Cloud-native supply chain service platform

Abstract

The present invention belongs to the field of project data management, and discloses a cloud-native supply chain service platform, including a demand order management module and an order matching module; the demand order management module is used to obtain the customer's demand order; the order matching module includes a database unit, a pre-matching unit, a display unit and a confirmation unit; the database unit is used to store the supplier's supply information and a set A of keywords of the supply information; the pre-matching unit is used to obtain a set B of keywords in the demand order, and calculate the matching value between the set B and the set A corresponding to each supplier, and transmit the list of suppliers with matching values ​​greater than a set threshold and the supply information to the display unit; the display unit is used to display the list of suppliers and the supply information sent by the pre-matching unit; the confirmation unit is used for the staff to select the final confirmed supplier from the list of suppliers. The present invention effectively improves the matching speed of demand orders and improves the distribution speed of the supply chain.

Description

Technical Field

[0001] The present invention relates to the field of project data management, and in particular to a cloud-native based supply chain service platform. Background Art

[0002] Supply chain service platform refers to a platform that manages the entire process from warehousing to distribution of goods. In the process of matching demand orders and suppliers, existing supply chain service platforms generally use manual matching, that is, the staff first checks the content of the demand order, and then searches the supplier database based on the content to determine whether a suitable supplier can be found. However, this matching method needs to deal with too many suppliers, and the matching speed is relatively slow. When there are many demand orders, it will affect the matching speed of the demand orders, thereby affecting the distribution speed of the supply chain. Summary of the invention

[0003] The purpose of the present invention is to disclose a cloud-native supply chain service platform to solve the problem of how to improve the matching speed of demand orders of the supply chain service platform, thereby improving the distribution speed of the supply chain.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] The present invention provides a cloud-native-based supply chain service platform, including a demand order management module and an order matching module;

[0006] The demand order management module is used to obtain customer demand orders;

[0007] The order matching module includes a database unit, a pre-matching unit, a display unit and a confirmation unit;

[0008] The database unit is used to store the supply information of the supplier and a set A of keywords of the supply information;

[0009] The pre-matching unit is used to obtain a set B of keywords in the demand order, calculate a matching value between the set B and a set A corresponding to each supplier, and transmit a list of suppliers whose matching values ​​are greater than a set threshold and supply information to the display unit;

[0010] The display unit is used to display the list of suppliers and supply information sent by the pre-matching unit;

[0011] The confirmation unit is used by staff to select the final confirmed suppliers from the list of suppliers.

[0012] Preferably, it also includes a supplier module and a progress management module;

[0013] The confirmation unit is also used to forward the demand order to the supplier module used by the final confirmed supplier;

[0014] The supplier module is used for suppliers to upload the production progress of demand orders to the progress management module;

[0015] The progress management module is used to store the production progress of demand orders and for staff to view the production progress of demand orders.

[0016] Preferably, it also includes a logistics management module and a logistics module.

[0017] The supplier module is also used for the supplier to upload the shipment information of the goods to the logistics management module when shipping after the supplier has completed the production of the goods corresponding to the demand order;

[0018] The logistics module is used by logistics distribution companies to upload the logistics information of goods to the logistics management module.

[0019] Preferably, the logistics management module is also used for staff to view the delivery information and logistics information of the goods.

[0020] Preferably, it also includes a staff authority management module;

[0021] The staff authority management module is used to determine whether the staff has the authority to use the order matching module, progress management module, and logistics management module.

[0022] Preferably, the supply information includes text data of the supplier's main business.

[0023] Preferably, the demand order includes text data of the goods that the customer needs to purchase.

[0024] Preferably, the keyword set A of the supply information is acquired by a preset keyword acquisition algorithm and stored in the database unit.

[0025] Preferably, obtaining a set B of keywords in the demand order includes:

[0026] Calculate the difficulty coefficient of analyzing the text data of the goods that the customer needs to purchase;

[0027] According to the analysis difficulty coefficient, a corresponding keyword algorithm is selected to obtain keywords in the text data of the goods to be purchased.

