A multi-role exhibition scene-oriented intelligent reception scheduling and information collaboration method and system

Abstract

The application provides a multi-role convention and exhibition scene-oriented intelligent reception scheduling and information collaboration method and system, aiming to solve the problems of information fragmentation, high dependence on manual scheduling and difficulty in multi-role collaboration in the prior art convention and exhibition reception. The application includes constructing a multi-role account and a resource pool; converting collected guest itinerary information and personalized needs into a structured form of a multi-tuple; intelligently scheduling based on the multi-tuple to generate a reception task scheme containing vehicle pick-up, accommodation and catering; visualizing the reception task scheme and differentially assigning it to corresponding executors and guests, supporting task state updating and rescheduling mechanism. The application not only schedules a single task, but also links the reception arrangement and state change of the three business boards of pick-up, check-in and catering, and realizes information synchronization of multiple roles.

Description

Technical Field

[0001] This invention belongs to the field of computer data processing and intelligent scheduling technology, specifically relating to an intelligent reception scheduling and information collaboration method and system for multi-role exhibition scenarios. It is particularly suitable for large-scale exhibitions and conferences, integrating multiple resources such as pick-up and drop-off, accommodation, and catering to achieve intelligent reception scheduling with real-time collaboration among multiple roles. Background Technology

[0002] With the rapid development of the exhibition and convention industry, large-scale conferences, expos, and other events involve a large number of participants, guests of varying levels, and complex reception needs (involving flight transfers, hotel check-ins, catering arrangements, etc.). Existing technologies typically suffer from the following problems:

[0003] ① Severe information silos: Transportation, accommodation, and catering are often managed by different departments or systems, resulting in a lack of data sharing. For example, flight delay information cannot be synchronized in real time with transportation drivers and hotel catering staff, leading to wasted resources.

[0004] ②Low scheduling efficiency: Traditional methods rely heavily on manual Excel spreadsheets or telephone communication for vehicle and personnel scheduling, lacking intelligent algorithm support. When faced with unforeseen changes (such as guests rescheduling their travel plans), manual response is slow and prone to errors.

[0005] ③ Insufficient collaboration capabilities: The lack of a unified working group platform leads to sluggish information flow between on-site reception staff, drivers, and hotel front desk staff, making it impossible to achieve "collaboration at your fingertips," which affects the quality of reception services and the guest experience.

[0006] Therefore, there is an urgent need for a system method that can integrate multi-source data, realize intelligent resource scheduling, and enable real-time collaboration of information among multiple roles. Summary of the Invention

[0007] This invention provides an intelligent reception scheduling and information collaboration method and system for multi-role exhibition scenarios, aiming to solve the problems of information fragmentation, high dependence on manual scheduling, and difficulty in multi-role collaboration in existing exhibition reception technologies.

[0008] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0009] In a first aspect, the present invention provides an intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios, comprising the following steps:

[0010] S100. Construct multi-role accounts and resource pools; the multi-role accounts include administrators, executors, and guests, and the resource pool includes vehicle resources, accommodation resources, and catering resources;

[0011] S200: The collected itinerary information and personalized needs of each guest are converted into a structured plural group.

[0012] S300. Based on the tuple, intelligent scheduling is performed, and a vehicle route planning model based on an improved genetic algorithm is used to generate a vehicle pick-up and drop-off task plan for each guest; and an event-driven timeline model is used to generate an accommodation and catering reception task plan for each guest.

[0013] S400: Visualize the vehicle pick-up and drop-off task plan and the accommodation and catering reception task plan for the administrator to confirm; differentiate them to the corresponding executors and guests, so that the executors can perform the reception tasks and the guests can view the itinerary and the executors' contact information;

[0014] S500: The executor updates the task status and provides feedback at key nodes in completing the reception task; when an abnormal event is detected, the reception task plan is regenerated based on the local re-search algorithm, and a change warning is issued.

[0015] A further solution: In step S100, the executors include drivers, hotel staff, and volunteers; the vehicle resources include vehicle type, quantity, and status; the accommodation resources include room type and number of rooms; and the catering resources include time slots and table numbers.

[0016] A further solution: In step S200, the collected guest itinerary information and personalized needs are converted into a structured reception task model. The reception task model formalizes the reception needs of each guest into a tuple containing multi-dimensional attributes. ;

[0017] Where i is an index. Represents the multi-group of the i-th guest;

[0018] The "I" represents the information set of the guest, including the task ID, guest itinerary information, guest level, number of accompanying persons, and contact information;

[0019] The C represents the set of constraints, including time window constraints, spatial constraints, and special service constraints;

[0020] R represents the resource requirement set, including vehicle type, room type preference, and dietary restrictions;

[0021] P represents the priority parameter set, including guest level weights. ;

[0022] S represents the current task status set, including pending assignment, confirmed, in execution, completed, and exception.

