Message interaction method and device

Abstract

The invention relates to a message interaction method and device, and belongs to the technical field of message interaction, and the method comprises the following steps: a 5G message standard communication service receives a session message of a user, and sends the session message to a message access service of a 5G message ecological service platform; the message access service of the 5G message ecological service platform matches an AI source for the session message of the user according to a preset route, and sends the session message of the user to an AI control engine of the 5G message ecological service platform; an AI control engine of the 5G message ecological service platform sends the session message of the user to a matched AI source for intelligent processing to obtain an AI processing result; and sending the AI processing result to the user. According to the invention, the AI control engine is arranged in the 5G message ecological service platform, the control and scheduling of various AI sources are realized, the optimal and most suitable AI service capability is introduced into the 5G message ecological service platform, and the AI service capability of message interaction is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of message interaction, and in particular, relates to a message interaction method and device. Background Art

[0002] The 5G message MaaP feature proposed the concept of Chatbot application very early. Its vision is to have artificial intelligence capabilities on the application side to interact with users intelligently. At present, the implementation method of providing AI services on the application side is to implement and manage AI functions for related functions according to their business needs and application scenarios, or to call external AI capabilities through local deployment, API interfaces, etc. Some AI capabilities are relatively mature at present, such as voice recognition, but taking the 5G message Chatbot application message interaction scenario as an example, the goal is to achieve automated application message conversation interaction capabilities that meet user expectations, are related to the current Chatbot application field, and are close to the communication experience between people. Since it involves technologies such as AI semantic recognition and machine learning, it is still a technically difficult area in the industry. Its capabilities are constantly evolving, and different representative products emerge in different periods. Although there are many domestic and foreign products providing related AI services on the existing network, there is no single product that can truly meet the various business needs of different applications of 5G messages. The technical capabilities of Chatbot application implementers connected to 5G messages vary greatly. In full accordance with the RCS standard definition, the Chatbot application side implements AI-based intelligent message conversation capabilities. The threshold is too high and the quality of implementation is uneven.

[0003] Recently, OpenAI has launched the ChatGPT service. The intelligent conversation capabilities and quality demonstrated by ChatGPT have been recognized by the public and triggered a wave of follow-up in the industry. However, ChatGPT belongs to a foreign company, and its implementation model and service capabilities are not suitable for direct application in domestic businesses. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the invention is to provide a message interaction method and device, which realizes the control and scheduling of multiple AI sources by building an AI control engine into the 5G message ecological service platform, introduces the best and most suitable AI service capabilities into the 5G message ecological service platform, and improves the AI ​​service capabilities of message interaction.

[0005] In a first aspect of the present invention, a message interaction method is proposed, which is applied to a system including: a 5G message standard communication service, a 5G message ecological service platform and a Chatbot, including:

[0006] The 5G message standard communication service receives the user's session message and sends the session message to the message access service of the 5G message ecological service platform;

[0007] The message access service of the 5G message ecological service platform matches the AI ​​source for the user's conversation message according to the preset route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform;

[0008] The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result;

[0009] Sending the AI ​​processing result to the user;

[0010] Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

[0011] Furthermore, in the above-mentioned message interaction method, in the system composed of 5G message standard communication service, 5G message ecological service platform and Chatbot, the 5G message ecological service platform is built on the 5G message standard communication service in an overlay network manner, and the 5G message ecological service platform is used for Chatbot access.

[0012] Furthermore, in the above-mentioned message interaction method, the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, and also includes:

[0013] The AI ​​control engine of the 5G message ecological service platform performs collaborative orchestration on the matching AI sources according to the collaborative orchestration logic in the Chatbot preset strategy;

[0014] The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the AI ​​source after collaborative arrangement for intelligent processing to obtain the AI ​​processing result;

[0015] Among them, the results of collaborative orchestration include at least: serial, parallel and backup modes.

[0016] Furthermore, in the above-mentioned message interaction method, the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, and also includes:

[0017] If the type of the matched AI source is a controllable AI source, set the associated AI source training corpus information;

[0018] The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the controllable AI source for intelligent processing to obtain a first AI processing result, and the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the associated AI source for intelligent processing to obtain a second AI processing result;

[0019] The AI ​​control engine performs content intervention processing on the first AI processing result and the second processing result according to the content intervention logic in the Chatbot preset strategy to obtain the AI ​​processing result.

