Modularized intelligent assembly type combined transportation packaging system

Abstract

The invention discloses a modular intelligent assembly type combined transportation packaging system, and relates to the field of packaging, and the system comprises an information collection unit which is used for obtaining the sensitive factor information of to-be-transported goods; the module function library is used for storing various standard modules with different functional characteristics; the matching scoring unit is used for constructing a module matching scoring model and generating a module adaptation scoring table based on the adaptation relationship between the functional characteristics of each standard module and the cargo sensitive factors; the combination optimization unit is used for selecting a group of optimal module combination schemes meeting the protection requirements from the module function library by adopting an optimization algorithm according to the module adaptation score table; and the structure generation unit is used for generating a container structure blueprint based on the optimal module combination scheme. According to the invention, the standard module can be intelligently matched according to the cargo characteristics and the structured assembly scheme is output, so that the problems that the existing container system cannot automatically configure the module according to the individual demand of the cargo, the efficiency is low and the adaptability is poor are solved.

Description

Technical Field

[0001] The present invention relates to the field of containerization, and more particularly to a modular intelligent assembled intermodal containerization system. Background Art

[0002] Intermodal transport is a comprehensive transportation method widely used in modern logistics systems. It refers to the use of two or more modes of transport (such as road, rail, water, or air) to transfer and distribute goods without changing the cargo loading unit. With the diversification of global supply chains and the normalization of cross-border trade, intermodal transport systems are playing an increasingly critical role in improving logistics efficiency, reducing transportation costs, and simplifying transshipment processes.

[0003] To accommodate diverse cargo characteristics and transport routes, container systems (particularly the transport structure of containerized units) are gradually evolving towards modularization, intelligence, and standardization. Within this trend, prefabricated modular units are widely used to construct disassembled and reassembled containerized structures. Their core goal is to meet the personalized transport needs of different types of cargo in terms of vibration protection, temperature and humidity control, and structural support. However, while modularization has been implemented in some containerized equipment, current practical applications still face a number of key challenges that cannot be ignored.

[0004] First, most existing container systems are designed in a standardized manner based on universal structures. They lack the ability to deeply perceive and respond to the "sensitive attributes" of cargo, and are unable to achieve personalized matching for typical cargo characteristics such as "fear of pressure, fear of moisture, fear of shock, and sensitivity to temperature"; secondly, the selection and structural layout of modules often rely on manual experience and judgment, and lack a systematic scoring mechanism and combination strategy, making it difficult to achieve a reasonable balance between functional completeness and assembly efficiency; in addition, due to the diversity and adjustability of the combination methods between various functional modules, how to meet protection needs while taking into account energy consumption control, space utilization and assembly convenience has also become a challenge that is difficult to balance in current system design.

[0005] In this context, how to design an intermodal container system with intelligent structural module selection, automated combination strategy optimization, and the ability to generate a clear assembly structure based on cargo transportation needs has become a core issue that needs to be overcome in the current logistics equipment field. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a modular intelligent assembled intermodal container system to solve the problems mentioned in the background technology.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A modular intelligent assembled intermodal container system, comprising:

[0009] An information collection unit, used to obtain sensitive factor information of the goods to be transported;

[0010] Module function library, used to store a variety of standard modules with different functional characteristics;

[0011] The matching scoring unit is used to build a module matching scoring model and generate a module matching scoring table based on the matching relationship between the functional characteristics of each standard module and the sensitive factors of the goods;

[0012] A combination optimization unit, configured to select a set of optimal module combination solutions that meet protection requirements from the module function library using an optimization algorithm according to the module adaptation score table;

[0013] A structure generation unit is used to generate a container structure blueprint based on the optimal module combination solution.

[0014] In some embodiments, the information collection unit includes:

[0015] Input interface module, used to receive goods description information input by the user;

[0016] A database extraction module, configured to extract corresponding sensitive factor information from a cargo database according to the cargo description information;

[0017] The structured output module is used to convert the acquired sensitive factor information into a standardized structured format.

[0018] In some embodiments, the sensitive factor information includes any one or more of the following: shock sensitivity, pressure sensitivity, moisture sensitivity, and temperature adaptation range.