[0023] Based on the above scheme, the reception task model transforms non-standard guest reception needs into mathematical expressions that can be directly calculated by the algorithm through structured data, thus ensuring the accuracy of subsequent reception scheduling.

[0024] A further solution: In step S300, the steps of generating a vehicle pick-up and drop-off plan for each guest using a vehicle route planning model based on an improved genetic algorithm include:

[0025] S301. Generate multiple initial plans for vehicle pick-up and drop-off tasks using a greedy strategy.

[0026] S302. Construct a multi-objective fitness function F(x) and calculate the fitness of each generated initial scheme for the vehicle pick-up and drop-off task;

[0027] S303. Iterate through selection, crossover and mutation operations in sequence until a preset number of iterations is reached or the fitness converges, and output the optimal initial vehicle pick-up and drop-off task scheme as the final vehicle pick-up and drop-off task scheme; wherein, the vehicle pick-up and drop-off task scheme includes vehicle allocation, driving route and estimated departure time.

[0028] Based on the above scheme, a greedy strategy is used to generate multiple initial schemes for vehicle pick-up and drop-off tasks. First, it can be ensured that guests with higher levels are assigned to the nearest available vehicle that meets the vehicle type requirements. On this basis, selection, crossover and mutation operations are used in sequence to iterate and avoid the generated initial schemes for vehicle pick-up and drop-off tasks from getting stuck in local optima. This improves the rationality and stability of the path planning results and makes the final output schemes for vehicle pick-up and drop-off tasks more executable.

[0029] A further solution: In step S302, the target fitness function F(x) is constructed using a weighted summation method, and a normalization process is added. The formula includes:

[0030] ;

[0031] , ;

[0032] ;

[0033] ,

[0034] and ;

[0035] Among them, the This represents the actual vehicle operating cost, the stated This represents the theoretical maximum vehicle operating cost. Normalized vehicle operating costs; This indicates the waiting time for the weighted guests. This represents a summation calculation, the... This represents the ranking weight of the i-th guest. This represents the actual waiting time of the i-th guest; the... This represents the theoretical maximum guest waiting time. Indicates the normalized guest waiting time; the stated Indicates the degree of constraint violation, the stated Indicates the penalty threshold, the Indicates the degree of violation of normalization constraints, the stated This indicates that the degree of constraint violation is capped; x represents the initial plan for the vehicle pick-up and drop-off task. The normalized vehicle driving cost weights are represented by the following. The normalized guest waiting time weights are represented by the following. This indicates the weight of the degree of violation of normalized vehicle constraints.

[0036] Based on the above scheme, the multi-objective fitness function adopts a weighted summation form and is combined with normalization processing. This can unify the optimization objectives of vehicle driving cost, guest waiting time and constraint violation degree under the same evaluation framework, flexibly adjust the importance of each optimization objective, and enable the generated vehicle pick-up and drop-off task scheme to achieve comprehensive optimization in terms of vehicle driving cost, guest waiting time and constraint violation degree.

[0037] A further solution: In step S300, the step of generating an accommodation and catering service plan for each guest using an event-driven timeline model includes:

[0038] S304. Using real-time traffic data from the map API, and combining it with the flight landing time or train arrival time in the guest information set I of the tuple, calculate the estimated arrival time at the hotel; generate the accommodation reception task plan based on the estimated arrival time at the hotel.

[0039] S305. Determine whether the catering reservation task is triggered based on whether the estimated arrival time at the hotel falls within the catering reception time. If triggered, generate a catering reception task plan.

[0040] Based on the above scheme, when generating catering reception task plans, the estimated arrival time at the hotel is used as the trigger condition to determine whether to enter the catering reception time. This enables on-demand triggering and automatic generation of catering tasks, avoids unnecessary resource reservation or scheduling conflicts, and improves the refinement of catering reception and the efficiency of resource utilization.

[0041] A further solution: In step S304, the formula for calculating the estimated arrival time at the hotel is:

[0042] ;

[0043] Among them, the Indicates the hotel arrival time; the stated This indicates the guest's flight arrival time or train arrival time; This indicates the fixed time required to exit an airport or train station; the aforementioned This represents a dynamic prediction of real-time traffic conditions based on a map API; the... This indicates the buffer time.

[0044] Based on the above scheme, a buffer time, or fault tolerance mechanism, is introduced into the formula for calculating the estimated arrival time at the hotel. This can effectively cope with the impact of uncertainties such as flight delays and traffic congestion on time prediction, thereby improving the stability and reliability of the estimated arrival time at the hotel.

[0045] A further solution: In step S305, the dining time period is set as... The start time for dining is The conditions for triggering the catering reservation task are:

[0046] ;

[0047] Among them, the Indicates the start time of the meal service. Indicates the end time of the meal; the stated Indicates the start time when meals are available. Indicates the room check-in time, the stated This indicates the minimum set meal time.

