Multi-terminal converged communication platform for travel

Abstract

The invention discloses a multi-terminal converged communication platform for tourism. The platform comprises a tourism behavior map modeling module, an intention analysis processing module, a cross-device trust authentication module, a multi-terminal parameter acquisition module, a communication resource allocation module and a data interaction execution module. The tourism behavior map modeling module generates a behavior map node set based on a space-time tourism behavior map inference model, the intention analysis processing module outputs an intention analysis result through a bidirectional association tourism intention analysis model, and the cross-device trust authentication module constructs platform parameters in combination with a mobile communication cross-device trust chain to judge a device trust level. The multi-terminal parameter acquisition module acquires parameters such as communication bandwidth and signal strength, the communication resource allocation module generates a resource allocation scheme according to the parameters, and the data interaction execution module establishes a communication link to transmit data. According to the platform, tourist demands can be accurately matched, communication safety and resource utilization efficiency are guaranteed, and tourism multi-terminal communication stability and adaptability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tourism communication, and in particular to a multi-terminal fusion communication platform for tourism. BACKGROUND

[0002] In current tourism activities, tourists often obtain services and share information through various terminal devices, and frequent data interaction between different devices is required, and precise service matching based on tourist behavior and demand is also required. The development of mobile communication technology promotes cross-device collaboration to become an important direction for optimizing tourism services, and the collaboration of device identification association, behavior trajectory analysis, demand intention interpretation, trust level determination, communication parameter collection and resource allocation is the key to ensuring stable and efficient multi-terminal communication. In the existing tourism scene, multi-terminal devices are mostly in a scattered communication state, lacking of systematic integration and reasoning of spatio-temporal tourism behavior data, and a perfect cross-device trust system and dynamic resource allocation mechanism has not been formed, making it difficult to meet the needs of tourists for multi-terminal data interaction, timeliness, accuracy and security in different tourism scenarios, therefore, it is urgent to build a fusion communication platform that can realize multi-module collaboration.

[0003] The existing multi-terminal communication technology related to tourism has two significant shortcomings: first, the cross-device trust authentication and intention analysis are disconnected, relying only on single device identification or simple communication records to determine the trust level of the device, without combining spatio-temporal behavior trajectory and demand labels for associated operations, resulting in a mismatch between trust authentication results and actual device usage needs in the tourism scene, making it difficult for authenticated devices to meet specific tourism data transmission needs; second, the multi-terminal communication parameter collection and resource allocation are fragmented, with the collection process only obtaining basic communication data without associating with device interaction frequency, data transmission type and other information in the tourism scene, and the resource allocation only follows fixed rules without dynamically adjusting weights and schemes based on real-time collected parameters, resulting in resource allocation that cannot adapt to the dynamic communication needs of different devices in the tourism process, causing communication resource waste or critical data transmission delay. SUMMARY

[0004] In order to overcome the shortcomings and deficiencies of the prior art, the present application provides a multi-terminal fusion communication platform for tourism.

[0005] The technical scheme adopted by the present application is a multi-terminal fusion communication platform for tourism, comprising: a tourism behavior graph modeling module, receiving multi-terminal device identification information transmitted by a mobile communication cross-device trust chain construction platform, extracting device-associated tourism trajectory data based on a spatiotemporal tourism behavior graph reasoning model, and generating a behavior graph node set; an intention analysis processing module, obtaining the node set output by the behavior graph modeling module, correlating the trajectory features in the node set with tourism demand labels through a bidirectional correlation tourism intention analysis model, and outputting an intention analysis result; a cross-device trust authentication module, receiving the analysis result of the intention analysis processing module, combining the device trust value parameters of the mobile communication cross-device trust chain construction platform, performing trust level judgment on the multi-terminal devices, and outputting a list of devices that pass authentication; a multi-terminal parameter acquisition module, connected to the device list of the cross-device trust authentication module, acquiring the communication bandwidth, signal strength, and data transmission delay parameters of each device, and forming a parameter matrix; a communication resource allocation module, receiving the parameter matrix of the multi-terminal parameter acquisition module, performing weight allocation on the parameters in the matrix according to the resource allocation rules of tourism multi-terminal communication, and outputting a resource allocation scheme; a data interaction execution module, connected to the communication resource allocation module, establishing a communication link between multi-terminal devices according to the allocation scheme, transmitting tourism-related data, and the behavior graph modeling module, the intention analysis processing module, the cross-device trust authentication module, the multi-terminal parameter acquisition module, the communication resource allocation module, and the data interaction execution module sequentially perform data transmission and control signal interaction.

[0006] Further, in the intention analysis processing module, the operation formula of the bidirectional correlation tourism intention analysis model is: wherein, is the intention analysis result value, is the graph correlation weight coefficient, is the node feature vector output by the behavior graph modeling module, is the tensor product operator symbol, is the tourism demand label vector, is the device data weight coefficient, is the device trust vector of the mobile communication cross-device trust chain construction platform, is the dot product operator symbol, is the signal strength parameter vector of the multi-terminal parameter acquisition module; in the cross-device trust authentication module, the trust level judgment formula is: wherein, is the device trust level value, is the authentication parameter weight coefficient, is the device identification matching degree parameter, is the exclusive OR operator symbol, is the historical communication reliability parameter, is the communication parameter weight coefficient, is a communication bandwidth parameter, is a Hadamard product operator symbol, is a data transmission delay parameter.

[0007] Further, in the multi-terminal parameter acquisition module, the parameter matrix generation formula is: wherein, is a multi-terminal parameter matrix, is a communication bandwidth parameter of the nth device, is a signal strength parameter of the nth device, is a data transmission delay parameter of the nth device, is a basic parameter weight, is a connection duration parameter of the nth device and the mobile communication cross-device trust chain construction platform, is a tourism data transmission frequency parameter of the nth device, is a trust chain association parameter weight; in the communication resource allocation module, the resource allocation scheme calculation formula is: wherein, is a resource allocation scheme vector, is a parameter weight matrix, is a corresponding element multiplication operator symbol, is a total resource vector of multi-terminal communication for tourism.

[0008] Further, in the behavior graph modeling module, the behavior graph node set generation formula is: wherein, is a behavior graph node set matrix, is a device trajectory coordinate parameter matrix transmitted by the mobile communication cross-device trust chain construction platform, is a trajectory weight coefficient, is a matrix addition operator symbol, is a trajectory correlation degree parameter matrix output by the space-time tourism behavior graph reasoning model, is an association degree weight coefficient; in the data interaction execution module, the communication link transmission rate calculation formula is: wherein, is a link transmission rate value, is a resource allocation amount parameter output by the communication resource allocation module, is a resource conversion coefficient, is a signal strength mean parameter of the multi-terminal parameter acquisition module, is a signal influence coefficient.

[0009] Further, in the intention analysis processing module, the optimization formula of the bidirectional associated tourism intention analysis model is: wherein, The optimized intention analysis result value, The initial analysis result value, The optimization coefficient, The behavior graph node feature vector, The dot product operator symbol, The tourism demand label vector; in the cross-device trust authentication module, the trust chain update formula is: Wherein, The updated trust chain parameter, The old trust chain parameter, The update coefficient, The historical communication reliability parameter, The Hadamard product operator symbol, The communication bandwidth parameter.

[0010] Further, in the multi-terminal parameter acquisition module, the parameter anomaly detection formula is: Wherein, The parameter anomaly value, The real-time collected parameter matrix, The historical parameter mean matrix, The absolute value operator symbol, The anomaly detection weight; in the communication resource allocation module, the resource adjustment formula is: Wherein, The adjusted resource allocation scheme, The initial allocation scheme, The adjustment coefficient, The parameter anomaly value vector, The dot product operator symbol, The emergency degree parameter vector of tourism multi-terminal communication.

