An exhibition hall path planning method and system based on a WeChat applet

Abstract

The application discloses an exhibition hall path planning method and system based on a WeChat applet. First, a composite key of each exhibition hall is obtained, and then an index key is generated by using the composite key and an edge weight value between the exhibition halls. Next, a required exhibition hall set is retrieved from all the exhibition halls by using the index key, so that efficient retrieval of a target exhibition hall is realized. Then, a path comprehensive cost of each exhibition hall in the exhibition hall set is calculated by using a formula, the exhibition hall with the minimum path comprehensive cost is selected as a next node, and a locally optimal path from a current position to the next node is obtained. The next node is taken as a starting exhibition hall to continue path planning until all the locally optimal paths are obtained, and the globally optimal path is generated by merging all the locally optimal paths. Since all the local paths are completed under the guidance of the path comprehensive cost, the calculation of the local paths of all the subgraphs conforms to the globally optimal direction, so that efficient path planning is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of exhibition hall path planning, and particularly to an exhibition hall path planning method and system based on a WeChat mini-program. Background Art

[0002] With the continuous improvement of people's material living standards, people increasingly attach importance to the pursuit of spiritual enjoyment. Under this background, large comprehensive exhibition halls such as museums and art galleries are increasingly favored by people. However, there are a large number of exhibition halls in these large comprehensive exhibition halls and they are widely distributed. How to efficiently find the target exhibition halls that meet the requirements from a large number of exhibition halls and perform efficient path planning is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0003] By providing an exhibition hall path planning method and system based on a WeChat mini-program, the present invention can efficiently find the target exhibition halls that meet the requirements from a large number of exhibition halls and perform efficient path planning.

[0004] The present invention provides an exhibition hall path planning method based on a WeChat mini-program, including:

[0005] Step S110: Calculate the composite key of each exhibition hall through the formula ; where is the position coordinate of the exhibition hall corresponding in the grid, is the corresponding time slice, is among the themes of the exhibition hall, by comparing the exhibit coverage rate of each theme of the exhibition hall, find the theme with the largest exhibit coverage rate as the theme of the exhibition hall;

[0006] between the composite key and the edge weight value ij between exhibition hall i and exhibition hall j to generate an index key IndexEntry = <Key = (grid position, time slot, theme), Value = (E

[0007]

[0007] Step S130: Retrieve the set of exhibition halls that meet the requirements from all exhibition halls through the index key ;

[0008] Step S140: Calculate the comprehensive path cost of each exhibition hall in the exhibition hall set through the formula ; where is a preset weight, is the weight, is from exhibition hall n to the end exhibition hall physical distance, For exhibition hall n and the final exhibition hall Thematic similarity between them;

[0009] Step S150: Select The smallest pavilion is taken as the next node x, and the local optimal path from the current position to the next node x is obtained; the next node x is taken as the pavilion n and the steps S140 and S150 are continued until all local optimal paths are obtained;

[0010] Step S160: Merge all locally optimal paths to generate a globally optimal path.

[0011] Specifically, it also includes:

[0012] Through formula The edge weights between exhibition hall i and exhibition hall j are calculated. ;in, To determine the thematic similarity between pavilion i and pavilion j, Let i be the distance between exhibition hall i and exhibition hall j. The maximum acceptable distance, For human traffic, For time decay, , and For the preset weights, The interest weight of the exhibition hall.

[0013] Specifically, it also includes:

[0014] Through formula For the edge weights Perform the update to obtain the updated edge weights. ;in, The overall cost of the path for exhibition hall i, The total cost of the route to exhibition hall j.

[0015] Specifically, it also includes:

[0016] Through formula The interest weights of each pavilion were calculated. ;in, The time users spend browsing each exhibition hall on the mini-program. The time allotted for users to browse all the exhibition halls on the mini-program. The number of times a user clicks on each exhibition hall in the mini-program. The number of times a user clicks on all the exhibition halls in the mini-program. The theme similarity between the current exhibition hall theme and the user's preferred theme;

[0017] Update the edge weights through the formula to obtain the updated edge weights ; where is the average interest weight between pavilion i and pavilion j.