[0028] Preferably, the calculation function of the matching value is:

[0029]

[0030] matval A,B Represents the matching value between set A and set B; judval bIndicates the judgment value of keyword b in set B. If set A contains b, then judval b The value of 1, otherwise, judval b The value of is 0, and nwdB represents the total number of keywords contained in set B.

[0031] Compared with the prior art, the present invention can automatically match a list of suppliers that meet the requirements based on the text information of the demand order, thereby narrowing the selection range of the staff responsible for selecting suppliers, effectively improving the matching speed of the demand order, and effectively improving the distribution speed of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A schematic diagram of the cloud-native supply chain service platform of the present invention.

[0034] Figure 2 Another schematic diagram of the cloud-native supply chain service platform of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] like Figure 1 In one embodiment shown, the present invention provides a cloud-native-based supply chain service platform, including a demand order management module and an order matching module;

[0037] The demand order management module is used to obtain customer demand orders;

[0038] The order matching module includes a database unit, a pre-matching unit, a display unit and a confirmation unit;

[0039] The database unit is used to store the supply information of the supplier and a set A of keywords of the supply information;

[0040] The pre-matching unit is used to obtain a set B of keywords in the demand order, calculate a matching value between the set B and a set A corresponding to each supplier, and transmit a list of suppliers whose matching values ​​are greater than a set threshold and supply information to the display unit;

[0041] The display unit is used to display the list of suppliers and supply information sent by the pre-matching unit;

[0042] The confirmation unit is used by staff to select the final confirmed suppliers from the list of suppliers.

[0043] The above implementation can automatically match a list of suppliers that meet the requirements based on the text information of the demand order, thereby narrowing the selection range of the staff responsible for selecting suppliers, effectively improving the matching speed of the demand order, and effectively improving the distribution speed of the supply chain.

[0044] In some embodiments, the order matching module is configured using cloud native technology and installed in a cloud server.

[0045] Cloud native is a way to build and run applications that fully utilizes the advantages of cloud computing. It is a set of technical systems and methodologies. Cloud native is a combination of "cloud + native". "Cloud" means that the application is located in the cloud, not in a traditional data center; "native" can be understood as something that comes with it, that is, the application is designed with the cloud environment in mind from the beginning.

[0046] Cloud-native applications are developed on a microservices architecture (called microservices), which are designed as independent modules serving a specific purpose.

[0047] The order matching module is deployed using cloud native technology, so that the order matching module can adopt cloud technology based on the cloud environment, make full use of the elastic scaling and distributed characteristics of the cloud platform, and ultimately run efficiently, stably and securely in the cloud.

[0048] Preferably, if Figure 2 As shown, it also includes supplier module and progress management module;

[0049] The confirmation unit is also used to forward the demand order to the supplier module used by the final confirmed supplier;

[0050] The supplier module is used for suppliers to upload the production progress of demand orders to the progress management module;

[0051] The progress management module is used to store the production progress of demand orders and for staff to view the production progress of demand orders.

[0052] Specifically, the vendor module is used by different vendors and is installed in the computing devices used by the vendors.

[0053] During the production process of demand orders, suppliers can upload production progress through the supplier module, for example, the production quantity of each type of goods.

[0054] Preferably, it also includes a logistics management module and a logistics module.

[0055] The supplier module is also used for the supplier to upload the shipment information of the goods to the logistics management module when shipping after the supplier has completed the production of the goods corresponding to the demand order;

[0056] The logistics module is used by logistics distribution companies to upload the logistics information of goods to the logistics management module.

[0057] Specifically, the delivery information includes the name of the logistics company that undertakes the task of transporting the goods, the delivery time, the logistics order number, etc. The logistics information includes the time when the goods pass through the logistics nodes during transportation and the location of the goods.