[0011] Further, the cross-device trust authentication module comprises: a device identification verification unit receiving the analysis result of the intention analysis processing module, extracting the hardware identification and software identification information of the multi-terminal device, comparing the identification information with the preset identification library of the mobile communication cross-device trust chain construction platform, screening the devices with matched identification, and generating a matching result; a trust value calculation unit obtaining the matching result of the device identification verification unit, calling the historical communication data of the mobile communication cross-device trust chain construction platform, calculating the communication success rate and data integrity parameters of the device, combining the preset trust algorithm, and obtaining the trust value of each device; a trust level division unit receiving the trust value of the trust value calculation unit, dividing the device into three trust levels of high, medium and low according to the trust level threshold of the multi-terminal communication of the tourism, and outputting the level division result; and an authentication result feedback unit obtaining the level result of the trust level division unit, including the high and medium level devices in the authentication pass list, marking the low level device as to be verified, and feeding back the authentication list to the multi-terminal parameter collection module.

[0012] Further, the multi-terminal parameter collection module comprises: a bandwidth collection unit connecting the authentication pass device list of the cross-device trust authentication module, sending a bandwidth detection instruction through the device communication interface, receiving the real-time bandwidth data fed back by the device, sampling the data, and obtaining the communication bandwidth parameters of each device; a signal strength collection unit scanning the signal frequency band of the authentication pass device by using the wireless signal detection module, collecting the signal strength value under different frequency bands, calculating the mean value after removing the abnormal value, and generating the signal strength parameter; a delay collection unit sending a timestamp request signal to the authentication pass device, recording the time difference between signal sending and receiving, taking the average after multiple measurements, and obtaining the data transmission delay parameter; and a parameter integration unit receiving the parameters of the bandwidth collection unit, the signal strength collection unit and the delay collection unit, arranging the parameters in the order of device number, forming a multi-terminal parameter matrix, and transmitting to the communication resource allocation module.

[0013] Further, the communication resource allocation module comprises: a parameter weight determination unit receiving the parameter matrix of the multi-terminal parameter collection module, determining the weight values of the communication bandwidth, signal strength and data transmission delay parameters in combination with the scene demand of the multi-terminal communication of the tourism, and generating a weight matrix; a resource demand calculation unit calculating the resource demand values of each device according to the parameter matrix and the weight matrix, the demand value being the sum of the products of each parameter and the corresponding weight, and obtaining a device resource demand list; a resource allocation unit obtaining the demand list of the resource demand calculation unit, combining the total resource amount of the multi-terminal communication of the tourism, allocating the resources according to the demand priority, generating an initial resource allocation scheme; a scheme verification unit receiving the initial resource allocation scheme, checking whether the scheme meets the minimum resource demand of each device, adjusting the weight and recalculating if the scheme does not meet the requirement, and transmitting the final scheme to the data interaction execution module.

[0014] Beneficial effects: the application proposes a multi-terminal fusion communication platform for tourism, which integrates spatio-temporal tourism behavior data to generate node sets through a tourism behavior graph modeling module, and realizes the correlation interpretation of behavior and demand by matching an intention analysis processing module, so as to accurately match the service demand of the multi-terminal equipment of tourists; the cross-device trust authentication module determines the level in combination with the device identifier and trust parameter, which can ensure the security of multi-terminal interaction; the multi-terminal parameter acquisition module comprehensively acquires data such as communication bandwidth and signal strength, and cooperates with the communication resource allocation module to dynamically adjust the allocation scheme, which can improve the resource utilization efficiency, and the data interaction execution module ensures stable transmission of multi-terminal data. The platform uses the demand result output by the intention analysis processing module and the trust parameter of the cross-device trust authentication module in linkage, and combines spatio-temporal tourism behavior data for authentication determination, so that the authentication result matches the demand of device use in the tourism scene, avoiding the situation that the authentication passes but the device cannot meet the transmission demand; in view of the fragmentation problem of multi-terminal communication parameter acquisition and resource allocation, the multi-terminal parameter acquisition module acquires comprehensive parameters related to device interaction, and the communication resource allocation module dynamically adjusts the weight and allocation scheme according to real-time parameters, rather than relying on fixed rules, which adapts to the dynamic communication demand of the device in the tourism process, reduces resource waste and transmission delay. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 The platform module composition diagram of the application is shown in the figure;

[0016] Figure 2 The platform running flowchart of the application is shown in the figure. DETAILED DESCRIPTION

[0017] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict, and the present application will be further described in detail in combination with the drawings and specific embodiments.

[0018] As shown in the figure, Figure 1 A multi-terminal fusion communication platform for tourism comprises:

[0019] The tourism behavior graph modeling module receives the multi-terminal device identifier information transmitted by the mobile communication cross-device trust chain construction platform, extracts the device-associated tourism trajectory data based on the spatio-temporal tourism behavior graph reasoning model, and generates a behavior graph node set;

[0020] Specifically, the tourism behavior graph modeling module is the basis for the platform to associate tourism behavior with communication needs. It receives multi-terminal device identification information transmitted by the mobile communication cross-device trust chain construction platform, extracts device-related tourism trajectory data based on the spatio-temporal tourism behavior graph reasoning model, and finally generates a set of behavior graph nodes. By integrating the trajectory information of multiple terminals, it provides structured behavior data support for subsequent intent analysis, and establishes a correspondence between device identification and tourism behavior to ensure that subsequent communication services can accurately match the behavior characteristics of the device owner. This module needs to maintain real-time data interaction with the mobile communication cross-device trust chain construction platform. The device identification information obtained needs to include device hardware number, software version, historical communication records, etc. Trajectory data includes geographic location, stay duration, and movement path of tourists at different time periods. The completeness of these data directly affects the accuracy of the behavior graph node set. In specific implementation, the module first receives the multi-terminal device identification information sent by the mobile communication cross-device trust chain construction platform, removes duplicates and formats the information, and filters out the device identification currently in active state, excluding invalid or offline device data. Then, it calls the spatio-temporal tourism behavior graph reasoning model to associate the filtered device identification with the corresponding tourism trajectory data and extract key features from the trajectory data, such as high-frequency activity areas from 9 am to 6 pm, long-distance trajectory segments with single movement exceeding 5 kilometers, and scenic locations with stay time exceeding 1 hour. Based on these features, the nodes of the behavior graph are constructed, each node including device identification, trajectory feature type, and time range corresponding to the feature. Meanwhile, the connection between nodes is established based on the chronological order and spatial correlation of the trajectory, forming a complete set of behavior graph nodes. After the node set is generated, it is transmitted to the intent analysis processing module to provide data basis for subsequent demand interpretation. The entire process needs to ensure the real-time data transmission, with the time from receiving device identification to outputting node set controlled within 10 seconds to meet the real-time service needs in tourism scenarios.

[0021] The intent analysis processing module obtains the node set output by the behavior graph modeling module, performs correlation operation on the trajectory features and tourism demand labels in the node set through the bidirectional association tourism intent analysis model, and outputs the intent analysis result.

