game services, application services, etc.) for the terminal or a client installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 1404.

[0052] The above network may include but is not limited to at least one of the following: wired network, wireless network. The above wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the above wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal may not be limited to a PC, a mobile phone, a tablet computer, etc.

[0053] The AI ​​assistant interaction method of the embodiment of the present application can be executed by a server, or by a terminal, or by both a server and a terminal. The terminal can also execute the AI ​​assistant interaction method of the embodiment of the present application by a client installed thereon.

[0054] Taking the AI ​​assistant interaction method in this embodiment executed by the terminal as an example, Figure 2 An AI assistant interaction method provided in an embodiment of the present application includes the following steps:

[0055] Step S202: Acquire the interactive operation triggered by the user.

[0056] The AI ​​assistant interaction method in this embodiment can be applied to scenarios where it is necessary to obtain corresponding query results according to the user's query instructions. In the embodiment of this application, the AI ​​assistant interaction method is described by taking the AI ​​assistant interaction on a smart mobile terminal as an example. For other types of terminals, such as tablet computers, computers, etc., the above AI assistant interaction method is also applicable if there is no contradiction.

[0057] Specifically, the interactive operation can be an operation performed by the user on the smart mobile terminal through key operation, voice input, touch screen operation, gesture operation and other interactive methods, which is intended to trigger the operation of the AI ​​assistant. The key operation can be pressing a preset AI assistant operation key; the voice input can be a voice signal to the smart mobile terminal to wake up the AI ​​assistant; the touch screen operation can be clicking on the application or applet corresponding to the AI ​​assistant on the smart mobile terminal to wake up the AI ​​assistant; the gesture operation can be a gesture to wake up the AI ​​assistant on the smart mobile terminal.

[0058] Step S204, determining the target AI assistant and the target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of the two preset AI assistants, and each preset AI assistant corresponds to a target information library with different information.

[0059] Specifically, after obtaining the interactive operation triggered by the user, the interactive operation can be identified to determine the operation type of the interactive operation. For example, when the interactive operation is a key operation, it can be determined whether the interactive operation is a short press or a long press, a single press or a double press of the AI ​​assistant running key, etc. Different operation types can trigger different AI assistants and cause the AI ​​assistant to call different information libraries.

[0060] The information library can be a collection of information that the AI ​​assistant needs to rely on during the query process. The information library may include, but is not limited to, at least one of the following: a privacy information library and an Internet public information library. Among them, the privacy information library is a collection of the user's private information, such as memo information, chat information, etc., and whether the privacy information library can be called by the AI ​​assistant requires the user's consent before it can be called; the Internet public information library can be a collection of network public information. At the same time, the target AI assistant can only be one of the two preset AI assistants (for example, the first AI assistant and the second AI assistant), and the target information library corresponding to the first AI assistant may include: a privacy information library and an Internet public information library, and the target information library corresponding to the second AI assistant may only contain an Internet public information library.

[0061] As an optional implementation, as in the aforementioned method, the preset AI assistant includes a first AI assistant and a second AI assistant, and step S204 can be implemented by the following steps to determine the target AI assistant and the target information library called by the target AI assistant according to the operation type of the interactive operation: when the operation type of the interactive operation is the first type, the first AI assistant is determined as the target AI assistant, wherein the first AI assistant is an AI assistant that can perform model reasoning based on the user's privacy information and Internet public information, and the target information library called by the first AI assistant includes privacy information and Internet public information; when the operation type of the interactive operation is the second type, the second AI assistant is determined as the target AI assistant, and the target information library called by the target AI assistant includes Internet public information, wherein the second AI assistant is an AI assistant that can perform model reasoning based on Internet public information, and the target information library called by the second AI assistant includes Internet public information. Specifically, when it is determined that the operation type of the interactive operation is the first type, that is, it is determined that the target information library to be called includes the user's private information and Internet public information, that is, in this case, the target information library can include both the private information library and the Internet public information library; when it is determined that the operation type of the interactive operation is the second type, that is, it is determined that the target information library to be called only includes Internet public information, that is, in this case, the target information library only includes the Internet public information library, and the target AI assistant is the second AI assistant. Optionally, the first AI assistant is an AI assistant obtained by applying non-private information for model training; the second AI assistant is an AI assistant obtained by applying private information and non-private information for model training.

