Supply chain user sorting method and device based on collaborative filtering algorithm

Abstract

The invention relates to the technical field of supply chain management, and provides a supply chain user sorting method and device based on a collaborative filtering algorithm. The method comprises the following steps: acquiring an operation request for any supply chain service triggered by any first supply chain user under any sorting optimization standard; responding to the operation request to obtain historical interaction times and corresponding weight coefficients of the first supply chain user and each second supply chain user for the supply chain business under different sorting optimization standards; based on a collaborative filtering algorithm, determining a recommendation sorting value of each second supply chain user according to all historical interaction times and weight coefficients of the first supply chain user and each second supply chain user; according to all the recommendation sorting values, the recommendation sorting of all the second supply chain users corresponding to the first supply chain user for the supply chain business under the sorting optimization standard is determined, the recommendation sorting is more reasonable and accurate, and the recommendation accuracy and the business handling efficiency of the supply chain users are improved.

Description

Technical Field

[0001] The present application relates to the technical field of supply chain management, and specifically to a supply chain user sorting method, device and storage medium based on a collaborative filtering algorithm. Background Art

[0002] In the prior art, the ranking of supply chain users can be based on static value ranking. For example, supply chain users can be statically recommended based on any one of the numerical size of their work numbers, the pinyin ranking of their names, and the importance of their names. Supply chain users can also be dynamically recommended based on any one of the frequency of interaction between users and supply chain users and the interaction time between users and supply chain users.

[0003] However, the recommended ranking of supply chain users will continue to change with time and interactive behavior. If the recommended ranking of supply chain users is determined by the above static recommendation method, the recommended ranking is not accurate enough. If the recommended ranking of supply chain users is determined by the above dynamic recommendation method, the social network data formed by supply chain users during interaction will also have a greater impact on the recommended ranking of supply chain users. If this impact cannot be considered more comprehensively, the recommendation accuracy of the supply chain user ranking will be low due to lack of consideration factors, which will lead to a lot of time spent on selecting supply chain users. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a supply chain user ranking method, device and storage medium based on a collaborative filtering algorithm, so as to solve the problem of low recommendation accuracy for supply chain users in the prior art.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a supply chain user ranking method based on a collaborative filtering algorithm, comprising:

[0006] Obtaining an operation request for any supply chain business triggered by any first supply chain user under any sorting optimization criteria, where the sorting optimization criteria at least include the supply chain application, interaction scenario, and interaction source of the first supply chain user;

[0007] Responding to the operation request to obtain the number of historical interactions between the first supply chain user and each second supply chain user for supply chain business under different sorting optimization criteria and the corresponding weight coefficients;

[0008] Based on the collaborative filtering algorithm, the recommendation ranking value of each second supply chain user is determined according to the total number of historical interactions between the first supply chain user and each second supply chain user and the weight coefficient;

[0009] The recommended rankings for the supply chain businesses of all second supply chain users corresponding to the first supply chain user under the ranking optimization standard are determined according to all the recommended ranking values.

[0010] In an embodiment of the present application, based on a collaborative filtering algorithm, determining the recommended ranking value of each second supply chain user according to the total number of historical interactions between the first supply chain user and each second supply chain user and a weight coefficient includes: obtaining a first user feature set of the first supply chain user and a second user feature set of each second supply chain user; determining a matching degree between the first supply chain user and each second supply chain user according to the first user feature set and each second user feature set; based on a collaborative filtering algorithm, determining the recommended ranking value of each second supply chain user according to the matching degree, total number of historical interactions and a weight coefficient between the first supply chain user and each second supply chain user.

[0011] In an embodiment of the present application, determining the matching degree of the first supply chain user with each second supply chain user based on the first user feature set and each second user feature set includes: determining a first number of common features between the first user feature set and each second user feature set, and a second number of all features; determining the Jaccard similarity coefficient and cosine similarity between the first supply chain user and each second supply chain user based on the first number and the second number; determining the matching degree of the first supply chain user with each second supply chain user based on the Jaccard similarity coefficient and the cosine similarity.

[0012] In an embodiment of the present application, based on a collaborative filtering algorithm and according to the matching degree between the first supply chain user and each second supply chain user, all historical interaction times and a weight coefficient, determining the recommended ranking value for each second supply chain user includes: for each historical interaction number between the first supply chain user and each second supply chain user, determining the product between the historical interaction times and the corresponding weight coefficient; determining the sum of all products, and determining the product between the sum of all products and the matching degree as the recommended ranking value for each second supply chain user.

