Communication method, apparatus, device, and readable storage medium

Abstract

The application discloses a communication method, device and equipment and a readable storage medium, relates to the technical field of communication, and comprises the following steps: receiving event information sent by a first terminal device when detecting a communication event; and sending a communication instruction to an operator server when the event information meets a preset condition for establishing communication, wherein the communication instruction is used for establishing communication between the operator server and a second terminal device. Through the method, a communication request can be automatically initiated to other terminal devices.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a communication method, apparatus, device, and readable storage medium. Background Technology

[0002] In the current communication process, users need to manually initiate communication requests from their terminal devices to other terminal devices to achieve communication. For example, in the scenario of a user ordering takeout, during the delivery process, the user needs to manually initiate a communication request from their terminal device to the delivery person's terminal device and inquire about the delivery status after the communication is established. This process cannot automatically initiate communication requests to other terminal devices, resulting in a poor user experience. Summary of the Invention

[0003] This application provides a communication method, apparatus, device, and readable storage medium to solve the problem of being unable to automatically initiate communication requests to other terminal devices.

[0004] Firstly, a communication method is provided for use on a cloud server, including:

[0005] Receive event information sent by the first terminal device when it detects a communication event;

[0006] When the event information meets the preset conditions for establishing communication, a communication instruction is sent to the operator server. The communication instruction is used to establish communication between the operator server and the second terminal device.

[0007] Optionally, before sending a communication instruction to the operator server when the event information meets the preset conditions for establishing communication, the following steps are included:

[0008] The event information is used to determine whether to establish communication between the operator server and the second terminal device.

[0009] In the case of establishing communication between the operator server and the second terminal device, it is determined whether the event information meets the preset conditions.

[0010] Optionally, the event information includes: an entity set and the communication intent corresponding to the entity set; the entity set includes entity information required to establish communication.

[0011] Optionally, when the event information meets the preset conditions for establishing communication, sending a communication instruction to the operator server includes:

[0012] In response to the event information, the mapping information corresponding to the event information in the preset mapping table is obtained. The mapping information is used to determine the information required to establish communication or the information required during the communication interaction process.

[0013] Context analysis is performed on the event information and the mapping information to determine the first state information corresponding to the event information;

[0014] Determine whether the first state information satisfies the second state information, wherein the preset condition includes the second state information;

[0015] If the first state information satisfies the second state information, it is determined that the event information satisfies the preset condition, and the communication instruction is sent to the operator server.

[0016] Optionally, the communication instructions include at least one of the following:

[0017] Perform a first action; the first action includes at least one of initiating a voice call or sending rich media information.

[0018] Identify the communication target;

[0019] Execute script information, which is used to determine the interaction flow after communication is established;

[0020] Verify the security and integrity of the communication commands;

[0021] Determine the generation time of the communication command;

[0022] Track the communication process;

[0023] Manage communication quality.

[0024] Secondly, a communication method is provided for use with an operator server, including:

[0025] Receive and respond to communication instructions sent by the cloud server, and obtain the digital signature information in the communication instructions;

[0026] The security and integrity of the communication instructions are verified using the digital signature information.

[0027] If the verification is successful, a communication invitation instruction is generated based on the communication instruction;

[0028] The communication invitation instruction is sent to the core network to request the establishment of communication with the second terminal device, which is the terminal device corresponding to the communication object in the communication instruction.

[0029] Optionally, the method further includes:

[0030] In response to the successful establishment of communication between the operator server and the second terminal device, the operator sends first interactive information to the second terminal device based on the execution script information in the communication instruction. The first interactive information is voice information, which is generated based on the text information in the execution script information.

[0031] The system receives the second interaction information sent by the second terminal device, sends the third interaction information corresponding to the second interaction information to the second terminal device based on the interaction flow corresponding to the execution script information, until a preset interaction result is obtained, and then ends the communication.

[0032] Thirdly, a communication device is provided for use on a cloud server, comprising:

[0033] The receiving module is used to receive event information sent by the first terminal device when it detects a communication event;

[0034] The sending module is used to send a communication instruction to the operator server when the event information meets the preset conditions for establishing communication. The communication instruction is used to establish communication between the operator server and the second terminal device.

[0035] Fourthly, a communication device is provided for use in an operator's server, comprising:

[0036] A receiving module is used to receive and respond to communication instructions sent by a cloud server, and to obtain digital signature information from the communication instructions;

[0037] The verification module is used to verify the security and integrity of the communication command using the digital signature information;

[0038] The generation module is used to generate a communication invitation instruction based on the communication instruction if the verification is successful.

[0039] The first sending module is used to send the communication invitation instruction to the core network to request the establishment of communication with the second terminal device, wherein the second terminal device is the terminal device corresponding to the communication object in the communication instruction.

[0040] Fifthly, embodiments of this application provide an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the communication method as described in the first aspect.

[0041] In a sixth aspect, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the communication method as described in the first aspect.

