Order generation method, device and storage medium

Abstract

The present invention provides an order generation method, device and storage medium, which randomly generates an empty order corresponding to the first simulation time period; based on the number of coding containers in the empty order, extracts n item coding information from the corresponding historical order data group, and uses the n item coding information to fill the n coding containers respectively; traverses the item coding information in the n coding containers, and forms order information corresponding to the first simulation time period based on the number of n item coding information and related data; based on the order information, the comparison result with the target transaction volume of the historical time period corresponding to the first simulation time period determines the target order information, and then determines the target order information of other simulation time periods. Since the target order information determined by this scheme is more matched with the actual transaction volume of the first simulation time period, the supply chain scheme matching the simulation period can be accurately formed through the target order data of each simulation time period.

Description

Technical Field

[0001] The embodiments of the present invention relate to the fields of e-commerce and computer technology, and in particular to an order generating method, device and storage medium. Background Art

[0002] Supply chain is a core component of business operations. Supply chain is used to supply goods to the corresponding areas in the simulation period. When designing a supply chain solution, it is often necessary to conduct supply chain simulation for various scenarios to analyze the effect of the supply chain, such as whether it can meet the transaction volume requirements.

[0003] The supply chain simulation platform currently cannot cover different scenarios. The supply chain simulation platform outputs simulation results based on historical scenarios and cannot cover scenarios with changes in transaction volume, resulting in distorted simulation results.

[0004] The relationship between the number of orders and transaction volume in historical scenarios is complex. The simulation results of the supply chain simulation platform are difficult to cope with the complex relationship between the number of orders and transaction volume, resulting in distorted simulation results.

[0005] Therefore, the main problem currently faced is that it is impossible to form a supply chain solution that matches the simulation period in the face of complex transaction volume relationships. Summary of the invention

[0006] An order generation method, device and storage medium provided by the embodiments of the present invention can accurately form a supply chain solution that matches the simulation period.

[0007] The technical solution of the present invention is achieved in this way:

[0008] An embodiment of the present invention provides an order generation method, comprising:

[0009] Randomly generate an empty order corresponding to the first simulation time period; the empty order includes: n coding containers; n is an integer greater than or equal to 1;

[0010] Based on the number of coded containers in the empty order, n item coding information is extracted from the corresponding historical order data group, and the n coded containers are filled with the n item coding information respectively; the historical order data group is formed based on historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coded containers;

[0011] Traversing the item coding information in the n coding containers, and forming order information corresponding to the first simulation time period based on the number of the n item coding information and related data;

[0012] Based on the order information, the target order information is determined by comparing the target transaction volume of the historical time period corresponding to the first simulation time period, and then the target order information of other simulation time periods is determined to form a supply chain solution.

[0013] In the above scheme, the relevant data includes: random number, sum of frequency correlation and transaction volume correlation;

[0014] The traversing the item coding information in the n coding containers and forming the order information corresponding to the first simulation time period based on the number of the n item coding information and related data includes:

[0015] If n is greater than or equal to 2, then the item coding information in the i-th coding container is traversed; i is a positive integer greater than or equal to 1 and less than n;

[0016] Based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information, adjusting the item coding information in the i-th coding container until the traversal of the item coding information in the n coding containers is completed;

[0017] Combine the preset transaction volume average and transaction volume maximum in the historical order data group to generate basic transaction volume information corresponding to the n item coding information after the traversal is completed;

[0018] Based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, the basic transaction volume information respectively corresponding to the n item coding information is adjusted to form the order information.

[0019] In the above scheme, the random number based on the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information are used to adjust the item coding information in the i-th coding container until the traversal of the item coding information in the n coding containers is completed. The method further includes:

[0020] Generate random numbers corresponding to the n item coding information respectively; the random numbers are random numbers greater than 0 and less than 1;

[0021] The step of adjusting the item coding information in the i-th coding container based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information until the traversal of the item coding information in the n coding containers is completed includes:

[0022] Processing to obtain an i-th random number corresponding to the item coding information in the i-th coding container, and comparing it with a preset threshold;

[0023] If the comparison result indicates that the i-th random number is less than the preset threshold, the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information in the historical order data group is calculated; the frequency correlations between the item coding information in the i-th coding container and other item coding information are pre-calculated;

[0024] If the sum of the frequency correlations is less than the frequency threshold, any other item coding information is used as the new item coding information in the i-th coding container until the traversal of the n item coding information is completed.

[0025] In the above solution, after the processing obtains the comparison result of the i-th random number corresponding to the i-th item coding information and the preset threshold, the method further includes:

[0026] If the comparison result indicates that the i-th random number is not less than the preset threshold, the i+1-th random number of the item coding information in the i+1-th coding container is compared with the preset threshold to obtain the comparison result of the item coding information in the i+1-th coding container, and based on the comparison result, continue to traverse the remaining item coding information.

[0027] In the above scheme, if the comparison result indicates that the i-th random number is less than the preset threshold, then after counting the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information in the historical order data group, the method further includes:

[0028] If the sum of the frequency correlations is not less than the frequency threshold, based on the transaction volume correlations corresponding to the current n item coding information in the historical order data group, the transaction volume information corresponding to the n item coding information is formed, and then the order information is formed.

[0029] In the above solution, based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, adjusting the basic transaction volume information respectively corresponding to the n item coding information to form the order information includes:

[0030] In the historical order data group, determining target order data including the n item coding information at the same time;

[0031] Based on the transaction volume correlation corresponding to the n item coding information obtained in advance in the target order data, the basic transaction volume information corresponding to the n item coding information is adjusted to obtain the transaction volume information corresponding to the n item coding information, thereby forming the order information.

[0032] In the above solution, the basic transaction volume information corresponding to the n item coding information is adjusted based on the transaction volume correlation corresponding to the n item coding information obtained in advance in the target order data to obtain the transaction volume information corresponding to the n item coding information, including:

[0033] The basic transaction volume information corresponding to the t-1th item coding information is multiplied by the ratio of the historical transaction volume information of the tth item coding information in the target order data to the historical transaction volume information of the t-1th item coding information to obtain the transaction volume information corresponding to the tth item coding information, and then the transaction volume information corresponding to the n item coding information is obtained; t is a positive integer greater than or equal to 2 and less than n.

[0034] In the above solution, before adjusting the basic transaction volume information respectively corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information in the historical order data group to form the order information, the method further includes:

[0035] If n is equal to 1, then the basic transaction volume information corresponding to the n item coding information after the traversal is completed is generated in combination with the preset transaction volume average and transaction volume maximum in the historical order data group.

[0036] In the above scheme, before generating the empty orders corresponding to the first simulation time period by using the roulette method, the method further includes:

[0037] Extracting a plurality of order data corresponding to the plurality of historical time periods in a preset storage space according to preset conditions; each order data includes: at least one item coding information, and each item coding information includes: corresponding historical transaction volume information;

[0038] Calculate the target transaction volumes corresponding to the multiple historical time periods respectively in combination with the multiple order data;

[0039] According to the quantity of item coding information in the plurality of order data, the plurality of order data are divided into a plurality of historical order data groups; the order data in each historical order data group contains the same quantity of item coding information;

[0040] At the same time, multiple transaction related information corresponding to the multiple historical order data groups are calculated respectively.

[0041] In the above solution, the preset conditions include: node information, region information and item category information of the multiple historical time periods;

[0042] The extracting, in the preset storage space according to the preset conditions, a plurality of order data corresponding to the plurality of historical time periods comprises:

[0043] The plurality of order data corresponding to the plurality of historical time periods are extracted in the preset storage space according to the node information of the plurality of historical time periods, the region information and the category information of the items.

[0044] In the above solution, the step of combining the plurality of order data to calculate the target transaction volumes corresponding to the plurality of historical time periods respectively includes:

[0045] Counting the sum of the historical transaction volume information of the order data in each historical time period to obtain the baseline of each historical time period;

[0046] Obtaining a coefficient of variation, multiplying the baseline of each historical time period by the coefficient of variation and then adding the resultant to the baseline to obtain a theoretical transaction volume for each historical time period;

[0047] The theoretical transaction volume of each historical time period is added to a random variable to obtain the target transaction volume of each historical time period, and then the target transaction volumes corresponding to the multiple historical time periods are obtained.

[0048] In the above scheme, the multiple transaction related information includes: transaction volume mean, transaction volume maximum, transaction volume distribution frequency information of each item coding information, frequency correlation matrix and transaction volume correlation matrix;

[0049] The simultaneously calculating a plurality of transaction-related information respectively corresponding to the plurality of historical order data groups comprises:

[0050] The transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix respectively corresponding to the multiple historical order data groups are calculated simultaneously.

[0051] In the above scheme, the simultaneous calculation of the transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix respectively corresponding to the multiple historical order data groups includes:

[0052] Add the historical transaction volume information of all item code information in each historical order data group, and divide by the number of item code information in each historical order data group to obtain the transaction volume mean of each historical order data group;

[0053] Determining the largest historical transaction volume information among the historical transaction volume information corresponding to the item code information in each historical order data group as the maximum transaction volume;

[0054] In each of the historical order data groups, the number of order data containing each of the item coding information is divided by the total amount of the order data in each of the historical order data groups to obtain the transaction volume distribution frequency information of each of the item coding information;

[0055] Calculating the frequency correlation between every two item code information in each historical order data group, and arranging the frequency correlation between each item code information and other item code information according to the order of the item code information in each historical order data group to form each row of the frequency correlation matrix, thereby forming the frequency correlation matrix;

[0056] The transaction volume correlation between every two item coding information in each historical order data group is calculated, and the transaction volume correlation between each item coding information and other item coding information is arranged according to the order of the item coding information in each historical order data group to form each row of the transaction volume correlation matrix, thereby forming the transaction volume correlation matrix.

