Method and system for terminal automatic triggering of pre-established communication sessions

Abstract

The application discloses a method and system for automatically triggering a pre-established communication session by a terminal, and relates to the technical field of mission critical communication, and the method comprises the following steps: collecting multi-source sensing information; judging whether a current scene meets a condition for triggering communication based on the multi-source sensing information; if yes, initiating a resource application for the pre-established communication session to a network side; if a communication link is successfully established, maintaining session resources within a set time; and if the session resources are not used beyond the set time, releasing the session resources, which helps to solve the problem that the prior art cannot realize the automatic triggering of the pre-established communication session by the terminal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mission critical communication, in particular to a method and system for automatically triggering a pre-established communication session by a terminal. BACKGROUND

[0002] In mission critical communication, the establishment of a traditional communication session relies on manual initiation by the terminal side or static strategies by the network side, which cannot meet the instant communication needs in emergency events, mobile environments or high-risk scenarios.

[0003] Existing pre-established communication mechanisms are mostly based on background rule control, lacking real-time environment perception and intelligent judgment capabilities on the terminal side, resulting in delayed communication response and low resource utilization efficiency. For example, in patent CN109874114B, a method for pre-establishing a cluster system based on MCPTT is proposed, but there is no mention of an intelligent triggering mechanism based on user behavior prediction. In patent CN103152700B, Samsung's PoC solution involves the terminal sending specific messages to maintain the session, although the terminal is involved to some extent, but overall, most solutions are based on the core network or server pre-allocating bearer / session resources according to strategies, and the terminal is passive, lacking a design for the terminal to autonomously predict and initiate a session.

[0004] Therefore, there is an urgent need for a terminal-side triggering mechanism that can combine local environmental data, user behavior, state recognition, and automatically infer communication needs based on a deep learning model, to improve the real-time and intelligent level of pre-established sessions. SUMMARY

[0005] Therefore, the present application proposes a method and system for automatically triggering a pre-established communication session by a terminal, which can automatically trigger a pre-established communication session by a terminal.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] A method for automatically triggering a pre-established communication session by a terminal, comprising:

[0008] Collecting multi-source sensing information;

[0009] Determining whether the current scenario meets the conditions for triggering communication based on the multi-source sensing information, and if so, initiating a resource application for a pre-established communication session to the network side;

[0010] If the communication link is successfully established, maintaining the session resources within a set time, and if the session resources are not used beyond the set time, releasing the session resources.

[0011] On the basis of the above technical solutions, the present application can also be improved as follows:

[0012] Optionally, after the step of collecting multi-source sensing information, further comprising:

[0013] data pre-processing the multi-source sensing information to obtain structured data that can be input into a deep learning model;

[0014] inputting the structured data into a trained deep learning model to perform scene recognition and risk assessment, and outputting a quantitative risk score;

[0015] if the risk score is higher than a preset threshold, initiating a resource application for a pre-established communication session to a network side.

[0016] Optionally, the method of automatically triggering a pre-established communication session by a terminal further comprises:

[0017] when the risk score is lower than a preset threshold, re-collecting multi-source sensing information and re-entering the assessment process.

[0018] Optionally, the determining whether the current scene meets the condition for triggering communication based on the multi-source sensing information comprises:

[0019] determining whether the multi-source sensing information meets the condition for triggering communication based on a preset rule logic, and if so, initiating a resource application for a pre-established communication session to a network side.

[0020] Optionally, the multi-source sensing information includes but is not limited to external perception data and terminal communication state data.

[0021] The external perception data includes but is not limited to video images, environmental audio, motion posture, geographic location information, and environmental physical information.

[0022] The terminal communication state data reflects the current communication capability of the terminal and the stability of the network environment, and includes but is not limited to wireless signal strength, channel quality indicator, neighbor cell information, communication failure rate statistics, or historical session log.

[0023] A system for automatically triggering a pre-established communication session by a terminal, comprising:

[0024] a data collection module for collecting multi-source sensing information;

[0025] a trigger determination module for determining whether the current scene meets the condition for triggering communication based on the multi-source sensing information;

[0026] a communication control module for initiating a resource application for a pre-established communication session to a network side when the current scene meets the condition for triggering communication;

[0027] The call holding module is configured to hold session resources for a set time if the communication link is successfully established, and release the session resources if the session resources are not used beyond the set time.

[0028] Optionally, the system further comprises a data preprocessing module and an AI inference module.