[0022] Specifically, the intention analysis processing module plays a key role in converting behavior data into explicit needs. It obtains the node set output by the tourism behavior graph modeling module, performs correlation operations on the trajectory features and tourism demand labels in the node set through the bidirectional correlation tourism intention analysis model, and finally outputs the intention analysis result. Breaking the limitation of "only transmitting data without interpreting needs" in traditional communication, through the bidirectional correlation of trajectory features and demand labels, the potential communication needs of tourists are accurately identified, such as the need for high-definition picture transmission when staying at a scenic spot, the need for stable navigation data reception when moving long distances, etc., providing demand guidance for subsequent cross-device trust authentication and resource allocation. The module needs to pre-set a demand label library including tourism scenarios, including picture transmission, video call, navigation data, scenic introduction, catering reservation, etc. At the same time, it needs to establish the correlation rules between trajectory features and demand labels to ensure accurate matching of corresponding demand types during the operation process. In specific implementation, the module first receives the behavior graph node set transmitted by the tourism behavior graph modeling module, extracts the features of each node in the node set, determines the trajectory feature type and related parameters corresponding to each node, such as trajectory features with a stay duration of more than 1 hour and located in a scenic area, trajectory features with a moving speed of less than 5 km / h and surrounded by catering facilities, etc. Then, the bidirectional correlation tourism intention analysis model is called to perform correlation operations on the extracted trajectory features and the pre-set demand label library. During the operation process, the appearance frequency, duration, spatial correlation degree, etc. of the trajectory features need to be combined to determine the core demand label corresponding to each trajectory feature, for example, the high-frequency appearance of scenic area stay trajectory features is preferentially associated with "scenic introduction" and "picture transmission" demand labels, and long-distance moving trajectory features are preferentially associated with "navigation data" demand labels. After the operation is completed, the module sorts the demand labels and associated confidence levels corresponding to each device into the intention analysis result, with a confidence level of more than 80% to ensure the accuracy of demand interpretation, and then transmits the result to the cross-device trust authentication module to provide demand reference for device trust level determination.

[0023] The cross-device trust authentication module receives the analysis result of the intention analysis processing module, combines the device trust value parameters of the mobile communication cross-device trust chain construction platform, performs trust level determination on the multi-terminal devices, and outputs a list of devices that pass the authentication.

[0024] Specifically, the cross-device trust authentication module is the core link to ensure the security of multi-terminal communication. The function is to receive the analysis result of the intention analysis and processing module, combine the device trust value parameters of the mobile communication cross-device trust chain construction platform, and determine the trust level of the multi-terminal device. The output is a list of devices that pass the authentication. Avoiding the single dependence of traditional authentication on device identification, the authentication result meets the security standard and adapts to specific tourism needs by fusing the demand analysis result and the trust value parameter, preventing the occurrence of "safe but useless" authentication devices. At the same time, a cross-device trust system is built to improve the security and reliability of multi-terminal communication. The device trust value parameters obtained by the module from the mobile communication cross-device trust chain construction platform include historical communication success rate, data integrity, security vulnerability repair situation, and associated trust degree with other devices. These parameters need to be standardized to ensure that they can be directly used for trust level determination. In specific implementation, the module first receives the intention analysis result output by the intention analysis and processing module, extracts the device identification and corresponding demand label in the result, and clearly defines the communication demand type that each device needs to meet, such as devices that need to transmit high-definition pictures need to have high bandwidth stability, and devices that need to receive navigation data need to have low transmission delay. Then get the trust value parameters of these devices from the mobile communication cross-device trust chain construction platform, and quantitatively process the parameters, for example, convert the historical communication success rate into a score of 0-100, convert the data integrity according to the proportion of transmission data without loss into the corresponding score, convert the security vulnerability repair situation according to the repair timeliness rate into the corresponding score, and convert the associated trust degree according to the interaction frequency with high-trust devices into the corresponding score. Then, according to the demand label, set the weight of each trust value parameter, such as setting the weight of the bandwidth stability related parameter under the high-definition picture transmission demand to 40%, and setting the weight of the transmission delay related parameter under the navigation data receiving demand to 45%. The comprehensive trust score of each device is calculated by weighting. Set the trust score of 80 points or more as the high-trust level, 60-79 points as the medium-trust level, and 60 points or less as the low-trust level. The high-trust and medium-trust level devices are included in the authentication pass list, and the low-trust level devices are excluded. Finally, the list of devices that pass the authentication is transmitted to the multi-terminal parameter collection module, which includes device identification, trust level, and corresponding demand label.

[0025] The multi-terminal parameter collection module interfaces with the device list of the cross-device trust authentication module, collects the communication bandwidth, signal strength, and data transmission delay parameters of each device, and forms a parameter matrix.

[0026] Specifically, the multi-terminal parameter collection module is the premise of realizing accurate resource allocation. The function is to connect the device list of the cross-device trust authentication module, collect the communication bandwidth, signal strength, and data transmission delay parameters of each device, and form a parameter matrix. It makes up for the defects of incomplete and non-real-time parameter collection in traditional communication, collects parameters that are strongly related to tourism communication demand, provides accurate data support for subsequent resource allocation, ensures that resource allocation can adapt to the actual communication capacity of each device, and avoids resource mismatch caused by parameter loss. The module needs to use real-time collection technology to ensure that the parameters can reflect the current communication state of the device, and the collection frequency is set to once every 30 seconds. At the same time, it needs to have parameter anomaly detection capability to exclude abnormal parameters caused by temporary device failure and ensure the accuracy of the parameter matrix. In specific implementation, the module first receives the list of devices that pass the authentication from the cross-device trust authentication module, establishes communication connection with each device, and starts the collection process by sending parameter collection instructions. When collecting communication bandwidth, standard data packets are sent to the device, the transmission time and size of the data packets are recorded, the transmission volume per unit time is calculated, the real-time communication bandwidth is obtained, each collection is repeated 3 times, and the average value is taken as the final bandwidth parameter to ensure that the error is controlled within 5%; When collecting signal strength, the signal detection unit scans the communication frequency band currently used by the device, records the signal power value in the frequency band, converts it into a signal strength value, and at the same time excludes interference signals in the frequency band to ensure that the signal strength parameter can truly reflect the communication signal quality of the device; When collecting data transmission delay, a request signal with a timestamp is sent to the device, the time difference between the signal sending time and the feedback signal receiving time of the device is recorded, the maximum and minimum values are removed after multiple measurements, and the average value of the remaining values is taken as the data transmission delay parameter. After collection is completed, the communication bandwidth, signal strength, and data transmission delay parameters of each device are arranged into a parameter matrix in the order of the device list, each row of the matrix corresponds to three parameters of one device, and each column corresponds to different device values of the same parameter. Then the parameter matrix is transmitted to the communication resource allocation module.

[0027] The communication resource allocation module receives the parameter matrix of the multi-terminal parameter collection module, allocates weights to the parameters in the matrix according to the resource allocation rules of tourism multi-terminal communication, and outputs a resource allocation scheme.

