Emergency food supply distribution method, device and equipment based on big data

Abstract

The present application relates to a method, device and equipment for food supply distribution for emergency events based on big data, and belongs to the field of emergency event command technology. The method of the present application includes: obtaining and processing the event entity based on the description information of the target emergency event to obtain the event dimension data of the target emergency event; performing matrix operations on the event dimension data and the pre-constructed and determined unit influence factor matrix to obtain the food supply distribution description matrix for the target emergency event; generating a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and outputting it to the outside; wherein the unit influence factor matrix is ​​pre-constructed and determined based on the food supply distribution plan of similar historical emergency events that have occurred. The present application can quickly and reasonably obtain a recommended food supply distribution plan for emergency events, providing relevant commanders with a strong basis for making the next decision.

Description

Technical Field

[0001] The present application belongs to the field of emergency incident command technology, and specifically relates to a method, device and equipment for emergency incident food supply distribution based on big data. Background Art

[0002] At present, in the field of emergency command, considering the mobility and diversity of food, as well as the types and levels of events, the types of property losses in a broad sense are diverse. There are too many factors to consider in the specific implementation of the food distribution plan. Manual decisions on what type of event and what kind of food distribution plan to adopt can no longer fully cover these factors.

[0003] With the development of big data technology, data aggregation, and the integrity of data modeling systems, we can use information technology to map events into entity relationship data, and then digitize the records of past events. We can summarize and analyze a large number of historical events, dimensionalize the corresponding influencing factors through dimensional modeling, and make the specific quantitative values ​​of the events facts.

[0004] The specific factors of an emergency are very likely to change. The food distribution plan that takes a long time to formulate needs to be re-formulated because of a change. The flexibility is too low and the manual plan-making cycle is long. These are all risk points. Therefore, it is an urgent need to use a reasonable recommended distribution plan as a reference for auxiliary decision-making to further distribute food materials.

[0005] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] In order to overcome the problems existing in the relevant technology at least to a certain extent, the present application provides a method, device and equipment for emergency food supply distribution based on big data, and provides a reference solution for emergency food supply distribution based on big data technology, so as to help allocate food resources more timely and reasonably in emergency event handling.

[0007] To achieve the above objectives, this application adopts the following technical solutions:

[0008] First,

[0009] The present application provides a method for emergency food supply distribution based on big data, the method comprising:

[0010] Acquire and perform event entity processing based on the description information of the target emergency event to obtain the event dimension data of the target emergency event;

[0011] Performing a matrix operation on the event dimension data and a pre-constructed unit impact factor matrix to obtain a food supply distribution description matrix for the target emergency event;

[0012] Generate a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and output it externally;

[0013] The unit impact factor matrix is ​​pre-constructed and determined based on food supply distribution plans for similar historical emergency events that have occurred.

[0014] Optionally, the process of pre-constructing and determining the unit impact factor matrix includes:

[0015] Collect data information on public historical emergency event information, model the collected data information through dimensional modeling methods, and build data calculation sample sets and test sample sets for different types of events based on the modeled data;

[0016] For the unit impact factor matrix corresponding to each type of event, the following construction and determination process is performed respectively:

[0017] Import the data of the data calculation sample set of this type of event into the preset event model for calculation to obtain the initial unit impact factor matrix;

[0018] The initial unit impact factor matrix is ​​adjusted and verified based on the initial unit impact factor matrix and the test sample set of this type of event, and the initial unit impact factor matrix that meets the verification conditions is used as the unit impact factor matrix of this type of event.

[0019] Optionally, the data collection of public historical emergency event information includes:

[0020] Collect data information from target network sources;

[0021] Among them, the target network information source includes the official website of emergency events, and the collected data information includes classification information of the events, event level information, information on factors affecting the events, and information on food resources required for the events.

[0022] Optionally, the collected data information is modeled by a dimensional modeling method, including:

[0023] The collected data information is digitized through database modeling methods to obtain materialized quantitative information data;

[0024] Based on the quantitative information data, event dimension data extraction and fact data integration are performed to obtain event dimension data of each historical emergency event and fact data of each historical emergency event;

[0025] Among them, the event dimension data includes: event attribute information data, and attribute data of food supply influencing factors involved in the event; the fact data includes: corresponding quantitative numerical data of food supply influencing factors, and quantity data of various types of food supplied for each historical emergency event.