[0018] Specifically, it further includes:

[0019] Calculate the user-preferred theme at time t through the formula ; where is the historical interest decay factor, and is the user-preferred theme at time t-1;

[0020] Update the user-preferred theme through the user-preferred theme at time t.

[0021] The present invention also provides a pavilion path planning system based on a WeChat mini-program, including:

[0022] A composite key calculation module for calculating the composite key of each pavilion through the formula ; where is the position coordinate of the pavilion in the grid, is the corresponding time slice, is among the themes of the pavilion. By comparing the exhibit coverage rate of each theme of the pavilion, find the theme with the highest exhibit coverage rate as the theme of the pavilion;

[0023] An index key generation module for generating an index key IndexEntry = <Key = (grid position, time slot, theme), Value = (E and the edge weight between pavilion i and pavilion j ij );

[0024] A pavilion set retrieval module for retrieving a set of pavilions that meet the requirements from all pavilions through the index key ;

[0025] A path comprehensive cost calculation module for calculating the path comprehensive cost of each pavilion in the pavilion set through the formula ; where is the preset weight, is the physical distance from pavilion n to the end pavilion ; ​For exhibition hall n and the final exhibition hall Thematic similarity between them;

[0026] The local optimal path planning module is used to select... The smallest exhibition hall is taken as the next node x, and the local optimal path from the current position to the next node x is obtained; the next node x is taken as the exhibition hall n and the path comprehensive cost calculation module and the local optimal path planning module are continued until all local optimal paths are obtained;

[0027] The global optimal path generation module is used to merge all local optimal paths to generate the global optimal path.

[0028] Specifically, it also includes:

[0029] The edge weight calculation module is used to calculate the edge weight using the formula. The edge weights between exhibition hall i and exhibition hall j are calculated. ;in, To determine the thematic similarity between pavilion i and pavilion j, Let i be the distance between exhibition hall i and exhibition hall j. The maximum acceptable distance, For human traffic, For time decay, , and For the preset weights, The interest weight of the exhibition hall.

[0030] Specifically, it also includes:

[0031] The first update module for edge weights is used to update the weights using a formula. For the edge weights Perform the update to obtain the updated edge weights. ;in, The overall cost of the path for exhibition hall i, The total cost of the route to exhibition hall j.

[0032] Specifically, it also includes:

[0033] The interest weight calculation module is used to calculate the interest weight using a formula. The interest weights of each pavilion were calculated. ;in, The time users spend browsing each exhibition hall on the mini-program. The time allotted for users to browse all the exhibition halls on the mini-program. The number of times a user clicks on each exhibition hall in the mini-program. The number of times a user clicks on all the exhibition halls in the mini-program. The theme similarity between the current exhibition hall theme and the user's preferred theme;

[0034] The second update module for edge weights is used to update the edge weights using the formula. For the edge weights Perform the update to obtain the updated edge weights. ;in, Let be the average interest weights for pavilion i and pavilion j.

[0035] Specifically, it also includes:

[0036] The user preference topic calculation module is used to calculate user preferences using formulas. Calculate the user preference topics at time t ;in, Historical interest decay factor User preferred topics at time t-1;

[0037] The user preference topic update module is used to update the user preference topics at time t. Update user preference themes.

[0038] One or more technical solutions provided in this invention have at least the following technical effects or advantages:

[0039] First, obtain the composite key for each pavilion, then generate an index key using the composite key and the edge weights between pavilions. Next, retrieve the set of pavilions that meet the requirements from all pavilions using the index key, achieving efficient retrieval of the target pavilion. Then, calculate the comprehensive path cost of each pavilion in the set using a formula, select the pavilion with the minimum comprehensive path cost as the next node, and obtain the locally optimal path from the current position to the next node. Continue path planning with the next node as the starting pavilion until all locally optimal paths are obtained, and merge all locally optimal paths to generate the globally optimal path. Since all local paths are completed under the guidance of the comprehensive path cost, the calculation of local paths in all subgraphs conforms to the globally optimal direction, thus achieving efficient path planning. Attached Figure Description

[0040] Figure 1 A flowchart of an exhibition hall path planning method based on WeChat Mini Program provided in an embodiment of the present invention;

[0041] Figure 2 A module diagram of an exhibition hall path planning system based on WeChat mini-programs provided in an embodiment of the present invention. Detailed Implementation

[0042] This invention provides a method and system for exhibition hall path planning based on WeChat mini-programs, which can efficiently identify target exhibition halls that meet the requirements from a large number of exhibition halls and perform efficient path planning.