[0057] In the above scheme, the frequency correlation between every two item coding information in each historical order data group is calculated, and the frequency correlation between each item coding information and other item coding information is arranged according to the order of the item coding information in each historical order data group to form each row of the frequency correlation matrix, thereby forming the frequency correlation matrix, including:

[0058] According to the order of the item coding information in each historical order data group, the number of the order data including both the k-th item coding information and the m-th item coding information is divided by the number of the order data including only the k-th item coding information, to obtain the first frequency correlation between the k-th item coding information and the m-th item coding information, until m is equal to q, to ​​obtain q-1 first frequency correlations corresponding to each item coding information respectively; k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group;

[0059] According to the order of the item code information in each historical order data group, the number of the order data including both the k-th item code information and the m-th item code information is divided by the number of the order data including only the m-th item code information, to obtain the second frequency correlation between the m-th item code information and the k-th item code information, until k is equal to q, to ​​obtain q-1 second frequency correlations corresponding to each item code information;

[0060] The q-1 first frequency correlations and q-1 second frequency correlations of the first item code information are used as the first row of the frequency correlation matrix until the nth row of the frequency correlation matrix is ​​formed, thereby forming the frequency correlation matrix.

[0061] In the above scheme, the calculation of the transaction volume correlation between every two item coding information in each historical order data group is performed, and the transaction volume correlation between each item coding information and other item coding information is arranged according to the order of the item coding information in each historical order data group to form each row of the transaction volume correlation matrix, thereby forming the transaction volume correlation matrix, including:

[0062] According to the order of the item coding information in each historical order data group, q-1 order data including both the k-th item coding information and the m-th item coding information are determined in each historical order data group; k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group;

[0063] Compare the transaction volume information corresponding to the k-th item code information and the m-th item code information included in each order data, and then obtain q-1 transaction volume correlations corresponding to the k-th item code information, until k is equal to q, and obtain q-1 transaction volume correlations corresponding to the q item code information;

[0064] The q-1 transaction volume correlations of the first item coding information are used as the first row of the transaction volume correlation matrix until the qth row of the transaction volume correlation matrix is ​​formed, thereby forming the transaction volume correlation matrix.

[0065] In the above solution, the target order information is determined based on the order information and the comparison result with the target transaction volume of the historical time period corresponding to the first simulation time period, including any one of the following:

[0066] If the transaction volume included in the order information is not less than the target transaction volume, determining that the order information is the target order information;

[0067] If the transaction volume included in the order information is less than the target transaction volume, the process of forming the order information continues until the target order information is obtained.

[0068] The embodiment of the present invention further provides an order generating device, comprising:

[0069] An order forming unit, used for randomly generating an empty order corresponding to the first simulation time period; the empty order includes: n coding containers; n is an integer greater than or equal to 1;

[0070] A data extraction unit, configured to extract n item coding information from a corresponding historical order data group based on the number of coding containers in the empty order, and use the n item coding information to fill the n coding containers respectively; the historical order data group is a collection of historical order data corresponding to the number of coding containers formed based on historical order data in multiple historical time periods;

[0071] The order forming unit is further used to traverse the item coding information in the n coding containers, and form order information corresponding to the first simulation time period based on the number of the n item coding information and related data;

[0072] A determination unit is used to determine the target order information based on the order information and the comparison result of the target transaction volume of the historical time period corresponding to the first simulation time period, and then determine the target order information of other simulation time periods for the supply chain to supply.

[0073] An embodiment of the present invention further provides an order generating device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the steps in the above method when executing the program.

[0074] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are implemented.

[0075] In the embodiment of the present invention, an empty order corresponding to the first simulation time period is randomly generated; the empty order includes: n coding containers; based on the number of coding containers in the empty order, n item coding information is extracted from the corresponding historical order data group, and the n item coding information is used to fill the n coding containers respectively; the historical order data group is formed based on the historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coding containers; the item coding information in the n coding containers is traversed, and the order information corresponding to the first simulation time period is formed based on the number of n item coding information and related data; based on the order information, the target order information is determined based on the comparison result of the target transaction volume of the historical time period corresponding to the first simulation time period, and then the target order information of other simulation time periods is determined, and then the supply chain plan is formed. Since the target order information is formed based on the corresponding order information, and the order information is formed based on the number of n item coding information and related data in the randomly generated empty order, the target order data is more matched with the actual transaction volume of the first simulation time period, so the target order data of each simulation time period generated by this scheme can accurately form a supply chain plan matching the simulation period. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0077] Figure 2 An optional effect diagram of the order generation method provided in an embodiment of the present invention;

[0078] Figure 3 An optional effect diagram of the order generation method provided in an embodiment of the present invention;

[0079] Figure 4 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0080] Figure 5 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0081] Figure 6 An optional effect diagram of the order generation method provided in an embodiment of the present invention;

[0082] Figure 7 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0083] Figure 8 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0084] Fig. 9An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0085] Fig.10 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0086] Fig.11 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0087] Fig.12 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0088] Fig.13 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0089] Fig.14 An optional effect diagram of the order generation method provided in an embodiment of the present invention;

[0090] Fig.15 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0091] Fig.16 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0092] Fig.17 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0093] Fig.18 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0094] Fig.19 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0095] Fig. 20 An optional flow chart of an order generation method provided in an embodiment of the present invention;

[0096] Fig.21 A schematic diagram of the structure of an order generating device provided by an embodiment of the present invention;

[0097] Fig. 22 A schematic diagram of a hardware entity of an order generating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0098] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present invention. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.

[0099] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0100] If similar descriptions of "first / second" appear in the invention document, the following description is added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the invention described herein can be implemented in an order other than that illustrated or described herein.

[0101] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0102] Figure 1 An optional flow chart of the order generation method provided in the embodiment of the present invention is combined with Figure 1 The steps shown are explained.

[0103] S101. Randomly generate an empty order corresponding to a first simulation time period; the empty order includes: n coding containers.

[0104] In the embodiment of the present invention, the server randomly generates an empty order corresponding to the first simulation time period, wherein the empty order includes: n encoding containers, where n is an integer greater than or equal to 1.

[0105] The first simulation time period is a time period of the simulation period. The simulation period may include multiple simulation time periods. For example, the simulation period may be from October 1 to October 7. The first simulation time period may be October 1 within the simulation period.

[0106] In the embodiment of the present invention, the server randomly generates an empty order including n coded containers by using a roulette method in combination with the corresponding occurrence frequency of each item coding information in the pre-generated multiple historical order data. The number n of coded containers in the empty order is random. The multiple historical order data groups are formed based on the historical order data in multiple historical time periods. The multiple historical time periods are historical time periods corresponding to the multiple simulation time period pairs in the simulation period.

[0107] Exemplary, combined Figure 2 ,The server generates an empty order using the roulette method, which includes three encoding containers.

[0108] S102: Based on the number of coding containers in the empty order, n item coding information is extracted from the corresponding historical order data group, and the n item coding information is used to fill the n coding containers respectively.

[0109] In the embodiment of the present invention, the server extracts n item coding information from the corresponding historical order data group based on the number of coding containers in the empty order, and uses the n item coding information to fill the n coding containers respectively. The historical order data group is formed based on historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coding containers.

[0110] In the embodiment of the present invention, the server forms multiple historical order data groups based on historical order data in multiple historical time periods in advance. The historical order data in each historical order data group includes the same number of item coding information. The server randomly selects n item coding information from the historical order data group including n item coding information. The server uses the n item coding information to fill the n coding containers in the empty order respectively.

[0111] Exemplary, combined Figure 3 , the server extracts three item coding information including: SKU1, SKU2 and SKU3. The server fills the three item coding information into the three coding containers of the empty order respectively.

[0112] S103, traversing the item coding information in the n coding containers, and forming order information corresponding to the first simulation time period based on the number of the n item coding information and related data.

[0113] In the embodiment of the present invention, the server traverses the item coding information in the n coding containers, and forms order information corresponding to the first simulation time period based on the number of the n item coding information and related data.

[0114] In the embodiment of the present invention, the server sequentially traverses the item coding information in the n coding containers. When the number of the n item coding containers is 1, the server combines the preset transaction volume mean and transaction volume maximum in the historical order data group to generate the basic transaction volume information corresponding to the 1 item coding information. Among them, the basic transaction volume information generated by the server is close to the transaction volume mean and does not exceed the transaction volume maximum. The server then adjusts the basic transaction volume information corresponding to the 1 item coding information based on the transaction volume correlation corresponding to the 1 item coding information in the historical order data group, and then forms the order information.

[0115] When the number of n item coding containers is greater than or equal to 2, the server adjusts the item coding information in the i-th coding container based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information until the traversal of the item coding information in the n coding containers is completed. The server then uses the same method to generate the basic transaction volume information corresponding to the n item coding information after the traversal is completed. Finally, the server adjusts the basic transaction volume information corresponding to the n item coding information so that the basic transaction volume information corresponding to the n item coding information will not differ too much from the historical transaction volume, thereby forming order information.

[0116] In the embodiment of the present invention, the server may also use the same method in S103 to generate order information corresponding to other simulation time periods within the simulation period.