[0026] Optionally,

[0027] The event attribute information data includes: event name, event level, event classification, and occurrence location;

[0028] The attribute data of food supply influencing factors involved in the incident include: disaster-affected population, casualty population, vulnerable group population, population density, and supply days.

[0029] Optionally, the expression form of the preset event model is as follows:

[0030]

[0031] A*B=C,

[0032] Among them, aij represents the attribute value of the jth influencing factor of the ith event, cij represents the quantity of the jth food required for the ith event, and the matrix B represents the initial unit influencing factor matrix. The elements in the matrix B are used to represent the distribution amount of each type of food determined by each influencing factor.

[0033] Optionally, the adjusting and verifying the initial unit impact factor matrix based on the initial unit impact factor matrix and the test sample set of the event of this type, and taking the initial unit impact factor matrix that meets the verification conditions as the unit impact factor matrix of the event of this type, includes:

[0034] Step 1, using the initial unit impact factor matrix as the current matrix to be verified;

[0035] Step 2, using the influencing factor data of an event in the test sample set and the current matrix to calculate and obtain the calculated required food resource row matrix of the event;

[0036] Step 3, based on the calculated required food resource row matrix and the actual required resource row matrix of the event in the test sample set, calculate the satisfaction verification coefficient for the current matrix;

[0037] Step 4, determine whether the satisfaction verification coefficient is the maximum value. If so, use the current matrix as the unit impact factor matrix of this type of event. Otherwise, adjust the impact factor constant of the current matrix, use the adjusted matrix as the new current matrix, and jump to step 2.

[0038] Optionally, the expression form of the satisfaction verification coefficient S0 is as follows:

[0039]

[0040] Among them, X represents the total amount of food determined based on the actual required resource row matrix, and Y represents the total amount of food determined based on the calculated required food resource row matrix.

[0041] Second,

[0042] The present application provides an emergency food supply distribution device based on big data, the device comprising:

[0043] An acquisition processing module is used to acquire and perform event entity processing based on the description information of the target emergency event to obtain event dimension data of the target emergency event;

[0044] A calculation processing module, used for performing matrix operations on the event dimension data and a pre-constructed and determined unit impact factor matrix to obtain a food supply distribution description matrix for the target emergency event;

[0045] A generating output module, used for generating a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and outputting it externally;

[0046] The unit impact factor matrix is ​​pre-constructed and determined based on food supply distribution plans for similar historical emergency events that have occurred.

[0047] Thirdly,

[0048] The present application provides an electronic device, including:

[0049] a memory having an executable program stored therein;

[0050] A processor is used to execute the executable program in the memory to implement the steps of the above method.

[0051] This application adopts the above technical solution, which has at least the following beneficial effects:

[0052] The technical solution of the present application is based on big data technology, and performs dimensional fact separation according to the food supply distribution plan of historical emergency events to obtain a unit influence factor matrix that represents the influencing factors on food distribution in the event dimensional data. Then, when facing new similar emergency events, the unit influence factor matrix can be used to calculate the dimensional data of the influencing factors of the emergency event, and the recommended food supply distribution plan that can respond to the event can be quickly and reasonably obtained, providing relevant commanders with a strong basis for making the next decision. The technical solution of the present application avoids the problem of too many food and material distribution operators and too long a program planning cycle.

[0053] Other advantages, objectives, and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the following description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the technical solution of the present application or the prior art, and constitute a part of the specification. Among them, the accompanying drawings expressing the embodiments of the present application are used together with the embodiments of the present application to explain the technical solution of the present application, but do not constitute a limitation on the technical solution of the present application.

[0055] Figure 1 A flowchart of a method for allocating food supply for emergencies based on big data provided by one embodiment of the present application;

[0056] Figure 2 A schematic diagram illustrating the overall design architecture of the technical solution of this application;

[0057] Figure 3 A schematic diagram of the structure of an emergency food supply and distribution device based on big data provided by one embodiment of the present application;

[0058] Figure 4 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation methods obtained by ordinary technicians in the field without creative work belong to the scope of protection of the present application.

[0060] As described in the background technology, currently, in the field of emergency command, considering the mobility and diversity of food, as well as the types and levels of events, the types of property losses in a broad sense are diverse. There are too many factors to consider in the specific implementation of the food distribution plan, and manual decision-making on what type of event and what kind of food distribution plan to adopt for the degree of event occurrence can no longer fully cover these factors.