[0062] For example, when it is preset that the AI ​​assistant run button is short pressed, the evoked target AI assistant can only call the AI ​​assistant in the Internet public information library, and when the AI ​​assistant run button is long pressed, the evoked target AI assistant can call the AI ​​assistant in the privacy information library and the Internet public information library; if the operation type of the interactive operation is a short press, the target information library is the Internet public information library, and the target AI assistant is the second AI assistant that can only call the Internet public information library; if the operation type of the interactive operation is a long press, the target information library may include: the privacy information library and the Internet public information library, or include both the privacy information library and the Internet public information library, and then the target AI assistant is the first AI assistant that only calls the privacy information library.

[0063] As an optional implementation, as in the aforementioned method, the aforementioned steps can be implemented by steps S302 and S304 as described below: when the operation type of the interactive operation is the first type, it is determined that the target AI assistant is the first AI assistant, and the information library called by the target AI assistant includes the user's privacy information:

[0064] Step S302: When the operation type of the interactive operation is the first type, privacy prompt information is generated and displayed, wherein the privacy prompt information is used to indicate that the target information library to be called by the target AI assistant contains the user's privacy information.

[0065] That is to say, when the operation type of the interactive operation is the first type, the user's private information will be retrieved. At this time, in order to prevent the user's private information from being retrieved by the AI ​​assistant due to accidental touch, a privacy prompt information is generated and displayed to indicate to the user that the first AI assistant will be awakened and the first AI assistant will retrieve the user's private information. Optionally, the privacy prompt information can be displayed in a pop-up window, or in a voice broadcast, etc.

[0066] Step S304: upon receiving a confirmation operation for the privacy prompt information, determining that the target AI assistant is the first AI assistant, and that the information library called by the target AI assistant includes the user's privacy information.

[0067] Specifically, after the user sees the privacy prompt information on the smart mobile terminal, the user can confirm whether to allow the first AI assistant to be invoked and whether to allow the user's privacy information to be called. When a confirmation operation is received for the privacy prompt information, it is determined that the first AI assistant can be invoked, and the information library allowed to be called includes the privacy information library. If a rejection operation is received for the privacy prompt information, it is determined that the first AI assistant cannot be invoked, and the information library called by the invoked target AI assistant must not include the privacy information library.

[0068] The privacy prompt information may include a first control for indicating that the use of the privacy information is allowed and a second control for indicating that the use of the privacy information is not allowed, so performing a confirmation operation on the privacy prompt information may be an operation on the first control, and performing a rejection operation on the privacy prompt information may be an operation on the second control. In addition, the confirmation operation or the rejection operation may also be performed by voice, which are not listed here one by one.

[0069] Step S206, in response to the query instruction triggered by the user, obtain the target AI assistant to refer to the target information library for model reasoning and determine the target query result.

[0070] Specifically, after the target AI assistant is awakened, the user can input query instructions through voice, text or image; then the target AI assistant can query in the target information database according to the query instruction to obtain the target query result corresponding to the query instruction and obtained with reference to the target information database.

[0071] For example, when the target information database only includes the Internet public information database, this situation is generally only used to query broad knowledge or common sense questions, etc. For example, when the query instruction is "Will it rain tomorrow?", you can query the Internet public information to get the corresponding target query result; when the target information database includes a private information database, the user needs to query in his or her own personal data. For example, when the query instruction is "What are your plans for tomorrow?", the AI ​​assistant can only query the private information database, such as querying the user's memo, chat history, calendar and other personal information to determine the user's plans for tomorrow. In addition, when the query instruction is "Help me arrange tomorrow's itinerary," the AI ​​assistant can first query the private information database to obtain what the user is going to do and where tomorrow, and then query the Internet public information database to obtain driving routes to various locations.

[0072] Step S208: display the target query result.

[0073] Specifically, after the target query result is obtained, the target query result can be displayed on the device triggered by the user.

[0074] As an optional implementation, as in the aforementioned method, after determining the first query result corresponding to the query instruction, the method further includes the following steps: in response to the first query instruction triggered by the user, the target AI assistant refers to the target information library to perform model reasoning and determine the first query result; in response to the second query instruction triggered by the user; the target AI assistant responds to the second query instruction, obtains the second query result corresponding to the second query instruction based on the second query result and with reference to the target information library; and determines the second query result as the target query result. That is to say, after obtaining the first query result, the target AI assistant can continue to query based on the first query result, and when querying for the second time, it can also refer to the aforementioned target information library, so as to obtain the second query result corresponding to the second query instruction based on the first query result and the target information library, and finally determine the second query result as the target query result.

