Communication method and device based on artificial intelligence

Abstract

The invention discloses a communication method and device based on artificial intelligence, and the method comprises the steps: carrying out the authentication of intelligent equipment through a business platform according to dialing information when a communication platform receives the dialing information sent by the intelligent equipment; if the authentication is passed, establishing a communication long connection between the intelligent device and a target terminal to which the dialing information belongs; when the target terminal does not answer the call, switching to an AI service platform, and recording the call content; and when a hang-up signal sent by the intelligent equipment is received, cutting off the communication long connection, extracting a call summary of the call content through the service platform, and returning the call summary to the intelligent equipment. Therefore, a user can obtain feedback in real time in the communication process in a mode of accessing the AI call by dialing the intelligent equipment, so that the call content is prevented from being missed, and the communication flexibility is improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a communication method and device based on artificial intelligence. Background Art

[0002] With the rapid development of artificial intelligence, changes in people's lifestyles are gradually increasing, driving people's lives towards intelligence.

[0003] Traditional communication methods have gradually exposed many shortcomings in the face of increasingly complex information interaction needs. Single communication devices often have limited functions, are unable to meet users' diverse usage scenario needs, and have low communication flexibility. Summary of the invention

[0004] The present invention provides a communication method and device based on artificial intelligence, which solves the technical problems in the prior art that a single communication device often has limited functions, is difficult to meet the diverse usage scenario requirements of users, and has low communication flexibility.

[0005] The present invention provides an artificial intelligence-based communication method, which is applied to a communication platform, wherein the communication platform is respectively connected to a smart device, a business platform, and an AI service platform for communication, and the method comprises:

[0006] When receiving the dialing information sent by the smart device, authenticating the smart device according to the dialing information through the service platform;

[0007] If the authentication is successful, a long communication connection is established between the smart device and the target terminal to which the dial-up information belongs;

[0008] When the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded;

[0009] When a hang-up signal sent by the smart device is received, the long communication connection is cut off and a call summary of the call content is extracted through the service platform and returned to the smart device.

[0010] Optionally, when receiving the dialing information sent by the smart device, authenticating the smart device according to the dialing information through the service platform includes:

[0011] When receiving the dialing information sent by the smart device, the business platform verifies whether the smart device has established an association relationship with the dialing information; the smart device is used to respond to the external user instruction and generate the dialing information;

[0012] If the verification is successful, the authentication is determined to be successful, the target terminal to which the dialing information belongs is matched from the service platform, and the call policy corresponding to the target terminal is obtained;

[0013] If the verification fails, it is determined that the authentication fails, and a prompt message is returned to the smart device.

[0014] Optionally, when the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded, including:

[0015] When the target terminal does not answer the call, a call transfer method is selected according to the call strategy corresponding to the target terminal;

[0016] If the call transfer mode is an audio call, the call is transferred to the corresponding AI audio call service according to the user account to which the smart device belongs;

[0017] If the call transfer mode is a video call, the call is transferred to the corresponding AI video call service according to the user account to which the smart device belongs;

[0018] The language processing model is called through the AI ​​audio call service or the AI ​​video call service to respond to the call information input from the smart device, return AI audio, and record the call content.

[0019] Optionally, when receiving a hang-up signal sent by the smart device, cutting off the long communication connection and extracting a call summary of the call content through the service platform and returning it to the smart device includes:

[0020] When receiving a hang-up signal sent by the smart device, cutting off the long communication connection;

[0021] The call content is converted into text information through the AI ​​service platform and synchronized to the business platform;

[0022] The service platform calls a text extraction model to summarize the text information and generate a call summary corresponding to the call content;

[0023] The call summary is returned to the smart device through the service platform.

[0024] Optionally, it also includes:

[0025] The call summary is returned to the mobile device associated with the smart device through the service platform.

[0026] Optionally, the method further comprises:

[0027] When the target terminal answers the call, a voice call channel is established between the smart device and the target terminal.

[0028] Optionally, the method further comprises:

[0029] Responding to the input user account via the mobile device, associating the smart device and the target communication number to the user account;

[0030] The mobile device responds to the user configuration information, performs AI communication configuration on the mobile device and the smart device, and synchronizes to the AI ​​service platform through the business platform.

[0031] Optionally, the step of responding to the user account inputted through the mobile device and associating the smart device and the target communication number with the user account comprises:

[0032] Associating the mobile device with the user account in response to the input user account via a device application of the mobile device;

[0033] Scanning the terminal identification of the smart device by the device application to associate the smart device with the user account;

[0034] Sending the device information of the smart device, the user account and the target communication number to the business platform through the device application;

[0035] The device information, the user account and the target communication number are associated through the service platform, and a number device binding notification is returned to the communication platform.