[0048] Based on the above scheme, once guests arrive at the hotel and check in, the catering reservation task will only be triggered if the remaining available catering time meets the minimum dining time requirement. This ensures that the catering reception task scheme is actually feasible and avoids situations where the time is too short and guests do not have enough time to eat.

[0049] A further solution: In step S500, the abnormal event includes flight or train delays in the guest's itinerary information.

[0050] Secondly, the present invention provides an intelligent reception scheduling and information collaboration system for multi-role exhibition scenarios, comprising:

[0051] The data management module is used to build and manage multi-role accounts and resource pools; wherein, the resource pools include vehicle resources, accommodation resources and catering resources, and the multi-role accounts include administrators, executors and guests;

[0052] The intelligent scheduling engine, connected to the data management module, is used to convert guest itinerary information and personalized needs collected through the guest terminal into a structured tuple, and generate a reception task plan including vehicle pick-up and drop-off, accommodation and catering based on the tuple; and to automatically trigger a rescheduling mechanism to regenerate the reception task plan when an abnormal event is detected.

[0053] A multi-terminal application module, connected to both the data management module and the intelligent scheduling engine, includes:

[0054] The workgroup side is used by administrators to input resource information, visually display the reception task plan generated by the intelligent scheduling engine, and support manual intervention or fine-tuning.

[0055] The execution end is used to receive and display only the reception task plans related to the current executor in real time;

[0056] The guest interface allows guests to enter their personal information and personalized needs, view their real-time schedule, and see the contact information of the corresponding executives.

[0057] The execution terminal is also used to update the task status at key nodes in the completion of the reception task, and to feed back the task status to the intelligent scheduling engine and the executor related to the reception task in real time; when the intelligent scheduling engine receives an abnormal event, it regenerates the reception task plan and sends a change warning to the multi-terminal application module.

[0058] The beneficial effects of this invention are as follows:

[0059] 1. This invention constructs a unified reception task model and resource pool, and introduces a multi-role account system on this basis. When intelligently generating reception task plans, different types of resources such as vehicles, accommodation, and catering no longer operate in isolation. Instead, they are dynamically linked to the personalized needs of guests, using the guests' itinerary information as a trigger event. This creates a linkage between vehicle pick-up and drop-off, accommodation, and catering tasks, enhancing the continuity and consistency of the reception process. Furthermore, it reduces reliance on human experience and conflicts or duplicate arrangements caused by information fragmentation.

[0060] 2. This invention utilizes multi-role accounts to enable each role to share task status, achieving real-time synchronization and transparent workflow for reception tasks. Executors can efficiently execute tasks based on the latest reception plan and provide status feedback, while guests can promptly obtain itinerary arrangements and contact information for relevant executors, thereby reducing communication costs and minimizing information errors. The closed-loop collaboration among roles within the same information framework not only improves the response speed of reception tasks but also enhances the controllability and reliability of the overall reception scheduling process.

[0061] In addition, this invention distributes reception task plans in a differentiated manner based on role attributes, pushes only necessary information, and de-identifies sensitive data to ensure information security and improve execution efficiency.

[0062] 3. When an anomaly is detected, the intelligent reception scheduling and information collaboration system for multi-role exhibition scenarios of this invention does not simply issue an alarm, but automatically finds alternative resource solutions or adjusts the time window based on the local re-search algorithm to achieve dynamic repair of the reception task plan. Attached Figure Description

[0063] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a flowchart of an intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to the present invention;

[0065] Figure 2 This is a flowchart of step S300, which generates a reception task plan that includes vehicle pick-up and drop-off, accommodation, and catering. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the protection scope of the present invention.

[0067] Example 1:

[0068] like Figure 1 As shown, this embodiment provides an intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios, including the following steps:

[0069] S100. Construct multi-role accounts and resource pools; the multi-role accounts include administrators, executors, and guests, and the resource pool includes vehicle resources, accommodation resources, and catering resources;

[0070] S200: The collected itinerary information and personalized needs of each guest are converted into a structured plural group.

[0071] S300. Based on the tuple, intelligent scheduling is performed, and a vehicle route planning model based on an improved genetic algorithm is used to generate a vehicle pick-up and drop-off task plan for each guest; and an event-driven timeline model is used to generate an accommodation and catering reception task plan for each guest.

[0072] S400: Visualize the vehicle pick-up and drop-off task plan and the accommodation and catering reception task plan for the administrator to confirm; differentiate them to the corresponding executors and guests, so that the executors can perform the reception tasks and the guests can view the itinerary and the executors' contact information;

[0073] S500: The executor updates the task status and provides feedback at key nodes in completing the reception task; when an abnormal event is detected, the reception task plan is regenerated based on the local re-search algorithm, and a change warning is issued.

[0074] A more specific example of step S100 is as follows: the administrator is the person responsible for the scheduling of the conference reception, i.e., the overall controller; the executors include drivers, hotel staff, catering staff and volunteers; the vehicle resources include vehicle type (e.g., commercial vehicle, bus, accessible vehicle), quantity and status; the accommodation resources include room type (e.g., suite, double room, standard room) and number of rooms; the catering resources include time slots and table numbers.