[0042] In a seventh aspect, embodiments of this application provide a computer program product, including computer instructions that, when executed by a processor, implement the steps of the communication method as described in the first aspect.

[0043] In this embodiment, the cloud server receives event information sent by the first terminal device when it detects a communication event. If the event information meets the preset conditions for establishing communication, the cloud server sends a communication command to the operator server. During this process, the cloud server can send a communication command to the operator server when the event information meets the preset conditions, enabling the operator server to proactively initiate communication with other terminal devices. Attached Figure Description

[0044] Figure 1 A flowchart of a communication method provided in an embodiment of this application;

[0045] Figure 2 A flowchart illustrating another communication method provided in an embodiment of this application;

[0046] Figure 3 A schematic diagram of a communication interaction structure provided in an embodiment of this application;

[0047] Figure 4 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0048] Figure 5 This is a schematic diagram of another communication device provided in an embodiment of this application;

[0049] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and are not used to describe a specified order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, a first object can be one or more. Furthermore, in the specification and claims, "and" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0052] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. However, the following description describes New Radio (NR) systems for illustrative purposes, and NR terminology is used in most of the following description. These technologies can also be applied to applications beyond NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0053] like Figure 1 As shown, Figure 1 The communication method provided in this application, applied to a cloud server, comprises the following steps:

[0054] Step 101: Receive event information sent by the first terminal device when it detects a communication event.

[0055] In some embodiments, the event information includes: an entity set and a communication intent corresponding to the entity set; the entity set includes entity information required to establish communication.

[0056] For example, the first terminal device may have a terminal service plugin. After being authorized, the terminal service plugin can register an event listener and listen for and obtain user-authorized application data in real time through system interfaces and security interfaces, such as food delivery order status data, logistics information data, and system data. System data may include calendar events, SMS messages, etc. The terminal service plugin can clean and structure multi-source heterogeneous application data locally on the first terminal device and use a lightweight model for preliminary intent recognition, such as recognizing a delivery delivery event.

[0057] For example, terminal service plugins on a terminal device subscribe to specific application data, such as SMS messages, notifications, and calendars, using callback functions. When the state of application data A changes, the terminal service plugin asynchronously pushes the corresponding event instance (or communication event) to application data A. To the listener, which contains the raw data payload. .

[0058] For example, suppose the application dataset Listening function satisfy: This means that for each authorized application data (Such as SMS messages, notifications, calendars, etc.), each has a corresponding listener function. Its function is to extract data from the application. Raw data load acquired This is converted into a standardized event instance. .in, An event instance that carries metadata such as timestamps and source identifiers.

[0059] The first terminal device can also remove event instances based on regular expression rule sets. Irrelevant information, such as advertisements and CAPTCHAs, can be removed. For example, the first terminal device can select key text segments through word weight calculation, such as an improved weighting technique commonly used in information retrieval and text mining. Furthermore, the first terminal device can predefine the domain patterns corresponding to event examples. For example, assuming the application data is logistics data from a shopping application, and the resulting event example is based on this logistics data, the first terminal device can determine that the domain pattern corresponding to the event example is a logistics pattern. The logistics pattern includes information such as the logistics carrier and tracking number. The first terminal device can use a lightweight sequence labeling model, such as a conditional random field model, to map the text information in the event example to the carrier, tracking number, and other relevant information, generating a structured information object (or entity set). For the entity set, the first terminal device can use a lightweight classifier to predict the intent category. , obtain event information (I, ).

[0060] For example, taking the case where the first terminal device detects a change in logistics data in a shopping application, assuming the current logistics status is "awaiting delivery to the doorstep," the first terminal device can obtain an entity set based on the logistics data in the shopping application. This entity set includes entity information such as the logistics carrier and tracking number. The communication intent corresponding to this entity set is: to communicate with the current delivery person's terminal device through the operator's server to determine the logistics placement point and delivery time. For instance, the event information could be: the entity set includes: {event: "Have the courier deliver to the doorstep", company: "Courier Company 1", pickup_code: "1234", Tracking Number: "1566634"}, with the intent category being to call the delivery person.

[0061] Step 102: If the event information meets the preset conditions for establishing communication, a communication instruction is sent to the operator server. The communication instruction is used to establish communication between the operator server and the second terminal device.

[0062] In some embodiments, before sending a communication instruction to the operator server when the event information meets the preset conditions for establishing communication, the process includes:

[0063] The event information is used to determine whether to establish communication between the operator server and the second terminal device.

[0064] In the case of establishing communication between the operator server and the second terminal device, it is determined whether the event information meets the preset conditions.

[0065] In this embodiment, after receiving the event information, the cloud server needs to determine whether to establish communication between the operator server and the second terminal device. That is, in this embodiment, the communicating parties are the operator server and the second terminal device. The operator server generates voice or text messages for the communication process by calling pre-deployed digital human data to achieve communication with the second terminal device. If the cloud server determines that communication between the operator server and the second terminal device needs to be established, it then determines whether the event information meets the preset conditions for establishing communication.

