Intelligent screening and precise matching method for mission demand and supply information

Abstract

The present invention discloses an intelligent screening and precise matching method for guarantee task demand and supply information, which belongs to the field of data processing technology, including: collecting supply information based on preset types, establishing a material database based on the supply information; obtaining a demand list corresponding to the guarantee task performed by the demander, combining all demand lists to generate a demand database based on the guarantee task; constructing a screening matching model, the screening matching model analyzes and calculates the matching coefficient between the supply information and the demand list, and extracts supply response information from the material database based on the matching coefficient; constructing a mathematical model, evaluating the guarantee efficiency of the supply response information based on the mathematical model, adjusting the parameters of the screening matching model based on the guarantee efficiency, generating a precise matching model, and completing the guarantee task based on the precise matching model. The present invention can improve the comprehensiveness of intelligent screening and precise matching of guarantee tasks.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and specifically relates to an intelligent screening and precise matching method for guarantee mission requirements and supply information. Background Art

[0002] With the rapid development of information technology, especially driven by technologies such as the Internet of Things, big data, and artificial intelligence, the management of support demand and supply information for complex tasks has become increasingly important. In the fields of military operations, disaster relief, and large-scale project management, quickly and accurately matching demand and supply resources is the key to improving the efficiency and success rate of operations. In traditional support task management, information matching between demanders and suppliers is often done manually, which has the limitations of low efficiency and inaccurate matching.

[0003] In order to solve the above problems, some automated and intelligent matching systems have emerged in recent years. These systems improve the matching efficiency by integrating the information of demanders and suppliers and using database management and query technology. However, most of these systems are still based on static matching rules, lack the ability to adapt to dynamically changing environments, and have limited intelligence.

[0004] Therefore, it is necessary to build intelligent screening and precise matching algorithms to analyze and process a large amount of demand and supply information in real time, realize automated and intelligent matching, and achieve efficient and precise matching between demand and supply through the comprehensive use of modern information technology, especially artificial intelligence technology, so as to improve the execution efficiency and success rate of the guarantee mission. Summary of the invention

[0005] In view of the above-mentioned technical problems, the present invention provides an intelligent screening and precise matching method for guarantee task demand and supply information, which includes:

[0006] S1: Collecting supply information based on preset types, and establishing a material database based on the supply information;

[0007] S2: Obtain a demand list corresponding to the guarantee task to be performed by the demander, and combine all the demand lists to generate a demand database based on the guarantee task;

[0008] S3: constructing a screening matching model, wherein the screening matching model analyzes and calculates a matching coefficient between the supply information and the demand list, and extracts supply response information from the material database based on the matching coefficient;

[0009] S4: Construct a mathematical model, evaluate the guarantee efficiency of the supply response information based on the mathematical model, adjust the parameters of the screening and matching model based on the guarantee efficiency, generate a precise matching model, and complete the guarantee task based on the precise matching model.

[0010] Furthermore, in S2, establishing a material database comprises the following steps:

[0011] Digitally process the supply information based on the preset type to generate a structured table, and obtain relationship information between any two structured tables based on the ER model;

[0012] defining a first constraint condition of the structured table, constructing a first database based on the first constraint condition, and writing the structured table into the first database based on the relationship information;

[0013] The performance value of the first database is verified based on a preset period, the first database is optimized based on the performance value, and the material database is generated.

[0014] Further, extracting the supply response information comprises the following steps:

[0015] Extracting a first feature vector of the supply information and a second feature vector of the demand list based on a data mining algorithm, standardizing the first feature vector and the second feature vector to generate a supply-side feature vector and a demand-side feature vector respectively;

[0016] Calculate the cosine similarity between the supplier feature vector and the demander feature vector based on a matching algorithm, and generate the matching coefficient based on a value corresponding to the cosine similarity;

[0017] A first threshold is set, the supplier feature vector whose matching coefficient is greater than or equal to the first threshold is extracted and set as a reference feature vector, and the supply information corresponding to the reference feature vector is set as the supply response information.

[0018] Furthermore, the construction of the mathematical model comprises the following steps:

[0019] Evaluation information of the supply response information is extracted based on the evaluation tag, a multi-objective function is set based on the evaluation tag, and the mathematical model is constructed based on the multi-objective function and a second constraint condition, wherein the second constraint condition includes a constraint value corresponding to the evaluation tag.

