Resource strategy request method and device, electronic equipment and storage medium

Abstract

The invention provides a resource strategy request method and device, electronic equipment and a storage medium, and can be applied to the technical field of digital marketing, the technical field of big data and the technical field of artificial intelligence. Reading project feature data for the target project from a project log storage center; based on the item feature data, calling a calculation engine to calculate and obtain a target curve shape representation parameter and a target consumption level parameter of a target resource consumption curve associated with the target item; generating a curve model of the target resource consumption curve according to the target curve shape representation parameter and the target consumption level parameter; and sending the curve model of the target resource consumption curve to a strategy solving system, so that the strategy solving system returns a resource configuration strategy for the target project to a user based on the curve model.

Description

Technical Field

[0001] The present disclosure relates to the fields of digital marketing technology, big data technology, and artificial intelligence technology, and specifically to a resource policy request method, device, equipment, medium, and program product. Background Art

[0002] In various resource projects, it is usually necessary to predict resource consumption in order to generate resource allocation strategies.

[0003] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related technology: the current strategy generation methods are mostly based on historical scattered data for pattern summary and prediction, which firstly increases the complexity of the prediction, and secondly, the resource consumption pattern data is a series of scattered points, without a specific calculation model and lacks smoothness, which slows down the solution of the downstream strategy solver and reduces the responsiveness of the system. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a resource policy request method, apparatus, device, medium and program product.

[0005] In one aspect of the present disclosure, a resource policy request method is provided, comprising:

[0006] In response to a resource policy request for a target project initiated by a user, reading project feature data for the target project from a project log storage center;

[0007] Based on the project characteristic data, the calculation engine is called to calculate the target curve shape representation parameters and the target consumption magnitude parameters of the target resource consumption curve associated with the target project, wherein the target curve shape representation parameters are used to characterize the morphological change trend of the target resource consumption curve, and the target consumption magnitude parameters are used to characterize the steepness or flatness of the target resource consumption curve;

[0008] Generate a curve model of a target resource consumption curve according to a target curve shape representation parameter and a target consumption magnitude parameter;

[0009] The curve model of the target resource consumption curve is sent to the policy solving system, so that the policy solving system returns the resource configuration policy for the target project to the user based on the curve model.

[0010] According to an embodiment of the present disclosure, generating a curve model of a target resource consumption curve according to a target curve shape representation parameter and a target consumption level parameter includes:

[0011] The target comprehensive shape representation parameters of the target resource consumption curve are calculated according to the target curve shape representation parameters and the target consumption magnitude parameters;

[0012] A curve model for generating a target resource consumption curve according to target comprehensive morphological representation parameters.

[0013] According to an embodiment of the present disclosure, invoking a calculation engine to calculate a target curve shape representation parameter and a target consumption level parameter of a target resource consumption curve associated with a target project includes:

[0014] Input the project feature data into the pre-trained project classification model and output the target project category of the target project;

[0015] Determine target curve shape representation parameters of target resource consumption curve according to target project category;

[0016] The project feature data is input into a pre-trained consumption level prediction model, and the target consumption level parameters of the target resource consumption curve associated with the target project are output.

[0017] According to an embodiment of the present disclosure, determining a target curve shape representation parameter of a target resource consumption curve according to a target project category includes:

[0018] Reading target relational data from M sets of relational data stored in a database, wherein the M sets of relational data correspond to M project categories, and the M sets of relational data are used to characterize curve shape representation parameters corresponding to each of the M project categories, and M is a positive integer;

[0019] According to the target relationship data, the target curve shape representation parameters are determined.

[0020] According to an embodiment of the present disclosure, the M groups of relationship data are constructed by the following method:

[0021] Read N groups of historical delivery data for N historical projects from the project log storage center, where N is a positive integer;

[0022] Calling a predetermined curve fitting algorithm to generate N groups of historical resource consumption curves corresponding to N historical projects based on N groups of historical delivery data, wherein each historical resource consumption curve corresponds to a group of comprehensive morphological representation parameters;

[0023] Calling a predetermined clustering algorithm, clustering N historical projects based on comprehensive morphological representation parameters of each historical resource consumption curve, and obtaining M project clusters, wherein the M project clusters correspond to the M project categories;

[0024] Based on the comprehensive morphological representation parameters associated with the M project clusters, the curve shape representation parameters corresponding to each of the M project categories are determined to construct M groups of relationship data.

[0025] According to an embodiment of the present disclosure, clustering N historical projects based on comprehensive morphological representation parameters of each historical resource consumption curve includes:

[0026] Based on the comprehensive morphological representation parameters of the historical resource consumption curves, determine the curve shape representation parameters and consumption magnitude parameters of each historical resource consumption curve;

[0027] Clustering the N historical items based on the curve shape representation parameters and consumption magnitude parameters of each historical resource consumption curve; or

[0028] The N historical projects are clustered based on curve shape representation parameters of each historical resource consumption curve.

[0029] According to an embodiment of the present disclosure, the project classification model is trained by the following method:

[0030] Read N groups of project feature data for N historical projects from the project log storage center;

[0031] According to N groups of project feature data and the clustering results of N historical projects, a project classification model is trained.

[0032] Another aspect of the present disclosure provides a resource policy request device, including an acquisition module, a calculation module, a generation module, and a sending module.