[0019] In some embodiments, the module function library is modularly classified according to functional characteristics, and includes at least one or more of the following types of standard modules:

[0020] Shockproof modules with different levels of buffering capabilities;

[0021] Dehumidification module, used to regulate humidity levels within a closed environment;

[0022] Temperature control module, used to maintain the required temperature range of the goods;

[0023] Support modules are used to fix the structure or balance the center of gravity of irregular cargo;

[0024] Thermal insulation module, used to reduce the heat conduction rate to delay temperature changes;

[0025] The anti-pressure module has structural pressure resistance to protect sensitive cargo.

[0026] In some embodiments, the matching scoring unit includes:

[0027] Parameter mapping module, used to map the functional characteristics of each standard module with the sensitive factors of the goods;

[0028] A scoring calculation module is used to calculate the fitness score of each standard module using a weighted scoring algorithm based on the mapping results;

[0029] The scoring table generation module is used to generate a module adaptation scoring table.

[0030] In some embodiments, when generating the adaptation score table, the score table generation module sorts the adaptation scores therein from high to low.

[0031] In some embodiments, the combinatorial optimization unit includes:

[0032] An optimization model building module is used to build a combination optimization model based on the adaptation score table;

[0033] Algorithm execution module, used to call the heuristic optimization algorithm execution module combination search;

[0034] The combination scheme screening module is used to screen out the optimal module combination scheme from multiple feasible solutions and output it as the final assembly scheme.

[0035] In some embodiments, the heuristic optimization algorithm is any one of the following: a greedy algorithm, a genetic algorithm, or an ant colony algorithm.

[0036] In some embodiments, the structure generation unit includes:

[0037] The structural arrangement module is used to determine the arrangement order, spatial position and relative connection method of each standard module according to the module combination plan;

[0038] Parameter configuration module, used to configure corresponding functional parameters for each selected module;

[0039] The blueprint output module is used to generate the container structure blueprint and output it in the form of graphical files and structured instruction formats for reading and execution by the automated assembly system.

[0040] In some embodiments, the output container structure blueprint includes module type, three-dimensional layout diagram, functional parameter settings and assembly sequence instructions.

[0041] The advantage of the present invention over the existing technology is that, by introducing an intelligent identification and modular combination mechanism based on cargo-sensitive factors, the present invention can achieve differentiated matching of container structures for different types of cargo, effectively improving safety and adaptability during transportation; at the same time, combined with the scoring model and optimization algorithm, it automatically generates the optimal module combination and structural assembly plan, reduces manual dependence, improves assembly efficiency, and has good scalability and self-learning capabilities, and is suitable for personalized container needs in various intermodal transport scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is the overall workflow diagram of the present invention;

[0043] Figure 2 It is a detailed flow chart of the information acquisition unit of the present invention;

[0044] Figure 3 is a workflow diagram of the matching scoring unit of the present invention;

[0045] Figure 4 It is an optimization process diagram of the combination optimization unit of the present invention. DETAILED DESCRIPTION

[0046] The specific embodiments of the present invention will be described below with reference to the accompanying drawings.

[0047] This invention provides a modular, intelligent, prefabricated intermodal container system. Through intelligent, modular design, it automatically generates an optimal container structure based on the specific needs of the goods being transported. This system is particularly suitable for intermodal transport scenarios, ensuring the safety and stability of goods during transportation while improving efficiency and reducing costs.

[0048] like Figure 1 As shown, the system of the present invention includes:

[0049] An information collection unit, used to obtain sensitive factor information of the goods to be transported;

[0050] Module function library, used to store a variety of standard modules with different functional characteristics;

[0051] The matching scoring unit is used to build a module matching scoring model and generate a module matching scoring table based on the matching relationship between the functional characteristics of each standard module and the sensitive factors of the goods;

[0052] A combination optimization unit, configured to select a set of optimal module combination solutions that meet protection requirements from the module function library using an optimization algorithm according to the module adaptation score table;

[0053] A structure generation unit is used to generate a container structure blueprint based on the optimal module combination solution.

[0054] More specifically, Figure 2 As shown, the first step is to obtain detailed information from the user about the cargo to be transported, particularly any sensitive factors that may affect its safety. These sensitive factors can be understood as characteristics of the cargo that are susceptible to external conditions during transportation, such as susceptibility to vibration damage, pressure sensitivity, moisture tolerance, and suitable temperature range. This information forms the basis for subsequent module selection and combination, and therefore must be accurately collected and processed.