[0043] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0044] like Figure 1 As shown, the exhibition hall path planning method based on WeChat Mini Program provided in this embodiment of the invention includes:

[0045] Step S110: Using the formula The composite bonds of each pavilion were calculated. ;in, The coordinates of the exhibition hall's location on the grid. , For the corresponding time slices, for example: 9:00 is defined as If the partitioning rules specify a time interval of 30 minutes, then... This indicates the time period from 9:00 to 9:30. This indicates the first time slice. Time period. For the exhibition hall Within each theme, the exhibit coverage of each theme in the exhibition hall was compared. Calculate the exhibit coverage rate The largest theme is taken as the theme of the exhibition hall; for example, in the Hubei Provincial Museum, there is a set of original exhibition hall theme data with 0.1, 0.7, 0.2. The theme distribution vector of the Hubei Provincial Museum generated based on the LDA model is: T i =[0.1,0.7,0.2], at this time K=3 (k=3 indicates that the Hubei Provincial Museum has 3 themes: k=1 for "History of the War of Resistance Against Japan", k=2 for "Revolutionary Figures", and k=3 for "Cultural Heritage"). Input Ti=[0.1,0.7,0.2], and by calculating and comparing p1=0.1, p2=0.7, and p3=0.2, the maximum value corresponds to k=2, so the theme number of this exhibition hall is 2.

[0046] The following discusses composite bonds. The storage will be explained in detail:

[0047] First, determine the system load status and confirm the CPU utilization of each node (e.g., Node1: 80%, Node2: 30%). Input the composite key containing multiple exhibition hall nodes generated in step S110, and then press the spatial grid. (i.e., geographical location) and time slot Data is divided based on (i.e., opening hours). A threshold N is set.max = The shard size of 500 needs to meet the requirement of not exceeding the threshold. If it exceeds the threshold limit, the data needs to be split. Through the formula Find the CPU with the lowest utilization rate and store the split data in it. For example: If the number of shard nodes exceeds 500 (such as 600 nodes), it is split into and according to the time slot, and the CPU that originally processed is used to process the data of . At the same time, use the formula to find the CPU with the lowest utilization rate and hand over the data of to it for processing. Among them, is the shard area with the geographical location of and the opening time of , is the allocation of data processing in the area, , is for all the lowest utilization rate of .

[0048] Step S120: Generate an index key IndexEntry=<Key=(grid position, time slot, theme), Value=(E and the edge weight value between pavilion i and pavilion j )> through the composite key ij ;

[0049] Specifically, calculate the edge weight value between pavilion i and pavilion j through the formula ; among them, is the theme similarity between pavilion i and pavilion j, is the distance between pavilion i and pavilion j, is the maximum acceptable distance, is the number of people flow, that is, the number of people entering the pavilion per minute; is the time decay, is , and are preset weights, is the interest weight of the pavilion.

[0050] If the change in the dynamic number of people flow is large and reaches the trigger condition (the condition needs to be set manually, assuming the condition is the change in the number of people flow ), start dynamic update, recalculate the edge weight value, mark the cache of the previous relevant edge weight value as invalid, and update the edge weight value.

[0051] The embodiments of the present invention provide two methods for updating the edge weight value The methods are as follows:

[0052] Through formula Edge weights Perform the update to obtain the updated edge weights. ;in, The overall cost of the path for exhibition hall i, Let h(n) be the total cost of the path to pavilion j. The weights of the pavilions are dynamically adjusted according to h(n) to tilt the path towards the optimal target path. If the weights of pavilion j are... Smaller (closer to the target), then Increasing the weight increases the edge weight between pavilion i and pavilion j, which encourages the algorithm to prioritize pavilion j as the next pavilion to visit when pavilion i is in use.