[0066] In some embodiments, sending a communication instruction to the operator server when the event information meets the preset conditions for establishing communication includes:

[0067] In response to the event information, obtain the mapping information corresponding to the event information in a preset mapping relation table, where the mapping information is used to determine the information required for establishing communication or the information required during the communication interaction process;

[0068] Perform context analysis on the event information and the mapping information to determine the first status information corresponding to the event information;

[0069] Determine whether the first status information meets the second status information, where the preset conditions include the second status information;

[0070] When the first status information meets the second status information, determine that the event information meets the preset conditions, and send the communication instruction to the operator server.

[0071] Exemplarily, the cloud server determines whether the event information meets the preset conditions through a condition engine. The conditions can exist in the form of "if - then", and its logic can be formalized as: .

[0072] where Φ is a condition judgment function, which can also be a judgment function containing multiple sub - conditions, and performs complex logic evaluation through context; Ψ is an action generation function, which constructs a communication instruction according to the condition result. In some embodiments, assuming that multiple preset conditions are met, the cloud server determines the priorities corresponding to each preset condition, and takes the preset condition with the highest priority as the preset condition met by the event information. The priority can be preset or calculated dynamically according to the context. For example, conditions related to security or emergency status have the highest priority.

[0073] There is also a database in the cloud server, which is used to store mapping information. The mapping information is used to determine the information required for establishing communication or the information required during the communication interaction process. For example, taking the establishment of communication between the operator server and the terminal device of the courier as an example, the entity set in the event information includes: {event: "Have the courier deliverto the doorstep", company: "Express Company 2", pickup_code: "1234", Tracking Number: "1566634"}, and the intent category is to call the courier's phone. In this case, during the process of the operator server establishing communication with the courier's terminal device, the operator server cannot determine the contact phone number of the courier's terminal device, while the cloud server can determine the contact phone number of the courier's terminal device corresponding to the logistics carrier through the mapping information, and obtain the contact phone number required for establishing communication.

[0074] The cloud server then performs contextual analysis on the event information and mapping information to determine the first state information corresponding to the event information. For example, the cloud server synchronizes and aligns the event information and mapping information on the timeline, parses the event information and mapping information, and uses the user's current state as the first state information.

[0075] For example, the mapping information includes: "User is in a meeting", "No one is at home", "User is currently at the company", and "Contact number of the delivery person's terminal device". The event information includes: "Logistics tracking number", "Delivery code", and "Courier company". The cloud server determines the user's current status as being in a meeting at the company and the courier being delivered by using the event information and mapping information.

[0076] The cloud server then determines whether the first state information meets the second state information corresponding to the preset conditions. If so, it generates the corresponding communication instruction. For example, the second state information is: the user's state is "in a meeting at the company, and the package is being delivered," and the first state information is: the user's current state is "in a meeting at the company, and the package is being delivered." It is clear that the first and second state information are the same, meaning the first state information satisfies the second state information. The cloud server generates the communication instruction corresponding to the state information. The communication instruction could be: the cloud server instructs the operator's server to call the delivery person, instructing them to leave the package at the door.

[0077] In some embodiments, the communication instructions include at least one of the following:

[0078] Perform a first action; the first action includes at least one of initiating a voice call or sending rich media information.

[0079] Identify the communication target;

[0080] Execute script information, which is used to determine the interaction flow after communication is established;

[0081] Verify the security and integrity of the communication commands;

[0082] Determine the generation time of the communication command;

[0083] Track the communication process;

[0084] Manage communication quality.

[0085] In this embodiment, the communication instruction can be a structured digital object, which includes at least one of the following fields: action field, communication object field, execution script field, timestamp field, random number field, digital signature field, additional field, communication identity number (id) field, communication quality field, etc.

[0086] The communication process is structured as follows: **Action Field:** This field identifies the first action to be performed. For example, if the action field is "call," the first action is to initiate a voice call. **Communication Object Field:** This field identifies the communication object, which can be the contact number of the communication object's terminal device. **Execution Script Field:** This field determines the execution script information, including the interaction flow, script, voice parameters, and alternative interaction paths for the digital human deployed on the operator's server. **Timestamp Field:** This field determines the generation time of the communication command, preventing replay attacks. A random number field is also used to prevent replay attacks. **Digital Signature Field:** This field verifies the security and integrity of the communication command. The digital signature is generated by the cloud server using a private key, based on at least one of the action field, communication object field, execution script field, timestamp field, and random number field. **Additional Fields:** These fields determine other execution parameters, such as the timing of the communication command invocation ("execute after a 5-minute delay") and communication retry policies. **Communication ID Field:** This field tracks the communication process, enabling end-to-end link tracing and problem localization. **Communication Quality Field:** This field manages communication quality, defining service quality requirements, latency, reliability, and other information related to the communication process.