[0020] Furthermore, in the above-mentioned message interaction method, after the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, it also includes:

[0021] The AI ​​control engine sends the user's conversation message and the same type of AI processing result corresponding to the AI ​​processing result to the controllable AI source according to the secondary AI training logic in the Chatbot preset strategy;

[0022] The controllable AI source performs secondary AI training to obtain AI processing results.

[0023] Furthermore, in the above-mentioned message interaction method, the matching AI source is connected to the control engine in a plug-in manner, and the control engine connects to the matching AI source through the gateway to realize the control and scheduling of the matching AI source;

[0024] Among them, the types of AI sources include: locally controllable AI sources built into the 5G message ecological service platform, locally uncontrollable AI sources built into the 5G message ecological service platform, remote calls to external controllable AI sources, and remote calls to external uncontrollable AI sources.

[0025] Furthermore, in the above-mentioned message interaction method, the content intervention processing includes:

[0026] The first AI processing result and the second processing result are scanned, and information content shielding, information content replacement, format conversion and information tailing processing are performed through keyword matching, security policy management and identification, combined with the message ecology or the currently called Chatbot application requirements.

[0027] In a second aspect of the present invention, a message interaction device is further proposed, which is applied to a system including: a 5G message standard communication service, a 5G message ecological service platform and a Chatbot, including:

[0028] The receiving module and the first sending module are used for receiving the user's session message through the 5G message standard communication service, and sending the session message to the message access service of the 5G message ecological service platform;

[0029] Matching module: a message access service for the 5G message ecological service platform matches an AI source for the user's conversation message according to a preset route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform;

[0030] Intelligent processing module: The AI ​​control engine used in the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result;

[0031] The second sending module is used to send the AI ​​processing result to the user;

[0032] Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

[0033] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory;

[0034] The processor is used to execute any one of the message interaction methods described above by calling the program or instruction stored in the memory.

[0035] In a fourth aspect of the present invention, a computer-readable storage medium is further proposed, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute any one of the message interaction methods described above.

[0036] The beneficial effects of the present invention are as follows: the present invention receives the user's conversation message through the 5G message standard communication service, and sends the conversation message to the message access service of the 5G message ecological service platform; the message access service of the 5G message ecological service platform matches the user's conversation message with an AI source according to a pre-set route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform; the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain an AI processing result; and sends the AI ​​processing result to the user. The present invention realizes the control and scheduling of multiple AI sources by building an AI control engine into the 5G message ecological service platform, introduces the best and most suitable AI service capabilities into the 5G message ecological service platform, and improves the AI ​​service capabilities of message interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0038] Figure 1 A message interaction method provided by an embodiment of the present invention Figure 1 ;

[0039] Figure 2 A method for obtaining AI processing results provided by an embodiment of the present invention Figure 1 ;

[0040] Figure 3 A method for obtaining AI processing results provided by an embodiment of the present invention Figure 2 ;

[0041] Figure 4 A method for obtaining AI processing results provided by an embodiment of the present invention Figure 3 ;

[0042] Figure 5 A diagram of a message interaction device provided by an embodiment of the present invention;

[0043] Figure 6 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0045] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0046] In the description of the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be internal communication between two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0048] The present invention proposes a message interaction method, device, electronic device and storage medium. By building an AI control engine into a 5G message ecological service platform, control and scheduling of multiple AI sources are achieved, the optimal and most suitable AI service capabilities are introduced into the 5G message ecological service platform, and the AI ​​service capabilities of message interaction are improved.

[0049] Method Embodiment

[0050] Figure 1 A message interaction method provided by an embodiment of the present invention Figure 1 .

[0051] In the first aspect of the present invention, a message interaction method is proposed, which is applied to a system including: a 5G message standard communication service, a 5G message ecological service platform and a Chatbot, combined with Figure 1 ,include:

[0052] S1: The 5G message standard communication service receives the user's conversation message and sends the user's conversation message to the message access service of the 5G message ecological service platform.