[0117] S104. Based on the order information, the target order information is determined by comparing the target transaction volume of the historical time period corresponding to the first simulation time period, and then the target order information of other simulation time periods is determined to form a supply chain solution.

[0118] In an embodiment of the present invention, the server determines the target order information based on the order information and the comparison result of the target transaction volume of the historical time period corresponding to the first simulation time period, and then determines the target order information of other simulation time periods, and then forms a supply chain plan.

[0119] In an embodiment of the present invention, the server precalculates the target transaction volumes corresponding to a plurality of historical time periods. The server compares the order information with the target transaction volumes of the historical time periods corresponding to the first simulation time period. If the transaction volume of the order information is not less than the target transaction volume, the order information is determined to be the target order information. If the transaction volume of the order information is less than the target transaction volume, the server re-executes the process of S101-S103 to determine new order information, and then determines the target order information based on the new order information and the target transaction volume. The server generates the target order information of a plurality of simulation time periods of the simulation period through the above method. Then, the server uses the target order information of the plurality of simulation time periods to form a supply chain solution that matches the simulator.

[0120] The order information may include at least one item coding information. Each item coding information includes corresponding transaction volume information. The server adds the transaction volume information of all item coding information in the order information to obtain the total transaction volume information, and compares the total transaction volume information with the target transaction volume to obtain a comparison result. The server determines the final target order information based on the comparison result.

[0121] In the embodiment of the present invention, an empty order corresponding to the first simulation time period is randomly generated; the empty order includes: n coding containers; based on the number of coding containers in the empty order, n item coding information is extracted from the corresponding historical order data group, and the n coding containers are filled with the n item coding information respectively; the historical order data group is formed based on the historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coding containers; the item coding information in the n coding containers is traversed, and the order information corresponding to the first simulation time period is formed based on the number of n item coding information and related data; based on the order information, the target order information is determined based on the comparison result of the target transaction volume of the historical time period corresponding to the first simulation time period, and then the target order information of other simulation time periods is determined, and then an accurate supply chain plan is formed. Since the target order information is formed based on the corresponding order information, and the order information is formed based on the number of n item coding information and related data in the randomly generated empty order, the target order data is more matched with the actual transaction volume of the first simulation time period, so the target order data of each simulation time period generated by this scheme can accurately form a supply chain plan matching the simulation period.

[0122] In some embodiments, see Figure 4 , Figure 4 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 1 The illustrated S103 can be implemented through S105 to S107, which will be described in conjunction with each step.

[0123] S105. If n is greater than or equal to 2, the item coding information in the i-th coding container is adjusted according to the order of the item coding information in the n coding containers, based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information, until the traversal of the item coding information in the n coding containers is completed.

[0124] In the embodiment of the present invention, if the server detects that the number n of the coding containers in the empty order is greater than or equal to 2, the item coding information in the ith coding container is adjusted according to the order of the item coding information in the n coding containers, based on the random number of the item coding information in the ith coding container and the sum of the frequency correlations with other item coding information, until the traversal of the item coding information in the n coding containers is completed.

[0125] In the embodiment of the present invention, since the number n of the coding containers in the empty order is randomly determined, the server needs to first detect whether n is greater than or equal to 2. If it is greater than 2, the server will traverse the n item coding information in sequence according to the order of the n item coding information. The server adjusts the item coding information based on the random number generated by the item coding information in each coding container and the sum of the frequency correlations between the coding information and other item coding information. The server can use the same method to adjust the n item coding information.

[0126] In the embodiment of the present invention, the server may adjust the item coding information by: the server replaces the item coding information with other item coding information in the empty order.

[0127] S106. Generate basic transaction volume information corresponding to the n item coding information after the traversal is completed by combining the preset transaction volume average and transaction volume maximum in the historical order data group.

[0128] In the embodiment of the present invention, the server combines the preset transaction volume average and the transaction volume maximum in the historical order data group to generate basic transaction volume information corresponding to the n item coding information after the traversal is completed.

[0129] In the embodiment of the present invention, the server pre-calculates the transaction volume average and the maximum transaction volume in the historical order data set. The server generates corresponding basic transaction volume information for n item coding information respectively. Among them, each basic transaction volume information is not greater than the maximum transaction volume and is within a certain numerical range of the transaction volume average.

[0130] S107. Based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, adjust the basic transaction volume information respectively corresponding to the n item coding information, thereby forming order information.

[0131] In the embodiment of the present invention, the server adjusts the basic transaction volume information corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, and then forms the order information.

[0132] In the embodiment of the present invention, the server determines target order data including n item coding information in the historical order data group, adjusts the basic transaction volume information corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information obtained in advance in the target order data, obtains the transaction volume information corresponding to the n item coding information, and then forms the order information.

[0133] In the embodiment of the present invention, the server adjusts the basic transaction volume information of each item coding information based on the transaction volume ratio between each item coding information and the previous item coding information in the target order data, obtains the transaction volume information corresponding to the n item coding information, and then forms the order information.

[0134] In the embodiment of the present invention, the server adjusts the basic transaction volume information of each item coding information according to the ratio of the transaction volume of each item coding information to the previous item coding information, including: the server multiplies the basic transaction volume information of the previous item coding information by the ratio of the transaction volume to obtain the transaction volume information corresponding to the item coding information. Exemplarily, the transaction volume information of SKU2 = (basic transaction volume information of SKU1 * transaction volume information of SKU2 in historical orders / transaction volume information of SKU1 in historical orders).

[0135] In the embodiment of the present invention, when the number of item coding information in the empty order is greater than or equal to 2, the server adjusts each item coding information based on the random number of the item coding information in each coding container and the sum of the frequency correlations with other item coding information, and finally generates corresponding order information based on the transaction volume correlation, so that the empty order better matches the actual transaction volume in the first simulation time period, so as to form an accurately matched supply chain.

[0136] In some embodiments, see Figure 5 , Figure 5 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 4 The illustrated S105 can be implemented through S108 to S111 , which will be described in conjunction with each step.

[0137] S108, generating random numbers corresponding to n item coding information respectively.

[0138] In the embodiment of the present invention, the server generates random numbers corresponding to n pieces of item coding information.

[0139] Among them, the random number can be a random number between 0 and 1.

[0140] S109. Process and obtain the comparison result between the i-th random number corresponding to the item coding information in the i-th coding container and a preset threshold.

[0141] In an embodiment of the present invention, the server processes and obtains the comparison result between the i-th random number corresponding to the item coding information in the i-th coding container and a preset threshold.

[0142] In an embodiment of the present invention, the server compares the i-th random number corresponding to the i-th item coding information with a preset threshold to obtain a comparison result.

[0143] Among them, the preset threshold can also be a random number between 0 and 1.

[0144] S110. If the comparison result indicates that the i-th random number is less than the preset threshold, then in the historical order data group, count the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information.

[0145] In an embodiment of the present invention, if the server detects that the comparison result indicates that the i-th random number is less than the preset threshold, then in the historical order data group, count the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information.

[0146] In an embodiment of the present invention, for each SKU in an empty order, the server generates a random number R between 0 and 1. If the R of the SKU i is < P, then calculate the sum C i of the frequency correlations between the SKU SKUi and the other n - 1 SKUs through formula (1).

[0147]

[0148] Among them, n is the number of n item coding information, SKU i , SKU j is the frequency correlation between the i-th item coding information and the j-th item coding information. The server adds the frequency correlations between the i-th item coding information and the remaining n - 1 item coding information to obtain the sum C SKUi of the frequency correlations.

[0149] S111. If the sum of the frequency correlations is less than the frequency threshold, then use any other item coding information as the new item coding information in the i-th coding container until all n item coding information is traversed.

[0150] In the embodiment of the present invention, if the server detects that the sum of the frequency correlations is less than the frequency threshold, any other item coding information is used as the new item coding information in the i-th coding container until the traversal of n item coding information is completed.

[0151] In the embodiment of the present invention, if the server detects that the sum of the frequency correlations is less than the frequency threshold, any other item coding information is used as the item coding information in the new i-th coding container. Then, the server continues to traverse the i+1-th item coding information and continues to perform the above traversal process.

[0152] In the embodiment of the present invention, combined with Figure 6 , the server detects that the sum of the frequency correlations of SKU1 is less than the frequency threshold, and the server randomly determines NEW_SKU1 from SKU2 and SKU3. The server fills NEW_SKU1 in the first coding container, and then continues to traverse the remaining item coding information.

[0153] In the embodiment of the present invention, when the number of item coding information in the empty order is greater than or equal to 2, the server generates a random number corresponding to each item coding information. The server replaces and updates each item coding information based on the size of the random number of the item coding information in each coding container and the preset threshold, and the sum of the frequency correlations with other item coding information and the frequency threshold, so that the empty order better matches the actual transaction volume in the first simulation time period, so as to form an accurately matched supply chain.

[0154] In some embodiments, see Figure 7 , Figure 7 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 5 The illustrated S109 may also be implemented through S112 , which will be described in conjunction with each step.

[0155] S112. If the comparison result indicates that the i-th random number is not less than the preset threshold, the i+1-th random number of the item coding information in the i+1-th coding container is compared with the preset threshold to obtain the comparison result of the item coding information in the i+1-th coding container, and based on the comparison result, continue to traverse the remaining item coding information.