[0020] Furthermore, the evaluating the guarantee efficiency of the supply response information based on the mathematical model comprises the following steps:

[0021] The mathematical model solves any supply response information based on the weighted sum method and outputs the response result;

[0022] Generate a transportation route based on the location information in the evaluation tag, collect a sequence of environmental factors that change over time in the transportation route, build a prediction model based on a neural network, input the sequence of environmental factors into the prediction model for training, and output a corresponding prediction result within a prediction time, and output a path optimization value corresponding to the prediction time based on the prediction result and the transportation route;

[0023] The response result and the path optimization value are normalized and then accumulated to output the guaranteed efficiency.

[0024] Furthermore, the generating of the accurate matching model comprises the following steps:

[0025] Obtain the guarantee efficiency corresponding to any of the supply response information, set the supply response information with the guarantee efficiency greater than or equal to a second threshold as the standard response information, obtain the correlation between any two standard response information based on the evaluation label, adjust the parameters of the screening and matching model based on the correlation, repeat this step until the total number of the standard response information output by the screening and matching model is less than a third threshold, and set the adjusted screening and matching model as the precise matching model.

[0026] Furthermore, completing the guarantee task based on the precise matching model includes the following steps:

[0027] The precise matching model matches the demand database with the material database to determine whether the demand list corresponds to the matched standard response information one-to-one. If not, the standard response information with the highest guarantee efficiency is set as the optimal response information. If the optimal response information corresponds to multiple demand lists, one demand list is selected in turn based on the time feature, and the remaining demand lists are re-matched. This step is repeated until the demand lists correspond to the matched standard response information one-to-one and all the guarantee tasks are completed.

[0028] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0029] The present invention first constructs a material database through structured tables, which is conducive to improving the integrity of supply information. Then, a demand database is generated by collecting the demand lists corresponding to the guarantee tasks, which can execute multiple guarantee tasks at the same time and improve the comprehensiveness of the demand lists. Finally, supply response information is extracted from the material database through a screening matching model, and the supply response information is evaluated through a mathematical model, which can improve the accuracy of analyzing the demand lists.

[0030] The present invention can also generate an accurate matching model by adjusting parameters of the mathematical model to the screening matching model, thereby realizing intelligent matching of multiple security tasks and improving the accuracy of matching the requirements of the security tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The present invention is a flowchart of the steps of an intelligent screening and precise matching method for guarantee mission requirements and supply information. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0033] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0034] like Figure 1 As shown, an intelligent screening and precise matching method for guarantee mission demand and supply information includes:

[0035] S1: Collect supply information based on preset types and establish a material database based on the supply information.

[0036] Specifically, in this embodiment, the supply information is the inventory information provided by the supplier, wherein the supplier refers to the support unit or warehouse distributed in certain specific areas, and the inventory information should include the name, type, specification, quantity (including inventory quantity and available quantity within a time limit) of the support materials such as accessories, tools, facilities, and technical materials, as well as the type, name, gender, age, major, professional title or functional level of the technicians. The material database refers to the database generated after analyzing and processing the supply information.

[0037] S2: Obtain the demand list corresponding to the guarantee task performed by the demander, and combine all demand lists to generate a demand database based on the guarantee task.

[0038] Specifically, in this embodiment, the demander refers to a relatively clear unit, the support task refers to the type of task to be performed, the demand list refers to the actual demand for specific support tasks (such as accessories, tools, facilities, technical materials and other support materials and technical personnel), and the demand database refers to a database that can form a digital demand information list (including the unit name, number, address of the demander, and the name, type, specification, quantity, time limit, etc. of the required support resources).

[0039] S3: Construct a screening and matching model. The screening and matching model analyzes and calculates the matching coefficient between the supply information and the demand list, and extracts the supply response information from the material database based on the matching coefficient.

[0040] Specifically, in this embodiment, the screening matching model refers to a model for matching demand and supply, wherein the screening matching model includes a data mining algorithm and a matching algorithm, and the data mining algorithm refers to the process of extracting valuable information and knowledge from a large amount of data through algorithms and statistical analysis methods, which can be used for cluster analysis, feature extraction, classification algorithms, and natural language processing. The matching algorithm refers to a function algorithm for calculating the matching coefficient. The matching coefficient is a coefficient value used to measure the degree of matching between the supply information and the demand list. The supply response information refers to the supply information in the material database that meets the demand list, wherein the number of supply response information can be multiple.

[0041] S4: Construct a mathematical model, evaluate the guarantee efficiency of the supply response information based on the mathematical model, adjust the parameters of the screening and matching model based on the guarantee efficiency, generate a precise matching model, and complete the guarantee task based on the precise matching model.

