A tourism information management method based on a service type collaborative robot

Abstract

The application discloses a kind of tourism information management methods based on service type collaborative robot, it is related to federal learning technical field, including, tourist identity is bound with service type collaborative robot sandbox, generates tourist mirror image set;Tourist mirror image set is input into geographic fence detector, combines real-time geographic coordinate and compares electronic grid map, and the operation signal and buffer zone signal of crossing boundary signal are output through physical isolation double channel;Based on buffer zone operation signal triggers service type collaborative robot to generate privacy gradient parameter set;Federal encryption box receives privacy gradient parameter set and is converted into gear coding sequence output;If geographic fence detector outputs crossing boundary signal, then trigger physical fuse destroys tourist mirror image set.The application realizes the dynamic generation of personalized service parameters based on tourist identity characteristics by executing model training iteration on initial service label in service type collaborative robot local privacy sandbox.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of federated learning, and particularly relates to a tourism information management method based on a service-type collaborative robot. BACKGROUND

[0002] In the application scenario of deep integration of service-type robots and intelligent information management, the data privacy protection and dynamic service response mechanism in the multi-agent collaborative environment are facing systematic challenges; with the wide penetration of distributed computing architecture in the public service industry, how to realize the precise scheduling and trusted interaction of cross-domain service resources while ensuring that the user identity information is not traceable has become a core issue to improve the intelligent service level; therefore, constructing a collaborative management mechanism with physical-level isolation capability, supporting dynamic strategy generation and complying with privacy compliance constraints has become a key technical path to realize autonomous and trusted decision-making of service-type robots.

[0003] The existing tourism information management system mostly adopts an architecture based on location-based service (LBS) and central server interaction, and realizes attraction recommendation or path planning by reporting coordinates on a mobile terminal; this usually relies on continuous authorization of user location data, which has a privacy exposure risk and lacks effective support for local decision-making capability of service robots. To alleviate the privacy problem, some solutions introduce differential privacy or anonymization processing technology, but this easily leads to decreased service accuracy or increased response delay, making it difficult to balance security and efficiency. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a tourism information management method based on a service-type collaborative robot to solve the problem of privacy exposure risk.

[0006] To solve the above technical problems, the present application provides the following technical solutions.

[0007] In a first aspect, the present application provides a tourism information management method based on a service-type collaborative robot, which comprises:

[0008] binding the tourist identity with the service-type collaborative robot sandbox to generate a tourist mirror set;

[0009] inputting the tourist mirror set into a geofence detector, comparing an electronic raster map with real-time geographic coordinates, and outputting a buffer zone operation signal and a boundary crossing signal through a physically isolated double-channel; based on the buffer zone operation signal, triggering the service-type collaborative robot to generate a privacy gradient parameter set;

[0010] the federated encryption box receives the privacy gradient parameter set and converts it into a gear encoding sequence output; if the geofence detector outputs a boundary crossing signal, a physical fuse is triggered to destroy the tourist mirror set;

[0011] The gear code sequence is input into the federal aggregation core to generate a federal global parameter through weighted aggregation; after the federal global parameter is received by the tourist service center, a strategy execution instruction is generated through analysis and processing.

[0012] As a preferred scheme of the tourism information management method based on the service-type collaborative robot, the tourist identity is bound to the service-type collaborative robot sandbox, and the binding is specifically as follows:

[0013] The passport information page of the tourist is scanned by the optical character recognition component built in the service-type collaborative robot;

[0014] The name, nationality, passport number and birth date of the tourist are extracted from the passport information page;

[0015] The service-type collaborative robot starts a privacy sandbox, and performs one-way hash processing on the extracted name, nationality, passport number and birth date of the tourist to generate a unique identity code;

[0016] The generated unique identity code is written into the isolated storage area of the privacy sandbox to establish the binding relationship between the tourist identity and the service-type collaborative robot sandbox.

[0017] As a preferred scheme of the tourism information management method based on the service-type collaborative robot, the tourist mirror set is generated, and the generation is specifically as follows:

[0018] The preset service preference template is called, the default language, common payment method and basic tour type are loaded according to the extracted nationality, and the initial service label is formed;

[0019] The initial service label and the unique identity code are stored in the isolated storage area of the privacy sandbox to generate the tourist mirror set.

[0020] As a preferred scheme of the tourism information management method based on the service-type collaborative robot, the tourist mirror set is input into the geofence detector, and the real-time geographic coordinates are compared with the national boundary line coordinate range in the electronic grid map pre-stored in the local geofence detector, and the physical isolated double-channel output buffer band operation signal and the out-of-boundary signal are generated, and the generation is specifically as follows:

[0021] The geofence detector compares the associated real-time geographic coordinates with the national boundary line coordinate range pre-stored in the local electronic grid map in the geofence detector;

[0022] If the real-time geographic coordinates are located within five kilometers outside the national boundary line coordinate range, the buffer band operation signal is generated;

[0023] If the real-time geographic coordinates fall into the area on the opposite side of the national boundary line coordinate range, the out-of-boundary signal is generated;

[0024] The buffer zone operation signal and the out-of-bound signal are output respectively through physical isolation.

[0025] As a preferred scheme of the tourism information management method based on the service-type collaborative robot, the service-type collaborative robot generates a privacy gradient parameter set based on the buffer zone operation signal, and the specific process is as follows.

[0026] The service-type collaborative robot receives the buffer zone operation signal from the geofence detector, and starts the service preference model in the local privacy sandbox.