[0028] Specifically, the communication resource allocation module is the core of optimizing the utilization of communication resources. The function is to receive the parameter matrix of the multi-terminal parameter acquisition module, allocate weights to the parameters in the matrix according to the resource allocation rules of multi-terminal communication in tourism, and output the resource allocation scheme. It breaks the traditional resource allocation mode of "equal allocation" or "fixed allocation", realizes dynamic and accurate allocation of resources by combining the device parameters and demand characteristics in the tourism scene, improves the resource utilization efficiency, and at the same time ensures that the key tourism communication demand can obtain priority resource support, such as sufficient bandwidth resources for tourists to shoot videos at scenic spots. The module needs to preset the resource allocation rules of multi-terminal communication in tourism, which includes the parameter weight corresponding to different demand labels, the allocation priority of the total amount of resources, the matching relationship between the communication capacity of the device and the amount of resource allocation, etc. In specific implementation, the module first receives the parameter matrix transmitted by the multi-terminal parameter acquisition module, combines the device demand label fed back by the cross-device trust authentication module to determine the core communication demand of each device, such as the device with the demand label of "video call", the communication bandwidth and signal strength are the core parameters, and the device with the demand label of "navigation data", the data transmission delay is the core parameter. Then set the weight of each parameter according to the resource allocation rules, for example, under the demand of "video call", the communication bandwidth weight is set to 50%, the signal strength weight is set to 35%, and the data transmission delay weight is set to 15%; under the demand of "navigation data", the data transmission delay weight is set to 55%, the communication bandwidth weight is set to 25%, and the signal strength weight is set to 20%. According to the weight, the weight calculation of each device parameter in the parameter matrix is carried out, and the resource demand score of each device is obtained, and the total amount of available communication resources is obtained, including the total bandwidth, signal coverage resources, and transmission channel quantity. According to the resource demand score from high to low, the devices are sorted, and the resources are allocated to the high-score devices first. In the allocation process, it needs to ensure that the amount of resources obtained by each device is not less than its minimum demand threshold, such as the minimum bandwidth demand of "video call" device is not less than 2Mbps, and the maximum delay demand of "navigation data" device is not more than 100ms. Finally, the resource allocation amount, the type of allocated resources, and the resource use duration of each device are sorted into a resource allocation scheme, which needs to specify the resource parameters corresponding to each device, and then the scheme is transmitted to the data interaction execution module.

[0029] The data interaction execution module is connected with the communication resource allocation module, establishes the communication link between the multi-terminal devices according to the allocation scheme, and transmits the tourism related data. The behavior graph modeling module, the intention analysis processing module, the cross-device trust authentication module, the multi-terminal parameter acquisition module, the communication resource allocation module, and the data interaction execution module sequentially transmit data and interact with control signals.

[0030] Specifically, the data interaction execution module is the final execution link for realizing multi-terminal data transmission. The function is to connect the communication resource allocation module, establish a communication link between multi-terminal devices according to the allocation scheme, and transmit tourism-related data. The resource allocation scheme is converted into actual communication behavior. Through the establishment of a stable communication link, it ensures that the tourism data can be transmitted efficiently according to the demand, and at the same time realizes the cooperative communication between multi-terminal devices, meets the diversified data interaction needs of tourists in the tourism process, such as photo sharing between multiple devices, navigation data synchronization, scenic spot information push, etc. The module needs to have link state monitoring capability, real-time detection of communication link bandwidth stability, signal strength change, data transmission delay fluctuation, etc. Once an abnormality is found, the adjustment mechanism can be started in time. In specific implementation, the module first receives the resource allocation scheme transmitted by the communication resource allocation module, extracts the device identifier, resource allocation amount, resource type, etc. in the scheme, determines the device pair and link parameters that need to establish a communication link, such as device A and device B need to establish a communication link with a bandwidth of 5Mbps and a delay of no more than 80ms for transmitting high-definition scenic spot photos; device C and device D need to establish a communication link with a signal strength of no less than -70dBm and a bandwidth of 2Mbps for synchronizing navigation data. Then according to the link parameters, select the appropriate communication protocol and transmission channel, such as high-definition photo transmission adopts a protocol that supports large file transmission, and navigation data synchronization adopts a low-delay protocol, and at the same time initialize the configuration of the transmission channel, set the bandwidth upper limit, delay threshold, data verification method and other parameters of the channel. After the configuration is completed, the link establishment request is sent to the related devices, and after the device confirmation response, the formal communication link is established, and the transmission process of the tourism-related data is started. During the transmission process, the module monitors the link state in real time, collects the actual bandwidth, signal strength, and transmission delay parameters of the link every 10 seconds. If it is found that the actual parameters exceed the threshold set in the scheme, such as the bandwidth is less than 80% of the allocation amount, the delay exceeds the set value by 120%, the resource allocation scheme is immediately fed back to the communication resource allocation module, and the resource allocation scheme is requested to be adjusted. After the scheme is updated, the link parameters are reconfigured to ensure that the data transmission continues to meet the needs.

[0031] Preferably, in the intention analysis processing module, the operation formula of the bidirectional associated tourism intention analysis model is: wherein, is the intention analysis result value, is the graph association weight coefficient, is the node feature vector output by the behavior graph modeling module, is the tensor product operator symbol, is the tourism demand label vector, is the device data weight coefficient, is the device trust vector of the mobile communication cross-device trust chain construction platform, is the dot product operator symbol, is a signal strength parameter vector of the multi-terminal parameter acquisition module; in the cross-device trust authentication module, a trust level determination formula is: wherein, is a device trust level value, is an authentication parameter weight coefficient, is a device identification matching degree parameter, is an exclusive or operator symbol, is a historical communication reliability parameter, is a communication parameter weight coefficient, is a communication bandwidth parameter, is a Hadamard product operator symbol, is a data transmission delay parameter.

[0032] Specifically, the requirement interpretation accuracy and authentication adaptability are improved by constructing the correlation operation and the trust level determination logic. In the intention analysis processing module, the operation logic combines the behavior graph node features and the tourism demand tags, and introduces a weight coefficient to adjust the influence proportion. In the scenic spot shooting scene, the graph correlation weight coefficient is set to 0.6, and the device data weight coefficient is set to 0.4. In the real-time navigation scene, they are set to 0.3 and 0.7 respectively, so as to ensure that the analysis result meets the scene requirements. The determination logic of the cross-device trust authentication module integrates parameters such as device identification matching degree and historical communication reliability. In the high-definition video transmission scene, the authentication parameter weight coefficient is set to 0.5, and the communication parameter weight coefficient is set to 0.5. In the real-time voice scene, they are set to 0.3 and 0.7 respectively. When implemented, first, the node feature vector, the device trust vector and other basic data output by the module are acquired, and then the operation is completed according to the set logic, and finally the result is used for device communication permission allocation. The whole process is controlled within 8 seconds from data acquisition to result output, ensuring real-time performance and making the output result accurately adapt to the requirements of demand matching and security authentication in multi-terminal communication in the tourism scene.

[0033] Preferably, in the multi-terminal parameter acquisition module, the parameter matrix generation formula is: wherein, is a multi-terminal parameter matrix, is a communication bandwidth parameter of the nth device, is a signal strength parameter of the nth device, is a data transmission delay parameter of the nth device, is a basic parameter weight, is a connection duration parameter of the nth device and the mobile communication cross-device trust chain construction platform, is a tourism data transmission frequency parameter of the nth device, is a trust chain correlation parameter weight; in the communication resource allocation module, the resource allocation scheme calculation formula is: wherein, is a resource allocation scheme vector, is a parameter weight matrix, is a corresponding element multiplication operator symbol, is a total resource vector of multi-terminal communication for tourism.

[0034] Specifically, in the multi-terminal parameter acquisition module, the parameter matrix generation logic combines the device basic communication parameters and the trust chain associated parameters, the basic parameter weight is set to 0.7, and the trust chain associated parameter weight is set to 0.3, wherein the basic parameters include communication bandwidth, signal strength, and data transmission delay, and the trust chain associated parameters include device and trust chain connection duration and tourism data transmission frequency; the scheme calculation logic of the communication resource allocation module is based on the parameter matrix, combined with the preset weight matrix and the total resource, the weight matrix includes communication bandwidth weight set to 0.4, signal strength set to 0.3, and data transmission delay set to 0.3, the current available total bandwidth is set to 100Mbps, and the transmission channel number is set to 20. When implemented, first collect each device parameter, such as device A bandwidth 20Mbps, signal strength-65dBm, delay 50ms, connection duration 3 hours, and transmission frequency 15 times / hour, generate a matrix according to the logic, and calculate and allocate the scheme by combining the weight and resource data, device A is allocated bandwidth 10Mbps and channel 2, which ensures that the scheme meets the device requirements and there is no resource waste, and the entire calculation process error is controlled within 5%.

