CN115062978A - Weight assignment method, apparatus, computer device, storage medium, and program product - Google Patents

Weight assignment method, apparatus, computer device, storage medium, and program product Download PDF

Info

Publication number
CN115062978A
CN115062978A CN202210683741.9A CN202210683741A CN115062978A CN 115062978 A CN115062978 A CN 115062978A CN 202210683741 A CN202210683741 A CN 202210683741A CN 115062978 A CN115062978 A CN 115062978A
Authority
CN
China
Prior art keywords
historical resource
resource
historical
dimension
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210683741.9A
Other languages
Chinese (zh)
Inventor
张�雄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202210683741.9A priority Critical patent/CN115062978A/en
Publication of CN115062978A publication Critical patent/CN115062978A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present application relates to the field of artificial intelligence technology, and may be used in the field of internet finance and other fields, and is especially weight distributing method, device, computer equipment, storage medium and program product. The method comprises the following steps: acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of all dimensions in a target enterprise; fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between the historical resource structure and the historical resource added value; determining the target resource weight of each dimension according to the response surface model; the target resource weight is the weight which enables the historical resource of each dimension to be added with the largest value. By adopting the method, the resource allocation accuracy and efficiency can be improved.

Description

Weight assignment method, apparatus, computer device, storage medium, and program product
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a weight assignment method, apparatus, computer device, storage medium, and program product.
Background
There are a variety of resources that are typically managed by an enterprise, such as the infrastructure of the enterprise, the products produced by the enterprise, and so forth. When managing resources, the resource increment values need to be estimated from different dimensions (for example, different branches, different departments, different product types, and the like), and the resource amount required by the different dimensions is reasonably distributed according to the estimation result, so that the resource increment value of each dimension is maximized.
In the related art, resources with corresponding quantities are allocated to different dimensions of an enterprise mainly through manual work according to historical experiences. However, the related art method has problems of low resource allocation accuracy and efficiency.
Disclosure of Invention
In view of the above, it is desirable to provide a weight assignment method, apparatus, computer device, storage medium, and program product capable of improving assignment accuracy and assignment efficiency.
In a first aspect, the present application provides a weight assignment method, including:
acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of all dimensions in a target enterprise;
fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between the historical resource structure and the historical resource added value;
determining the target resource weight of each dimension according to the response surface model; the target resource weight is the weight which enables the increment value of the historical resource of each dimension to be maximum.
In one embodiment, obtaining the historical resource added value and the historical resource weight of each dimension based on the historical resource data of each dimension in the target enterprise includes:
acquiring the historical resource occupation amount of each dimension based on the historical resource data of each dimension in the target enterprise;
and determining the historical resource increment value and the historical resource weight of each dimension according to the historical resource occupation amount.
In one embodiment, determining the historical resource increase value of each dimension according to the historical resource occupation amount comprises:
obtaining historical resources of each dimensionality according to the historical resource occupation amount and a preset resource rate;
and determining the historical resource increment value of each dimension according to the historical resource of each dimension.
In one embodiment, determining the historical resource weight of each dimension according to the historical resource occupancy comprises:
acquiring a plurality of historical resource occupancy quantities corresponding to the historical resource data of each dimension based on the historical resource data of each dimension in the target enterprise;
and determining the historical resource weight of each dimension according to the occupation amount of each historical resource and the occupation amount of the historical resources of each dimension.
In one embodiment, fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model of the historical resource structure and the historical resource added value includes:
fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight;
and constructing a response surface model of the historical resource structure and the historical resource added value according to the functional relation.
In one embodiment, the fitting processing is performed on the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight, and the method comprises the following steps:
acquiring a data range of historical resource data of each dimension, and determining the data range as a constraint condition;
fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a function expression between the historical resource added value and the historical resource weight;
and obtaining a functional relation between the historical resource added value and the historical resource weight based on the functional expression and the constraint condition.
In one embodiment, the method further comprises:
obtaining the precision of a historical resource structure and a response surface model of a historical resource added value;
judging whether the precision of the response surface model is greater than a preset precision threshold value or not;
and if the precision of the response surface model is greater than a preset precision threshold, executing a step of determining the target resource weight of each dimension.
In one embodiment, the method further comprises:
if the precision of the response surface model is smaller than or equal to the preset precision threshold, the material mixing design and response surface analysis method is used for continuously carrying out fitting processing on the historical resource added value and the historical resource weight of each dimensionality until the precision of the response surface model is larger than the preset precision threshold.
In one embodiment, determining the target resource weight of each dimension according to the response surface model includes:
performing visual drawing on the response surface model to obtain a response surface curve corresponding to the response surface model;
and determining the weight with the largest historical resource increment value in the response surface curve as the target resource weight of each dimension.
In one embodiment, the method further comprises:
and displaying the target resource weight of each dimension in a preset visual mode.
In a second aspect, the present application further provides a weight assignment device, including:
the first acquisition module is used for acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of all dimensions in a target enterprise;
the first processing module is used for fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between the historical resource structure and the historical resource added value;
the determining module is used for determining the target resource weight of each dimension according to the response surface model; the target resource weight is the weight which enables the historical resource of each dimension to be added with the largest value.
In a third aspect, the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the method steps in any of the embodiments of the first aspect when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the method steps in any of the embodiments of the first aspect.
In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the method steps in any of the embodiments of the first aspect described above.
The method comprises the steps of obtaining historical resource added values and historical resource weights of all dimensions based on historical resource data of all dimensions in a target enterprise, fitting the historical resource added values and the historical resource weights of all dimensions to obtain a response surface model between a historical resource structure and the historical resource added values, and determining the target resource weights of all dimensions according to the response surface model. The target resource weight in the method is the weight which enables the historical resource added value of each dimension to be the maximum, the relation between the historical resource added value and the historical resource weight can be determined more quickly and accurately by fitting the historical resource added value and the historical resource weight of each dimension, the accuracy of a response surface model of a historical resource structure and the historical resource added value is higher, compared with the prior art that the weight is distributed in a manual mode, the efficiency of obtaining the target resource weight of each dimension through the response surface model is higher, and the accuracy of the target resource weight of each dimension is also higher.