[0053] or,

[0054] Through formula The interest weights of each pavilion were calculated. ;in, The time users spend browsing each exhibition hall on the mini-program. The time allotted for users to browse all the exhibition halls on the mini-program. The number of times a user clicks on each exhibition hall in the mini-program. The number of times a user clicks on all the exhibition halls in the mini-program. This represents the theme similarity between the current exhibition hall's theme and the user's preferred theme. For example, if a user stays for 150 seconds and clicks 5 times (out of a total of 100 clicks in the exhibition hall), the path similarity is 0.7. That is, the interest weight of this exhibition hall is 56%.

[0055] Through formula Edge weights Perform the update to obtain the updated edge weights. ;in, Let i be the average interest weight of pavilion i and pavilion j, i.e. For example: original edge weights Theme similarity =0.8, =0.76, then the corrected .

[0056] Specifically, this embodiment of the invention also updates the user preference theme, as follows:

[0057] Through formula Calculate the user preference topics at time t ;in, Historical interest decay factor User preferred topics at time t-1;

[0058] User preference topics at time t Update user-preferred themes. For example: If The result is [0.9, 0.2]. If the value is [0.85, 0.3], then the updated value is... . Changes will then affect the next edge weight. The calculations form a closed loop. For example: Input cached data shows that user A has used the mini-program multiple times, and their historical preference is "History of the War of Resistance Against Japan" (topic interest weight). The score was 0.8. The visitor spent 150 seconds in Hall V1 (History of the War of Resistance Against Japan) (out of a total visit time of 300 seconds), and Hall V1 received 20 clicks (out of a total of 100 clicks). The similarity between the V1 theme and the historical theme was... The value is 0.9, representing the user interest vector. =[0.8,0.2] (History of the War of Resistance Against Japan, Revolutionary Figures), Initial Pavilion Edge Weights: E V1→V5 =0.5, E V3→出口 =0.4, E V5→出口 =0.6. Use the formula to calculate the interest weight. Then adjust the path weights. It should be noted that if this is your first time using the mini-program, you will be entering the initial edge weights. If this is not the first time using this service, enter the updated edge weights. Then, the user interest vector is updated using a decay function: , Output edge weights User interest vector The results showed that the weight of the theme "History of the War of Resistance Against Japan" increased, while the weight of the theme "Revolutionary Figures" decreased.

[0059] Step S130: By index key The program retrieves a set of exhibition halls that meet the user's requirements from all exhibition halls. Specifically, it supports fast searching based on multiple conditions using an index key (e.g., "Grid=3,5 & Time=09:00-09:15 & Theme=History of the War of Resistance Against Japan"). During the filtering process, it prioritizes conditions with high filtering rates (e.g., if the condition "Grid=3,5" filters out 20% of the exhibition halls, "Time=09:00-09:15" filters out 40%, and "Theme=History of the War of Resistance Against Japan" filters out 70%, then it prioritizes filtering by theme, then by time, and finally by location). This enables fast searching. Finally, it outputs a set of exhibition halls that meet the user's requirements after querying and filtering, taking into account actual visitor traffic (excluding exhibition halls excluded by dynamic penalties). For example, when a user asks, "I want to see an exhibition hall on the theme of the War of Resistance Against Japan. The time is 09:10, and I am near the 3rd row, 5th column area of ​​the museum," the mini-program directly uses the index key (G... 3,5 (T2, History of the War of Resistance Against Japan), filter according to the criteria from highest to lowest screening rate to find the corresponding collection of exhibition halls. These exhibition halls simultaneously meet the above user needs, thus enabling rapid retrieval. The dynamic penalty term c(n) is calculated by real-time reading of pedestrian flow sensor data. If the number of people queuing for exhibition hall n is ≥15, set c(n)=+∞ to force the algorithm to detour and skip that exhibition hall.