[0055] This process relies on three closely coordinated submodules. First, users submit a description of their shipment through an intuitive input interface. Imagine a scenario where a user needs to ship a shipment of precision electronic instruments. They might enter information such as "Cargo Type: Electronic Instruments, Dimensions: 50cm x 30cm x 20cm, Weight: 15kg, Special Requirements: Shockproof and Moistureproof." This interface can be designed as a web form with drop-down menus and text boxes, allowing users to complete their input by simply filling in the necessary fields.

[0056] Next, based on this descriptive information, the system will extract relevant sensitive factors from a pre-built cargo database. This database is like a knowledge base, which stores the typical characteristics of various types of cargo. For example, after entering "electronic instruments", the system may automatically recognize that this type of cargo is usually afraid of shock and moisture, and has certain temperature requirements (such as 5°C to 35°C). If the information entered by the user explicitly mentions certain special needs, such as "moisture-proof", the database will further confirm and supplement this information to ensure that no key points are missed. Such searches can also be performed using large language models. In some trained large language models, such as Chatgpt, the corresponding cargo can be input to output the corresponding sensitive factors.

[0057] The extracted sensitive factor information is organized into a standardized format for easy use by subsequent system modules. For example, the system might generate a structured data file with the following content: Shock-sensitive: Yes, Pressure-sensitive: No, Humidity-sensitive: Yes, Temperature adaptability range: 5-35°C. This format can be implemented using JSON or XML, ensuring clear and consistent data transmission within the system.

[0058] Through this series of steps, the information collection unit can efficiently obtain and organize the sensitive characteristics of the goods, laying the foundation for subsequent module matching and optimization.

[0059] After collecting information about the cargo's sensitive factors, the system selects appropriate standard modules from a rich library of module functions. This library is like a toolbox filled with various functional "parts," each designed for specific transportation needs. These modules are categorized by functional characteristics to ensure they cover the various possible protection requirements for cargo.

[0060] For example, a shock-absorbing module is designed specifically for shock-sensitive cargo and may include built-in cushioning materials of varying strengths, such as foam pads, air bags, or spring shock absorbers. For example, if fragile glassware is being transported, the system might select a high-grade shock-absorbing module that can absorb up to 90% of the shock energy, ensuring the cargo is not damaged during bumpy transport.

[0061] Dehumidification modules are suitable for moisture-sensitive cargo. They can regulate the humidity level within the container through built-in desiccant or small dehumidification equipment. For example, when transporting a batch of wooden furniture, this module can maintain humidity below 50% to prevent the wood from deforming due to moisture. Temperature control modules are more suitable for cargo that requires a specific temperature, such as pharmaceuticals or frozen foods. They may contain refrigeration and heating elements to stabilize the temperature within a user-specified range, such as 0°C to 8°C.

[0062] In addition, there are support modules for securing irregularly shaped cargo to prevent shifting during transport; insulation modules for mitigating temperature fluctuations with insulating materials; and crush-resistant modules for protecting vulnerable cargo with high-strength materials. These modules are designed to be highly flexible, allowing their functional strength to be adjusted based on specific needs. For example, crush-resistant modules may have different load-bearing ratings, ranging from 50kg to 500kg, allowing users to select the appropriate model based on the weight of their cargo.

[0063] The modular nature of this module library is one of the system's core advantages. Each module is like a building block that can be used individually or combined to form a customized protection solution.

[0064] With the cargo's sensitivity information and the module function library, the next step is to determine which modules are most suitable for the current transportation task. This is the task of the matching and scoring unit. Using a scientific method, it matches the module's functional characteristics with the cargo's sensitivity factors, assigns a score to each module, and ultimately generates a score sheet.

[0065] like Figure 3 As shown, this process begins with parameter mapping. The system examines each of the cargo's sensitive factors and identifies modules that can address them. For example, if the cargo is sensitive to vibration, the system will select all vibration-proofing modules; if it's also sensitive to moisture, it will add a dehumidification module. This mapping acts like a bridge, connecting needs with solutions.

[0066] The scoring module then assigns a score to each module using a weighted scoring algorithm. This algorithm considers multiple factors, such as the module's functional effectiveness, cost, size, and weight. For example, if a shock-absorbing module absorbs 80% of vibration, costs 100 yuan, and is of moderate size, the system might give it a higher score, such as 85. Meanwhile, another shock-absorbing module offers better results (absorbing 90%) but costs twice as much and is larger, so it might receive a score of 80, due to its lower cost-performance ratio.