[0029] The data preprocessing module is further configured to preprocess the multi-source sensing information to obtain structured data that can be input into a deep learning model.

[0030] The AI inference module is further configured to input the structured data into a trained deep learning model to perform scene recognition and risk assessment, and output a quantitative risk score.

[0031] If the risk score is higher than a preset threshold, the system initiates a resource application for pre-establishing a communication session to a network side.

[0032] The AI inference module is deployed on a local, edge computing node or cloud server.

[0033] Optionally, the trigger judgment module is further configured to judge whether the risk score is higher than a preset threshold, and initiate a resource application for pre-establishing a communication session to a network side when the risk score is higher than the preset threshold, and re-collect multi-source sensing information and re-enter an evaluation process when the risk score is lower than the preset threshold.

[0034] Optionally, the trigger judgment module is further configured to judge whether the multi-source sensing information meets a condition for triggering a communication based on a preset rule logic, and initiate a resource application for pre-establishing a communication session to a network side if the multi-source sensing information meets the condition.

[0035] Optionally, the system is applicable to a critical task communication system, and a communication module thereof supports MCPTT, MCDate and MCVideo services based on a 3GPP standard.

[0036] An electronic device comprises a memory, a processor and a computer program stored on the memory and running on the processor, and the processor implements steps of the method when executing the computer program.

[0037] The present application has the following advantages:

[0038] The method for automatically triggering pre-established communication sessions of the terminal in the application, by independently collecting multi-source sensing information and judging the scene of the terminal, realizes the automatic pre-establishment of the communication session, breaks away from the dependence on manual operation and network static strategy, and significantly improves the response speed of the key task communication. In the emergency or mobile scene, the communication resources can be preempted in advance to avoid the establishment failure caused by resource conflict. At the same time, the mechanism of releasing the resources if not used within the set time can reduce the waste of network resources, and the timeliness of response and resource utilization efficiency are taken into account, which is especially suitable for the scene such as public safety and emergency rescue with extremely high requirement on communication real-time, and guarantees the continuity and reliability of task execution. BRIEF DESCRIPTION OF DRAWINGS

[0039] For the purpose of illustration but not limitation, the application will now be described in conjunction with the embodiments of the application and the accompanying drawings, in which:

[0040] Figure 1 The first flowchart of the method for automatically triggering pre-established communication sessions of the terminal in the embodiment of the application;

[0041] Figure 2 The second flowchart of the method for automatically triggering pre-established communication sessions of the terminal in the embodiment of the application;

[0042] Figure 3 The first schematic diagram of the main components of the system for automatically triggering pre-established communication sessions of the terminal in the embodiment of the application;

[0043] Figure 4 The second schematic diagram of the main components of the system for automatically triggering pre-established communication sessions of the terminal in the embodiment of the application;

[0044] Figure 5 The structural schematic diagram of the terminal device in the embodiment of the application.

[0045] Figure 6 A typical application flow of the application in the railway scene:

[0046] Figure 7 The schematic diagram of the pre-established communication intelligent triggering mechanism of the application in the fire emergency scene.

[0047] Figure 8 An application schematic diagram of the application in the urban transportation scene or public transportation system.

[0048] Figure 9 The model local deployment architecture diagram of the embodiment of the application.

[0049] Figure 10 The model cloud deployment architecture diagram of the embodiment of the application.

[0050] Figure 11 This is a diagram of the edge AI inference deployment architecture according to an embodiment of the present invention.

[0051] Figure 12 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0052] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0053] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0054] It should be noted that, where there is no conflict, the embodiments and features of the present invention can be combined with each other. The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0055] Figure 1 This is a flowchart illustrating the method for automatically triggering the pre-establishment of a communication session by a terminal in an embodiment of the present invention, as shown below. Figure 1 As shown, the method for automatically triggering the pre-establishment of a communication session by a terminal provided in this embodiment of the invention includes the following steps S101 to S103.

[0056] S101 collects information from multiple sensor sources.

[0057] The terminal collects multi-source sensor information such as images, audio, acceleration, and positioning.

[0058] Multi-source sensing information includes external sensing data and terminal communication status data;

[0059] The external perception data includes, but is not limited to, video images (collected by a camera), environmental audio (collected by a microphone), motion posture (acceleration, angular velocity, etc. collected by an inertial sensor), geographic location information (collected by a GNSS / Beidou positioning module), and environmental physical information (temperature and humidity, light intensity, air pressure, etc. sensors).