[0027] The initial service label of the tourist mirror image set is input into the service preference model, and a local training iteration is performed.

[0028] After the training is completed, the service preference model parameters are stored in the local privacy sandbox built in the service-type collaborative robot.

[0029] The service-type collaborative robot reads the service preference model parameters before the local training iteration and the service preference model parameters after the local training iteration from the local privacy sandbox, and extracts the update content of the language preference layer weight, the payment method preference layer weight, and the tour type preference layer weight, to generate a privacy gradient parameter set.

[0030] As a preferred scheme of the tourism information management method based on the service-type collaborative robot, the federal encryption box receives the privacy gradient parameter set and converts it into a gear encoding sequence output, and the specific process is as follows.

[0031] The federal encryption box receives the privacy gradient parameter set from the service-type collaborative robot.

[0032] The language preference layer weight, the payment method preference layer weight, and the tour type preference layer weight in the privacy gradient parameter set are arranged in order of the respective preference layer weights to form a gradient parameter sequence.

[0033] According to the size of the value of each preference layer weight in the gradient parameter sequence, the language preference layer weight, the payment method preference layer weight, and the tour type preference layer weight are mapped to a preset scale interval of the mechanical encoding disc.

[0034] The federal encryption box drives the mechanical encoding disc to rotate to the corresponding scale position, and outputs the corresponding gear encoding sequence through the linkage of the physical gear set of the mechanical encoding disc.

[0035] As a preferred scheme of the tourism information management method based on the service-type collaborative robot, if the geofence detector outputs the out-of-bound signal, the physical fuse destroys the tourist mirror image set, and the specific process is as follows.

[0036] The out-of-bound signal is transmitted to the storage center of the tourist mirror set through a special channel isolated physically;

[0037] The storage center of the tourist mirror set receives the out-of-bound signal and immediately starts the built-in physical fuse;

[0038] The physical fuse performs a mechanical deformation action to destroy the magnetic recording layer in the storage center of the tourist mirror set, so that the tourist mirror set is irreparably destroyed.

[0039] As a preferred scheme of the tourism information management method based on the service type collaborative robot, the gear code sequence is input into the federal aggregation core to generate a federal global parameter through weighted aggregation, and the specific process is as follows:

[0040] The federal aggregation core obtains gradient parameter sequences from multiple service type collaborative robots, and determines a weighting coefficient according to the tourist service frequency of each service type collaborative robot;

[0041] The weight update values of the language preference layer, the payment method preference layer and the tour type preference layer are accumulated according to the weighting coefficient to generate updated layer parameters;

[0042] The updated layer parameters of each preference layer are combined to form a federal global parameter.

[0043] As a preferred scheme of the tourism information management method based on the service type collaborative robot, after the federal global parameter is received by the tourist service center, a strategy execution instruction is generated through analysis and processing, and the specific process is as follows:

[0044] The tourist service center receives the federal global parameter, and reads the weight values of the language preference layer, the payment method preference layer and the tour type preference layer in the federal global parameter through an internal analysis structure;

[0045] The weight values of each preference layer are matched with a preset judgment condition table to determine corresponding service strategy configuration items;

[0046] The service strategy configuration items are converted into specific strategy execution instructions and sent to the control end of the service type collaborative robot.

[0047] As a preferred scheme of the tourism information management method based on the service type collaborative robot, the service strategy configuration item is a specific service setting defined by the service type collaborative robot, including configuration options of language preference, payment method preference and tour type preference, guiding the service type collaborative robot to perform corresponding service operations.

[0048] The application has the beneficial effects that: by performing model training iteration on the initial service label in the service-type collaborative robot local privacy sandbox, the personalized service parameter dynamic generation based on the tourist identity characteristics is realized. The pre-trained service preference model is used to adjust the weight of the default language, common payment method and basic tour type in the initial service label, and the service preference model parameter update is completed; after the service preference model completes the training locally, the weight update content between the service preference model parameters before the local training iteration and the service preference model parameters after the local training iteration is extracted, the privacy gradient parameter set is generated, the original identity information of the tourist and the initial service label are ensured not to leave the privacy sandbox, the data privacy security is ensured, and subsequent federal aggregation is supported to check the privacy gradient parameter sets from multiple service-type collaborative robots for weighted aggregation, and the individualization, safety and collaborative efficiency of the service strategy generation in the tourism information management are improved. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0050] Fig. 1 Flowchart of the tourism information management method based on the service-type collaborative robot.

[0051] Fig. 2 Flowchart of the geographic fence and double-channel branch.

[0052] Fig. 3 Flowchart of the service preference model and the privacy gradient parameter set.

[0053] Fig. 4 Flowchart of the tourist service center analysis and strategy execution instruction. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings of the specification.

[0055] In the following description, many specific details are set forth in order to provide a thorough understanding of the application, but the application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the application, therefore the application is not limited to the specific embodiments disclosed below.

[0056] Second, the "one embodiment" or "an embodiment" referred to herein can include a particular feature, structure, or characteristic. The various embodiments appearing at different places in this specification can not all refer to the same embodiment or to the same implementations or alternatives of the same implementation.

[0057] Referring to Figs. 1-4 For one embodiment of the present application, the embodiment provides a tourism information management method based on a service-type collaborative robot, comprising the following steps:

[0058] S1, binding the tourist identity with the service-type collaborative robot sandbox to generate a tourist mirror set.