[0053] Specifically, in an embodiment of the present invention, a user's conversation message may be a problem in any field of user resources, such as medicine, chemistry, etc. The user's conversation message is sent to the 5G message standard communication service, and the 5G message standard communication service receives the user's conversation message and sends the user's conversation message to the message access service of the 5G message ecological service platform.

[0054] S2: The message access service of the 5G message ecological service platform matches the AI ​​source for the user's conversation message according to the pre-set route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform.

[0055] Specifically, in an embodiment of the present invention, the pre-set route is the Chatbot subscription information. The message access service of the 5G message ecological service platform receives the user's conversation message, and matches the AI ​​source for the user's conversation message according to the Chatbot subscription information. The matched AI source here is the AI ​​source closest to the user's conversation message field, and it can also be multiple AI sources.

[0056] S3: The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result.

[0057] Specifically, in an embodiment of the present application, after matching the AI ​​source closest to the user's conversation message field, the AI ​​control engine of the 5G message ecological service platform controls and schedules the matched AI source to perform intelligent processing on the user's conversation message to obtain an AI processing result. The intelligent processing here can be the execution of GPT deep learning logic.

[0058] S4: Send AI processing results to the user.

[0059] Specifically, in the embodiment of the present application, after obtaining the AI ​​processing result, the AI ​​processing result is sent to the user, so that the user obtains the result that matches the conversation message, thereby improving the AI ​​service capability of message interaction.

[0060] Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

[0061] It should be understood that the present invention realizes the integration of AI control engine in the 5G message ecological service platform, and provides the implementation method of ecological layer AI policy configuration and interactive message AI intelligent processing.

[0062] Furthermore, in the above-mentioned message interaction method, in the system composed of 5G message standard communication service, 5G message ecological service platform and Chatbot, the 5G message ecological service platform is built on the 5G message standard communication service in an overlay network manner, and the 5G message ecological service platform is used for Chatbot access.

[0063] Specifically, in the embodiments of the present invention, on the 5G message standard communication service, a 5G message ecological service platform is built by overlaying the network, which is responsible for the unified access of Chatbots across the entire network. The unified 5G message ecological service platform is used to provide the AI ​​service capabilities required for 5G message conversation interaction for the accessed Chatbots, thereby comprehensively lowering the threshold for Chatbots to realize AI intelligent interactive services themselves. In the 5G message ecological service platform, the built-in AI control engine is used to control and schedule various AI sources, introduce the best and most suitable AI service capabilities into the 5G message ecological service platform, and keep up with the development of AI technology.

[0064] Figure 2 A method for obtaining AI processing results provided by an embodiment of the present invention Figure 1 .

[0065] Furthermore, in the above-mentioned message interaction method, the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, combined with Figure 2 , and also includes two steps S21 to S22:

[0066] S21: The AI ​​control engine of the 5G message ecological service platform collaboratively orchestrates the matching AI sources according to the collaborative orchestration logic in the Chatbot preset strategy.

[0067] Specifically, in an embodiment of the present invention, the collaborative orchestration of matched AI sources is to combine and orchestrate AI sources of different capabilities according to the user's conversation messages to realize an AI service chain for message interaction scenarios. Here, an independent processing logic unit can be set to combine and orchestrate AI sources of different capabilities to meet various intelligent conversation requirements.

[0068] S22: The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the collaboratively orchestrated AI source for intelligent processing to obtain the AI ​​processing result.

[0069] Specifically, in an embodiment of the present invention, for example: the AI ​​control engine of the 5G message ecological service platform sends the user's conversation messages to the first AI source and the second AI source respectively; the first AI source performs voice recognition on the conversation message and user image recognition corresponding to the user conversation message, and then performs a GPT deep learning conversation to obtain the result of the first AI source; the second AI source performs voice recognition on the conversation message and then performs semantic analysis and intelligent search to obtain the result of the second AI source; the result of the first AI source and the result of the second AI source are backed up to obtain the AI ​​processing result, and after obtaining the AI ​​processing result, the AI ​​processing result is sent to the user, so that the user obtains a result that matches the conversation message.

[0070] Among them, the results of collaborative orchestration include at least: serial, parallel and backup modes.

