Resource allocation method and device, storage medium and computer device

Abstract

The application discloses a resource distribution method and device, a storage medium and a computer device. The method comprises the following steps: obtaining a resource cancellation user and preset resources; comparing the user characteristics of the resource cancellation user and a target user to determine the first similarity between the resource cancellation user and the target user; comparing the resource characteristics of the preset resources and historical resources corresponding to a first user to determine the second similarity between the preset resources and the historical resources; determining the preset resource cancellation probability of the target user according to the first similarity and the second similarity; and distributing the preset resources to the target user according to the resource cancellation probability. The method of the application can realize automatic resource dynamic allocation without network model training, can ensure the objectivity and fairness of resource distribution, can make the target user obtain resources that are more in line with the user's own needs, can improve the use effect of resources and the user shopping experience, and can help to enhance user loyalty.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer equipment, and in particular to a resource distribution method and device, a storage medium and a computer equipment. BACKGROUND

[0002] With the continuous development of e-commerce, e-commerce occupies an increasingly important position in the daily life of users. As an effective means of intelligent marketing, coupons can activate and enhance the potential order demand of users while introducing new users to the platform. In related technologies, a network model is usually used to match coupons, but a large amount of sample data is often needed to support the training of the network model. If the sample data is less, the accuracy of the network model will be greatly reduced, which is not conducive to accurately distributing coupons on demand. SUMMARY

[0003] Therefore, the present application provides a resource distribution method and device, a storage medium and a computer equipment, which accurately distribute resources to users in need by comparing the similarity of user features and resource features, thereby improving resource utilization and conversion rate.

[0004] According to one aspect of the present application, a resource distribution method is provided, comprising:

[0005] obtaining a resource cancellation user and a preset resource;

[0006] comparing the user features of the resource cancellation user and a target user to determine the first similarity between the resource cancellation user and the target user;

[0007] comparing the resource features of the preset resource and the historical resource corresponding to the first user to determine the second similarity between the preset resource and the historical resource, the first user being a resource cancellation user whose first similarity is greater than or equal to a first preset similarity;

[0008] determining the target user's cancellation probability for the preset resource according to the first similarity and the second similarity;

[0009] distributing the preset resource to the target user according to the resource cancellation probability.

[0010] Optionally, the target user's cancellation probability for the preset resource is determined according to the first similarity and the second similarity, specifically comprising:

[0011] if the second similarity is greater than or equal to a second preset similarity, the historical resource corresponding to the second similarity is determined as the first resource;

[0012] if the historical resource includes the first resource, the first user corresponding to the historical resource is determined as the second user;

[0013] According to the first similarity corresponding to the second user and the second similarity of the second user corresponding to the first resource, a resource cancellation probability is calculated.

[0014] Optionally, according to the first similarity corresponding to the second user and the second similarity of the second user corresponding to the first resource, the resource cancellation probability is calculated, and specifically includes:

[0015] The product of the first similarity corresponding to the second user and the second similarity of the second user corresponding to the first resource is calculated.

[0016] According to the number of the second users, the mean value of the product is calculated as the resource cancellation probability.

[0017] Optionally, according to the resource cancellation probability, the preset resource is issued to the target user, and specifically includes:

[0018] If the resource cancellation probability is greater than the preset cancellation probability, the preset resource corresponding to the resource cancellation probability is issued to the target user.

[0019] Optionally, the resource issuing method further includes:

[0020] If the preset resource is successfully issued to the target user, an issuing prompt information of the preset resource is output.

[0021] According to another aspect of the present application, a resource issuing device is provided, including:

[0022] The acquisition module is configured to acquire a resource cancellation user and a preset resource.

[0023] The determination module is configured to compare the user features of the resource cancellation user and the target user to determine the first similarity between the resource cancellation user and the target user; compare the resource features of the preset resource and the historical resource corresponding to the first user to determine the second similarity between the preset resource and the historical resource, the first user being the resource cancellation user whose first similarity is greater than or equal to a first preset similarity; and according to the first similarity and the second similarity, determine the resource cancellation probability of the target user relative to the preset resource.

[0024] The resource configuration module is configured to issue the preset resource to the target user according to the resource cancellation probability.

[0025] Optionally, the determination module is specifically configured to determine the historical resource corresponding to the second similarity as the first resource if the second similarity is greater than or equal to a second preset similarity; determine the first user corresponding to the historical resource as the second user if the historical resource includes the first resource; and calculate the resource cancellation probability according to the first similarity corresponding to the second user and the second similarity of the second user corresponding to the first resource.

[0026] Optionally, the determining module is specifically configured to calculate a product of the first similarity corresponding to the second user and the second similarity of the second user corresponding to the first resource; and calculate a mean value of the product as the resource cancellation probability according to the number of the second users.

[0027] Optionally, the resource configuration module is specifically configured to, if the resource cancellation probability is greater than a preset cancellation probability, distribute a preset resource corresponding to the resource cancellation probability to the target user.

[0028] Optionally, the resource distribution apparatus further comprises:

[0029] The prompting module is configured to, if the preset resource is successfully distributed to the target user, output a distribution prompt information of the preset resource.

[0030] According to another aspect of the present application, a readable storage medium is provided, which stores a program or instructions, and the program or instructions are executed by a processor to implement the steps of the above resource distribution method.

[0031] According to another aspect of the present application, a computer device is provided, which comprises a storage medium, a processor and a computer program stored in the storage medium and executable on the processor, and the processor executes the program to implement the steps of the above resource distribution method.

[0032] By the above technical solution, first, the resource cancellation user existing resource cancellation operation and the preset resource to be distributed to the user by the platform are acquired. By comparing the difference between the user characteristics of the resource cancellation user and the target user meeting the resource distribution condition, the first similarity between the resource cancellation user and the target user is determined, and the first user with the first similarity greater than or equal to a first preset similarity is selected from the resource cancellation user, so as to determine the user possibly having similar resource use preference with the target user by using the first similarity. Then, the resource characteristics of the preset resource and the historical resource ever used by the first user are compared, the second similarity between the preset resource and the historical resource is determined, so as to determine the resource possibly meeting the preference of the first user in the preset resource by using the second similarity. Thus, according to the first similarity and the second similarity of the second user, the resource cancellation probability of the target user to different preset resources can be determined. Finally, the preset resource is distributed to the target user as needed according to the resource cancellation probability. Thus, the automatic resource dynamic distribution can be realized without network model training, even in the case of small amount of sample data, the resource can still be accurately distributed to the target user who needs it more, the objectivity and fairness of the resource distribution are ensured, the target user can obtain the resource more meeting his / her own needs, the use effect of the resource is improved, the total transaction amount is increased, the user can be provided with appropriate preferential policy, the user shopping experience is improved, and the user loyalty is enhanced.

[0033] The above description is only a summary of the technical solutions of the present application. In order to enable one skilled in the art to better understand the technical means of the present application, the present application can be implemented according to the content of the description, and in order to enable the above and other purposes, characteristics and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0034] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application, and the illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0035] Figure 1 A flowchart of a resource allocation method provided by an embodiment of the present application is shown;

[0036] Figure 2 A structural block diagram of a resource allocation device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0037] In the following, the present application will be described in detail with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0038] The embodiments of the present application will be described in detail below, and examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as a limitation on the present application.

[0039] Those skilled in the art can understand that, unless specifically stated, the singular forms "a", "an" and "the" used herein also include the plural forms. It should be further understood that the use of the phrase "comprising" in the specification of the present application means that the features, integers, steps, operations, elements and / or components exist, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we say that an element is "connected" or "joined" to another element, it can be directly connected or joined to the other element, or there can be an intermediate element. In addition, "connected" or "joined" used herein can include wireless connection or wireless connection. The phrase "and / or" used herein includes all or any single unit and all combinations of the associated listed items.

[0040] Exemplary embodiments according to this application will now be described in greater detail below with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in various different forms, and should not be construed as being limited to the embodiments set forth herein. It should be understood that the embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0041] A resource distribution method is provided in the present embodiment, as shown in the figure, the method comprises: Figure 1

[0042] Step 101, obtaining resource cancellation users and preset resources;

[0043] Among them, the resource cancellation user is a user who has a resource cancellation operation, that is, a user who has used resources for deduction consumption. The preset resource is a resource that the platform can distribute to the user. The preset resource can be a coupon, a token, a red envelope, etc.

[0044] Step 102, comparing the user characteristics of the resource cancellation user and the target user to determine the first similarity between the resource cancellation user and the target user;

[0045] Specifically, the user characteristics include: user consumption ability level, price sensitivity, loyalty, resource demand intensity, scene preference characteristics, user behavior characteristics, resource preference characteristics, etc.

[0046] It is worth mentioning that the target user represents a user who can be allocated resources. Before inputting the attribute characteristics of the target user into the resource allocation model, all users registered on the platform can be filtered through the preset conditions, so as to determine the target user who can be allocated resources. For example, users with purchase records are target users, or users in a login state are target users. Through user filtering, not only the data amount of model data processing is reduced, the system running pressure is reduced, but also the resources are avoided to be allocated to users who do not need resources, which helps to allocate resources more reasonably.

[0047] Step 103, comparing the resource characteristics of the preset resource and the historical resource corresponding to the first user to determine the second similarity between the preset resource and the historical resource;

[0048] Among them, the first user is a resource cancellation user whose first similarity is greater than or equal to a first preset similarity. The first preset similarity can be reasonably set according to the accuracy of business demand and the income target, for example, 80%, 95%, etc.

[0049] Specifically, the resource characteristics include: resource type, resource quantity, resource threshold, resource amount, resource discount, resource validity period, etc. The resource can be a coupon, a token, a red envelope, etc. For example, the resource characteristics are a coupon of 100 yuan with a discount of 30 yuan or a token of 100,000 yuan.​

[0050] In this embodiment, the first similarity between the resource cancellation user and the target user is determined by comparing the difference between the user features of the resource cancellation user and the target user who meets the resource distribution condition, and the first user with the first similarity greater than or equal to the first preset similarity is screened out from the resource cancellation user, so as to determine the user who may have similar resource use preferences with the target user by using the first similarity. Then, the second similarity between the preset resource and the historical resource used by the first user is determined by comparing the resource features of the preset resource and the historical resource, so as to determine the resource in the preset resource that may meet the preferences of the first user by using the second similarity. Thus, the resource that the target user may need can be matched by using the first similarity and the second similarity of the second user corresponding to the first resource, so as to facilitate subsequent accurate resource distribution.

[0051] In step 104, the resource cancellation probability of the target user with respect to the preset resource is determined according to the first similarity and the second similarity.

[0052] In this embodiment, after the first similarity and the second similarity of the second user corresponding to the first resource are determined, the resource cancellation probability of the target user with respect to different preset resources can be determined according to the first similarity and the second similarity. Thus, the demand degree of different target users for different resources can be analyzed by the resource cancellation probability, so as to subsequently distribute the corresponding preset resources to different target users according to the resource cancellation probability. Therefore, even in the case of small sample data, the resources can still be accurately distributed to the target users who need them more, so as to achieve the purpose of automatic resource dynamic allocation and improve the conversion rate of resources.

[0053] In actual application scenarios, step 104, i.e., determining the resource cancellation probability of the target user with respect to the preset resource according to the first similarity and the second similarity, specifically includes:

[0054] In step 104-1, if the second similarity is greater than or equal to the second preset similarity, the historical resource corresponding to the second similarity is determined as the first resource.

[0055] The second preset similarity can be reasonably set according to the accuracy of business demand and the income target, for example, 85%, 90%, etc.

[0056] In step 104-2, if the historical resource includes the first resource, the first user corresponding to the historical resource is determined as the second user.

[0057] In step 104-3, the resource cancellation probability is calculated according to the first similarity of the second user and the second similarity of the second user corresponding to the first resource.

[0058] In this embodiment, the size relationship between the second similarity and the second preset similarity is compared. When the second similarity is greater than or equal to the second preset similarity, the historical resource corresponding to the second similarity is taken as the first resource meeting the platform preferential policy. The first user who has checked the first resource is recorded as the second user, so as to filter the second user who has used the first resource similar to the preset resource from the plurality of first users. According to the first similarity between the second user and the target user and the second similarity between the first resource corresponding to the second user and the preset resource, the resource check probability of the target user to the different preset resource can be determined. In order to subsequently distribute the corresponding preset resource to different target users through the resource check probability. Therefore, in the case of small sample data, the resource can still be accurately distributed to the target user who needs it more, so as to achieve the purpose of automatic resource dynamic allocation, and further improve the conversion rate of the resource.

[0059] Further, as a refinement and expansion of the above embodiment, in order to completely describe the specific implementation process of the embodiment, step 104-3 specifically includes: calculating the product of the first similarity corresponding to the second user and the second similarity of the first resource corresponding to the second user; and calculating the average of the product as the resource check probability according to the number of second users.

[0060] In this embodiment, after the second user whose first similarity meets the first preset similarity condition and whose historical resource contains the first resource is filtered out, the second user and the first resource corresponding to the second user are taken as a data set. Therefore, the check probability of any target user to the preset resource can be abstracted as the arithmetic average of the product of the first similarity of all second users in the data set and the second similarity of the first resource corresponding to the second user.

[0061] Taking the n second users filtered out as an example, the resource check probability is calculated by the following formula:

[0062]

[0063] In the formula, q represents the resource check probability, q c pc represents the first similarity of the cth second user, p c qc represents the second similarity of the first resource corresponding to the cth second user, (1≤c≤n).

[0064] For example, the preset resource is a coupon of 100 yuan minus 50 yuan. Through user feature comparison, users A, B and C similar to the target user W are screened out from the resource redemption users. Among them, user A has redeemed a coupon of 100 yuan minus 50 yuan and a coupon of 300 yuan minus 100 yuan, user B has used a 5 yuan red packet, and user C has redeemed a coupon of 100 yuan minus 40 yuan and a coupon of 100 yuan minus 50 yuan. Through comparison, the coupon of 100 yuan minus 50 yuan can be taken as the first resource. At this time, users A and C are recorded as the second user. Referring to the above formula, the resource redemption probability of the target user W with respect to the preset resource can be calculated

[0065] Step 105, according to the resource redemption probability, the preset resource is issued to the target user.

[0066] The resource issuing method proposed in the embodiments of the present application first acquires resource redemption users who have resource redemption operations and preset resources to be issued to users by the platform. By comparing the differences between the user features of the resource redemption users and the target users who meet the resource issuing conditions, the first similarity between the resource redemption users and the target users is determined, and the first users whose first similarity is greater than or equal to the first preset similarity are screened out from the resource redemption users, so as to determine the users who may have similar resource use preferences as the target user by using the first similarity. Then, the resource features of the preset resource and the historical resources used by the first users are compared, and the second similarity between the preset resource and the historical resources is determined, so as to determine the resources in the preset resource that may meet the preferences of the first users by using the second similarity. Thus, according to the first similarity of the second user and the second similarity of the first resource corresponding to the second user, the resource redemption probability of the target user for different preset resources can be determined. Finally, the preset resource is issued to the target user as needed according to the resource redemption probability. Thus, automatic resource dynamic allocation can be realized without network model training. Even in the case of small amount of sample data, the resource can still be accurately issued to the target user who needs it more, ensuring the objectivity and fairness of resource issuing, enabling the target user to obtain resources that meet his own needs, improving the use effect of resources, being conducive to improving the total transaction amount, providing appropriate preferential policies for users, improving the shopping experience of users, and helping to enhance user loyalty.

[0067] For example, (1) the users who have redeemed coupons in the past 7 days are taken as candidate set users (resource redemption users), the similarity between each to-be-issued coupon user (target user) and the candidate set is calculated, and the similar users (the first preset similarity is set according to the business demand of model accuracy) corresponding to each to-be-issued coupon user greater than the first preset similarity are found out.

[0068] (2) The historical redemptions of the similar users corresponding to each to-be-issued coupon user form a coupon candidate set. Similarity calculation is performed between each to-be-issued coupon and the coupon candidate set (the coupon features include type, threshold, amount, discount, validity period, etc.). Similar coupons greater than a second preset similarity (the setting of the second preset similarity depends on the business demand of model accuracy) are found out.

[0069] (3) For any to-be-issued coupon i, for any to-be-issued coupon user j, based on step (1) and step (2), the part k in which the user similarity (first similarity) meets the first preset similarity and the coupon similarity (second similarity) meets the second preset similarity, then the redemption probability of any to-be-issued coupon user j for the to-be-issued coupon i can be abstracted as the arithmetic mean of the user similarity of all users in the data set k and the coupon similarity of the user redeeming the coupon.

[0070] In an actual application scenario, step 105, that is, issuing the preset resource to the target user according to the resource redemption probability, specifically includes:

[0071] Step 105-1, if the resource redemption probability is greater than the preset redemption probability, issuing the preset resource corresponding to the resource redemption probability to the target user.

[0072] In this embodiment, the matching degree between the target user and the preset resource is determined by the resource redemption probability. The greater the resource redemption probability, the higher the matching degree. Therefore, if the resource redemption probability is greater than the preset redemption probability, it means that the target user has a greater demand for the preset resource, and the preset resource can be distributed to the target user. Thus, the target user can be issued with a resource that is more suitable for his own use, realizing personalized and refined allocation of coupons, which helps to improve the conversion rate of coupons and user loyalty, not only saving the user's shopping funds, but also helping to improve user stickiness and platform revenue.

[0073] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to completely describe the specific implementation process of the embodiment, after step 105, the resource issuing method further includes: if the preset resource is successfully issued to the target user, outputting an issuing prompt information of the preset resource.

[0074] In this embodiment, after performing the issuing operation of the preset resource, it is detected whether the preset resource is successfully issued to the target user. When the preset resource is successfully issued to the target user, the issuing prompt information of the preset resource is outputted. Not only can the user know in time that there is a new resource issued, improving the user's convenience in using the resource, but also the user can be reminded to use the resource in time, improving the possibility of using the resource, which helps to save the target user's funds.

[0075] Further, as described above,Figure 2 As a specific implementation of the above resource allocation method, the embodiment of the present application provides a resource allocation device 200, which comprises an acquisition module 201, a determination module 202 and a resource configuration module 203.

[0076] The acquisition module 201 is configured to acquire a resource cancellation user and a preset resource.

[0077] The determination module 202 is configured to compare the user features of the resource cancellation user and a target user to determine a first similarity between the resource cancellation user and the target user; compare the resource features of the preset resource and historical resources corresponding to a first user to determine a second similarity between the preset resource and the historical resources, the first user being a resource cancellation user whose first similarity is greater than or equal to a first preset similarity; and determine a resource cancellation probability of the target user with respect to the preset resource according to the first similarity and the second similarity.

[0078] The resource configuration module 203 is configured to allocate the preset resource to the target user according to the resource cancellation probability.

[0079] In this embodiment, a resource cancellation user who has a resource cancellation operation and a preset resource to be allocated to a user by the platform are first acquired. By comparing the differences between the user features of the resource cancellation user and a target user who meets the resource allocation condition, a first similarity between the resource cancellation user and the target user is determined, and a first user whose first similarity is greater than or equal to a first preset similarity is selected from the resource cancellation user, so as to determine a user who is likely to have similar resource use preferences as the target user by using the first similarity. Then, the resource features of the preset resource and historical resources used by the first user are compared to determine a second similarity between the preset resource and the historical resources, so as to determine a resource in the preset resource that is likely to meet the preferences of the first user by using the second similarity. Thus, according to the first similarity and the second similarity of the second user, a resource cancellation probability of the target user with respect to different preset resources can be determined. Finally, the preset resource is allocated to the target user on demand according to the resource cancellation probability. Thus, automatic resource dynamic allocation can be realized without network model training. Even in the case of a small amount of sample data, the resource can still be accurately allocated to a target user who needs it more, which not only improves the use effect of the resource, is conducive to increasing the total transaction amount, but also provides appropriate preferential policies for the user, improves the user shopping experience, and helps to enhance user loyalty.

[0080] Further, the determining module 202 is specifically configured to: if the second similarity is greater than or equal to a second preset similarity, determine the historical resource corresponding to the second similarity as the first resource; if the historical resource includes the first resource, determine the first user corresponding to the historical resource as the second user; and calculate the resource cancellation probability according to the first similarity corresponding to the second user and the second similarity of the first resource corresponding to the second user.

[0081] Further, the determining module 202 is specifically configured to: calculate the product of the first similarity corresponding to the second user and the second similarity of the first resource corresponding to the second user; and calculate the mean value of the product as the resource cancellation probability according to the number of the second users.

[0082] Further, the resource configuration module 203 is specifically configured to: if the resource cancellation probability is greater than a preset cancellation probability, issue the preset resource corresponding to the resource cancellation probability to the target user.

[0083] Further, the resource issuing apparatus 200 further includes a prompting module (not shown in the figure), which is configured to: if the preset resource is successfully issued to the target user, output an issuing prompt information of the preset resource.

[0084] The specific limitation of the resource issuing apparatus can refer to the limitation of the resource issuing method in the foregoing, and will not be described here. Each module in the above resource issuing apparatus can be realized by software, hardware and a combination thereof in whole or in part. The above each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in the form of software, so as to call and execute the operation corresponding to each module by the processor.

[0085] Based on the above method as shown in Figure 1 , correspondingly, the embodiment of the present application also provides a readable storage medium, which stores a computer program, and the program is executed by the processor to realize the above resource issuing method as shown in Figure 1 .

[0086] Based on such understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.), and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in each embodiment scenario of the present application.

[0087] Based on the above method as shown in Figure 1 , and Figure 2In order to achieve the above object, the virtual device embodiment shown by the present application further provides a computer device, which can be a personal computer, a server, a network device, etc., and the computer device comprises a storage medium and a processor; the storage medium is used for storing a computer program; and the processor is used for executing the computer program to realize the above-mentioned Figure 1 The resource issuing method shown.

[0088] Optionally, the computer device can further comprise a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface can comprise a display screen, an input unit such as a keyboard, etc. The optional user interface can further comprise a USB interface, a card reader interface, etc. The network interface can optionally comprise a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0089] Those skilled in the art can understand that the computer device structure provided by the present embodiment does not constitute a limitation on the computer device, and can comprise more or fewer components, or combine certain components, or different component arrangements.

[0090] The storage medium can further comprise an operating system and a network communication module. The operating system is a program for managing and saving computer device hardware and software resources, and supports the running of information processing programs and other software and / or programs. The network communication module is used for realizing the communication between the components in the storage medium, and the communication with other hardware and software in the entity device.

[0091] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary general hardware platforms, and the resource cancellation user and the preset resource can also be obtained by hardware implementation; the user characteristics of the resource cancellation user and the target user are compared to determine the first similarity between the resource cancellation user and the target user; the resource characteristics of the preset resource and the historical resource corresponding to the first user are compared to determine the second similarity between the preset resource and the historical resource, and the first user is the resource cancellation user whose first similarity is greater than or equal to the first preset similarity; according to the first similarity and the second similarity, the target user's probability of canceling the preset resource is determined; and the preset resource is issued to the target user according to the resource cancellation probability. The embodiments of the present application do not need network model training to realize automatic resource dynamic allocation. Even in the case of small amount of sample data, the resource can still be accurately issued to the target user who needs it more, ensuring the objectivity and fairness of resource allocation, and enabling the target user to obtain resources that meet their own needs. Not only does it improve the use effect of resources, but it also helps to increase the total transaction amount, provides appropriate preferential policies for users, improves the user shopping experience, and helps to enhance user loyalty.

[0092] Those skilled in the art can understand that the drawings are only a schematic of a preferred implementation scenario, and the modules or flows in the drawings are not necessarily required for implementing the present application. Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be changed and located in one or more devices different from the implementation scenario. The modules of the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0093] The above application numbers are only for description, and do not represent the advantages and disadvantages of the implementation scenario. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any changes that those skilled in the art can think of should fall within the protection scope of the present application.

Claims

1. A resource distribution method, characterized in that, The method includes: Obtain resource cancellation users and preset resources, wherein the resource cancellation users are users who have performed resource cancellation operations; By comparing the user characteristics of the resource redemption user and the target user, a first similarity is determined between the resource redemption user and the target user, wherein the target user is the user to be allocated the preset resource; By comparing the resource characteristics of the preset resource and the historical resource corresponding to the first user, a second similarity between the preset resource and the historical resource is determined, and the first user is the resource cancellation user whose first similarity is greater than or equal to the first preset similarity. If the second similarity is greater than or equal to the second preset similarity, the historical resource corresponding to the second similarity is determined as the first resource; If the historical resource includes the first resource, the first user corresponding to the historical resource is determined as the second user; Calculate the product of the first similarity corresponding to the second user and the second similarity corresponding to the first resource of the second user; The mean of the products is calculated based on the number of the second users and used as the resource write-off probability of the preset resource. According to the resource redemption probability, the preset resources are distributed to the target users.

2. The resource distribution method according to claim 1, characterized in that, The step of distributing the preset resources to the target user according to the resource redemption probability specifically includes: If the resource redemption probability is greater than the preset redemption probability, the preset resource corresponding to the resource redemption probability will be distributed to the target user.

3. The resource distribution method according to claim 1 or 2, characterized in that, The method further includes: If the preset resource is successfully distributed to the target user, a notification message indicating the distribution of the preset resource will be output.

4. A resource distribution device, characterized in that, The device includes: The acquisition module is used to acquire resource cancellation users and preset resources, wherein the resource cancellation users are users who have performed resource cancellation operations; A determination module is configured to compare the user characteristics of the resource redemption user and the target user to determine a first similarity between the resource redemption user and the target user, wherein the target user is a user to be allocated the preset resource; and to compare the resource characteristics of the preset resource and the historical resources corresponding to the first user to determine a second similarity between the preset resource and the historical resources, wherein the first user is the resource redemption user whose first similarity is greater than or equal to the first preset similarity; and if the second similarity is greater than or equal to the second preset similarity, to determine the historical resource corresponding to the second similarity as the first resource; and if the historical resource includes the first resource, to determine the first user corresponding to the historical resource as the second user; and to calculate the product of the first similarity corresponding to the second user and the second similarity corresponding to the first resource; and to calculate the mean of the product based on the number of second users as the resource redemption probability; The resource allocation module is used to distribute the preset resources to the target user according to the resource redemption probability.

5. The resource distribution device according to claim 4, characterized in that, The resource allocation module is specifically used to distribute the preset resources corresponding to the resource redemption probability to the target user if the resource redemption probability is greater than the preset redemption probability.

6. The resource distribution device according to claim 4 or 5, characterized in that, The device further includes: The notification module is used to output a notification message for the distribution of the preset resources if the preset resources are successfully distributed to the target user.

7. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the steps of the resource allocation method as described in any one of claims 1 to 3.

8. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the program, it implements the resource allocation method as described in any one of claims 1 to 3.

Images