[0075] Optionally, when the first query result is obtained by the target AI assistant by calling the Internet public information database, the target AI assistant in this case is the second AI assistant. If the user asks again after obtaining the first query result, the target AI assistant can respond to the second query instruction triggered based on the first query result, integrate the Internet public information database again to determine the second query result corresponding to the second query instruction, and display the second query result. For example, when the first query result is "Tomorrow the weather will be cloudy and turn to light rain", if the user issues the second query instruction "When will it rain" again, the target AI assistant can determine based on the first query result that the user wants to know when it will start to rain tomorrow, and then continue to query in the Internet public information database to determine the specific time when it will rain tomorrow.

[0076] Optionally, when the first query result is obtained by the AI ​​assistant by calling the privacy information library, the target AI assistant in this case is the first AI assistant. If the user asks again after obtaining the first query result, the target AI assistant can respond to the second query instruction triggered by the first query result, integrate the privacy information library again to determine the second query result corresponding to the second query instruction, and display the second query result. For example, when the first query result is obtained by querying the photo library (i.e., one of the privacy information libraries) for photos of this year's trip to Beijing, if the user again issues a second query instruction "What are the photos of returning home after the trip", the target AI assistant can determine based on the first query result that the user wants to know the photos of the process of returning home after the trip to Beijing, and then can determine the photos of the process of returning home after the trip to Beijing based on the shooting time of the photos of this year's trip to Beijing (i.e., the time information obtained by the first query result), and continue to query in the photo library, and display the photos of the process of returning home.

[0077] This embodiment uses an operation type based on interactive operations to determine the target information library, and the first query result finally obtained is determined based on the target information library and the query instruction, so that the AI ​​assistant can be controlled to call different information libraries according to different interactive operations, thereby achieving the technical effect of customizing different AI assistants for users to cope with different user demand scenarios and improve user experience, thereby solving the technical problem of evoking a single AI assistant function existing in related technologies.

[0078] As an optional implementation, as in the aforementioned method, the aforementioned step S204 can be implemented by steps S402 to S408 as follows to determine the target information library called by the AI ​​assistant according to the operation type of the interactive operation:

[0079] Step S402: determine the target application on which the interactive operation acts.

[0080] Specifically, on a smart mobile terminal, different applications can call the AI ​​assistant to implement AI functions, but different applications have different corresponding permissions. Therefore, it is necessary to determine the target application on which the interactive operation acts. Optionally, as long as the application running on the main interface at the moment of invoking the AI ​​assistant is determined, it can be determined as the target application.

[0081] Step S404: Determine a designated AI assistant and at least one designated information library available to the target application according to the information usage permission of the target application.

[0082] Specifically, different applications have different information usage permissions. In this embodiment, the information usage permission may be whether or not the application has the permission to use the private information library. For example, the photo album may have the permission to use private information, but the game may not have the permission to use private information. Furthermore, the permission to use private information may be further refined. For example, the photo album may have the permission to use all local photos, but not the permission to use chat records.

[0083] The information library and AI assistant corresponding to each application can be configured in advance in the information usage permission configuration file, so that after the target application is determined, the information library and AI assistant corresponding to the target application can be queried in the information usage permission configuration file and determined as the designated information library and designated AI assistant.

[0084] Step S406: When the designated AI assistant includes the AI ​​assistant indicated by the operation type, the AI ​​assistant indicated by the operation type is determined as the target AI assistant; when at least one designated information library includes the information library indicated by the operation type, the information library indicated by the operation type is determined as the target information library.

[0085] After determining the designated information library, the designated information library can be compared with the information library corresponding to the operation type. When at least one designated information library includes the information library indicated by the operation type, the information library indicated by the operation type is determined as the target information library. After determining the designated AI assistant, the designated AI assistant can be compared with the AI ​​assistant corresponding to the operation type. When at least one designated AI assistant includes the AI ​​assistant indicated by the operation type, the AI ​​assistant indicated by the operation type is determined as the target information library.

[0086] Step S408: When the designated AI assistant does not include the AI ​​assistant indicated by the operation type, the designated AI assistant is determined as the target AI assistant; when at least one designated information library does not include the information library indicated by the operation type, the target information library is determined in at least one designated information library.

[0087] When at least one designated information library does not include the information library indicated by the operation type, the target application cannot use the information library indicated by the operation type, so the target information library can only be determined from at least one designated information library corresponding to the target application. When at least one designated information library does not include the AI ​​assistant indicated by the operation type, the target application cannot enable the AI ​​assistant indicated by the operation type, so the target AI assistant can only be determined from at least one designated AI assistant corresponding to the target application.

[0088] The method of this embodiment can limit the information and AI assistant that can be used by each application by setting information usage permissions corresponding to the application, thereby improving the security of the information.