[0156] In the embodiment of the present invention, if the server detects that the comparison result indicates that the i-th random number is not less than a preset threshold, the i+1-th random number of the item coding information in the i+1-th coding container is compared with the preset threshold to obtain the comparison result of the item coding information in the i+1-th coding container, and based on the comparison result, the traversal of the remaining item coding information is continued.

[0157] Exemplarily, if the server detects that the comparison result corresponding to the first item coding information indicates that the first random number is not less than a preset threshold, the server compares the second random number of the item coding information in the second coding container with the preset threshold to obtain the comparison result of the item coding information in the second coding container, and based on the comparison result, continues to traverse the remaining item coding information.

[0158] In the embodiment of the present invention, if the server detects that the random number of an item coding information is not less than a preset threshold, the traversal of the next item coding information will continue until the traversal of all item coding information is completed. This scheme can adjust each item coding information, thereby making the order information more compatible with the first simulation time period.

[0159] In some embodiments, see Figure 8 , Figure 8 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 5 The illustrated S110 may also be implemented through S113 , which will be described in conjunction with each step.

[0160] S113. If the sum of the frequency correlations is not less than the frequency threshold, based on the transaction volume correlations corresponding to the current n item coding information in the historical order data group, the transaction volume information corresponding to the n item coding information is formed, and then the order information is formed.

[0161] In an embodiment of the present invention, if the server detects that the sum of the frequency correlations is not less than the frequency threshold, based on the transaction volume correlations corresponding to the current n item coding information in the historical order data group, the transaction volume information corresponding to the n item coding information is formed, and then the order information is formed.

[0162] In the embodiment of the present invention, if the sum of the frequency correlations of the item coding information is not less than the frequency threshold, it means that the item coding information is highly correlated with other item coding information, and the process of forming order information is executed without executing the process of adjusting the item coding information, thereby saving the time of order generation and improving the efficiency of supply chain formation.

[0163] In some embodiments, see Fig. 9 , Fig. 9 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 4 The illustrated S107 can be implemented through S114-S115, which will be described in conjunction with each step.

[0164] S114. In the historical order data group, target order data including n item coding information is determined.

[0165] In the embodiment of the present invention, the server determines target order data including n item coding information in the historical order data group.

[0166] The target order data may include z item coding information, where z is greater than or equal to n.

[0167] In the embodiment of the present invention, the server may determine the target order data including SKU1, SKU2 and SKU3 in the historical order data group.

[0168] S115. Based on the transaction volume correlations corresponding to the n item coding information obtained in advance in the target order data, the basic transaction volume information corresponding to the n item coding information is adjusted to obtain the transaction volume information corresponding to the n item coding information, thereby forming order information.

[0169] In the embodiment of the present invention, the server adjusts the basic transaction volume information corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information pre-obtained in the target order data, obtains the transaction volume information corresponding to the n item coding information, and then forms the order information.

[0170] In the embodiment of the present invention, the server adjusts the basic transaction volume information corresponding to the n item coding information based on the transaction volume correlation between each item coding information and the next item coding information obtained in advance in the target order data, obtains the transaction volume information corresponding to the n item coding information, and then forms the order information.

[0171] In the embodiment of the present invention, the server uses the transaction volume correlation corresponding to each item coding information to adjust the basic transaction volume corresponding to each item coding information, thereby avoiding the formation of transaction volume information with large errors and making the order information more consistent with the actual transaction volume in the first simulation time period.

[0172] In some embodiments, see Fig.10 , Fig.10 An optional flow chart of the order generation method provided in an embodiment of the present invention, Fig. 9 The illustrated S115 can be implemented through S116 , which will be described in conjunction with each step.

[0173] S116. Multiply the basic transaction volume information corresponding to the t-1th item coding information by the ratio of the historical transaction volume information of the tth item coding information in the target order data to the historical transaction volume information of the t-1th item coding information to obtain the transaction volume information corresponding to the tth item coding information, and then obtain the transaction volume information corresponding to the n item coding information respectively.

[0174] In the embodiment of the present invention, the server multiplies the basic transaction volume information corresponding to the t-1th item coding information by the ratio of the historical transaction volume information of the tth item coding information in the target order data to the historical transaction volume information of the t-1th item coding information, and obtains the transaction volume information corresponding to the tth item coding information, until t equals n, and then obtains the transaction volume information corresponding to the n item coding information, respectively. Wherein, t is a positive integer greater than or equal to 2 and less than n.

[0175] In the embodiment of the present invention, the server multiplies the basic transaction volume information corresponding to the first item coding information by the ratio of the historical transaction volume information of the second item coding information in the target order data to the historical transaction volume information of the first item coding information to obtain the transaction volume information corresponding to the second item coding information. The server adopts the same method to obtain the remaining transaction volume information corresponding to the n item coding information.

[0176] In some embodiments, see Fig.11 , Fig.11 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 2 The steps before S107 shown can be implemented through S117, which will be described in conjunction with each step.

[0177] S117. If n is equal to 1, then the preset transaction volume average and maximum transaction volume in the historical order data group are combined to generate basic transaction volume information corresponding to the n item coding information after the traversal is completed.

[0178] In an embodiment of the present invention, if the server detects that the number of coded containers in the empty order is 1, the server directly combines the preset transaction volume average and maximum transaction volume in the historical order data group to generate basic transaction volume information corresponding to the n item coding information after the traversal is completed.

[0179] In some embodiments, see Fig.12 , Fig.12 An optional flow chart of the order generation method provided for an embodiment of the present invention will be described in conjunction with each step.

[0180] S118. Extracting multiple order data corresponding to multiple historical time periods in a preset storage space according to preset conditions.

[0181] In the embodiment of the present invention, the server extracts a plurality of order data corresponding to a plurality of historical time periods in a preset storage space according to preset conditions.

[0182] In the embodiment of the present invention, the server can extract at least one order data corresponding to each of the multiple historical time periods from its own memory according to preset conditions. The at least one order data in each time period is combined to form multiple order data.

[0183] In the embodiment of the present invention, the server needs to use the relevant data of the mall main site order, including the time period data of the order, the area data of the order, and the target category data to extract the target SKU list, order quantity data, and sales data. The order data is stored in the distributed file system (Hadoop Distributed File System, HDFS), and the server needs to obtain the required relevant data from HDFS through the Hive computing engine.

[0184] S119. Calculate the target transaction volumes corresponding to the multiple historical time periods by combining the multiple order data.

[0185] In the embodiment of the present invention, the server combines multiple order data to calculate target transaction volumes corresponding to multiple historical time periods.

[0186] In the embodiment of the present invention, the server calculates the baseline of each historical time period in combination with the order data of each historical time period, and then calculates the target transaction volume of each historical time period in combination with the coefficient of variation and the random variable.

[0187] S120. Divide the plurality of order data into a plurality of historical order data groups according to the quantity of item coding information in the plurality of order data.

[0188] In the embodiment of the present invention, the server divides the multiple order data into multiple historical order data groups according to the quantity of item coding information in the multiple order data, wherein the order data in each historical order data group contains the same quantity of item coding information.

[0189] In the embodiment of the present invention, the structure of the historical order data group is the number of SKUs contained in the order. According to the number of SKUs contained, all order data can be divided into multiple historical order data groups.

[0190] S121. Simultaneously calculate multiple transaction-related information corresponding to multiple historical order data groups.

[0191] In the embodiment of the present invention, the server simultaneously calculates multiple transaction-related information corresponding to multiple historical order data groups.

[0192] In the embodiment of the present invention, the server simultaneously calculates the transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix corresponding to multiple historical order data groups respectively.

[0193] In the embodiment of the present invention, the server uses the spark distributed computing framework to improve the efficiency of order data processing. The server imports all historical order data groups into the resilient distributed datasets (RDD) of spark, and then the server can simultaneously calculate the transaction volume mean, transaction volume maximum, transaction volume distribution frequency information of each item coding information, frequency correlation matrix and transaction volume correlation matrix corresponding to multiple historical order data groups.

[0194] In an embodiment of the present invention, the server calculates the target transaction volume for multiple historical time periods through multiple order data for multiple historical time periods, and calculates the transaction volume mean, maximum transaction volume, transaction volume distribution frequency information of each item coding information, frequency correlation matrix and transaction volume correlation matrix for each historical order data group, providing a data basis for the subsequent formation of order information, so that the order information better matches the actual transaction volume in the first simulation time period.

[0195] In some embodiments, see Fig.13 , Fig.13 An optional flow chart of the order generation method provided in an embodiment of the present invention, Fig.12 The shown S118-S119 can be implemented through S122-S125, which will be explained in conjunction with each step.

[0196] S122. Extracting a plurality of order data corresponding to a plurality of historical time periods in a preset storage space according to the node information, the region information, and the category information of the items in the plurality of historical time periods.

[0197] In the embodiment of the present invention, the server extracts a plurality of order data corresponding to a plurality of historical time periods in a preset storage space according to the node information, the region information and the category information of the items in the plurality of historical time periods.

[0198] In an embodiment of the present invention, the server obtains node information, region information, and item category information of multiple historical time periods configured by the user. The server then extracts at least one order data corresponding to each historical time period from a preset storage space based on the node information, region information, and item category information of the multiple historical time periods. The at least one order data of each historical time period is combined to form multiple order data.

[0199] S123. Count the sum of historical transaction volume information of order data in each historical time period to obtain a baseline for each historical time period.

[0200] In the embodiment of the present invention, the server counts the sum of historical transaction volume information of order data in each historical time period to obtain a baseline for each historical time period.