[0060] Step S140: Using the formula The comprehensive path cost of each pavilion in the pavilion set was calculated. ;in, To preset weights, From exhibition hall n to the final exhibition hall physical distance, For exhibition hall n and the final exhibition hall Thematic similarity between them;

[0061] Step S150: Select The smallest pavilion is chosen as the next node x, and the locally optimal path from the current position to the next node x is obtained. Example: If the theme of pavilion A is "History of the War of Resistance Against Japan," the theme similarity of the current pavilion is 0.6, and it is 50 meters from the target, then h(n) = 0.7 × 50 + 0.3 × (1 − 0.6) = 35 + 0.12 = 35.12; another pavilion B has the theme "Heroic Deeds," the theme similarity of the current pavilion is 0.7, and it is 70 meters from the target, then... If the optimal path is selected, then Pavilion A will be chosen. Continue executing steps S140 and S150 with the next node x as pavilion n until all locally optimal paths are obtained. Since all local paths are completed under the guidance of h(n), the calculation of local paths in all subgraphs conforms to the globally optimal direction, so finally only cross-subgraph path merging is needed.

[0062] It should be noted that the generated paths are stored in the system background. When a user searches for an exhibition hall again and the exhibition hall is included in the previously stored paths, the program directly reads the cached paths and outputs the recommended paths.

[0063] The specific implementation process is as follows:

[0064] Input user query data (G x,y (T2, History of the War of Resistance Against Japan) First, step S130 retrieves a set of exhibition halls that meet the criteria. Then, the background checks whether a path contains all the exhibition halls in the set. If a path is found, it is directly read and output; otherwise, step S150 plans the route. When the weight of one side of a path stored in the background changes, all paths containing that weight become invalid. Step S150 regenerates the path and stores it in the background, thus achieving collaborative updating of the cache.

[0065] Step S160: Merge all locally optimal paths to generate a globally optimal path.

[0066] To check and record device status in real time, the path result and device status are entered into the mini-program to evaluate the device's computing power, thereby enabling task allocation and dynamic task unloading.

[0067] The specific implementation process and the technical means involved are as follows:

[0068] Input device status:

[0069] Mobile terminal: mobile phone (40% CPU idle, 500MB remaining memory, 100ms latency); Edge node: server deployed in the museum (70% CPU idle, 4GB memory, 10ms latency); Cloud: AWS EC2 instance (40% CPU idle, 16GB memory, 50ms latency).

[0070] First, through the formula Computational capability assessment; among which, This represents the percentage of idle CPU time on the terminal. For available memory space, This refers to network latency, measured in milliseconds (ms). Specifically: Capability 移动端=(40% / 100%)×0.5×(1 / 100)=0.002, Capability 边缘 =0.7×4×(1 / 10)=0.28, Capability 云端 =0.4×16×(1 / 50)=0.128. It can be seen that the edge node has the strongest capability (0.28), and the core computing tasks are assigned to the edge node. For the tasks of processing data, if the mobile device is sufficient, the mobile device executes locally; otherwise, it is offloaded to the edge node or the cloud for processing. Specifically, if Capability local ≥ (such as =0.1, set by the developer), it is executed locally; otherwise, it is offloaded to the edge node or the cloud (select the one with stronger computing power for execution).

[0071] In this embodiment, the core computing tasks include: the retrieval and matching computing task of the index key, the interest weight computing task of the exhibition hall, and the edge weight value computing task between exhibition halls.

[0072] As Figure 2 shown, the exhibition hall path planning system based on WeChat mini-program provided by the embodiment of the present invention includes:

[0073] The composite key calculation module 100 is used to calculate the composite key of each exhibition hall through the formula ; where is the position coordinate of the exhibition hall corresponding in the grid , , is the corresponding time slice. For example, 9:00 is defined as . The slicing rule stipulates that the time interval is 30 minutes, then represents the time period from 9:00 to 9:30, while represents the time period of the time slice. is among the themes of the exhibition hall. By comparing the exhibit coverage of each theme of the exhibition hall, the theme with the largest exhibit coverage is obtained as the theme of the exhibition hall.