[0089] As an optional implementation, as in the aforementioned method, when the operation type of the interactive operation is the first type, the target AI assistant refers to the target information library to perform model reasoning and determine the target query result, including:

[0090] Obtain a first query result corresponding to the query instruction, which is determined by the target AI assistant in response to the query instruction and after searching the private information library and the Internet public information library according to preset weights, wherein the preset weights are used to indicate the importance of the private information library and the Internet public information library when querying.

[0091] That is to say, when the operation type of the interactive operation is of the first type, the target information library may include a privacy information library and an Internet public information library, and the target AI assistant may call the privacy information library and the Internet public information library at the same time, and may call the privacy information library and the Internet public information library according to preset weights, and adjust the queried results according to the preset weights, so that the first query result finally determined can effectively combine the information in the privacy information library and the Internet public information library.

[0092] As an optional implementation, the aforementioned method further includes the following steps: obtaining AI assistant switching information; in response to the AI ​​assistant switching information, switching the target AI assistant, and switching the information library called by the AI ​​assistant from the first information library to the second information library, wherein the target AI assistant is any one of the two preset AI assistants, one of the first information library and the second information library includes privacy information and Internet public information, and the other only includes Internet public information, and the first information library and the second information library correspond one-to-one to the two preset AI assistants. In other words, after obtaining the AI ​​assistant switching information, it is necessary to switch the AI ​​assistant and the information library at the same time. The first information library in this embodiment is the information library currently used by the target AI assistant, and the second information library is the information library that can be called by the switched AI assistant. Through the method of this embodiment, the switching of AI assistants can be achieved, so that the AI ​​assistant can meet real-time requirements.

[0093] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, 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 modules involved are not necessarily required by the present application.

[0094] 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 a necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, 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 (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0095] According to another aspect of an embodiment of the present application, an AI assistant interaction device for implementing the above-mentioned AI assistant interaction method is also provided. Figure 5 is a structural block diagram of an optional AI assistant interaction device according to an embodiment of the present application, such as Figure 5 As shown, the device may include:

[0096] An acquisition module 51 is used to acquire an interactive operation triggered by a user;

[0097] An information library determination module 52 is used to determine a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of two preset AI assistants, and each preset AI assistant corresponds to a target information library of different information;

[0098] A result determination module 53 is used to respond to a query instruction triggered by a user, and the target AI assistant refers to the target information library to perform model reasoning and determine the target query result;

[0099] The display module 54 is used to display the target query result.

[0100] It should be noted that the acquisition module 51 in this embodiment can be used to execute the above step S202, the information library determination module 52 in this embodiment can be used to execute the above step S204, the result determination module 53 in this embodiment can be used to execute the above step S206, and the display module 54 in this embodiment can be used to execute the above step S208.

[0101] Through the above-mentioned module, the target information library can be determined by adopting the operation type based on the interactive operation, and the first query result finally obtained is determined according to the target information library and the query instruction, so that the AI ​​assistant can be controlled to call different information libraries according to different interactive operations, thereby achieving the technical effect of being able to evoke different AI assistant functions, thereby solving the technical problem of evoked a single AI assistant function existing in the related technology.

[0102] The device in this embodiment, in addition to the above-mentioned modules, may also include a module for executing any method in any of the aforementioned AI assistant interaction method embodiments.

[0103] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0104] According to another aspect of an embodiment of the present application, an electronic device for implementing the above-mentioned AI assistant interaction method is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0105] According to another embodiment of the present application, there is also provided an electronic device, including: Figure 4 As shown, the electronic device may include: a processor 1501 , a communication interface 1502 , a memory 1503 and a communication bus 1504 , wherein the processor 1501 , the communication interface 1502 , and the memory 1503 communicate with each other via the communication bus 1504 .

[0106] Memory 1503, used for storing computer programs;

[0107] The processor 1501 is used to implement the following steps when executing the program stored in the memory 1503:

[0108] Step S202: Acquire the interactive operation triggered by the user.

[0109] Step S204, determining the target AI assistant and the target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of the two preset AI assistants, and each preset AI assistant corresponds to a target information library with different information.

[0110] Step S206, in response to the query instruction triggered by the user, obtain the target AI assistant to refer to the target information library for model reasoning and determine the target query result.

[0111] Step S208: display the target query result.

[0112] Optionally, in this embodiment, the above-mentioned communication bus can be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0113] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0114] As an example, the memory 1503 may include, but is not limited to, the acquisition module 51, the information base determination module 52, and the result determination module 53 in the AI ​​assistant interaction device. In addition, it may also include, but is not limited to, other module units in the AI ​​assistant interaction device, which will not be repeated in this example.

[0115] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0116] An embodiment of the present application further provides a computer-readable storage medium, the storage medium including a stored program, wherein the method steps of the above method embodiment are executed when the program is run.