[0201] In the embodiment of the present invention, the server aggregates the order data by time, and sums the transaction volumes of all SKUs to obtain a baseline for each historical time period.

[0202] S124. Obtain a coefficient of variation, multiply the baseline of each historical time period by the coefficient of variation, and then add the resultant to the baseline to obtain a theoretical transaction volume for each historical time period.

[0203] In the embodiment of the present invention, the server obtains the variation coefficient, multiplies the baseline of each historical time period by the variation coefficient, and then adds the baseline to obtain the theoretical transaction volume of each historical time period.

[0204] In the embodiment of the present invention, the server obtains the coefficient of variation configured by the user, and multiplies the baseline of each historical time period by the coefficient of variation and then adds the baseline to obtain the theoretical transaction volume of each historical time period. Exemplarily, the server multiplies each baseline by the corresponding coefficient of variation of demand, and then uses a rounding function to round the calculation result to obtain the theoretical transaction volume of each historical time period. Exemplarily, the server can calculate the theoretical transaction volume target_s_t by formula (2):

[0205] target_s_t=round(s_t*(1+demand_ratio)) (2)

[0206] Among them, round is the rounding function, s_t is the baseline, and demand_ratio is the coefficient of change. The server multiplies the baseline by the value of the coefficient of change plus 1, and then uses the rounding function to obtain the theoretical transaction volume.

[0207] S125. Add the theoretical transaction volume of each historical time period to the random variable to obtain the target transaction volume of each historical time period, and then obtain the target transaction volumes corresponding to multiple historical time periods.

[0208] In the embodiment of the present invention, the server adds the theoretical transaction volume of each historical time period to the random variable to obtain the target transaction volume of each historical time period, and then obtains the target transaction volumes corresponding to multiple historical time periods.

[0209] In the embodiment of the present invention, the server introduces volatility: on the basis of the theoretical transaction volume, a disturbance term of normal distribution is introduced to obtain the target transaction volume. The introduction of volatility can mainly increase the volatility of sales volume and restore the market environment more reasonably.

[0210] In the embodiment of the present invention, the server uses the historical sales volume as a benchmark, adds sales volume changes and disturbances, and generates the target transaction volume. Taking the coffee machine category as an example, Fig.14 Curve 1 in the middle is the baseline, curve 3 is the curve with a 30% increase in curve 1, and curve 3 is the final target trading volume after curve 1 is increased by 30% + disturbance.

[0211] In the embodiment of the present invention, the server adjusts the baseline in combination with the coefficient of variation and the random variable to obtain the final target transaction volume, so that the target transaction volume is closer to the market environment.

[0212] In some embodiments, see Fig.13 , Fig.13 An optional flow chart of the order generation method provided in an embodiment of the present invention, Fig.12 The illustrated S121 can be implemented through S126, which will be described in conjunction with each step.

[0213] S126. Simultaneously calculate the transaction volume mean, transaction volume maximum, transaction volume distribution frequency information of each item coding information, frequency correlation matrix and transaction volume correlation matrix corresponding to multiple historical order data groups.

[0214] In the embodiment of the present invention, the server simultaneously calculates the transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix corresponding to multiple historical order data groups respectively.

[0215] In some embodiments, see Fig.15 , Fig.15 An optional flow chart of the order generation method provided in an embodiment of the present invention, Fig.12 The illustrated S121 can be implemented through S127 - S131 , which will be described in conjunction with each step.

[0216] S127. Add up the historical transaction volume information of all item coding information in each historical order data group, and divide by the number of item coding information in each historical order data group to obtain the transaction volume mean of each historical order data group.

[0217] In the embodiment of the present invention, the server adds up the historical transaction volume information of all item coding information in each historical order data group, and divides the sum by the number of item coding information in each historical order data group to obtain the transaction volume mean of each historical order data group.

[0218] S128. Determine the largest historical transaction volume information from the historical transaction volume information corresponding to the item code information in each historical order data group as the maximum transaction volume.

[0219] In the embodiment of the present invention, the server determines the largest historical transaction volume information from the historical transaction volume information corresponding to the item code information in each historical order data group as the maximum transaction volume.

[0220] S129. In each historical order data group, the number of order data containing each item coding information is divided by the total amount of order data in each historical order data group to obtain transaction volume distribution frequency information of each item coding information.

[0221] In the embodiment of the present invention, the server divides the number of order data containing each item coding information in each historical order data group by the total amount of order data in each historical order data group to obtain the transaction volume distribution frequency information of each item coding information.

[0222] Exemplarily, the transaction volume distribution frequency information of SKU1 = the number of order data containing SKU1 / the number of total order data.

[0223] S130, calculating the frequency correlation between every two item coding information in each historical order data group, and arranging the frequency correlations of each item coding information with respect to other item coding information according to the order of the item coding information in each historical order data group to form each row of a frequency correlation matrix, thereby forming a frequency correlation matrix.

[0224] In an embodiment of the present invention, the server calculates the frequency correlation between every two item coding information in each historical order data group, and arranges the frequency correlation of each item coding information with respect to other item coding information according to the order of the item coding information in each historical order data group to form each row of the frequency correlation matrix, thereby forming a frequency correlation matrix.

[0225] The server may obtain the sum of the frequency correlations in the frequency correlation matrix by statistics.

[0226] S131. Calculate the transaction volume correlation between every two item coding information in each historical order data group, and arrange the transaction volume correlations of each item coding information with respect to other item coding information according to the order of the item coding information in each historical order data group to form each row of a transaction volume correlation matrix, thereby forming a transaction volume correlation matrix.

[0227] In the embodiment of the present invention, the server calculates the transaction volume correlation between every two item coding information in each historical order data group, and arranges the transaction volume correlation of each item coding information corresponding to other item coding information according to the order of the item coding information in each historical order data group to form each row of the transaction volume correlation matrix, thereby forming a transaction volume correlation matrix.

[0228] In the embodiment of the present invention, the server may obtain the transaction volume correlations between n item coding information and other item coding information in the transaction volume correlation matrix, and then adjust the transaction volume of the corresponding item coding information.

[0229] In some embodiments, see Fig.16 , Fig.16 An optional flow chart of the order generation method provided in an embodiment of the present invention, Fig.15 The illustrated S129 can be implemented through S132 - S134 , which will be described in conjunction with each step.

[0230] S132. According to the order of the item coding information in each historical order data group, the number of order data including both the k-th item coding information and the m-th item coding information is divided by the number of order data including only the k-th item coding information to obtain the first frequency correlation between the k-th item coding information and the m-th item coding information, until m equals q, to ​​obtain q-1 first frequency correlations corresponding to each item coding information.

[0231] In the embodiment of the present invention, the server divides the number of order data including both the kth item coding information and the mth item coding information by the number of order data including only the kth item coding information according to the order of the item coding information in each historical order data group, and obtains the first frequency correlation between the kth item coding information and the mth item coding information, until m equals q, and obtains q-1 first frequency correlations corresponding to each item coding information. Wherein, k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group.

[0232] In the embodiment of the present invention, the server divides the number of order data including both the first item code information and the second item code information by the number of order data including only the first item code information, and obtains the first frequency correlation between the first item code information and the second item code information. The server divides the number of order data including both the first item code information and the third item code information by the number of order data including only the first item code information, and obtains the first frequency correlation between the first item code information and the third item code information. According to the above method, the server can obtain q-1 first frequency correlations corresponding to the q item code information in each historical order data group.

[0233] S133. According to the order of the item coding information in each historical order data group, the number of order data including both the k-th item coding information and the m-th item coding information is divided by the number of order data including only the m-th item coding information to obtain the second frequency correlation between the m-th item coding information and the k-th item coding information, until k equals q, to ​​obtain q-1 second frequency correlations corresponding to each item coding information.

[0234] In the embodiment of the present invention, the server divides the number of order data including both the kth item coding information and the mth item coding information by the number of order data including only the mth item coding information according to the order of the item coding information in each historical order data group, and obtains the second frequency correlation between the mth item coding information and the kth item coding information, until k equals q, and obtains q-1 second frequency correlations corresponding to each item coding information.

[0235] In the embodiment of the present invention, the server divides the number of order data including both the first item code information and the second item code information by the number of order data including only the second item code information, and obtains the second frequency correlation between the first item code information and the second item code information. The server divides the number of order data including both the first item code information and the third item code information by the number of order data including only the third item code information, and obtains the second frequency correlation between the first item code information and the third item code information. According to the above method, the server can obtain q-1 second frequency correlations corresponding to the q item code information in each historical order data group.

[0236] S134. Use the q-1 first frequency correlations and n-1 second frequency correlations of the first item coding information as the first row of the frequency correlation matrix until the qth row of the frequency correlation matrix is ​​formed, thereby forming a frequency correlation matrix.

[0237] In the embodiment of the present invention, the server uses q-1 first frequency correlations and n-1 second frequency correlations of the first item coding information as the first row of the frequency correlation matrix until the qth row of the frequency correlation matrix is ​​formed, thereby forming a frequency correlation matrix.

[0238] In the embodiment of the present invention, the server forms a frequency correlation matrix for each historical order data group, and in the subsequent traversal process of empty orders, the sum of the frequency correlations of the encoded information in the corresponding historical order data group can be more conveniently extracted.

[0239] In some embodiments, see Fig.17 , Fig.17An optional flow chart of the order generation method provided in an embodiment of the present invention, Fig.15 The illustrated S131 can be implemented through S135-S137, which will be described in conjunction with each step.

