Generated material distribution method combined with artificial intelligence and cloud platform

Abstract

The invention discloses a method for generating material distribution in combination with artificial intelligence and a cloud platform. The method comprises the following steps: receiving data associated with one or more entities; generating, using at least one processor, one or more attribute values for each of the one or more entities based on the received data; selecting, from a set of candidates, an optimal candidate corresponding to each of the one or more entities; assigning the selected optimal candidate to a corresponding entity; according to the invention, the optimal candidate is dynamically selected from a group of candidates through the generated attribute value, and the candidate is re-evaluated and adjusted through the feedback mechanism and the continuous optimization capability when new information is received, so that the optimization of the allocation scheme is ensured; therefore, the problems of low response speed and inflexible decision caused by dependence on static rules and manual intervention in a traditional system are solved, and the efficiency and accuracy of material distribution are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of material distribution, and in particular to a material distribution method and a cloud platform combined with artificial intelligence. Background Art

[0002] Traditional material allocation systems usually rely on manual and static rules to manage the supply chain. These systems lack real-time response and adaptive capabilities and cannot effectively cope with rapidly changing market demands and supply chain conditions. The efficiency and accuracy of material allocation are often limited, resulting in inefficient supply chain operations and slow response, making it difficult to meet the dynamic needs of modern enterprises. Summary of the invention

[0003] The purpose of the present invention is to provide a material allocation generation method and cloud platform combined with artificial intelligence, which can re-evaluate and adjust candidates when new information is received through feedback mechanism and continuous optimization capabilities to ensure the optimization of the allocation plan.

[0004] The purpose of the present invention can be achieved through the following technical solutions: This application provides a method for generating material allocation in combination with artificial intelligence, comprising the following steps: receiving data associated with one or more entities; generating, using at least one processor, one or more attribute values ​​for each of the one or more entities based on the received data; selecting, from a set of candidates, an optimal candidate corresponding to each of the one or more entities; wherein the optimal candidate is a candidate determined to best fulfill the requirement for a corresponding entity of the one or more entities based on the one or more attribute values ​​generated; The selected best candidate is assigned to a corresponding entity.

[0005] Furthermore, the method further includes: feeding back the assignment result of the optimal candidate to the group of candidates.

[0006] Furthermore, it also includes dynamically re-evaluating and adjusting the assigned best candidate based on the information fed back to a group of candidates, including: Receiving new information that the best candidate entity has been assigned; re-evaluating the assigned best candidate based on the new information received; If the received new information indicates that the already assigned best candidate is no longer the best candidate, Then the following operations are performed: a new optimal candidate is identified from the remaining set of candidates based on the result of the re-evaluation, and the new optimal candidate is assigned to the corresponding entity.

[0007] Further, the method of dynamically adjusting the set of candidates by calculating the generated attribute values ​​includes: adding a second layer of candidates to the set of candidates based on the one or more generated attribute values.

[0008] Furthermore, the group of candidates also includes: optimizing the candidate group based on the one or more attribute values ​​generated, and deleting the third-level candidates in the group of candidates when the existence of the third-level candidates no longer meets the current attribute value evaluation criteria.

[0009] Further, the group of candidates also includes: adding a fourth-layer candidate to the group of candidates as a first-layer candidate based on the one or more attribute values ​​generated; adding a fifth-layer candidate to the group of candidates as a second-layer candidate based on the one or more attribute values ​​generated; deleting a sixth-layer candidate based on the one or more attribute values ​​generated; converting a seventh-layer candidate from the first layer to the second layer of the group of candidates based on the one or more attribute values ​​generated; and converting an eighth-layer candidate from the second layer to the third layer of the group of candidates based on the one or more attribute values ​​generated.

[0010] Further, based on the one or more attribute values ​​generated, the seventh layer candidate is converted from the second layer of the group of candidates to the first layer; and based on the one or more attribute values ​​generated, the eighth layer candidate is converted from the third layer of the group of candidates to the second layer.