[0042] Specifically, in this embodiment, the mathematical model refers to a model used to analyze resource allocation problems, which usually includes a set of mathematical equations, inequalities, functions or logical expressions, which are used to capture and express the key features and internal laws of the problem, such as linear programming models, network flow models and multi-objective optimization models. Guarantee efficiency is a numerical value corresponding to the effectiveness of supply response information. By adjusting the parameters of the screening and matching model through guarantee efficiency, the screening and matching model after adjusting the parameters can be set as a precise matching model. The precise matching model can intelligently match the corresponding supply information to any demand list in the demand database in turn, and can complete various guarantee tasks quickly and accurately.

[0043] As a preferred technical solution of the present invention, establishing a material database includes the following steps:

[0044] The supply information is digitized based on the preset type to generate a structured table, and the relationship information between any two structured tables is obtained based on the ER model.

[0045] A first constraint condition of the structured table is defined, a first database is constructed based on the first constraint condition, and the structured table is written into the first database based on the relationship information.

[0046] The performance value of the first database is verified based on a preset period, the first database is optimized based on the performance value, and a material database is generated.

[0047] Specifically, in this embodiment, digital processing refers to the process of converting supply information in a non-digital format into a digital format so that the supply information can be recognized, stored, processed and analyzed by a computer system, including but not limited to data formatting, data cleaning and data encoding. A structured table refers to a structured spreadsheet or a table in a database format. The ER model (Entity-Relationship Model) is a data model used to describe entities in the real world and the relationships between entities. Relationship information refers to the fields of each structured table and the relationships between structured tables, including but not limited to logical relationships, foreign key relationships and entity data relationships.

[0048] The first constraint condition refers to the constraint information contained in the constructed database, including but not limited to primary key, foreign key and uniqueness constraint. The first constraint condition can set the way of writing or reading data in the first database.

[0049] The performance value refers to the result of monitoring the performance of the first database through a preset period, such as query response time, memory usage, etc. The first database is tuned through the performance value to generate a material database, that is, tuning operations such as adjusting memory allocation and optimizing query plans. The database management system can be effectively used to generate a material database from digitally processed data, and ensure the efficient operation of the material database and the security of the data.

[0050] As a preferred technical solution of the present invention, extracting supply response information includes the following steps:

[0051] Based on the data mining algorithm, the first feature vector of the supply information and the second feature vector of the demand list are extracted respectively, and the first feature vector and the second feature vector are standardized to generate the supply side feature vector and the demand side feature vector respectively.

[0052] The cosine similarity between the supplier's feature vector and the demander's feature vector is calculated based on the matching algorithm, and the matching coefficient is generated based on the numerical value corresponding to the cosine similarity.

[0053] A first threshold is set, a supplier feature vector whose matching coefficient is greater than or equal to the first threshold is extracted, and set as a reference feature vector, and supply information corresponding to the reference feature vector is set as supply response information.

[0054] Specifically, in this embodiment, the normalization process can ensure that each feature vector has equal importance in similarity calculation, including but not limited to minimum and maximum normalization, decimal scaling normalization, etc.

[0055] The matching algorithm refers to an algorithm that matches any supplier feature vector with a demand feature vector and calculates the cosine similarity between the two, where the cosine similarity is used to evaluate the similarity of the directions of the two feature vectors. Regardless of the size of the vectors, the value corresponding to the cosine similarity is set as the matching coefficient. The first threshold is a similarity threshold used to determine the degree of matching between the demander and the supplier. By comparing the matching coefficient and the first threshold, multiple supply response information can be extracted from the material database.

[0056] As a preferred technical solution of the present invention, constructing a mathematical model includes the following steps:

[0057] Evaluation information of the supply response information is extracted based on the evaluation tag, a multi-objective function is set based on the evaluation tag, and a mathematical model is constructed based on the multi-objective function and a second constraint condition, wherein the second constraint condition includes a constraint value corresponding to the evaluation tag.

[0058] Specifically, in this embodiment, the evaluation tag refers to the tag information used to evaluate whether the guarantee task is efficient, wherein the evaluation tag includes location information, storage information, and a deployment time window. The location information refers to the location of the supplier corresponding to the supply response information, and the route distance can be calculated through the location information. The storage information refers to the warehouse distribution of the supplier corresponding to the supply response information. The deployment time window refers to the deployment time of resources. The evaluation information refers to the data information contained in the guarantee task and the corresponding multiple supply response information extracted through the evaluation tag, including but not limited to text type and numerical type evaluation information.