[0013] In an embodiment of the present application, the method also includes: for each historical number of interactions between the first supply chain user and each second supply chain user, determining whether the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user; when the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user, determining the weight coefficient corresponding to the historical number of interactions as a preset value; when the supply chain application and interaction scenario corresponding to the historical number of interactions are different from the supply chain application and interaction scenario corresponding to the first supply chain user, determining the sum of the preset weights of each standard in the sorting optimization standard corresponding to the historical number of interactions as the weight coefficient of the historical number of interactions.

[0014] In an embodiment of the present application, determining the recommended ranking of supply chain business for all second supply chain users corresponding to the first supply chain user under the ranking optimization standard based on all recommended ranking values ​​includes: arranging all recommended ranking values ​​in order from large to small, and determining the ranking of all recommended ranking values ​​as the recommended ranking.

[0015] In an embodiment of the present application, the supply chain user ranking method further includes: sending the recommended ranking to the terminal interface of the first supply chain user, so that the terminal interface displays all second supply chain users according to the recommended ranking.

[0016] In an embodiment of the present application, the interactive scenario includes at least one of a fixed-point pricing scenario, a price shift scenario, a provisional price scenario, and a quasi-formal price scenario.

[0017] The second aspect of the present application provides a supply chain user ranking device based on a collaborative filtering algorithm, comprising:

[0018] a memory configured to store instructions;

[0019] The processor is configured to call instructions from the memory and implement the above-mentioned supply chain user ranking method based on collaborative filtering algorithm when executing the instructions.

[0020] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned supply chain user ranking method based on the collaborative filtering algorithm.

[0021] Through the above technical solution, when ranking supply chain users, the impact of supply chain applications, interaction scenarios and interaction sources on the recommended ranking of supply chain users is taken into consideration. The recommended ranking value of each second supply chain user is determined based on the historical number of interactions between the first supply chain user and each second supply chain user, and the weight coefficient under different ranking optimization standards. Then, the recommended ranking of each second supply chain user is obtained. The recommended ranking is more reasonable and accurate, which improves the recommendation accuracy of supply chain users and greatly improves the business handling efficiency of supply chain users.

[0022] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0024] Figure 1 The flowchart of the supply chain user ranking method based on the collaborative filtering algorithm according to the embodiment of the present application is schematically shown;

[0025] Figure 2 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0027] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0028] Figure 1 The flowchart of the supply chain user ranking method based on the collaborative filtering algorithm according to the embodiment of the present application is schematically shown. Figure 1 As shown, in one embodiment of the present application, a supply chain user ranking method based on a collaborative filtering algorithm is provided, comprising the following steps:

[0029] Step 101: Obtain an operation request for any supply chain business triggered by any first supply chain user under any sorting optimization standard, where the sorting optimization standard at least includes the supply chain application, interaction scenario, and interaction source of the first supply chain user.

[0030] Collaborative filtering algorithms can predict content that users may be interested in and recommend this content to users by analyzing the similarities between users or things. When sorting supply chain users based on the collaborative filtering algorithm, any first supply chain user can initiate an operation request for any supply chain business under any sorting optimization standard. The processor can obtain the operation request triggered by any first supply chain user. Among them, the first supply chain user refers to a supply chain expert, and the supply chain expert refers to a user in the chain owner enterprise who has the ability to actively initiate interactive behaviors, for example, it can be an internal employee of the chain owner enterprise who can initiate interactive behaviors. Supply chain business refers to the user interaction behavior of the first supply chain user in the supply chain application. For example, supply chain business may include transfer business, forwarding business, assignment business, and claim business.

[0031] The sorting optimization criteria at least include the supply chain application, interaction scenario and interaction source of the first supply chain user. Supply chain applications refer to different applications in the industrial Internet platform, such as Supplier Relationship Management (SRM), Supplier Information Management (SIM), and Procurement Cost Management (PCM). Users, roles and permissions can be independently configured in each supply chain application. The basic data between any two supply chain applications is isolated, and the relevant pages in the supply chain application can include user interaction functions such as transfer, forwarding, assignment and claiming.