[0240] S135. According to the order of the item coding information in each historical order data group, determine q-1 intermediate order data including both the k-th item coding information and the m-th item coding information in each historical order data group.

[0241] In the embodiment of the present invention, the server determines q-1 intermediate order data including both the kth item coding information and the mth item coding information in each historical order data group according to the order of the item coding information in each historical order data group. Wherein, k and m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group.

[0242] S136. Compare the transaction volume information corresponding to the k-th item coding information and the m-th item coding information included in each order data, and then obtain q-1 transaction volume correlations corresponding to the k-th item coding information, until k is equal to q, and obtain q-1 transaction volume correlations corresponding to the q item coding information.

[0243] In the embodiment of the present invention, the server compares the transaction volume information corresponding to the k-th item coding information and the m-th item coding information included in each order data, and then obtains q-1 transaction volume correlations corresponding to the k-th item coding information, until k is equal to q, and obtains q-1 transaction volume correlations corresponding to the q item coding information.

[0244] In the embodiment of the present invention, the server compares the transaction volume information corresponding to the first item code information and the second item code information included in each order data to obtain the transaction volume correlation between the first item code information and the second item code information. The server compares the transaction volume information corresponding to the first item code information and the third item code information included in each order data to obtain the transaction volume correlation between the first item code information and the third item code information. According to the above method, the server can obtain q-1 transaction volume correlations corresponding to the q item code information in each historical order data group.

[0245] S137. Use the q-1 transaction volume correlations of the first item coding information as the first row of the transaction volume correlation matrix until the qth row of the transaction volume correlation matrix is ​​formed, thereby forming a transaction volume correlation matrix.

[0246] In the embodiment of the present invention, the server uses the q-1 transaction volume correlations of the first item coding information as the first row of the transaction volume correlation matrix until the qth row of the transaction volume correlation matrix is ​​formed, thereby forming the transaction volume correlation matrix.

[0247] In the embodiment of the present invention, the server forms a transaction volume correlation matrix for each historical order data group, and in the subsequent order information formation process, the transaction volume correlation of the corresponding coded information in the corresponding historical order data group can be more conveniently extracted.

[0248] In some embodiments, see Fig.18 , Fig.18 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 1 The illustrated S104 can be implemented through S138, which will be described in conjunction with each step.

[0249] S137. If the transaction volume included in the order information is not less than the target transaction volume, the order information is determined to be the target order information.

[0250] In the embodiment of the present invention, if the server detects that the transaction amount included in the order information is not less than the target transaction amount, the order information is determined to be the target order information.

[0251] In some embodiments, see Fig.19 , Fig.19 An optional flow chart of the order generation method provided in an embodiment of the present invention, Figure 1 The illustrated S104 can be implemented through S139, which will be described in conjunction with each step.

[0252] S138. If the transaction volume included in the order information is less than the target transaction volume, continue to execute the process of forming the order information until the target order information is obtained.

[0253] In the embodiment of the present invention, if the server detects that the transaction volume included in the order information is less than the target transaction volume, the process of forming the order information will continue to be executed until the target order information is obtained, that is, the process of S101-S103 will continue to be executed.

[0254] In some embodiments, see Fig. 20 , Fig. 20 An optional flow chart of the order generation method provided for an embodiment of the present invention will be described in conjunction with each step.

[0255] S201. Trading volume target.

[0256] In the embodiment of the present invention, the data extraction module of the server extracts the order data in the distributed file system according to the simulation time, regional information and category information. Each order data includes: at least one sku information, and each sku information includes corresponding transaction volume data. The server calculates the transaction volume target of each simulation time period of the corresponding simulation period by combining the extracted order data through the data processing module.

[0257] S202. Order structure distribution.

[0258] In the embodiment of the present invention, the server forms a plurality of historical order data groups according to the extracted order data.

[0259] S203. SKU transaction volume information statistics.

[0260] In the embodiment of the present invention, the server can simultaneously calculate the transaction volume distribution, frequency correlation matrix, transaction volume correlation matrix and transaction volume basic statistics corresponding to multiple historical order data groups.

[0261] S204: Generate an empty order with SKU quantity n.

[0262] In the embodiment of the present invention, the server generates an empty order with n SKU quantity through a random order generation module.

[0263] S205. Draw n SKUs through roulette.

[0264] S206, n=1.

[0265] In the embodiment of the present invention, the server determines whether n is equal to 1. If n is equal to 1, S212 is executed. If n is not equal to 1, S207 is executed.

[0266] S207, R <P。

[0267] In the embodiment of the present invention, the server determines the SKU i Whether the corresponding random number R is less than P. If R is less than P, execute S211. If R is not less than P, execute S208.

[0268] S208: Correlation calculation.

[0269] S209, Correlation <C。

[0270] In the embodiment of the present invention, the server determines whether the statistical correlation is less than a threshold value C. If the correlation is less than C, S212 is executed. If not, S210 is executed.

[0271] S210, SKU correlation adjustment.

[0272] S211. Traverse n times.

[0273] S212: Generate transaction volume.

[0274] S213. Adjustment of trading volume relationship.

[0275] S214: Order generation.

[0276] S215. Achieve daily target trading volume.

[0277] In the embodiment of the present invention, the server determines whether the transaction volume in the order reaches the corresponding target transaction volume through the order timing control module. If it reaches, the order is determined to be a target order. If not, it returns to execute step S204.

[0278] S216, order generation is completed.

[0279] Please see, Fig.21 A schematic diagram of the structure of an order generating device provided in an embodiment of the present invention.

[0280] The embodiment of the present invention further provides an order generating device 800 , comprising: an order forming unit 803 , a data extracting unit 804 and a determining unit 805 .

[0281] The order forming unit 803 is used to randomly generate an empty order corresponding to the first simulation time period; the empty order includes: n coding containers; n is an integer greater than or equal to 1;

[0282] The data extraction unit 804 is used to extract n item coding information from the corresponding historical order data group based on the number of coding containers in the empty order, and use the n item coding information to fill the n coding containers respectively; the historical order data group is formed based on historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coding containers;

[0283] The order forming unit 803 is further used to traverse the item coding information in the n coding containers, and form order information corresponding to the first simulation time period based on the number of the n item coding information and related data;

[0284] The determination unit 805 is used to determine the target order information based on the comparison result of the order information and the target transaction volume of the historical time period corresponding to the first simulation time period, and then determine the target order information of other simulation time periods for the supply chain to supply.

[0285] In an embodiment of the present invention, the relevant data includes: a random number, a sum of frequency correlations and a transaction volume correlation; the order forming unit 803 in the order generating device 800 is used to traverse the item coding information in the i-th coding container if n is greater than or equal to 2; i is a positive integer greater than or equal to 1 and less than n; based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information, the item coding information in the i-th coding container is adjusted until the traversal of the item coding information in the n coding containers is completed; combined with the preset transaction volume mean and transaction volume maximum in the historical order data group, the basic transaction volume information corresponding to the n item coding information after the traversal is completed is generated; based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, the basic transaction volume information corresponding to the n item coding information is adjusted, thereby forming the order information.

[0286] In the embodiment of the present invention, the order forming unit 803 in the order generating device 800 is used to generate random numbers corresponding to the n item coding information respectively; the random numbers are random numbers greater than 0 and less than 1; the i-th random number corresponding to the item coding information in the i-th coding container is processed and compared with a preset threshold; if the comparison result indicates that the i-th random number is less than the preset threshold, the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information in the historical order data group is counted; the frequency correlations between the item coding information in the i-th coding container and other item coding information are pre-calculated; if the sum of the frequency correlations is less than the frequency threshold, any other item coding information is used as the new item coding information in the i-th coding container, until the traversal of the n item coding information is completed.

[0287] In the embodiment of the present invention, the order forming unit 803 in the order generating device 800 is used to compare the i+1th random number of the item coding information in the i+1th coding container with the preset threshold value if the comparison result indicates that the i-th random number is not less than the preset threshold value, to obtain the comparison result of the item coding information in the i+1th coding container, and continue to traverse the remaining item coding information based on the comparison result.

[0288] In an embodiment of the present invention, the order forming unit 803 in the order generating device 800 is used to form the transaction volume information corresponding to the n item coding information respectively based on the transaction volume correlation corresponding to the current n item coding information in the historical order data group if the sum of the frequency correlations is not less than the frequency threshold, and then form the order information.

[0289] In the embodiment of the present invention, the order forming unit 803 in the order generating device 800 is used to determine the target order data including the n item coding information in the historical order data group; based on the transaction volume correlation corresponding to the n item coding information obtained in advance in the target order data, the basic transaction volume information corresponding to the n item coding information is adjusted to obtain the transaction volume information corresponding to the n item coding information, thereby forming the order information.

[0290] In an embodiment of the present invention, the order forming unit 803 in the order generating device 800 is used to multiply the basic transaction volume information corresponding to the t-1th item coding information by the ratio of the historical transaction volume information of the t-1th item coding information in the target order data to the historical transaction volume information of the t-1th item coding information, to obtain the transaction volume information corresponding to the t-1th item coding information, and then obtain the transaction volume information corresponding to the n item coding information respectively; t is a positive integer greater than or equal to 2 and less than n.

[0291] In an embodiment of the present invention, the order forming unit 803 in the order generating device 800 is used to, if n is equal to 1, combine the preset transaction volume mean and transaction volume maximum in the historical order data group to generate basic transaction volume information corresponding to the n item coding information after the traversal is completed.