[0059] S1.1, scanning the passport information page of the tourist through the optical character recognition component built in the service-type collaborative robot, extracting the tourist's name, nationality, passport number and date of birth from the passport information page;

[0060] The service-type collaborative robot starts the local privacy sandbox, and performs one-way hash processing on the extracted tourist's name, nationality, passport number and date of birth to generate a unique identity code; wherein the local privacy sandbox is an isolated data processing space inside the service-type collaborative robot, which is used for safe storage and processing of tourist data, and is based on existing privacy protection technology (such as sandbox isolation);

[0061] Specifically, in the privacy sandbox, a SHA-256 hash function is started to perform one-way hash processing on the extracted tourist's name, nationality, passport number and date of birth: first, the tourist's name, nationality, passport number and date of birth are spliced into a string in order (such as the field arrangement order of the passport information page), for example, the tourist's name, nationality, passport number and date of birth are connected in turn, separated by a separator "|", to form a complete input string; then, the complete input string is input into the SHA-256 hash function, and the SHA-256 hash function performs one-way conversion on the input string to generate a fixed-length 256-bit hash value; the 256-bit hash value is stored as a unique identity code in the isolated storage area of the local privacy sandbox, and is used for subsequent binding of the tourist identity and the service-type collaborative robot sandbox.

[0062] S1.2, write the generated unique identity code to the isolated storage area of the privacy sandbox to establish the binding relationship between the tourist identity and the service-type collaborative robot sandbox;

[0063] Specifically, first, a unique record entry is created in the isolated storage area for storing the unique identity code, and the record entry takes the unique identity code as the primary key; then, the unique identity code is associated with the internal identifier of the service collaborative robot sandbox, the internal identifier is a fixed string of the service collaborative robot sandbox, and is used to identify the current service collaborative robot sandbox entity; then, in the record entry of the isolated storage area, a key-value pair is added to map the unique identity code to the internal identifier of the service collaborative robot sandbox, forming a binding relationship; finally, the record entry is saved to the isolated storage area to ensure the persistence of the association between the unique identity code and the internal identifier of the service collaborative robot sandbox, which is used for subsequent generation of the tourist mirror set;

[0064] The preset service preference template is called to load the default language, common payment method and basic guide type according to the extracted nationality to form an initial service label;

[0065] Specifically, first, the nationality information extracted from the passport information page is read from the isolated storage area; then, the service preference template preset in the service collaborative robot sandbox is accessed, the service preference template is a preset mapping table, which is set based on the statistical data of nationality and common tourism service demand, and contains the correspondence between nationality and default language, common payment method and basic guide type, for example, the nationality "China" corresponds to the default language "Chinese", the common payment method is "mobile payment", and the basic guide type is "historical and cultural guide"; according to the nationality information, the corresponding default language, common payment method and basic guide type are found in the service preference template, and the matched entries are extracted; then, the extracted default language, common payment method and basic guide type are combined into a structured data set, named initial service label.

[0066] S1.3, the initial service label is associated with the generated unique identity code for storage in the isolated storage area of the privacy sandbox, and a tourist mirror set is generated.

[0067] S2, the tourist mirror set is input into the geofence detector, and the real-time geographic coordinates are compared with the electronic grid map, and the physical isolation double-channel output buffer band operation signal and the out-of-boundary signal are output; based on the buffer band operation signal, the service collaborative robot generates a privacy gradient parameter set.

[0068] S2.1, the service collaborative robot starts the built-in positioning component to collect real-time geographic coordinates, and the real-time geographic coordinates include latitude and longitude data.

[0069] S2.2, the geofence detector receives the tourist mirror set and receives the real-time geographic coordinates from the service collaborative robot, and associates the real-time geographic coordinates with the unique identity code in the tourist mirror set with a timestamp;

[0070] The geofence detector compares the associated real-time geographic coordinates with the national boundary line coordinate range in the electronic grid map pre-stored locally in the geofence detector; wherein the electronic grid map is a digitized map pre-stored locally in the geofence detector, used to store the national boundary line coordinate range, and the geofence detector judges the region where the real-time geographic coordinates are located by comparing the real-time geographic coordinates with the national boundary line coordinate range;

[0071] If the real-time geographic coordinates are located within a five-kilometer range outside the national boundary line coordinate range, a buffer zone operation signal is generated;

[0072] If the real-time geographic coordinates fall into the opposite side region of the national boundary line coordinate range (i.e. the geographic region on the other side of the border line, for example, if the border line is a national boundary, the opposite side region of the national boundary line coordinate range is the geographic range of the neighboring country or region on the other side of the border line), a crossing signal is generated;

[0073] The buffer zone operation signal and the crossing signal are respectively output through physically isolated double channels;

[0074] Specifically, first, the geofence detector confirms the generated buffer zone operation signal and crossing signal; then, the geofence detector transmits the buffer zone operation signal to the physically isolated first channel, which is an independent signal transmission line, and is only used to transmit the buffer zone operation signal to the service-type collaborative robot to trigger subsequent operations; next, the geofence detector transmits the crossing signal to the physically isolated second channel, which is another independent signal transmission line, and is only used to transmit the crossing signal to the tourist mirror image set storage center to trigger the physical fuse; finally, the buffer zone operation signal is transmitted to the service-type collaborative robot through the first channel, and the crossing signal is transmitted to the tourist mirror image set storage center through the second channel, ensuring that the output processes of the signals (the buffer zone operation signal and the crossing signal) are isolated and do not interfere with each other;

[0075] It should be noted that by comparing the real-time geographic coordinates with the national boundary line coordinate range in the electronic grid map, the buffer zone operation signal and the crossing signal are generated and output through physically isolated double channels; compared with the lack of privacy protection and dynamic response capability in the prior art, this step uses physically isolated double channels to output the buffer zone operation signal and the crossing signal, ensuring that the signal transmission is isolated and does not interfere with each other, triggering the local training of the service-type collaborative robot or the destruction of the tourist mirror image set, improving the data security and real-time performance, and solving the defects of location data leakage and response lag.