[0060] The terminal communication state data is used to reflect the current communication capability of the terminal and the stability of the network environment, and includes:

[0061] Wireless signal strength, channel quality indicator, surrounding base station information (neighbor cell identification, frequency point scanning), network type identification (such as LTE / 5G / 5G-R / GSM-R), communication failure rate statistics or historical session logs, and the like, signal strength, RSRP / SINR, neighbor cell, network mode, and the like.

[0062] The multi-source sensing information is directly collected by the built-in sensor, and the original data is collected and transmitted to the downstream module in real time through the built-in sensor interface and the peripheral perception device.

[0063] S102, whether the current scene meets the condition of triggering communication is judged based on the multi-source sensing information, if yes, the resource application of pre-establishing a communication session is initiated to the network side.

[0064] The multi-source sensing information is determined to meet the condition of triggering communication based on a preset rule logic, if yes, the resource application of pre-establishing a communication session is initiated to the network side, such as the resource application of pre-establishing a communication session to an MCX, 5G-R, or the like.

[0065] For example, when the wireless signal strength is lower than -80dBm, the motion speed mutation is greater than 10m / s 2 , and no network heartbeat signaling is received for 3 seconds.

[0066] Any condition is considered as a high-risk state of communication, and the communication control module establishes a session. The module can be realized as a state machine or a condition matching logic, and does not need to be supported by a deep learning model.

[0067] S103, if the communication link is successfully established, the session resource is maintained for a set time, and if the set time is exceeded without using the session resource, the session resource is released.

[0068] The method for the terminal to automatically trigger a pre-established communication session further includes:

[0069] Figure 2 A second flowchart of the method for the terminal to automatically trigger a pre-established communication session in the embodiment of the application is shown in FIG. 2. Figure 2As shown, the method for automatically triggering a pre-established communication session by a terminal provided by the embodiment of the present application comprises the following steps S101-S103.

[0070] S101, collect multi-source sensing information.

[0071] S102, perform data preprocessing on the multi-source sensing information to obtain structured data that can be input into a deep learning model;

[0072] S103, input the structured data into the deep learning model to perform scene recognition and risk assessment, and output a quantitative risk score;

[0073] The deep learning model, such as a convolutional neural network (CNN), a long short-term memory network (LSTM), or a multi-modal fusion network, is deployed. This module receives preprocessed data, performs inference operations such as risk assessment, behavior recognition, or scene classification, and outputs a communication trigger score value or a confidence result.

[0074] The present application does not limit the specific deployment location of the deep learning model, which can not belong to the terminal locally (such as an embedded chip), an edge device (such as a control cabinet, an edge server), or a cloud platform, or a hybrid deployment. Each deployment method has differences in network conditions, response time, and resource capability, and can be included in the implementation scope of the present method.

[0075] S104, determine whether the risk score is higher than a preset threshold, and when the risk score is higher than the preset threshold, initiate a resource application for a pre-established communication session to the network side;

[0076] When the risk score is lower than the preset threshold, re-collect multi-source sensing information.

[0077] S105, if the communication link is successfully established, maintain the session resources within a set time, and if the session resources are not used beyond the set time, release the session resources.

[0078] Figure 3 The first schematic diagram of the main components of the system for automatically triggering a pre-established communication session by a terminal in the embodiment of the present application. As shown in the figure, Figure 3 The system 1 for automatically triggering a pre-established communication session by a terminal provided by the embodiment of the present application comprises a data collection module 10, a trigger judgment module 20, a communication control module 30, and a call maintenance module 40.

[0079] The data collection module 10 is used to collect multi-source sensing information.

[0080] The trigger judgment module 20 is used for judging whether the current scene meets the condition of triggering communication based on the multi-source sensing information; the judgment processing module is not only used for judging the communication trigger condition, but also can be used as a central control logic unit to realize the cooperative operation of the data collection module, the communication control module and the call keeping module.

[0081] The communication control module 30 is used for initiating the resource application of the pre-established communication session to the network side when the current scene meets the condition of triggering communication.

[0082] The call keeping module 40 is used for keeping the session resource within a set time when the communication link is successfully established, and releasing the session resource if the session resource is not used beyond the set time.

[0083] Figure 4 The first schematic view of the main components of the terminal automatic trigger pre-established communication session system in the embodiment of the application is shown in the figure. Figure 4 As shown in the figure, the terminal automatic trigger pre-established communication session system 1 provided by the embodiment of the application includes a data collection module 10, a data preprocessing module 50, an AI inference module 60, a trigger judgment module 20, a communication control module 30 and a call keeping module 40.

[0084] The data collection module 10 is used for collecting multi-source sensing information.

[0085] The data preprocessing module 50 is used for pre-processing the multi-source sensing information to obtain structured data that can be input into a deep learning model.

[0086] The AI inference module 60 is used for inputting the structured data into the deep learning model to perform scene recognition and risk assessment, and outputting a quantitative risk score.

[0087] The trigger judgment module 20 is used for judging whether the risk score is higher than a preset threshold value, initiating the resource application of the pre-established communication session to the network side when the risk score is higher than the preset threshold value, and re-collecting multi-source sensing information and re-entering the assessment process when the risk score is lower than the preset threshold value.

[0088] The trigger judgment module 20 is also used for judging whether the multi-source sensing information meets the condition of triggering communication based on a preset rule logic.

[0089] The communication control module 30 is used for initiating the resource application of the pre-established communication session to the network side when the current scene meets the condition of triggering communication.

[0090] The call keeping module 40 is used for keeping the session resource within a set time when the communication link is successfully established, and releasing the session resource if the session resource is not used beyond the set time.

[0091] As Figure 5 The structure of the terminal device is shown in the embodiment of the application. The terminal device 70 includes a processor 701, a data acquisition module 702, a memory 703, an AI accelerator 704, a communication module 705, and the like.

[0092] The processor 701 is configured to coordinate the workflow of each module, including controlling the triggering and scheduling of data acquisition, managing the connection state of the communication module, calling the AI inference task, and loading the model parameters and configuration data from the memory.

[0093] The data acquisition module 702 is configured to acquire the perception data around the terminal, including but not limited to position, speed, acceleration, image, audio, and state parameters of the current communication channel (such as RSSI, SINR, RSRP, etc.). The module can collect data based on periodic polling or event triggering.

[0094] The memory 703 is configured to store the communication control program, model parameters, temporary data buffer, trigger rule configuration, and the like. The processor can access the memory to realize the integrity of the terminal running logic.

[0095] The AI accelerator 704 is an optional module configured to execute the neural network model deployed locally by the terminal, such as a multi-modal fusion model based on a convolutional neural network (CNN) or a Transformer, and output a score value for communication triggering judgment. The accelerator can be called by the processor and cooperate with the memory to load parameters and intermediate calculation data.

[0096] The communication module 705 is configured to connect to a key communication network, including but not limited to MCX, FRMCS / 5G-R, or GSM-R network. The module receives the communication establishment instruction from the processor or the AI inference result, and completes the pre-establishment, maintenance, and release of the session.

[0097] In some embodiments, the AI accelerator 804 can be omitted, and the processor can directly make a communication triggering judgment based on the collected data and the preset rules, thereby constituting a lightweight terminal implementation scheme.

[0098] In Figure 6 In the railway scene embodiment shown, the train terminal periodically monitors its own position, speed, and communication environment state, and judges whether it is close to the dispatch blind area in combination with the preset map information. When it is detected that the train is about to enter or has entered the dispatch blind area, the terminal side triggering module immediately starts the communication and establishment process, and applies for session establishment resources to the dispatch center in advance.

[0099] The mechanism ensures that the train always maintains a usable communication link in a high-risk communication area. Once an emergency call is needed, the dispatcher can immediately complete the call through the existing session channel, significantly reducing the communication establishment delay and ensuring safe dispatch.

[0100] As Figure 7 shown, an embodiment of the present application is applied to a fire communication scenario. The fire terminal is usually deployed in a wearable device carried by a firefighter or a handheld terminal, and has environmental perception and intelligent judgment capabilities.

[0101] The fire terminal collects multi-modal sensing data such as temperature, smoke, toxic gas concentration, vibration, sound, etc. in real time. When the system detects a fire or a dangerous event (such as rapid temperature rise, excessive smoke, personnel falling, etc.), the judgment module judges the severity of the event according to the preset rules or AI inference results.

[0102] If it is judged that there is a communication risk or an emergency response is needed, the system immediately starts the communication pre-establishment mechanism. The terminal initiates a session pre-establishment request to the communication core system (such as MCX, emergency communication private network, etc.), and allocates dispatch links and resources in advance.

[0103] The communication session is in an active standby state. Once the firefighter needs to establish voice, video or data communication with the command center, it can be instantly connected, significantly reducing communication delay and ensuring the efficiency of frontline response.

[0104] This mechanism also supports "multi-point concurrent triggering" or "instruction cascading transmission", which is suitable for the pre-establishment of multi-level communication links between the front line and the command in large-scale fire, building linkage, industrial explosion and other scenarios.

[0105] As Figure 8 shown, the present application deploys a vehicle terminal in the scenarios of urban public transportation, subway, law enforcement patrol vehicles, etc. The terminal is equipped with a camera, an AI accelerator, an image analysis module and a communication control module.

[0106] The vehicle terminal can collect real-time image data of the front lane, station, passenger dynamics, platform, etc. and perform content recognition through local image analysis algorithms (such as YOLO, ResNet, Transformer, etc.). For example, when detecting:

[0107] road congestion, abnormal crowd gathering, people falling, illegal intrusion into the track area, etc., the image analysis module will output a trigger signal, and then the communication module will initiate a pre-establishment request for a communication session, and establish a communication channel with the traffic control center or the emergency command platform in advance.

[0108] This mechanism ensures that the command center can access the image or voice channel in real time after the occurrence of an emergency, shortens the response time, and improves the safety and efficiency of urban operation.

[0109] Figure 9 The local deployment-based communication triggering mechanism is shown, data is input from a data collection module, and is transmitted to an AI inference module; the AI inference module loads a deployed deep learning model from a local memory; the data is processed by the AI inference module and is judged in combination with the model, and a decision result of whether to trigger communication is output.

[0110] This process forms a local closed-loop response chain of "collection-judgment-control".

[0111] As shown in Figure 10 In the cloud deployment architecture, the AI inference module is deployed on a remote cloud platform, and the terminal device does not need to have local AI processing capability. The terminal uploads data to the cloud AI inference module, the latter loads the model for analysis, and returns the result to the terminal communication control module for triggering session establishment.

[0112] This deployment mode is suitable for application scenarios with good network conditions, limited terminal resources and frequent model updates, such as city traffic, emergency command platforms and industrial detection.

[0113] As shown in Figure 11 In the edge deployment architecture, the AI inference module is deployed on an edge device close to the terminal, such as a train control cabinet, a vehicle-mounted edge computing box or a base station node. The terminal uploads data to the edge AI module for analysis, and the result is fed back to the terminal control module to decide whether to establish a session.

[0114] The above Figures 9 to 11 The different AI inference deployment paths adaptable by the application are shown. According to the communication scene, terminal capability and network environment, model deployment can be selected in the terminal locally, in an edge gateway or in the cloud. All architectures are constructed based on the three-step closed-loop mechanism of data collection, AI decision and communication control, and can all access the automatic triggering pre-established communication mechanism proposed by the application to improve system response efficiency and communication reliability.

[0115] The terminal described in the application is suitable for a critical task communication system, especially for high-reliability and high-real-time communication scenes such as railways, emergencies, public security and power. The terminal communication module supports MCX (Mission Critical Services) services based on the 3GPP standard, including MCPTT (Mission Critical Push To Talk), MCData (Mission Critical Data) and MCVideo (Mission Critical Video) services.

[0116] The terminal can communicate with the MCX server on the network side, support unified management and scheduling of voice, data and video resources, and have key task communication capabilities such as multi-service integration, priority control, QoS guarantee and the like. Through the automatic trigger pre-established communication session mechanism of the application, the terminal can establish link resources in advance in a specific scenario to reduce call setup delay and improve emergency communication efficiency and stability.

[0117] Figure 12 An electronic device entity structure schematic diagram provided by the embodiment of the application is shown in the figure, and the electronic device includes a processor 701, a memory 703 and a bus 706. Figure 12

[0118] The processor 701, the memory 702 and the bus 706 complete mutual communication through the bus 706.

[0119] The processor 701 is used to call the program instruction in the memory 702 to execute the method provided by each method embodiment and execute the method provided by the embodiment of the application.

[0120] The embodiment provides a non-transient computer readable storage medium, which stores computer instructions, and the computer instructions make the computer execute the method provided by the embodiment of the application.

[0121] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program executes the steps including the above method embodiments when executed; and the foregoing storage medium includes ROM, RAM, magnetic disc or optical disc and various storage media that can store program codes.