[0074] The index key generation module 200 is used to generate the index key IndexEntry = <Key = (grid position, time slot, theme), Value = (E and the edge weight value between exhibition hall i and exhibition hall j); ij >;

[0075] Specifically, embodiments of the present invention also include:

[0076] The edge weight calculation module is used to calculate the edge weight using the formula. The edge weights between exhibition hall i and exhibition hall j were calculated. ;in, To determine the thematic similarity between pavilion i and pavilion j, Let i be the distance between exhibition hall i and exhibition hall j. The maximum acceptable distance, Traffic flow refers to the number of people entering the exhibition hall per minute; For time decay, , and For the preset weights, The interest weight of the exhibition hall.

[0077] This invention provides two methods for updating edge weights. Specifically, embodiments of the present invention further include:

[0078] The first update module for edge weights is used to update the weights using the formula. Edge weights Perform the update to obtain the updated edge weights. ;in, The overall cost of the path for exhibition hall i, Let h(n) be the total cost of the path to pavilion j. The weights of the pavilions are dynamically adjusted according to h(n) to tilt the path towards the optimal target path. If the weights of pavilion j are... Smaller (closer to the target), then Increasing the weight increases the edge weight between pavilion i and pavilion j, which encourages the algorithm to prioritize pavilion j as the next pavilion to visit when pavilion i is in use.

[0079] or,

[0080] The interest weight calculation module is used to calculate the weight using a formula. The interest weights of each pavilion were calculated. ;in, The time users spend browsing each exhibition hall on the mini-program. The time allotted for users to browse all the exhibition halls on the mini-program. The number of times a user clicks on each exhibition hall in the mini-program. The number of times a user clicks on all the exhibition halls in the mini-program. The theme similarity between the current exhibition hall theme and the user's preferred theme;

[0081] The second update module for edge weights is used to update the edge weights using the formula. Edge weights Perform the update to obtain the updated edge weights. ;in, Let i be the average interest weight of pavilion i and pavilion j, i.e. ;

[0082] This invention also updates user preference themes. Specifically, this invention further includes:

[0083] The user preference topic calculation module is used to calculate user preferences using formulas. Calculate the user preference topics at time t ;in, Historical interest decay factor User preferred topics at time t-1;

[0084] The user preference topic update module is used to update the user preference topics at time t. Update user preference themes.

[0085] Exhibition hall collection retrieval module 300, used for index key The program retrieves a set of exhibition halls that meet the user's requirements from all exhibition halls. Specifically, it supports fast searching based on multiple conditions using index keys (e.g., "Grid=3,5 & Time=09:00-09:15 & Theme=History of the War of Resistance Against Japan"). During the filtering process, it prioritizes conditions with high filtering rates (e.g., if the condition "Grid=3,5" filters out 20% of the exhibition halls, "Time=09:00-09:15" filters out 40%, and "Theme=History of the War of Resistance Against Japan" filters out 70%, then it prioritizes filtering by theme, then by time, and finally by location). This enables fast searching. Finally, it outputs a set of exhibition halls that meet the user's requirements after querying and filtering, taking into account actual visitor traffic (excluding exhibition halls excluded by dynamic penalties). For example, when a user asks, "I want to see an exhibition hall on the theme of the history of the War of Resistance Against Japan. The time is 09:10, and I am near the 3rd row, 5th column area of ​​the museum," the mini-program directly uses the index key... The selection process is based on the criteria, ranked from highest to lowest screening rate, to find the corresponding collection of exhibition halls. These exhibition halls simultaneously meet the above user needs, thus enabling rapid retrieval. The dynamic penalty term c(n) is calculated by real-time reading of pedestrian flow sensor data. If the number of people queuing for exhibition hall n is ≥15, set c(n)=+∞ to force the algorithm to detour and skip that exhibition hall.

[0086] The route comprehensive cost calculation module 400 is used to calculate the cost of a route using a formula. The comprehensive path cost of each pavilion in the pavilion set was calculated. ;in, To preset weights, From exhibition hall n to the final exhibition hall physical distance, For exhibition hall n and the final exhibition hall Thematic similarity between them;

[0087] The local optimal path planning module 500 is used for selection. The smallest pavilion is taken as the next node x, and the local optimal path from the current position to the next node x is obtained; the next node x is taken as the pavilion n and the path comprehensive cost calculation module 400 and the local optimal path planning module 500 are continued until all local optimal paths are obtained; since all local paths are completed under the guidance of h(n), the calculation of local paths of all subgraphs conforms to the global optimal direction, so only cross-subgraph path merging is needed in the end.