[0117] Optionally, in this embodiment, the storage medium may include but is not limited to: a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0118] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0119] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0120] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 units or modules, which can be electrical or other forms.

[0122] 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 provided in this embodiment.

[0123] 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.

[0124] The above is only a preferred implementation of the present application. 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 application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An AI assistant interaction method, characterized in that: include: Get interactive operations triggered by the user; Determine a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of two preset AI assistants, and each of the preset AI assistants corresponds to a target information library of different information; In response to the query instruction triggered by the user, the target AI assistant performs model reasoning with reference to the target information library to determine the target query result; The target query result is displayed.

2. The method according to claim 1, characterized in that The preset AI assistant includes a first AI assistant and a second AI assistant, and determining a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation includes: In a case where the operation type of the interactive operation is the first type, determining the first AI assistant as the target AI assistant, wherein the first AI assistant is an AI assistant that can perform model reasoning based on the user's private information and Internet public information, and the target information library called by the first AI assistant includes the private information and the Internet public information; When the operation type of the interactive operation is the second type, the second AI assistant is determined as the target AI assistant, and the target information library called by the target AI assistant includes Internet public information, wherein the second AI assistant is an AI assistant that can perform model reasoning based on Internet public information, and the target information library called by the second AI assistant includes the Internet public information.

3. The method according to claim 2, characterized in that The step of determining, when the operation type of the interactive operation is the first type, that the target AI assistant is the first AI assistant, and the information library called by the target AI assistant includes the privacy information of the user, includes: When the operation type of the interactive operation is the first type, privacy prompt information is generated and displayed, wherein the privacy prompt information is used to indicate that the target information library to be called by the target AI assistant contains the user's private information; Upon receiving a confirmation operation on the privacy prompt information, the target AI assistant is determined to be the first AI assistant.

4. The method according to claim 1, characterized in that The query instruction includes a first query instruction and a second query instruction, and in response to the query instruction triggered by the user, the target AI assistant performs model reasoning with reference to the target information library, and determines the target query result includes: In response to the first query instruction triggered by the user, the target AI assistant performs model reasoning with reference to the target information library to determine a first query result; In response to a second query instruction triggered by the user, obtaining a second query result corresponding to the second query instruction based on the second query result and referring to the target information database; The second query result is determined as the target query result.

5. The method according to claim 1, characterized in that The step of determining a target information library to be called by the AI ​​assistant according to the operation type of the interactive operation includes: Determining a target application on which the interactive operation acts; Determine, according to the information usage rights of the target application, a designated AI assistant and at least one designated information library available to the target application; In a case where the designated AI assistant includes the AI ​​assistant indicated by the operation type, the AI ​​assistant indicated by the operation type is determined as the target AI assistant; in a case where the at least one designated information library includes the information library indicated by the operation type, the information library indicated by the operation type is determined as the target information library; In a case where the designated AI assistant does not include the AI ​​assistant indicated by the operation type, the designated AI assistant is determined as the target AI assistant; in a case where the at least one designated information library does not include the information library indicated by the operation type, the target information library is determined in the at least one designated information library.

6. The method according to claim 2, characterized in that When the operation type of the interactive operation is the first type, the target AI assistant performs model reasoning with reference to the target information library to determine the target query result, including: Obtain a first query result corresponding to the query instruction, which is determined by the target AI assistant in response to the query instruction and after querying the private information repository and the public information repository according to a preset weight, wherein the preset weight is used to indicate the importance of the private information repository and the public information repository when querying.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Get AI assistant switching information; In response to the AI ​​assistant switching information, the target AI assistant is switched, and the information library called by the AI ​​assistant is switched from the first information library to the second information library, wherein the target AI assistant is any one of two preset AI assistants, one of the first information library and the second information library includes private information and Internet public information, and the other only includes the Internet public information, and the first information library and the second information library correspond one-to-one to the two preset AI assistants.

8. An AI assistant interaction device, characterized in that: include: An acquisition module, used to acquire the interactive operation triggered by the user; An information library determination module, used to determine a target AI assistant and a target information library called by the target AI assistant according to the operation type of the interactive operation; the target AI assistant is any one of two preset AI assistants, and each of the preset AI assistants corresponds to a target information library of different information; A result determination module, configured to respond to a query instruction triggered by the user, and the target AI assistant refers to the target information library to perform model reasoning and determine a target query result; A display module is used to display the target query result.

9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein: The processor, the communication interface and the memory communicate with each other via the communication bus, wherein: The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 7 by running the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 7 when executed.

Images