[0292] In an embodiment of the present invention, the data extraction unit 804 in the order generation device 800 is used to extract multiple order data corresponding to the multiple historical time periods in a preset storage space according to preset conditions; each order data includes: at least one item coding information, and each item coding information includes: corresponding historical transaction volume information; combining the multiple order data, calculating the target transaction volumes corresponding to the multiple historical time periods respectively; according to the number of item coding information in the multiple order data, dividing the multiple order data into multiple historical order data groups; the order data in each historical order data group contains the same number of item coding information; and simultaneously calculating multiple transaction-related information corresponding to the multiple historical order data groups respectively.

[0293] In an embodiment of the present invention, the preset conditions include: node information, area information and category information of the multiple historical time periods; the data extraction unit 804 in the order generation device 800 is used to extract the multiple order data corresponding to the multiple historical time periods in the preset storage space based on the node information of the multiple historical time periods, the area information and the category information of the items.

[0294] In an embodiment of the present invention, the determination unit 805 in the order generation device 800 is used to count the sum of the historical transaction volume information of the order data in each historical time period to obtain the baseline of each historical time period; obtain the variation coefficient, multiply the baseline of each historical time period by the variation coefficient and then add the baseline to obtain the theoretical transaction volume of each historical time period; add the theoretical transaction volume of each historical time period to the random variable to obtain the target transaction volume of each historical time period, and then obtain the target transaction volumes corresponding to the multiple historical time periods.

[0295] In an embodiment of the present invention, the determination unit 805 in the order generation device 800 is used to simultaneously calculate the transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix respectively corresponding to the multiple historical order data groups.

[0296] In the embodiment of the present invention, the determining unit 805 in the order generating device 800 is used to add the historical transaction volume information of all the item coding information in each historical order data group, and divide it by the number of the item coding information in each historical order data group to obtain the transaction volume mean of each historical order data group; among the historical transaction volume information corresponding to the item coding information in each historical order data group, determine the largest historical transaction volume information as the maximum transaction volume; in each historical order data group, divide the number of order data respectively containing each item coding information by the total amount of the order data in each historical order data group to obtain the transaction volume distribution of each item coding information. The method further comprises the steps of: calculating the frequency correlation between each two item coding information in each historical order data group, arranging the frequency correlation between each item coding information and other item coding information according to the order of the item coding information in each historical order data group, forming each row of the frequency correlation matrix, and further forming the frequency correlation matrix; calculating the transaction volume correlation between each two item coding information in each historical order data group, arranging the transaction volume correlation between each item coding information and other item coding information according to the order of the item coding information in each historical order data group, and further forming the transaction volume correlation matrix.

[0297] In the embodiment of the present invention, the determining unit 805 in the order generating device 800 is used to obtain the first frequency correlation between the kth item coding information and the mth item coding information by dividing the number of the order data including both the kth item coding information and the mth item coding information by the number of the order data including only the kth item coding information according to the order of the item coding information in each historical order data group, until m is equal to q, and q-1 first frequency correlations corresponding to each item coding information are obtained; k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group; according to each historical order data group, The order of the item coding information in a single data group is obtained by dividing the number of the order data including both the kth item coding information and the mth item coding information by the number of the order data including only the mth item coding information, to obtain the second frequency correlation between the mth item coding information and the kth item coding information, until k is equal to q, to ​​obtain q-1 second frequency correlations corresponding to each item coding information; the q-1 first frequency correlations and q-1 second frequency correlations of the first item coding information are used as the first row of the frequency correlation matrix, until the nth row of the frequency correlation matrix is ​​formed, thereby forming the frequency correlation matrix.

[0298] In an embodiment of the present invention, the determination unit 805 in the order generation device 800 is used to determine q-1 order data including both the k-th item coding information and the m-th item coding information in each historical order data group according to the order of the item coding information in the historical order data group; k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group; the transaction volume information corresponding to the k-th item coding information and the m-th item coding information included in each order data are compared, and then q-1 transaction volume correlations corresponding to the k-th item coding information are obtained, until k is equal to q, and q-1 transaction volume correlations corresponding to the q item coding information are obtained; the q-1 transaction volume correlations of the first item coding information are used as the first row of the transaction volume correlation matrix, until the q-th row of the transaction volume correlation matrix is ​​formed, and then the transaction volume correlation matrix is ​​formed.

[0299] In an embodiment of the present invention, the determination unit 805 in the order generating device 800 is used to determine that the order information is the target order information if the transaction volume included in the order information is not less than the target transaction volume; if the transaction volume included in the order information is less than the target transaction volume, continue to execute the process of forming the order information until the target order information is obtained.

[0300] In the embodiment of the present invention, an empty order corresponding to the first simulation time period is randomly generated by the order forming unit 803; the empty order includes: n coding containers; the data extraction unit 804 extracts n item coding information from the corresponding historical order data group based on the number of coding containers in the empty order, and uses the n item coding information to fill the n coding containers respectively; the historical order data group is formed based on the historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coding containers; the order forming unit 803 traverses the item coding information in the n coding containers, and forms the order information corresponding to the first simulation time period based on the number of n item coding information and related data; the determination unit 805 determines the target order information based on the order information and the comparison result of the target transaction volume of the historical time period corresponding to the first simulation time period, and then determines the target order information of other simulation time periods, and then forms an accurate supply chain solution. Since the target order information is formed based on the corresponding order information, and the order information is formed based on the number of n item coding information and related data in the randomly generated empty order, the target order data is more consistent with the actual transaction volume in the first simulation time period. Therefore, by using the target order data for each simulation time period generated by this scheme, a supply chain scheme that matches the simulation period can be accurately formed.

[0301] It should be noted that, in the embodiment of the present invention, if the above-mentioned order generation method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium and includes several instructions for enabling an order generation device (which can be a personal computer, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present invention is not limited to any specific combination of hardware and software.

[0302] Correspondingly, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are implemented.

[0303] Correspondingly, an embodiment of the present invention provides an order generating device, including a memory 802 and a processor 801, wherein the memory 802 stores a computer program that can be executed on the processor 801, and the processor 801 implements the steps in the above method when executing the program.

[0304] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of the present invention, please refer to the description of the method embodiments of the present invention for understanding.

[0305] It should be noted that Fig. 22 A schematic diagram of a hardware entity of an order generating device provided by an embodiment of the present invention, such as Fig. 22 As shown, the hardware entity of the order generating device 800 includes: a processor 801 and a memory 802, wherein;

[0306] The processor 801 generally controls the overall operation of the order generation device 800 .

[0307] The memory 802 is configured to store instructions and applications executable by the processor 801, and can also cache data to be processed or processed by the processor 801 and each module in the order generating device 800 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented through flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0308] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present invention, the size of the serial number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. The serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0309] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0310] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0311] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0312] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0313] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a magnetic disk or an optical disk, and other media that can store program codes.

[0314] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a mobile storage device, ROM, a magnetic disk or an optical disk.

[0315] The above is only an embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which 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. An order generation method, characterized in that: include: Randomly generate empty orders corresponding to the first simulation time period; The empty order includes: n encoding containers; n is an integer greater than or equal to 1; Based on the number of coded containers in the empty order, n item coding information is extracted from the corresponding historical order data group, and the n coded containers are filled with the n item coding information respectively; the historical order data group is formed based on historical order data in multiple historical time periods, and is a collection of historical order data corresponding to the number of coded containers; If n is greater than or equal to 2, the item coding information in the i-th coding container is adjusted according to the order of the item coding information in the n coding containers, based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information, until the traversal of the item coding information in the n coding containers is completed; i is a positive integer greater than or equal to 1 and less than n; Combine the preset transaction volume average and transaction volume maximum in the historical order data group to generate basic transaction volume information corresponding to the n item coding information after the traversal is completed; Based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, adjusting the basic transaction volume information respectively corresponding to the n item coding information, thereby forming the order information; Based on the order information, the target order information is determined by comparing the target transaction volume of the historical time period corresponding to the first simulation time period, and then the target order information of other simulation time periods is determined to form a supply chain solution.

2. The order generation method according to claim 1, characterized in that: The method further comprises: adjusting the item coding information in the i-th coding container according to the order of the item coding information in the n coding containers based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information until the traversal of the item coding information in the n coding containers is completed: Generate random numbers corresponding to the n item coding information respectively; the random numbers are random numbers greater than 0 and less than 1; The adjusting the item coding information in the i-th coding container according to the order of the item coding information in the n coding containers based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information until the traversal of the item coding information in the n coding containers is completed includes: Processing to obtain an i-th random number corresponding to the item coding information in the i-th coding container, and comparing it with a preset threshold; If the comparison result indicates that the i-th random number is less than the preset threshold, the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information in the historical order data group is calculated; the frequency correlations between the item coding information in the i-th coding container and other item coding information are pre-calculated; If the sum of the frequency correlations is less than the frequency threshold, any other item coding information is used as the new item coding information in the i-th coding container until the traversal of the n item coding information is completed.

3. The order generation method according to claim 2, characterized in that: After the processing obtains the i-th random number corresponding to the item coding information in the i-th coding container and compares it with the preset threshold, before combining the preset transaction volume average and transaction volume maximum in the historical order data group to generate the basic transaction volume information corresponding to the n item coding information after the traversal is completed, the method further includes: If the comparison result indicates that the i-th random number is not less than the preset threshold, the i+1-th random number of the item coding information in the i+1-th coding container is compared with the preset threshold to obtain the comparison result of the item coding information in the i+1-th coding container, and based on the comparison result, continue to traverse the remaining item coding information.