[0088] The global optimal path generation module 600 is used to merge all local optimal paths to generate a global optimal path.

[0089] To check and record device status in real time, the system inputs path results and device status into a mini-program to evaluate the device's computing power, thereby enabling task allocation and dynamic task unloading. This embodiment of the invention also includes:

[0090] The task allocation module is used to assign tasks using formulas. Computational ability assessment; among which, This represents the percentage of idle CPU time on the terminal. For available memory space, This refers to network latency, measured in milliseconds (ms). Specifically: Capability 移动端 = (40% / 100%) × 0.5 × (1 / 100) = 0.002, Capability 边缘 =0.7×4×(1 / 10)=0.28, Capability 云端 =0.4×16×(1 / 50)=0.128, indicating that edge nodes have the strongest capability (0.28), so core computing tasks should be allocated to edge nodes. For data processing tasks, if the mobile device... If sufficient, the process is executed locally on the mobile device; otherwise, it is offloaded to an edge node or the cloud for processing. Specifically, if Capability... local ≥ (like =0.1 (set by the developer), execute locally, otherwise unload to edge nodes or the cloud (choose the one with stronger computing power).

[0091] In this embodiment, the core computing tasks include: index key retrieval and matching calculation task, interest weight calculation task for exhibition halls, and edge weight calculation task between exhibition halls.

[0092] In summary, the embodiments of the present invention improve the retrieval performance of exhibition halls by optimizing composite queries. Furthermore, by incorporating dynamic programming techniques, high-speed path planning is achieved.

[0093] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0095] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0096] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0097] Any aspects of this invention not described in detail in the embodiments are well-known techniques to those skilled in the art. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this invention and not to limit it. Although this invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this invention without departing from the spirit and scope of this invention, and all such modifications and substitutions should be covered within the scope of the claims of this invention.

Claims

1. A method for planning exhibition hall paths based on WeChat Mini Programs, characterized in that, include: Step S110: Using the formula The composite bonds of each pavilion were calculated. ;in, The coordinates of the exhibition hall's location on the grid. For the corresponding time slices, For the exhibition hall Within each theme, the exhibit coverage of each theme in the exhibition hall was compared. Calculate the exhibit coverage rate The main theme serves as the central theme of the exhibition hall; Step S120: Through the composite key and the edge weight value between exhibition hall i and exhibition hall j generate an index key IndexEntry = <Key = (grid position, time slot, theme), Value = (E ij )>; Step S130: Using the index key Retrieve a set of exhibition halls that meet the requirements from all exhibition halls; Step S140: Using the formula The comprehensive path cost for each exhibition hall in the aforementioned exhibition hall set was calculated. ;in, To preset weights, From exhibition hall n to the final exhibition hall physical distance, For exhibition hall n and the final exhibition hall Thematic similarity between them; Step S150: Select The smallest pavilion is taken as the next node x, and the local optimal path from the current position to the next node x is obtained; the next node x is taken as the pavilion n and the steps S140 and S150 are continued until all local optimal paths are obtained; Step S160: Merge all locally optimal paths to generate a globally optimal path.

2. The exhibition hall path planning method based on WeChat mini-program as described in claim 1, characterized in that, Also includes: Through formula The edge weights between exhibition hall i and exhibition hall j are calculated. ;in, To determine the thematic similarity between pavilion i and pavilion j, Let i be the distance between exhibition hall i and exhibition hall j. The maximum acceptable distance, For human traffic, For time decay, , and For the preset weights, The interest weight of the exhibition hall.

3. The exhibition hall path planning method based on WeChat mini-program as described in claim 2, characterized in that, Also includes: Through formula For the edge weights Perform the update to obtain the updated edge weights. ;in, The overall cost of the path for exhibition hall i, The total cost of the route to exhibition hall j.