[0061] With the development of big data technology, data aggregation, and the integrity of data modeling systems, we can use information technology to map events into entity relationship data, and then digitize the records of past events. We can summarize and analyze a large number of historical events, dimensionalize the corresponding influencing factors through dimensional modeling, and make the specific quantitative values ​​of the events facts.

[0062] The specific factors of an emergency are very likely to change. The food distribution plan that takes a long time to formulate needs to be re-formulated because of a change. The flexibility is too low and the manual plan-making cycle is long. These are all risk points. Therefore, it is an urgent need to use a reasonable recommended distribution plan as a reference for auxiliary decision-making to further distribute food materials.

[0063] To this end, the present application proposes a method for allocating food supply for emergencies based on big data, which provides a reference recommendation plan for allocating food supply for emergencies based on big data technology, so as to help allocate food resources more timely and reasonably in emergency event handling.

[0064] In one embodiment, if Figure 1 As shown, the emergency food supply distribution method based on big data proposed in this application includes:

[0065] Step S110, acquiring and performing event entity processing based on the description information of the target emergency event to obtain event dimension data of the target emergency event;

[0066] Step S120, performing a matrix operation on the event dimension data and the pre-constructed unit impact factor matrix to obtain a food supply distribution description matrix for the target emergency event;

[0067] It should be noted that the unit impact factor matrix here is pre-constructed and determined based on the food supply distribution plan of similar historical emergency events that have occurred. The relevant construction and determination process is mainly based on the big data technology mentioned in the background technology. This process will be introduced later and will not be described in detail here.

[0068] Step S130, generating a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and outputting it to the outside for reference by relevant commanders.

[0069] The technical solution of the present application is based on big data technology, and performs dimensional fact separation according to the food supply distribution plan of historical emergency events to obtain a unit influence factor matrix that represents the influencing factors on food distribution in the event dimensional data. Then, when facing new similar emergency events, the unit influence factor matrix can be used to calculate the dimensional data of the influencing factors of the emergency event, and the recommended food supply distribution plan that can respond to the event can be quickly and reasonably obtained, providing relevant commanders with a strong basis for making the next decision. The technical solution of the present application avoids the problem of too many food and material distribution operators and too long a program planning cycle.

[0070] The following is an introduction to the pre-construction and determination process of the unit impact factor matrix.

[0071] To facilitate understanding of the technical solution of the present application, the overall technical architecture of the present application is first introduced below.

[0072] The technical solution of this application introduces a big data modeling system, which extracts the influencing factors of historical events through the actual demand for food required for the occurrence of historical events, digitizes the influencing factors, obtains a reasonable supply model through data modeling, and provides a digitized supply quantity of food through actual supply material calculation. In the application, dynamic adjustments can be made based on the level and type of the target event and the dynamic changes in the occurrence of the event, providing a more scientific supply solution reference for the food supply of emergency events.

[0073] like Figure 2 As shown, in the technical architecture of this application, the main process processing stages are divided into data dimension modeling and data calculation modeling. On the whole, the collected data is modeled through the dimensional modeling method, and the existing modeled data is processed through the data modeling solution to obtain the unit supply data of specific food types. Then, a reasonable food supply plan is recommended based on the influencing factors of the new emergency events that actually occurred.

[0074] Specifically, in this application, the process of pre-constructing and determining the unit impact factor matrix includes:

[0075] (A) Data Dimension Modeling Phase

[0076] In this phase, data information of public historical emergency events is collected, the collected data information is modeled through dimensional modeling methods, and data calculation sample sets and test sample sets for different types of events are constructed based on the modeled data;

[0077] Specifically, during this stage, data collection is conducted on publicly available historical emergency event information, including:

[0078] Collect data information from target network sources;

[0079] Among them, the target network information sources include official websites of emergency events, various network search platforms, etc.; the collected data information includes classification information of events (such as natural disasters, public health events, etc.), event level information (such as general, large, etc.), information on factors affecting the events, and information on food resources required for the events.

[0080] Specifically, in this stage, the collected data information is modeled through dimensional modeling methods, including:

[0081] The collected data information is digitized through database modeling methods to obtain materialized quantitative information data. It is easy to understand that materialization here (or its result) is to construct a piece of descriptive information in the real world into an entity (referring to a table) through database modeling (building a table). For example, an event table generated by the information of an event can be called an entity. This process is carried out by data processing developers using relevant big data processing tools and methods;

[0082] Afterwards, it is necessary to extract event dimension data and integrate factual data based on the quantitative information data to obtain the event dimension data of each historical emergency event and the factual data of each historical emergency event.