[0058] The logistics module is configured to match the logistics information, shipping information and logistics order number.

[0059] Preferably, the logistics management module is also used for staff to view the delivery information and logistics information of the goods.

[0060] Specifically, the staff can check the delivery information and logistics information based on the logistics order number, demand order number, etc.

[0061] Preferably, it also includes a staff authority management module;

[0062] The staff authority management module is used to determine whether the staff has the authority to use the order matching module, progress management module, and logistics management module.

[0063] Specifically, only when the staff has the permission to use the corresponding module, the corresponding module receives the operation instruction input by the staff.

[0064] Preferably, determining whether the staff member has the use authority includes:

[0065] Obtain the staff member's ID through face recognition, and obtain the staff member's access rights based on the ID;

[0066] Determine whether the staff's usage permissions include the permission to use the order matching module;

[0067] Determine whether the staff member's permission to use the progress management module includes permission to use the progress management module;

[0068] Determine whether the staff's usage permissions include the permission to use the logistics management module.

[0069] Preferably, the staff member's number is obtained by face recognition, including:

[0070] Obtaining facial images of staff members;

[0071] Get the number corresponding to the face image.

[0072] In other implementations, the staff member's number may also be obtained through the staff member's fingerprint image.

[0073] Preferably, obtaining the serial number corresponding to the face image includes:

[0074] The facial image of the staff member is matched with the facial images in the employee information database to determine the number corresponding to the facial image of the staff member.

[0075] Specifically, the employee information database contains information such as the number, facial image, position, and authority of each staff member.

[0076] Preferably, matching the facial image of the staff member with the facial images in the employee information database includes:

[0077] Use pha to represent the face image of the staff member, and use phb to represent the face image in the employee information database;

[0078] Calculate the similarity between pha and phb;

[0079] If the similarity is greater than the set similarity threshold, the number corresponding to phb is used as the number corresponding to pha.

[0080] Specifically, the matching process is to match pha with the facial images in the employee information database one by one.

[0081] Preferably, calculating the similarity between pha and phb includes:

[0082] Get the foreground parts in pha and phb respectively to obtain image phafr and image phbfr;

[0083] Compute the similarity between phafr and image phbfr.

[0084] Specifically, by calculating the similarity of only the foreground part, the similarity can better reflect the similarity between the two faces, because the information of the background part is removed and the foreground part is the face part.

[0085] Preferably, the process of performing foreground extraction on ph is as follows, ph∈{pha,phb}:

[0086] Get the grayscale image pf corresponding to ph;

[0087] From pf, the gray value is in the interval [gray mi ,gray ma ] pixels make up the image pi, gray mi and gray ma Respectively represent the minimum and maximum values ​​of the interval;

[0088] The Otsu method was used to calculate pi and obtain the segmentation threshold;

[0089] Use the segmentation threshold to segment the image ph, and take the pixels greater than the segmentation threshold as the pixels of the foreground part in ph.

[0090] Specifically, the present invention does not directly calculate the segmentation threshold based on all pixels. If the pixel values ​​of the foreground pixels are high overall, the calculated threshold may also be high, which may cause some pixels belonging to the foreground but with relatively low grayscale values ​​to be mistakenly classified as background, thus affecting the integrity of the obtained foreground. mi ,gray ma ] pixels, which can alleviate the situation where the threshold is too high. Thus, the integrity of the foreground part is improved.

[0091] Preferably, gray mi and gray ma The method of obtaining is:

[0092] Get the minimum value of D that satisfies the following inequality and use this minimum value as gray mi Values:

[0093]

[0094] Get the maximum value of E that satisfies the following inequality and use this maximum value as gray ma Values:

[0095]

[0096] num j and num k They represent the number of pixels with grayscale values ​​j and k respectively; numgray is the total number of pixels in pf.