[0032] Interaction scenarios refer to usage scenarios under different business modules of supply chain applications. In an embodiment of the present application, for example, the interaction scenario includes at least one of a fixed-point pricing scenario, a price translation scenario, a provisional price scenario, and a quasi-formal price scenario. The same interaction scenario may appear in multiple supply chain applications, that is, corresponding interaction scenarios may exist in different supply chain applications. The source of interaction refers to the source of the party that interacts with the first supply chain user. The sources of interaction may include users, user groups, and groups. Among them, a user group refers to a dynamic user group that meets a certain combination of business rules, and a group refers to a static user group associated with a collaborative office community and a combined architecture. For example, for a first supply chain user, it can interact with a user, a user in a user group, or a user in a group.

[0033] Step 102: Respond to the operation request to obtain the historical interaction times and corresponding weight coefficients of the first supply chain user and each second supply chain user for supply chain business under different sorting optimization criteria.

[0034] The processor may respond to an operation request triggered by any first supply chain user to obtain the number of historical interactions between the first supply chain user and each second supply chain user for supply chain business under different sorting optimization criteria and the corresponding weight coefficients.

[0035] Among them, the second supply chain users include all internal employees of the chain leader enterprise, as well as users who have opened collaborative accounts in upstream and downstream enterprises of the supply chain. All internal employees of the chain leader enterprise include supply chain experts, as well as users in the chain leader enterprise who do not have the ability to actively initiate interactive behaviors. Users who have opened collaborative accounts in upstream and downstream enterprises of the supply chain can only receive and assist, and cannot actively initiate interactive behaviors.

[0036] The first supply chain user can interact with at least one second supply chain user, specifically, they can interact in different supply chain applications, different interaction scenarios and different interaction sources. When the first supply chain user interacts with any second supply chain user on any supply chain business under any ranking optimization standard, there may be corresponding historical interaction times and weight coefficients.

[0037] For example, supply chain expert A initiates two assignments to user B in "Gongqi Business Unit-Business Area-Business Group" in the pending approval-fixed-point pricing of the SRM system. If the preset weight corresponding to the SRM system is 10, the preset weight corresponding to pending approval-fixed-point pricing is 5, and the preset weight corresponding to "Gongqi Business Unit-Business Area-Business Group" is 3, then the weight coefficient of supply chain expert A's interaction with user B under the sorting optimization criteria of supply chain application as SRM system, interaction scenario as fixed-point pricing scenario, and interaction source as user group is 18, and the number of interactions for the supply chain business as assigned business is 2 times.

[0038] For another example, supply chain expert A initiated three assignments to user B in the pending approval-price shift of the SRM system. If the preset weight corresponding to the SRM system is 10, the preset weight corresponding to the pending approval-price shift is 3, and the preset weight corresponding to the user is 10, then the weight coefficient of supply chain expert A interacting with user B under the sorting optimization criteria of supply chain application as SRM system, interaction scenario as price shift scenario, and interaction source as user is 23, and the number of interactions for the supply chain business as the assignment business is 3 times.

[0039] Step 103: Based on the collaborative filtering algorithm and according to the total number of historical interactions between the first supply chain user and each second supply chain user and the weight coefficient, determine the recommendation ranking value of each second supply chain user.

[0040] The processor may determine the recommendation ranking value of each second supply chain user based on a collaborative filtering algorithm and according to all historical interaction times and weight coefficients between the first supply chain user and each second supply chain user.

[0041] In an embodiment of the present application, based on a collaborative filtering algorithm, determining the recommended ranking value of each second supply chain user according to the total number of historical interactions between the first supply chain user and each second supply chain user and a weight coefficient includes: obtaining a first user feature set of the first supply chain user and a second user feature set of each second supply chain user; determining a matching degree between the first supply chain user and each second supply chain user according to the first user feature set and each second user feature set; based on a collaborative filtering algorithm, determining the recommended ranking value of each second supply chain user according to the matching degree, total number of historical interactions and a weight coefficient between the first supply chain user and each second supply chain user.

[0042] The processor may obtain a first user feature set of the first supply chain user and a second user feature set of each second supply chain user. The user feature set may include the gender, position, rank, and organizational structure of the supply chain user. The processor may determine the matching degree between the first supply chain user and each second supply chain user based on the first user feature set and each second user feature set.