[0059] The multi-objective function is a multi-objective optimization algorithm that can consider multiple objectives (multi-objective functions) simultaneously in an optimization process and try to find a set of solutions that achieve the best trade-off between multiple objectives. The multi-objective function includes but is not limited to demand coverage, supply resource utilization, cost-effectiveness, user satisfaction and other function distributions set by evaluation tags. The demand coverage refers to the proportion of the number of support task requirements that can be met through intelligent screening and precise matching to the total number of requirements. For example, if there are 100 support task requirements and the system can find suitable supply information for 90 of them, then the demand coverage is 90%. The supply resource utilization refers to the proportion of the number of supply resources actually used to the total number of supply resources. High utilization indicates that the system can effectively integrate and utilize existing resources to avoid waste. For example, if there are 100 units of supply resources and 80 units are actually used, then the supply resource utilization is 80%. User satisfaction can be summarized in text based on user feedback. Cost-effectiveness refers to the comprehensive consideration of costs and benefits to calculate the return on investment of the system to determine its economic feasibility. The second constraint refers to determining the constraint range of the multi-objective function corresponding to each evaluation tag.

[0060] For example, the demand coverage is maximized by the first formula, which is: ,in, is a binary decision variable that equals 1 if supply j is assigned to demand i and 0 otherwise; It is the demand measure of demand i for supply j. The optimal value of each objective function can be calculated by the first formula.

[0061] As a preferred technical solution of the present invention, evaluating the guarantee efficiency of supply response information based on a mathematical model includes the following steps:

[0062] The mathematical model solves any supply response information based on the weighted sum method and outputs the response result.

[0063] Generate a transportation route based on the location information in the evaluation label, collect the environmental factor sequence that changes over time in the transportation route, build a prediction model based on a neural network, input the environmental factor sequence into the prediction model for training, and output the corresponding prediction result within the prediction time, and output the path optimization value corresponding to the prediction time based on the prediction result and the transportation route.

[0064] The response results and path optimization values ​​are normalized and accumulated, and the guarantee efficiency is output.

[0065] Specifically, in this embodiment, the weighted sum method is a commonly used method in multi-objective optimization, which combines multiple objectives into a single scalar objective function by assigning weights to different multi-objective functions, wherein the weight of each evaluation information is determined according to the relative importance or priority of different evaluation labels. The response result refers to the result of the mathematical model analyzing and solving the supply response information.

[0066] The transportation route refers to the route for deployment after completing the guarantee task. The environmental factor sequence refers to the sequence data composed of time changes in the environmental factor values ​​corresponding to the historical data in the historical time period, where the environmental factors include but are not limited to traffic flow, weather and rainfall. The prediction model is a deep learning model constructed by a neural network, for example, the LSTM (Long Short-Term Memory) model. By training the prediction model with multiple environmental factor sequences, the environmental factors in the future prediction time can be predicted, and the prediction results corresponding to the environmental factors can be output. Then, the transportation route combined with the prediction results can predict the deployment time of the supply information for completing the guarantee task, and the proportion of the deployment time is set as the path optimization value. For example, the deployment time usually required for the transportation route is 5, and the predicted deployment time after combining the prediction results is 2, then the path optimization value is 5 / 2=2.5. If the predicted deployment time after combining the prediction results is smaller, the path optimization value is larger, indicating that the transportation route is more conducive to the deployment of supply response information within the prediction time.

[0067] Normalization can adjust the scale of the data to make the distribution of the data corresponding to the response results and path optimization values ​​more uniform and standardized.

[0068] As a preferred technical solution of the present invention, generating an accurate matching model includes the following steps:

[0069] Obtain the guarantee efficiency corresponding to any supply response information, set the supply response information with a guarantee efficiency greater than or equal to the second threshold as the standard response information, obtain the correlation between any two standard response information based on the evaluation label, adjust the parameters of the screening matching model based on the correlation, repeat this step until the total number of standard response information output by the screening matching model is less than the third threshold, and set the adjusted screening matching model as the precise matching model.

[0070] Specifically, in this embodiment, since there may be multiple supply response information, the guarantee efficiency corresponding to the demand list is multiple, and it is necessary to screen the multiple supply response information again by comparing the second threshold with the guarantee efficiency to generate standard response information. The correlation refers to the numerical ratio or supplier resource quantity ratio corresponding to the two standard response information determined by the relationship information between the two standard response information in the material database. For example, both the standard response information A1 and the standard response information A2 meet the demand list, but the supplier resource quantity corresponding to the standard response information A1 is twice the supplier resource quantity corresponding to the standard response information A2. The correlation between the two standard response information can be calculated as 1 / 2=0.5. The parameters of the screening matching model are then adjusted by the ratio of the correlation until the total number of standard response information matched by the screening matching model to the demand list is less than the third threshold, and an accurate matching model can be generated. This step can improve the matching accuracy of the supply information.