[0035] Preferably, in the behavior graph modeling module, the behavior graph node set generation formula is: wherein, is a behavior graph node set matrix, is a device trajectory coordinate parameter matrix transmitted by the mobile communication cross-device trust chain construction platform, is a trajectory weight coefficient, is a matrix addition operator symbol, is a trajectory correlation degree parameter matrix output by the spatiotemporal tourism behavior graph reasoning model, is a correlation degree weight coefficient; in the data interaction execution module, the communication link transmission rate calculation formula is: wherein, is a link transmission rate value, is a resource allocation amount parameter output by the communication resource allocation module, is a resource conversion coefficient, is a signal strength average parameter of the multi-terminal parameter acquisition module, is a signal influence coefficient.

[0036] Specifically, in the multi-end parameter collection module, the parameter matrix generation logic combines the device basic communication parameters and the trust chain associated parameters, the basic parameter weight is set to 0.7, and the trust chain associated parameter weight is set to 0.3, wherein the basic parameters include communication bandwidth, signal strength, and data transmission delay, and the trust chain associated parameters include device connection duration and tourism data transmission frequency; the scheme calculation logic of the communication resource allocation module is based on the parameter matrix, combined with the preset weight matrix and the total amount of resources, the communication bandwidth weight in the weight matrix is set to 0.4, the signal strength is set to 0.3, and the data transmission delay is set to 0.3, the current available total bandwidth is set to 100Mbps, and the transmission channel number is set to 20. In implementation, first, the parameters of each device are collected, such as the bandwidth of device A is 20Mbps, the signal strength is-65dBm, the delay is 50ms, the connection duration is 3 hours, and the transmission frequency is 15 times / hour. After the matrix is generated according to the logic, the allocation scheme is calculated in combination with the weight and resource data, device A is allocated with a bandwidth of 10Mbps and 2 channels, which ensures that the scheme meets the device requirements and there is no resource waste, and the error of the entire calculation process is controlled within 5%.

[0037] Preferably, in the intention analysis processing module, the optimization formula of the bidirectional associated tourism intention analysis model is: wherein, is the optimized intention analysis result value, is the initial analysis result value, is the optimization coefficient, is the behavior graph node feature vector, is the dot product operator symbol, is the tourism demand label vector; in the cross-device trust authentication module, the trust chain update formula is: wherein, is the updated trust chain parameter, is the old trust chain parameter, is the update coefficient, is the historical communication reliability parameter, is the Hadamard product operator symbol, is the communication bandwidth parameter.

[0038] Specifically, in the intent analysis processing module, the optimization logic is based on the initial analysis result, combined with the behavior graph node features and demand label association data, and the optimization coefficient is set according to the initial confidence. When the confidence is 60%, the coefficient is set to 0.5, and when the confidence is 80%, the coefficient is set to 0.2, to ensure that the confidence after optimization is improved to more than 85%. The cross-device trust chain update logic is based on the old trust chain parameters, combined with the historical communication reliability and bandwidth association data, and the update coefficient is set according to the old parameter validity. When the validity is 70%, the coefficient is set to 0.4, and when the validity is 90%, the coefficient is set to 0.1. The old trust chain parameters need to include communication data in the past 7 days. When implementing, first obtain the initial analysis result confidence of device C as 70%, and the old trust chain parameter validity as 80%. Then collect the node feature and demand label association data overlap rate as 75%, the historical communication reliability as 90%, and the bandwidth stability as 85%. According to the logic, optimize the analysis result (the confidence is improved to 88%) and update the trust chain parameters (the validity is improved to 86%). The entire process of data collection time is controlled within 5 seconds, the optimization and update error is not more than 4%, and the result ensures the support of subsequent communication links.

[0039] Preferably, in the multi-terminal parameter acquisition module, the parameter anomaly detection formula is: wherein, is the parameter anomaly value, is the real-time acquired parameter matrix, is the historical parameter mean matrix, is the absolute value operator, is the anomaly detection weight; in the communication resource allocation module, the resource adjustment formula is: wherein, is the adjusted resource allocation scheme, is the initial allocation scheme, is the adjustment coefficient, is the parameter anomaly value vector, is the dot product operator, is the emergency parameter vector of the multi-terminal communication of tourism.

[0040] Specifically, in the multi-terminal parameter collection module, the abnormality detection logic compares the difference between the real-time parameters and the historical average value, the abnormality detection weight is set according to the parameter type, the data transmission delay weight is set to 0.5, the communication bandwidth is set to 0.3, and the signal strength is set to 0.2. The historical average value needs to be calculated for nearly 1 hour of data, updated once every 5 minutes, and the difference exceeding 20% is determined as abnormal; the adjustment logic of the communication resource allocation module is based on the initial scheme, combined with the abnormal value and the communication urgency, the adjustment coefficient is set according to the abnormal degree, the coefficient is set to 0.6 when the abnormality is 30%, and the coefficient is set to 0.3 when the abnormality is 10%. The urgency is set according to the data type, the navigation data urgency is set to 0.9, and the photo data is set to 0.5. When implemented, the device D real-time delay is collected 70ms, the historical average value is 50ms (the difference is 40%), and it is determined to be abnormal; the initial scheme is that the device D is allocated a bandwidth of 5Mbps, combined with the abnormal value and the navigation data urgency 0.9, the adjustment coefficient is set to 0.7, the adjusted bandwidth = 5x(1+0.7x(40%x0.9)) = 5x1.252 = 6.26Mbps, the adjustment process time is controlled within 4 seconds, the error is not more than 6%, the scheme is adapted to the current state of the device, and the communication stability is ensured.

[0041] Preferably, the cross-device trust authentication module comprises: a device identification verification unit, receiving the analysis result of the intention analysis processing module, extracting the hardware identification and software identification information of the multi-terminal device, comparing the identification information with the preset identification library of the mobile communication cross-device trust chain construction platform, screening out the devices with matched identification, and generating a matching result; a trust value calculation unit, obtaining the matching result of the device identification verification unit, calling the historical communication data of the mobile communication cross-device trust chain construction platform, calculating the communication success rate and data integrity parameters of the device, combining the preset trust algorithm, and obtaining the trust value of each device; a trust level division unit, receiving the trust value of the trust value calculation unit, dividing the device into high, medium and low trust levels according to the trust level threshold of the multi-terminal communication of the tourist, and outputting the level division result; an authentication result feedback unit, obtaining the level result of the trust level division unit, including the high and medium level devices in the authentication pass list, marking the low level devices as to be verified, and feeding back the authentication list to the multi-terminal parameter collection module.

[0042] Specifically, the cross-device trust authentication module includes four units of device identification verification, trust value calculation, trust level division, and authentication result feedback, and realizes hierarchical trust authentication to improve accuracy. After receiving the analysis result of the intent analysis processing module, the device identification verification unit extracts device hardware number, software version and other identification information, compares it with the preset identification library of the mobile communication cross-device trust chain construction platform, sets the matching degree threshold to 90%, and excludes devices below the threshold. The matching result is generated for the devices that pass the matching; the trust value calculation unit obtains the matching result, calls the historical communication data of the trust chain platform in the past 7 days, calculates the device communication success rate and data integrity parameters, the communication success rate is calculated according to the ratio of the number of successful transmissions to the total number of transmissions, and the data integrity is calculated according to the ratio of the amount of non-loss data to the total data., combined with the preset algorithm, the trust value is obtained by weighting the two parameters according to the weights of 60% and 40% respectively, and the trust value range is set to 0-100; the trust level division unit receives the trust value, and according to the trust level threshold of the multi-terminal communication of the tourism, sets 80 points and above as the high trust level, 60-79 points as the medium trust level, and 59 points and below as the low trust level. According to this standard, the device level is divided and the result is output; the authentication result feedback unit obtains the level result, and the high and medium level devices are included in the authentication pass list, and the low level devices are marked as to be verified. The authentication list is fed back to the multi-terminal parameter collection module, and the whole authentication process is controlled within 12 seconds from receiving the analysis result to feeding back the list, ensuring that it does not affect the subsequent parameter collection progress.

[0043] Preferably, the multi-terminal parameter collection module includes: a bandwidth collection unit connected to the authentication pass device list of the cross-device trust authentication module, sends a bandwidth detection instruction through the device communication interface, receives real-time bandwidth data feedback from the device, and performs sampling processing on the data to obtain the communication bandwidth parameters of each device; a signal strength collection unit uses a wireless signal detection module to scan the signal frequency band of the authentication pass device, collects the signal strength value under different frequency bands, calculates the mean value after removing the outliers, and generates the signal strength parameter; a delay collection unit sends a timestamp request signal to the authentication pass device, records the time difference between signal sending and receiving, takes the average after multiple measurements, and obtains the data transmission delay parameter; a parameter integration unit receives the parameters of the bandwidth collection unit, the signal strength collection unit and the delay collection unit, organizes the parameters according to the device number sequence, forms a multi-terminal parameter matrix, and transmits it to the communication resource allocation module.

[0044] Specifically, the multi-terminal parameter collection module includes bandwidth collection, signal strength collection, delay collection, and parameter integration four units, which realize comprehensive and accurate parameter collection. The bandwidth collection unit interfaces with the authentication passed device list of the cross-device trust authentication module, sends a bandwidth detection instruction through the device communication interface, the instruction sending interval is set to 5 seconds, after receiving the real-time bandwidth data feedback by the device each time, 5 times of continuous sampling are performed, the maximum value and the minimum value are removed, and the average value of the remaining 3 times of data is taken as the communication bandwidth parameter of the device, the error is controlled within ±2 Mbps; the signal strength collection unit scans the signal frequency band of the authentication passed device by using the wireless signal detection module, the scanning range covers 800MHz-2600MHz mainstream communication frequency band, 10 signal strength values are collected for each frequency band, the abnormal values exceeding the reasonable range of-40dBm to-110dBm are removed, and the average value of the remaining values is calculated as the signal strength parameter; the delay collection unit sends a time-stamped request signal to the authentication passed device, records the time difference between the signal sending time and the feedback signal receiving time, repeatedly measures 8 times, removes the abnormal values with a deviation exceeding 10ms, and takes the average value of the remaining 6 times of data as the data transmission delay parameter, the precision is controlled within ±1ms; after receiving the parameters of the three collection units, the parameter integration unit sorts the parameters according to the device number from small to large, arranges the communication bandwidth, signal strength, and data transmission delay parameters of each device correspondingly, forms a parameter matrix of multiple rows and three columns, and transmits the matrix to the communication resource allocation module within 3 seconds after the matrix is generated, to ensure the timeliness of the parameters.

[0045] Preferably, the communication resource allocation module includes: a parameter weight determination unit that receives the parameter matrix of the multi-terminal parameter collection module, determines the weight values of the communication bandwidth, signal strength, and data transmission delay parameters in combination with the scene requirements of the multi-terminal communication of the tourism, and generates a weight matrix; a resource demand calculation unit that calculates the resource demand values of each device according to the parameter matrix and the weight matrix, the demand value being the sum of the products of each parameter and the corresponding weight, and obtains a device resource demand list; a resource allocation unit that obtains the demand list of the resource demand calculation unit, allocates resources according to the demand priority in combination with the total resource amount of the multi-terminal communication of the tourism, generates an initial resource allocation scheme; a scheme verification unit that receives the initial resource allocation scheme, checks whether the scheme meets the minimum resource demand of each device, adjusts the weight and recalculates if the scheme does not meet the requirement, and transmits the final scheme to the data interaction execution module until the scheme meets the requirement.

[0046] Specifically, the communication resource allocation module comprises four units: parameter weight determination, resource demand calculation, resource allocation, and scheme verification, achieving dynamic and reasonable resource allocation. The parameter weight determination unit receives the parameter matrix from the multi-terminal parameter acquisition module and sets weights based on the needs of the tourism multi-terminal communication scenario. In the scenario of high-definition image transmission in scenic areas, the communication bandwidth weight is set to 50%, the signal strength weight to 30%, and the data transmission delay weight to 20%. In the scenario of real-time navigation, the data transmission delay weight is set to 55%, the communication bandwidth weight to 25%, and the signal strength weight to 20%, with the total weight fixed at 100%. The resource demand calculation unit, based on the parameter matrix and weight matrix, multiplies each parameter of each device by its corresponding weight and sums the results to obtain the device's resource demand value. The demand value ranges from 0 to 100, with higher values ​​indicating more urgent resource needs. The resource allocation unit obtains the list of demand values. Subsequently, based on the available multi-terminal communication resources for tourism, the total bandwidth is set to 200Mbps and the number of transmission channels is set to 30. The devices are sorted from high to low demand values, and resources are allocated to devices with high demand values ​​first. During allocation, it is ensured that each device receives a bandwidth of not less than 2Mbps and a transmission channel of not less than 1. After receiving the initial allocation scheme, the scheme verification unit checks whether the resources of each device meet the minimum demand threshold. If there are devices with a bandwidth of less than 2Mbps or fewer than 1 channel, the parameter weights are readjusted (the adjustment range does not exceed ±5%) and the allocation scheme is recalculated until all devices meet the minimum demand. The final scheme is transmitted to the data interaction execution module within 5 seconds to ensure the feasibility and rationality of resource allocation.

[0047] The spatiotemporal tourism behavior graph reasoning model is the core technical component of this invention for processing multi-device tourism trajectory data and constructing a behavior association graph. It integrates device spatiotemporal information with tourism behavior characteristics to form a structured behavior data system. In its implementation, the model first receives multi-device identification information transmitted from a mobile communication cross-device trust chain construction platform, filters out trajectory data corresponding to active devices, including spatiotemporal parameters such as the device's geographical location, dwell time, and movement path in the tourism scenario. Then, it extracts features from this data, identifying key behavioral features such as high-frequency activity areas, long-distance movement segments, and scenic spot stops. Based on the temporal order and spatial correlation between features, it constructs node connections, generating a behavior graph node set. Each node in the set includes information such as device identification, behavior feature type, and the corresponding time range, and the connection strength between nodes is determined by the behavioral correlation. The model transforms scattered device trajectory data into structured behavioral graphs, providing data support for subsequent intent analysis. It breaks through the limitations of traditional fragmented tourism behavior data, presenting the correspondence between devices and tourism behaviors in a graph-like manner, making subsequent demand interpretation more targeted. At the same time, it lays the behavioral data foundation for accurate adaptation of multi-terminal communication, ensuring that communication services can match the actual tourism behavior characteristics of tourists.