4. The order generation method according to claim 2, characterized in that: If the comparison result indicates that the i-th random number is less than the preset threshold, after counting the sum of the frequency correlations between the item coding information in the i-th coding container and other item coding information in the historical order data group, the method further includes: If the sum of the frequency correlations is not less than the frequency threshold, based on the transaction volume correlations corresponding to the current n item coding information in the historical order data group, the transaction volume information corresponding to the n item coding information is formed, and then the order information is formed.

5. The order generation method according to any one of claims 1 to 4, characterized in that: The adjusting the basic transaction volume information respectively corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, thereby forming the order information, includes: In the historical order data group, determining target order data including the n item coding information at the same time; Based on the transaction volume correlation corresponding to the n item coding information obtained in advance in the target order data, the basic transaction volume information corresponding to the n item coding information is adjusted to obtain the transaction volume information corresponding to the n item coding information, thereby forming the order information.

6. The order generation method according to claim 5, characterized in that: The adjusting the basic transaction volume information respectively corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information obtained in advance in the target order data to obtain the transaction volume information respectively corresponding to the n item coding information includes: The basic transaction volume information corresponding to the t-1th item coding information is multiplied by the ratio of the historical transaction volume information of the tth item coding information in the target order data to the historical transaction volume information of the t-1th item coding information to obtain the transaction volume information corresponding to the tth item coding information, until t equals n, and then the transaction volume information corresponding to the n item coding information is obtained respectively; t is a positive integer greater than or equal to 2 and less than n.

7. The order generation method according to claim 1, characterized in that: Before adjusting the basic transaction volume information respectively corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information in the historical order data group to form the order information, the method further includes: If n is equal to 1, then the basic transaction volume information corresponding to the n item coding information after the traversal is completed is generated in combination with the preset transaction volume average and transaction volume maximum in the historical order data group.

8. The order generation method according to claim 1, characterized in that: Before randomly generating empty orders corresponding to the first simulation time period, the method further includes: Extracting a plurality of order data corresponding to the plurality of historical time periods in a preset storage space according to preset conditions; each order data includes: at least one item coding information, and each item coding information includes: corresponding historical transaction volume information; Calculate the target transaction volumes corresponding to the multiple historical time periods respectively in combination with the multiple order data; According to the quantity of item coding information in the plurality of order data, the plurality of order data are divided into a plurality of historical order data groups; the order data in each historical order data group contains the same quantity of item coding information; At the same time, multiple transaction related information corresponding to the multiple historical order data groups are calculated respectively.

9. The order generation method according to claim 8, characterized in that: The preset conditions include: node information, region information and item category information of the multiple historical time periods; The extracting, in the preset storage space according to the preset conditions, a plurality of order data corresponding to the plurality of historical time periods comprises: The plurality of order data corresponding to the plurality of historical time periods are extracted in the preset storage space according to the node information of the plurality of historical time periods, the region information and the category information of the items.

10. The order generation method according to claim 8, characterized in that: The step of combining the plurality of order data and calculating the target transaction volumes respectively corresponding to the plurality of historical time periods includes: Counting the sum of the historical transaction volume information of the order data in each historical time period to obtain the baseline of each historical time period; Obtaining a coefficient of variation, multiplying the baseline of each historical time period by the coefficient of variation and then adding the resultant to the baseline to obtain a theoretical transaction volume for each historical time period; The theoretical transaction volume of each historical time period is added to a random variable to obtain the target transaction volume of each historical time period, and then the target transaction volumes corresponding to the multiple historical time periods are obtained.

11. The order generation method according to claim 8, characterized in that: The multiple transaction related information include: transaction volume mean, transaction volume maximum, transaction volume distribution frequency information of each item coding information, frequency correlation matrix and transaction volume correlation matrix; The simultaneously calculating a plurality of transaction-related information respectively corresponding to the plurality of historical order data groups comprises: The transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix respectively corresponding to the multiple historical order data groups are calculated simultaneously.

12. The order generation method according to claim 11, characterized in that: The simultaneously calculating the transaction volume mean, the transaction volume maximum, the transaction volume distribution frequency information of each item coding information, the frequency correlation matrix and the transaction volume correlation matrix respectively corresponding to the multiple historical order data groups, comprises: Add the historical transaction volume information of all item code information in each historical order data group, and divide by the number of item code information in each historical order data group to obtain the transaction volume mean of each historical order data group; Determining the largest historical transaction volume information among the historical transaction volume information corresponding to the item code information in each historical order data group as the maximum transaction volume; In each of the historical order data groups, the number of order data containing each of the item coding information is divided by the total amount of the order data in each of the historical order data groups to obtain the transaction volume distribution frequency information of each of the item coding information; Calculating the frequency correlation between every two item code information in each historical order data group, and arranging the frequency correlation between each item code information and other item code information according to the order of the item code information in each historical order data group to form each row of the frequency correlation matrix, thereby forming the frequency correlation matrix; The transaction volume correlation between every two item coding information in each historical order data group is calculated, and the transaction volume correlation between each item coding information and other item coding information is arranged according to the order of the item coding information in each historical order data group to form each row of the transaction volume correlation matrix, thereby forming the transaction volume correlation matrix.

13. The order generation method according to claim 12, characterized in that: The calculating the frequency correlation between every two item code information in each historical order data group, arranging the frequency correlation between each item code information and other item code information according to the order of the item code information in each historical order data group to form each row of the frequency correlation matrix, and further forming the frequency correlation matrix, includes: According to the order of the item coding information in each historical order data group, the number of the order data including both the k-th item coding information and the m-th item coding information is divided by the number of the order data including only the k-th item coding information, to obtain the first frequency correlation between the k-th item coding information and the m-th item coding information, until m is equal to q, to ​​obtain q-1 first frequency correlations corresponding to each item coding information respectively; k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group; According to the order of the item code information in each historical order data group, the number of the order data including both the k-th item code information and the m-th item code information is divided by the number of the order data including only the m-th item code information, to obtain the second frequency correlation between the m-th item code information and the k-th item code information, until k is equal to q, to ​​obtain q-1 second frequency correlations corresponding to each item code information; The q-1 first frequency correlations and q-1 second frequency correlations of the first item code information are used as the first row of the frequency correlation matrix until the nth row of the frequency correlation matrix is ​​formed, thereby forming the frequency correlation matrix.

14. The order generation method according to claim 12, characterized in that: The calculating of the transaction volume correlation between each two item coding information in each historical order data group, arranging the transaction volume correlation between each item coding information and other item coding information according to the order of the item coding information in each historical order data group, forming each row of the transaction volume correlation matrix, and further forming the transaction volume correlation matrix, includes: According to the order of the item coding information in each historical order data group, q-1 order data including both the k-th item coding information and the m-th item coding information are determined in each historical order data group; k, m are positive integers greater than or equal to 1 and less than q, and k and m are different; q is the number of item coding information in each historical order data group; Compare the transaction volume information corresponding to the k-th item code information and the m-th item code information included in each order data, and then obtain q-1 transaction volume correlations corresponding to the k-th item code information, until k is equal to q, and obtain q-1 transaction volume correlations corresponding to the q item code information; The q-1 transaction volume correlations of the first item coding information are used as the first row of the transaction volume correlation matrix until the qth row of the transaction volume correlation matrix is ​​formed, thereby forming the transaction volume correlation matrix.

15. The order generation method according to claim 1, characterized in that: The target order information is determined based on the order information and the comparison result with the target transaction volume of the historical time period corresponding to the first simulation time period, including any one of the following: If the transaction volume included in the order information is not less than the target transaction volume, determining that the order information is the target order information; If the transaction volume included in the order information is less than the target transaction volume, the process of forming the order information continues until the target order information is obtained.

16. An order generating device, characterized in that: include: An order forming unit, used for randomly generating an empty order corresponding to a first simulation time period; The empty order includes: n encoding containers; n is an integer greater than or equal to 1; A data extraction unit, configured to extract n item coding information from a corresponding historical order data group based on the number of coding containers in the empty order, and use the n item coding information to fill the n coding containers respectively; the historical order data group is a collection of historical order data corresponding to the number of coding containers formed based on historical order data in multiple historical time periods; The order forming unit is further configured to, if n is greater than or equal to 2, adjust the item coding information in the i-th coding container according to the order of the item coding information in the n coding containers, based on the random number of the item coding information in the i-th coding container and the sum of the frequency correlations with other item coding information, until the traversal of the item coding information in the n coding containers is completed; i is a positive integer greater than or equal to 1 and less than n; The order forming unit is further used to generate basic transaction volume information corresponding to the n item coding information respectively after the traversal is completed, combining the preset transaction volume average and transaction volume maximum in the historical order data group; The order forming unit is further configured to adjust the basic transaction volume information respectively corresponding to the n item coding information based on the transaction volume correlation corresponding to the n item coding information in the historical order data group, thereby forming the order information; A determination unit is used to determine the target order information based on the order information and the comparison result of the target transaction volume of the historical time period corresponding to the first simulation time period, and then determine the target order information of other simulation time periods for the supply chain to supply.

17. An order generating device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the steps in the method according to any one of claims 1 to 15 are implemented.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 15 are implemented.

Images