[0011] A material distribution cloud platform generated in combination with artificial intelligence, including data collection module, processing module, distribution module and feedback module; The data collection module is responsible for collecting information related to the goods or items to be allocated; the processing module is responsible for analyzing the collected information and sorting the candidate carriers based on the analysis results to determine the optimal carrier; the allocation module is responsible for assigning the optimal carrier to the corresponding goods or items, and the feedback module is responsible for feeding back the allocation results to the processing module so that the processing module can update the ranking of the candidate carriers based on the allocation results.

[0012] Preferably, the material distribution cloud platform also includes a dynamic adjustment module, which is responsible for dynamically adjusting the number of candidate carriers based on information provided by the processing module.

[0013] Preferably, the material distribution cloud platform also includes a self-learning module, which is responsible for automatically learning the behavior patterns of candidate carriers based on historical data and adjusting the ranking of candidate carriers.

[0014] The beneficial effects of the present invention are: Through real-time data processing and analysis, it is possible to instantly receive and analyze dynamic data from suppliers, warehouses, demanders and other related entities, and use at least one processor to generate key attribute values, solving the problem of decision lag and inaccurate allocation decisions caused by the lack of real-time data processing capabilities in traditional systems, thereby improving the real-time and accuracy of allocation decisions, ensuring that all links in the supply chain operate efficiently under the guidance of the latest information, and improving overall operational efficiency; By dynamically selecting the best candidate from a group of candidates based on the generated attribute values, and re-evaluating and adjusting the candidates when new information is received through the built-in feedback mechanism and continuous optimization capabilities, the optimization of the allocation plan is guaranteed. At the same time, it also has the ability to dynamically adjust the candidate group, and can add or delete candidates according to the latest attribute values, as well as adjust the candidate hierarchy, thus solving the problems of slow response and inflexible decision-making caused by reliance on static rules and manual intervention in traditional systems. Through this dynamic selection and optimization mechanism, the efficiency and accuracy of material allocation are significantly improved, and adaptability and flexibility are enhanced, enabling it to quickly respond to changes in the market or supply chain and optimize the overall supply chain operational efficiency and responsiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0016] Figure 1 A schematic diagram of a process for generating material allocation in combination with artificial intelligence provided in Example 1 of the present application; Figure 2 A schematic diagram of a process for dynamically re-evaluating and adjusting the assigned optimal candidate by combining the method for generating material allocation with artificial intelligence provided in Example 1 of the present application; Figure 3 A schematic diagram of the structure of a material distribution cloud platform combined with artificial intelligence provided in Example 1 of the present application. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0018] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0019] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0020] Example 1 See also Figure 1-Figure 2 ,This embodiment provides a material allocation generation method and cloud platform combined with artificial intelligence, which re-evaluates and adjusts the candidates when new information is received, to ensure the optimization of the allocation scheme.

[0021] The present invention provides a method for generating material allocation in combination with artificial intelligence, comprising the following steps: In step S101, data associated with one or more entities is received; specifically, data associated with suppliers, warehouses or demanders, including receiving new orders, updating order status, canceling orders, adding new suppliers, changing suppliers, increasing production capacity, reducing production capacity, changing material types, adjusting prices and other information.

[0022] In step S102, at least one processor is used to generate one or more attribute values ​​for each of the one or more entities based on the received data; the attribute values ​​include but are not limited to demand forecast, inventory level, cost-benefit analysis, etc.; The best candidate corresponding to each of the one or more entities is selected from a group of candidates; these candidates are different material sources or allocation schemes, and the determination of the best candidate is based on the generated attribute values, and the importance or priority of the candidate can be dynamically adjusted according to the change of the attribute value to ensure that the requirements of the corresponding entity can be best fulfilled.