Drawings
FIG. 1 is a diagram of an application environment of a weight assignment method in one embodiment;
FIG. 2 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 3 is a schematic flow chart diagram of a weight assignment method in one embodiment;
FIG. 4 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 5 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 6 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 7 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 8 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 9 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 10 is a schematic illustration of a response surface in one embodiment;
FIG. 11 is a schematic illustration of a response surface in one embodiment;
FIG. 12 is a flow diagram illustrating a method for assigning weights in one embodiment;
FIG. 13 is a flow diagram illustrating a method for weight assignment in one embodiment;
FIG. 14 is a flow diagram illustrating a method for weight assignment in one embodiment;
fig. 15 is a block diagram showing the structure of a weight assignment device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that the weight distribution method, apparatus, server, storage medium, and program product of the present application may be applied to the field of artificial intelligence, and may also be applied to other technical fields except the field of artificial intelligence.
The weight distribution method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. The server includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the server is configured to provide computing and control capabilities. The memory of the server comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the server is used for storing data in the weight assignment process. The network interface of the server is used for communicating with an external terminal through network connection. The server may be implemented by an independent server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a method for weight assignment is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s201, acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of multiple dimensions in a target enterprise.
The multiple dimensions specifically refer to the dimensions of mechanisms, departments, products and the like in the target enterprise, and the historical resource data comprises historical resource data corresponding to the mechanism dimensions, historical resource data corresponding to the department dimensions and historical resource data corresponding to the product dimensions. For example, the historical resource data may be resource management data for the past year, the past two years, or the past five years. The historical resource added value may refer to an added value of resources of the target enterprise in different dimensions in a past period, and the historical resource weight may be a resource weight of the target enterprise in different dimensions in a past period. Where a resource may refer to a company's physical entity, virtual or any physical and virtual combination of entities, for example, the resource may be an economy, a product, a device, a cost, and so on. Taking resources as enterprise products as an example, the resource added value herein may refer to the number of products, the cost of the products, the corresponding economy of the products, and the like, and accordingly, the resource weight refers to the percentage of the number of products in different dimensions, the percentage of the cost of the products in different dimensions, and the like. Taking resources as enterprise equipment as an example, the resource added value may refer to the number of the equipment, the operating time of the equipment, the cost of the equipment, and the like, and correspondingly, the resource weight refers to the proportion of the number of the equipment in different dimensions, the proportion of the operating time of the equipment in different dimensions, and the like.
Optionally, different dimensions in the target enterprise correspond to different identification information, identification information of historical resource data in the same dimension is the same, and the server may obtain the historical resource added value and the historical resource weight of each dimension from the database according to the identification information of different dimensions. Optionally, the server may calculate the historical resource increase value of each dimension according to the historical resource data of each dimension by using a calculation formula of the historical resource increase value, and for one of the dimensions, the server obtains a weight between each historical resource data by calculating a ratio of each historical resource data in the one dimension to the total historical resource data in the dimension, and determines the weight as the historical resource weight. In this embodiment, a manner of obtaining the historical resource added value and the historical resource weight of each dimension based on the historical resource data of each dimension in the target enterprise is not limited.
S202, fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between the historical resource structure and the historical resource added value.
The fitting refers to connecting the plurality of historical resource weights through a curve to obtain a curve corresponding to the model between the historical resource added value and the historical resource weight.
Specifically, the historical resource increment value changes continuously with the change of the historical resource weight, and different historical resource weights correspond to different historical resource increment values. And fitting the historical resource added value and the historical resource weight of each dimension once or for multiple times to obtain a response surface model of the historical resource structure and the historical resource added value, wherein N dimensions correspond to N response surface models of the historical resource structure and the historical resource added value. The server can fit the historical resource added value and the historical resource weight of each dimension by a common fitting method to obtain a relational expression between the historical resource added value and the historical resource weight, and a response surface model between the historical resource structure and the historical resource added value is determined according to the relational expression. The fitting method may be a least squares method or an approximate discrete data method, or the like.
S203, determining the target resource weight of each dimension according to the response surface model; the target resource weight is the weight which enables the increment value of the historical resource of each dimension to be maximum.
The target resource weight comprises a target resource weight of an organization dimension, a target resource weight of a department dimension and a historical resource weight of a product dimension.
Specifically, the server may determine the target resource weight with the largest historical resource increment value of a certain dimension by analyzing the response surface model corresponding to the dimension, and generate the result file according to the target resource weight corresponding to each dimension. The target resource weight of the organization dimension refers to the weight occupation proportion of different branches under the condition that the added value of the historical resources is the maximum; the target resource weight of department dimension refers to the weight occupation proportion of different departments under the condition that the added value of the historical resources is the maximum; the target resource weight of the product dimension refers to the weight occupation proportion of different types of products under the condition that the increment value of the historical resources is the maximum.
Further, the server can transmit the target resource weight of the organization dimension to an assessment system corresponding to the organization; the target resource weight of the organization dimension is transmitted to an assessment system corresponding to a department; and transmitting the target resource weight of the product dimension to a corresponding assessment system of the product.
The weight distribution method comprises the steps of obtaining historical resource added values and historical resource weights of all dimensions based on historical resource data of all dimensions in a target enterprise, fitting the historical resource added values and the historical resource weights of all dimensions to obtain a response surface model between a historical resource structure and the historical resource added values, and determining the target resource weights of all dimensions according to the response surface model. The target resource weight in the method is the weight which enables the historical resource added value of each dimension to be the maximum, the relation between the historical resource added value and the historical resource weight can be determined more quickly and accurately by fitting the historical resource added value and the historical resource weight of each dimension, the accuracy of a response surface model of a historical resource structure and the historical resource added value is higher, compared with the prior art that the weight is distributed in a manual mode, the efficiency of obtaining the target resource weight of each dimension through the response surface model is higher, and the accuracy of the target resource weight of each dimension is also higher.