[0033] The acquisition module is used to read the project feature data for the target project from the project log storage center in response to the resource policy request for the target project initiated by the user;

[0034] A calculation module, for calling a calculation engine to calculate, based on the project characteristic data, a target curve shape representation parameter and a target consumption magnitude parameter of a target resource consumption curve associated with a target project, wherein the target curve shape representation parameter is used to characterize a morphological change trend of the target resource consumption curve, and the target consumption magnitude parameter is used to characterize a steepness or a flatness of the target resource consumption curve;

[0035] A generating module, used for generating a curve model of a target resource consumption curve according to a target curve shape representation parameter and a target consumption magnitude parameter;

[0036] The sending module is used to send the curve model of the target resource consumption curve to the strategy solving system, so that the strategy solving system returns the resource configuration strategy for the target project to the user based on the curve model.

[0037] According to an embodiment of the present disclosure, the generation module includes a calculation unit and a generation unit.

[0038] The calculation unit is used to calculate the target comprehensive shape representation parameter of the target resource consumption curve according to the target curve shape representation parameter and the target consumption level parameter;

[0039] A generating unit is used to generate a curve model of a target resource consumption curve according to target comprehensive morphological representation parameters.

[0040] According to an embodiment of the present disclosure, the calculation module includes a classification unit and a determination unit.

[0041] The classification unit is used to input the project feature data into the pre-trained project classification model and output the target project category of the target project;

[0042] A determination unit, used to determine a target curve shape representation parameter of a target resource consumption curve according to a target project category;

[0043] The prediction unit is used to input the project feature data into a pre-trained consumption level prediction model, and output a target consumption level parameter of a target resource consumption curve associated with the target project.

[0044] According to an embodiment of the present disclosure, the determining unit includes a reading subunit and a first determining subunit.

[0045] The reading subunit is used to read the target relational data from M sets of relational data stored in the database, wherein the M sets of relational data correspond to M types of project categories, and the M sets of relational data are used to characterize the curve shape representation parameters corresponding to each of the M types of project categories, and M is a positive integer;

[0046] The first determination subunit is used to determine the target curve shape representation parameters according to the target relationship data.

[0047] According to an embodiment of the present disclosure, the above-mentioned device also includes a construction module for constructing M groups of relationship data, and the construction module includes a first reading unit, a fitting unit, a clustering unit, and a construction unit.

[0048] The first reading unit is used to read N groups of historical delivery data for N historical projects from the project log storage center, where N is a positive integer;

[0049] A fitting unit, used to call a predetermined curve fitting algorithm to generate N groups of historical resource consumption curves corresponding to N historical projects based on N groups of historical delivery data, wherein each historical resource consumption curve corresponds to a group of comprehensive morphological representation parameters;

[0050] A clustering unit, used for calling a predetermined clustering algorithm, clustering N historical projects based on comprehensive morphological representation parameters of each historical resource consumption curve, and obtaining M project clusters, wherein the M project clusters correspond to the M project categories;

[0051] The construction unit is used to determine the curve shape representation parameters corresponding to each of the M project categories based on the comprehensive morphological representation parameters associated with the M project clusters, so as to construct M groups of relationship data.

[0052] According to an embodiment of the present disclosure, the clustering unit includes a second determining subunit, a first clustering subunit, and a second clustering subunit.

[0053] The second determining subunit is used to determine the curve shape representation parameters and consumption magnitude parameters of each historical resource consumption curve based on the comprehensive morphological representation parameters of the historical resource consumption curve;

[0054] A first clustering subunit is used to cluster the N historical items based on a curve shape representation parameter and a consumption level parameter of each historical resource consumption curve; or

[0055] The second clustering subunit is used to cluster the N historical items based on the curve shape representation parameters of each historical resource consumption curve.

[0056] According to an embodiment of the present disclosure, the above-mentioned device also includes a training module for training to obtain a project classification model, and the training module includes a second reading unit and a training unit.

[0057] The second reading unit is used to read N groups of project feature data for N historical projects from the project log storage center;

[0058] The training unit is used to train a project classification model according to N groups of project feature data and a clustering result of clustering N historical projects.

[0059] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned resource policy request method.

[0060] Another aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the resource policy request method described above.

[0061] Another aspect of the present disclosure further provides a computer program product, including a computer program, which implements the resource policy request method when executed by a processor.

[0062] The embodiment of the present disclosure uses the above-mentioned resource strategy request method, based on the implicit association between project characteristics, resource allocation strategy and project resource consumption curve, to determine the information representation parameters of the target resource consumption curve according to the project characteristics, and then establish a curve model. In this way, the relationship between the total resource consumption of the project and the value of the project single product can be known based on the curve model, so as to formulate a better resource allocation strategy. For a new project, the project characteristics are associated with the project resource consumption curve, and the corresponding resource consumption is directly predicted according to the project-related settings, which is used for project decision makers to set the resource delivery budget, facilitate the algorithm to be tuned in advance, improve the project delivery effect, and reduce the user's use threshold. In the above-mentioned method of the present disclosure, the resource consumption curve model of the project is established based on the project feature data, which can effectively represent the curve's change trend information and the curve's original numerical information. The resource consumption curve model is provided for the downstream solver to solve. On the one hand, when the computer stores project information, it does not need to store a large amount of scattered data, but only needs to store a set of curve parameters, which greatly reduces storage. Moreover, because the function model has regularity and smoothness, it can speed up the calculation speed of the downstream solver, and has higher execution efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0064] Figure 1 The application scenario diagram of the resource policy request method, apparatus, device, medium and program product according to the embodiment of the present disclosure is schematically shown;

[0065] Figure 2 A flowchart of a resource policy request method according to an embodiment of the present disclosure is schematically shown;

[0066] Figure 3 A flowchart of a method for calculating curve parameters of a target resource consumption curve associated with a target project according to an embodiment of the present disclosure is schematically shown;

[0067] Figure 4 A data interaction flow chart of a resource policy request method according to an embodiment of the present disclosure is schematically shown;

[0068] Figure 5 The structure block diagram of the resource policy request device according to the embodiment of the present disclosure is schematically shown;

[0069] Figure 6 A block diagram of an electronic device suitable for implementing a resource policy request method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0070] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0071] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0072] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0073] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0074] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security, and national security.