[0048] The bidirectional association tourism intent parsing model is a key technical tool in this invention for transforming behavioral data into demand. By establishing a bidirectional mapping relationship between tourism behavior characteristics and demand tags, it accurately identifies the communication needs of tourists across multiple devices. In implementation, the model first acquires the behavior graph node set output by the spatiotemporal tourism behavior graph inference model, extracting trajectory feature parameters from the node set, such as duration of stay at attractions, movement speed, and activity area type. Then, it calls a pre-set tourism demand tag library, with tags including image transmission, video calls, navigation data, and attraction introductions. Subsequently, through bidirectional association operations, the trajectory features are matched with the demand tags. On one hand, it infers possible demand types based on trajectory features; for example, if the duration of stay at an attraction exceeds one hour, it prioritizes associating the tags "image transmission" and "attraction introduction." On the other hand, it uses demand tags to verify the rationality of the trajectory feature matching and adjusts the association weights. Finally, it outputs the intent parsing result, including demand tags and association confidence levels. The confidence level needs to be controlled above 80% to ensure accuracy. The model's role is to transform behavioral data without clear demand orientation into clear communication requirements, providing demand guidance for cross-device trust authentication and resource allocation. It solves the problem of "only transmitting data without interpreting demands" in traditional communication, improves the accuracy of demand interpretation through bidirectional correlation, and makes subsequent device authentication and resource allocation more in line with the actual needs of tourism scenarios, avoiding the disconnect between communication services and tourists' needs.

[0049] The mobile communication cross-device trust chain construction platform is the fundamental technology platform in this invention for ensuring the communication security of multiple devices and providing trust parameter support. It establishes a device trust assessment system to form a trust association network covering multiple devices. In the implementation process, the platform first collects basic information about multiple devices, including hardware serial numbers, software versions, and historical communication records, to establish basic device profiles. Then, it performs real-time monitoring and data statistics on the devices' communication behavior, calculating trust-related parameters such as historical communication success rate, data integrity, security vulnerability remediation status, and frequency of interaction with other devices. The communication success rate is calculated as the ratio of successful transmissions to total transmissions, and data integrity is calculated as the ratio of the amount of data without loss to the total amount of data. Based on these parameters, a device trust value assessment system is constructed, quantifying the trust value of each device (range 0-100), and establishing trust chains based on the interaction relationships between devices. The trust level of a device in the trust chain is affected by the trust status of associated devices. Simultaneously, the platform regularly updates device trust parameters to ensure the timeliness of trust assessment. The platform's function is to provide trust value parameters for cross-device trust authentication modules, support device trust level determination, and make up for the shortcomings of traditional cross-device authentication that relies solely on a single identifier. Through multi-dimensional trust parameters and a trust chain system, it improves the security and adaptability of device authentication, avoids communication risks caused by untrusted devices accessing the network, and provides a trust foundation for the security and stability of multi-terminal communication, ensuring the reliability of data interaction in tourism scenarios.

[0050] like Figure 2As shown, a multi-terminal converged communication platform for tourism operates through different steps, including: First, the tourism behavior graph modeling module receives multi-terminal device identification information transmitted by the mobile communication cross-device trust chain construction platform, calls the spatiotemporal tourism behavior graph inference model to extract features and construct nodes for the tourism trajectory data associated with the devices, generates a behavior graph node set, and transmits the node set to the intent parsing processing module; Second, the intent parsing processing module receives the behavior graph node set, uses a bidirectional association tourism intent parsing model to perform association calculations on the trajectory features in the node set with preset tourism demand tags, generates intent parsing results, and sends the results to the cross-device trust authentication module; Third, the cross-device trust authentication module, combined with the device trust parameters of the mobile communication cross-device trust chain construction platform, determines the trust level of the multi-terminal devices corresponding to the intent parsing results. The process involves six steps: First, the system filters out a list of certified devices and transmits it to the multi-terminal parameter acquisition module. Second, the multi-terminal parameter acquisition module connects to the list of certified devices, collects communication bandwidth, signal strength, and data transmission delay parameters for each device, organizes these parameters into a parameter matrix, and sends the matrix to the communication resource allocation module. Third, the communication resource allocation module, based on the resource allocation rules for multi-terminal tourism communication, assigns weights to the parameters in the parameter matrix and calculates resource requirements, generating a resource allocation scheme, which is then transmitted to the data interaction execution module. Fourth, the data interaction execution module establishes communication links between the multi-terminal devices according to the resource allocation scheme, performs format conversion and grouping processing on tourism-related data, and realizes data interaction and transmission between the multi-terminal devices through the established links. Simultaneously, it monitors the link status in real time, and if any abnormalities occur, it feeds back to the communication resource allocation module for scheme adjustment.

[0051] A multi-terminal converged communication platform for tourism offers significant advantages in precise demand matching. By integrating spatiotemporal tourism behavior data and generating node sets through a tourism behavior graph modeling module, and combining this with an intent parsing module to interpret the correlation between behavioral characteristics and tourism demand tags, the platform can accurately capture service demands transmitted by tourists through multiple devices, avoiding service mismatches caused by ambiguous demand interpretation in traditional communication models. Addressing the disconnect between cross-device trust authentication and intent parsing in existing technologies, the platform links the demand results output by the intent parsing module with the device trust parameters of the cross-device trust authentication module, combining spatiotemporal tourism behavior data to determine trust levels. This ensures that authenticated devices not only meet security standards but also adapt to the transmission needs of specific tourism scenarios, completely resolving the mismatch between authentication results and actual needs.

[0052] The platform boasts significant advantages in communication security and resource utilization efficiency: The cross-device trust authentication module, combined with device trust parameters built from the mobile communication cross-device trust chain, classifies and classifies multi-device devices, effectively filtering out devices with security risks and ensuring the security of multi-device data interaction; the multi-device parameter acquisition module comprehensively acquires key data such as communication bandwidth, signal strength, and data transmission latency of each device, providing accurate basis for resource allocation; the communication resource allocation module then dynamically adjusts the allocation scheme based on this real-time data, significantly improving resource utilization efficiency. Addressing the shortcomings of existing technologies where parameter acquisition and resource allocation are separate, the platform achieves close collaboration between the multi-device parameter acquisition module and the communication resource allocation module. This allows resource allocation to move beyond fixed rules and adjust in real-time based on the dynamic communication parameters of devices during the travel process, avoiding both resource waste and delays in critical data transmission.

[0053] Furthermore, the platform demonstrates excellent stability in multi-device data transmission: the data interaction execution module establishes communication links based on the scheme output by the communication resource allocation module, while simultaneously monitoring the link status in real time. If any anomalies occur, they are promptly reported to the resource allocation module for scheme adjustments, ensuring the continuous and stable transmission of tourism-related data between multiple devices. This end-to-end dynamic monitoring and adjustment mechanism further compensates for the lack of flexible adaptability in traditional platforms during data transmission. Combined with the aforementioned advantages in demand matching, security authentication, and resource allocation, it forms an optimization system covering all aspects of multi-device communication, comprehensively improving the overall performance of multi-device converged communication in tourism scenarios.