[0076] S2.3, the geofence detector forwards the initial service label in the tourist mirror image set to the service-type collaborative robot;

[0077] The service-type collaborative robot receives the buffer zone operation signal from the geofencing detector, and starts a service preference model in a local privacy sandbox.

[0078] S2.4, input the initial service tag in the tourist mirror set into the service preference model, and perform a local training iteration;

[0079] Specifically: first, read the initial service tag in the tourist mirror set from the isolated storage area, the initial service tag contains the preference data of default language, common payment method and basic tour type; then, the initial service tag is used as the input data of the service preference model, the service preference model is a pre-trained neural network, which includes language preference layer, payment method preference layer and tour type preference layer; then, the service preference model adjusts the language preference layer weight, payment method preference layer weight and tour type preference layer weight according to the preference data of the initial service tag, completes a weight update process, and forms updated service preference model parameters; finally, the updated service preference model parameters are stored in the local privacy sandbox for subsequent generation of privacy gradient parameter set;

[0080] Service preference model training process:

[0081] The service preference model is a pre-trained neural network, and the initial training process is completed before the deployment of the service-type collaborative robot; the training data is derived from tourism service historical data, including language preference, payment method preference and tour type preference of tourists of different nationalities; the gradient descent method is used to adjust the weights of language preference layer, payment method preference layer and tour type preference layer multiple times: first, input the tourist service preference data set in the tourism service historical data into the service preference model, the tourist service preference data set includes the default language, common payment method and basic tour type data of tourists of different nationalities; then, the service preference model adjusts the language preference layer weight, payment method preference layer weight and tour type preference layer weight layer by layer according to the tourist service preference data set, and gradually updates the weight value by comparing the difference between the predicted output and the actual preference data each time; then, repeat this adjustment process multiple times until the weight value tends to be stable, forming the initial service preference model parameters;

[0082] After training, the service preference model parameters are stored in the local privacy sandbox built in the service-type collaborative robot, supporting subsequent local training iteration based on the initial service tag;

[0083] The service-type collaborative robot reads the service preference model parameters before local training iteration and the service preference model parameters after local training iteration from the local privacy sandbox, extracts the update content of the language preference layer weight, payment method preference layer weight and tour type preference layer weight, generates a privacy gradient parameter set, and transmits it to the federal encryption box built in the service-type collaborative robot;

[0084] Specifically: first, read the service preference model parameters before local training iteration and the service preference model parameters after local training iteration from the isolated storage area of the local privacy sandbox, the service preference model parameters include the numerical values of the language preference layer weight, the payment method preference layer weight and the tour type preference layer weight; then, compare the service preference model parameters before local training iteration and the service preference model parameters after local training iteration, extract the change values of the language preference layer weight, the payment method preference layer weight and the tour type preference layer weight before and after iteration, and form a weight update content set; then, arrange the language preference layer weight change value, the payment method preference layer weight change value and the tour type preference layer weight change value in the weight update content set in the order of the language preference layer, the payment method preference layer and the tour type preference layer, and generate a privacy gradient parameter set; finally, through the internal data interface built in the service collaborative robot, the privacy gradient parameter set is transmitted to the federal encryption box built in the service collaborative robot for subsequent processing.

[0085] S2.5、It should be noted that this step uses machine learning technology to perform local training iteration of the service preference model to generate a privacy gradient parameter set; compared with the deficiencies of data privacy leakage, personalized service response lag and lack of dynamic scene adaptation in the prior art of applying machine learning in tourism information management, this step innovatively combines geographic fence and federal learning mechanism, protects the safety of tourist data through the local privacy sandbox environment, avoids the transmission of raw data; uses real-time location monitoring of the geographic fence to dynamically trigger local training, ensuring that the service preference model adjusts quickly according to the real-time location of the tourists; generates a privacy gradient parameter set through federal learning to realize multi-robot collaborative optimization of service strategy; solves the defects of easy leakage of tourist data, inability of personalized service to adapt to dynamic scenes in real time and low efficiency of cross-device collaboration in the prior art, and improves the privacy protection capability, real-time response capability and collaboration efficiency of tourism information management.

[0086] S3、The federal encryption box receives the privacy gradient parameter set and converts it into a gear code sequence output; if the geographic fence detector outputs an out-of-bound signal, a physical fuse is triggered to destroy the tourist mirror set.