Fig. 3 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of all dimensions in a target enterprise. On the basis of the embodiment shown in fig. 2, as shown in fig. 3, the method may include the following steps:
s301, acquiring the historical resource occupation amount of each dimension based on the historical resource data of each dimension in the target enterprise.
Wherein, the historical resource occupation amount refers to the resource amount occupied in the dimension.
Specifically, when the target enterprise is a bank, the historical resource data of each dimension in the target enterprise includes historical resource data of a bank institution dimension, historical resource data of a department dimension, and historical resource data of a product dimension. In the method of the embodiment, based on the contracts signed by the products, after the historical resource occupation amount of each single contract is obtained through a related calculation formula, the historical resource occupation amounts of the organization dimension, the department dimension and the product dimension in the bank are respectively calculated according to the historical resource occupation amount of each single contract.
The calculation process of the historical resource occupancy of each single contract can be expressed as: and multiplying the net profit of the product in the contract by the correlation coefficient, and taking the obtained product result as the historical resource occupation amount occupied by each contract. Wherein the correlation coefficient may be determined by historical experience. For example, the net profit of a product in a contract is 2, the correlation coefficient is 0.9, and the historical resource occupancy of the contract is 2 × 0.9 — 1.8.
Further, the historical resource occupation amount of the organization dimension, the department dimension and the product dimension is respectively calculated according to the historical resource occupation amount of each single contract. For the organization dimension, the contracts are classified according to different organizations, resources occupied by the contracts signed by the same organization are summed, and the obtained summation result is used as the historical resource occupation amount of the organization dimension. For the department dimension, determining the weight proportion of each department according to the number of people, working hours and other factors paid by different departments on products, distributing the historical resource occupation amount occupied by each single contract according to the weight proportion of each department to obtain the historical resource occupation amount of each department, summing the historical resource occupation amounts of each department, and taking the obtained summation result as the historical resource occupation amount of the department dimension. For the product dimension, classifying all contracts according to the types of the products, summing the historical resource occupation amount of each type of products, and taking the summation result as the historical resource occupation amount of the product dimension.
S302, determining the historical resource increment value and the historical resource weight of each dimension according to the historical resource occupation amount.
Specifically, for one dimension, each dimension includes a plurality of historical resource occupancy amounts, the sum of the plurality of historical resource occupancy amounts is the historical resource occupancy amount of the dimension, the ratio of the plurality of historical resource occupancy amounts to the historical resource occupancy amount of the dimension is calculated, and the plurality of ratios are used as the historical resource weight of the dimension. Meanwhile, the historical resource increase value is the difference between the net profit and the historical resource occupation amount, and the historical resource increase value of a certain dimension is obtained by calculating the difference between the net profit and the historical resource occupation amount of the dimension.
Further, it can be understood that the server may input the historical resource increase value and the historical resource weight of each dimension into a preset anomaly detection model, and filter the historical resource increase value and the abnormal value in the historical resource weight of each dimension through the anomaly detection model to obtain the historical resource increase value and the historical resource weight without anomalies.
According to the weight distribution method, the historical resource occupation amount of each dimension is obtained based on the historical resource data of each dimension in the target enterprise, and the historical resource added value and the historical resource weight of each dimension are determined according to the historical resource occupation amount. The historical resource weight in the method is the ratio of the occupation amount of a plurality of historical resources in one dimension to the occupation amount of the historical resources in the dimension, and a more accurate historical resource increment value and the historical resource weight can be obtained through the occupation amount of the historical resources in each dimension.
Fig. 4 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for determining historical resource increase values of all dimensions according to the historical resource occupation amount. On the basis of the embodiment shown in fig. 3, as shown in fig. 4, the method may include the following steps:
s401, obtaining historical resources of each dimensionality according to the historical resource occupation amount and the preset resource rate.
Specifically, the preset resource rate may be determined through historical experience. For each dimension of the historical resources, the historical resources are equal to the product of the historical resource occupancy and the preset resource rate. For example, when the historical resource occupancy of the organization dimension is 5 and the preset resource rate is 0.15, the historical resource of the organization dimension is 5 × 0.15 — 0.75.
S402, determining the historical resource added value of each dimension according to the historical resource of each dimension.
Specifically, for a dimension, the historical resource increment value of the dimension is the difference between the net profit of the dimension and the historical resource, and the historical resource increment value of each dimension is the difference between the net profit of each dimension and the historical resource. For example, when the historical resources of the organization dimension are 0.75 and the net profit of the organization dimension is 3, the historical resources of the organization dimension are increased by 3-0.75 to 0.25.
According to the weight distribution method, historical resources of all dimensions are obtained according to the historical resource occupation amount and the preset resource rate, and the historical resource added value of each dimension is determined according to the historical resources of each dimension. The historical resource increment value of a certain dimension in the method is the difference value between the net profit of the dimension and the historical resource, and the historical resource increment value of each dimension can be accurately determined through the historical resource.
Fig. 5 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for determining the historical resource weight of each dimension according to the historical resource occupation amount. On the basis of the embodiment shown in fig. 3, as shown in fig. 5, the method may include the following steps:
s501, acquiring a plurality of historical resource occupation amounts corresponding to the historical resource data of each dimension based on the historical resource data of each dimension in the target enterprise.
Specifically, each dimension corresponds to a total historical resource occupancy, and the historical resource occupancy of the dimension includes a plurality of historical resource occupancies. For example, historical resource occupancy for an organization dimension includes multiple historical resource occupancies for different organizations; the historical resource occupancy of department dimension comprises a plurality of historical resource occupancies of different departments; the historical resource occupancy for a product dimension includes a plurality of historical resource occupancies for different products.