[0054] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0055] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-terminal converged communication platform for tourism, characterized in that, include: The tourism behavior graph modeling module receives multi-terminal device identification information transmitted by the mobile communication cross-device trust chain construction platform, extracts tourism trajectory data associated with the devices based on the spatiotemporal tourism behavior graph inference model, and generates a behavior graph node set; the intent parsing processing module obtains the node set output by the behavior graph modeling module, performs association calculations on the trajectory features and tourism demand tags in the node set through a bidirectional association tourism intent parsing model, and outputs the intent parsing result. The cross-device trust authentication module receives the parsing result from the intent parsing processing module, combines it with the device trust value parameters of the mobile communication cross-device trust chain construction platform, determines the trust level of multiple devices, and outputs a list of authenticated devices. The multi-terminal parameter acquisition module connects to the device list of the cross-device trust authentication module and collects the communication bandwidth, signal strength, and data transmission delay parameters of each device to form a parameter matrix. The communication resource allocation module receives the parameter matrix from the multi-terminal parameter acquisition module, assigns weights to the parameters in the matrix according to the resource allocation rules for multi-terminal tourism communication, and outputs a resource allocation scheme. The data interaction execution module is connected to the communication resource allocation module. According to the allocation scheme, it establishes a communication link between multiple devices and transmits tourism-related data. The behavior graph modeling module, intent parsing and processing module, cross-device trust authentication module, multi-terminal parameter acquisition module, communication resource allocation module, and data interaction execution module sequentially perform data transmission and control signal interaction.

2. The multi-terminal converged communication platform for tourism according to claim 1, characterized in that, In the intent parsing processing module, the calculation formula for the bidirectional association tourism intent parsing model is as follows: ,in, The result value of the intent parsing, These are the graph association weighting coefficients. The node feature vectors output by the behavior graph modeling module. This is the tensor product operator. For tourism demand tag vectors, For equipment data weighting coefficients, The platform builds device trust vectors for cross-device trust chains in mobile communications. This is the dot product operator. The signal strength parameter vector of the multi-terminal parameter acquisition module; the trust level determination formula in the cross-device trust authentication module is: ,in, This represents the device trust level value. For the certification parameter weighting coefficients, For device identifier matching parameters, The XOR operator. Historical communication reliability parameters, These are the weighting coefficients for communication parameters. For communication bandwidth parameters, This is the Hadamard product operator. This is the data transmission delay parameter.

3. The multi-terminal converged communication platform for tourism according to claim 1, characterized in that, In the multi-terminal parameter acquisition module, the parameter matrix generation formula is: ,in, It is a multi-terminal parameter matrix. This refers to the communication bandwidth parameter of the nth device. Let n be the signal strength parameter of the nth device. Let n be the data transmission delay parameter for the nth device. Based on the weights of the basic parameters, The connection duration parameter for the nth device and the mobile communication cross-device trust chain platform. Let n be the frequency parameter for tourism data transmission of the nth device. The weights are the parameters associated with the trust chain; in the communication resource allocation module, the resource allocation scheme is calculated as follows: ,in, For resource allocation scheme vectors, For the parameter weight matrix, This is the element-wise multiplication operator. This is the total resource vector for multi-terminal communication in tourism.

4. The multi-terminal converged communication platform for tourism according to claim 1, characterized in that, In the behavior graph modeling module, the formula for generating behavior graph node sets is: ,in, For the behavior graph node set matrix, To construct a device trajectory coordinate parameter matrix for cross-device trust chain in mobile communications, For trajectory weighting coefficients, This is the matrix addition operator. The trajectory correlation parameter matrix output by the spatiotemporal tourism behavior graph inference model. The correlation weight coefficient is used; in the data interaction execution module, the communication link transmission rate is calculated as follows: ,in, This represents the link transmission rate value. The resource allocation parameters output by the communication resource allocation module. The resource conversion coefficient. This refers to the average signal strength parameter of the multi-terminal parameter acquisition module. This is the signal influence coefficient.

5. A multi-terminal converged communication platform for tourism according to claim 1, characterized in that, In the intent parsing processing module, the optimization formula for the bidirectional association tourism intent parsing model is: ,in, The optimized intent parsing result value. This is the initial parsing result value. To optimize the coefficients, These are the feature vectors of the behavior graph nodes. This is the dot product operator. The tag vector represents the travel demand; in the cross-device trust authentication module, the trust chain update formula is: ,in, For the updated trust chain parameters, For old trust chain parameters, To update the coefficients, Historical communication reliability parameters, This is the Hadamard product operator. This refers to the communication bandwidth parameter.

6. A multi-terminal converged communication platform for tourism according to claim 1, characterized in that, In the multi-terminal parameter acquisition module, the formula for parameter anomaly detection is: ,in, For abnormal parameter values, This is a parameter matrix acquired in real time. This is the historical parameter mean matrix. This is the absolute value operator. The weighting factor is used for anomaly detection; the resource adjustment formula in the communication resource allocation module is: ,in, The adjusted resource allocation plan, For the initial allocation scheme, To adjust the coefficient, For the parameter outlier vector, This is the dot product operator. This is a vector of urgency parameters for multi-terminal communication in tourism.

7. A multi-terminal converged communication platform for tourism according to claim 1, characterized in that, The cross-device trust authentication module includes: a device identifier verification unit, which receives the parsing result from the intent parsing processing module, extracts the hardware and software identifiers of multi-device devices, compares the identifier information with the preset identifier library of the mobile communication cross-device trust chain construction platform, filters out devices with matching identifiers, and generates a matching result; a trust value calculation unit, which obtains the matching result from the device identifier verification unit, calls the historical communication data of the mobile communication cross-device trust chain construction platform, calculates the communication success rate and data integrity parameters of the devices, and obtains the trust value of each device by combining a preset trust algorithm; a trust level division unit, which receives the trust value from the trust value calculation unit, divides the devices into three trust levels (high, medium, and low) according to the trust level threshold of multi-device communication in tourism, and outputs the level division result; and an authentication result feedback unit, which obtains the level result from the trust level division unit, includes high and medium level devices in the authentication pass list, marks low level devices as pending verification, and feeds the authentication list back to the multi-device parameter acquisition module.

8. A multi-terminal converged communication platform for tourism according to claim 1, characterized in that, The multi-terminal parameter acquisition module includes: a bandwidth acquisition unit, which interfaces with the list of authenticated devices in the cross-device trust authentication module, sends bandwidth detection commands through the device communication interface, receives real-time bandwidth data from the devices, samples and processes the data to obtain the communication bandwidth parameters of each device; a signal strength acquisition unit, which uses a wireless signal detection module to scan the signal frequency bands of authenticated devices, collects signal strength values ​​in different frequency bands, removes outliers, calculates the average, and generates signal strength parameters; a delay acquisition unit, which sends a timestamp request signal to authenticated devices, records the time difference between signal transmission and reception, and takes the average after multiple measurements to obtain data transmission delay parameters; and a parameter integration unit, which receives parameters from the bandwidth acquisition unit, signal strength acquisition unit, and delay acquisition unit, organizes the parameters according to the device number order, forms a multi-terminal parameter matrix, and transmits it to the communication resource allocation module.

9. A multi-terminal converged communication platform for tourism according to claim 1, characterized in that, The communication resource allocation module includes: a parameter weight determination unit, which receives the parameter matrix from the multi-terminal parameter acquisition module, determines the weight values ​​of communication bandwidth, signal strength, and data transmission delay parameters based on the scenario requirements of multi-terminal tourism communication, and generates a weight matrix; a resource requirement calculation unit, which calculates the resource requirement value of each device based on the parameter matrix and the weight matrix, where the requirement value is the sum of the products of each parameter and its corresponding weight, and obtains a device resource requirement list; a resource allocation unit, which obtains the requirement list from the resource requirement calculation unit, allocates resources according to requirement priority based on the total resource volume of multi-terminal tourism communication, and generates an initial resource allocation scheme; and a scheme verification unit, which receives the initial resource allocation scheme, checks whether the scheme meets the minimum resource requirements of each device, and if not, adjusts the weights and recalculates until the scheme meets the requirements, and then transmits the final scheme to the data interaction execution module.

Images