[0097] Specifically, gray mi and gray maThe value of is obtained based on the minimum and maximum grayscale values ​​when the cumulative number of pixels with different grayscale values ​​accounts for 0.05. mi and gray ma It can change with the changes of different grayscale images, thereby improving the application scope of the foreground extraction method of the present invention.

[0098] Preferably, the supply information includes text data of the supplier's main business.

[0099] In some embodiments, the supply information also includes the supplier's production capacity data and the performance parameters of the products that can be produced.

[0100] For example, for a supplier of plastic products, the performance parameters include the size information, raw material information, weight, load-bearing capacity, production cycle, etc. of various types of plastic products.

[0101] Preferably, the demand order includes text data of the goods that the customer needs to purchase.

[0102] In some implementations, the demand order also includes a demand order number, demand information for each type of goods, etc.

[0103] Preferably, the keyword set A of the supply information is acquired by a preset keyword acquisition algorithm and stored in the database unit.

[0104] Specifically, by pre-acquiring the keywords in set A, there is no need to extract the keywords in set A in the subsequent process of matching demand orders, thereby further improving the efficiency of order matching.

[0105] Specifically, the preset keyword acquisition algorithm may be a keyword extraction algorithm based on statistical features.

[0106] Preferably, obtaining a set B of keywords in the demand order includes:

[0107] Calculate the difficulty coefficient of analyzing the text data of the goods that the customer needs to purchase;

[0108] According to the analysis difficulty coefficient, a corresponding keyword algorithm is selected to obtain keywords in the text data of the goods to be purchased.

[0109] Specifically, the present invention can obtain different algorithms to extract keywords according to the analysis difficulty coefficient, so that when the text data is relatively simple, an algorithm with a faster operation speed can be used to obtain keywords, and when the text data is relatively complex, an algorithm with a stronger extraction ability but a more time-consuming algorithm can be used to obtain keywords. This avoids directly using an algorithm with a stronger extraction ability but a more time-consuming algorithm to obtain keywords, resulting in a longer time required to obtain keywords for relatively simple text data. This is conducive to improving the matching speed of the orders of the present invention.

[0110] Preferably, calculating the analysis difficulty coefficient of the text data of the goods that the customer needs to purchase includes:

[0111] Use a preset word segmentation algorithm to perform word segmentation processing on the text data of the goods that the customer needs to purchase, and obtain a set C of words contained in the text data;

[0112] The difficulty coefficient of the analysis is calculated based on set C.

[0113] Specifically, the word segmentation algorithm may be a maximum matching algorithm, a shortest path word segmentation algorithm, or the like.

[0114] Preferably, the difficulty coefficient is calculated based on the set C, including:

[0115] The calculation function of the analysis difficulty coefficient is:

[0116]

[0117] Among them, anadif C represents the word segmentation difficulty coefficient of set C, typu represents the set of types of the length of words in set C, and w i Indicates the weight of type i words in set C, num i Indicates the number of words of type i contained in set C, num al represents the total number of words contained in the set C, w mid Indicates the median weight of all types of words, distwrd max Indicates the maximum number of characters between two adjacent stop words in the text data of the goods that the customer needs to purchase. stddist indicates the preset number. stddist is greater than distwrd. max , num tot The total number of characters in the text data representing the goods that the customer needs to purchase, num stp It represents the number of stop words contained in the text data of the goods that the customer needs to purchase. α, β, and δ represent the preset type weight, interval weight, and quantity weight, respectively. α∈[0.1,0.5], β∈(0.1,0.3), and δ∈(0.1,0.3).

[0118] Specifically, the analysis difficulty coefficient is calculated from three aspects: the difference in the number of words of various lengths, the character length of consecutive non-stop words, and the number of stop words. In the present invention, the more types of word lengths, the greater the difference between the number of different types of words, and the greater the difference between the number of different types of words. max The larger the value of is, the fewer the number of stop words is, which means the more complex the content of the text data is, and the more difficult it is to extract keywords. Because at this time, there are not enough stop words to divide the text data, and the continuous length of non-stop words is very long.