[0071] It should be understood that by collaboratively orchestrating AI sources, the AI ​​service capabilities of message interaction are further enhanced.

[0072] Figure 3 A method for obtaining AI processing results provided by an embodiment of the present invention Figure 2 .

[0073] Furthermore, in the above-mentioned message interaction method, the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, combined with Figure 3 , and also includes three steps S31 to S33:

[0074] S31: If the type of the matched AI source is a controllable AI source, set the associated AI source training corpus information.

[0075] Specifically, in an embodiment of the present invention, the types of matched AI sources include: a locally controllable AI source built into the 5G message ecological service platform, a locally uncontrollable AI source built into the 5G message ecological service platform, a remote call to an external controllable AI source, and a remote call to an external uncontrollable AI source; if the type of the matched AI source is a locally controllable AI source built into the 5G message ecological service platform or a remote call to an external controllable AI source, the associated AI source training corpus information is set.

[0076] S32: The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the controllable AI source for intelligent processing to obtain the first AI processing result, and the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the associated AI source for intelligent processing to obtain the second AI processing result.

[0077] Specifically, in an embodiment of the present invention, the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to a locally controllable AI source built into the 5G message ecological service platform or remotely calls an external controllable AI source for intelligent processing to obtain a first AI processing result, and the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to an associated AI source for intelligent processing to obtain a second AI processing result.

[0078] S33: The AI ​​control engine performs content intervention processing on the first AI processing result and the second processing result according to the content intervention logic in the Chatbot preset strategy to obtain an AI processing result.

[0079] Specifically, in an embodiment of the present invention, content intervention processing is performed on the first AI processing result and the second processing result to obtain an AI processing result. The method of content intervention processing is described in detail below. After obtaining the AI ​​processing result, the AI ​​processing result is sent to the user, so that the user obtains a result that matches the conversation message.

[0080] It should be understood that by performing content intervention processing on different AI processing results obtained from different AI sources, the AI ​​service capabilities of message interaction are further enhanced.

[0081] Figure 4 A method for obtaining AI processing results provided by an embodiment of the present invention Figure 3 .

[0082] Furthermore, in the above-mentioned message interaction method, the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, and then combines Figure 4 , and also includes two steps S41 to S42:

[0083] S41: The AI ​​control engine sends the user's conversation message and the same type of AI processing results corresponding to the AI ​​processing results to the controllable AI source according to the secondary AI training logic in the Chatbot preset strategy;.

[0084] Specifically, in an embodiment of the present application, after obtaining the AI ​​processing result, the user's conversation message and the interactive information flow of the same type of AI processing result corresponding to the AI ​​processing result are sent to the controllable AI source in a mirrored form.

[0085] S42: The controllable AI source performs secondary AI training to obtain an AI processing result.

[0086] Specifically, in an embodiment of the present application, secondary AI training is performed to implement application-controllable AI source training data to improve the data, and AI processing results are obtained by widely absorbing information flows of mature AI capabilities within the same scheduling range. After obtaining the AI ​​processing results, the AI ​​processing results are sent to users, so that users obtain results that match the conversation messages.

[0087] It should be understood that by performing secondary AI training on the user's conversation messages and the same type of AI processing results corresponding to the AI ​​processing results to obtain the AI ​​processing results, the AI ​​service capabilities of message interaction are further improved.

[0088] Furthermore, in the above-mentioned message interaction method, the matching AI source is connected to the control engine in a plug-in manner, and the control engine connects to the matching AI source through the gateway to realize the control and scheduling of the matching AI source;

[0089] Among them, the types of AI sources include: locally controllable AI sources built into the 5G message ecological service platform, locally uncontrollable AI sources built into the 5G message ecological service platform, remote calls to external controllable AI sources, and remote calls to external uncontrollable AI sources.

[0090] Specifically, in the embodiments of the present invention, for example: the AI ​​control module is connected to the first AI source through the first AI source gateway; the AI ​​control module is connected to the second AI source through the second AI source gateway; the AI ​​control module is connected to the third AI source through the third AI source gateway, and the matching AI sources are connected to the control engine in a plug-in manner, and the corresponding associated AI source gateways can be deployed at any time to be responsible for the connection.

[0091] Furthermore, in the above-mentioned message interaction method, the content intervention processing includes:

[0092] The first AI processing result and the second processing result are scanned, and information content shielding, information content replacement, format conversion and information tailing processing are performed through keyword matching, security policy management and identification, combined with the message ecology or the currently called Chatbot application requirements.

[0093] Specifically, in the embodiment of the present invention, the above-mentioned content intervention processing method is used to achieve information feedback from different AI sources that is closer to user conversation messages.

[0094] Device Embodiment

[0095] Figure 5 A diagram of a message interaction device provided in an embodiment of the present invention.

[0096] In a second aspect of the present invention, a message interaction device is also proposed, which is applied to a system including: a 5G message standard communication service, a 5G message ecological service platform and a Chatbot, combined with Figure 5 ,include:

[0097] The receiving module 51 and the first sending module 52 are used for the 5G message standard communication service to receive the user's session message and send the session message to the message access service of the 5G message ecological service platform.

[0098] Specifically, in an embodiment of the present invention, the user's conversation message received by the receiving module 51 may be a problem in any field of user resources, such as: medical field, chemical field, etc.; the first sending module 52 sends the user's conversation message to the 5G message standard communication service, and the 5G message standard communication service receives the user's conversation message and sends the user's conversation message to the message access service of the 5G message ecological service platform.

[0099] Matching module 53: The message access service for the 5G message ecological service platform matches the AI ​​source for the user's conversation message according to the pre-set route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform.

[0100] Specifically, in an embodiment of the present invention, the pre-set route is the Chatbot subscription information. The message access service of the 5G message ecological service platform receives the user's conversation message. The matching module 53 matches the AI ​​source for the user's conversation message according to the Chatbot subscription information. The matched AI source here is the AI ​​source closest to the user's conversation message field, and it can also be multiple AI sources.

[0101] Intelligent processing module 54: The AI ​​control engine used in the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result.

[0102] Specifically, in the embodiment of the present application, after matching the AI ​​source closest to the user's conversation message field, the AI ​​control engine of the 5G message ecological service platform controls and schedules the matched AI source to perform intelligent processing on the user's conversation message through the intelligent processing module 54 to obtain the AI ​​processing result. The intelligent processing here can be the execution of GPT deep learning logic.

[0103] The second sending module 55 is used to send the AI ​​processing result to the user.

[0104] Specifically, in the embodiment of the present application, after obtaining the AI ​​processing result, the second sending module 55 sends the AI ​​processing result to the user, so that the user obtains a result that matches the conversation message, thereby improving the AI ​​service capability of message interaction.

[0105] Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

[0106] It should be understood that the present invention realizes the integration of AI control engine in the 5G message ecological service platform, and provides the implementation method of ecological layer AI policy configuration and interactive message AI intelligent processing.

[0107] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory;

[0108] The processor is used to execute any one of the message interaction methods described above by calling the program or instruction stored in the memory.

[0109] In a fourth aspect of the present invention, a computer-readable storage medium is further proposed, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute any one of the message interaction methods described above.

[0110] Figure 6 It is a schematic block diagram of an electronic device provided by an embodiment of the present invention.

[0111] like Figure 6 As shown, the electronic device includes: at least one processor 601, at least one memory 602 and at least one communication interface 603. The various components in the electronic device are coupled together through a bus system 604. The communication interface 603 is used to transmit information between external devices. It can be understood that the bus system 604 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 604 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 6 Various buses are labeled as bus system 604 .

[0112] It can be understood that the memory 602 in this embodiment can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0113] In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system and application programs.

[0114] The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. A program that implements any method in a message interaction method provided in an embodiment of the present invention can be included in the application.

[0115] In an embodiment of the present invention, the processor 601 calls a program or instruction stored in the memory 602, specifically, a program or instruction stored in an application, and the processor 601 is used to execute the steps of each embodiment of a message interaction method provided in an embodiment of the present invention.