[0043] Specifically, the processor can determine the Jaccard similarity coefficient between the first supply chain user and each second supply chain user based on the Jaccard algorithm, and can determine the cosine similarity between the first supply chain user and each second supply chain user, thereby determining the matching degree between the first supply chain user and each second supply chain user based on the Jaccard similarity coefficient and the cosine similarity.

[0044] In an embodiment of the present application, determining the matching degree of the first supply chain user with each second supply chain user based on the first user feature set and each second user feature set includes: determining a first number of common features between the first user feature set and each second user feature set, and a second number of all features; determining the Jaccard similarity coefficient and cosine similarity between the first supply chain user and each second supply chain user based on the first number and the second number; determining the matching degree of the first supply chain user with each second supply chain user based on the Jaccard similarity coefficient and the cosine similarity.

[0045] The processor may determine a first number of common features between the first user feature set and each second user feature set, and a second number of all features. The processor may determine a Jaccard similarity coefficient and a cosine similarity between the first supply chain user and each second supply chain user based on the first number and the second number.

[0046] Specifically, the Jaccard similarity coefficient and the cosine similarity can be determined based on the following formula (1) and formula (2), respectively:

[0047]

[0048] Among them, wuv1 refers to the Jaccard similarity coefficient between the first supply chain user u and the second supply chain user v, N(u) refers to the first user feature set of the first supply chain user u, N(v) refers to the second user feature set of the second supply chain user v, N(u)∩N(v) refers to the first number of common features between the first supply chain user u and the second supply chain user v, and N(u)∪N(v) refers to the second number of all features between the first supply chain user u and the second supply chain user v.

[0049] The cosine similarity is determined by the following formula:

[0050]

[0051] Among them, w uv2 It refers to the cosine similarity between the first supply chain user u and the second supply chain user v.

[0052] The processor may determine the matching degree between the first supply chain user and each second supply chain user according to the Jaccard similarity coefficient and the cosine similarity. Specifically, the processor may weight the Jaccard similarity coefficient and the cosine similarity respectively to obtain a weighted sum value, which is the matching degree between the first supply chain user and each second supply chain user.

[0053] The above-mentioned Jaccard similarity coefficient is used to compare "whether the absolute values ​​are the same". It is mainly used to calculate the similarity between individuals measured by symbolic measurement or Boolean value measurement. Because the characteristic attributes of individuals are all identified by symbolic measurement or Boolean value, it is impossible to measure the size of the specific value of the difference. Only the result of "whether they are the same" can be obtained. The Jaccard similarity coefficient focuses on whether the common characteristics between individuals are consistent.

[0054] The above cosine similarity is used to compare "array feature similarity", which mainly distinguishes differences in direction and is insensitive to absolute values. It is more used to use the similarity and difference of user feature points, and at the same time corrects the problem of inconsistent measurement standards that may exist among users.

[0055] After determining the matching degree of each second supply chain user of the first supply chain user, the processor may determine the recommendation ranking value of each second supply chain user based on a collaborative filtering algorithm and according to the matching degree of the first supply chain user with each second supply chain user, all historical interaction times and weight coefficients.

[0056] In an embodiment of the present application, based on a collaborative filtering algorithm and according to the matching degree between the first supply chain user and each second supply chain user, all historical interaction times and a weight coefficient, determining the recommended ranking value for each second supply chain user includes: for each historical interaction number between the first supply chain user and each second supply chain user, determining the product between the historical interaction times and the corresponding weight coefficient; determining the sum of all products, and determining the product between the sum of all products and the matching degree as the recommended ranking value for each second supply chain user.

[0057] For each historical number of interactions between the first supply chain user and each second supply chain user, the processor can determine the product of the historical number of interactions and the corresponding weight coefficient, and can sum all the products to obtain the sum of all products. Then, the processor can determine the product of the matching degrees corresponding to the sum of all products, and can determine the product as the recommended ranking value of each second supply chain user relative to the first supply chain user.

[0058] In an embodiment of the present application, the method also includes: for each historical number of interactions between the first supply chain user and each second supply chain user, determining whether the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user; when the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user, determining the weight coefficient corresponding to the historical number of interactions as a preset value; when the supply chain application and interaction scenario corresponding to the historical number of interactions are different from the supply chain application and interaction scenario corresponding to the first supply chain user, determining the sum of the preset weights of each standard in the sorting optimization standard corresponding to the historical number of interactions as the weight coefficient of the historical number of interactions.

[0059] For each historical number of interactions between the first supply chain user and each second supply chain user, the processor may determine whether the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user.