[0122] The above specific embodiments do not constitute a limitation on the protection scope of the application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can occur depending on design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principle of the application should be included in the protection scope of the application.​

Claims

1. A method for a terminal to automatically trigger a pre-established communication session, characterized by, Comprise: Collecting multi-source sensing information, the multi-source sensing information comprising external perception data and terminal communication state data; The external perception data comprises: video image, environmental audio; motion posture, Geographic location information and environmental physical information; The terminal communication state data reflects the current communication capability of the terminal and the stability of the network environment, and the terminal communication state data comprises wireless signal strength, channel quality indicator, neighbor cell information, communication failure rate statistics or historical session log; Based on the multi-source sensing information, it is judged whether the current scene meets the condition of triggering communication, if yes, the resource application of pre-establishing communication session is initiated to the network side; If the communication link is successfully established, the session resource is maintained within a set time, and if the session resource is not used beyond the set time, the session resource is released.

2. The method of automatically triggering a pre-established communication session by a terminal according to claim 1, characterized in that, After the step of collecting multi-source sensing information, it further comprises: Data preprocessing is performed on the multi-source sensing information to obtain structured data that can be input into a deep learning model; The structured data is input into a trained deep learning model for scene recognition and risk assessment to output a quantitative risk score; If the risk score is higher than a preset threshold, the resource application of pre-establishing session is initiated to the network side.

3. The method of automatically triggering a pre-established communication session by a terminal according to claim 2, characterized in that, The method for the terminal to automatically trigger pre-establishing communication session further comprises: When the risk score is lower than a preset threshold, multi-source sensing information is re-collected, and the evaluation process is re-entered.

4. The method of automatically triggering a pre-established communication session by a terminal according to claim 1, wherein, The judgment based on the multi-source sensing information whether the current scene meets the condition of triggering communication comprises: Based on a preset rule logic, it is judged whether the multi-source sensing information meets the condition of triggering communication, if yes, the resource application of pre-establishing communication session is initiated to the network side.

5. A system for a terminal to automatically trigger a pre-established communication session, characterized in that, Comprise: A data collection module for collecting multi-source sensing information, the multi-source sensing information comprising external perception data and terminal communication state data; The external perception data comprises: video image, environmental audio; motion posture, Geographic location information and environmental physical information; The terminal communication state data reflects the current communication capability of the terminal and the stability of the network environment, and the terminal communication state data comprises wireless signal strength, channel quality indicator, neighbor cell information, communication failure rate statistics or historical session log; A trigger judgment module for judging based on the multi-source sensing information whether the current scene meets the condition of triggering communication; A communication control module for initiating the resource application of pre-establishing communication session to the network side when the current scene meets the condition of triggering communication; A call maintaining module for maintaining the session resource within a set time if the communication link is successfully established, and releasing the session resource if the session resource is not used beyond the set time.

6. The system for automatic triggering of pre-established communication sessions by a terminal according to claim 5, characterized in that, The system for the terminal to automatically trigger pre-establishing communication session further comprises a data preprocessing module and an AI inference module; The data preprocessing module is further used for data preprocessing on the multi-source sensing information to obtain structured data that can be input into a deep learning model; The AI inference module is further used for inputting the structured data into a trained deep learning model for scene recognition and risk assessment to output a quantitative risk score; If the risk score is higher than a preset threshold, a resource application for pre-establishing a communication session is initiated to a network side. The AI inference module is deployed on a local, edge computing node, or cloud server.

7. The system for automatic triggering of pre-established communication sessions by a terminal according to claim 6, characterized in that, The trigger judgment module is further configured to judge whether the risk score is higher than a preset threshold, and when the risk score is higher than the preset threshold, initiate a resource application for pre-establishing a communication session to a network side, and when the risk score is lower than the preset threshold, re-collect multi-source sensing information and re-enter an evaluation process.

8. The system for automatic triggering of pre-established communication sessions by a terminal according to claim 6, characterized in that, The trigger judgment module is further configured to judge, based on a preset rule logic, whether the multi-source sensing information meets a condition for triggering communication, and if yes, initiate a resource application for pre-establishing a communication session to a network side.

9. The system of any of claims 5-8, wherein, The system is applicable to a key task communication system, and the communication module supports MCPTT, MCData, and MCVideo services based on a 3GPP standard.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The processor, when executing the computer program, implements steps of the method according to any one of claims 1 to 4. The processor, when executing the computer program, implements steps of the method according to any one of claims 1 to 4.

Images