[0071] As a preferred technical solution of the present invention, completing the guarantee task based on the precise matching model includes the following steps:

[0072] The precise matching model matches the demand database with the material database to determine whether the demand list corresponds to the matching standard response information. If not, the standard response information with the highest guarantee efficiency is set as the optimal response information. If the optimal response information corresponds to multiple demand lists, one demand list is selected in turn based on the time characteristics, and the remaining demand lists are re-matched. Repeat this step until the demand list and the matching standard response information correspond to each other one-to-one and all guarantee tasks are completed.

[0073] Specifically, in this embodiment, since multiple guarantee tasks may be carried out simultaneously, the precise matching model matches all demand lists in the demand database with the supply information in the material database. One-to-one correspondence means that the standard response information matched by any demand list is unique, where the same standard response information may match multiple demand lists. Therefore, it is necessary to arrange the matching scheduling of guarantee tasks according to time characteristics. Through this step, the comprehensiveness of intelligent screening and precise matching of supply information can be improved.

[0074] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0075] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0076] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

[0078] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent screening and precise matching method for guarantee mission demand and supply information, characterized in that: The method comprises the following steps: Collect supply information based on preset types, and establish a material database based on the supply information; Obtain a demand list corresponding to the guarantee task performed by the demander, and combine all the demand lists to generate a demand database based on the guarantee task; Constructing a screening and matching model, wherein the screening and matching model analyzes and calculates a matching coefficient between the supply information and the demand list, and extracts supply response information from the material database based on the matching coefficient; Constructing a mathematical model, evaluating the guarantee efficiency of the supply response information based on the mathematical model, adjusting the parameters of the screening and matching model based on the guarantee efficiency, generating a precise matching model, and completing the guarantee task based on the precise matching model; Wherein, the construction of the mathematical model comprises the following steps: Extracting evaluation information of the supply response information based on the evaluation tag, setting a multi-objective function based on the evaluation tag, and constructing the mathematical model based on the multi-objective function and a second constraint condition, wherein the second constraint condition includes a constraint value corresponding to the evaluation tag; Generating an accurate matching model comprises the following steps: Obtain the guarantee efficiency corresponding to any of the supply response information, set the supply response information with the guarantee efficiency greater than or equal to a second threshold as the standard response information, obtain the correlation between any two standard response information based on the evaluation label, adjust the parameters of the screening and matching model based on the correlation, repeat this step until the total number of the standard response information output by the screening and matching model is less than a third threshold, and set the adjusted screening and matching model as the precise matching model.

2. The method according to claim 1, characterized in that The establishment of the material database comprises the following steps: Digitally process the supply information based on the preset type to generate a structured table, and obtain relationship information between any two structured tables based on the ER model; defining a first constraint condition of the structured table, constructing a first database based on the first constraint condition, and writing the structured table into the first database based on the relationship information; The performance value of the first database is verified based on a preset period, the first database is optimized based on the performance value, and the material database is generated.

3. The method according to claim 1, characterized in that Extracting the supply response information comprises the following steps: Extracting a first feature vector of the supply information and a second feature vector of the demand list based on a data mining algorithm, standardizing the first feature vector and the second feature vector to generate a supply-side feature vector and a demand-side feature vector respectively; Calculate the cosine similarity between the supplier feature vector and the demander feature vector based on a matching algorithm, and generate the matching coefficient based on a value corresponding to the cosine similarity; A first threshold is set, the supplier feature vector whose matching coefficient is greater than or equal to the first threshold is extracted and set as a reference feature vector, and the supply information corresponding to the reference feature vector is set as the supply response information.

4. The method according to claim 1, characterized in that: The evaluating the guarantee efficiency of the supply response information based on the mathematical model comprises the following steps: The mathematical model solves any supply response information based on the weighted sum method and outputs the response result; Generate a transportation route based on the location information in the evaluation tag, collect a sequence of environmental factors that change over time in the transportation route, build a prediction model based on a neural network, input the sequence of environmental factors into the prediction model for training, and output a corresponding prediction result within a prediction time, and output a path optimization value corresponding to the prediction time based on the prediction result and the transportation route; The response result and the path optimization value are normalized and then accumulated to output the guaranteed efficiency.

5. The method according to claim 1, characterized in that Completing the guarantee task based on the precise matching model includes the following steps: The precise matching model matches the demand database with the material database to determine whether the demand list corresponds to the matched standard response information one-to-one. If not, the standard response information with the highest guarantee efficiency is set as the optimal response information. If the optimal response information corresponds to multiple demand lists, one demand list is selected in turn based on the time feature, and the remaining demand lists are re-matched. This step is repeated until the demand lists correspond to the matched standard response information one-to-one and all the guarantee tasks are completed.

Images