[0067] The specific scoring formula can be set as follows:

[0068] Sc=w1·E+w2·(1-C norm )+w3·(1-Si norm );

[0069] Here, w1, w2, and w3 are weight coefficients, representing the importance of functional effect, cost, and size, respectively, ranging from 0 to 1, and the sum is 1 (for example, w1 = 0.5, w2 = 0.3, w3 = 0.2). E is the quantitative value of the module effect (for example, the shockproof ability ranges from 0 to 1); C norm and Si norm It is the value after normalizing the cost and size (for example, dividing by the maximum value, ranging from 0 to 1). The significance of this formula is to balance the effect and resource consumption to ensure that the selected module is both practical and economical.

[0070] Finally, the scoring table generation module compiles the scores for all modules into a table and sorts them from highest to lowest. For example, for shock-sensitive goods, the scoring table might display: Shockproof Module A (85 points), Shockproof Module B (80 points), Shockproof Module C (70 points). This ranking makes subsequent module selection more intuitive.

[0071] After the scoring table is generated, the system needs to select the best combination from a large number of modules, which should not only meet all the protection needs of the goods but also take into account the constraints of cost and space. Figure 4 As shown, this part of the work is completed by the combinatorial optimization unit, which is achieved through mathematical modeling and algorithm search.

[0072] First, the optimization model building module creates a mathematical model based on the score table. The core of this model is an objective function, such as maximizing the total score of all modules:

[0073]

[0074] Among them, Sc i is the score of the i-th module, x i Is a variable of 0 or 1, indicating whether this module is selected. At the same time, the model will add some constraints, such as the total cost cannot exceed the budget:

[0075] Cost i is the price of the i-th module, and B represents the budget value;

[0076] There are also volume restrictions:

[0077] Where V i represents the volume caused by the i-th module, and Vmax is the total volume allowed for the container.

[0078] These constraints ensure that the combination scheme is feasible in practical applications.

[0079] Since the number of possible combinations is very large (for example, there are 10 modules, each of which is optional or not, there are 2 10 = 1024 combinations), which is impractical to calculate one by one using traditional methods. Therefore, the system uses heuristic optimization algorithms to quickly find a near-optimal solution. Commonly used algorithms include greedy algorithms, genetic algorithms, and ant colony algorithms.

[0080] The greedy algorithm starts with an empty set and gradually builds up a module combination, selecting the module with the highest current score each time until all requirements are met or a constraint limit (such as cost or volume) is reached. Its core is to make local optimal decisions and quickly obtain a feasible solution.

[0081] More specifically, the process begins with initialization, where the initial portfolio is empty and has a total score of 0. From the remaining modules, the highest-scoring module is selected and added to the portfolio. Scoring is based on the compatibility of the module's functionality with the cargo requirements. After adding a module, verification is performed to ensure that all protection requirements (such as shock and moisture resistance) are met, and that cost or volume limits are not exceeded. If not all requirements are met and the constraints allow, the next highest-scoring module is selected. If all requirements are met or no more modules can be added, the process stops.

[0082] Example: Suppose the cargo requires shockproofing, moisture-proofing, and support protection. First, starting from an empty set, the system selects the highest-scoring shockproof module (e.g., shockproof module A with a score of 85) and adds it to the combination, bringing the total score to 85. Second, from the remaining modules, the system selects the highest-scoring dehumidification module (e.g., dehumidification module B with a score of 80), bringing the total score to 165. Third, if a support module is also required, the system selects the highest-scoring support module (e.g., support module C with a score of 75), bringing the total score to 240. If all requirements (shockproofing, moisture-proofing, and support) are met and no constraints are exceeded, the output combination is: shockproof module A + dehumidification module B + support module C, with the highest possible total score.

[0083] An example of a genetic algorithm is as follows:

[0084] Genetic algorithms imitate biological evolution by randomly generating multiple combination schemes (individuals), using "crossover" and "mutation" operations to continuously optimize, explore the global solution space, and ultimately find a better solution.

[0085] First, initialize the population and randomly generate multiple module combinations (such as 10 individuals), each of which is composed of several modules. Next, calculate the total score of each combination, and the higher the score, the better. Select some individuals (such as the top 50%) according to the score to enter the next generation. Exchange modules between selected individuals to generate new individuals. For example, individual A (shockproof module A + dehumidification module B) and individual B (shockproof module C + support module D) cross to generate a new individual (shockproof module A + support module D). The new individual randomly replaces the module with a small probability, such as changing support module D to support module G. Repeat selection, crossover, and mutation for several rounds (such as 50 generations) until the individual with the highest score is stable or the iteration limit is reached. Select the individual with the highest score as the final solution.