Further, optionally, the server may obtain, from the database, a plurality of historical resource occupancy amounts corresponding to the historical resource data of the dimension according to the identification information of the dimension. Optionally, the server may calculate, by using a calculation formula of the management data and the resource occupancy amount, a plurality of historical resource occupancy amounts corresponding to the historical resource data of the dimension. This embodiment is not limited to this.
And S502, determining the historical resource weight of each dimension according to the occupation amount of each historical resource and the occupation amount of the historical resources of the dimension.
Specifically, each historical resource occupation corresponds to one historical resource weight, and the server determines the ratio of each historical resource occupation to the historical resource occupation of the dimension as the historical resource weight of each dimension by calculating the ratio of each historical resource occupation to the historical resource occupation of the dimension. For example, when there are 4 historical resource occupancies in the organization dimension, and the ratios between the 4 historical resource occupancies and the historical resource occupancies of the dimension are 0.2, 0.4, 0.3, and 0.1, respectively, the historical resource weight of the organization dimension is 2: 4: 3: 1.
the weight distribution method comprises the steps of obtaining a plurality of historical resource occupation amounts corresponding to historical resource data of all dimensions in a target enterprise based on the historical resource data of all dimensions, and determining the historical resource weight of all dimensions according to the historical resource occupation amounts and the historical resource occupation amounts of the dimensions. The historical resource weight in the method is the ratio of the occupancy of a plurality of historical resources in one dimension to the occupancy of the historical resources in the dimension, and the historical resource weight of each dimension can be accurately determined through the occupancy of the historical resources.
Fig. 6 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for determining the historical resource weight of each dimension according to the historical resource occupation amount. On the basis of the embodiment shown in fig. 2, as shown in fig. 6, the method may include the following steps:
s601, fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight.
Specifically, the server may use the historical resource weight of each dimension as a factor variable of the mixing design and response surface analysis method, use the historical resource added value of each dimension as a factor index of the mixing design and response surface analysis method, and fit the historical resource added value and the historical resource weight by using the mixing design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight. The factor indexes are used for reflecting resource configuration structures of banks, and the factor indexes of the mechanism dimension refer to historical resource weights of the mechanism dimension; the factor index of the department dimension refers to the historical resource weight of the department dimension; the factor index of the product dimension refers to the historical resource weight of the product dimension.
Illustratively, taking product dimensions as an example, when the product types are A, B, C respectively, x1 is the ratio of resources occupied by a product a to the sum of resources occupied by A, B, C three products, x2 is the ratio of resources occupied by a product B to the sum of resources occupied by A, B, C three products, x3 is the ratio of resources occupied by a product C to the sum of resources occupied by A, B, C three products, and the data of historical resource increment values and historical resource weights of the product dimensions are shown in table 1.
TABLE 1
Figure BDA0003699275450000101
The server may perform data fitting on the data in table 1 through a Quartic mixing Model (Quartic mix Model), and the obtained functional relation between the added value of the historical resource and the weight of the historical resource may be represented as:
EVA i,t ＝β 0 +β 1 x 1,i,t +β 2 x 2,i,t +β 3 x 3,i,t +β 4 x 1,i,t x 2,i,t +β 5 x 2,i,t x 3,i,t +
β 6 x 1,i,t x 3,i,t +β 7 x 1,i,t x 2,i,t (x 1,i,t -x 2,i,t )+β 8 x 2,i,t x 3,i,t (x 2,i,t -x 3,i,t )+
β 9 x 1,i,t x 3,i,t (x 1,i,t -x 3,i,t )+β 10 x 1,i,t 2 x 2,i,t x 3,i,t +β 11 x 1,i,t x 2,i,t 2 x 3,i,t +
β 12 x 1,i,t x 2,i,t x 3,i,t 2 +β 13 x 1,i,t x 2,i,t (x 1,i,t -x 2,i,t ) 2 +β 14 x 2,i,t x 3,i,t (x 2,i,t -x 3,i,t ) 2 +
β 15 x 1,i,t x 3,i,t (x 1,i,t -x 3,i,t ) 2 +ε
wherein, beta is undetermined coefficient of a first-order polynomial to a fourth-order polynomial, i represents a number, t represents a year, epsilon represents residual error of the model, and the four parameters of beta, i, t and epsilon are obtained by historical data fitting calculation.
S602, according to the functional relation, a response surface model of the historical resource structure and the historical resource added value is constructed.
Specifically, the server may input the functional relation to a model construction tool, construct a response surface model of the history resource structure and the history resource added value through the model construction tool, and display the response surface model of the history resource structure and the history resource added value in a visual manner.
The weight distribution method comprises the steps of fitting historical resource added values and historical resource weights of all dimensions by using a material mixing design and response surface analysis method to obtain a functional relation between the historical resource added values and the historical resource weights, and constructing a response surface model of a historical resource structure and the historical resource added values according to the functional relation. According to the method, through fitting processing, the obtained functional relation between the historical resource added value and the historical resource weight is more accurate, so that the response surface model of the historical resource structure and the historical resource added value is more accurate.
Fig. 7 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for obtaining a functional relation between a historical resource added value and a historical resource weight by fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method. On the basis of the embodiment shown in fig. 6, as shown in fig. 7, the method may include the following steps:
s701, acquiring a data range of historical resource data of each dimension, and determining the data range as a constraint condition.
The constraint condition means that in the optimization design, an objective function depends on a design variable, and the value range of the design variable has various limiting conditions. The constraint conditions of the mixing design and response surface analysis method can be expressed as follows:
Figure BDA0003699275450000111
wherein q represents the number of factors considered in the design of the mixed material; s q-1 Is a regular simplex in q-1 dimensional Euclidean space; x is the number of i Is a factor index.