[0087] S3.1、The federal encryption box receives the privacy gradient parameter set from the service collaborative robot;

[0088] Arrange the language preference layer weight, the payment method preference layer weight and the tour type preference layer weight in the privacy gradient parameter set in the order of the respective preference layer weights to form a gradient parameter sequence;

[0089] According to the size of the weight value of each preference layer in the gradient parameter sequence, the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight are mapped to the preset scale interval of the mechanical coding disc;

[0090] Specifically, first, the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight in the gradient parameter sequence are read, and the weight value is in the form of a floating point number; then, the value of the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight is compared with the preset scale interval of the mechanical coding disc, the preset scale interval of the mechanical coding disc is set based on the weight value range of the language preference layer, the payment method preference layer and the guide type preference layer, and is a fixed value range list, for example, the language preference layer weight corresponds to the scale interval 0 to 100, the payment method preference layer weight corresponds to the scale interval 101 to 200, and the guide type preference layer weight corresponds to the scale interval 201 to 300; then, according to the size of the weight value of each preference layer, it is determined that the language preference layer weight value corresponds to the scale interval 0 to 100, the payment method preference layer weight value corresponds to the scale interval 101 to 200, and the guide type preference layer weight value corresponds to the scale interval 201 to 300, for example, if the language preference layer weight value falls within the interval 0 to 100, it is mapped to a specific scale position within the scale interval 0 to 100 corresponding to the language preference layer weight value; finally, the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight are respectively mapped to the corresponding scale interval of the mechanical coding disc, and the mapping process is completed.

[0091] The federal encryption box drives the mechanical coding disc to rotate to the corresponding scale position, and outputs the corresponding gear coding sequence through the linkage of the physical gear set of the mechanical coding disc;

[0092] Specifically, first, the federal encryption box receives the mapped mechanical scale interval positions of the language preference layer weight, the payment method preference layer weight, and the guide type preference layer weight, for example, the language preference layer weight is mapped to a specific position within the scale interval 0 to 100, the payment method preference layer weight is mapped to a specific position within the scale interval 101 to 200, and the guide type preference layer weight is mapped to a specific position within the scale interval 201 to 300; then, the federal encryption box starts the internal motor, and according to the scale positions of the language preference layer weight, the payment method preference layer weight, and the guide type preference layer weight, respectively drives the mechanical code disc to rotate to the corresponding scale point; next, the rotating action of the mechanical code disc is transmitted through the physical gear set, the physical gear set is composed of multiple gears, and the rotating action is converted into a gear rotation sequence according to the preset gear tooth ratio; finally, the rotation sequence of the physical gear set is recorded as a gear code sequence, the gear code sequence represents the combination of the scale position in binary form, which is used for subsequent transmission to the central aggregation node; wherein, the gear tooth ratio is set based on the range of the mechanical code disc scale interval, for example, the language preference layer weight corresponds to a gear tooth ratio of 1:1, the payment method preference layer weight is 1:2, and the guide type preference layer weight is 1:3;

[0093] The gear code sequence is transmitted to the central aggregation node through the special communication interface of the federal encryption box in the form of a differential signal through a shielded cable; wherein, the differential signal is a communication method that transmits opposite electrical signals through two signal lines to reduce interference; the shielded cable is a cable wrapped with a metal shielding layer to prevent external electromagnetic interference from affecting signal transmission.

[0094] S3.2, the geographic fence detector continuously monitors the real-time geographic coordinates of the tourists, and if the real-time geographic coordinates fall into the region on the opposite side of the national boundary line coordinate range, an out-of-bound signal is generated;

[0095] The out-of-bound signal is transmitted to the storage center of the tourist mirror set through a physically isolated special channel;

[0096] After the storage center of the tourist mirror set receives the out-of-bound signal, the built-in physical fuse is immediately started;

[0097] The physical fuse performs a mechanical deformation action to destroy the magnetic recording layer in the storage center of the tourist mirror set, causing the tourist mirror set to be irrecoverably destroyed;

[0098] Specifically, first, the physical fuse receives the out-of-bound signal from the geofencing detector, triggering the internal mechanical switch to activate; then, the mechanical switch activates the spring drive mechanism in the physical fuse, which releases the pre-stored mechanical force to push a set of metal cutting blades to move; next, the metal cutting blades directly act on the magnetic recording layer of the tourist mirror image set storage center, which is the physical medium for storing the tourist mirror image set, such as the magnetic coating of a disk; the metal cutting blades destroy the structure of the magnetic recording layer through physical cutting or extrusion, making the stored tourist mirror image set data completely unreadable or recoverable; finally, after the physical fuse completes the action, the magnetic recording layer is permanently damaged, ensuring that the tourist mirror image set is irrecoverably destroyed.

[0099] S4. Input the gear encoding sequence into the federal aggregation core to generate federal global parameters through weighted aggregation; the tourist service center receives the federal global parameters and generates strategy execution instructions after parsing and processing.

[0100] S4.1, the central aggregation node receives the gear encoding sequence transmitted through the shielded cable;

[0101] The gear encoding sequence is parsed by the photoelectric sensor array in the central aggregation node to restore the corresponding gradient parameter sequence;

[0102] Specifically, first, the central aggregation node receives the gear encoding sequence transmitted through the shielded cable, which represents the scale position combination of language preference layer weight, payment method preference layer weight and guide type preference layer weight in binary form; then, the photoelectric sensor array scans the gear encoding sequence to identify the high and low state of each binary bit in the gear encoding sequence, for example, high indicates 1 and low indicates 0; next, the photoelectric sensor array converts the scanned gear encoding sequence into a corresponding binary sequence and restores it to the original numerical form of language preference layer weight, payment method preference layer weight and guide type preference layer weight; finally, the restored language preference layer weight, payment method preference layer weight and guide type preference layer weight are arranged in the order of language preference layer weight, payment method preference layer weight and guide type preference layer weight to form a gradient parameter sequence, which is used for subsequent distribution to the update field of the language preference layer, payment method preference layer and guide type preference layer.