[0086] For example, the initial population consists of three individuals: Individual A: Shockproof Module A (85 points) + Dehumidification Module B (80 points), for a total score of 165; Individual B: Shockproof Module C (70 points) + Support Module D (75 points), for a total score of 145; and Individual C: Dehumidification Module E (60 points) + Insulation Module F (65 points), for a total score of 125. The first step is to select individuals A and B with high scores. The second step is to cross-generate new individuals, such as Individual D (Shockproof Module A + Support Module D, for a total score of 160). The third step is to perform mutation, potentially replacing Support Module D in Individual D with Support Module G (80 points), raising the total score to 165. After iteration, the final output may be a combination with a higher score, such as Shockproof Module A + Dehumidification Module B + Support Module G.

[0087] After selecting the module combination, the system needs to "assemble" these modules into a complete container structure and generate a detailed blueprint. This part of the work is handled by the structure generation unit, which converts the abstract module selection into a concrete implementation plan.

[0088] First, the structural layout module determines the placement and connection of each module within the container. For example, an anti-vibration module might be placed underneath and around the cargo, forming a protective layer; a dehumidification module might be placed in a corner, connected to the entire space via ducts. The system considers the size and shape of the modules to ensure they fit seamlessly together while leaving ample space for the cargo itself.

[0089] Next, the parameter configuration module sets specific operating parameters for each module. For example, the temperature control module might have a target temperature of 5-8°C, and the dehumidification module a target humidity of 40%. These parameters are determined directly based on the cargo's sensitivity information to ensure the modules are operating at their maximum potential.

[0090] Finally, the blueprint output module generates a complete container structure blueprint, including module types, 3D layout, parameter settings, and assembly sequence. For example, the blueprint might instruct, "First install the bottom anti-vibration module, then add the cargo, then secure the side support modules, and finally connect the top dehumidification module." This blueprint can be displayed as a graphical file (like a CAD drawing) or output as structured instructions (like a JSON file), making it easy for automated assembly systems to directly read and execute it.

[0091] Through the collaborative work of these five units, this modular, intelligent, prefabricated intermodal container system achieves intelligent and automated delivery from cargo information collection to final structure generation. For example, if a pharmaceutical company needs to transport a batch of vaccines, the system will automatically select temperature control and shockproof modules based on the vaccine's temperature requirements (2-8°C) and shockproofing requirements. After optimizing the combination, it generates a blueprint for rapid assembly on the automated production line.

[0092] More specifically, each module of the present invention can be implemented in the following manner:

[0093] The information collection unit is responsible for obtaining sensitive factor information of the goods to be transported. To implement this, we can use the following technical means: Use HTML, CSS, and JavaScript to develop a web-based user input interface. Users enter basic information about the goods (such as type, size, weight) and special requirements (such as shockproof and moisture-proof) through the browser. The back-end uses Python's Flask framework to receive and process this data to ensure data integrity and preliminary verification. A MySQL database is used to store sensitive factor information of common goods. After the user enters the type of goods, the system automatically extracts relevant data through SQL queries. Python's pymysql library can realize database connection and query. The information input by the user and extracted from the database is standardized into JSON format through Python scripts to ensure that subsequent modules can be used seamlessly. This does not require a large language model, but can be achieved through simple rules and scripts. This method relies on traditional web development technology and database technology, has strong implementation and mature technology, and is suitable for rapid deployment and actual use.

[0094] The module function library is used to store a variety of standard modules and their functional characteristics. The specific implementation is as follows: A MongoDB database is used to store module information because it supports a flexible document structure, suitable for storing diverse module attributes (such as functionality, cost, and size). Each module is stored as a JSON document for easy querying and updating. A web-based management system is developed, using the React framework on the front end and Node.js on the back end, allowing administrators to add, edit, and delete modules. Data is interacted with MongoDB via a RESTful API. This approach leverages existing NoSQL databases and web technologies, is easy to scale and maintain, and is completely feasible to implement.

[0095] The matching scoring unit is responsible for generating a module compatibility score table. This is achieved by using a Python rule engine that uses if-else logic to match the cargo's sensitivity factors with module features. For example, if the cargo is sensitive to shock, shockproof modules are prioritized. The scoring algorithm uses a weighted approach, with weights preset by experts (e.g., shockproof modules are considered important at 50%). The Python NumPy library is used to calculate the score for each module.