[0083] The event dimension data here include: event attribute information data, and attribute data of food supply influencing factors involved in the event; for example, event attribute information data include: event level, event classification, location of occurrence, etc.; for example, attribute data of food supply influencing factors involved in the event include: disaster-stricken population, casualties, vulnerable groups, population density, supply days, etc.

[0084] The factual data here include: the corresponding quantitative numerical data of the factors affecting food supply, and the quantity data of various types of food supplied in each historical emergency event;

[0085] It is easy to understand that the above fact data integration is based on the smallest granularity of events. For example, the types of food supplies required for different types of emergency events of different levels in the integrated calculation include:

[0086] Food types: The main categories include grains, vegetables, fruits, processed foods, meat, and beverages; subcategories of the main categories are:

[0087] Food: flour, rice, corn, soybeans, other food;

[0088] Vegetables: fresh vegetables, frozen vegetables, pickled vegetables, dehydrated vegetables, other vegetables;

[0089] Fruits: fresh fruits, frozen fruits, dried fruits, other fruits;

[0090] Processed food: semi-finished products of rice and flour, quick-frozen food, baked food, cooked food, compressed food, ready-to-eat food, canned food;

[0091] Meat: livestock meat, poultry meat, other meat;

[0092] Beverages: drinking water, electrolyte drinks, other beverages;

[0093] The calculation of quantity data involves deriving the total amount of each type of food supplied at each event.

[0094] Generally speaking, the data dimension modeling phase belongs to the data preparation phase, which provides the required data for event model processing in the subsequent data calculation modeling phase.

[0095] (B) Data Computation Modeling Stage

[0096] In the above data preparation, relevant data sets of various types of events (including data calculation sample sets and test sample sets) can be obtained. For example, in this application, based on event classification (natural disasters, accidents and disasters, public health events, social security events) and event levels (general, large, major, and particularly major), event types can be divided into 16 types. Obviously, each type of event needs to be considered separately to obtain the corresponding unit impact factor matrix.

[0097] Therefore, in this stage, this application will carry out the following construction and determination process for the unit impact factor matrix corresponding to each type of event:

[0098] Import the data of the data calculation sample set of this type of event into the preset event model for calculation to obtain the initial unit impact factor matrix;

[0099] The initial unit impact factor matrix is ​​adjusted and verified based on the initial unit impact factor matrix and the test sample set of this type of event, and the initial unit impact factor matrix that meets the verification conditions is used as the unit impact factor matrix of this type of event.

[0100] Specifically, in the above process, the expression form of the preset event model is as follows:

[0101]

[0102] A*B=C (1)

[0103] In expression (1), aij represents the attribute value of the jth influencing factor of the ith event, cij represents the quantity of the jth food required for the ith event, and the matrix B represents the initial unit influencing factor matrix. The elements in the matrix B are used to represent the distribution amount of each type of food determined by each influencing factor.

[0104] For example, for an M-type event, there are 10 cumulative influencing factors, corresponding to the value a of the 10 influencing factors, and there are 20 types of cumulatively supplied food materials, corresponding to the food value c. The 10 influencing factors here are a quantitative concept, and the influencing factors specifically refer to the influencing factors related to food supply.

[0105] If there are 1000 events in the data calculation sample set of M type events, then the event model of expression (1) is substituted into the matrix data:

[0106]

[0107]

[0108] Based on A*B=C in expression (1), according to the matrix operation rules, B=A -1 C, AA -1 =E, the initial unit impact factor matrix B can be calculated.

[0109]

[0110] In expression (4), is the impact factor constant, which is a common divisor extracted from the matrix.

[0111] Once the specific initial unit impact factor matrix B is obtained, the initial impact factor matrix can be adjusted and verified based on the initial unit impact factor matrix and the test sample set of this type of event, and the initial unit impact factor matrix that meets the verification conditions can be used as the unit impact factor matrix of this type of event.

[0112] Specifically, the adjustment verification process includes:

[0113] Step 1: Use the initial unit impact factor matrix as the current matrix for the test to be verified.

[0114] Step 2, using the influencing factor data of an event in the test sample set and the current matrix to calculate and obtain the calculated required food resource row matrix of the event;

[0115] Here we continue to take the M type event as an example. In step 2, based on expressions (1) and (4), a P matrix of the same type as matrix A (P = (p11, p12, ... p101)) is constructed according to the data of an event in the test sample set. Based on PB = Q, a Q matrix of the same type as matrix C (Q = (q11, q12, ... p120)) is calculated.