[0075] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0076] An embodiment of the present disclosure provides a resource policy request method, including:

[0077] In response to a resource policy request for a target project initiated by a user, project characteristic data for the target project is read from a project log storage center; based on the project characteristic data, a computing engine is called to calculate target curve shape representation parameters and target consumption level parameters of a target resource consumption curve associated with the target project, wherein the target curve shape representation parameters are used to characterize the morphological change trend of the target resource consumption curve, and the target consumption level parameters are used to characterize the steepness or flatness of the target resource consumption curve; a curve model of the target resource consumption curve is generated according to the target curve shape representation parameters and the target consumption level parameters; and the curve model of the target resource consumption curve is sent to a policy solving system, so that the policy solving system returns a resource configuration policy for the target project to the user based on the curve model.

[0078] Figure 1 The application scenario diagram of the resource policy request method, apparatus, device, medium and program product according to the embodiments of the present disclosure is schematically shown.

[0079] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0080] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0081] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0082] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0083] In the application scenario of the embodiment of the present disclosure, the user can initiate a request for obtaining a resource configuration policy to the server 105 through the first terminal device 101, the second terminal device 102, and the third terminal device 103. In response to the user request, the server 105 can be used to execute the resource policy request method of the embodiment of the present disclosure, read the project characteristic data for the target project from the project log storage center, and derive the curve parameters of the target resource consumption curve associated with the target project based on the project characteristic data, generate a curve model of the target resource consumption curve, and send the curve model of the target resource consumption curve to the policy solving system, so that the policy solving system returns the resource configuration policy for the target project to the user based on the curve model.

[0084] It should be noted that the resource policy request method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the resource policy request device provided in the embodiment of the present disclosure can generally be set in the server 105. The resource policy request method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the resource policy request device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0085] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0086] The following will be based on Figure 1 The scene described by Figure 2 to Figure 6 The resource policy request method of the disclosed embodiment is described in detail.

[0087] Figure 2 The flowchart of the resource policy request method according to the embodiment of the present disclosure is schematically shown.

[0088] like Figure 2As shown, the resource policy request method of this embodiment includes operations S201 to S204.

[0089] In operation S201, in response to a resource policy request for a target project initiated by a user, project feature data for the target project is read from a project log storage center;

[0090] In operation S202, based on the project characteristic data, a calculation engine is called to calculate a target curve shape representation parameter and a target consumption level parameter of a target resource consumption curve associated with the target project, wherein the target curve shape representation parameter is used to characterize the morphological change trend of the target resource consumption curve, and the target consumption level parameter is used to characterize the steepness or flatness of the target resource consumption curve;

[0091] In operation S203, a curve model of a target resource consumption curve is generated according to the target curve shape representation parameter and the target consumption level parameter;

[0092] In operation S204, the curve model of the target resource consumption curve is sent to the policy solving system, so that the policy solving system returns a resource configuration policy for the target project to the user based on the curve model.

[0093] According to the embodiments of the present disclosure, the above-mentioned resource policy request method can be applied in various resource configuration scenarios. In the resource configuration scenarios, corresponding resource configuration policies need to be formulated.

[0094] For example, in the resource management scenario of the manufacturing industry, for different raw material unit prices and corresponding different resource consumption (project expenditure amounts), it is necessary to formulate a reasonable resource allocation strategy with the ultimate goal of maximizing the ratio of product profit to total material consumption amount (input-output ratio) with the most appropriate material unit price.

[0095] For another example, in an advertising scenario, for different advertising bidding items, corresponding to different resource consumption (total advertising costs), it is necessary to formulate a reasonable resource allocation strategy with the most appropriate advertising bid to maximize the ratio of advertising revenue to total advertising budget (input-output ratio) as the ultimate goal.

[0096] Taking the advertising delivery scenario as an example, when advertisers deliver online ads on online advertising marketing platforms, they usually set the advertising feature data such as the target audience, delivery time period, delivery materials, and advertising bids. When the advertising system receives an ad request, it first parses the user information of the request and obtains the user's features from the feature library, and then matches the series of requested features with the conditions set by the advertiser. For a request, it can usually match multiple ads (called the bidding queue of the request), and these matched ads are sorted according to certain sorting rules (positively correlated with the ad bid), and the ads in the front will get the opportunity to be displayed.

[0097] According to an embodiment of the present disclosure, in operation S201, a project management staff member, as a requesting user, may initiate a resource policy request for a target project to a policy service system.

[0098] In response to user requests, the policy service system reads the project feature data for the target project at the project log storage center. The project feature data may include the project's targeted population, project execution period, project execution region, project single product resource value, etc. The project feature data can be converted into a fixed-length numerical vector for representation, i.e., a feature vector. Taking the advertising delivery scenario as an example, the project feature data may include a series of features such as the targeted population of the advertisement, delivery region, delivery period discount coefficient, delivery product information, etc.