4. The exhibition hall path planning method based on WeChat mini-program as described in claim 2, characterized in that, Also includes: Through formula The interest weights of each pavilion were calculated. ;in, The time users spend browsing each exhibition hall on the mini-program. The time allotted for users to browse all the exhibition halls on the mini-program. The number of times a user clicks on each exhibition hall in the mini-program. The number of times a user clicks on all the exhibition halls in the mini-program. The theme similarity between the current exhibition hall theme and the user's preferred theme; Through formula For the edge weights Perform the update to obtain the updated edge weights. ;in, Let be the average interest weights for pavilion i and pavilion j.

5. The exhibition hall path planning method based on WeChat mini-program as described in claim 4, characterized in that, Also includes: Through formula Calculate the user preference topics at time t ;in, Historical interest decay factor User preferred topics at time t-1; User preference topics at time t Update user preference themes.

6. A museum path planning system based on WeChat Mini Programs, characterized in that, include: The composite bond calculation module is used to calculate the composite bond using formulas. The composite bonds of each pavilion were calculated. ;in, The coordinates of the exhibition hall's location on the grid. For the corresponding time slices, For the exhibition hall Within each theme, the exhibit coverage of each theme in the exhibition hall was compared. Calculate the exhibit coverage rate The main theme serves as the central theme of the exhibition hall; An index key generation module for generating an index key by means of the composite key and the edge weight value between pavilion i and pavilion j to generate an index key IndexEntry = <Key=(grid location, time slot, theme), Value=(E ij )>; The exhibition hall collection retrieval module is used to retrieve information via the index key. Retrieve a set of exhibition halls that meet the requirements from all exhibition halls; The route cost calculation module is used to calculate the overall cost using formulas. The comprehensive path cost for each exhibition hall in the aforementioned exhibition hall set was calculated. ;in, To preset weights, From exhibition hall n to the final exhibition hall physical distance, For exhibition hall n and the final exhibition hall Thematic similarity between them; The local optimal path planning module is used to select... The smallest exhibition hall is taken as the next node x, and the local optimal path from the current position to the next node x is obtained; the next node x is taken as the exhibition hall n and the path comprehensive cost calculation module and the local optimal path planning module are continued until all local optimal paths are obtained; The global optimal path generation module is used to merge all local optimal paths to generate the global optimal path.

7. The exhibition hall path planning system based on WeChat mini-program as described in claim 6, characterized in that, Also includes: The edge weight calculation module is used to calculate the edge weight using the formula. The edge weights between exhibition hall i and exhibition hall j are calculated. ;in, To determine the thematic similarity between pavilion i and pavilion j, Let i be the distance between exhibition hall i and exhibition hall j. The maximum acceptable distance, For human traffic, For time decay, , and For the preset weights, The interest weight of the exhibition hall.

8. The exhibition hall path planning system based on WeChat mini-program as described in claim 7, characterized in that, Also includes: The first update module for edge weights is used to update the weights using the formula. For the edge weights Perform the update to obtain the updated edge weights. ;in, The overall cost of the path for exhibition hall i, The total cost of the route to exhibition hall j.

9. The exhibition hall path planning system based on WeChat mini-program as described in claim 7, characterized in that, Also includes: The interest weight calculation module is used to calculate the weight using a formula. The interest weights of each pavilion were calculated. ;in, The time users spend browsing each exhibition hall on the mini-program. The time allotted for users to browse all the exhibition halls on the mini-program. The number of times a user clicks on each exhibition hall in the mini-program. The number of times a user clicks on all the exhibition halls in the mini-program. The theme similarity between the current exhibition hall theme and the user's preferred theme; The second update module for edge weights is used to update the edge weights using the formula. For the edge weights Perform the update to obtain the updated edge weights. ;in, Let be the average interest weights for pavilion i and pavilion j.

10. The exhibition hall path planning system based on WeChat mini-program as described in claim 9, characterized in that, Also includes: The user preference topic calculation module is used to calculate user preferences using formulas. Calculate the user preference topics at time t ;in, Historical interest decay factor User preferred topics at time t-1; The user preference topic update module is used to update the user preference topics at time t. Update user preference themes.

Images