[0087] After the cloud server determines the communication command, it can determine the confidence level of the communication command and use the confidence level as a safety threshold. If the confidence level is lower than the preset threshold, the communication command may be suspended or converted into a confirmation request to the user. After the user confirms, the cloud server then sends the communication command to the operator's server.

[0088] Communication commands can be transmitted through a high-speed internal channel established between the cloud server and the operator's server. This channel is not the public internet, but a dedicated line or a trusted link determined by the operator's interface gateway.

[0089] like Figure 2 As shown, Figure 2 Another communication method flowchart provided in this application embodiment, applied to an operator server, includes the following specific steps:

[0090] Step 201: Receive and respond to the communication command sent by the cloud server, and obtain the digital signature information in the communication command.

[0091] Step 202: Verify the security and integrity of the communication command using the digital signature information.

[0092] Step 203: If the verification is successful, generate a communication invitation instruction based on the communication instruction.

[0093] Step 204: Send the communication invitation instruction to the core network to request the establishment of communication with the second terminal device, wherein the second terminal device is the terminal device corresponding to the communication object in the communication instruction.

[0094] In this embodiment, after the operator server receives the communication command, it performs bidirectional transport layer security authentication with the cloud server to verify the cloud server's identity. If the authentication is successful, the operator server uses a pre-configured cloud server public key to verify the digital signature information (digital signature field) in the communication command to determine its security and integrity. Only if the authentication is successful will the communication command be processed by the operator server, generating a corresponding communication invitation command; otherwise, the communication command will be recorded and discarded. The operator server can also perform compliance checks on the communication command based on preset business policies, such as frequency restrictions and communication target blacklists / whitelists. The operator server can also verify the status of the second terminal device and whether the current communication complies with the operator's business policies, such as call frequency restrictions and call time restrictions.

[0095] The operator server can also be referred to as the operator network capability open platform, which includes a media resource server. The media resource server is used to apply for and configure corresponding digital human voice resources, video resources, or interactive logic.

[0096] During the process of the operator's server processing communication commands, the operator's server uses an interpretation engine to convert the communication commands into network native commands that can be understood by the network core network. The core network can be the IP Multimedia Subsystem (IMS), Mobile Switching Center (MSC), etc.

[0097] The operator server then sends network-native instructions to the media resource server. The media resource server checks whether the current media resource pool has sufficient resources, such as idle digital human voice ports and available RTP media stream bandwidth. If resources are sufficient, the media resource server configures the corresponding digital human. The operator server then sends the corresponding communication invitation instruction to the core network to request the establishment of a communication link led by the digital human to the communication target, in order to apply for communication between the operator server and the terminal device (or second terminal device) of the communication target.

[0098] During this process, the operator's server can create a unique session context (Sctx) for the communication process, where Sctx = {session_id, CMD, start_time, caller_id, media_resource_id}. Sctx is used to issue native network commands and send corresponding communication invitation commands to the core network.

[0099] Among them, session_id is the session ID corresponding to the communication process; CMD is the communication command; start_time is the communication time; caller_id is an authenticated official number representing the operator's identity to establish the credibility of the call; and media_resource_id is the digital human's ID.

[0100] The communication invitation instruction can also be called the Session Initiation Protocol (SIP) invitation instruction, or SIP INVITE.

[0101] In some embodiments, the method further includes:

[0102] In response to the successful establishment of communication between the operator server and the second terminal device, the operator sends first interactive information to the second terminal device based on the execution script information in the communication instruction. The first interactive information is voice information, which is generated based on the text information in the execution script information.

[0103] The system receives the second interaction information sent by the second terminal device, sends the third interaction information corresponding to the second interaction information to the second terminal device based on the interaction flow corresponding to the execution script information, until a preset interaction result is obtained, and then ends the communication.

[0104] In this embodiment, after the core network receives the communication invitation instruction, it sends a communication request to the second terminal device. Upon receiving and responding to the communication request, communication between the operator server and the second terminal device is successfully established. Based on the execution script information in the communication instruction, the operator server sends first interactive information to the second terminal device. This first interactive information is the voice information of the digital human configured by the media resource server. For example, in a communication scenario where a voice call is initiated with a delivery person, the text information in the execution script is: "Hello, I am the intelligent assistant of [user name]. Can you arrange door-to-door delivery for package [logistics tracking number]?" The operator server interacts with the delivery person via voice using the text information in the execution script.

[0105] The following example illustrates the communication process in detail.

[0106] After successful communication command verification, the operator's server sends an authenticated SIP INVITE request to the Serving-Call Session Control Function (S-CSCF) in the IMS core network. The SIP INVITE request contains the contact phone number of the terminal device being communicated and a specific service identifier. The IMS core network routes the communication request to the mobile network where the contact phone number resides based on the contact phone number. During the communication interaction, media parameters are negotiated in advance using the Session Description Protocol to ensure compatibility between the two ends.

[0107] Once the terminal device of the communication target rings and is answered, the call enters an active state, and the digital human interaction officially begins. After the call is connected, a bidirectional real-time transmission protocol media stream channel is established between the media resource server in the operator's server and the terminal device of the communication target.