[0099] According to the embodiments of the present disclosure, project features are directly related to resource allocation strategies and have a direct impact on the optimization of resource allocation. For example, during the advertising bidding process, the advertiser's settings, including targeting, bidding, budget and other project features, are important conditions for whether an advertisement can win a display opportunity. So when advertisers are placing advertisements, how can they reasonably set the bids and budgets for each advertisement (the budget will affect whether the advertisement is retrieved and whether it can enter the bidding queue), that is, formulate a reasonable advertising placement strategy, so as to achieve the optimal resource allocation purpose.

[0100] According to the embodiments of the present disclosure, the target resource consumption curve associated with the target project is used to characterize the relationship between the total resource consumption of the project and the change in the value of the project item. There is a one-to-one correspondence between the project characteristics of each project and the project resource consumption curve. The project characteristics determine the type of the project, and the project resource consumption curves corresponding to different project types present different curve shapes.

[0101] Based on the above description, project characteristics are directly related to resource allocation strategies. Since there is a one-to-one correlation between project characteristics and project resource consumption curves, resource allocation strategies can be formulated based on project resource consumption curves. For example, in the advertising scenario, a reasonable resource allocation strategy is formulated to maximize advertising revenue and minimize advertising resource consumption with the most appropriate advertising bid.

[0102] According to an embodiment of the present disclosure, since there is a correlation between project characteristics and project resource consumption curves, in operation S202, based on project characteristic data, a calculation engine is called to calculate information representation parameters of a target resource consumption curve associated with a target project, such as target curve shape representation parameters and target consumption level parameters.

[0103] After determining that the information of the curve represents the curve parameters, the target resource consumption curve can be drawn, and a curve model of the target resource consumption curve, such as a curve function model, can be output.

[0104] According to the embodiments of the present disclosure, after the curve function model is obtained, the parameters of the model can be sent to the policy solving system, so that the policy solving system returns the resource allocation strategy for the target project to the user based on the curve model. For example, historical projects similar to the target project can be found from the massive historical delivery data stored in the project log storage center, and the historical delivery situation can be provided to the decision maker for formulating the resource allocation strategy.

[0105] According to the embodiments of the present disclosure, for projects that have already been launched, they can be further optimized based on historical launch conditions in order to achieve better launch effects. For example, the project resource allocation strategy can be optimized based on the relationship between the total resource consumption of the project and the value of a single item in the project, that is, the resource consumption situation.

[0106] However, for newly built projects (cold start plans), there is no historical investment data. How to know the resource consumption of the project in advance and optimize the resource allocation of the project is a difficult problem.

[0107] Based on this, the embodiment of the present disclosure uses the above method to determine the information representation parameters of the resource consumption curve based on the implicit correlation between project characteristics, resource allocation strategy and project resource consumption curve, and then establish a curve model. In this way, the relationship between the total resource consumption of the project and the value of the project items can be known based on the curve model, so as to formulate a better resource allocation strategy. For new projects, the project characteristics are associated with the project resource consumption curve, and the corresponding resource consumption is directly predicted based on the project-related settings, which is used for project decision makers to set resource delivery budgets, facilitate early algorithm tuning, improve project delivery effects, and lower user usage thresholds.

[0108] In the current strategy generation methods, most of them are based on historical scattered data for regularity summary and prediction. First, it will increase the complexity of prediction. Secondly, the resource consumption regularity data is a series of scattered points, without a specific calculation model and without smoothness, which will slow down the downstream strategy solver and reduce the responsiveness of the system. For example, in the advertising scenario, most of the related technologies extract features based on the relevant settings of the advertisement, and use a single bid as a feature to measure the similarity of advertisements under a single bid, so as to obtain information such as the cost of the advertisement under the bid. For multiple bids, multiple model estimates are used. In this way, not only a large amount of storage is occupied, but also the solution speed is slow.

[0109] In the above method disclosed in the present invention, a resource consumption curve model of a project is established based on project characteristic data, which can effectively represent the change trend information of the curve and the original numerical information of the curve. The resource consumption curve model is provided for solving by a downstream solver. On the one hand, when storing project information, the computer does not need to store a large amount of scattered data, but only needs to store a set of curve parameters, which greatly reduces storage. Furthermore, because the function model has regularity and smoothness, the calculation speed of the downstream solver can be accelerated, and it has higher execution efficiency and accuracy.

[0110] According to an embodiment of the present disclosure, a curve model for generating a target resource consumption curve according to a target curve shape representation parameter and a target consumption level parameter includes:

[0111] Firstly, the target comprehensive shape representation parameters of the target resource consumption curve are calculated according to the target curve shape representation parameters and the target consumption magnitude parameters;

[0112] Afterwards, a curve model of the target resource consumption curve is generated according to the target comprehensive morphological representation parameters.

[0113] According to an embodiment of the present disclosure, the curve model of the target resource consumption curve can adopt a spline function curve model, and the model parameters of the spline function curve model include three parameters: t, c, and k, through which a curve can be uniquely determined. Among them, parameter c is a comprehensive morphological representation parameter, which is used to characterize the overall morphological characteristics of the curve, and parameters t and k are hyperparameters of the curve model, which are customized by the user.

[0114] Furthermore, the comprehensive morphological representation parameter c can be decomposed into a curve shape representation parameter s and a consumption level parameter I, c = I*s. The curve shape representation parameter is used to characterize the morphological change trend of the resource consumption curve, and the consumption level parameter is used to characterize the steepness or flatness of the target resource consumption curve.

[0115] The comprehensive morphological representation parameter c is: composed of multiple c iThe parameter vector composed of . The parameter vector obtained after normalizing the parameter vector c is the curve shape representation parameter s (vector); the maximum value c in the parameter vector c max It represents the consumption level parameter I of the curve.

[0116] According to an embodiment of the present disclosure, after obtaining the target curve shape representation parameters and the target consumption level parameters, the target comprehensive morphological representation parameter c of the target resource consumption curve can be calculated based on c=I*s, and the final curve model parameters of the curve are expressed as (t, c, k).

[0117] According to an embodiment of the present disclosure, a spline function is used as a curve model, and the prediction of the curve can be decomposed into curve shape and curve magnitude prediction by decomposing a parameter vector.

[0118] The scatter-point processing method in the related art may result in similar projects being similar only at a single point, which also results in a large difference between the change trend of the resource consumption curve predicted in the end and the actual change trend. And it cannot guarantee monotonicity. For example, in the advertising project scenario, according to the law of nature, the higher the advertising bid, the higher the total resource consumption of the project. However, the resource consumption curve predicted by the scatter-point processing method is not necessarily a monotonic function. It may result in the final prediction result showing that the resource consumption of the high bid is less than that of the low bid, which is not in line with the law of nature.

[0119] According to the properties of the spline function, the comprehensive morphological representation parameter c is monotonic and non-decreasing, and the resource consumption curve model can strictly guarantee the monotonic and non-decreasing property. Therefore, it can ensure that the changes in project resource consumption obtained by the downstream solver based on the curve model of the resource consumption curve maintain a consistent change pattern with the value of the resource item, which is more in line with the laws of nature, is conducive to the solution of downstream algorithms, improves system efficiency and system fault tolerance, and improves algorithm accuracy and precision.

[0120] Figure 3 The flowchart of a method for calculating curve parameters of a target resource consumption curve associated with a target project according to an embodiment of the present disclosure is schematically shown. Figure 4 The following schematically shows a data interaction flow chart of the resource policy request method according to an embodiment of the present disclosure. Figure 3 , Figure 4 The resource policy request method of the embodiment of the present disclosure is further explained.

[0121] like Figure 3 As shown, the method of this embodiment includes operations S301 to S303.

[0122] In operation S301, the project feature data is input into a pre-trained project classification model, and a target project category of a target project is output;

[0123] In operation S302, a target curve shape representation parameter of a target resource consumption curve is determined according to the target project category;

[0124] In operation S303, the project feature data is input into a pre-trained consumption level prediction model, and a target consumption level parameter of a target resource consumption curve associated with the target project is output.

[0125] like Figure 4 As shown, the system architecture to which the resource policy request method can be applied includes a resource provider client, a resource delivery platform, a project announcement medium, a project log storage center, and a policy service system, wherein the policy service system includes an upstream processing system (not shown in the figure) and a downstream policy solving system (policy solver). The policy service system, as the execution subject of the resource policy request method of the embodiment of the present disclosure, is used to respond to the resource policy request of the project management staff.

[0126] Taking the advertising delivery scenario as an example, when advertisers, as resource providers, deliver online advertisements through the client on the online advertising marketing platform (resource delivery platform), they usually set a series of features (project feature data) such as the targeted population, delivery region, delivery time discount coefficient, delivery product information, etc. When the resource delivery platform receives an advertisement request, it will first parse the user information of the request and obtain the user's features from the feature library, and then match the series of requested features with the conditions set by the advertiser. For a request, it can usually match multiple advertisements (called the bidding queue of the request), and these matched advertisements will be sorted according to certain sorting rules (positively correlated with the advertisement bid), and the advertisements in the front will have the opportunity to be displayed through project announcement media, such as shopping platforms, media platforms, etc.

[0127] Among them, the data in the entire project delivery process, including project feature data, project delivery data (such as advertising bidding data, etc.) is stored in the project log storage center.

[0128] The upstream processing system in the policy service system can read the project feature data from the project log storage center, input the project feature data into a pre-trained project classification model, output the target project category of the target project, and further determine the target curve shape representation parameters of the target resource consumption curve based on the target project category; at the same time, the project feature data is input into a pre-trained consumption level prediction model, and the target consumption level parameters of the target resource consumption curve associated with the target project are output.

[0129] According to the embodiments of the present disclosure, a project type corresponds to a curve shape, and a curve shape corresponds to a curve shape representation parameter; therefore, the project category and the curve shape representation parameter of the model curve have a one-to-one relationship. The target curve shape representation parameter of the target resource consumption curve can be determined according to the target project category, specifically including:

[0130] First, the target relational data is read from M groups of relational data stored in the database, wherein the M groups of relational data correspond to M project categories, and the M groups of relational data are used to characterize the curve shape representation parameters corresponding to each of the M project categories, and M is a positive integer.

[0131] Then, the target curve shape representation parameter is determined based on the target relationship data, that is, the value of the curve shape representation parameter is determined based on the correspondence between the item category and the parameter value.

[0132] Furthermore, if Figure 4 As shown, the item classification model and the consumption level prediction model can be pre-trained.

[0133] Among them, the project classification model is trained by the following method:

[0134] N groups of project feature data for N historical projects are read from a project log storage center; a project classification model is trained based on the N groups of project feature data and a clustering result of clustering the N historical projects.