[0116] Step 3, based on the calculated required food resource row matrix Q and the actual required resource row matrix R (R = (r11, r12, ... r120)) of the event in the test sample set, calculate the satisfaction verification coefficient for the current matrix. The expression form of the satisfaction verification coefficient here is as follows:

[0117]

[0118] In expression (5), S0 represents the satisfaction verification coefficient, X represents the total amount of food determined based on the actual required resource row matrix, and Y represents the total amount of food determined based on the calculated required food resource row matrix;

[0119] In step 3, continuing the previous example, the following specific calculation formula can be obtained from expression (5):

[0120]

[0121] Then the value of the satisfaction verification coefficient can be calculated.

[0122] Then proceed to step 4 to determine whether the satisfaction verification coefficient is the maximum value. If so, the current matrix is ​​used as the unit impact factor matrix of this type of event. Otherwise, the impact factor constant of the current matrix is ​​adjusted, the adjusted matrix is ​​used as the new current matrix, and jump to step 2.

[0123] It should be noted that in step 4, the influence factor constant of the current matrix is ​​adjusted The test adjustment is based on the initial influencing factor constant. The value of the satisfaction verification coefficient calculated during the adjustment process forms a normal distribution curve with a maximum value close to 1. The maximum value S in the curve is taken. max The corresponding impact factor constant is used, and the current matrix corresponding to the impact factor constant is used as the unit impact factor matrix of this type of event.

[0124] It is easy to understand that returning to Figure 1In the application process shown in FIG. 1 , the row matrix data of the matrix A type can be constructed according to the event dimension data of the newly occurring target emergency event. Based on the row matrix data and the unit impact factor matrix (matrix B type matrix) of the same type of event determined by the above process, the food supply distribution description matrix (matrix C type matrix) is calculated based on expression (1). Then, based on the food supply distribution information contained in the food supply distribution description matrix, a food supply distribution recommendation plan is generated and output to the outside for reference by relevant commanders.

[0125] In the technical solution of the present application, the food distribution plan is universal, the influencing factors can change, the type of distributed food can change, the corresponding results will change, and by extension, the method of the present application can also be used in general resource allocation recommendation scenarios for non-food products.

[0126] Figure 3 A schematic diagram of a big data-based emergency food supply distribution device provided in one embodiment of the present application is shown in FIG. Figure 3 As shown, the dispensing device 300 comprises:

[0127] The acquisition processing module 301 is used to acquire and perform event entity processing based on the description information of the target emergency event to obtain the event dimension data of the target emergency event;

[0128] A calculation processing module 302 is used to perform a matrix operation on the event dimension data and a pre-constructed unit impact factor matrix to obtain a food supply distribution description matrix for the target emergency event;

[0129] A generating output module 303, used to generate a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and output it externally;

[0130] The unit impact factor matrix is ​​pre-constructed and determined based on food supply distribution plans for similar historical emergency events that have occurred.

[0131] Regarding the allocation device 300 in the above-mentioned related embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0132] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown as follows: Figure 4 As shown, the electronic device 400 includes:

[0133] Memory 401, on which executable programs are stored;

[0134] The processor 402 is used to execute the executable program in the memory 401 to implement the steps of the above method.

[0135] Regarding the electronic device 400 in the above embodiment, the specific manner in which its processor 402 executes the program in the memory 401 has been described in detail in the embodiment of the method, and will not be elaborated here.

[0136] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any person familiar with the technology within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for emergency food supply distribution based on big data, characterized in that: include: Acquire and perform event entity processing based on the description information of the target emergency event to obtain the event dimension data of the target emergency event; Performing a matrix operation on the event dimension data and a pre-constructed unit impact factor matrix to obtain a food supply distribution description matrix for the target emergency event; Generate a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and output it externally; The unit impact factor matrix is ​​pre-constructed and determined based on the food supply distribution plan of similar historical emergency events that have occurred; The process of pre-constructing and determining the unit impact factor matrix includes: Collect data information on public historical emergency event information, model the collected data information through dimensional modeling methods, and build data calculation sample sets and test sample sets for different types of events based on the modeled data; For the unit impact factor matrix corresponding to each type of event, the following construction and determination process is performed respectively: Import the data of the data calculation sample set of this type of event into the preset event model for calculation to obtain the initial unit impact factor matrix; Based on the initial unit impact factor matrix and the test sample set of the event of this type, the initial impact factor matrix is ​​adjusted and verified, and the initial unit impact factor matrix that meets the verification conditions is used as the unit impact factor matrix of the event of this type; The expression form of the preset event model is as follows: A*B=C Among them, aij represents the attribute value of the jth influencing factor of the ith event, cij represents the quantity of the jth food required for the ith event, and the matrix B represents the initial unit influencing factor matrix. The elements in the matrix B are used to represent the distribution amount of each type of food determined by each influencing factor.