[0075] A more specific example of step S200 is: converting the collected guest itinerary information and personalized needs into a structured reception task model, wherein the reception task model formalizes the reception needs of each guest into a multi-dimensional set of attributes. ;

[0076] Where i is an index. Represents the multi-group of the i-th guest;

[0077] The "I" represents the information set of the guest, including task ID, guest itinerary information (including guest name, flight or train number, and estimated arrival time of the flight or train), guest level, number of accompanying persons, and contact information. It should be noted that the priority rule for the guest level can be set as: government guests > speakers > general attendees;

[0078] C represents a set of constraints, including time window constraints (the earliest to latest acceptable vehicle pick-up and drop-off times for the guest), spatial constraints (the coordinates of the origin (airport or train station) and destination (hotel), and special service constraints (e.g., whether wheelchair access is required). The time window constraint uses the guest's itinerary as an anchor point, determining the earliest and latest acceptable vehicle pick-up and drop-off times based on the guest's estimated flight or train arrival time. This ensures that the vehicle pick-up and drop-off services match the guest's actual itinerary, preventing the guest from waiting too long or missing the service.

[0079] R represents the resource requirement set, including vehicle type, room type preference, and dietary restrictions;

[0080] P represents the priority parameter set, including guest level weights. ;

[0081] S represents the current task status set, including pending assignment, confirmed, in execution, completed, and exception.

[0082] like Figure 2 As shown, a more specific example of step S300 is: the step of generating a vehicle pick-up and drop-off task plan for each guest using a vehicle route planning model based on an improved genetic algorithm includes:

[0083] S301. Use a greedy strategy to generate multiple initial plans for vehicle pick-up and drop-off tasks, that is, prioritize assigning high-level guests to the nearest available vehicle that meets the vehicle type requirements.

[0084] S302. Construct a multi-objective fitness function F(x) and calculate the fitness of each generated initial scheme for the vehicle pick-up and drop-off task;

[0085] Specifically, the target fitness function F(x) is constructed using a weighted summation method with added normalization. The formula includes:

[0086] ;

[0087] , ;

[0088] ;

[0089] ,

[0090] and ;

[0091] Among them, the This represents the actual vehicle operating cost, the stated This represents the theoretical maximum vehicle travel cost (i.e., the highest vehicle travel cost that occurs when generating all initial vehicle pick-up and drop-off task plans using a greedy strategy). Normalized vehicle operating costs; Indicates the waiting time for the weighted guests. This represents a summation calculation, the... This represents the ranking weight of the i-th guest. This represents the actual waiting time of the i-th guest; the... This represents the theoretical maximum guest waiting time. Indicates the normalized guest waiting time; the stated Indicates the degree of constraint violation, the stated Indicates the penalty threshold, the Indicates the degree of violation of normalization constraints, the stated This indicates that the degree of constraint violation is capped; x represents the initial plan for the vehicle pick-up and drop-off task. The normalized vehicle driving cost weights are represented by the following: The normalized guest waiting time weights are represented by the following. This indicates the weight of the degree of violation of normalized vehicle constraints.

[0092] The multi-objective fitness function The fitness of each initial scheme x for the vehicle pick-up and drop-off task is calculated based on three objectives: vehicle operating cost, guest waiting time, and penalty for breach of contract; wherein, the The fitness value is in the range of [0,1], and the larger the fitness value, the better the initial plan for the vehicle pick-up and drop-off task.

[0093] S303. The initial vehicle pick-up and drop-off task schemes generated in step S301 are iterated through selection, crossover and mutation operations in sequence. After reaching a preset number of iterations or after the fitness converges, the optimal initial vehicle pick-up and drop-off task scheme is output as the final vehicle pick-up and drop-off task scheme. The vehicle pick-up and drop-off task scheme includes vehicle allocation, driving route and estimated departure time.

[0094] Specifically, the selection operation employs a roulette wheel strategy. The selection probability of each initial vehicle pick-up / drop-off task is calculated as: the fitness of each initial vehicle pick-up / drop-off task / total fitness (always fitness = the sum of the fitness of all initial vehicle pick-up / drop-off task plans). The selection probability of each initial vehicle pick-up / drop-off task plan is then mapped onto a roulette wheel, and the initial vehicle pick-up / drop-off task plans with high fitness are retained.

[0095] The following example further illustrates the selection operation: Suppose there are three initial plans for a vehicle pick-up and drop-off task: Plan A, Plan B, and Plan C. The probability of selecting each initial plan is calculated as follows: Plan A is 43.8%, Plan B is 35.1%, and Plan C is 21.1%. The three initial plans are mapped onto a roulette wheel (divided into intervals according to probability): interval A [0, 0.438], interval B [0.438, 0.789], and interval C [0.789, 1]. Each time, a random decimal number in the range [0, 1] is generated. The initial plan corresponding to the interval it falls into is selected (e.g., if the random number is 0.5 and falls into interval B, then initial plan B is selected). Fifty decimal numbers are generated randomly, resulting in 50 initial plans. Since initial plan A occupies the largest interval on the roulette wheel, it has the highest proportion among the 50 selected initial plans.