[0060] Among them, the supply chain applications and interaction scenarios corresponding to the historical number of interactions refer to the supply chain applications and interaction scenarios when the first supply chain user and each second supply chain user interacted with each other in the previous supply chain business, and the supply chain applications and interaction scenarios corresponding to the first supply chain user refer to the supply chain applications and interaction scenarios when the first supply chain user initiates an operation request on a wake-up panel.

[0061] When the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as those corresponding to the first supply chain user, it means that the first supply chain user and the second supply chain user may interact more frequently in this case, and the processor may determine that the weight coefficient corresponding to the historical number of interactions is a preset value. The preset value may be customized based on actual conditions, for example, the preset value may be set to 30.

[0062] When the supply chain application and interaction scenario corresponding to the historical number of interactions are different from the supply chain application and interaction scenario corresponding to the first supply chain user, the processor can determine the sum of the preset weights of each criterion in the sorting optimization criteria corresponding to the historical number of interactions, and determine the sum of the preset weights as the weight coefficient of the historical number of interactions.

[0063] Taking supply chain expert A and user B as an example, if the matching degree between supply chain expert A and user B is 0.92, the weight coefficient of supply chain expert A when interacting with user B is 18 under the sorting optimization standard that the supply chain application is the SRM system, the interaction scenario is the fixed-point pricing scenario, and the interaction source is the user group, and the number of interactions for the supply chain business is 2 times. The weight coefficient of supply chain expert A when interacting with user B is 23 under the sorting optimization standard that the supply chain application is the SRM system, the interaction scenario is the price shift scenario, and the interaction source is the user, and the number of interactions for the supply chain business is the assigned business is 3 times.

[0064] When supply chain expert A initiates an operation request to assign a business under pending approval-fixed-point pricing in the SRM system, user B's recommended ranking value for supply chain expert A is: X1=0.92×(30×2+23×3)=118.68. When supply chain expert A initiates an operation request to assign a business under pending approval-price shift in the SRM system, user B's recommended ranking value for supply chain expert A is: X1=0.92×(18×2+30×3)=115.92.

[0065] Step 104: Determine the recommended rankings for the supply chain services of all second supply chain users corresponding to the first supply chain user under the ranking optimization standard according to all the recommended ranking values.

[0066] The processor may determine, based on all the recommended ranking values, the recommended rankings for the supply chain services of all the second supply chain users corresponding to the first supply chain user under the ranking optimization standard.

[0067] In an embodiment of the present application, determining the recommended ranking of supply chain business for all second supply chain users corresponding to the first supply chain user under the ranking optimization standard based on all recommended ranking values ​​includes: arranging all recommended ranking values ​​in order from large to small, and determining the ranking of all recommended ranking values ​​as the recommended ranking.

[0068] The processor may arrange all the recommended ranking values ​​in descending order, and determine the ranking of all the recommended ranking values ​​as the recommended ranking. That is, the larger the recommended ranking value, the larger the corresponding recommended ranking.

[0069] In an embodiment of the present application, the supply chain user ranking method further includes: sending the recommended ranking to the terminal interface of the first supply chain user, so that the terminal interface displays all second supply chain users according to the recommended ranking.

[0070] The processor may send the recommended ranking to the terminal interface of the first supply chain user, so that the terminal interface displays all the second supply chain users according to the recommended ranking. The terminal interface may include but is not limited to a display interface or pop-up window of a personal computer, a laptop, a smart phone, a tablet computer, and a portable wearable device.

[0071] Through the above technical solution, when ranking supply chain users, the impact of supply chain applications, interaction scenarios and interaction sources on the recommended ranking of supply chain users is taken into consideration. The recommended ranking value of each second supply chain user is determined based on the historical number of interactions between the first supply chain user and each second supply chain user, and the weight coefficient under different ranking optimization standards. Then, the recommended ranking of each second supply chain user is obtained. The recommended ranking is more reasonable and accurate, which improves the recommendation accuracy of supply chain users and greatly improves the business handling efficiency of supply chain users.

[0072] Figure 1 FIG. 1 is a flow chart of a supply chain user ranking method based on a collaborative filtering algorithm in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0073] In one embodiment, a supply chain user ranking device based on a collaborative filtering algorithm is provided, comprising:

[0074] a memory configured to store instructions;

[0075] The processor is configured to call instructions from the memory and implement the above-mentioned supply chain user ranking method based on collaborative filtering algorithm when executing the instructions.