Specifically, the server may obtain the maximum historical resource data and the minimum historical resource data in the historical resource data of a certain dimension, and determine the maximum historical resource data and the minimum historical resource data as the constraint conditions corresponding to the dimension. For example, the maximum and minimum values of the factor indexes are determined according to the data in table 1, so that the constraint condition of the dimension can be determined, and the constraint condition of the dimension is shown in table 2.
TABLE 2
Figure BDA0003699275450000112
Figure BDA0003699275450000121
S702, fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a function expression between the historical resource added value and the historical resource weight.
Specifically, the server may sort the dimensions according to the importance degrees of the dimensions, arrange more important dimensions at a front position, and arrange less important dimensions at a rear position. And fitting the historical resource added values and the historical resource weights of different dimensions according to the arrangement sequence of the dimensions to obtain a function expression between the historical resource added values and the historical resource weights of the dimensions.
S703, obtaining a function relation between the historical resource added value and the historical resource weight based on the function expression and the constraint condition.
Specifically, the functional relation between the historical resource increase value and the historical resource weight includes a functional expression and a constraint condition between the historical resource increase value and the historical resource weight, and the functional relation between the historical resource increase value and the historical resource weight may be represented as:
EVA i,t ＝β 0 +β 1 x 1,i,t +β 2 x 2,i,t +β 3 x 3,i,t +β 4 x 1,i,t x 2,i,t +β 5 x 2,i,t x 3,i,t +
β 6 x 1,i,t x 3,i,t +β 7 x 1,i,t x 2,i,t (x 1,i,t -x 2,i,t )+β 8 x 2,i,t x 3,i,t (x 2,i,t -x 3,i,t )+
β 9 x 1,i,t x 3,i,t (x 1,i,t -x 3,i,t )+β 10 x 1,i,t 2 x 2,i,t x 3,i,t +β 11 x 1,i,t x 2,i,t 2 x 3,i,t +
β 12 x 1,i,t x 2,i,t x 3,i,t 2 +β 13 x 1,i,t x 2,i,t (x 1,i,t -x 2,i,t ) 2 +β 14 x 2,i,t x 3,i,t (x 2,i,t -x 3,i,t ) 2 +
β 15 x 1,i,t x 3,i,t (x 1,i,t -x 3,i,t ) 2 +ε
s.t x 1 +x 2 +x 3 ＝1
0.0205<x 1 <0.8758；0.0319<x 2 <0.8882；0.0913<x 3 <0.9476
the weight distribution method comprises the steps of obtaining a data range of historical resource data of each dimension, determining the data range as a constraint condition, fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a function expression between the historical resource added value and the historical resource weight, and obtaining a function relation between the historical resource added value and the historical resource weight based on the function expression and the constraint condition. According to the method, a function expression between the historical resource added value and the historical resource weight is obtained through a material mixing design and response surface analysis method, and meanwhile, constraint conditions are determined according to the data range of historical resource data, so that the accuracy of the obtained function relation is higher.
Fig. 8 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for judging whether the precision of a response surface model is greater than the preset precision. On the basis of the embodiment shown in fig. 6, as shown in fig. 8, the method may include the following steps:
s801, obtaining the precision of the historical resource structure and the response surface model of the historical resource added value.
Specifically, the accuracy of the response surface model is a judgment condition for determining whether the response surface model satisfies the requirement. The server can calculate the absolute value of the difference value between the output historical resource increment value of the response surface model and the historical actual historical resource increment value, and the accuracy of the response surface model is determined according to the absolute value of the difference value. The larger the absolute value of the difference value between the historical resource increment value and the historical actual resource increment value output by the response surface model is, the lower the precision of the response surface model is; the smaller the absolute value of the difference value between the historical resource increment value output by the response surface model and the historical actual historical resource increment value is, the higher the precision of the response surface model is.
S802, judging whether the precision of the response surface model is larger than a preset precision threshold value.
The preset precision threshold value is determined through historical experience and actual requirements.
Optionally, the server may compare the precision of the response surface model with a preset precision threshold, and if the precision of the response surface model is greater than the preset precision threshold, the response surface model satisfies a preset condition; and if the precision of the response surface model is less than or equal to the preset precision threshold, the response surface model does not meet the preset condition. Optionally, the server may analyze the precision of the response surface model by a reliability analysis method, and determine whether the precision of the response surface model is greater than a preset precision threshold.
And S803, if the precision of the response surface model is greater than a preset precision threshold, executing a step of determining the target resource weight of each dimension.
Specifically, when the precision of the response surface model is greater than a preset precision threshold value, and the response surface model meets a preset condition, determining the weight of the target resource through the response surface model, and calculating the maximum historical resource increase value through the weight of the target resource.
S804, if the precision of the response surface model is smaller than or equal to a preset precision threshold, fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method until the precision of the response surface model is larger than the preset precision threshold.
Specifically, when the precision of the response surface model of a certain dimension is less than or equal to the preset precision threshold, the response surface model does not meet the preset condition, the server may fit the historical resource added value and the historical resource weight of the dimension again by using a material mixing design and response surface analysis method, continue to judge the precision of the response surface model obtained by fitting, and so on, until the precision of the response surface model of the dimension is greater than the preset precision threshold, determine the response surface model greater than the preset precision threshold as the response surface model of the dimension.
The weight distribution method comprises the steps of judging whether the precision of a response surface model is greater than a preset precision threshold value or not by obtaining the precision of the response surface model of a historical resource structure and a historical resource added value, if the precision of the response surface model is greater than the preset precision threshold value, executing the step of determining the target resource weight of each dimension, and if the precision of the response surface model is less than or equal to the preset precision threshold value, continuing to perform fitting processing on the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method until the precision of the response surface model is greater than the preset precision threshold value. According to the method, the accuracy of the response surface model is judged, and the response surface model with the accuracy not meeting the preset accuracy threshold needs to be fitted again, so that the accuracy of the response surface model is higher.