[0096] Based on the above case, the initial solution with a higher selection probability is selected more often. With the total fitness remaining unchanged, the higher the selection probability, the greater the fitness of the corresponding initial solution. That is, the initial solution of the vehicle pick-up and drop-off task with high fitness is retained.

[0097] The crossover operation employs the Partial Mapping Crossover (PMX) operator, which randomly swaps the task allocation segments in the two initial vehicle pick-up and drop-off task schemes to generate a new combination of vehicle pick-up and drop-off task schemes.

[0098] The following example further illustrates the cross-operation: For instance, there are two initial plans for the vehicle pick-up and drop-off tasks, namely Initial Plan A and Initial Plan B. In Initial Plan A, vehicle 1 picks up guest 1 first and then guest 3, and vehicle 2 picks up guest 2 first and then guest 4. In Initial Plan B, vehicle 1 picks up guest 2 first and then guest 1, and vehicle 2 picks up guest 4 first and then guest 3. Initial Plan A and Initial Plan B are represented by codes: Initial Plan A [1, 3, 2, 4], Initial Plan B [2, 1, 4, 3].

[0099] Randomly swap the task allocation fragments of initial scheme A and initial scheme B (positions 2 and 3 in the encoded representation): Take the task allocation fragment [3, 2] of initial scheme A and the task allocation fragment [1, 4] of initial scheme B and swap them, resulting in initial scheme A [1, 1, 4, 4] and initial scheme B [2, 3, 2, 3]. Since both the temporary scheme A and temporary scheme B obtained after the swap have mapping conflicts (there are duplicate tasks, one guest takes on two tasks), adjust the 1 and 4 on the unswapped task allocation fragments of initial scheme A through the mapping relationship (since 3 and 1 are in the same position and 2 and 4 are in the same position in the taken task allocation fragments of initial scheme A [3, 2] and initial scheme B [1, 4], this mapping relationship is 3↔1, 2↔4) to obtain a new scheme A [3, 1, 4, 2]. Adjust the 2 and 3 on the unswapped task allocation fragments of initial scheme B through the mapping relationship (1↔3, 4↔2) to obtain a new scheme B [4, 3, 2, 1].

[0100] The final combination of vehicle pick-up and drop-off solutions is as follows: In the new solution A, vehicle 1 picks up guest 3 first and then guest 1, and vehicle 2 picks up guest 4 first and then guest 2; In the new solution B, vehicle 1 picks up guest 4 first and then guest 3, and vehicle 3 picks up guest 2 first and then guest 1.

[0101] The mutation operation employs a mutation operator to randomly swap the vehicles or the pick-up / drop-off order in two tasks for an initial scheme of the vehicle pick-up / drop-off task, in order to escape local optima.

[0102] The following example further illustrates the cross-operation: For instance, an initial vehicle pick-up and drop-off plan has two tasks, Task A and Task B. Task A involves vehicle 1 picking up guests in the following order: Guest 1, Guest 6, and Guest 4. Task B involves vehicle 2 picking up guests in the following order: Guest 3, Guest 5, and Guest 2. By swapping the third guest picked up in Task A and Task B, a new combination of vehicle pick-up and drop-off plans is generated: Task A: Vehicle 1 picks up guests in the following order: Guest 1, Guest 6, and Guest 2; Task B: Vehicle 2 picks up guests in the following order: Guest 3, Guest 5, and Guest 4.

[0103] In addition, the preset number of iterations can be set according to the scale of the event (including the number of vehicles and guests). For example, for small-scale events (e.g., 3-5 vehicles and 20-50 guests), the number of iterations can be set to 100-300; for medium-scale events (e.g., 5-10 vehicles and 50-150 guests), the number of iterations can be set to 300-800; and for large-scale events (e.g., more than 10 vehicles and more than 150 guests), the number of iterations can be set to 800-2000+.

[0104] Based on the above approach, the steps for generating accommodation and catering service plans for each guest using an event-driven timeline model include:

[0105] S304. Using real-time traffic data from the map API, and combining it with the flight landing time or train arrival time in the guest information set I of the tuple, calculate the estimated arrival time at the hotel; generate the accommodation reception task plan based on the estimated arrival time at the hotel.

[0106] Specifically, the formula for calculating the estimated arrival time at the hotel is:

[0107] ;

[0108] Among them, the Indicates the hotel arrival time; the stated This indicates the guest's flight arrival time or train arrival time; This indicates the fixed time required to exit an airport or train station; the aforementioned This represents a dynamic prediction of real-time traffic conditions based on a map API; the... This indicates the buffer time.