[0023] In step S103, selecting an optimal candidate corresponding to each of the one or more entities from a group of candidates, wherein the optimal candidate is a candidate determined to best fulfill the requirement for the corresponding entity of the one or more entities based on the generated one or more attribute values; In step S104, the selected optimal candidate is assigned to a corresponding entity; Preferably, the method further includes, step S105, feeding back the assignment result of the optimal candidate to the group of candidates.

[0024] Preferably, in step S105, it also includes dynamically re-evaluating and adjusting the assigned optimal candidate according to the information fed back to the group of candidates, and the specific contents include: S201, receiving new information about the entity that has been assigned the best candidate; S202, re-evaluating the assigned best candidate based on the received new information; S203: If the received new information indicates that the assigned optimal candidate is no longer the optimal candidate; S204: perform the following operations: identify a new optimal candidate from the remaining set of candidates based on the result of the re-evaluation, and assign the new optimal candidate to the corresponding entity.

[0025] A highly dynamic and adaptive material allocation optimization mechanism has been implemented. It receives and analyzes new information about assigned candidates in real time, re-evaluates existing allocations to ensure that the allocation plan is always optimal. When new information shows that the current candidate no longer meets the optimal criteria, the system will automatically screen out new optimal options from other candidates and quickly update the assignment, thereby ensuring that material allocation decisions are always the latest and most accurate, effectively responding to rapid changes in the market and supply chain, and improving overall operational efficiency and responsiveness.

[0026] Preferably, the method of dynamically adjusting the set of candidates by calculating the generated attribute values ​​comprises: adding a second layer of candidates to the set of candidates based on the generated one or more attribute values.

[0027] Preferably, the group of candidates also includes: optimizing the candidate group based on the one or more attribute values ​​generated, and deleting the third-layer candidates in the group of candidates when the existence of the third-layer candidates no longer meets the current attribute value evaluation criteria.

[0028] Not only can new candidates be added, but the hierarchy of existing candidates can also be deleted or adjusted based on the generated attribute values. This dynamic adjustment mechanism enables the system to respond quickly to changes in the market or supply chain.

[0029] Preferably, the group of candidates also includes: adding fourth-layer candidates to the group of candidates as first-layer candidates based on the one or more attribute values ​​generated; adding fifth-layer candidates to the group of candidates as second-layer candidates based on the one or more attribute values ​​generated; deleting sixth-layer candidates based on the one or more attribute values ​​generated; converting seventh-layer candidates from the first layer to the second layer of the group of candidates based on the one or more attribute values ​​generated; and converting eighth-layer candidates from the second layer to the third layer of the group of candidates based on the one or more attribute values ​​generated.

[0030] Dynamically optimize and manage candidate groups. Through evaluation results based on key attribute values, candidates at different levels are upgraded, demoted or eliminated, ensuring that the candidate pool always maintains the best and most competitive options to adapt to the ever-changing market and supply chain.

[0031] Preferably, the group of candidates also includes: adding fourth-layer candidates to the group of candidates as first-layer candidates based on the one or more attribute values ​​generated; adding fifth-layer candidates to the group of candidates as second-layer candidates based on the one or more attribute values ​​generated; deleting sixth-layer candidates based on the one or more attribute values ​​generated; converting seventh-layer candidates from the second layer to the first layer of the group of candidates based on the one or more attribute values ​​generated; and converting eighth-layer candidates from the third layer to the second layer of the group of candidates based on the one or more attribute values ​​generated.

[0032] Specifically, this passage describes a dynamic candidate tier adjustment mechanism, the purpose of which is to accurately promote, demote or eliminate candidates through real-time analysis of generated attribute values. Specifically, it allows lower-tier candidates (such as tier 4) to leap to higher tiers (such as tier 1) based on outstanding attribute performance, while removing candidates who no longer meet the criteria (such as tier 6) from the candidate pool, and adjusting some candidates between tiers based on their current performance (such as tier 7 to tier 2, or tier 8 to tier 2). The effect of this mechanism is to optimize material allocation decisions in the supply chain, ensure the flexibility and competitiveness of the supply chain, and improve the efficiency of resource allocation and the ability to respond to market changes.