Fig. 9 is a schematic flow chart of a weight assignment method according to an embodiment of the present application. The embodiment of the application relates to an optional implementation mode for determining the target resource weight of each dimension according to a response surface model. On the basis of the embodiment shown in fig. 2, as shown in fig. 9, the method may include the following steps:
and S901, performing visual drawing on the response surface model to obtain a response surface curve corresponding to the response surface model.
Specifically, the server may draw the response surface model corresponding to the response surface model into a graph form through drawing software, so as to obtain a response surface curve corresponding to the response surface model. For example, fig. 10 and 11 are curved surface diagrams of response surfaces of historical resource structures and historical resource added values, in fig. 10, three vertexes of a bottom surface of the curved surface diagram of the response surface correspond to three types of products, the three types of products are A, B and C respectively, an axis perpendicular to the bottom surface corresponds to the historical resource added value, the highest point in the curved surface diagram is a point with the largest resource value, and the proportion of A, B and C corresponding to the point is the optimal weight. The area of the irregular circle in fig. 11 is an increased value of the historical resource corresponding to the different weights of the historical resource.
S902, determining the weight with the largest historical resource increment value in the response surface curve as the target resource weight of each dimension.
For each dimension in the target enterprise, response surface analysis is performed on historical resource data of the dimension to determine a historical resource added value is the largest under which historical resource weight is obtained. Illustratively, by fitting the data in table 1 and table 2, the final target resource weight is a: b: c is 0.5:0.22: 0.28. The target resource weight and the historical resource increment value may be represented in table 3.
TABLE 3
Product dimension x1 x2 x3 Historical resource increment value
Optimal resource structure 0.50 0.22 0.28 1.97
According to the weight distribution method, the response surface model is visually drawn to obtain a response surface curve corresponding to the response surface model, and the weight with the largest historical resource increment value in the response surface curve is determined as the target resource weight of each dimension. According to the method, the response surface model is visually drawn, so that the relation between the historical resource added value and the historical resource weight in the response surface model can be observed more clearly, and the response surface model can be evaluated more clearly from multiple dimensions.
In another embodiment, the present application relates to an alternative implementation of visually presenting weights of target resources. On the basis of the embodiment shown in fig. 2, the method may include: and displaying the target resource weight of each dimension in a preset visual mode.
For example, the highest point in the surface map in fig. 10 is the point with the largest resource value, the ratio of A, B and C corresponding to the point is the optimal weight, the irregular circle with the smallest area in fig. 11 is the point with the largest resource value, and the ratio of A, B and C corresponding to the point is the optimal weight.
According to the weight distribution method, the target resource weight of each dimension is displayed in a preset visual mode. The method visually displays the target resource weight of each dimension, so that the target resource weight of each dimension can be observed more clearly, and the target resource weight of each dimension can be evaluated more clearly from multiple dimensions.
In one embodiment, to facilitate understanding by those skilled in the art, the following detailed description is made of a weight assignment method, which may include, as shown in fig. 12:
s1201, acquiring the historical resource occupation amount of each dimension based on the historical resource data of multiple dimensions in the target enterprise;
s1202, obtaining historical resources of each dimensionality according to the historical resource occupation amount and a preset resource rate;
s1203, determining historical resource added values of all dimensions according to the historical resources of all dimensions;
s1204, acquiring a plurality of historical resource occupancy amounts corresponding to the historical resource data of each dimension based on the historical resource data of each dimension in the target enterprise;
s1205, determining the historical resource weight of each dimension according to the historical resource occupation amount of each historical resource and the historical resource occupation amount of each dimension;
s1206, acquiring a data range of historical resource data of each dimension, and determining the data range as a constraint condition;
s1207, fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a function expression between the historical resource added value and the historical resource weight;
s1208, obtaining a functional relation between the historical resource added value and the historical resource weight based on the functional expression and the constraint condition;
s1209, constructing a response surface model of the historical resource structure and the historical resource added value according to the functional relation;
s1210, acquiring the precision of the historical resource structure and the response surface model of the historical resource added value;
s1211, judging whether the precision of the response surface model is larger than a preset precision threshold value;
s1212, if the precision of the response surface model is greater than a preset precision threshold, executing a step of determining the target resource weight of each dimension;
s1213, visually drawing the response surface model to obtain a response surface curve corresponding to the response surface model;
s1214, determining the weight with the largest historical resource increment value in the response surface curve as the target resource weight of each dimension;
s1215, displaying the target resource weight of each dimension in a preset visual mode;
and S1216, if the precision of the response surface model is smaller than or equal to the preset precision threshold, continuing to perform fitting processing on the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method until the precision of the response surface model is larger than the preset precision threshold.
It should be noted that, for the descriptions in S1201-S1216, reference may be made to the descriptions related to the foregoing embodiments, and the effects thereof are similar, and the description of this embodiment is not repeated herein.
Further, it can be understood that fig. 13 and fig. 14 show a flow chart of the weight distribution method, and fig. 13 shows an overall flow chart of the weight distribution method, first obtaining resource management data and historical resource proportion, and preprocessing the data; and fitting the preprocessed data by using a material mixing design and response surface analysis method to obtain a response surface analysis model, transmitting the response surface analysis model to a service system, and performing difference analysis on an actual operation result and a simulation result of service execution.
Further, fig. 14 is a specific flowchart in the weight distribution method, which is to obtain resource data and historical resource proportions of different organizations, departments, and products of the bank, calculate historical resource added values and total historical resource added values of different dimensions of the different organizations, departments, and products, and remove or perform tail reduction on abnormal observed values existing in the data to obtain preprocessed data. Respectively constructing a material mixing design from different mechanisms, departments and product dimensions, automatically setting an optimization domain according to actual data, designing a reliability response surface scheme, constructing a response surface model by using a big data technology, verifying the precision of the response surface model, transmitting the response surface analysis model to a service system if the precision of the response surface model is greater than preset precision, and performing difference analysis on an actual operation result and a simulation result of service execution; and if the precision of the response surface model is smaller than or equal to the preset precision, continuing to construct the response surface model until the precision of the response surface model is larger than a preset threshold value.