[0036] Optionally, the step of performing AI communication configuration on the mobile device and the smart device by responding to user configuration information through the mobile device, and synchronizing to the AI ​​service platform through the business platform includes:

[0037] Responding to user configuration information through the mobile device, performing AI communication configuration on the smart device and the target terminal, and generating configuration synchronization information to send to the business platform;

[0038] The configuration synchronization information is sent to the AI ​​service platform through the business platform to synchronize the AI ​​communication configuration.

[0039] The present invention also provides an artificial intelligence-based communication device, which is applied to a communication platform, wherein the communication platform is respectively connected to a smart device, a business platform, and an AI service platform for communication, and the device comprises:

[0040] An authentication calling module, used for authenticating the smart device according to the dialing information through the service platform when receiving the dialing information sent by the smart device;

[0041] A long connection establishment module, used for establishing a long communication connection between the smart device and the target terminal to which the dial-up information belongs if the authentication is passed;

[0042] An AI switching module is used to switch the call to the AI ​​service platform and record the call content when the target terminal does not answer the call;

[0043] The call summary returning module is used to cut off the long communication connection and extract the call summary of the call content through the business platform and return it to the smart device when receiving the hang-up signal sent by the smart device.

[0044] It can be seen from the above technical solutions that the present invention has the following advantages:

[0045] When the communication platform receives the dialing information sent by the smart device, the business platform authenticates the smart device according to the dialing information; if the authentication is successful, a long communication connection is established between the smart device and the target terminal to which the dialing information belongs; when the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded; when the hang-up signal sent by the smart device is received, the long communication connection is cut off and the call summary of the call content is extracted through the business platform and returned to the smart device. In this way, by dialing the smart device to access the AI ​​answering call, users can get real-time feedback during the communication process, avoid missing the call content, and improve communication flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 A system architecture diagram for executing an artificial intelligence-based communication method in an embodiment of the present invention;

[0048] Figure 2 A flowchart of a communication method based on artificial intelligence provided by an embodiment of the present invention;

[0049] Figure 3 A data flow diagram of artificial intelligence-based communication in an embodiment of the present invention;

[0050] Figure 4 It is a timing diagram of the overall communication process in an embodiment of the present invention;

[0051] Figure 5 A detailed timing diagram of the AI ​​call process in an embodiment of the present invention;

[0052] Figure 6 4 is a structural block diagram of an artificial intelligence-based communication device in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The embodiment of the present invention provides a communication method and device based on artificial intelligence, which is used to solve the technical problem that a single communication device often has limited functions, is difficult to meet the diverse usage scenario requirements of users, and has low communication flexibility. The user dials by waking up the smart device through a call, and after dialing, the call is made through wireless communication of the call number. The relevant AI call is made through the policy configured by the user. For example, when no one answers the speaker user, it is switched to AI to answer the call. The caller can communicate with the AI ​​to inform the AI ​​system of the relevant content. After the call is over, the AI ​​system will remind the user of the relevant information of the call in various forms, so as to achieve the effect of not missing the user's message. The diversity of wireless calls of call numbers is increased, the user experience is enriched, and the functions of smart devices are enriched. It provides a direction for wireless communication and increases the usage scenarios of AI. The smart device is equipped with the ability of dialing wireless communication, the call number communication is intelligent, AI is integrated into the dialing real-time communication, the call application scenarios are enriched, and a large-span intelligent dialing call scenario is realized. Let the AI ​​agent help the owner to make autonomous calls, achieve the functional characteristics of talking first and then reminding, and make AI a successful telephone butler. It greatly reduces missed calls and reduces the number of times calls are made but no one answers, resulting in messages not being able to reach individuals.

[0054] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 , Figure 1 A system architecture diagram for executing an artificial intelligence-based communication method in an embodiment of the present invention.

[0056] In this embodiment, the system includes a communication platform, smart devices, a business platform and an AI service platform. The communication platform is used as the center to communicate with the smart devices, the business platform and the AI ​​service platform respectively, and the business platform communicates with the smart devices and the AI ​​service platform respectively, so that the business platform can call the model in the AI ​​service platform for data processing, and interact with the smart devices without the need for the communication platform to establish a long communication connection, so as to realize the feedback notification of call information.