[0076] In one embodiment, a storage medium is provided, on which a program is stored, and when the program is executed by a processor, the supply chain user ranking method based on the collaborative filtering algorithm is implemented.

[0077] In one embodiment, a processor is provided, and the processor is used to run a program, wherein the program executes the above-mentioned supply chain user ranking method based on the collaborative filtering algorithm when it is run.

[0078] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 2 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data such as the recommended ranking value of each second supply chain user. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a supply chain user ranking method based on a collaborative filtering algorithm is implemented.

[0079] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0080] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining an operation request for any supply chain business triggered by any first supply chain user under any sorting optimization standard, where the sorting optimization standard at least includes the supply chain application, interaction scenario, and interaction source in which the first supply chain user is located; responding to the operation request to obtain the number of historical interactions between the first supply chain user and each second supply chain user for the supply chain business and the corresponding weight coefficient under different sorting optimization standards; determining a recommended sorting value for each second supply chain user based on a collaborative filtering algorithm and according to all the historical interactions between the first supply chain user and each second supply chain user and the weight coefficient; and determining, according to all the recommended sorting values, a recommended sorting of all second supply chain users corresponding to the first supply chain user for the supply chain business under the sorting optimization standard.

[0081] In one embodiment, determining the recommended ranking value of each second supply chain user based on a collaborative filtering algorithm and according to the total number of historical interactions between the first supply chain user and each second supply chain user and a weight coefficient includes: obtaining a first user feature set of the first supply chain user and a second user feature set of each second supply chain user; determining the matching degree between the first supply chain user and each second supply chain user based on the first user feature set and each second user feature set; determining the recommended ranking value of each second supply chain user based on a collaborative filtering algorithm and according to the matching degree, total number of historical interactions and a weight coefficient between the first supply chain user and each second supply chain user.

[0082] In one embodiment, determining the degree of match between a first supply chain user and each second supply chain user based on a first user feature set and each second user feature set includes: determining a first number of common features between the first user feature set and each second user feature set, and a second number of all features; determining a Jaccard similarity coefficient and a cosine similarity between the first supply chain user and each second supply chain user based on the first number and the second number; and determining the degree of match between the first supply chain user and each second supply chain user based on the Jaccard similarity coefficient and the cosine similarity.

[0083] In one embodiment, based on a collaborative filtering algorithm and according to the matching degree between the first supply chain user and each second supply chain user, all historical interaction times and a weight coefficient, determining the recommended ranking value for each second supply chain user includes: for each historical interaction number between the first supply chain user and each second supply chain user, determining the product between the historical interaction times and the corresponding weight coefficient; determining the sum of all products, and determining the product between the sum of all products and the matching degree as the recommended ranking value for each second supply chain user.

[0084] In one embodiment, the method also includes: for each historical number of interactions between the first supply chain user and each second supply chain user, determining whether the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user; when the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user, determining the weight coefficient corresponding to the historical number of interactions as a preset value; when the supply chain application and interaction scenario corresponding to the historical number of interactions are different from the supply chain application and interaction scenario corresponding to the first supply chain user, determining the sum of the preset weights of each standard in the sorting optimization standard corresponding to the historical number of interactions as the weight coefficient of the historical number of interactions.

[0085] In one embodiment, determining the recommended ranking of supply chain businesses of all second supply chain users corresponding to the first supply chain user under the ranking optimization standard based on all recommended ranking values ​​includes: arranging all recommended ranking values ​​in order from large to small, and determining the ranking of all recommended ranking values ​​as the recommended ranking.

[0086] In one embodiment, the supply chain user ranking method further includes: sending the recommended ranking to the terminal interface of the first supply chain user, so that the terminal interface displays all second supply chain users according to the recommended ranking.

[0087] In one embodiment, the interactive scenario includes at least one of a fixed-point pricing scenario, a price translation scenario, a provisional price scenario, and a quasi-formal price scenario.

[0088] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the steps of a supply chain user ranking method based on a collaborative filtering algorithm.