[0033] It should be explained that, data associated with one or more entities is received; at least one processor is used to generate one or more attribute values ​​for each of the one or more entities based on the received data, and the best candidate corresponding to each of the one or more entities is selected from a group of candidates, wherein the best candidate is determined to be the candidate that best fulfills the requirements of the corresponding entity of the one or more entities based on the one or more attribute values ​​generated; the selected best candidate is assigned to the corresponding entity; the assignment result of the best candidate is fed back to the group of candidates; new information about the entity to which the best candidate has been assigned is received; the assigned best candidate is re-evaluated based on the received new information, and if the received new information indicates that the assigned best candidate still meets the requirements, the following operations are performed: the new information is added to a group of candidates.

[0034] This process intelligently analyzes data associated with entities, generates key attribute values, and selects the best candidates for material allocation based on them. At the same time, the assignment results and new information are integrated into the candidate group through a feedback mechanism, thereby achieving continuous evaluation and optimization of assigned candidates, ensuring that the material allocation plan always reflects the latest needs and conditions, thereby improving the responsiveness, flexibility and overall efficiency of the supply chain.

[0035] The effect of this process is to establish a flexible and responsive material allocation method that uses artificial intelligence technology to conduct in-depth analysis of entity-related data, generate key attribute values, intelligently select the best candidates to meet entity needs, and dynamically re-evaluate and update the candidate pool when new information emerges. This mechanism not only ensures that material allocation decisions are always based on the latest and most accurate data, but also improves the adaptability and efficiency of the system through continuous feedback and information updates, thereby optimizing the operation of the entire supply chain.

[0036] Example 2 This embodiment is a material distribution cloud platform combined with artificial intelligence, which is applied to a production line monitoring method for digital production. Figure 3 As shown, the material distribution cloud platform includes a data collection module, a processing module and a distribution module; The data collection module is responsible for collecting information related to the goods or items to be allocated; the processing module is responsible for analyzing the collected information and sorting the candidate carriers based on the analysis results to determine the optimal carrier; the allocation module is responsible for assigning the optimal carrier to the corresponding goods or items.

[0037] Preferably, the material distribution cloud platform also includes a feedback module, which is responsible for feeding back the distribution results to the processing module, so that the processing module can update the ranking of candidate carriers based on the distribution results. In this way, the processing module can adjust the ranking of candidate carriers in real time, thereby improving distribution efficiency and accuracy.

[0038] Preferably, the material distribution cloud platform also includes a dynamic adjustment module, which is responsible for dynamically adjusting the number of candidate carriers based on the information provided by the processing module. In this way, the processing module can flexibly adjust the number of candidate carriers according to current demand, thereby further improving distribution efficiency and accuracy.

[0039] Preferably, the material distribution cloud platform also includes a self-learning module, which is responsible for automatically learning the behavior patterns of candidate carriers based on historical data and adjusting the ranking of candidate carriers accordingly. In this way, the processing module can more accurately predict the performance of candidate carriers, thereby further improving distribution efficiency and accuracy.

[0040] Example 1 combines the contents of Example 2, specifically by combining artificial intelligence technology, to achieve highly dynamic and adaptive optimization of the material allocation process, and solves many problems existing in traditional systems. First, through real-time data processing and analysis capabilities, it can instantly receive and analyze dynamic data from suppliers, warehouses, demanders and other related entities, including new orders, order status updates, supplier changes, production capacity adjustments, etc. These data are processed by at least one processor to generate key attribute values, such as demand forecasts, inventory levels, cost-benefit analysis, etc.

[0041] In actual operation, the system selects the best candidate from a group of candidates based on the generated attribute values. These candidates can be different material sources or allocation schemes. The intelligent analysis capability allows it to dynamically adjust the importance or priority of the candidates according to the changes in the attribute values ​​to ensure that the selected candidates can best meet the needs of the corresponding entities. Then, through the feedback mechanism and continuous optimization capabilities, the assignment results of the best candidates are fed back to the candidate group, and new information about the assigned candidates is received. This mechanism enables the system to re-evaluate the assigned best candidates based on the latest information to ensure that the allocation plan is always optimal. If new information shows that the current candidate no longer meets the optimal criteria, a new best candidate will be automatically screened and the assignment will be updated; With the ability to dynamically adjust the candidate population, add or remove candidates based on generated attribute values, and adjust the tiers of candidates, this mechanism enables the system to quickly respond to changes in the market or supply chain, ensuring that allocation decisions are based on the latest and most accurate data.

[0042] Ultimately, through intelligent analysis and dynamic adjustment, the efficiency and accuracy of material distribution were significantly improved, and through continuous feedback and information update mechanisms, intelligent and adaptive optimization of supply chain management was achieved, optimizing the operational efficiency and responsiveness of the overall supply chain.

[0043] Example 3 An electronic device is provided, comprising: a memory configured to store instructions; and a processor connected to the memory and configured to access the memory and execute the instructions to: receive data associated with one or more entities; use at least one processor to generate one or more attribute values ​​for each of the one or more entities based on the received data; select an optimal candidate corresponding to each of the one or more entities from a group of candidates, wherein the optimal candidate is a candidate determined to best fulfill requirements for the corresponding entity of the one or more entities based on the one or more attribute values ​​generated; and assign the selected optimal candidate to the corresponding entity.

[0044] Example 4 A computer-readable medium is provided, on which a computer program is stored. The computer program has program instructions embodied therein, and the program instructions are executable by a computing device so as to enable the computing device to execute the method for generating material allocation combined with artificial intelligence.

[0045] Example 5 This embodiment adds a description of the candidate evaluation and selection algorithm in the process of selecting the best candidate. By adopting advanced multi-objective optimization algorithms, such as NSGA-II, intelligent optimization of material allocation in the supply chain is achieved. It not only comprehensively considers multiple objectives such as demand satisfaction, inventory cost, transportation cost, delivery time and supply chain risk, and generates a Pareto optimal solution set that balances various objectives, but also adjusts and optimizes the material allocation plan in real time through a dynamic feedback mechanism, ensuring the efficient operation of the supply chain, maximizing cost-effectiveness and minimizing risks, while improving the adaptability and responsiveness of the supply chain.

[0046] Specifically include: Receive data associated with one or more entities, including data related to suppliers, warehouses or demand parties, which may include: new order information, updated order status, order cancellations, new suppliers, supplier changes, increased or decreased capacity, changes in material types and price adjustments; At least one processor is used to generate one or more attribute values ​​for each entity based on the received data; the attribute values ​​include: demand forecast, inventory level, cost-benefit analysis, delivery time and supply chain risk assessment.

[0047] Among them, by defining the objective function, an objective function is established for each optimization goal, which will be used to evaluate the performance of candidates on different goals; including demand satisfaction: maximizing order fulfillment rate; inventory cost: minimizing inventory holding cost; transportation cost: minimizing transportation cost; delivery time: minimizing delivery time; supply chain risk: minimizing the risk of supply chain disruption; Set constraints, including supplier capacity limits, warehouse storage capacity, budget limits, and delivery time windows; Use multi-objective optimization algorithms to build optimization models and integrate multiple objective functions into one framework; The specific optimization model is expressed as: Create an initial population, which is a potential solution generated randomly or based on a heuristic method. Calculate the fitness of each individual in the initial population, that is, their performance on multiple objective functions, perform non-dominated sorting, and divide the individuals in the population into different levels according to the non-dominated relationship. If a solution dominates another solution, that is, it is not worse in all objectives and better in at least one objective, it is considered to be better. For individuals in the same non-dominated level, the crowding degree is calculated to measure the distribution density of the solution. The higher the crowding degree, the better the diversity of the solution. Based on the non-dominated sorting and crowding degree, excellent individuals are selected to be retained for the next generation. The selected individuals are crossover operated to generate new offspring. The crossover operation should be designed according to the characteristics of the problem to maintain the effectiveness of the solution. The offspring are mutated to introduce new genetic diversity to prevent the algorithm from premature convergence. The newly generated offspring are merged with the current population to prepare for the selection of the next generation. A new round of fitness evaluation, non-dominated sorting and crowding degree calculation is performed on the merged population. The iterative process is carried out. After each iteration, check whether the algorithm converges to a set of stable solutions. By solving the optimization model, a Pareto optimal solution set is obtained; these solutions represent the trade-offs between different objectives, ensuring that each solution cannot be further improved on a certain objective without losing the performance of other objectives; candidates are evaluated, each solution in the Pareto optimal solution set is evaluated, and the candidate that best meets the comprehensive requirements is selected.