[0135] The method of clustering N historical items will be described in detail in the subsequent embodiments and will not be described in detail here.

[0136] The clustering result of clustering N historical projects is to label the N historical projects as project category labels. The model is trained according to the N groups of project feature data and project category labels to obtain a project classification model.

[0137] The consumption level prediction model is also constructed through historical data. Specifically, a linear regression model can be constructed based on the project characteristic data of multiple historical projects and the consumption level parameters of the resource consumption curves of these historical projects to obtain a consumption level prediction model, which is used to predict the consumption level parameters of the resource consumption curve of a project based on the project characteristic data of the project.

[0138] The method for determining the consumption level parameter of the resource consumption curve of the historical project will be described in detail in the subsequent embodiments and will not be described in detail here.

[0139] According to an embodiment of the present disclosure, multiple sets of relationship data are stored in the database, that is, the corresponding relationship between the project category and the curve shape representation parameter. The multiple sets of relationship data are constructed by processing the historical delivery data of the historical project. The construction of multiple sets of relationship data needs to be based on the clustering results of multiple historical projects. The following specifically introduces the construction method of M sets of relationship data (including the method of clustering multiple historical projects), including the following operations:

[0140] Operation 11: Read N groups of historical delivery data for N historical projects from the project log storage center, where N is a positive integer.

[0141] Historical investment data may include data such as the value of individual items in historical projects and total project resource consumption.

[0142] For example, in an advertising delivery scenario, advertisers create delivery plans on the advertising delivery platform and deliver ads. Users visit websites / APPs, triggering websites / APPs to submit ad requests to the advertising platform.

[0143] The advertising platform will match a series of corresponding advertisements according to the information of the requested user, rank the series of advertisements by bidding, and return the winning advertisement to the website / APP for display. The plan information (project feature data) established by the advertiser and the data of the entire bidding process (project delivery data) will be recorded in the system log. The project delivery data includes the advertising expenditure under each historical bid.

[0144] For example, Table 1 shows data examples of different bids and corresponding expenditures during the historical delivery of an advertisement.

[0145] Table 1

[0146]

[0147]

[0148] Operation 12: Call a predetermined curve fitting algorithm to generate N groups of historical resource consumption curves corresponding to N historical projects based on N groups of historical delivery data, wherein each historical resource consumption curve corresponds to a group of comprehensive morphological representation parameters.

[0149] According to an embodiment of the present disclosure, based on a spline function curve fitting algorithm, historical delivery data can be read, curve fitting can be performed, a resource consumption scatter curve of a historical delivery plan can be output, and the scatter table can be stored in a database.

[0150] For example, in an advertising delivery scenario, a spline function is used to fit the bid-spending scatter sequence in Table 1 to obtain a curve representation (t, c, k) after fitting, where the same hyperparameters t and k are set for all curves, and each curve can be distinguished by using a comprehensive morphological representation parameter vector c.

[0151] Operation 13: calling a predetermined clustering algorithm to cluster the N historical projects based on the comprehensive form representation parameters of each historical resource consumption curve to obtain M project clusters, wherein the M project clusters correspond to the M project categories;

[0152] Operation 14: Based on the comprehensive morphological representation parameters associated with the M project clusters, determine the curve shape representation parameters corresponding to each of the M project categories to construct M groups of relationship data.

[0153] According to an embodiment of the present disclosure, specifically, clustering N historical projects based on the comprehensive morphological representation parameters of each historical resource consumption curve includes the following operations (including a method for determining the consumption magnitude parameters of the resource consumption curves of the historical projects):

[0154] Operation 21: Based on the comprehensive morphological representation parameters of the historical resource consumption curves, determine the curve shape representation parameters and consumption magnitude parameters of each historical resource consumption curve.

[0155] The comprehensive morphological representation parameter c can be decomposed into the curve shape representation parameter s and the consumption level parameter I, c = I*s. The comprehensive morphological representation parameter c is: i The parameter vector.

[0156] The parameter vector obtained by normalizing the parameter vector c is the curve shape representation parameter s (vector); the maximum value c in the parameter vector c max It represents the consumption level parameter I of the curve.

[0157] Operation 22, clustering, specifically, clustering the N historical items based on the curve shape representation parameters and consumption magnitude parameters of each historical resource consumption curve; or clustering the N historical items based on the curve shape representation parameters of each historical resource consumption curve.

[0158] According to an embodiment of the present disclosure, clustering N historical items based on the curve shape representation parameter and the consumption level parameter of each historical resource consumption curve may be performed by the following method:

[0159] Based on the curve shape representation parameter vector s of each historical resource consumption curve, the similarity values ​​sim1 between each of the N historical items are calculated; for example, a cosine similarity algorithm may be used.

[0160] Based on the absolute difference between the consumption level parameters of each historical resource consumption curve, calculate the similarity value sim2 between each pair of N historical items;

[0161] Sim1 and sim2 are fused to obtain the comprehensive similarity value sim between each two of the N historical items, for example, by using a linear combination for fusion: a*sim1+b*sim2=sim.

[0162] Based on the comprehensive similarity values ​​sim between each pair of N historical projects, the N historical projects are clustered. A variety of clustering algorithms can be used for clustering, such as the K-Means clustering algorithm. Project personnel pre-specify the number of categories K according to their work experience, and clustering is performed based on this.