[0103] S4.2, distribute the gradient parameter sequence to the update field of the language preference layer, payment method preference layer and guide type preference layer according to the preset rule;

[0104] Specifically, first, the gradient parameter sequence is obtained from the central aggregation node, the gradient parameter sequence includes the numerical values of the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight, and the arrangement order is the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight; then, the preset allocation rule table in the central aggregation node is accessed, the allocation rule table is set based on the mapping relationship between the arrangement order of the language preference layer weight, the payment method preference layer weight and the guide type preference layer weight in the gradient parameter sequence and the corresponding update field, the allocation rule table defines the corresponding relationship between each weight in the gradient parameter sequence and the language preference layer, the payment method preference layer and the guide type preference layer update field, for example, the language preference layer weight corresponds to the language preference layer update field, the payment method preference layer weight corresponds to the payment method preference layer update field, and the guide type preference layer weight corresponds to the guide type preference layer update field; then, according to the allocation rule table, the language preference layer weight value in the gradient parameter sequence is stored to the language preference layer update field, the payment method preference layer weight value is stored to the payment method preference layer update field, and the guide type preference layer weight value is stored to the guide type preference layer update field; finally, the storage of the language preference layer update field, the payment method preference layer update field and the guide type preference layer update field is completed, an update field set is formed, and is used for subsequent processing of the federal aggregation core.

[0105] S4.3, the central aggregation node submits the gradient parameter sequence from the multiple service-type collaborative robots to the internal federal aggregation core;

[0106] The federal aggregation core obtains the gradient parameter sequence from the multiple service-type collaborative robots, and determines a weighting coefficient according to the tourist service frequency of each service-type collaborative robot;

[0107] Specifically, first, the federal aggregation core receives a plurality of gradient parameter sequences sent by the service-type collaborative robots submitted by the central aggregation node; then, the visitor service frequency data of each service-type collaborative robot is extracted from the service record database in the central aggregation node, which records the number of times each service-type collaborative robot handles visitor requests in a specific time period, for example, a service-type collaborative robot handles 100 visitor requests; then, the visitor service frequency data of each service-type collaborative robot is compared with a preset frequency-coefficient mapping table, which is set based on the statistical relationship between visitor service frequency and service-type collaborative robot contribution, and the frequency-coefficient mapping table defines the corresponding relationship between visitor service frequency and weighting coefficient, for example, 100 requests correspond to a weighting coefficient of 0.5, and 200 requests correspond to a weighting coefficient of 0.8; then, according to the frequency-coefficient mapping table, the corresponding weighting coefficient is assigned to the gradient parameter sequence of each service-type collaborative robot, for example, the service-type collaborative robot handling 100 requests is assigned a weighting coefficient of 0.5; finally, the gradient parameter sequence of each service-type collaborative robot is associated with the corresponding weighting coefficient and stored to form a weighting coefficient assignment set, which is used to generate an updated layer parameter.

[0108] S4.4, the weight update value of the same preference layer (language preference layer, payment method preference layer and tour type preference layer) is calculated by adding the weighting coefficient, and an updated layer parameter is generated, and the expression is:

[0109] ;

[0110] In the formula, is a layer parameter, representing the final updated weight value of the language preference layer, the payment method preference layer or the tour type preference layer, is the total number of service-type collaborative robots participating in the federal aggregation core processing, for example, if there are 10 service-type collaborative robots, = 10, is the index of the service-type collaborative robot, used to identify a certain one of the plurality of service-type collaborative robots participating in the federal aggregation core processing, for example, = 1 represents the first service-type collaborative robot, = 2 represents the second service-type collaborative robot, is the weighting coefficient of the th service-type collaborative robot, which is obtained from the frequency-coefficient mapping table based on visitor service frequency, for example, 100 requests correspond to a weighting coefficient of 0.5, is the weight update value of the corresponding preference layer in the gradient parameter sequence of the th service-type collaborative robot, for example, the language preference layer weight update value;

[0111] The updated layer parameters of each preference layer are combined to form a federal global parameter, which is transmitted to the tourist service center.

[0112] S4.5, the tourist service center receives the federal global parameter, and reads the weight values of the language preference layer, the payment method preference layer and the tour type preference layer in the federal global parameter through an internal parsing structure.

[0113] Specifically, first, the tourist service center receives the federal global parameter from the center aggregation node, and the federal global parameter contains the updated layer parameters of the language preference layer, the updated layer parameters of the payment method preference layer and the updated layer parameters of the tour type preference layer; then, the tourist service center starts an internal parsing structure, which is a predefined data processing program for parsing the structured data of the federal global parameter; then, the parsing structure extracts the weight values of the language preference layer, the weight values of the payment method preference layer and the weight values of the tour type preference layer in the federal global parameter in order of the language preference layer, the payment method preference layer and the tour type preference layer, for example, the weight values of the language preference layer represent the language preference priority, the weight values of the payment method preference layer represent the payment method priority, and the weight values of the tour type preference layer represent the tour type priority; finally, the extracted weight values of the language preference layer, the weight values of the payment method preference layer and the weight values of the tour type preference layer are stored in the local storage area of the tourist service center; wherein the predefined data processing program is written based on the structured data format and parsing logic of the federal global parameter, and the specific implementation depends on the programming language or script language selected by the developer.