[0109] Preferably, the It can be set to 30-45 minutes, the aforementioned The buffer time can be set to 15-20 minutes to deal with uncertainties such as flight delays, traffic congestion, or data fluctuations.

[0110] S305. Determine whether the catering reservation task is triggered based on whether the estimated arrival time at the hotel falls within the catering reception time. If triggered, generate a catering reception task plan.

[0111] Specifically, the designated dining time period is... The start time for dining is The conditions for triggering the catering reservation task are:

[0112] ;

[0113] Among them, the Indicates the start time of the meal service. Indicates the end time of the meal; the stated Indicates the start time when meals are available. Indicates the room check-in time. This indicates the minimum set meal time (which can be set to 30 minutes).

[0114] When the triggering conditions are met, the system combines the dietary restrictions in the resource requirement set R to match the table number that meets the requirements and generates a "dining guide" which is then pushed to the guest.

[0115] If a catering task is not generated because the triggering conditions are not met, it indicates that the guest will not have sufficient dining time within the current catering time window after completing check-in. The corresponding executor can mark the catering task as "abnormal," automatically triggering a rescheduling mechanism to recalculate and generate a new catering task plan; for example, the guest's catering task can be moved to the next catering time window (e.g., postponed from dinner to late-night snack or the next day's breakfast). Alternatively, the abnormal catering task can be pushed to the administrator for manual intervention.

[0116] The following example will be used to illustrate step S305 in detail:

[0117] Assuming Guest A's flight lands and the route planning calculation shows that they arrive at the hotel at 18:10, that is... = 18:10, set the room check-in time to 20 minutes, then = 18:30. After Guest B's flight lands, route planning calculates that they will arrive at the hotel at 19:20, which is... = 19:30, set the room check-in time to 20 minutes, then = 19:50.

[0118] Set the dining time slots as [18:00, 20:00], with the shortest dining time. It lasts for 30 minutes.

[0119] After guest A completes the room check-in procedures, there are still 90 minutes left before the end of the catering time (20:00-18:30=90 minutes), and 90 minutes > 30 minutes, which meets the triggering condition. Therefore, a catering reception task is generated for guest A and reserved.

[0120] After Guest B completes the room check-in process, there are still 10 minutes left before the end of the meal service (20:00-19:50=10 minutes), which is less than 30 minutes, so the meal reservation task will not be triggered.

[0121] A more specific example of S500 is as follows: In step S500, the detected abnormal events include flight or train delays in the guest's itinerary information. Of course, the abnormal events also include failure to trigger the catering reservation task.

[0122] Example 2:

[0123] This embodiment provides an intelligent reception scheduling and information collaboration system for multi-role exhibition scenarios. The system is built on a cloud server and adopts a microservice architecture. The system includes:

[0124] The data management module is used to build and manage multi-role accounts and resource pools; wherein, the resource pools include vehicle resources, accommodation resources and catering resources, and the multi-role accounts include administrators, executors and guests;

[0125] The intelligent scheduling engine, connected to the data management module, is used to convert guest itinerary information and personalized needs collected through the guest terminal into a structured tuple, and generate a reception task plan including vehicle pick-up and drop-off, accommodation and catering based on the tuple; and to automatically trigger a rescheduling mechanism to regenerate the reception task plan when an abnormal event is detected.

[0126] A multi-terminal application module, connected to both the data management module and the intelligent scheduling engine, includes:

[0127] The workgroup side is used by administrators to input resource information, visually display the reception task plan generated by the intelligent scheduling engine, and support manual intervention or fine-tuning.

[0128] The execution end is used to receive and display only the reception task plans related to the current executor in real time;

[0129] The guest app is used by guests to enter their personal information and personalized needs, view their personal schedules in real time, and view the contact information of the corresponding executives; the guest app can be a guest mini-program.

[0130] The execution terminal is also used to update the task status at key nodes in the completion of the reception task, and to feed back the task status to the intelligent scheduling engine and the executor related to the reception task in real time; when the intelligent scheduling engine receives an abnormal event, it regenerates the reception task plan and sends a change warning to the multi-terminal application module.

[0131] In addition, when managing the resource pool, the data management module also records the timestamps of each vehicle pick-up and drop-off task, accommodation reception task, and catering reception task, and generates reception efficiency reports (such as average airport pick-up waiting time and vehicle punctuality rate) to provide data support for subsequent exhibition optimization.

[0132] The following is a specific case study to further illustrate the present invention's intelligent reception scheduling and information collaboration method and system for multi-role exhibition scenarios:

[0133] Case Scenario: A sharing session is held on Sunday afternoon with 50 attendees (including professors and general participants). The intelligent reception scheduling and information collaboration system for multi-role conference scenarios, based on this invention, is used to schedule and manage the reception for this sharing session. The execution process is as follows:

[0134] The first step is data preparation and pre-meeting configuration:

[0135] The data management module constructs multi-role accounts and resource pools; administrators enter vehicle resources (e.g., bus A, capacity 55 people; sedan B, capacity 3 people; sedan C, capacity 2 people), accommodation resources (10 double rooms, 10 twin rooms), and catering resources (setting lunch and dinner time windows) through the workgroup terminal; and set the guest level: professors > ordinary participants.