[0089] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0093] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0094] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0095] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0096] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0097] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A supply chain user ranking method based on collaborative filtering algorithm, characterized in that: The supply chain user sorting method comprises: Obtaining an operation request for any supply chain business triggered by any first supply chain user under any sorting optimization criteria, wherein the sorting optimization criteria at least includes the supply chain application, interaction scenario, and interaction source of the first supply chain user; Responding to the operation request to obtain the number of historical interactions between the first supply chain user and each second supply chain user for the supply chain business under different sorting optimization criteria and the corresponding weight coefficients; Based on the collaborative filtering algorithm, and according to the total number of historical interactions between the first supply chain user and each second supply chain user and the weight coefficient, determine the recommendation ranking value of each second supply chain user; The recommended rankings of all second supply chain users corresponding to the first supply chain user for the supply chain business under the ranking optimization standard are determined according to all the recommended ranking values.

2. The supply chain user ranking method based on collaborative filtering algorithm according to claim 1 is characterized in that: The method of determining the recommendation ranking value of each second supply chain user based on the collaborative filtering algorithm and according to the total number of historical interactions between the first supply chain user and each second supply chain user and the weight coefficient includes: Acquire a first user feature set of the first supply chain user and a second user feature set of each second supply chain user; Determining a matching degree between the first supply chain user and each second supply chain user according to the first user feature set and each second user feature set; Based on the collaborative filtering algorithm, the recommendation ranking value of each second supply chain user is determined according to the matching degree between the first supply chain user and each second supply chain user, all historical interaction times and weight coefficients.

3. The supply chain user ranking method based on collaborative filtering algorithm according to claim 2 is characterized in that: Determining the matching degree between the first supply chain user and each second supply chain user according to the first user feature set and each second user feature set includes: determining a first number of common features between the first user feature set and each second user feature set, and a second number of all features; Determine the Jaccard similarity coefficient and the cosine similarity between the first supply chain user and each second supply chain user according to the first quantity and the second quantity; The matching degree between the first supply chain user and each second supply chain user is determined according to the Jaccard similarity coefficient and the cosine similarity.

4. The supply chain user ranking method based on collaborative filtering algorithm according to claim 2 is characterized in that: The method based on the collaborative filtering algorithm and determining the recommended ranking value of each second supply chain user according to the matching degree between the first supply chain user and each second supply chain user, the total number of historical interactions and the weight coefficient includes: For each historical number of interactions between the first supply chain user and each second supply chain user, determine the product of the historical number of interactions and the corresponding weight coefficient; The sum of all products is determined, and the product of the sum of all products and the matching degree is determined as a recommended ranking value for each second supply chain user.

5. The supply chain user ranking method based on collaborative filtering algorithm according to claim 1 is characterized in that: The method further comprises: For each historical number of interactions between the first supply chain user and each second supply chain user, determining whether the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user; In a case where the supply chain application and interaction scenario corresponding to the historical number of interactions are the same as the supply chain application and interaction scenario corresponding to the first supply chain user, determining the weight coefficient corresponding to the historical number of interactions to be a preset value; When the supply chain application and interaction scenario corresponding to the historical number of interactions are different from the supply chain application and interaction scenario corresponding to the first supply chain user, the sum of the preset weights of each criterion in the sorting optimization criteria corresponding to the historical number of interactions is determined as the weight coefficient of the historical number of interactions.

6. The supply chain user ranking method based on collaborative filtering algorithm according to claim 1 is characterized in that: The determining, according to all the recommended ranking values, the recommended rankings of all the second supply chain users corresponding to the first supply chain user for the supply chain business under the ranking optimization standard comprises: All the recommended ranking values ​​are arranged in descending order, and the ranking of all the recommended ranking values ​​is determined as the recommended ranking.

7. The supply chain user ranking method based on collaborative filtering algorithm according to any one of claims 1 to 6, characterized in that: The supply chain user sorting method further includes: The recommended ranking is sent to the terminal interface of the first supply chain user, so that the terminal interface displays all the second supply chain users according to the recommended ranking.

8. The supply chain user ranking method based on collaborative filtering algorithm according to any one of claims 1 to 6, characterized in that: The interactive scenario includes at least one of a fixed-point pricing scenario, a price shift scenario, a provisional price scenario, and a quasi-formal price scenario.

9. A supply chain user ranking device based on collaborative filtering algorithm, characterized in that: The supply chain user sorting device comprises: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the supply chain user ranking method based on collaborative filtering algorithm according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute the supply chain user ranking method based on a collaborative filtering algorithm according to any one of claims 1 to 8.

Images