[0114] The weight values of each preference layer are matched with a preset judgment condition table to determine the corresponding service strategy configuration item.

[0115] Specifically, first, read the language preference layer weight value, the payment method preference layer weight value and the tour type preference layer weight value from the local storage area of the tourist service center; then, access the preset judgment condition table in the tourist service center, the judgment condition table is set based on the statistical relationship between the range of the language preference layer weight value, the payment method preference layer weight value and the tour type preference layer weight value and the priority of the tourism service demand, the judgment condition table is a predefined mapping table containing the corresponding relationship between the weight value range and the service strategy configuration item, for example, the language preference layer weight value in the range of 0 to 50 corresponds to the "English tour" configuration item, and in the range of 51 to 100 corresponds to the "Chinese tour" configuration item; the payment method preference layer weight value in the range of 0 to 50 corresponds to the "credit card payment" configuration item, and in the range of 51 to 100 corresponds to the "mobile payment" configuration item; the tour type preference layer weight value in the range of 0 to 50 corresponds to the "historical and cultural tour" configuration item, and in the range of 51 to 100 corresponds to the "natural scenery tour" configuration item; then, compare the language preference layer weight value, the payment method preference layer weight value and the tour type preference layer weight value with the corresponding range in the judgment condition table respectively, determine the range to which each weight value belongs, for example, the language preference layer weight value 45 corresponds to the "English tour" configuration item; finally, according to the comparison result, extract the service strategy configuration item corresponding to the language preference layer weight value, the service strategy configuration item corresponding to the payment method preference layer weight value and the service strategy configuration item corresponding to the tour type preference layer weight value, form a service strategy configuration item set, which is used for subsequent generation of strategy execution instructions.

[0116] S4.6, convert the service strategy configuration item into a specific strategy execution instruction, and send it to the control end of the service type collaborative robot;

[0117] Specifically, first, a service strategy configuration item set is read from a local storage area of the visitor service center, the service strategy configuration item set including a service strategy configuration item corresponding to a language preference layer weight value, a service strategy configuration item corresponding to a payment method preference layer weight value, and a service strategy configuration item corresponding to a tour type preference layer weight value; then, a preset instruction conversion table in the visitor service center is accessed, the instruction conversion table being set based on a mapping relationship between the service strategy configuration item and a service-type collaborative robot executable operation, the instruction conversion table being a predefined mapping table including a corresponding relationship between the service strategy configuration item and a strategy execution instruction, for example, an "English tour" configuration item corresponding to an instruction "set voice output to English", a "mobile payment" configuration item corresponding to an instruction "preferentially enable a mobile payment interface", and a "historical and cultural tour" configuration item corresponding to an instruction "load historical and cultural tour content"; next, according to the instruction conversion table, the service strategy configuration item corresponding to the language preference layer weight value in the service strategy configuration item set is converted into a corresponding language strategy execution instruction, the service strategy configuration item corresponding to the payment method preference layer weight value is converted into a corresponding payment strategy execution instruction, and the service strategy configuration item corresponding to the tour type preference layer weight value is converted into a corresponding tour strategy execution instruction, to form a strategy execution instruction set; finally, the strategy execution instruction set is transmitted to a control end of the service-type collaborative robot in the form of an encrypted data packet through a communication interface of the visitor service center, for guiding the service-type collaborative robot to perform a corresponding service operation.

[0118] The embodiment also provides a computer device suitable for the case of the tourism information management method based on the service-type collaborative robot, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the tourism information management method based on the service-type collaborative robot proposed in the above embodiment.

[0119] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to perform wired or wireless communication with an external terminal. The wireless communication can be realized through WIFI, a carrier network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0120] The embodiment also provides a storage medium on which a computer program is stored, the program being executed by a processor to implement the travel information management method based on the service-type collaborative robot proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk.

[0121] To sum up, the application achieves dynamic generation of personalized service parameters based on tourist identity features by performing model training iteration on an initial service label in a local privacy sandbox of the service-type collaborative robot. The pre-trained service preference model is used to adjust the weights of the default language, common payment method, and basic tour guide type in the initial service label, thereby updating the service preference model parameters. After the service preference model is trained locally, the weight update content between the service preference model parameters before the local training iteration and the service preference model parameters after the local training iteration is extracted to generate a set of privacy gradient parameters, ensuring that the original identity information of the tourist and the initial service label do not leave the privacy sandbox, thereby guaranteeing data privacy security and supporting subsequent federal aggregation to check the privacy gradient parameter sets from multiple service-type collaborative robots for weighted aggregation, thereby improving the personalization, security, and collaborative efficiency of service strategy generation in travel information management.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the application rather than limit the application. Although the application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the application, and all of them should be covered in the scope of the claims of the application.

Claims

1. A travel information management method based on a service-type collaborative robot, characterized by: The method comprises the following steps: binding the tourist identity with the service collaborative robot sandbox to generate a tourist mirror set; inputting the tourist mirror set into the geofence detector, comparing the real-time geographic coordinates with the electronic grid map, and outputting the buffer zone operation signal and the out-of-bound signal through the physically isolated double channels; based on the buffer zone operation signal, triggering the service collaborative robot to generate a privacy gradient parameter set; the federal encryption box receives the privacy gradient parameter set and converts it into a gear coding sequence output; if the geofence detector outputs the out-of-bound signal, the physical fuse destroys the tourist mirror set; inputting the gear coding sequence into the federal aggregation core to generate a federal global parameter through weighted aggregation; after receiving the federal global parameter, the tourist service center analyzes and processes to generate a strategy execution instruction.