[0136] The second step is to enter the itinerary and generate the reception task plan:

[0137] Professor Zhang, the guest, filled in his travel information through the guest app: flight number CA1234, estimated arrival time Sunday morning at 10:00, contact information; personalized requirements: double room, light diet.

[0138] The intelligent scheduling engine transforms the travel information and personalized needs into a multi-factor group Task={Task ID: G_001, Zhang XX, Phone XXXX, Professor, Arrival at 10:00, Terminal 2, Double Room, Light};

[0139] Based on the status of the resource group and resource pool, the intelligent scheduling engine generates a reception task plan that includes vehicle pick-up and drop-off, accommodation and catering: Professor Zhang → Business sedan B (driver Mr. Wang) → Double room 111 → Vegetarian lunch table 8.

[0140] The third step involves multi-role collaborative execution:

[0141] On the workgroup side: The central control screen displays all generated reception task plans and supports adjustments to vehicles or rooms.

[0142] Driver's App: Mr. Wang sees the task: "Pick up Professor Zhang (phone number XXXX), business sedan B (license plate number XX), flight number CA1234, T2 terminal arrival gate, arrive at 10:00".

[0143] Guest Mini Program: Professor Zhang saw: "Airport pick-up vehicle license plate number XX, driver Mr. Wang's phone number XXX, hotel double room 111, lunch 12:00, table number 8 (vegetarian)".

[0144] Step 4: Status feedback and abnormal rescheduling:

[0145] Scenario 1: When no abnormal event occurs:

[0146] Driver Wang arrived at the airport pick-up point and clicked "Arrived" on the driver's app. The guest received a notification on the mini-program: "Your driver is ready, license plate number XX." After picking up the guest, driver Wang clicked "Picked up." The hotel front desk received a pop-up message "Vehicle is arriving soon" and prepared the room key in advance. The business sedan B arrived at the hotel. After Professor Zhang checked in, the hotel staff clicked "Check-in complete." Professor Zhang was seated at table number 8, and the staff clicked "Dining complete."

[0147] Scenario 2: When an anomaly occurs (Professor Zhang's flight is delayed):

[0148] The intelligent dispatch engine monitored the flight API and found that flight CA1234 was delayed until 12:00. The intelligent dispatch engine triggered the rescheduling mechanism: the original business sedan B was released and reassigned to other guests; and business sedan C (Mr. Li, license plate number XX) was reassigned to pick up Professor Zhang; table 8 was reserved (assuming that the catering reservation task can still be triggered).

[0149] The intelligent scheduling engine sends an alert:

[0150] Guest Mini Program: A pop-up message reads, "Your flight has been delayed. The pick-up time has been changed to 12:00. The license plate number of the pick-up vehicle has been changed to XX. Driver Mr. Li's phone number is XXX."

[0151] Driver's App: Mr. Li received a new task.

[0152] On the workgroup side: the main control screen displays "Task G_001 rescheduled successfully".

[0153] This invention is not limited to the above-described optional embodiments. Anyone can derive other various forms of products under the guidance of this invention. However, regardless of any changes made in their shape or structure, any technical solution that falls within the scope of the claims of this invention shall be protected by this invention.

Claims

1. A method for intelligent reception scheduling and information collaboration in multi-role exhibition scenarios, characterized in that, Includes the following steps: S100. Construct multi-role accounts and resource pools; the multi-role accounts include administrators, executors, and guests, and the resource pool includes vehicle resources, accommodation resources, and catering resources; S200: The collected itinerary information and personalized needs of each guest are converted into a structured plural group. S300. Based on the tuple, intelligent scheduling is performed, and a vehicle route planning model based on an improved genetic algorithm is used to generate a vehicle pick-up and drop-off task plan for each guest; and an event-driven timeline model is used to generate an accommodation and catering reception task plan for each guest. S400: Visualize the vehicle pick-up and drop-off task plan and the accommodation and catering reception task plan for the administrator to confirm; differentiate them to the corresponding executors and guests, so that the executors can perform the reception tasks and the guests can view the itinerary and the executors' contact information; S500: The executor updates the task status and provides feedback at key nodes in completing the reception task; when an abnormal event is detected, the reception task plan is regenerated based on the local re-search algorithm, and a change warning is issued.

2. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 1, characterized in that, In step S100, the executors include drivers, hotel staff, and volunteers; the vehicle resources include vehicle type, quantity, and status; the accommodation resources include room type and number of rooms; and the catering resources include time slots and table numbers.

3. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 2, characterized in that, In step S200, the collected guest itinerary information and personalized needs are converted into a structured reception task model. The reception task model formalizes the reception needs of each guest into a tuple containing multi-dimensional attributes. ; Where i is an index. Represents the multi-group of the i-th guest; The "I" represents the information set of the guest, including the task ID, guest itinerary information, guest level, number of accompanying persons, and contact information; The C represents the set of constraints, including time window constraints, spatial constraints, and special service constraints; R represents the resource requirement set, including vehicle type, room type preference, and dietary restrictions; P represents the priority parameter set, including guest level weights. ; S represents the current task status set, including pending assignment, confirmed, in execution, completed, and exception.

4. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 1, characterized in that, In step S300, the step of generating a vehicle pick-up and drop-off plan for each guest using a vehicle route planning model based on an improved genetic algorithm includes: S301. Generate multiple initial plans for vehicle pick-up and drop-off tasks using a greedy strategy. S302. Construct a multi-objective fitness function F(x) and calculate the fitness of each generated initial scheme for the vehicle pick-up and drop-off task; S303. Iterate through selection, crossover and mutation operations in sequence until a preset number of iterations is reached or the fitness converges, and output the optimal initial vehicle pick-up and drop-off task scheme as the final vehicle pick-up and drop-off task scheme; wherein, the vehicle pick-up and drop-off task scheme includes vehicle allocation, driving route and estimated departure time.

5. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 4, characterized in that, In step S302, the target fitness function F(x) is constructed using a weighted summation method with added normalization. The formula includes: ； ， ； ； ， and ; Among them, the This represents the actual vehicle operating cost, the stated This represents the theoretical maximum vehicle operating cost. Normalized vehicle operating costs; Indicates the waiting time for the weighted guests. This represents a summation calculation, the... This represents the ranking weight of the i-th guest. This represents the actual waiting time of the i-th guest; the... This represents the theoretical maximum guest waiting time. Indicates the normalized guest waiting time; the stated Indicates the degree of constraint violation, the stated Indicates the penalty threshold, the Indicates the degree of violation of normalization constraints, the stated This indicates that the degree of constraint violation is capped; x represents the initial plan for the vehicle pick-up and drop-off task. The normalized vehicle driving cost weights are represented by the following: The normalized guest waiting time weights are represented by the following. This indicates the weight of the degree of violation of normalized vehicle constraints.

6. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 4, characterized in that, In step S300, the step of generating an accommodation and catering service plan for each guest using an event-driven timeline model includes: S304. Using real-time traffic data from the map API, and combining it with the flight landing time or train arrival time in the guest information set I of the tuple, calculate the estimated arrival time at the hotel; generate the accommodation reception task plan based on the estimated arrival time at the hotel. S305. Determine whether the catering reservation task is triggered based on whether the estimated arrival time at the hotel falls within the catering reception time. If triggered, generate a catering reception task plan.

7. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 6, characterized in that, In step S304, the formula for calculating the estimated arrival time at the hotel is: ； Among them, the Indicates the hotel arrival time; the stated This indicates the guest's flight arrival time or train arrival time; This indicates the fixed time required to exit an airport or train station; the aforementioned This represents a dynamic prediction of real-time traffic conditions based on a map API; the... This indicates the buffer time.

8. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 7, characterized in that, In step S305, the dining time period is set as... The start time for dining is The conditions for triggering the catering reservation task are: ； Among them, the Indicates the start time of the meal service. Indicates the end time of the meal; the stated Indicates the start time when meals are available. Indicates the room check-in time. This indicates the minimum set meal time.

9. The intelligent reception scheduling and information collaboration method for multi-role exhibition scenarios according to claim 1, characterized in that, In step S500, the abnormal event includes flight or train delays in the guest's itinerary information.

10. An intelligent reception scheduling and information collaboration system for multi-role exhibition scenarios, characterized in that, include: The data management module is used to build and manage multi-role accounts and resource pools; wherein, the resource pools include vehicle resources, accommodation resources and catering resources, and the multi-role accounts include administrators, executors and guests; The intelligent scheduling engine, connected to the data management module, is used to convert guest itinerary information and personalized needs collected through the guest terminal into a structured tuple, and generate a reception task plan including vehicle pick-up and drop-off, accommodation and catering based on the tuple; and to automatically trigger a rescheduling mechanism to regenerate the reception task plan when an abnormal event is detected. A multi-terminal application module, connected to both the data management module and the intelligent scheduling engine, includes: The workgroup side is used by administrators to input resource information, visually display the reception task plan generated by the intelligent scheduling engine, and support manual intervention or fine-tuning. The execution end is used to receive and display only the reception task plans related to the current executor in real time; The guest interface allows guests to enter their personal information and personalized needs, view their real-time schedule, and see the contact information of the corresponding executives. The execution terminal is also used to update the task status at key nodes in the completion of the reception task, and to feed back the task status to the intelligent scheduling engine and the executor related to the reception task in real time; when the intelligent scheduling engine receives an abnormal event, it regenerates the reception task plan and sends a change warning to the multi-terminal application module.

Images