[0163] According to an embodiment of the present disclosure, the method of clustering N historical projects based on the curve shape representation parameters of each historical resource consumption curve refers to the above embodiment, which will not be described in detail here.

[0164] Based on the above resource policy request method, the present disclosure also provides a resource policy request device. Figure 5 The device is described in detail.

[0165] Figure 5 The structure block diagram of the resource policy request device according to the embodiment of the present disclosure is schematically shown.

[0166] like Figure 5 As shown, the resource policy request device 500 of this embodiment includes an acquisition module 501 , a calculation module 502 , a generation module 503 , and a sending module 504 .

[0167] The acquisition module 501 is used to read the project characteristic data for the target project from the project log storage center in response to the resource policy request for the target project initiated by the user;

[0168] A calculation module 502 is used to call a calculation engine to calculate a target curve shape representation parameter and a target consumption level parameter of a target resource consumption curve associated with a target project based on the project characteristic data, wherein the target curve shape representation parameter is used to characterize a morphological change trend of the target resource consumption curve, and the target consumption level parameter is used to characterize a steepness or a flatness of the target resource consumption curve;

[0169] A generating module 503, configured to generate a curve model of a target resource consumption curve according to a target curve shape representation parameter and a target consumption level parameter;

[0170] The sending module 504 is used to send the curve model of the target resource consumption curve to the policy solving system, so that the policy solving system returns the resource configuration strategy for the target project to the user based on the curve model.

[0171] According to the embodiment of the present disclosure, through the above-mentioned resource strategy request method, through the acquisition module 501, the calculation module 502, and the generation module 503, based on the implicit correlation between the project characteristics, the resource allocation strategy, and the project resource consumption curve, the information representation parameters of the target resource consumption curve can be determined according to the project characteristics, and then a curve model can be established. In this way, the relationship between the total resource consumption of the project and the value of the project items can be known based on the curve model, so as to formulate a better resource allocation strategy. For new projects, the project characteristics are associated with the project resource consumption curve, and the corresponding resource consumption is directly predicted according to the project-related settings, which is used for project decision makers to set resource delivery budgets, facilitate early algorithm tuning, improve project delivery effects, and lower user usage thresholds. In the above method disclosed in the present invention, a resource consumption curve model of a project is established based on project characteristic data, which can effectively represent the change trend information of the curve and the original numerical information of the curve. The resource consumption curve model is provided for solving by a downstream solver. On the one hand, when storing project information, the computer does not need to store a large amount of scattered data, but only needs to store a set of curve parameters, which greatly reduces storage. Furthermore, because the function model has regularity and smoothness, the calculation speed of the downstream solver can be accelerated, and it has higher execution efficiency and accuracy.

[0172] According to an embodiment of the present disclosure, the generation module 503 includes a calculation unit and a generation unit.

[0173] Among them, the calculation unit is used to calculate the target comprehensive form representation parameters of the target resource consumption curve according to the target curve shape representation parameters and the target consumption level parameters; the generation unit is used to generate the curve model of the target resource consumption curve according to the target comprehensive form representation parameters.

[0174] According to an embodiment of the present disclosure, the calculation module includes a classification unit and a determination unit.

[0175] Among them, the classification unit is used to input the project feature data into a pre-trained project classification model, and output the target project category of the target project; the determination unit is used to determine the target curve shape representation parameters of the target resource consumption curve according to the target project category; the prediction unit is used to input the project feature data into a pre-trained consumption level prediction model, and output the target consumption level parameters of the target resource consumption curve associated with the target project.

[0176] According to an embodiment of the present disclosure, the determining unit includes a reading subunit and a first determining subunit.

[0177] Among them, the reading subunit is used to read the target relationship data from M groups of relationship data stored in the database, wherein the M groups of relationship data correspond to M project categories, and the M groups of relationship data are used to characterize the curve shape representation parameters corresponding to each of the M project categories, and M is a positive integer; the first determination subunit is used to determine the target curve shape representation parameters according to the target relationship data.

[0178] According to an embodiment of the present disclosure, the above-mentioned device also includes a construction module for constructing M groups of relationship data, and the construction module includes a first reading unit, a fitting unit, a clustering unit, and a construction unit.

[0179] Among them, the first reading unit is used to read N groups of historical delivery data for N historical projects from the project log storage center, where N is a positive integer; the fitting unit is used to call a predetermined curve fitting algorithm to generate N groups of historical resource consumption curves corresponding to the N historical projects based on the N groups of historical delivery data, wherein each historical resource consumption curve corresponds to a group of comprehensive morphological representation parameters; the clustering unit is used to call a predetermined clustering algorithm to cluster the N historical projects based on the comprehensive morphological representation parameters of each historical resource consumption curve to obtain M project clusters, wherein the M project clusters correspond to M project categories; the construction unit is used to determine the curve shape representation parameters corresponding to each of the M project categories based on the comprehensive morphological representation parameters associated with the M project clusters, so as to construct M groups of relationship data.

[0180] According to an embodiment of the present disclosure, the clustering unit includes a second determining subunit, a first clustering subunit or a second clustering subunit.

[0181] Among them, the second determination subunit is used to determine the curve shape representation parameters and consumption level parameters of each historical resource consumption curve based on the comprehensive morphological representation parameters of the historical resource consumption curve; the first clustering subunit is used to cluster N historical projects based on the curve shape representation parameters and consumption level parameters of each historical resource consumption curve; or the second clustering subunit is used to cluster N historical projects based on the curve shape representation parameters of each historical resource consumption curve.

[0182] According to an embodiment of the present disclosure, the above-mentioned device also includes a training module for training to obtain a project classification model, and the training module includes a second reading unit and a training unit.

[0183] Among them, the second reading unit is used to read N groups of project feature data for N historical projects from the project log storage center; the training unit is used to train a project classification model based on the N groups of project feature data and the clustering results of clustering the N historical projects.

[0184] According to an embodiment of the present disclosure, any multiple modules among the acquisition module 501, the calculation module 502, the generation module 503, and the sending module 504 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 501, the calculation module 502, the generation module 503, and the sending module 504 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, at least one of the acquisition module 501, the calculation module 502, the generation module 503, and the sending module 504 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0185] Figure 6 A block diagram of an electronic device suitable for implementing a resource policy request method according to an embodiment of the present disclosure is schematically shown.

[0186] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0187] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0188] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 606 including a network interface card such as a LAN card, a modem, etc. The communication portion 606 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0189] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0190] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0191] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the resource policy request method provided by the embodiment of the present disclosure.

[0192] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0193] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 606, and / or installed from the removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0194] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 606, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0195] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0196] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0197] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0198] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A resource policy request method, comprising: In response to a resource policy request for a target project initiated by a user, reading project feature data for the target project from a project log storage center; Based on the project characteristic data, a calculation engine is called to calculate a target curve shape representation parameter and a target consumption magnitude parameter of a target resource consumption curve associated with the target project, wherein the target curve shape representation parameter is used to characterize a morphological change trend of the target resource consumption curve, and the target consumption magnitude parameter is used to characterize a steepness or a flatness of the target resource consumption curve; Generate a curve model of the target resource consumption curve according to the target curve shape representation parameter and the target consumption level parameter; The curve model of the target resource consumption curve is sent to a policy solving system, so that the policy solving system returns a resource configuration policy for the target project to the user based on the curve model.

2. The method according to claim 1, wherein: The curve model for generating the target resource consumption curve according to the target curve shape representation parameter and the target consumption level parameter includes: Calculate the target comprehensive shape representation parameter of the target resource consumption curve according to the target curve shape representation parameter and the target consumption level parameter; A curve model of the target resource consumption curve is generated according to the target comprehensive form representation parameters.

3. The method according to claim 1, wherein: The target curve shape representation parameters and target consumption level parameters of the target resource consumption curve associated with the target project are calculated by calling the calculation engine, including: Inputting the project feature data into a pre-trained project classification model, and outputting a target project category of the target project; Determining target curve shape representation parameters of the target resource consumption curve according to the target project category; The project feature data is input into a pre-trained consumption level prediction model, and a target consumption level parameter of a target resource consumption curve associated with the target project is output.

4. The method according to claim 3, wherein: Determining the target curve shape representation parameter of the target resource consumption curve according to the target project category includes: Reading target relationship data from M groups of relationship data stored in a database, wherein the M groups of relationship data correspond to M types of project categories, the M groups of relationship data are used to characterize curve shape representation parameters corresponding to each of the M types of project categories, and M is a positive integer; The target curve shape representation parameters are determined according to the target relationship data.

5. The method according to claim 4, wherein: The M groups of relationship data are constructed by the following method: Read N groups of historical delivery data for N historical projects from the project log storage center, where N is a positive integer; Calling a predetermined curve fitting algorithm to generate N groups of historical resource consumption curves corresponding to the N historical projects based on the N groups of historical delivery data, wherein each of the historical resource consumption curves corresponds to a group of comprehensive morphological representation parameters; Calling a predetermined clustering algorithm to cluster the N historical projects based on the comprehensive morphological representation parameters of each of the historical resource consumption curves to obtain M project clusters, wherein the M project clusters correspond to the M project categories; Based on the comprehensive morphological representation parameters associated with the M project clusters, the curve shape representation parameters corresponding to each of the M project categories are determined to construct the M groups of relationship data.

6. The method according to claim 5, wherein: Clustering the N historical items based on the comprehensive morphological representation parameters of each of the historical resource consumption curves includes: Determining curve shape representation parameters and consumption magnitude parameters of each of the historical resource consumption curves based on the comprehensive morphological representation parameters of the historical resource consumption curves; Clustering the N historical items based on the curve shape representation parameter and the consumption level parameter of each of the historical resource consumption curves; or The N historical items are clustered based on curve shape representation parameters of each of the historical resource consumption curves.

7. The method according to claim 4, wherein: The project classification model is trained by the following method: Read N groups of project feature data for N historical projects from the project log storage center; The project classification model is trained based on the N groups of project feature data and the clustering results of clustering the N historical projects.

8. A resource policy request device, comprising: An acquisition module, configured to read project characteristic data for a target project from a project log storage center in response to a resource policy request for the target project initiated by a user; A calculation module, configured to call a calculation engine to calculate, based on the project characteristic data, a target curve shape representation parameter and a target consumption magnitude parameter of a target resource consumption curve associated with the target project, wherein the target curve shape representation parameter is used to characterize a morphological change trend of the target resource consumption curve, and the target consumption magnitude parameter is used to characterize a steepness or a flatness of the target resource consumption curve; A generating module, configured to generate a curve model of the target resource consumption curve according to the target curve shape representation parameter and the target consumption level parameter; The sending module is used to send the curve model of the target resource consumption curve to the policy solving system, so that the policy solving system returns the resource configuration strategy for the target project to the user based on the curve model.

9. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images