2. The service-based collaborative robot-based travel information management method of claim 1, characterized by: The binding of the tourist identity with the service collaborative robot sandbox is as follows: scanning the passport information page of the tourist through the optical character recognition component built in the service collaborative robot; extracting the tourist's name, nationality, passport number and birth date from the passport information page; the service collaborative robot starts the privacy sandbox and performs one-way hash processing on the extracted tourist's name, nationality, passport number and birth date to generate a unique identity code; write the generated unique identity code into the isolated storage area of the privacy sandbox to establish the binding relationship between the tourist identity and the service collaborative robot sandbox.

3. The service-based collaborative robot-based travel information management method of claim 1, characterized by: The generation of the tourist mirror set is as follows: call the preset service preference template, load the default language, common payment method and basic tour type according to the extracted nationality to form an initial service label; complete the associated storage of the initial service label and the unique identity code in the isolated storage area of the privacy sandbox to generate the tourist mirror set.

4. The service-based collaborative robot-based travel information management method of claim 1, characterized by: The inputting of the tourist mirror set into the geofence detector, combining the real-time geographic coordinates with the electronic grid map, and outputting the buffer zone operation signal and the out-of-bound signal through the physically isolated double channels are as follows: The geofence detector compares the associated real-time geographic coordinates with the national boundary line coordinate range pre-stored in the local electronic grid map of the geofence detector; if the real-time geographic coordinates are within five kilometers outside the national boundary line coordinate range, a buffer zone operation signal is generated; if the real-time geographic coordinates fall into the area on the opposite side of the national boundary line coordinate range, an out-of-bound signal is generated; output the buffer zone operation signal and the out-of-bound signal through the physically isolated double channels respectively.

5. The service-based collaborative robot-based travel information management method of claim 1, wherein: The generation of the privacy gradient parameter set based on the buffer zone operation signal is as follows: the service collaborative robot receives the buffer zone operation signal from the geofence detector and starts the service preference model in the local privacy sandbox; input the initial service label in the tourist mirror set into the service preference model to perform local training iteration; after the training is completed, the service preference model parameters are stored in the local privacy sandbox built in the service collaborative robot; the service collaborative robot reads the service preference model parameters before and after the local training iteration from the local privacy sandbox and extracts the update content of the language preference layer weight, the payment method preference layer weight and the tour type preference layer weight to generate the privacy gradient parameter set.

6. The service-based collaborative robot-based travel information management method of claim 1, wherein: The federal encryption box receives the privacy gradient parameter set and converts it into a gear code sequence output, specifically as follows, The federal encryption box receives the privacy gradient parameter set from the service-oriented collaborative robot; The language preference layer weight, payment method preference layer weight, and tour type preference layer weight in the privacy gradient parameter set are arranged in order of the preference layer weight to form a gradient parameter sequence; According to the size of the value of each preference layer weight in the gradient parameter sequence, the language preference layer weight, payment method preference layer weight, and tour type preference layer weight are mapped to the preset scale interval of the mechanical coding disc; The federal encryption box drives the mechanical coding disc to rotate to the corresponding scale position, and outputs the corresponding gear code sequence through the linkage of the physical gear set of the mechanical coding disc.

7. The service-based collaborative robot-based travel information management method of claim 1, wherein: When the geo-fence detector outputs the out-of-bound signal, the physical fuse destroys the tourist mirror set, specifically as follows, The out-of-bound signal is transmitted to the storage center of the tourist mirror set through a physically isolated special channel; After receiving the out-of-bound signal, the storage center of the tourist mirror set immediately starts the built-in physical fuse; The physical fuse performs a mechanical deformation action to destroy the magnetic recording layer in the storage center of the tourist mirror set, causing the tourist mirror set to be irrecoverably destroyed. 8.The service-based collaborative robot-based travel information management method of claim 1, wherein: The gear code sequence is input into the federal aggregation core to generate a federal global parameter through weighted aggregation, specifically as follows, The federal aggregation core obtains gradient parameter sequences from multiple service-oriented collaborative robots, and determines a weighting coefficient according to the tourist service frequency of each service-oriented collaborative robot; The weight update values of the language preference layer, payment method preference layer, and tour type preference layer are accumulated according to the weighting coefficient to generate updated layer parameters; The updated layer parameters of each preference layer are combined to form a federal global parameter. 9.The service-based collaborative robot-based travel information management method of claim 1, wherein: After the tourist service center receives the federal global parameter, it analyzes and processes to generate a strategy execution instruction, specifically as follows, The tourist service center receives the federal global parameter and reads the weight values of the language preference layer, payment method preference layer, and tour type preference layer in the federal global parameter through the internal analysis structure; The weight values of each preference layer are matched with a preset judgment condition table to determine the corresponding service strategy configuration item; The service strategy configuration item is converted into a specific strategy execution instruction and sent to the control end of the service-oriented collaborative robot.

10. The service-based collaborative robot-based travel information management method of claim 9, characterized by: The service strategy configuration item is a specific service setting defined by the service-oriented collaborative robot, including configuration options for language preference, payment method preference, and tour type preference, guiding the service-oriented collaborative robot to perform corresponding service operations.

Images