According to the weight distribution method, the target resource weight in the method is the weight which enables the historical resource added value of each dimension to be the largest, the relation between the historical resource added value and the historical resource weight can be determined more quickly and accurately by fitting the historical resource added value and the historical resource weight of each dimension, the accuracy of a response surface model of a historical resource structure and the historical resource added value is higher, compared with the prior art that the weight is distributed in an artificial mode, the speed of obtaining the target resource weight of each dimension through the response surface model is higher, and the accuracy of the target resource weight of each dimension is higher.
It should be understood that, although the steps in the flowcharts related to the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a weight distribution apparatus for implementing the above-mentioned weight distribution method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the weight distribution device provided below can be referred to the limitations of the weight distribution method in the foregoing, and details are not described here.
In one embodiment, as shown in fig. 15, there is provided a weight assignment device including: a first obtaining module 11, a first processing module 12 and a determining module 13, wherein:
the first obtaining module 11 is configured to obtain a historical resource added value and a historical resource weight of each dimension based on historical resource data of each dimension in the target enterprise;
the first processing module 12 is configured to perform fitting processing on the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between the historical resource structure and the historical resource added value;
the determining module 13 is configured to determine target resource weights of the dimensions according to the response surface model; the target resource weight is the weight which enables the historical resource of each dimension to be added with the largest value.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the first obtaining module includes: a first obtaining unit and a first determining unit, wherein:
the first acquisition unit is used for acquiring the historical resource occupation amount of each dimension based on the historical resource data of each dimension in the target enterprise;
and the first determining unit is used for determining the historical resource increasing value and the historical resource weight of each dimension according to the historical resource occupation amount.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
Optionally, the first determining unit is configured to obtain historical resources of each dimension according to the historical resource occupation amount and a preset resource rate; and determining the historical resource increment value of each dimension according to the historical resource of each dimension.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
Optionally, the first determining unit is further configured to obtain, based on the historical resource data of each dimension in the target enterprise, a plurality of historical resource occupancy amounts corresponding to the historical resource data of each dimension; and determining the historical resource weight of each dimensionality according to the historical resource occupation amount and the historical resource occupation amounts of different dimensionalities.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the first processing module includes: a processing unit and a building unit, wherein:
the processing unit is used for fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight;
and the construction unit is used for constructing a response surface model of the historical resource structure and the historical resource added value according to the functional relation.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
Optionally, the processing unit is configured to obtain a data range of the historical resource data of each dimension, and determine the data range as a constraint condition; fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a function expression between the historical resource added value and the historical resource weight; and obtaining a functional relation between the historical resource added value and the historical resource weight based on the functional expression and the constraint condition.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the weight assigning apparatus further includes: second acquisition module, judge module and execution module, wherein:
the second acquisition module is used for acquiring the precision of the historical resource structure and the response surface model of the historical resource added value;
the judging module is used for judging whether the precision of the response surface model is greater than a preset precision threshold value;
and the execution module is used for executing the step of determining the target resource weight of each dimension under the condition that the precision of the response surface model is greater than a preset precision threshold.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the weight distribution apparatus further includes a second processing module, wherein:
and the second processing module is used for continuously performing fitting processing on the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method under the condition that the precision of the response surface model is less than or equal to a preset precision threshold value until the precision of the response surface model is greater than the preset precision threshold value.
The weight distribution device provided in this embodiment may implement the method embodiments described above, and the implementation principle and technical effect are similar, which are not described herein again.
In one embodiment, the determining module includes: a second acquisition unit and a second determination unit, wherein:
the second acquisition unit is used for performing visual drawing on the response surface model to obtain a response surface curve corresponding to the response surface model;
and the second determining unit is used for determining the weight with the largest historical resource increment value in the response surface curve as the target resource weight of each dimension.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
In one embodiment, the weight distribution apparatus further includes a display module, wherein:
and the display module is used for displaying the target resource weight of each dimension in a preset visual mode.
The weight distribution apparatus provided in this embodiment may implement the method embodiments described above, and the implementation principle and the technical effect are similar, which are not described herein again.
The respective modules in the weight distribution apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In an embodiment, a computer device is provided, comprising a memory in which a computer program is stored and a processor, which when executing the computer program realizes the method steps of any of the above method embodiments.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, realizes the method steps of any of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the method steps of any one of the above-mentioned method embodiments.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware that is instructed by a computer program, and the computer program may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (14)

1. A method of weight assignment, the method comprising:
acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of the dimensions in a target enterprise;
fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between a historical resource structure and the historical resource added value;
determining the target resource weight of each dimensionality according to the response surface model; the target resource weight is the weight which enables the resource increment value of each dimensionality to be maximum.
2. The method of claim 1, wherein obtaining historical resource increase values and historical resource weights for each dimension based on historical resource data for a plurality of dimensions in a target enterprise comprises:
acquiring the historical resource occupation amount of each dimension based on the historical resource data of each dimension in the target enterprise;
and determining the historical resource added value and the historical resource weight of each dimensionality according to the historical resource occupation amount.
3. The method of claim 2, wherein said determining historical resource increase values for each of said dimensions based on said historical resource occupancy comprises:
obtaining historical resources of each dimensionality according to the historical resource occupation amount and a preset resource rate;
and determining the historical resource increment value of each dimension according to the historical resources of each dimension.
4. The method of claim 2, wherein said determining historical resource weights for each of said dimensions based on said historical resource occupancy comprises:
acquiring a plurality of historical resource occupation amounts corresponding to the historical resource data of each dimension based on the historical resource data of each dimension in the target enterprise;
and determining the historical resource weight of each dimension according to the historical resource occupation amount of each dimension and the historical resource occupation amount of each dimension.