2. The method according to claim 1, characterized in that: The data collection of public historical emergency event information includes: Collect data information from target network sources; Among them, the target network information source includes the official website of emergency events, and the collected data information includes classification information of the events, event level information, information on factors affecting the events, and information on food resources required for the events.

3. The method according to claim 2, characterized in that The collected data information is modeled by a dimensional modeling method, including: The collected data information is digitized through database modeling methods to obtain materialized quantitative information data; Based on the quantitative information data, event dimension data extraction and fact data integration are performed to obtain event dimension data of each historical emergency event and fact data of each historical emergency event; Among them, the event dimension data includes: event attribute information data, and attribute data of food supply influencing factors involved in the event; the fact data includes: corresponding quantitative numerical data of food supply influencing factors, and quantity data of various types of food supplied for each historical emergency event.

4. The method according to claim 3, characterized in that The event attribute information data includes: event name, event level, event classification, and occurrence location; The attribute data of food supply influencing factors involved in the incident include: disaster-affected population, casualty population, vulnerable group population, population density, and supply days.

5. The method according to claim 1, characterized in that The adjusting and verifying the initial unit impact factor matrix based on the initial unit impact factor matrix and the test sample set of the event of this type, and taking the initial unit impact factor matrix that meets the verification conditions as the unit impact factor matrix of the event of this type, includes: Step 1, using the initial unit impact factor matrix as the current matrix to be verified; Step 2, using the influencing factor data of an event in the test sample set and the current matrix to calculate and obtain the calculated required food resource row matrix of the event; Step 3, based on the calculated required food resource row matrix and the actual required resource row matrix of the event in the test sample set, calculate the satisfaction verification coefficient for the current matrix; Step 4, determine whether the satisfaction verification coefficient is the maximum value. If so, use the current matrix as the unit impact factor matrix of this type of event. Otherwise, adjust the impact factor constant of the current matrix, use the adjusted matrix as the new current matrix, and jump to step 2.

6. The method according to claim 5, characterized in that The expression form of the satisfaction verification coefficient S0 is as follows: Among them, X represents the total amount of food determined based on the actual required resource row matrix, and Y represents the total amount of food determined based on the calculated required food resource row matrix.

7. An emergency food supply distribution device based on big data, characterized in that: include: An acquisition processing module is used to acquire and perform event entity processing based on the description information of the target emergency event to obtain event dimension data of the target emergency event; A calculation processing module, used for performing matrix operations on the event dimension data and a pre-constructed and determined unit impact factor matrix to obtain a food supply distribution description matrix for the target emergency event; A generating output module, used for generating a food supply distribution recommendation plan based on the food supply distribution information contained in the food supply distribution description matrix and outputting it externally; The unit impact factor matrix is ​​pre-constructed and determined based on the food supply distribution plan of similar historical emergency events that have occurred; wherein the pre-construction and determination process of the unit impact factor matrix includes: Collect data information on public historical emergency event information, model the collected data information through dimensional modeling methods, and build data calculation sample sets and test sample sets for different types of events based on the modeled data; For the unit impact factor matrix corresponding to each type of event, the following construction and determination process is performed respectively: Import the data of the data calculation sample set of this type of event into the preset event model for calculation to obtain the initial unit impact factor matrix; Based on the initial unit impact factor matrix and the test sample set of the event of this type, the initial unit impact factor matrix is ​​adjusted and verified, and the initial unit impact factor matrix that meets the verification conditions is used as the unit impact factor matrix of the event of this type; The expression form of the preset event model is as follows: A*B=C Among them, aij represents the attribute value of the jth influencing factor of the ith event, cij represents the quantity of the jth food required for the ith event, and the matrix B represents the initial unit influencing factor matrix. The elements in the matrix B are used to represent the distribution amount of each type of food determined by each influencing factor.

8. An electronic device, characterized in that: include: A memory having an executable program stored therein; A processor, configured to execute the executable program in the memory to implement the steps of the method according to any one of claims 1 to 6.

Images