[0119] w i It increases with the length of the word. For example, when the words have three types of lengths: 2, 3, and 4, the weight of a two-character word can be 0.2, the weight of a three-character word can be 0.3, and the weight of a four-character word can be 0.4.

[0120] Preferably, the corresponding keyword algorithm is selected according to the analysis difficulty coefficient to obtain the keywords in the text data of the goods to be purchased, including:

[0121] If anadif C If the difficulty coefficient is less than a preset first difficulty coefficient threshold, a keyword extraction algorithm based on statistical features is selected to obtain keywords in the text data of the goods to be purchased;

[0122] If anadif C If the value is greater than or equal to a preset first difficulty coefficient threshold and less than or equal to a preset second difficulty coefficient threshold, a keyword extraction algorithm based on a word vector is selected to obtain keywords in the text data of the goods to be purchased;

[0123] If anadif C If the difficulty coefficient is greater than a preset second difficulty coefficient threshold, a keyword extraction algorithm based on deep learning is selected to obtain keywords in the text data of the goods to be purchased.

[0124] Specifically, the calculation speed of the keyword extraction algorithm based on statistical features is relatively fast, but it can only obtain sufficiently accurate keyword extraction results in relatively simple texts, while the calculation speed of the keyword extraction algorithm based on deep learning is relatively slow, but it can obtain sufficiently accurate keyword extraction results in complex texts.

[0125] Preferably, the calculation function of the matching value is:

[0126]

[0127] matval A,B Represents the matching value between set A and set B; judval bIndicates the judgment value of keyword b in set B. If set A contains b, then judval b The value of 1, otherwise, judval b The value of is 0, and nwdB represents the total number of keywords contained in set B.

[0128] In some embodiments, the threshold is set at 0.8.