5. The method according to any one of claims 1 to 4, wherein the fitting process of the historical resource increase value and the historical resource weight of each dimension to obtain a response surface model of a historical resource structure and the historical resource increase value includes:
fitting the historical resource added value and the historical resource weight of each dimension by using a material mixing design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight;
and constructing a response surface model of the historical resource structure and the historical resource added value according to the functional relation.
6. The method according to claim 5, wherein the fitting process is performed on the historical resource added value and the historical resource weight of each dimension by using a mixed material design and response surface analysis method to obtain a functional relation between the historical resource added value and the historical resource weight, and the method includes:
acquiring a data range of historical resource data of each dimension, and determining the data range as a constraint condition;
fitting the historical resource added value and the historical resource weight of each dimension by using the material mixing design and response surface analysis method to obtain a function expression between the historical resource added value and the historical resource weight;
and obtaining a functional relation between the historical resource added value and the historical resource weight based on the functional expression and the constraint condition.
7. The method of claim 5, further comprising:
obtaining the precision of the historical resource structure and the response surface model of the historical resource added value;
judging whether the precision of the response surface model is greater than a preset precision threshold value or not;
and if the precision of the response surface model is greater than a preset precision threshold, executing a step of determining the target resource weight of each dimension.
8. The method of claim 7, further comprising:
if the precision of the response surface model is smaller than or equal to the preset precision threshold, fitting the historical resource added value and the historical resource weight of each dimension by using the material mixing design and response surface analysis method until the precision of the response surface model is larger than the preset precision threshold.
9. The method according to any one of claims 1-4, wherein determining a target resource weight for each of the dimensions according to the response surface model comprises:
performing visual drawing on the response surface model to obtain a response surface curve corresponding to the response surface model;
and determining the weight with the maximum increment value of the historical resources in the response surface curve as the target resource weight of each dimension.
10. The method according to any one of claims 1-4, further comprising:
and displaying the target resource weight of each dimension in a preset visualization mode.
11. An apparatus for assigning weights, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical resource added values and historical resource weights of all dimensions based on historical resource data of the dimensions in a target enterprise;
the first processing module is used for fitting the historical resource added value and the historical resource weight of each dimension to obtain a response surface model between the historical resource structure and the historical resource added value;
the determining module is used for determining the target resource weight of each dimensionality according to the response surface model; the target resource weight is the weight which enables the increment value of the historical resource of each dimensionality to be the maximum.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 10 when executing the computer program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 10.
14. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 10 when executed by a processor.
CN202210683741.9A 2022-06-17 2022-06-17 Weight assignment method, apparatus, computer device, storage medium, and program product Pending CN115062978A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210683741.9A CN115062978A (en) 2022-06-17 2022-06-17 Weight assignment method, apparatus, computer device, storage medium, and program product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210683741.9A CN115062978A (en) 2022-06-17 2022-06-17 Weight assignment method, apparatus, computer device, storage medium, and program product

Publications (1)

Publication Number Publication Date
CN115062978A true CN115062978A (en) 2022-09-16

Family

ID=83203307

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210683741.9A Pending CN115062978A (en) 2022-06-17 2022-06-17 Weight assignment method, apparatus, computer device, storage medium, and program product

Country Status (1)

Country Link
CN (1) CN115062978A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115618748A (en) * 2022-11-29 2023-01-17 支付宝(杭州)信息技术有限公司 Model optimization method, device, equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115618748A (en) * 2022-11-29 2023-01-17 支付宝(杭州)信息技术有限公司 Model optimization method, device, equipment and storage medium
CN115618748B (en) * 2022-11-29 2023-05-02 支付宝(杭州)信息技术有限公司 Model optimization method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
Azman et al. The accuracy of preliminary cost estimates in Public Works Department (PWD) of Peninsular Malaysia
Drew et al. The effect of client and type and size of construction work on a contractor’s bidding strategy
US7472084B2 (en) Method and apparatus for creating and managing a visual representation of a portfolio and determining an efficient allocation
Dosi et al. Production theory: accounting for firm heterogeneity and technical change
US8050959B1 (en) System and method for modeling consortium data
CA2611748A1 (en) System and method for risk assessment and presentment
Gan et al. A data mining framework for valuing large portfolios of variable annuities
Naldi et al. Profit-fairness trade-off in project selection
US20150269668A1 (en) Voting mechanism and multi-model feature selection to aid for loan risk prediction
Cosenza et al. Hierarchy models for the organization of economic spaces
Kaczmarska et al. Quantifying the sources of simulation uncertainty in natural catastrophe models
Rusydiana et al. Financial and social efficiency on indonesian Islamic banks
CN115062978A (en) Weight assignment method, apparatus, computer device, storage medium, and program product
US20120185326A1 (en) Contact stream optimization using fec and cc constraints
Gaspars-Wieloch The use of a modification of the Hurwicz’s decision rule in multicriteria decision making under complete uncertainty
JP2021111281A (en) Business operator classification device, method, program, business operator evaluation system, and credit risk evaluation system
Di Persio et al. An ambit stochastic approach to pricing electricity forward contracts: The case of the German energy market
de Llano Monelos et al. DEA as a business failure prediction tool Application to the case of galician SMEs
Pine et al. An Examination of Accidental‐Release Scenarios from Chemical‐Processing Sites: The Relation of Race to Distance
Giudici Integration of qualitative and quantitative operational risk data: A Bayesian approach
Todorov et al. Efficient quasi-Monte Carlo methods for multiple integrals in option pricing
Anande-Kur et al. Determinants of capital structure in the Nigerian manufacturing sector
Mwiya et al. Construction unit rate factor modelling using neural networks
Greberg et al. Using Gradient Boosting to Identify Pricing Errors in GLM-Based Tariffs for Non-life Insurance
Videira The Synergic Entropy. An efficient frontier output derived from merged input units boosted by synergy and constrained by critical input

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination