Resource allocation method, device, equipment and program product

Abstract

The invention discloses a resource allocation method, device and equipment and a program product, and relates to the technical field of financial science and technology. The method comprises the following steps: obtaining tag information of at least one dimension of a resource demander during application and customer group tag information of at least one customer group, and screening similar customer groups of the resource demander from the customer groups according to the customer group tag information and the tag information during application; obtaining customer group resource allocation amounts of the similar customer groups at at least one key time point, and synthesizing the customer group resource allocation amounts of the key time points to obtain an initial resource allocation amount; obtaining a customer group resource configuration label of at least one dimension of the similar customer group, and determining a first resource configuration adjustment coefficient according to the customer group resource configuration label of each dimension of the similar customer group; and according to the first resource configuration adjustment coefficient, adjusting the initial resource configuration amount of the resource demander to obtain a target resource configuration amount. According to the technical scheme of the embodiment of the invention, the accuracy of resource configuration is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a resource allocation method, device, equipment and program product. Background Art

[0002] Currently, resource allocators allocate resources based on resource allocation requests from resource demanders. For new resource demanders (i.e., those for whom resource allocators have not previously allocated resources), resource allocators typically determine the amount of resources to be allocated to resource demanders based on the information provided by the resource demanders at the time of their resource allocation application, as well as information provided by third-party platforms with the resource demanders' authorization, combined with their own resource allocation strategies.

[0003] The above solution has the following drawbacks: First, the information available to resource allocators regarding new resource demanders is extremely limited, and some of this information is difficult to verify. Therefore, it is difficult to accurately assess the resource demander's true situation and, consequently, to accurately allocate resources. Second, resource allocators rely primarily on a small number of fixed resource allocation strategies. To mitigate the risk of resource allocation, these strategies typically employ strict risk control measures, making it difficult to achieve precise resource allocation and meet the resource allocators' demand for high-precision resource allocation. Summary of the Invention

[0004] The present invention provides a resource configuration method, apparatus, device and program product, which improve the accuracy of resource configuration.

[0005] According to one aspect of the present invention, a resource configuration method is provided, the method comprising:

[0006] Obtaining at least one dimension of application label information of the resource demander and customer group label information of at least one customer group, and screening similar customer groups of the resource demander from the customer groups based on the customer group label information and the application label information;

[0007] Obtaining the customer group resource allocation amount of the similar customer group at at least one key time point, and combining the customer group resource allocation amounts at each key time point to obtain the initial resource allocation amount of the resource demander;

[0008] Obtaining a customer group resource configuration tag of at least one dimension of the similar customer group, and determining a first resource configuration adjustment coefficient based on the customer group resource configuration tags of each dimension of the similar customer group;

[0009] The initial resource allocation amount of the resource demander is adjusted according to the first resource allocation adjustment coefficient to obtain a target resource allocation amount.

[0010] According to another aspect of the present invention, a resource configuration device is provided, the device comprising:

[0011] A similar customer group screening module is used to obtain at least one dimension of application label information of the resource demander and customer group label information of at least one customer group, and screen similar customer groups of the resource demander from the customer groups based on the customer group label information and the application label information;

[0012] an initial allocation determination module, configured to obtain the customer group resource allocation amount of the similar customer group at at least one key time point, and to synthesize the customer group resource allocation amounts at each of the key time points to obtain the initial resource allocation amount of the resource demander;

[0013] an adjustment coefficient determination module, configured to obtain a customer group resource configuration tag of at least one dimension of the similar customer group, and determine a first resource configuration adjustment coefficient based on the customer group resource configuration tags of each dimension of the similar customer group;

[0014] The initial configuration adjustment module is used to adjust the initial resource configuration amount of the resource demander according to the first resource configuration adjustment coefficient to obtain a target resource configuration amount.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the resource configuration method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the resource configuration method described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the resource configuration method according to any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention filters out similar customer groups of the resource demander through the label information of at least one dimension of the resource demander at the time of application, which solves the problem that the resource allocator can obtain extremely limited information about the new resource demander and it is difficult to prove the authenticity of some information. The initial resource allocation amount of the resource demander is determined through the customer group resource allocation amount of the similar customer group at at least one key time point, and the first resource allocation adjustment coefficient is determined through the customer group configuration label of at least one dimension of the similar customer group. Based on the first resource configuration adjustment coefficient, the initial resource allocation amount of the resource demander is adjusted to obtain the target resource allocation amount of the resource demander, which improves the flexibility and adaptability of resource allocation, and improves the accuracy of resource allocation, thereby realizing accurate resource allocation for the resource demander.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flowchart of a resource configuration method provided according to the first embodiment of the present invention;

[0025] Figure 2 This is a flowchart of a resource configuration method provided according to the second embodiment of the present invention;

[0026] Figure 3 This is a flowchart of a resource configuration method provided according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a flowchart of a resource configuration method provided according to Embodiment 3 of the present invention;

[0028] Figure 5 This is a flowchart of a resource configuration method provided according to Embodiment 3 of the present invention;

[0029] Figure 6 This is a structural diagram of a resource configuration device provided according to a fourth embodiment of the present invention;

[0030] Figure 7 It is a structural diagram of an electronic device for implementing the resource configuration method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Example 1

[0034] Figure 1 This is a flow chart of a resource configuration method provided in Embodiment 1 of the present invention. This embodiment of the present invention is applicable to resource configuration for a new resource configuration party. The method can be performed by a resource configuration device, which can be implemented in hardware and / or software. The resource configuration device can be configured in an electronic device that carries the resource configuration function, such as a client or server.

[0035] See also Figure 1 The resource configuration method shown includes:

[0036] S110 , obtaining application label information of at least one dimension of the resource demander and customer group label information of at least one customer group, and screening similar customer groups of the resource demander from the customer groups based on the customer group label information and the application label information.

[0037] A resource requester may be a new resource requester among resource allocators. It can be understood that a resource requester may not have previously had resource allocation performed by a resource allocator. Optionally, the resources requested by the resource requester may include hardware resources, software resources, or credit card limits. For example, the resource is a credit card limit. The resource allocator may be a financial institution. The resource requester may be a new credit card applicant. Application tag information may be used to represent the resource requester's information when applying for resource allocation. The application tag information may include at least one dimension. For example, the application tag information may include the resource requester's characteristic information, resource information, business information, personalized information, and a reference resource allocation amount. The resource requester's characteristic information may represent the resource requester's characteristic status, such as the resource requester's identity. The resource requester's resource information may represent the resource status of the resource requester. The resource requester's business information may include information about the business for which the resource allocation is being applied for by the resource requester from the resource allocator. For example, credit card information may include card registration, annual fee, whether it is a co-branded card, and whether the card is downgraded. The resource requester's personalized information can be used to represent their needs for services and corresponding resource allocation. Examples include automatic repayment agreements, balance change notification agreements, multiple points, and optional card numbers. The resource requester's reference resource allocation amount can be the resource requester's resource allocation amount derived based on existing resource allocation policies.

[0038] A customer group may be a party that has already been resource allocated by a resource allocator. Customer group tag information may be used to represent the information of a customer group when applying for resource allocation. Customer group tag information may include at least one dimension. Exemplarily, customer group tag information may include customer group feature information, resource information, business information, personalized information, and reference resource allocation amount. Specifically, the customer group's feature information may be used to represent the customer group's feature status. The customer group's resource information may be used to represent the resources possessed by the customer group itself. The customer group's business information may be the business to which the resource allocation applied by the customer group from the resource allocator belongs. The customer group's personalized information may be used to represent the customer group's demand for the business and the corresponding resource allocation. The customer group's reference resource allocation amount may be the customer group's resource allocation amount obtained based on an existing resource allocation strategy.

[0039] The resource requester's similar customer groups can be customer groups with similar tag information at the time of the resource requester's application. There can be at least one similar customer group. Because the resource requester is new to the resource allocator, the amount of tag information at the time of the resource requester's application is limited. Therefore, the resource allocation amount for the resource requester can be determined and adjusted based on the tag information at the time of the application of the resource requester's similar customer groups. This can improve the accuracy of the data used to determine the resource allocation amount for the resource requester, thereby increasing the accuracy of the resource allocation amount for the resource requester.

[0040] Specifically, when a resource requester applies for resource allocation, with authorization from both the resource requester and the customer group, at least one dimension of the resource requester's application tag information and at least one customer group's customer tag information can be obtained. A similarity comparison can be performed between the customer group tag information of each customer group and the resource requester's application tag information, and a preset number of similar customer groups with a high degree of similarity to the resource requester can be selected from each customer group. The preset number can be a pre-determined number of similar customer groups. The preset number can be set and adjusted by technical personnel based on experience.

[0041] S120: Obtain the customer group resource allocation amount of a similar customer group at at least one key time point, and integrate the customer group resource allocation amount at each key time point to obtain the initial resource allocation amount of the resource demander.

[0042] Key time points can be reference points for determining the initial resource allocation amount. For example, key time points may include the time of resource allocation, six months after resource allocation, one year after resource allocation, 18 months after resource allocation, two years after resource allocation, and three years after resource allocation. The customer group resource allocation amount can be the resource allocation amount for similar customer groups at key time points. The customer group resource allocation amount can be used to represent the resource allocation status of similar customer groups.

[0043] Specifically, the customer group resource allocation amounts at each key time point can be input into a pre-trained initial resource allocation amount determination model to obtain the initial resource allocation amount for the resource demander. The initial resource allocation amount determination model can be used to determine the initial resource allocation amount for the resource demander. Exemplarily, the initial resource allocation amount determination model can be a machine learning model.

[0044] In an optional embodiment of the present invention, the customer group resource allocation amounts at each key time point are integrated to obtain the initial resource allocation amount of the resource demander, including: performing weighted summation on the customer group resource allocation amounts at each key time point to obtain the initial resource allocation amount of the resource demander.

[0045] Specifically, fixed weight values ​​for each key time point can be pre-set. Using these fixed weight values, the customer resource allocation amounts at each key time point can be directly weighted and summed to obtain the initial resource allocation amount for the resource demander. For example, corresponding fixed weight values ​​can be set based on the time distance from the current moment. For example, the closer the time distance to the current moment, the larger the corresponding fixed weight value. In another example, the fixed weight value for each key time point can be determined based on the correlation coefficient between each key time point and the final initial resource allocation amount.

[0046] This solution obtains the initial resource allocation amount of the resource demander by directly performing weighted summation on the customer group resource allocation amount at each key time point, thereby improving the efficiency of determining the initial resource allocation amount.

[0047] In an optional embodiment of the present invention, the customer group resource allocation amounts at each key time point are integrated to obtain the initial resource allocation amount of the resource demander, including: detecting the key data quantity of the customer group resource allocation amount at each key time point; when any key data quantity is less than or equal to the preset data quantity, merging the customer group resource allocation amounts at each key time point to obtain the first customer group resource allocation amount, the second customer group resource allocation amount and the third customer group resource allocation amount; and performing weighted summation of the first customer group resource allocation amount, the second customer group resource allocation amount and the third customer group resource allocation amount to obtain the initial resource allocation amount of the resource demander.

[0048] The key data quantity can be the number of data points representing the customer group resource allocation amount at a single key time point. The preset data quantity can be a preset lower limit for the key data quantity. The preset data quantity can be preset and adjusted by technical personnel based on experience. The first customer group resource allocation amount, the second customer group resource allocation amount, and the third customer group resource allocation amount can be the customer group resource allocation amounts obtained by combining at least two key time points. In comparison, the first customer group resource allocation amount, the second customer group resource allocation amount, and the third customer group resource allocation amount correspond to different key time points. For example, key time points may include the time of resource allocation, six months after resource allocation, one year after resource allocation, eighteen months after resource allocation, two years after resource allocation, and three years after resource allocation. The first customer group resource allocation amount can be the customer group resource allocation amount obtained by combining the time of resource allocation and six months after resource allocation. The second customer group resource allocation amount can be the customer group resource allocation amount obtained by combining one year after resource allocation and eighteen months after resource allocation. The third customer group resource allocation amount can be the customer group resource allocation amount obtained by combining two years after resource allocation and three years after resource allocation.

[0049] Specifically, the number of key data points for customer group resource allocation at each key time point can be detected. When the number of any key data point is less than or equal to a preset number of data points, the customer group resource allocation amounts at at least two key time points can be merged without cross-pollination. The median of the merged customer group resource allocation amounts can be selected to obtain the first customer group resource allocation amount, the second customer group resource allocation amount, and the third customer group resource allocation amount, respectively. A pre-set first weight, second weight, and third weight can be obtained. Based on the first weight, second weight, and third weight, a weighted sum of the first customer group resource allocation amount, the second customer group resource allocation amount, and the third customer group resource allocation amount can be taken to obtain the initial resource allocation amount of the resource demander. The first weight can be the weight of the first customer group resource allocation amount. The second weight can be the weight of the second customer group resource allocation amount. The third weight can be the weight of the third customer group resource allocation amount. The first weight, second weight, and third weight can be pre-set and adjusted by technical personnel.

[0050] This solution further improves the efficiency and accuracy of determining the initial resource allocation amount by merging the customer group resource allocation amounts when the number of any key data is less than or equal to the preset data number, and then determining the initial resource allocation amount of the resource demander based on the merged first customer group resource allocation amount, second customer group resource allocation amount and third customer group resource allocation amount.

[0051] S130: Obtain customer resource configuration labels of at least one dimension of a similar customer group, and determine a first resource configuration adjustment coefficient based on the customer resource configuration labels of each dimension of the similar customer group.

[0052] The customer group resource configuration label can be used to characterize the usage of customer group resources after configuration. The customer group resource configuration label may include at least one dimension. Exemplarily, the customer group resource configuration label may include business behavior information, resource configuration usage information, and risk information. For example, business behavior information may include credit card status, business usage activity, and other business handling. Resource configuration usage information may include resource configuration amount, resource configuration amount utilization rate, temporary adjustment of resource configuration amount, and active adjustment of resource configuration amount. Among them, the resource configuration amount may include the initial resource configuration amount, the target resource configuration amount, and the adjusted target resource configuration amount. Risk information may include failure to repay on time, overdue status, and gray and black lists. The first resource configuration adjustment coefficient can be used to adjust the initial resource configuration amount of the resource demander.

[0053] Specifically, after obtaining authorization from similar customer groups, customer resource allocation tags for at least one dimension of at least one similar customer group can be obtained. The customer resource allocation tags for each dimension can be input into a pre-trained first resource allocation adjustment coefficient determination model to obtain the first resource allocation adjustment coefficient for the resource demander.

[0054] In an optional embodiment of the present invention, a first resource configuration adjustment coefficient is determined based on the customer resource configuration labels of each dimension of similar customer groups, including: determining the first label score corresponding to the customer resource configuration label of each dimension based on the customer resource configuration labels of each dimension of similar customer groups; integrating the first label scores to obtain the first risk level of the resource demander; and determining the first resource configuration adjustment coefficient based on the first risk level of the resource demander.

[0055] The first tag score can be the score of a customer resource configuration tag for a single dimension. The first tag score can be used to represent the evaluation status of similar customer groups based on the customer resource configuration tag for a single dimension. A preset correspondence can exist between the customer resource configuration tag for a single dimension and the corresponding first tag score. Based on the customer resource configuration tag for a single dimension, the corresponding first tag score can be determined.

[0056] The first risk level can be used to comprehensively characterize resource demanders from the perspective of customer resource allocation tags across multiple dimensions. A preset correspondence exists between the first risk level and the combined results of each first comprehensive score. Based on the combined results of each first comprehensive score, a corresponding first risk level can be determined. Correspondingly, a preset correspondence exists between the first risk level and the first resource allocation amount adjustment coefficient. Based on the first risk level, a corresponding first allocation amount adjustment coefficient can be determined.

[0057] Specifically, for customer resource configuration tags in a single dimension for similar customer groups, a binning approach can be used to determine the number of tiers corresponding to the customer resource configuration tags in a single dimension. Scoring rules corresponding to customer resource configuration tags in a single dimension can be used to determine the first tag score for the resource demander in a single dimension based on the number of tiers corresponding to the configured resource configuration tags in a single dimension. The first tag scores can be combined, and based on the combined result of the first tag scores, the first risk level of the corresponding resource demander can be determined. Based on the first risk level of the resource demander, the corresponding first resource configuration adjustment coefficient can be determined.

[0058] This solution determines the first label score corresponding to the customer resource configuration label of each dimension based on the customer resource configuration label of each dimension, determines the first risk level of the corresponding resource demander based on each first label score, and then determines the first resource configuration adjustment coefficient of the resource demander, thereby improving the efficiency and accuracy of determining the first resource configuration adjustment coefficient.

[0059] S140: Adjust the initial resource allocation amount of the resource demander according to the first resource allocation adjustment coefficient to obtain a target resource allocation amount.

[0060] The target resource allocation amount can be the result of adjusting the initial resource allocation amount based on the first resource allocation adjustment coefficient. In comparison, the initial resource allocation amount only considers the customer resource allocation amounts of similar customer groups at each key time point; the target resource allocation amount, on the other hand, not only considers the customer resource allocation amounts of similar customer groups at each key time point but also takes into account the customer resource allocation labels of at least one dimension of similar customer groups. This makes the target resource allocation amount more accurate.

[0061] Specifically, the target resource allocation amount may be obtained by calculating the product of the initial resource allocation amount of the resource demander and the first resource allocation adjustment coefficient.

[0062] The technical solution of the embodiment of the present invention filters out similar customer groups of the resource demander through the label information of at least one dimension of the resource demander at the time of application, which solves the problem that the resource allocator can obtain extremely limited information about the new resource demander and it is difficult to prove the authenticity of some information. The initial resource allocation amount of the resource demander is determined through the customer group resource allocation amount of the similar customer group at at least one key time point, and the first resource allocation adjustment coefficient is determined through the customer group configuration label of at least one dimension of the similar customer group. Based on the first resource configuration adjustment coefficient, the initial resource allocation amount of the resource demander is adjusted to obtain the target resource allocation amount of the resource demander, which improves the flexibility and adaptability of resource allocation, and improves the accuracy of resource allocation, thereby realizing accurate resource allocation for the resource demander.

[0063] In an optional embodiment of the present invention, after adjusting the initial resource allocation amount of the resource demander according to the first resource allocation adjustment coefficient to obtain the target resource allocation amount, it also includes: obtaining the configured resource configuration tags of at least one dimension of the resource demander, and determining the second tag scores corresponding to the configured resource configuration tags of each dimension; integrating the second tag scores to obtain the second risk level of the resource demander; determining the second resource allocation adjustment coefficient according to the second risk level of the resource demander; and adjusting the target resource allocation amount of the resource demander according to the second resource configuration adjustment coefficient.

[0064] The configured resource configuration tag can be used to represent the usage of resource configuration for resource demanders. The configured resource configuration tag can include at least one dimension. For example, the configured resource configuration tag can include business behavior information, resource configuration usage information, and risk information.

[0065] The second tag score can be a score for a configured resource configuration tag in a single dimension. The second tag score can be used to represent the resource demander's evaluation of the configured resource configuration tag in a single dimension. A preset correspondence can exist between the configured resource configuration tag in a single dimension and the corresponding second tag score. Based on the configured resource configuration tag in a single dimension, the corresponding second tag score can be determined.

[0066] The second risk level can be used to comprehensively characterize resource demanders from the perspective of configured resource allocation tags across multiple dimensions. A preset correspondence exists between the second risk level and the combined results of each second comprehensive score. Based on the combined results of each second comprehensive score, a corresponding second risk level can be determined. Correspondingly, a preset correspondence exists between the second risk level and the second resource allocation amount adjustment coefficient. Based on the second risk level, a corresponding second allocation amount adjustment coefficient can be determined.

[0067] Specifically, for the resource demander's configured resource configuration tags in a single dimension, a binning method can be used to determine the number of bins corresponding to the configured resource configuration tags in a single dimension. Scoring rules corresponding to the configured resource configuration tags in a single dimension can be used to determine the resource demander's corresponding second tag score in a single dimension based on the number of bins corresponding to the configured resource configuration tags in a single dimension. The second tag scores can be combined, and based on the combined results of the second tag scores, the corresponding second risk level of the resource demander can be obtained. Based on the second risk level of the resource demander, the corresponding second resource configuration adjustment coefficient is determined.

[0068] After obtaining the target resource allocation amount, this solution determines the second label score corresponding to the configured resource configuration label of each dimension based on the configured resource configuration label of each dimension, determines the second risk level of the corresponding resource demander based on each second label score, and then determines the second resource allocation adjustment coefficient of the resource demander, and adjusts the target resource allocation amount of the resource demander based on the second resource configuration adjustment coefficient, determines the accuracy of the second resource configuration adjustment coefficient, and thus improves the accuracy of the target resource allocation amount of the resource demander.

[0069] Example 2

[0070] Figure 2A flow chart of a resource configuration method provided for the second embodiment of the present invention. Based on the above embodiments, the embodiment of the present invention concretizes "screening similar customer groups of the resource demander in the customer group based on the customer group label information and the label information at the time of application" into "building a customer group resource scoring matrix based on the customer group label information and the label information at the time of application; calculating the customer group similarity between the resource demander and each customer group based on the customer group resource scoring matrix; screening similar customer groups of the resource demander in the customer group based on the similarity of each customer group", and introduces the customer group resource scoring matrix to screen similar customer groups of the resource demander in the customer group, thereby improving the accuracy of screening similar customer groups of the resource demander. It should be noted that for the parts not described in detail in the embodiments of the present invention, please refer to the description of other embodiments.

[0071] See also Figure 2 The resource configuration method shown includes:

[0072] S210 , obtaining application label information of at least one dimension of the resource demander and customer label information of at least one customer group, and constructing a customer group resource scoring matrix based on the customer group label information and the application label information.

[0073] The customer group resource scoring matrix can be used to score and quantify the label information of the resource demander at the time of application and the customer group label information of the customer group. The rows of the customer group resource scoring matrix can be used to represent the resource demander or the customer group. The columns of the customer group resource scoring matrix can be used to represent the feature label dimensions of the resource demander's label information at the time of application (or the customer group label information of the customer group). Exemplarily, the label information at the time of application or the customer group label information can be annual income. Accordingly, the label information at the time of application or the customer group label information can be quantified by binning and normalization to obtain the value of the corresponding element in the customer group resource scoring matrix.

[0074] For example, the following formula can be used to represent the customer resource scoring matrix:

[0075]

[0076] Where R is the customer resource rating matrix; r ij is the quantitative value of the jth dimension corresponding to the customer group label information (or label information at the time of application) of the i-th customer group (or resource demander); m is the number of customer groups and resource demanders; n is the dimension of the label information at the time of application or the customer group label information.

[0077] Optionally, the customer group label information of the customer group and the label information of the resource demander at the time of application can be processed by binning and normalization to obtain the quantitative values ​​of the customer group label information of each customer group and the label information of the resource demander at the time of application, and then obtain the customer group resource scoring matrix.

[0078] Optionally, the customer group label information of the customer group and the label information of the resource demander at the time of application can be processed by binarizing the categorical variables and performing weight mapping to obtain the quantitative values ​​of the customer group label information of each customer group and the label information of the resource demander at the time of application, and then obtain the customer group resource scoring matrix.

[0079] S220: Calculate the customer group similarity between the resource demander and each customer group based on the customer group resource scoring matrix.

[0080] Customer group similarity can be the similarity between a resource demander and a single customer group. Customer group similarity can be used to characterize the degree of similarity between a resource demander and a single customer group.

[0081] Specifically, the customer group similarity between the resource demander and each customer group may be calculated based on the quantitative values ​​of the resource demander and customer group under different dimensional label information in the customer group resource scoring matrix.

[0082] For example, the following formula can be used to express the customer group similarity between the resource demander and the customer group:

[0083]

[0084] Where sim(u,v) is the customer group similarity between resource demander u and customer group v; n is the dimension of label information or customer group label information at the time of application; r uk is the quantitative value of the corresponding dimension of the label information of the resource demander u when applying; r vk It is the quantitative value of customer group v in the dimension corresponding to the customer group label information.

[0085] S230. Filter similar customer groups of resource demanders from among the customer groups based on the similarity of each customer group.

[0086] Specifically, the customer groups can be ranked from highest to lowest in similarity, and the customer groups corresponding to the preset number of customer groups ranked first in similarity can be selected to obtain similar customer groups for the resource demander. The preset number of customer groups can be a pre-determined number of similar customer groups. The preset number of customer groups can be set and adjusted by technical personnel based on experience. For example, the preset number of customer groups can be 50.

[0087] In an optional embodiment of the present invention, after screening similar customer groups of resource demanders among the customer groups based on the similarity of each customer group, it also includes: obtaining the resource allocation amount change rate of each similar customer group within a preset time period; and eliminating abnormal customer groups among each similar customer group based on the resource allocation amount change rate.

[0088] The preset time period can be a pre-set period used to detect whether the resource allocation amounts of similar customer groups change normally. The preset time period can be set and adjusted by technical personnel based on experience. For example, the preset time period can be one year. The resource allocation amount change rate can be used to indicate changes in the customer resource allocation amounts of similar customer groups within the preset time period. Abnormal customer groups can be similar customer groups with abnormal resource allocation amount change rates.

[0089] Specifically, with the authorization of similar customer groups, after screening similar customer groups of resource demanders in the customer groups based on the similarity of each customer group, the customer group resource allocation amount of each similar customer group within the preset time period can be obtained. Based on the customer group resource allocation amount of each similar customer group within the preset time period, the resource allocation amount change rate of each similar customer group within the preset time period can be calculated. The resource allocation amount change rate of each similar customer group within the preset time period can be compared with the preset resource allocation amount change rate threshold. When the resource allocation amount change rate of a similar customer group within the preset time period is greater than or equal to the preset resource allocation amount change rate threshold, the corresponding similar customer group is determined to be an abnormal customer group, and the abnormal customer group is eliminated from each similar customer group. Among them, the preset resource allocation amount change rate threshold can be the minimum value of the resource allocation amount change rate of the pre-set abnormal customer group. The preset resource allocation amount change rate threshold can be set and adjusted by technical personnel based on experience.

[0090] This solution introduces the rate of change of resource allocation amount for each similar customer group within a preset time period. By eliminating abnormal customer groups from similar customer groups, the accuracy of similar customer groups is further improved, thereby improving the accuracy of resource allocation.

[0091] S240: Obtain the customer group resource allocation amount of a similar customer group at at least one key time point, and integrate the customer group resource allocation amount at each key time point to obtain the initial resource allocation amount of the resource demander.

[0092] S250: Obtain customer resource configuration labels of at least one dimension of similar customer groups, and determine a first resource configuration adjustment coefficient based on the customer resource configuration labels of each dimension.

[0093] S260: Adjust the initial resource allocation amount of the resource demander according to the first resource allocation adjustment coefficient to obtain a target resource allocation amount.

[0094] The technical solution of the embodiment of the present invention constructs a customer group resource scoring matrix based on customer group label information and application label information, calculates the customer group similarity between the resource demander and each customer group based on the customer group resource scoring matrix, and screens similar customer groups of the resource demander from the customer group based on the similarity of each customer group. The customer group resource scoring matrix is ​​introduced to screen similar customer groups of the resource demander from the customer group, thereby improving the accuracy of screening similar customer groups of the resource demander.

[0095] Based on the above embodiments, Figure 3 This is a preferred embodiment of a resource configuration method provided by the present invention. Figure 3 The resource configuration method shown includes:

[0096] S310: With authorization from the new resource demander, obtain the application information of the resource demander and construct the application tag information of the resource demander; with authorization from the customer group, obtain the customer group tag information and the customer group resource configuration tag.

[0097] For resource allocators, data on millions of new resource demanders is generated every year. These demanders have never conducted business with a specific resource allocator and do not have any credit card, debit card, or merchant data. For these new demanders, third-party big data platforms can collect their data with their authorization.

[0098] Among them, the label information or customer group label information at the time of application may include characteristic information of the resource demander (or customer group), resource information, business information, personalized information and reference resource allocation amount, etc.

[0099] First, the characteristic information of the resource demander (or customer group) can be used to characterize the characteristic status of the resource demander (or customer group), such as the identity of the resource demander (or customer group).

[0100] Second, resource information about the resource demander (or customer group) can be used to characterize the resources available to the resource demander (or customer group). Business information about the resource demander (or customer group) can include information about the business for which the resource demander (or customer group) has requested resource allocation from the resource allocator. For example, credit card information might include card registration, annual fee, whether it is a co-branded card, and whether the card has been downgraded.

[0101] Third, personalized information about resource demanders (or customer groups) can be used to characterize their needs for services and corresponding resource allocations, such as automatic repayment agreements, balance change notification agreements, multiple points, and self-selected card numbers.

[0102] Fourth, the reference resource allocation amount of the resource demander (or customer group) may be the resource allocation amount of the resource demander (or customer group) obtained based on an existing resource allocation strategy.

[0103] The label information (or customer group label information) at the time of application can be used to classify and label new resource demanders (or customer groups). Figure 4 As shown, the label information of a new resource demander when applying may include Class A labels, Class B labels, Class C labels, Class D labels, and Class E labels. Class A labels can be the characteristic information of the resource demander; Class B labels can be the resource information of the resource demander; Class C labels can be the business information of the resource demander; Class D labels can be the personalized information of the resource demander; and Class E labels can be the reference resource allocation amount of the resource demander. For example, the card product information (i.e., the business information of the resource demander) is Class C label, and the sub-label C1 is the card level, including platinum card, gold card, or ordinary card; and the sub-label C2 is the annual fee of the card, which can be 500 yuan for a just-in-time fee, free annual fee, or reduced if the consumption meets the requirements.

[0104] Specifically, with the authorization of the new resource demander, the historical inventory data of the new resource demander and the information submitted at the time of application can be obtained from a third-party big data platform to obtain the application information. Based on the application information of the resource demander, multiple application tag information can be constructed.

[0105] Optionally, before executing this step, a risk check can be performed on the new resource demander based on the label information of the new resource demander at the time of application, such as being on the credit overdue list, failing the online verification, failing the mobile phone number, hitting the gray or black list, etc.; if the risk check passes, this step is executed; if the risk check fails, this step is not executed.

[0106] Among them, such as Figure 5As shown, the customer resource allocation tag can include business behavior information, resource allocation usage information, and risk information. First, business behavior information can include credit card status, business usage activity, and other business transactions. Credit card status can include activation, binding, or cancellation. Business usage activity can be identified by average monthly business usage. Other business transactions can be identified by average annual business transactions. Second, resource allocation usage information can include resource allocation amount, resource allocation amount utilization rate, temporary resource allocation amount adjustments, and proactive resource allocation amount adjustments. Resource allocation amount can include the initial resource allocation amount, target resource allocation amount, and adjusted target resource allocation amount. Temporary resource allocation amount adjustments can include the average annual number of temporary adjustments. Proactive resource allocation amount adjustments can include the average annual number of proactive adjustments. Third, risk information can include missed payments, the average annual number of overdue payments, and graylist and blacklist entries. Failed payments and overdue payments can be counted by average annual number. Graylists and blacklist entries can include specific lists, such as telecom fraud lists.

[0107] S320. Build a basic tag ledger based on the tag information of the resource demander at the time of application, the customer tag information of multiple customer groups, and the customer group resource configuration tags, and regularly update the basic tag ledger data.

[0108] Specifically, based on the application tag information collected in step S310, the customer tag information of multiple customer groups, and the customer resource configuration tags, the tags can be stored according to different time dimensions (such as the past 6 months, 1 year, 18 months, 2 years, and 3 years, etc.) to establish a tag basic ledger. Optionally, the tag basic ledger is updated regularly to ensure the completeness and accuracy of the customer group data. For example, data can be updated on a monthly basis, and the configured resource configuration tags of new resource demanders can be added to the tag basic ledger.

[0109] S330. According to the tag information of the new resource demander when applying for a card, obtain the customer group tag information in the tag basic ledger, and determine the similar customer groups of the resource demander based on the customer group tag information.

[0110] Specifically, based on the label information of the new resource demander when applying for the card, fuzzy matching can be performed in the label basic ledger to obtain similar customer groups of the resource demander.

[0111] For example, a customer resource scoring matrix can be constructed based on customer tag information and application tag information:

[0112] Among them, the characteristic label dimensions of customer group label information and application label information (category A-category E) are detailed in the attached Figure 4 Among them, customer groups include resource demanders and customer groups.

[0113] For example, the following formula can be used to represent the customer resource scoring matrix:

[0114]

[0115] Where R is the customer resource rating matrix; r ij is the quantitative value of the jth dimension corresponding to the customer group label information (or label information at the time of application) of the i-th customer group (or resource demander); m is the number of customer groups and resource demanders; n is the dimension of the label information at the time of application or the customer group label information.

[0116] For example, some quantification rules for customer group label information and application label information are as follows:

[0117]

[0118] The following formula can be used to express the customer group similarity between the resource demander and the customer group:

[0119]

[0120] Where sim(u,v) is the customer group similarity between resource demander u and customer group v; n is the dimension of label information or customer group label information at the time of application; r uk is the quantitative value of the corresponding dimension of the label information of the resource demander u when applying; r vk It is the quantitative value of customer group v in the dimension corresponding to the customer group label information.

[0121] You can sort in descending order by customer group similarity and select the top 50 similar customer groups (N=50).

[0122] Customer resource allocation tags for similar customer groups can be generated. For example, a flowchart structure can be used to analyze and output customer resource allocation tags (HJ categories) for similar customer groups. For example, A [similar customer group] --> B (business behavior information category H), A --> C (risk information category I), A --> D (resource allocation and usage information category J).

[0123] Optionally, similar customer groups can be processed for outliers based on their customer tag information, eliminating abnormal customer groups from the similar customer groups. For example, similar customer groups whose customer tag information changes by a greater than a certain threshold in the latter time dimension compared to the previous time dimension can be treated as abnormal customer groups and eliminated from the similar customer groups. For example, if the rate of change in the customer group resource allocation amount within a preset time period is greater than 100% (e.g., 10,000 to 30,000 within 1 year), they will be eliminated.

[0124] S340: Obtain the customer group resource allocation amount of a similar customer group at at least one key time point, and integrate the customer group resource allocation amount at each key time point to obtain the initial resource allocation amount of the resource demander.

[0125] Specifically, the customer resource allocation amounts at six key time points can be extracted from similar customer groups:

[0126] 1. The amount of customer group resources allocated during resource allocation (t=0);

[0127] 2. The amount of customer group resources allocated at the end of 6 months after resource allocation (t = 6);

[0128] 3. The amount of customer group resources allocated at the end of one year after resource allocation (t = 12);

[0129] 4. The amount of customer group resource allocation at the end of 18 months after resource allocation (t=18);

[0130] 5. The amount of customer group resource allocation at the end of the 2-year period after resource allocation (t = 24);

[0131] 6. The amount of customer resource allocation at the end of the three years after resource allocation (t=36).

[0132] The amount of customer group resource allocation at each key time point can be calculated by median calculation, and the median of the amount of customer group resource allocation at each key time point can be obtained, which can be marked as: P0, P6, P 12 ,P 18 ,P 24 ,P 36 .

[0133] Based on the data in the tag base ledger, you can set fixed weight values ​​corresponding to different key time points (satisfying ∑ weight = 1.0):

[0134] Key time points Weight value Weight setting basis Resource allocation time (t=0) 0.15 Initial resource allocation amount 6 months after resource allocation (t=6) 0.25 Verification of short-term business behavior stability 12 months after resource allocation (t=12) 0.30 Key behavioral turning points (highest weight) 18 months after resource allocation (t=18) 0.20 Mid-term credit performance assessment 24 months after resource allocation (t=24) 0.07 Long-term trend reference 36 months after resource allocation (t=36) 0.03 Long-term data attenuation reference

[0135] Among them, the Pearson correlation coefficient between the customer group resource allocation amount 12 months after resource allocation and the final stable customer group resource allocation amount is the highest (r=0.52), so it is given the maximum weight of 0.30.

[0136] The following formula can be used to calculate the initial resource allocation amount of the resource demander:

[0137] Initial resource allocation amount = (0.15×P0) + (0.25×P6) + (0.30×P 12 )+(0.20×P 18 )+(0.07×P 24 )+(0.03×P 36 );

[0138] Where, P0 is the customer group resource allocation amount at the time of resource allocation; P6 is the customer group resource allocation amount at the end of 6 months after resource allocation; P12 P is the amount of customer group resources allocated at the end of one year after resource allocation; 18 The amount of customer group resources allocated at the end of 18 months after resource allocation; P 24 The amount of customer group resources allocated at the end of 2 years after resource allocation; P 36 It is the amount of customer resource allocation at the end of 3 years after resource allocation.

[0139] Optionally, when the number of customer resource allocations N at a key time point is less than 30, you can enable key time point folding in the following way:

[0140] Original key time point Key period after the merger New weights t=0+t=6 Short-term (0-6M) 0.40 t=12+t=18 Mid-term (12-18M) 0.50 t=24+t=36 Long-term (24M+) 0.10

[0141] If the median amount of customer resource allocation in the short-term key time period = 10,000, the median amount of customer resource allocation in the medium-term key time period = 15,000, and the median amount of customer resource allocation in the long-term key time period = 18,000; then the initial resource allocation amount of the resource demander = (0.40×10,000)+(0.50×15,000)+(0.10×18,000)=13,300.

[0142] S350: Obtain customer resource allocation tags for at least one dimension of similar customer groups, and determine a first resource allocation adjustment coefficient based on the customer resource allocation tags for each dimension of the similar customer groups, adjust the initial resource allocation amount of the resource demander, and obtain a target resource allocation amount.

[0143] Customer resource allocation tags can include business behavior information, resource allocation usage information, and risk information. Business behavior information (Category H) includes credit card status, business usage activity, and other business transaction frequency. Risk information (Category I) includes missed payments, overdue payments, and graylist and blacklist status. Resource allocation usage information (Category J) includes resource allocation amounts, resource allocation amount utilization rate, temporary adjustments to resource allocation amounts, and proactive adjustments to resource allocation amounts.

[0144] Specifically, the following binning rules can be used to bin the customer resource configuration labels corresponding to the feature label dimension:

[0145] Feature label dimension Binning rules Number of bins Average monthly business usage Equal frequency binning (0-20%, 20%-40%, ...) 5 gears Average number of overdue payments per year [0],[1],[2],[≥3] 4 gears Resource allocation amount utilization rate ＜40％,40％-70％,＞70％ 3rd gear

[0146] The following scoring rules can be used to score the feature label dimension of the business behavior information to obtain the first label score corresponding to the business behavior information:

[0147] index Scoring Rules Credit card status Activate card = 2 points, bind card = 1 point, cancel card = 0 points Average monthly business usage Scoring is divided into 5 levels (0.5 / 1.0 / 1.5 / 2.0 / 2.5) Average monthly volume of other business +0.3 points for each type of business handled (upper limit 1.5 points)

[0148] The following scoring rules can be used to score the feature label dimension of risk information and obtain the first label score corresponding to the risk information:

[0149] index Scoring Rules Gray and black lists Telecommunications fraud = 0 points, other = 20 points, none = 40 points Average number of overdue payments per year 0 times = 30 points, each additional time - 10 points

[0150] The following scoring rules can be used to score the feature label dimension of resource configuration and usage information to obtain the first label score corresponding to the resource configuration and usage information:

[0151] index Scoring Rules Average monthly resource allocation utilization rate <40%=10 points, 40-90%=5 points, >90%=2 points Frequency of temporary adjustments to resource allocation amounts 0 times = 10 points, each additional time - 2 points

[0152] The following formula can be used to combine the scores of each first label:

[0153]

[0154] Where S 总 The comprehensive score of each first label; S 业务 Score the first label corresponding to the business behavior information; S 风险 Score the first label corresponding to the risk information; S 资源配置 Score the first tag corresponding to the resource configuration usage information.

[0155] The following risk level mapping rules can be used to determine the first risk level of the resource demander:

[0156] Comprehensive score First risk level Special rule priority ≥0.85 1 No risk events + usage rate <40% + Top 20% active 0.70-0.84 2 0.50-0.69 3 0.30-0.49 4 <0.30 5 Telecom fraud list direct judgment

[0157] The following first risk level can be used to determine the corresponding first resource allocation adjustment coefficient and the calculation formula for the final target resource allocation amount:

[0158] First risk level First resource allocation adjustment coefficient Calculation formula for target resource allocation amount 1 1.2 Initial resource allocation amount × 1.2 2 1.1 Initial resource allocation amount × 1.1 3 1 Initial resource allocation amount 4 0.8 Initial resource allocation amount × 0.8 5 0.5 Initial resource allocation amount × 0.5

[0159] Assume that the customer resource allocation amount at the key time point is: P0 = 10000; P6 = 12000; P 12 =15000;P 18 =16000;P 24 =18000;P 36 =20000; first risk level = 2;

[0160] Initial resource allocation amount = (0.15 × 10,000) + (0.25 × 12,000) + (0.30 × 15,000) + (0.20 × 16,000) + (0.07 × 18,000) + (0.03 × 20,000) = 14,660;

[0161] Target resource allocation amount = 14,660 × 1.1 = 16,126. This can be rounded up to 16,100. The recommended target resource allocation amount for new resource requirements is 16,100.

[0162] The present invention solves the problem of accurately determining the resource allocation amount when the information of the new resource demander is limited, improves the accuracy of resource allocation for the new resource demander, and reduces the need for resource allocation adjustment within a certain period after resource allocation.

[0163] Example 3

[0164] Figure 6 This is a schematic diagram of the structure of a resource configuration device provided in Embodiment 3 of the present invention. This embodiment of the present invention is applicable to the case of configuring resources for a new resource configuration party. The device can execute a resource configuration method. The device can be implemented in hardware and / or software. The device can be configured in an electronic device that carries the resource configuration function, such as a client or server.

[0165] See also Figure 6 The resource allocation device shown includes: a similar customer group screening module 610, an initial configuration determination module 620, a first adjustment coefficient determination module 630, and an initial configuration adjustment module 640. The similar customer group screening module 610 is configured to obtain application tag information of at least one dimension of a resource demander and customer group tag information of at least one customer group, and to screen similar customer groups of the resource demander from the customer groups based on the customer group tag information and the application tag information. The initial configuration determination module 620 is configured to obtain customer group resource allocation amounts of the similar customer group at at least one key time point and to synthesize the customer group resource allocation amounts at each key time point to obtain the initial resource allocation amount of the resource demander. The first adjustment coefficient determination module 630 is configured to obtain customer group resource allocation tags of at least one dimension of the similar customer group and to determine a first resource allocation adjustment coefficient based on the customer group resource allocation tags of each dimension of the similar customer group. The initial configuration adjustment module 640 is configured to adjust the initial resource allocation amount of the resource demander based on the first resource allocation adjustment coefficient to obtain the target resource allocation amount.

[0166] The technical solution of the embodiment of the present invention filters out similar customer groups of the resource demander through the label information of at least one dimension of the resource demander at the time of application, which solves the problem that the resource allocator can obtain extremely limited information about the new resource demander and it is difficult to prove the authenticity of some information. The initial resource allocation amount of the resource demander is determined through the customer group resource allocation amount of the similar customer group at at least one key time point, and the first resource allocation adjustment coefficient is determined through the customer group configuration label of at least one dimension of the similar customer group. Based on the first resource configuration adjustment coefficient, the initial resource allocation amount of the resource demander is adjusted to obtain the target resource allocation amount of the resource demander, which improves the flexibility and adaptability of resource allocation, and improves the accuracy of resource allocation, thereby realizing accurate resource allocation for the resource demander.

[0167] In an optional embodiment of the present invention, the similar customer group screening module 610 includes: a customer group resource scoring matrix construction unit, which is used to construct a customer group resource scoring matrix based on the customer group label information and the application label information; a customer group similarity calculation unit, which is used to calculate the customer group similarity between the resource demander and each of the customer groups based on the customer group resource scoring matrix; and a similar customer group screening unit, which is used to screen similar customer groups of the resource demander in the customer groups based on the similarity of each of the customer groups.

[0168] In an optional embodiment of the present invention, the similar customer group screening module 610 further includes: a resource allocation amount change rate acquisition unit, which is used to obtain the resource allocation amount change rate of each similar customer group within a preset time period after screening the similar customer groups of the resource demander in the customer groups according to the similarity of each customer group; and an abnormal customer group elimination unit, which is used to eliminate abnormal customer groups in each similar customer group according to the resource allocation amount change rate.

[0169] In an optional embodiment of the present invention, the initial configuration determination module 620 includes: a first initial configuration determination unit, configured to perform weighted summation on the customer group resource allocation amounts at each of the key time points to obtain the initial resource allocation amount of the resource demander.

[0170] In an optional embodiment of the present invention, the initial configuration determination module 620 includes: a customer group resource configuration amount merging unit, which is used to merge the customer group resource configuration amounts at each of the key time points to obtain the first customer group resource configuration amount, the second customer group resource configuration amount and the third customer group resource configuration amount; a second initial configuration determination unit, which is used to perform weighted summation of the first customer group resource configuration amount, the second customer group resource configuration amount and the third customer group resource configuration amount to obtain the initial resource configuration amount of the resource demander.

[0171] In an optional embodiment of the present invention, the first adjustment coefficient determination module 630 includes: a first label score determination unit, which is used to determine the first label score corresponding to the customer resource configuration label of each dimension according to the customer resource configuration label of each dimension of the similar customer group; a first risk level determination unit, which is used to integrate the first label scores to obtain the first risk level of the resource demander; and a first adjustment coefficient determination unit, which is used to determine the first resource configuration adjustment coefficient according to the first risk level of the resource demander.

[0172] In an optional embodiment of the present invention, the device includes: a second label score determination module, which is used to adjust the initial resource configuration amount of the resource demander according to the first resource configuration adjustment coefficient to obtain the target resource configuration amount, and then obtain the configured resource configuration label of at least one dimension of the resource demander, and determine the second label score corresponding to the configured resource configuration label of each dimension; a second risk level determination module, which is used to integrate each of the second label scores to obtain the second risk level of the resource demander; a second adjustment coefficient determination module, which is used to determine the second resource configuration adjustment coefficient according to the second risk level of the resource demander; and a target configuration adjustment module, which is used to adjust the target resource configuration amount of the resource demander according to the second resource configuration adjustment coefficient.

[0173] The resource configuration device provided in the embodiment of the present invention can execute the resource configuration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0174] In the technical solution of the embodiment of the present invention, the collected information is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0175] Example 4

[0176] According to an embodiment of the present invention, the present invention further provides an electronic device, a readable storage medium and a computer program product.

[0177] Figure 7A schematic diagram of the structure of an electronic device 700 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0178] like Figure 7 As shown, the electronic device 700 includes at least one processor 701, and a memory connected to the at least one processor 701 in communication, such as a read-only memory (ROM) 702, a random access memory (RAM) 703, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 701 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 702 or the computer program loaded from the storage unit 708 into the random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The processor 701, ROM 702 and RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0179] Multiple components in the electronic device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0180] The processor 701 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of the processor 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors for running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 701 executes the various methods and processes described above, such as the resource allocation method.

[0181] In some embodiments, the resource configuration method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by processor 701, one or more steps of the resource configuration method described above may be performed. Alternatively, in other embodiments, processor 701 may be configured to perform the resource configuration method in any other appropriate manner (e.g., by means of firmware).

[0182] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0183] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0184] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0186] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0187] A computing system may include clients and servers. The clients and servers are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS (Virtual Private Server) services.

[0188] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0189] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A resource configuration method, characterized in that: The method comprises: Obtaining at least one dimension of application label information of the resource demander and customer group label information of at least one customer group, and screening similar customer groups of the resource demander from the customer groups based on the customer group label information and the application label information; Obtaining the customer group resource allocation amount of the similar customer group at at least one key time point, and combining the customer group resource allocation amounts at each key time point to obtain the initial resource allocation amount of the resource demander; Obtaining a customer group resource configuration tag of at least one dimension of the similar customer group, and determining a first resource configuration adjustment coefficient based on the customer group resource configuration tags of each dimension of the similar customer group; The initial resource allocation amount of the resource demander is adjusted according to the first resource allocation adjustment coefficient to obtain a target resource allocation amount.

2. The method according to claim 1, characterized in that The step of screening a similar customer group of the resource demander from the customer group according to the customer group tag information and the application tag information includes: Constructing a customer group resource scoring matrix based on the customer group label information and the application label information; Calculating the customer group similarity between the resource demander and each of the customer groups based on the customer group resource scoring matrix; Based on the similarity of each customer group, similar customer groups of the resource demander are screened from the customer groups.

3. The method according to claim 2, characterized in that After screening the customer groups according to the similarities of the customer groups, the method further includes: Obtaining the rate of change of resource allocation amount for each similar customer group within a preset time period; Abnormal customer groups are eliminated from the similar customer groups based on the rate of change of the resource allocation amounts.

4. The method according to claim 1, wherein The customer group resource allocation amounts at each key time point are synthesized to obtain the initial resource allocation amount of the resource demander, including: The customer group resource allocation amounts at each of the key time points are weighted and summed to obtain the initial resource allocation amount of the resource demander.

5. The method according to claim 1, wherein The customer group resource allocation amounts at each key time point are synthesized to obtain the initial resource allocation amount of the resource demander, including: Detecting the number of key data on the amount of customer group resource allocation at each of the key time points; When the number of any key data is less than or equal to the preset number of data, the customer group resource allocation amounts at each key time point are combined to obtain the first customer group resource allocation amount, the second customer group resource allocation amount, and the third customer group resource allocation amount; The resource allocation amount of the first customer group, the resource allocation amount of the second customer group, and the resource allocation amount of the third customer group are weightedly summed to obtain the initial resource allocation amount of the resource demander.

6. The method according to claim 1, characterized in that The determining of the first resource allocation adjustment coefficient according to the customer group resource allocation labels of each dimension of the similar customer group includes: Determining, according to the customer group resource configuration tags of each dimension of the similar customer group, a first tag score corresponding to the customer group resource configuration tag of each dimension; Summarizing the scores of the first tags to obtain a first risk level of the resource demander; A first resource allocation adjustment coefficient is determined according to the first risk level of the resource demander.

7. The method according to claim 1, characterized in that After adjusting the initial resource allocation amount of the resource demander according to the first resource allocation adjustment coefficient to obtain the target resource allocation amount, the method further includes: Obtaining a configured resource configuration tag of at least one dimension of the resource demander, and determining a second tag score corresponding to the configured resource configuration tag of each dimension; Summarizing the second tag scores to obtain a second risk level of the resource demander; determining a second resource allocation adjustment coefficient according to a second risk level of the resource demander; The target resource allocation amount of the resource demander is adjusted according to the second resource allocation adjustment coefficient.

8. A resource allocation device, characterized in that: The device comprises: A similar customer group screening module is used to obtain at least one dimension of application label information of the resource demander and customer group label information of at least one customer group, and screen similar customer groups of the resource demander from the customer groups based on the customer group label information and the application label information; an initial allocation determination module, configured to obtain the customer group resource allocation amount of the similar customer group at at least one key time point, and to synthesize the customer group resource allocation amounts at each of the key time points to obtain the initial resource allocation amount of the resource demander; a first adjustment coefficient determination module, configured to obtain a customer group resource configuration tag of at least one dimension of the similar customer group, and determine a first resource configuration adjustment coefficient based on the customer group resource configuration tags of each dimension of the similar customer group; The initial configuration adjustment module is used to adjust the initial resource configuration amount of the resource demander according to the first resource configuration adjustment coefficient to obtain a target resource configuration amount.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the resource configuration method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the resource configuration method according to any one of claims 1 to 7.

Images