[0057] Among them, the business platform includes multiple groups of unit architectures for configuration and data processing, such as AI configuration units, device management units, communication configuration units, call record units and business management units. Smart devices include device apps, device voice control units and device communication units to receive user input audio or user commands for communication. The communication platform is used to integrate the communication authentication of the business platform, establish a large communication network, and call the AI ​​service platform for AI communication. The AI ​​service platform includes AI call units and AI large model units. AI communication can use the Haobai communication function. AI large models refer to "large parameter" models trained using large-scale data and powerful computing power. They can be implemented based on deep learning and neural networks, and can be configured and switched according to the business system.

[0058] See also Figure 2 , Figure 2 A flowchart of a communication method based on artificial intelligence provided by an embodiment of the present invention.

[0059] The present invention provides an artificial intelligence-based communication method, which is applied to a communication platform, wherein the communication platform is connected to a smart device for communication, and the method includes:

[0060] Step 201, when receiving dialing information sent by the smart device, the smart device is authenticated according to the dialing information through the service platform;

[0061] AI (Artificial Intelligence): Artificial intelligence is an important part of the intelligent discipline. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is a very broad science, including robotics, speech recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc.

[0062] Smart devices: refers to any device or machine with computing and processing capabilities. The smart devices here mainly include smart speakers, smart access control and other terminal devices with screens.

[0063] In the embodiment of the present invention, the smart device initiates a video call or an audio call through the user's trigger on the visual screen, and the smart device generates corresponding dialing information according to the trigger and sends it to the communication platform. When the communication platform receives the dialing information, it requests the service platform to authenticate the smart device according to the dialing information to verify the call authority of the smart device and the dialing information and related configuration information.

[0064] The dialing information may include but is not limited to device information and call number, etc. The call number (Callnumber) is a landline number or a mobile phone number, which here refers to a number that supports wireless communication.

[0065] In an example of the present invention, the communication platform is also connected to the business platform for communication; step 201 may include the following sub-steps:

[0066] When receiving the dialing information sent by the smart device, the business platform verifies whether the smart device has established an association relationship with the dialing information; the smart device is used to respond to external user instructions and generate dialing information;

[0067] If the verification is successful, the authentication is determined to be successful, the target terminal to which the dialing information belongs is matched from the service platform, and the call policy corresponding to the target terminal is obtained;

[0068] If the verification fails, the authentication is determined to have failed, and a prompt message is returned to the smart device.

[0069] In this embodiment, the user can perform relevant business configuration operations such as AI transfer configuration, communication configuration, and device management configuration in the mobile phone app and smart device app. The user's AI configuration information is synchronized to the AI ​​service, including AI-related configuration information such as AI timbre, AI image, and AI opening remarks. After the user completes the relevant configuration, the user can wake up the smart device with voice, and use voice input to recognize command dialing or manual dialing calls and other user commands. The smart device generates dialing information and sends it to the communication platform.

[0070] When the communication platform receives the dialing information, it first verifies whether the smart device has the communication function of the call number in the dialing information through the business platform. If the verification is passed, the target terminal to which the dialing information belongs is matched from the associated business platform to determine the association between the smart device and the target terminal, and returns the corresponding call strategy to the communication platform. If the verification fails, the communication platform returns a prompt message of failure to the smart device to inform the user that the current smart device does not have the communication authority for the communication number.

[0071] In addition, the business platform can also perform authentication verification on number activation information, binding status between smart devices and target terminals such as landlines, and anti-fraud.

[0072] It should be noted that the call strategy refers to the AI ​​call strategy, which is used to limit the communication method of AI transferred calls, such as audio calls, video calls, etc.

[0073] In the specific implementation, user commands can be divided into voice commands and manual commands. The voice assistant of the smart device is awakened by natural language sound, and the smart device is controlled by language to execute the corresponding command operation, or the corresponding command operation is manually performed by the user to realize the generation of dialing information. After the smart device generates the dialing information, the smart device dials up and communicates, docks with the module service SDK, and reports the dialing communication command and signaling to the communication platform. The communication platform receives the call command and signaling, and requests the business platform to verify whether the device and number have communication functions and other related authority verifications. The business platform performs relevant authentication verifications on number activation information, binding status of the device and landline, AI call strategy, anti-fraud, etc. The business platform returns the authentication results, call permissions, AI call strategy, etc. to the communication platform.

[0074] In another example of the present invention, before executing step 201, the method further includes the following steps S11-S12:

[0075] S11, responding to the input user account through the mobile device, associating the smart device and the target communication number to the user account;

[0076] In this embodiment, the user configures related calls and AI for the service through the App and device, and the App installed on the mobile device responds to the user account input by the user, and associates the target communication number of the smart device and the target terminal to be communicated with the user account, so that subsequent users can directly communicate with the target terminal corresponding to the target communication number through the smart device, and at the same time associate the user account to ensure the security of communication.

[0077] Furthermore, S11 may include the following sub-steps:

[0078] Associating the mobile device with the user account in response to the input user account via a device application of the mobile device;

[0079] Scan the terminal ID of the smart device through the device application and associate the smart device with the user account;

[0080] Send the device information, user account and target communication number of the smart device to the business platform through the device application;

[0081] The business platform associates device information, user account and target communication number, and returns the number device binding notification to the communication platform.

[0082] In the embodiment of the present invention, the user binds the mobile device to the user account in response to the input user account through the device application of the mobile device, that is, App, to complete the authorization of the mobile device by the user account. Since the target terminal is associated with the communication number, the user scans the terminal identification of the smart device, such as a QR code, through the device application, and the smart device returns the corresponding association page to the device application, responds to the user's input information on the association page, and binds the smart device to the user account.

[0083] After completing the association of the smart device, the user obtains the corresponding device information from the smart device, such as the communication method supported by the device, the communication range and the incoming call number, and sends the device information, user account and target communication number to the service platform through the device application. Among them, the target communication number refers to the communication number of the target terminal.

[0084] The business platform can associate the device information, user account and target communication number by creating a table or storing key-value pairs, and return a number device binding notification to the communication platform to inform the communication platform of the target communication number associated with the smart device under the user account.

[0085] S12. Respond to user configuration information through mobile devices, configure AI communication between mobile devices and smart devices, and synchronize to the AI ​​service platform through the business platform.

[0086] In the embodiment of the present invention, after the association between the smart device and the target terminal is completed, it is necessary to further perform AI communication configuration on the target terminal to realize AI communication between the target terminal and the smart device.

[0087] Further, S12 may include the following sub-steps:

[0088] Respond to user configuration information through mobile devices, perform AI communication configuration on smart devices and target terminals, and generate configuration synchronization information to send to the business platform;

[0089] Send configuration synchronization information to the AI ​​service platform through the business platform to synchronize AI communication configuration.

[0090] In this embodiment, the user performs relevant service configuration on the device application of the mobile device or the smart device, inputs the user configuration information to the mobile device or the smart device, and then performs the same AI communication configuration on the smart device and the target terminal. At the same time, the configuration synchronization information is generated according to the AI ​​communication configuration to the business platform, and the business platform synchronizes the AI ​​communication configuration by sending the configuration synchronization information to the AI ​​service platform.

[0091] Among them, AI communication configuration includes AI configuration and communication configuration. AI configuration includes tone, character image, AI opening remarks of call, etc. Communication configuration includes call mode, call duration and other configurations required for communication.

[0092] Step 202, if the authentication is successful, a long communication connection is established between the smart device and the target terminal to which the dial-up information belongs;

[0093] In this embodiment, after the call authentication is passed, the communication platform establishes a long call connection. Relevant calls can be made according to the AI ​​call strategy:

[0094] If it is a normal call, the communication platform will conduct normal communication network dial-up calls, dial-up communications, and network communications. The call ends when it ends. If it is an AI call, the AI ​​call is conducted according to the call strategy. The AI ​​call strategy is configured according to the business control module, including unconditional transfer, no answer transfer, etc.

[0095] Step 203: When the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded;

[0096] In this embodiment, when the called user of the target terminal does not answer the call or clicks to transfer, it indicates that the called user may not be convenient to answer the call. To avoid missing the call, the target terminal transfers to the AI ​​service platform for an AI call and records the call information during the AI ​​call.

[0097] The call content may include but is not limited to text records, call audio and call video.

[0098] In an example of the present invention, step 203 may include the following sub-steps:

[0099] If the target terminal does not answer the call, the call transfer method is selected according to the call strategy corresponding to the target terminal;

[0100] If the call transfer method is an audio call, it will be transferred to the corresponding AI audio call service according to the user account of the smart device;

[0101] If the call is transferred in the form of a video call, the call will be transferred to the corresponding AI video call service according to the user account of the smart device;

[0102] The language processing model is called through the AI ​​audio call service or AI video call service to respond to the call information input from the smart device, return AI audio, and record the call content.

[0103] In an embodiment of the present invention, after the called user of the target terminal does not answer the call or clicks to transfer, the call transfer mode is selected according to the call strategy corresponding to the target terminal, and the call transfer mode includes audio call and video call. If the call transfer mode is an audio call, the AI ​​call configuration recorded by the user account of the smart device in the target terminal, such as the timbre, AI call opening remarks and other effects, is determined, and the call is transferred to the corresponding AI audio call service.

[0104] Similarly, if the call is transferred as a video call, it will be transferred to the corresponding AI video call service according to the user account of the smart device and its AI call configuration, such as the video character image, AI call opening remarks and other effects.

[0105] The language processing model is called through the AI ​​audio call service or AI video call service to perform language recognition on the call information input by the smart device, perform natural language processing and other operations, return the corresponding AI audio, and record the call content of both parties. Specifically, the language recognition function of the speech processing model can be trained through a training set covering different accents, speaking speeds, environmental background noise, etc. After receiving the call information, feature extraction is performed on it to map the voice to the corresponding text, and then the text is analyzed, understood and processed such as semantic understanding, sentiment analysis or information extraction, etc., and semantic understanding is performed by segmenting the text and analyzing the sentence structure, and the AI ​​audio is fed back to the smart device according to the understood semantics and sentiment tendency.

[0106] In another example of the present invention, the method further comprises the following steps:

[0107] When the target terminal answers the call, a voice call channel is established between the smart device and the target terminal.

[0108] In this embodiment, if the called user of the target terminal answers the call, the communication platform establishes a voice call channel between the smart device and the target terminal, such as a communication network call, dial-up communication, or network communication. The call ends when the called user or the user of the smart device ends.

[0109] Step 204, when a hang-up signal is received from the smart device, the long communication connection is cut off and a call summary of the call content is extracted through the service platform and returned to the smart device.

[0110] If the communication platform receives a hang-up signal sent by the smart device, it indicates that the call between the smart device and the target terminal is over. The communication platform cuts off the long communication connection and further processes the recorded call content through the AI ​​service platform to simplify the unimportant parts of the call content, extract the call summary and return it to the smart device.

[0111] In one example of the present invention, step 204 may include the following sub-steps:

[0112] When receiving the hang-up signal sent by the smart device, the long communication connection is cut off;

[0113] The call content is converted into text information through the AI ​​service platform and synchronized to the business platform;

[0114] The business platform calls the text extraction model to summarize the text information and generate a call summary corresponding to the call content;

[0115] The call summary is returned to the smart device through the business platform.

[0116] In this embodiment, when the communication platform receives the hang-up signal sent by the smart device, it switches the long communication connection between the smart device and the target terminal, calls the AI ​​service platform to generate the text record, call audio and / or call video of this call, converts the text record, call audio and / or call video in the call content into text information, and synchronizes the call content to the business platform. The business platform summarizes the text information by calling the text extraction model, and extracts the call summary corresponding to the call content. After the business platform receives the call summary returned by the text extraction model, it returns the call summary to the smart device, and specifically sends the incoming call message and summary message, and reminds the user through the device terminal, App and other channels.

[0117] It should be noted that the text extraction model can select existing AI data big models, such as Wenxin Yiyan, Xingchen big models, etc., which can be set separately in the AI ​​big data module associated with the business platform or in the AI ​​service platform.

[0118] In addition, the call summary can be returned to the mobile device associated with the smart device through the business platform.

[0119] See also Figure 3 , Figure 3 The figure is a data flow diagram of artificial intelligence-based communication in an embodiment of the present invention.

[0120] The following process is based on the premise that the user has activated the service and has the relevant operation permissions.

[0121] (1) Business configuration process

[0122] Step a: Users can perform related business configuration operations such as AI transfer configuration, communication configuration, and device management configuration on mobile phone apps and smart terminal apps.

[0123] Step b: Synchronize the user's AI configuration information to the AI ​​service, including AI voice, AI image, AI opening remarks and other AI-related configuration information.

[0124] (2) Communication process

[0125] Step 1: The user initiates a communication, such as a video call or a voice call.

[0126] Step 2: The communication system receives the user's communication request, and requests the business system to verify the call authority and related configuration information of the device and number.

[0127] Step 3: Return the call permission verification result and related configuration information. After the authentication is passed, the communication system establishes a long communication connection.

[0128] Step 4: Carry out communication network communication, dial-up communication, and network communication.

[0129] Step 5: Make an AI call based on the communication configuration information, in accordance with the AI ​​call scenario, such as no one answering, do not disturb, etc.

[0130] Step 6: The user triggers the end of the call. The communication network call ends, the AI ​​call ends, and the communication long connection ends.

[0131] Step 7: End the AI ​​call, and the AI ​​service generates the call record and call audio or call video.

[0132] Step 8: The AI ​​service synchronizes the call record, audio, and video of this call to the business platform.

[0133] Step 9: The business platform processes call records and call details according to the business configuration. It can be processed through AI big models such as Wenxin Yiyan and Xingchen Big Model to summarize the call record summary.

[0134] Step 10: Notify the user of the call information. The user can be reminded of the AI ​​call information through device call devices, mobile phone apps, etc.

[0135] See also Figure 4 , Figure 4 It is a timing diagram of the overall communication process in an embodiment of the present invention.

[0136] The user binds the device through the App. The device and the call number are associated. The user scans the device QR code through the mobile App and the device is bound to the account. The App account is bound to the device information. The device information, account and call number information are associated with the business platform. After the binding is successful, a number device binding notification is sent.

[0137] User configuration: users can configure related services, calls, and AI through the App and device terminals. Perform AI and communication configuration on fixed phones and devices. AI configuration includes voice, character image, call AI opening remarks, and other configuration number communication configurations, and simultaneously set up the AI ​​service platform.

[0138] User calls are made through device dialing. Users can wake up the device with voice recognition commands or manually dial calls. Dial-up communication verifies whether the device has the communication function of the number. Number activation information, binding status of the device and landline, anti-fraud and other authentication verifications. After the call authentication is passed, the communication platform establishes a long call connection. Communication network calls, dial-up communication, network communication. Communication services, according to AI call strategies, transfer AI calls, including audio calls and video calls. AI communication services, according to the AI ​​call configuration of the number, tone, video character image, AI call opening remarks and other effects, make related AI calls. User hangs up the call. The communication platform cuts off the AI ​​call and ends the AI ​​call. The AI ​​call service ends the call and generates call audio, call video and call records. The communication platform ends the long call connection. The AI ​​call service generates call records, call audio and call video. Synchronize with the business platform. The business platform processes the call records. The business platform processes the call records through the AI ​​data big model module. The call records are summarized and summarized through the AI ​​data big model module Wenxin Yiyan and Xingchen big models. The processing results are returned to the business platform. The business platform reminds users of incoming call messages and processing summaries through device terminals and apps.

[0139] See also Figure 5 , Figure 5 The following is a detailed timing diagram of the AI ​​call process in an embodiment of the present invention.

[0140] In an embodiment of the present invention, the smart device receives user instructions, which are divided into voice instructions and manual instructions. Device dialing. The smart device dials up and communicates, and the module service SDK is connected. The dial-up communication instructions and signaling are reported to the communication platform. The communication platform receives the call instruction and signaling, and requests the service control module to verify whether the device and number have the communication function and other related authority verification. Number activation information, binding status of the device and the landline, AI call strategy, anti-fraud and other related authentication verifications. The service control module returns the authentication result. After the call authentication such as call authority and AI call strategy passes, the communication platform establishes a long call connection. Relevant calls can be made according to the AI ​​call strategy. Ordinary call, the communication platform makes ordinary communication network dial-up calls, dial-up communication, network communication. The call ends when it ends. AI call, AI call is made according to the call strategy. The AI ​​call strategy is configured according to the service control module. There are unconditional transfer, no answer transfer and other communication platform transfers to the AI ​​service platform. The call service transfers the AI ​​call and establishes a call link. Receive user voice and audio, and transmit the user audio to the AI ​​service platform in real time. The AI ​​communication service makes relevant AI calls according to the AI ​​call configuration of the number, the tone, the image of the video character, the AI ​​call opening remarks and other effects. The user audio is collected and processed through language recognition, natural speech processing, and large model processing. In response to the AI ​​answer, AI audio is generated. After the AI ​​service platform processes the user audio, it returns the AI ​​audio. The user hangs up. The device sends a call hang-up command to the communication service module. The communication platform sends an end call command to the AI ​​service platform to cut off the AI ​​call and end the AI ​​call. The communication platform ends the long call connection. After receiving the end call command, the AI ​​call service generates the text record, call audio or call video of this call. The AI ​​service platform synchronizes the call record, call audio and video to the business platform. The business platform processes the call record, call audio and video. The business platform sends the A call text record to the AI ​​text processing. The AI ​​big data module receives the call record and summarizes the call record through the AI ​​data big model module's Wenxin Yiyan, Xingchen big model and other related AI big data models. The AI ​​big model processing module returns the call record processing results to the business platform. The business platform sends out incoming call information and summary messages, and reminds users through device terminals, apps and other channels.

[0141] In this embodiment, number dialing communication is first adopted. Based on the smart speaker device, the user voice AI controls the dialing. The communication module performs AI proxy connection and transfers to the AI ​​call according to the AI ​​proxy connection policy conditions configured by the user. The AI ​​module AI language recognition and natural language processing take turns to answer the user. After the call is over, the AI ​​module synchronizes the call record with the business module, and after AI text processing, the user is reminded of the relevant information through the device media.

[0142] In an embodiment of the present invention, when the communication platform receives the dialing information sent by the smart device, the smart device is authenticated according to the dialing information through the service platform; if the authentication is successful, a long communication connection is established between the smart device and the target terminal to which the dialing information belongs; when the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded; when the hang-up signal sent by the smart device is received, the long communication connection is cut off and the call summary of the call content is extracted through the service platform and returned to the smart device. Thus, by dialing the smart device to access the AI ​​answering call, the user can get real-time feedback during the communication process, avoid missing the call content, and improve the flexibility of communication.

[0143] like Figure 6 As shown, Figure 6 4 is a structural block diagram of an artificial intelligence-based communication device in an embodiment of the present invention.

[0144] The present invention also provides an artificial intelligence-based communication device, which is applied to a communication platform, wherein the communication platform is respectively connected to a smart device, a business platform, and an AI service platform for communication, and the device comprises:

[0145] The authentication calling module 601 is used to authenticate the smart device according to the dialing information through the service platform when receiving the dialing information sent by the smart device;

[0146] A long connection establishing module 602 is used to establish a communication long connection between the smart device and the target terminal to which the dialing information belongs if the authentication is passed;

[0147] AI switching module 603, used to switch the call to the AI ​​service platform and record the call content when the target terminal does not answer the call;

[0148] The call summary returning module 604 is used to cut off the long communication connection and extract the call summary of the call content through the service platform and return it to the smart device when receiving the hang-up signal sent by the smart device.

[0149] Optionally, the authentication calling module 601 is specifically used for:

[0150] When receiving the dialing information sent by the smart device, the business platform verifies whether the smart device has established an association relationship with the dialing information; the smart device is used to respond to the external user instruction and generate the dialing information;

[0151] If the verification is successful, the authentication is determined to be successful, the target terminal to which the dialing information belongs is matched from the service platform, and the call policy corresponding to the target terminal is obtained;

[0152] If the verification fails, it is determined that the authentication fails, and a prompt message is returned to the smart device.

[0153] Optionally, the AI ​​switching module 602 is specifically used for:

[0154] When the target terminal does not answer the call, a call transfer method is selected according to the call strategy corresponding to the target terminal;

[0155] If the call transfer mode is an audio call, the call is transferred to the corresponding AI audio call service according to the user account to which the smart device belongs;

[0156] If the call transfer mode is a video call, the call is transferred to the corresponding AI video call service according to the user account to which the smart device belongs;

[0157] The language processing model is called through the AI ​​audio call service or the AI ​​video call service to respond to the call information input from the smart device, return AI audio, and record the call content.

[0158] Optionally, the call summary returning module 604 is specifically used for:

[0159] When receiving a hang-up signal sent by the smart device, cutting off the long communication connection;

[0160] The call content is converted into text information through the AI ​​service platform and synchronized to the business platform;

[0161] The service platform calls a text extraction model to summarize the text information and generate a call summary corresponding to the call content;

[0162] The call summary is returned to the smart device through the service platform.

[0163] Optionally, the call summary returning module 604 is further configured to:

[0164] The call summary is returned to the mobile device associated with the smart device through the service platform.

[0165] Optionally, the device further comprises:

[0166] The call channel establishing module is used to establish a voice call channel between the smart device and the target terminal when the target terminal answers the call.

[0167] Optionally, the device further comprises:

[0168] A first configuration module, configured to respond to a user account input via a mobile device and associate the smart device and a target communication number with the user account;

[0169] The second configuration module is used to respond to user configuration information through the mobile device, perform AI communication configuration on the mobile device and the smart device, and synchronize to the AI ​​service platform through the business platform.

[0170] Optionally, the first configuration module is specifically configured to:

[0171] Associating the mobile device with the user account in response to the input user account via a device application of the mobile device;

[0172] Scanning the terminal identification of the smart device by the device application to associate the smart device with the user account;

[0173] Sending the device information of the smart device, the user account and the target communication number to the business platform through the device application;

[0174] The device information, the user account and the target communication number are associated through the service platform, and a number device binding notification is returned to the communication platform.

[0175] Optionally, the second configuration module is specifically used to:

[0176] Responding to user configuration information through the mobile device, performing AI communication configuration on the smart device and the target terminal, and generating configuration synchronization information to send to the business platform;

[0177] The configuration synchronization information is sent to the AI ​​service platform through the business platform to synchronize the AI ​​communication configuration.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0179] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0180] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0182] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A communication method based on artificial intelligence, characterized in that: Applied to a communication platform, the communication platform is respectively connected to a smart device, a business platform and an AI service platform for communication, and the method includes: When receiving the dialing information sent by the smart device, authenticating the smart device according to the dialing information through the service platform; If the authentication is successful, a long communication connection is established between the smart device and the target terminal to which the dial-up information belongs; When the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded; When a hang-up signal sent by the smart device is received, the long communication connection is cut off and a call summary of the call content is extracted through the service platform and returned to the smart device.

2. The method according to claim 1, characterized in that When receiving the dialing information sent by the smart device, authenticating the smart device according to the dialing information through the service platform includes: When receiving the dialing information sent by the smart device, the business platform verifies whether the smart device has established an association relationship with the dialing information; the smart device is used to generate the dialing information in response to the external user instruction; If the verification is successful, the authentication is determined to be successful, the target terminal to which the dialing information belongs is matched from the service platform, and the call policy corresponding to the target terminal is obtained; If the verification fails, it is determined that the authentication fails, and a prompt message is returned to the smart device.

3. The method according to claim 1, characterized in that When the target terminal does not answer the call, the call is transferred to the AI ​​service platform and the call content is recorded, including: When the target terminal does not answer the call, a call transfer method is selected according to the call strategy corresponding to the target terminal; If the call transfer mode is an audio call, the call is transferred to the corresponding AI audio call service according to the user account to which the smart device belongs; If the call transfer mode is a video call, the call is transferred to the corresponding AI video call service according to the user account to which the smart device belongs; The language processing model is called through the AI ​​audio call service or the AI ​​video call service to respond to the call information input from the smart device, return AI audio, and record the call content.

4. The method according to claim 1, characterized in that: When receiving a hang-up signal sent by the smart device, cutting off the long communication connection and extracting a call summary of the call content through the service platform and returning it to the smart device include: When receiving a hang-up signal sent by the smart device, cutting off the long communication connection; The call content is converted into text information through the AI ​​service platform and synchronized to the business platform; The service platform calls a text extraction model to summarize the text information and generate a call summary corresponding to the call content; The call summary is returned to the smart device through the service platform.

5. The method according to claim 4, characterized in that Also includes: The call summary is returned to the mobile device associated with the smart device through the service platform.

6. The method according to claim 1, characterized in that The method further comprises: When the target terminal answers the call, a voice call channel is established between the smart device and the target terminal.

7. The method according to claim 1, characterized in that The method further comprises: Responding to the input user account through the mobile device, associating the smart device and the target communication number to the user account; The mobile device responds to the user configuration information, performs AI communication configuration on the mobile device and the smart device, and synchronizes to the AI ​​service platform through the business platform.

8. The method according to claim 7, characterized in that The step of responding to the input user account through the mobile device and associating the smart device and the target communication number with the user account includes: Associating the mobile device with the user account in response to the input user account via a device application of the mobile device; Scanning the terminal identification of the smart device by the device application to associate the smart device with the user account; Sending the device information of the smart device, the user account and the target communication number to the business platform through the device application; The device information, the user account and the target communication number are associated through the service platform, and a number device binding notification is returned to the communication platform.

9. The method according to claim 7, characterized in that: The step of responding to user configuration information through the mobile device, configuring AI communication between the mobile device and the smart device, and synchronizing the configuration to the AI ​​service platform through the business platform includes: Responding to user configuration information through the mobile device, performing AI communication configuration on the smart device and the target terminal, and generating configuration synchronization information to send to the business platform; The configuration synchronization information is sent to the AI ​​service platform through the business platform to synchronize the AI ​​communication configuration.

10. A communication device based on artificial intelligence, characterized in that: Applied to a communication platform, the communication platform is respectively connected to the intelligent device, the business platform and the AI ​​service platform for communication, and the device comprises: An authentication calling module, used for authenticating the smart device according to the dialing information through the service platform when receiving the dialing information sent by the smart device; A long connection establishment module, used for establishing a long communication connection between the smart device and the target terminal to which the dial-up information belongs if the authentication is passed; An AI switching module is used to switch the call to the AI ​​service platform and record the call content when the target terminal does not answer the call; The call summary returning module is used to cut off the long communication connection and extract the call summary of the call content through the business platform and return it to the smart device when receiving the hang-up signal sent by the smart device.

Images