[0096] The combinatorial optimization unit selects the optimal combination from the module library. This is achieved as follows: A linear programming model is constructed using the Python PuLP library. The goal is to maximize the total score, subject to constraints such as cost and volume. PuLP's built-in solvers (such as CBC) are called to calculate the optimal solution. For complex scenarios, a genetic algorithm, implemented using the DEAP library, can be used to simulate natural selection and find suboptimal solutions.

[0097] The structure generation unit generates a containerized structure blueprint. This is achieved by using Python to call the Blender API to automatically generate a 3D model of the module arrangement. Blender is an open-source 3D modeling tool that supports scripting and can generate structures based on module size and position. Module parameters (such as temperature control values) are set based on cargo requirements through Python scripts and embedded into the model. The blueprint output is generated as a DXF file (compatible with AutoCAD) using the Python ezdxf library to ensure integration with existing manufacturing processes.

[0098] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A modular intelligent assembled intermodal container system, characterized in that: include: An information collection unit, used to obtain sensitive factor information of the goods to be transported; Module function library, used to store a variety of standard modules with different functional characteristics; The matching scoring unit is used to build a module matching scoring model and generate a module matching scoring table based on the matching relationship between the functional characteristics of each standard module and the sensitive factors of the goods; A combination optimization unit, configured to select a set of optimal module combination solutions that meet protection requirements from the module function library using an optimization algorithm according to the module adaptation score table; A structure generation unit is used to generate a container structure blueprint based on the optimal module combination solution.

2. The modular intelligent assembled intermodal container system according to claim 1, characterized in that: The information collection unit includes: Input interface module, used to receive goods description information input by the user; A database extraction module, configured to extract corresponding sensitive factor information from a cargo database according to the cargo description information; The structured output module is used to convert the acquired sensitive factor information into a standardized structured format.

3. The modular intelligent assembled intermodal container system according to claim 1 or 2, characterized in that: The sensitive factor information includes any one or more of the following: fear of shock, fear of pressure, fear of moisture, and temperature adaptation range.

4. The modular intelligent assembled intermodal container system according to claim 1, characterized in that: The module function library is modularly classified according to functional characteristics, and includes at least one or more of the following types of standard modules: Shockproof modules with different levels of buffering capabilities; Dehumidification module, used to regulate humidity levels within a closed environment; Temperature control module, used to maintain the required temperature range of the goods; Support modules are used to fix the structure or balance the center of gravity of irregular cargo; Thermal insulation module, used to reduce the heat conduction rate to delay temperature changes; The anti-pressure module has structural pressure resistance to protect sensitive cargo.

5. The modular intelligent assembled intermodal container system according to claim 1, characterized in that: The matching scoring unit includes: Parameter mapping module, used to map the functional characteristics of each standard module with the sensitive factors of the goods; A scoring calculation module is used to calculate the fitness score of each standard module using a weighted scoring algorithm based on the mapping results; The scoring table generation module is used to generate a module adaptation scoring table.

6. The modular intelligent assembled intermodal container system according to claim 5, characterized in that: When generating the adaptation score table, the score table generating module sorts the adaptation scores therein from high to low.

7. The modular intelligent assembled intermodal container system according to claim 1, characterized in that: The combination optimization unit includes: An optimization model building module is used to build a combination optimization model based on the adaptation score table; Algorithm execution module, used to call the heuristic optimization algorithm execution module combination search; The combination scheme screening module is used to screen out the optimal module combination scheme from multiple feasible solutions and output it as the final assembly scheme.

8. The modular intelligent assembled intermodal container system according to claim 7, characterized in that: The heuristic optimization algorithm is any one of the following: greedy algorithm, genetic algorithm or ant colony algorithm.

9. The modular intelligent assembled intermodal container system according to claim 1, characterized in that: The structure generation unit includes: The structural arrangement module is used to determine the arrangement order, spatial position and relative connection method of each standard module according to the module combination plan; Parameter configuration module, used to configure corresponding functional parameters for each selected module; The blueprint output module is used to generate the container structure blueprint and output it in the form of graphical files and structured instruction formats for reading and execution by the automated assembly system.

10. The modular intelligent assembled intermodal container system according to claim 9, characterized in that: The output container structure blueprint includes module type, three-dimensional layout diagram, functional parameter settings and assembly sequence instructions.

Images