[0108] The media resource server dynamically loads the corresponding digital human engine instance based on the media_resource_id in the SCTX file. This digital human engine is a software module that integrates speech synthesis, natural language understanding, and dialogue management. After the digital human engine is loaded, the execution script field in the communication command is injected and parsed. The digital human engine initializes the dialogue state machine based on the execution script field, setting parameters such as the speech content, timbre, and speech rate for the first round of playback.

[0109] The digital human engine then drives the entire dialogue process, enabling intelligent interaction with the communication partner. Using text-to-speech technology, the engine synthesizes text information into highly natural-sounding speech in real time, plays it back to the communication partner via a real-time transmission protocol channel, and continuously detects voice activity from the communication partner's audio information, accurately identifying when the communication partner begins and ends speaking.

[0110] During the communication, the digital human engine sends the audio information to the automatic speech recognition module to be converted into text information, and the natural language understanding module immediately performs intent recognition and key information extraction. That is, the automatic speech recognition module converts audio information into text information in real time. During this process, the digital human engine searches for the most likely word sequence corresponding to the text information. The natural language understanding module performs semantic analysis on the text information, extracting intent and key information to drive state transitions in the dialogue. For example, for the input "deliver it around 4 PM," the natural language understanding module: intent is confirm_time (confirmation time), time is 16:00.

[0111] The dialogue state machine then determines the next action based on preset interaction logic: whether to continue asking questions, confirming information, or to perform an operation and end the call. The digital human engine generates natural and friendly response text based on preset interaction strategies and predefined templates, and synthesizes the response text into highly natural-sounding speech, which is then played to the communicating partner. This process repeats until the dialogue state machine reaches a preset final state, resulting in a preset interaction outcome, such as "task completed" or "confirmation failed."

[0112] After the call concludes, the carrier server performs orderly session cleanup and results feedback. The digital human engine plays a closing message according to the script, such as "Thank you for answering, goodbye." The carrier server sends a SIP termination request to the core network, normally releasing the call connection. This also releases the media ports and computing resources used in this session.

[0113] The operator's server generates a detailed interaction report, including call result (success / failure), call duration, conversation logs, and identified key information (such as the delivery person's promised pick-up time). This report is transmitted back to the cloud server in real time via a high-speed channel to update service status, record history, and provide user feedback.

[0114] The interactive report may include: communication result information, key information of the communication process, follow-up information for subsequent communications, and communication summary information. The communication result information is used to determine whether the communication achieved the preset goals, thus judging the final communication outcome. The key information of the communication process is a list of key events extracted from the communication, along with confidence levels, such as: {fact: "Agreed to door-to-door delivery", confidence: 0.95}. The follow-up information for subsequent communications is used to identify information that requires further follow-up. The communication summary information is a brief text summary outlining the communication content.

[0115] During communication and interaction, the dialogue state machine is mainly relied upon to determine the interaction information and whether the dialogue state machine has reached the preset final state. In other words, the dialogue state machine guides the entire interaction process. The dialogue state machine can be formally defined as: FSM=(Q,Σ,δ,q0,F).

[0116] Where Q = {q0, q1, ..., qn} is a finite set of states, representing different stages of the dialogue, such as greeting, explaining the purpose, asking questions, confirming, and ending. Σ is the set of input symbols, i.e., the set of intentions identified from the audio information of the communicating parties. δ: Q × Σ → Q is the state transition function, defined as the next state to which a certain intention should be received after a specific state. q0 ∈ Q is the initial state, usually the greeting. F ⊂ Q is the set of final states, representing whether the dialogue was successfully completed or failed.

[0117] The digital human engine determines the current state qc in real time and uses the dialogue state machine to determine the corresponding action, such as playing a voice message. The digital human engine then waits and recognizes the user's audio information to obtain the intent σ∈Σ. The digital human engine then jumps to the next state according to the transition function qnext=δ(qc,σ) in the dialogue state machine. This process is repeated until a final state qf∈F is reached.

[0118] like Figure 3 As shown, the communication method of this application is specifically illustrated through concrete examples.

[0119] Phase 1: Ordering and Initial Setup of Event Listeners

[0120] Event listeners in user food delivery ordering scenarios: Users select the food delivery scenario on the intelligent voice assistant page to place an order, and the event listener is deployed on the user's primary terminal device. Users can also choose which third-party food delivery apps the event listener monitors and configure some scenario attributes in the pop-up personalized preference settings page. After the monitoring settings are complete, users can choose different digital avatars and voices for different application scenarios to answer calls on their behalf, thus meeting the usage needs of the scenario.

[0121] Phase Two: Generating and Sending Event Information

[0122] At this stage, the primary terminal device no longer waits for incoming calls. Instead, an event listener within the device runs continuously in the background, proactively collecting and integrating data from multiple sources to create real-time awareness of the user's food delivery status. Optionally, after obtaining user authorization, the event listener establishes a secure connection with a third-party food delivery application. It periodically or triggers the retrieval of the user's real-time food delivery data, including: merchant information, estimated delivery time, order status, rider contact information, and the user's historical order preferences.

[0123] The event listener invokes the user's first terminal device permissions to obtain the user's real-time location and calendar information, such as whether they are in a meeting or whether the terminal device is in "Do Not Disturb" mode. It then determines the user's current "receive food delivery status." For example, if the user is at the office and has no meetings in the next 30 minutes, they are in a "receive food delivery status"; if the user is in a meeting room, they are in a "do not receive food delivery status."

[0124] Event listeners can also analyze historical call recordings and order data, using natural language processing technology to summarize user preferences and automatically create user profiles. For example, a user profile might include: "prefers to have takeout placed on the front end," "frequently orders from a particular light meal restaurant," and "usually has lunch between 12:00 and 13:00." These profiles provide a basis for personalized services in the future.

[0125] The event listener then sends the event information to the cloud server. The event information includes: real-time food delivery data, real-time geographical location, calendar information and user profiles, as well as the intent to initiate a voice call to the delivery driver corresponding to this data.

[0126] Phase 3: Context Analysis and Communication Command Generation

[0127] The cloud server transforms received data and intentions into action information and predicts potential problems. It compares the estimated delivery time of the food delivery with the current time in the data, and combines this with real-time traffic data (such as map interfaces) to make a judgment.

[0128] If the cloud server determines that the food delivery has a high risk of delay (e.g., the estimated delivery time has passed, but the rider's location is still far from the destination), the cloud server will determine it to be in a "proactive intervention required" state, which corresponds to the state corresponding to the preset conditions for establishing communication. The cloud server establishes communication between the operator's server and the delivery rider's second terminal device and determines the communication instructions.

[0129] The cloud server can combine data such as "user's current location" and "user's historical preference profile" to perform contextual analysis, determine the best delivery point for the food delivery, and generate corresponding communication instructions. The communication instructions include: initiating a voice call to the delivery person, the delivery person's contact number, script information such as: deliver the food to the company's front desk (because the user is in a meeting, and historically 80% of orders have chosen the front desk), and signature information.

[0130] The cloud server then sends communication commands to the operator's server.

[0131] Phase Four: Establishing Communication

[0132] Scenario 1: Actively calling the delivery driver

[0133] The operator's server receives the communication command and generates a corresponding communication invitation command. The operator's server then sends this communication invitation command to the core network. The core network receives the communication invitation command and sends a communication request to the deliveryman's second terminal device. The second terminal device receives the communication request, and at this point, a voice call is successfully established between the deliveryman's second terminal device and the operator's server. The operator's server calls the data human engine and uses text-to-speech technology to generate and broadcast a personalized voice message: "Hello, I am [User Name]'s intelligent secretary. Order [Order Number] may be delayed. The user is about to end their meeting; please prioritize delivery. After delivery, please place it directly at the company's front desk. Thank you." The entire process requires no user intervention, automatically completing the order reminder and delivery instructions.

[0134] After the dialogue achieves the preset interaction result, the operator's server generates a detailed interaction report and sends the report to the cloud server.

[0135] Once the food delivery status updates or the conversation reaches a pre-defined interaction result, the cloud server proactively synchronizes the interaction process via app push notifications, SMS messages, or even outbound calls to the user. Example message: "Hello, we have detected that your food delivery has been accepted by a delivery person and is expected to arrive at 12:15. According to your calendar, your meeting will have ended by then, and the delivery person has been automatically notified to deliver the food to your workstation. Please check your delivery."

[0136] Scenario 2: Receiving a call from a food delivery driver

[0137] When a delivery driver proactively calls a user's primary device, the event listener sends current event information, such as anticipated order details, proactive actions already performed (e.g., order reminders), and established delivery strategies, to the cloud server. The cloud server then forwards the event information to the carrier's server. Based on historical interaction information and event data, the carrier's server enables high-dimensional and precise interaction between the digital human and the delivery driver.

[0138] As can be seen from the above embodiments, the embodiments of this application achieve a fundamental shift from passively responding to communication requests to actively initiating communication requests. The lightweight business monitoring plugin and local intent recognition mechanism adopted on the terminal side complete the structured processing and abstract uploading of multi-source information, significantly reducing the computing load and transmission latency of the cloud server while ensuring the security of user privacy data. The cloud server generates accurate and executable communication instructions by integrating multi-source context information and dynamic arbitration based on whether preset communication conditions are met, thereby greatly improving the automation level and decision-making intelligence of transaction processing in complex scenarios. On the operator side, the trusted outbound calling and digital human interaction execution system based on the operator server transforms abstract communication instructions into high-quality call links and natural, smooth multi-turn interactive dialogues in real time. This design enables the digital human to dynamically drive the interaction process according to preset scripts and complete structured result feedback, ultimately forming a complete service loop covering perception, decision-making, execution, and feedback, effectively improving reliability and user experience consistency in real-world scenarios.

[0139] Please refer to Figure 4 , Figure 4 This is a schematic diagram of a communication device according to an embodiment of this application. The communication device 400 includes:

[0140] The receiving module 401 is used to receive event information sent by the first terminal device when it detects a communication event;

[0141] The sending module 402 is used to send a communication instruction to the operator server when the event information meets the preset conditions for establishing communication. The communication instruction is used to establish communication between the operator server and the second terminal device.

[0142] Optionally, the communication device 400 may also include:

[0143] The judgment module is used to determine whether to establish communication between the operator server and the second terminal device based on the event information;

[0144] The first determining module is used to determine whether the event information meets the preset conditions when communication is established between the operator server and the second terminal device.

[0145] Optionally, the event information includes: an entity set and the communication intent corresponding to the entity set; the entity set includes entity information required to establish communication.

[0146] Optionally, the transmitting module 402 may also include:

[0147] The acquisition unit is configured to, in response to the event information, acquire mapping information corresponding to the event information in a preset mapping table, wherein the mapping information is used to determine the information required to establish communication or the information required during the communication interaction process;

[0148] The first determining unit is configured to perform context analysis on the event information and the mapping information to determine the first state information corresponding to the event information;

[0149] The second determining unit is used to determine whether the first state information satisfies the second state information, wherein the preset condition includes the second state information;

[0150] The third determining unit is configured to determine that the event information satisfies the preset condition when the first state information satisfies the second state information, and then send the communication instruction to the operator server.

[0151] Optionally, the communication instructions include at least one of the following:

[0152] Perform a first action; the first action includes at least one of initiating a voice call or sending rich media information.

[0153] Identify the communication target;

[0154] Execute script information, which is used to determine the interaction flow after communication is established;

[0155] Verify the security and integrity of the communication commands;

[0156] Determine the generation time of the communication command;

[0157] Track the communication process;

[0158] Manage communication quality.

[0159] The communication device 400 provided in this application embodiment can perform the above-described... Figure 1 The method embodiments shown are similar in principle and technical effect, and will not be described again here.

[0160] Please refer to Figure 5 , Figure 5 This is a schematic diagram of another communication device according to an embodiment of this application. The communication device 500 includes:

[0161] The receiving module 501 is used to receive and respond to the communication instructions sent by the cloud server, and obtain the digital signature information in the communication instructions;

[0162] The verification module 502 is used to verify the security and integrity of the communication command through the digital signature information;

[0163] The generation module 503 is used to generate a communication invitation instruction based on the communication instruction if the verification is successful.

[0164] The first sending module 504 is used to send the communication invitation instruction to the core network to request the establishment of communication with the second terminal device, wherein the second terminal device is the terminal device corresponding to the communication object in the communication instruction.

[0165] Optionally, the communication device 500 may also include:

[0166] The second sending module is used to send first interactive information to the second terminal device in response to the successful establishment of communication between the operator server and the second terminal device, based on the execution script information in the communication instruction. The first interactive information is voice information, which is generated based on the text information in the execution script information.

[0167] The third sending module is used to receive the second interaction information sent by the second terminal device, send the third interaction information corresponding to the second interaction information to the second terminal device based on the interaction process corresponding to the execution script information, until a preset interaction result is obtained, and then end the communication.

[0168] The communication device 500 provided in this application embodiment can perform the above-described... Figure 2 The method embodiments shown are similar in principle and technical effect, and will not be described again here.

[0169] This application also provides an electronic device. Since the principle by which this electronic device solves the problem is similar to the communication method in the embodiments of this application, the implementation of this electronic device can be found elsewhere. Figure 1 The implementation of the method shown will not be repeated here. Figure 6 As shown, the electronic device according to an embodiment of this application includes: a processor 610, configured to read a program from a memory 620 and execute the following processes:

[0170] Receive event information sent by the first terminal device when it detects a communication event;

[0171] When the event information meets the preset conditions for establishing communication, a communication instruction is sent to the operator server. The communication instruction is used to establish communication between the operator server and the second terminal device.

[0172] Optionally, the processor 610 is also configured to read the program in the memory 620 and perform the following steps: before sending the communication instruction to the operator server when the event information meets the preset conditions for establishing communication, the steps include:

[0173] The event information is used to determine whether to establish communication between the operator server and the second terminal device.

[0174] In the case of establishing communication between the operator server and the second terminal device, it is determined whether the event information meets the preset conditions.

[0175] Optionally, the event information includes: an entity set and the communication intent corresponding to the entity set; the entity set includes entity information required to establish communication.

[0176] Optionally, the processor 610 is also used to read the program in the memory 620 and perform the following steps: when the event information meets the preset conditions for establishing communication, sending a communication instruction to the operator server includes:

[0177] In response to the event information, the mapping information corresponding to the event information in the preset mapping table is obtained. The mapping information is used to determine the information required to establish communication or the information required during the communication interaction process.

[0178] Context analysis is performed on the event information and the mapping information to determine the first state information corresponding to the event information;

[0179] Determine whether the first state information satisfies the second state information, wherein the preset condition includes the second state information;

[0180] If the first state information satisfies the second state information, it is determined that the event information satisfies the preset condition, and the communication instruction is sent to the operator server.

[0181] Optionally, the communication instructions include at least one of the following:

[0182] Perform a first action; the first action includes at least one of initiating a voice call or sending rich media information.

[0183] Identify the communication target;

[0184] Execute script information, which is used to determine the interaction flow after communication is established;

[0185] Verify the security and integrity of the communication commands;

[0186] Determine the generation time of the communication command;

[0187] Track the communication process;

[0188] Manage communication quality.

[0189] Among them, Figure 6 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 610 and memory represented by memory 620 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides the interface.

[0190] The electronic device provided in this application embodiment can perform the above-described functions. Figure 1 The method embodiments shown are similar in principle and technical effect, and will not be described again here.

[0191] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the above-described communication method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0192] This application also provides a computer program product, including computer instructions. When these computer instructions are executed by a processor, they implement the various processes of the above-described communication method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0193] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0194] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0195] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A communication method applied to a cloud server, characterized in that, include: Receive event information sent by the first terminal device when it detects a communication event; When the event information meets the preset conditions for establishing communication, a communication instruction is sent to the operator server. The communication instruction is used to establish communication between the operator server and the second terminal device.

2. The method according to claim 1, characterized in that, Before sending a communication instruction to the operator server when the event information meets the preset conditions for establishing communication, the process includes: The event information is used to determine whether to establish communication between the operator server and the second terminal device. In the case of establishing communication between the operator server and the second terminal device, it is determined whether the event information meets the preset conditions.

3. The method according to claim 1, characterized in that, The event information includes: an entity set and the communication intent corresponding to the entity set; the entity set includes entity information required to establish communication.

4. The method according to claim 1, characterized in that, When the event information meets the preset conditions for establishing communication, sending a communication instruction to the operator server includes: In response to the event information, the mapping information corresponding to the event information in the preset mapping table is obtained. The mapping information is used to determine the information required to establish communication or the information required during the communication interaction process. Context analysis is performed on the event information and the mapping information to determine the first state information corresponding to the event information; Determine whether the first state information satisfies the second state information, wherein the preset condition includes the second state information; If the first state information satisfies the second state information, it is determined that the event information satisfies the preset condition, and the communication instruction is sent to the operator server.

5. The method according to claim 1, characterized in that, The communication instructions include at least one of the following: Perform a first action; the first action includes at least one of initiating a voice call or sending rich media information. Identify the communication target; Execute script information, which is used to determine the interaction flow after communication is established; Verify the security and integrity of the communication commands; Determine the generation time of the communication command; Track the communication process; Manage communication quality.

6. A communication method applied to an operator's server, characterized in that, include: Receive and respond to communication instructions sent by the cloud server, and obtain the digital signature information in the communication instructions; The security and integrity of the communication instructions are verified using the digital signature information. If the verification is successful, a communication invitation instruction is generated based on the communication instruction; The communication invitation instruction is sent to the core network to request the establishment of communication with the second terminal device, which is the terminal device corresponding to the communication object in the communication instruction.

7. The method according to claim 6, characterized in that, The method further includes: In response to the successful establishment of communication between the operator server and the second terminal device, the operator sends first interactive information to the second terminal device based on the execution script information in the communication instruction. The first interactive information is voice information, which is generated based on the text information in the execution script information. The system receives the second interaction information sent by the second terminal device, sends the third interaction information corresponding to the second interaction information to the second terminal device based on the interaction flow corresponding to the execution script information, until a preset interaction result is obtained, and then ends the communication.

8. A communication device applied to a cloud server, characterized in that, include: The receiving module is used to receive event information sent by the first terminal device when it detects a communication event; The sending module is used to send a communication instruction to the operator server when the event information meets the preset conditions for establishing communication. The communication instruction is used to establish communication between the operator server and the second terminal device.

9. A communication device applied to an operator's server, characterized in that, include: A receiving module is used to receive and respond to communication instructions sent by a cloud server, and to obtain digital signature information from the communication instructions; The verification module is used to verify the security and integrity of the communication command using the digital signature information; The generation module is used to generate a communication invitation instruction based on the communication instruction if the verification is successful. The first sending module is used to send the communication invitation instruction to the core network to request the establishment of communication with the second terminal device, wherein the second terminal device is the terminal device corresponding to the communication object in the communication instruction.

10. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the communication method as claimed in any one of claims 1 to 5 or the steps of the communication method as claimed in any one of claims 6 to 7.

11. A computer-readable storage medium for storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the communication method as described in any one of claims 1 to 5 or the steps of the communication method as described in any one of claims 6 to 7.

12. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps in the communication method as described in any one of claims 1 to 5 or the steps in the communication method as described in any one of claims 6 to 7.

Images