[0048] Assign the selected best candidates to the corresponding entities to ensure that they can meet the actual supply chain needs; The assignment result of the selected best candidate is fed back to the system, and its actual performance is recorded. Then, based on the feedback information and new data, the assigned best candidate is re-evaluated. If the new information shows that the current candidate is no longer the best choice, a new best candidate is identified from the remaining set of candidates based on the result of the re-evaluation and assigned to the corresponding entity.

[0049] Example 6 The material allocation method combined with artificial intelligence is applied to a large manufacturing company whose supply chain network includes multiple suppliers, warehouses and demanders. The company needs to handle various order status changes and supply chain condition updates, such as order additions, cancellations, supplier changes, increases or decreases in production capacity, etc.

[0050] Specific process: Data reception: The enterprise first receives data associated with the supply chain entities, including the generation of new orders, updates to order status, changes in supplier information, adjustments to inventory levels, changes in material types, and price fluctuations.

[0051] Attribute value generation: Using at least one processor, attribute values ​​of each entity are generated based on the received data, such as key indicators such as demand forecast, inventory level, cost-benefit analysis, etc.

[0052] Best candidate selection: Among a set of candidates, which may be different material sources or allocation schemes, the best candidate is selected to meet the needs of each entity based on the generated attribute values.

[0053] Candidate assignment: Assign the selected best candidate to the corresponding entity, such as allocating materials from a specific supplier to a specific demander or warehouse.

[0054] Feedback and dynamic adjustment: Feedback the assignment results of the best candidates to the candidate population, and re-evaluate the assigned best candidates when new information about the assigned entities is received.

[0055] Specifically: When an enterprise receives an urgent order, the demand forecast attribute value will be updated accordingly, and a new optimal supplier will be re-evaluated and selected based on the new attribute value. If a supplier cannot meet the demand due to production capacity issues, the candidates will be dynamically adjusted based on cost-benefit analysis and other attribute values. It may be possible to convert the second-tier candidates to the first tier, or remove options that no longer meet the standards from the third-tier candidates.

[0056] In the supply chain, if a new supplier demonstrates higher cost-effectiveness and faster delivery capabilities, the system will convert it from a fourth-tier candidate to a first-tier candidate based on these generated attribute values.

[0057] Preferred solution: When market conditions change, such as raw material price fluctuations, the system will automatically promote more cost-effective suppliers from the second tier to the first tier based on the new cost-effectiveness analysis.

[0058] If a supplier is downgraded due to quality issues, the system will move it from the first tier to the second tier based on the quality attribute value, and may promote a new supplier from the fifth tier as a substitute.

[0059] Through this intelligent material allocation method, enterprises can achieve fast, accurate and automated management of material allocation in the supply chain, ensuring that relevant data can be updated in real time when urgent orders, market fluctuations or changes in supplier conditions occur, dynamically evaluate and select the best suppliers, automatically adjust the candidate hierarchy, and quickly respond to changes in demand to ensure that material allocation is always optimal, thereby significantly improving the efficiency and accuracy of material allocation, optimizing inventory management, reducing costs, enhancing market competitiveness, and ensuring the stability and adaptability of the supply chain.

[0060] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for generating material allocation in combination with artificial intelligence, characterized in that: receiving data associated with one or more entities; generating, using at least one processor, one or more attribute values ​​for each of the one or more entities based on the received data; selecting, from a set of candidates, an optimal candidate corresponding to each of the one or more entities; wherein the optimal candidate is a candidate determined to best fulfill the requirement for a corresponding entity of the one or more entities based on the one or more attribute values ​​generated; The selected best candidate is assigned to a corresponding entity.

2. The method for generating material allocation in combination with artificial intelligence according to claim 1, characterized in that: Also includes: The assignment result of the best candidate is fed back into the group of candidates.

3. The method for generating material allocation in combination with artificial intelligence according to claim 2, characterized in that: It also includes dynamically re-evaluating and adjusting the assigned best candidates based on information fed back into a group of candidates, including: Receiving new information that the best candidate entity has been assigned; re-evaluating the assigned best candidate based on the new information received; When the received new information indicates that the assigned best candidate is no longer the best candidate; Then the following operations are performed: a new optimal candidate is identified from the remaining set of candidates based on the result of the re-evaluation, and the new optimal candidate is assigned to the corresponding entity.

4. The method for generating material allocation in combination with artificial intelligence according to claim 3, characterized in that: The method of dynamically adjusting the set of candidates by calculating the generated attribute values ​​includes: adding a second layer of candidates to the set of candidates based on the one or more generated attribute values.

5. The method for generating material allocation in combination with artificial intelligence according to claim 3, characterized in that: The group of candidates further includes: optimizing the candidate group based on the one or more attribute values ​​generated, and deleting the third-layer candidates in the group of candidates when the existence of the third-layer candidates no longer meets the current attribute value evaluation criteria.

6. The method for generating material allocation in combination with artificial intelligence according to claim 5, characterized in that: The set of candidates also includes: adding a fourth layer candidate to the set of candidates as a first layer candidate based on the one or more attribute values ​​generated; adding a fifth layer candidate to the set of candidates as a second layer candidate based on the one or more attribute values ​​generated; deleting a sixth layer candidate based on the one or more attribute values ​​generated; converting a seventh layer candidate from the first layer to the second layer of the set of candidates based on the one or more attribute values ​​generated; and converting an eighth layer candidate from the second layer to the third layer of the set of candidates based on the one or more attribute values ​​generated.

7. The method for generating material allocation in combination with artificial intelligence according to claim 5, characterized in that: converting a seventh layer candidate from a second layer to a first layer of the set of candidates based on the one or more generated property values; and converting an eighth layer candidate from a third layer to a second layer of the set of candidates based on the one or more generated property values.

8. A cloud platform for material distribution combined with artificial intelligence, applied to the method for material distribution combined with artificial intelligence as claimed in any one of claims 1 to 7, characterized in that: The material distribution cloud platform is generated, including a data collection module, a processing module, a distribution module and a feedback module; The data collection module is responsible for collecting information related to the goods or items to be distributed; The processing module is responsible for analyzing the collected information, and ranking the candidate carriers based on the analysis results to determine the optimal carrier; The allocation module is responsible for assigning the best carrier to the corresponding goods or items; The feedback module is responsible for feeding back the allocation result to the processing module, so that the processing module can update the ranking of the candidate carriers based on the allocation result.

9. The material distribution cloud platform combined with artificial intelligence according to claim 8 is characterized by: The material distribution cloud platform also includes a dynamic adjustment module, which is responsible for dynamically adjusting the number of candidate carriers based on information provided by the processing module.

10. The material distribution cloud platform combined with artificial intelligence according to claim 8, characterized in that: The material distribution cloud platform also includes a self-learning module, which is responsible for automatically learning the behavior patterns of candidate carriers based on historical data and adjusting the ranking of candidate carriers.

Images