[0129] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Cloud-native supply chain service platform, characterized by: Including demand order management module and order matching module; The demand order management module is used to obtain customer demand orders; The order matching module includes a database unit, a pre-matching unit, a display unit and a confirmation unit; The database unit is used to store the supply information of the supplier and a set A of keywords of the supply information; The pre-matching unit is used to obtain a set B of keywords in the demand order, calculate a matching value between the set B and a set A corresponding to each supplier, and transmit a list of suppliers whose matching values ​​are greater than a set threshold and supply information to the display unit; The display unit is used to display the list of suppliers and supply information sent by the pre-matching unit; The confirmation unit is used by staff to select the final confirmed supplier from the supplier list; It also includes a supplier module and a progress management module; The confirmation unit is also used to forward the demand order to the supplier module used by the final confirmed supplier; The supplier module is used for suppliers to upload the production progress of demand orders to the progress management module; The progress management module is used to store the production progress of demand orders and for staff to view the production progress of demand orders; It also includes logistics management module and logistics module. The supplier module is also used for the supplier to upload the shipment information of the goods to the logistics management module when shipping after the supplier has completed the production of the goods corresponding to the demand order; The logistics module is used by logistics distribution companies to upload the logistics information of goods to the logistics management module; It also includes a staff rights management module; The staff authority management module is used to determine whether the staff has the authority to use the order matching module, progress management module, and logistics management module; Determine whether the staff has the permission to use the information, including: Obtain the staff member's ID through face recognition, and obtain the staff member's access rights based on the ID; Determine whether the staff's usage permissions include the permission to use the order matching module; Determine whether the staff member's permission to use the progress management module includes permission to use the progress management module; Determine whether the staff's permission to use the logistics management module includes permission to use the logistics management module; Obtaining the staff member's ID through face recognition includes: Obtaining facial images of staff members; Get the number corresponding to the face image; Get the number corresponding to the face image, including: Matching the facial image of the staff member with the facial images in the employee information database to determine the number corresponding to the facial image of the staff member; Matching the staff member's facial image with the facial images in the employee information database, including: Use pha to represent the face image of the staff member, and use phb to represent the face image in the employee information database; Calculate the similarity between pha and phb; If the similarity is greater than the set similarity threshold, the number corresponding to phb is used as the number corresponding to pha; Calculate the similarity between pha and phb, including: Get the foreground parts in pha and phb respectively to obtain image phafr and image phbfr; Calculate the similarity between phafr and image phbfr; The process of foreground extraction for ph is as follows, ph∈{pha,phb}: Get the grayscale image pf corresponding to ph; From pf, the gray value is in the interval [gray mi ,gray ma ] pixels make up the image pi, gray mi and gray ma Respectively represent the minimum and maximum values ​​of the interval; The Otsu method was used to calculate pi and obtain the segmentation threshold; Use the segmentation threshold to segment the image ph, and take the pixels greater than the segmentation threshold as the pixels of the foreground part of ph; Get a set of keywords B in the demand order, including: Calculate the difficulty coefficient of analyzing the text data of the goods that the customer needs to purchase; Select a corresponding keyword algorithm according to the analysis difficulty coefficient to obtain keywords in the text data of the goods to be purchased; Calculate the difficulty factor of analyzing the text data of the goods that the customer needs to purchase, including: Use a preset word segmentation algorithm to perform word segmentation processing on the text data of the goods that the customer needs to purchase, and obtain a set C of words contained in the text data; Calculate the analysis difficulty coefficient based on set C; The difficulty coefficient of the analysis is calculated based on set C, including: The calculation function of the analysis difficulty coefficient is: Among them, anadif C represents the word segmentation difficulty coefficient of set C, typu represents the set of types of the length of words in set C, and w i Indicates the weight of type i words in set C, num i Indicates the number of words of type i contained in set C, num al represents the total number of words contained in the set C, w mid Indicates the median weight of all types of words, distwrd max Indicates the maximum number of characters between two adjacent stop words in the text data of the goods that the customer needs to purchase. stddist indicates the preset number. stddist is greater than distwrd. max , num tot The total number of characters in the text data representing the goods that the customer needs to purchase, num stp Indicates the number of stop words contained in the text data of the goods that the customer needs to purchase, α, β, and δ represent the preset type weight, interval weight, and quantity weight, respectively, α∈[0.1,0.5], β∈(0.1,0.3), δ∈(0.1,0.3); gray mi and gray ma The method of obtaining is: Get the minimum value of D that satisfies the following inequality and use this minimum value as gray mi Values: Get the maximum value of E that satisfies the following inequality and use this maximum value as gray ma Values: num j and num k They represent the number of pixels with grayscale values ​​j and k respectively; numgray is the total number of pixels in pf.

2. The cloud-native supply chain service platform according to claim 1, characterized in that: The logistics management module is also used by staff to view the delivery information and logistics information of goods.

3. The cloud-native supply chain service platform according to claim 1, characterized in that: The supply information includes text data of the supplier's main business.

4. The cloud-native supply chain service platform according to claim 3 is characterized in that: The demand order includes text data of the goods that the customer needs to purchase.

5. The cloud-native supply chain service platform according to claim 4, characterized in that: The keyword set A of the supply information is acquired by a preset keyword acquisition algorithm and stored in the database unit.

6. The cloud-native supply chain service platform according to claim 4, characterized in that: Get a set of keywords B in the demand order, including: Calculate the difficulty coefficient of analyzing the text data of the goods that the customer needs to purchase; According to the analysis difficulty coefficient, a corresponding keyword algorithm is selected to obtain keywords in the text data of the goods to be purchased.

7. The cloud-native supply chain service platform according to claim 1, characterized in that: The calculation function of the matching value is: matval A,B Represents the matching value between set A and set B; judval b Indicates the judgment value of keyword b in set B. If set A contains b, then judval b The value of 1, otherwise, judval b The value of is 0, and nwdB represents the total number of keywords contained in set B.

Images