[0116] The 5G message standard communication service receives the user's session message and sends the session message to the message access service of the 5G message ecological service platform;

[0117] The message access service of the 5G message ecological service platform matches the AI ​​source for the user's conversation message according to the preset route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform;

[0118] The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result;

[0119] Sending the AI ​​processing result to the user;

[0120] Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

[0121] Any method in a message interaction method provided in an embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 601 or an instruction in the form of software. The above-mentioned processor 601 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0122] The steps of any method in a message interaction method provided in an embodiment of the present invention can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software units in the decoding processor. The software unit can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the method in combination with its hardware.

[0123] Those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0124] Those skilled in the art will appreciate that the description of each embodiment has its own emphasis, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0125] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0126] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A message interaction method, characterized in that: Applied to the system consisting of 5G message standard communication service, 5G message ecological service platform and Chatbot, including: The 5G message standard communication service receives the user's session message and sends the session message to the message access service of the 5G message ecological service platform; The message access service of the 5G message ecological service platform matches the AI ​​source for the user's conversation message according to the preset route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform; The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result; Sending the AI ​​processing result to the user; Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

2. A message interaction method according to claim 1, characterized in that: In the system consisting of the 5G message standard communication service, the 5G message ecological service platform and the Chatbot, the 5G message ecological service platform is built on the 5G message standard communication service in an overlay network manner, and the 5G message ecological service platform is used for the access of the Chatbot.

3. A message interaction method according to claim 1, characterized in that: The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, and also includes: The AI ​​control engine of the 5G message ecological service platform collaboratively arranges the matching AI sources according to the collaborative arrangement logic in the Chatbot preset strategy; The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the AI ​​source after collaborative arrangement for intelligent processing to obtain the AI ​​processing result; Among them, the results of collaborative orchestration include at least: serial, parallel and backup modes.

4. A message interaction method according to claim 1, characterized in that: The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, and also includes: If the type of the matched AI source is a controllable AI source, set the associated AI source training corpus information; The AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the controllable AI source for intelligent processing to obtain a first AI processing result, and the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the associated AI source for intelligent processing to obtain a second AI processing result; The AI ​​control engine performs content intervention processing on the first AI processing result and the second processing result according to the content intervention logic in the Chatbot preset strategy to obtain the AI ​​processing result.

5. A message interaction method according to claim 1, characterized in that: After the AI ​​control engine of the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result, it also includes: The AI ​​control engine sends the user's conversation message and the same type of AI processing result corresponding to the AI ​​processing result to the controllable AI source according to the secondary AI training logic in the Chatbot preset strategy; The controllable AI source performs secondary AI training to obtain AI processing results.

6. A message interaction method according to claim 1, characterized in that: The matching AI source is connected to the control engine in a plug-in manner. The control engine connects to the matching AI source through the gateway to realize the control and scheduling of the matching AI source; Among them, the types of AI sources include: locally controllable AI sources built into the 5G message ecological service platform, locally uncontrollable AI sources built into the 5G message ecological service platform, remote calls to external controllable AI sources, and remote calls to external uncontrollable AI sources.

7. A message interaction method according to claim 4, characterized in that: The content intervention processing includes: The first AI processing result and the second processing result are scanned, and information content shielding, information content replacement, format conversion and information tailing processing are performed through keyword matching, security policy management and identification, combined with the message ecology or the currently called Chatbot application requirements.

8. A message interaction device, characterized in that: Applied to the system consisting of 5G message standard communication service, 5G message ecological service platform and Chatbot, including: The receiving module and the first sending module are used for receiving the user's session message through the 5G message standard communication service, and sending the session message to the message access service of the 5G message ecological service platform; Matching module: a message access service for the 5G message ecological service platform matches the AI ​​source for the user's conversation message according to a preset route, and sends the user's conversation message to the AI ​​control engine of the 5G message ecological service platform; Intelligent processing module: The AI ​​control engine used in the 5G message ecological service platform sends the user's conversation message to the matching AI source for intelligent processing to obtain the AI ​​processing result; The second sending module is used to send the AI ​​processing result to the user; Among them, the pre-set routes include: AI sources suitable for conversation messages in different fields.

9. An electronic device, characterized in that: include: Processor and memory; The processor is used to execute a message interaction method as described in any one of claims 1 to 7 by calling the program or instruction stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute a message interaction method as described in any one of claims 1 to 7.

Images