CN112422711A

CN112422711A - Resource allocation method and device, electronic equipment and storage medium

Info

Publication number: CN112422711A
Application number: CN202011232898.7A
Authority: CN
Inventors: 李秋博; 吕龙云; 李晓东
Original assignee: Beijing 58 Information Technology Co Ltd
Current assignee: Beijing 58 Information Technology Co Ltd
Priority date: 2020-11-06
Filing date: 2020-11-06
Publication date: 2021-02-26
Anticipated expiration: 2040-11-06
Also published as: CN112422711B

Abstract

The invention provides a resource allocation method, a resource allocation device, electronic equipment and a storage medium. The method comprises the following steps: receiving a resource request instruction aiming at a target object, wherein the resource request instruction comprises a user identifier triggering the resource request instruction and an identifier of the target object; acquiring historical behavior data corresponding to the user identification and attribute information of the target object, and acquiring the conversion rate of the resource request instruction through a preset conversion rate prediction model according to the historical behavior data and the attribute information; responding to the fact that the conversion rate is higher than a preset probability threshold value, obtaining resources corresponding to the resource request instruction from a preset resource pool, and establishing a binding relation between the resources and the target object, wherein the resource pool comprises at least one resource; the conversion rate prediction model is obtained by training historical behavior data of a plurality of sample users with known connection states. Therefore, the method has the advantages of reducing abnormal conditions such as incapability of communication and the like, improving the resource utilization rate and saving the operation cost of the resource pool.

Description

Resource allocation method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a resource allocation method and apparatus, an electronic device, and a storage medium.

Background

A Resource Pool (Resource Pool) refers to a collection of various hardware and software involved in a cloud computing data center, and may be divided into computing resources, storage resources, and network resources according to the types of the hardware and software. The resource pool ID (Identity document) represents a unique identifier of a type of resource. Taking a virtual phone as an example, a resource pool containing at least one virtual phone may be set.

The virtual telephone is a telecommunication service integrating multiple functions of conversation, fax, message leaving, e-mail, short message, call forwarding, automatic paging, password protection and the like. When a user uses a virtual telephone, a virtual number needs to be allocated to realize communication between two terminals. For example, when a merchant posts, a virtual number may be allocated to the merchant in order to protect the real number of the merchant, and when the client user views the corresponding merchant post, the client user may contact the corresponding merchant through the virtual number of the corresponding merchant.

The existing method for allocating virtual numbers generally binds real numbers and virtual numbers one to one, and when resources in a virtual number pool do not meet the binding relationship of the real numbers enough, the earliest binding relationship needs to be unbound, so that the number pool resources are reused.

However, since it is not known whether a connection will be generated in the relation to be unbundled, especially in a high QPS (Query Per Second) scenario, the direct unbundling method increases the probability of failing to dial, and in extreme cases such as when the traffic triggering the binding scenario increases, connection failures such as unsuccessful dialing in a large range may occur, and then if the number pool capacity is increased to meet the binding requirement without limit, the cost may increase rapidly.

Disclosure of Invention

Embodiments of the present invention provide a resource allocation method, an apparatus, an electronic device, and a storage medium, so as to solve the problems of a low connection failure probability, a low resource utilization rate, and a low resource pool operation cost.

In order to solve the technical problem, the invention is realized as follows:

in a first aspect, an embodiment of the present invention provides a resource allocation method, including:

receiving a resource request instruction aiming at a target object, wherein the resource request instruction comprises a user identifier for triggering the resource request instruction and an identifier of the target object;

acquiring historical behavior data corresponding to the user identification and attribute information of the target object, and acquiring the conversion rate of the resource request instruction through a preset conversion rate prediction model according to the historical behavior data and the attribute information;

responding to the fact that the conversion rate is higher than a preset probability threshold value, obtaining resources corresponding to the resource request instruction from a preset resource pool, and establishing a binding relationship between the resources and the target object, wherein the resource pool comprises at least one resource;

the conversion rate prediction model is obtained by training historical behavior data of a plurality of sample users with known connection states.

Optionally, the step of obtaining the resource corresponding to the resource request instruction from a preset resource pool includes:

searching unbound resources from the resource pool, and taking any one unbound resource as a resource corresponding to the resource request instruction;

responding to the fact that no unbound resources exist in the resource pool, and obtaining the current conversion rate of each binding relation through the conversion rate prediction model;

and releasing the binding relation with the minimum conversion rate, and taking the resource corresponding to the currently released binding relation as the resource corresponding to the resource request instruction.

Optionally, the resource request instruction further includes a request parameter, and the step of obtaining a resource corresponding to the resource request instruction from a preset resource pool includes:

generating a resource pool identifier of the resource request instruction according to the request parameter and a data format condition of a preset resource pool identifier;

according to the resource pool identification and the preset priority of each resource pool, acquiring a target resource pool corresponding to the resource pool identification from the resource pools, and acquiring resources corresponding to the resource request instruction from the target resource pool;

the data format condition comprises at least one of a data type of a resource pool identifier, service parameters contained in the resource pool identifier, a data length of each service parameter in the resource pool identifier and a sequence of each service parameter in the resource pool identifier; the request parameter comprises at least one of a service category, a request channel type, a flow source identifier, a city identifier and a user identifier.

Optionally, the step of obtaining the resource corresponding to the resource request instruction from the target resource pool includes:

responding to the situation that no unbound resources exist in the target resource pool, and acquiring the current conversion rate of each binding relationship through the conversion rate prediction model;

Optionally, before the step of obtaining the historical behavior data corresponding to the user identifier and the attribute information of the target object, and obtaining the conversion rate of the resource request instruction according to the historical behavior data and the attribute information and through a preset conversion rate prediction model, the method further includes:

acquiring historical behavior data of each sample user, and performing data cleaning on the historical behavior data of the sample users;

extracting data characteristics of the historical behavior data after data cleaning, and training a preset machine learning model through the data characteristics;

and responding to the trained machine learning model passing a preset performance test, and taking the machine learning model as the conversion rate prediction model, wherein the performance test comprises at least one of an online test and an offline test.

Optionally, the resource includes a virtual number, and the method further includes:

receiving a call request, wherein the call request comprises a virtual number;

and acquiring a calling object which has a binding relation with the virtual number, and calling the calling object.

In a second aspect, an embodiment of the present invention provides a resource allocation apparatus, including:

the instruction receiving module is used for a resource request instruction, and the resource request instruction comprises a user identifier for triggering the resource request instruction and an identifier of the target object;

the conversion rate obtaining module is used for identifying corresponding historical behavior data and attribute information of the target object, and obtaining the conversion rate of the resource request instruction through a preset conversion rate prediction model according to the historical behavior data and the attribute information;

a resource obtaining module, configured to, in response to that the conversion rate is higher than a preset probability threshold, obtain a resource corresponding to the resource request instruction from a preset resource pool, and establish a binding relationship between the resource and the target object, where the resource pool includes at least one resource;

Optionally, the resource obtaining module includes:

the first resource acquisition submodule is used for searching unbound resources from the resource pool and taking any one unbound resource as a resource corresponding to the resource request instruction;

the conversion rate obtaining submodule is used for responding to the fact that unbound resources do not exist in the resource pool, and obtaining the current conversion rate of each binding relationship through the conversion rate prediction model;

and the second resource obtaining submodule is used for removing the binding relation with the minimum conversion rate and taking the resource corresponding to the currently removed binding relation as the resource corresponding to the resource request instruction.

Optionally, the resource obtaining module includes:

the resource pool identification generation submodule is used for generating the resource pool identification of the resource request instruction according to the request parameter and the data format condition of the preset resource pool identification;

a third resource obtaining submodule, configured to obtain, according to the resource pool identifier and according to a preset priority of each resource pool, a target resource pool corresponding to the resource pool identifier from the resource pool, and obtain, from the target resource pool, a resource corresponding to the resource request instruction;

Optionally, the third resource obtaining sub-module is specifically configured to:

Optionally, the apparatus further comprises:

the training data processing module is used for acquiring historical behavior data of each sample user and cleaning the historical behavior data of the sample users;

the model training module is used for extracting the data characteristics of the historical behavior data after data cleaning and training a preset machine learning model through the data characteristics;

and the model testing module is used for responding that the trained machine learning model passes a preset performance test and taking the machine learning model as the conversion rate prediction model, wherein the performance test comprises at least one of an online test and an offline test.

Optionally, the resource includes a virtual number, and the apparatus further includes:

a call request receiving module, configured to receive a call request, where the call request includes a virtual number;

and the call processing module is used for acquiring a call object which has a binding relationship with the virtual number and calling the call object.

In a third aspect, an embodiment of the present invention additionally provides an electronic device, including: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the resource allocation method according to the first aspect.

In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the steps of the resource allocation method according to the first aspect.

In the embodiment of the invention, the binding relation between the resources such as the virtual number and the like and the object is determined and the resources are distributed in a machine learning conversion rate pre-estimation mode. Therefore, the method has the advantages that the occurrence probability of abnormal conditions such as incapability of communication and the like under limited resources is greatly reduced, the utilization rate of each resource is improved, and the operation cost of the resource pool is saved.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive labor.

FIG. 1 is a flowchart illustrating steps of a method for allocating resources according to an embodiment of the present invention;

FIG. 2 is a flow chart of steps of another resource allocation method in an embodiment of the present invention;

FIG. 3 is a flow chart of steps of another method of resource allocation in an embodiment of the present invention;

FIG. 4 is a diagram illustrating a structure of data types identified by a resource pool in an embodiment of the present invention;

FIG. 5 is a flow chart illustrating a resource allocation process according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a resource allocation apparatus in an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of another resource allocation apparatus in an embodiment of the present invention;

fig. 8 is a schematic diagram of a hardware structure of an electronic device in the embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, a flowchart illustrating steps of a resource allocation method according to an embodiment of the present invention is shown.

Step 110, receiving a resource request instruction for a target object, where the resource request instruction includes a user identifier for triggering the resource request instruction and an identifier of the target object;

step 120, obtaining historical behavior data corresponding to the user identifier and attribute information of the target object, and obtaining a conversion rate of the resource request instruction according to the historical behavior data and the attribute information through a preset conversion rate prediction model; the conversion rate prediction model is obtained by training historical behavior data of a plurality of sample users with known connection states.

Step 130, in response to that the conversion rate is higher than a preset probability threshold, acquiring a resource corresponding to the resource request instruction from a preset resource pool, and establishing a binding relationship between the virtual number and the real number of the target object, where the resource pool includes at least one resource.

In the embodiment of the invention, the problem of resource distribution imbalance such as resource unavailability or resource waste is solved under the limited resource pool resources, and the operation cost of the number pool is saved, so that the overall experience of the user and the platform is improved. After receiving the resource request instruction each time and before allocating the resource to the resource request instruction, the conversion rate of the current resource request instruction, that is, the probability that the user triggering the corresponding resource request instruction uses the corresponding resource, may be estimated through a preset conversion rate prediction model, for example, in the case where the resource is a virtual phone, the conversion rate may be the probability of dialing a virtual number. And only if the conversion rate is higher than a preset probability threshold value, allocating resources for the corresponding resource request instruction. In different application scenarios, specific contents included in the resource may be set by user according to requirements, and the embodiment of the present invention is not limited thereto. For example, in the scenario of allocating access network paths, in order to protect the network path of the target object (e.g., a confidential website), a virtual access path may be covered for the network path, and then the resource at this time may be a virtual network path, in the scenario of allocating identification codes such as two-dimensional codes and bar codes, the resource may be a user identification code, in the scenario of a virtual telephone system, the resource may be a virtual number, and so on.

Specifically, a resource request instruction for a target object may be received, where the resource request instruction includes a user identifier that triggers the resource request instruction and an identifier of the target object; further, historical behavior data corresponding to the user identifier and attribute information of the target object can be acquired, so that the conversion rate of the resource request instruction is acquired through a preset conversion rate prediction model according to the historical behavior data corresponding to the user identifier, the attribute information of the target object and the historical behavior data and the attribute information; responding to the fact that the conversion rate is higher than a preset probability threshold value, obtaining resources corresponding to the resource request instruction from a preset resource pool, and establishing a binding relationship between the resources and the target object, wherein the resource pool comprises at least one resource; the conversion rate prediction model is obtained by training historical behavior data of a plurality of sample users with known connection states.

In the embodiment of the present invention, the user may trigger the resource request instruction in any available manner, which is not limited to this embodiment of the present invention. For example, in the context of a virtual phone system, a user views a contact address of a target object (e.g., a business, an individual user, etc.) through a client, for example, views a post sent by the target object and containing the contact address, views an order of the target object and containing the contact address, etc., and the corresponding user may trigger a resource request instruction for the corresponding target object, and so on.

For the same user, when the same user requests to view the contact way of the same target object each time, the resource request instruction for the corresponding target object is triggered once, that is, when the same user requests to view the contact way of the same target object each time, different virtual numbers are allocated to the corresponding target object, or the resource request instruction for the corresponding target object is triggered once only when the contact way of the same target object is viewed for the first time, then when the same user views the contact way of the same target object again in the following, the virtual number allocated to the same target object for the first time can be directly returned, that is, when the same user requests to view the contact way of the same target object each time, the same virtual number is allocated to the corresponding target object; or, for the same target object of the same user, triggering a resource request instruction for the corresponding target object once every N consecutive times of checking the contact way of the target object, and then after triggering the resource request instruction for the corresponding target object each time, when the same user repeatedly checks the contact way of the same target object N-1 consecutive times, directly returning the virtual number allocated to the same user for the latest time, that is, when the same user continuously requests to check the contact way of the same target object N times, the same virtual number is allocated to the corresponding target object, and the specific value of N may be set by user according to the requirement, generally, N may be an integer greater than 2.

And the resource request instruction comprises a user identifier for triggering the resource request instruction and an identifier of the target object. For example, if the user triggers the resource request instruction by viewing a post made by a certain merchant, the identification of the target object at this time may be the corresponding merchant, and particularly, the merchant identification of the corresponding merchant may be included in the resource request instruction.

The historical behavior data may include any historical behavior data related to any conversion rate that may be obtained, and the embodiment of the present invention is not limited thereto. For example, the historical behavior data may include a history of browsed content corresponding to the corresponding user identifier (e.g., content, category, heat, number of posts viewed), attribute information of an object to which each post viewed by the user identifier belongs (e.g., any information related to the object itself such as name, category, location, heat, score, etc. of the corresponding object), a history of resources used in the history (e.g., dialing a contact in the post viewed by the user, that is, a history of posts connected to the object corresponding to the post viewed by the user). In addition, the historical behavior data according to the requirement may also include attribute information of the corresponding user identifier corresponding to the user, such as the user name, gender, occupation, age, hobby, location, and the like.

Furthermore, in the embodiment of the present invention, the historical behavior data corresponding to the user identifier and the attribute information of the target object may be obtained in any available manner, which is not limited in the embodiment of the present invention.

In order to improve the accuracy of the estimated conversion rate, a machine learning model can be trained in advance through historical behavior data of a plurality of sample users with known connection states to obtain a conversion rate prediction model. The conversion rate prediction model may be any available machine learning model, and the embodiment of the present invention is not limited thereto. For example, the conversion rate prediction model may be a linear model, a neural network model (e.g., a fully-connected neural network model, a convolutional neural network model, a recurrent neural network model, etc.), a Logistic Regression model (LR), a Naive bayes model (Naive Bayesian, NB), an integration model, a Regression-related model, etc. The known connection state may be understood as whether the corresponding sample user uses (for example, dials a virtual number, establishes a social relationship with the virtual number, accesses a network path, and the like) the resource allocated to the corresponding sample user each time in the historical behavior data.

Under the condition that the conversion rate of the current resource request instruction is higher than the preset probability threshold, a resource which is not bound, namely is in an idle state at present, can be randomly acquired from a resource pool comprising at least one resource, and is used as a resource corresponding to the resource request instruction, namely a resource corresponding to a corresponding user identifier and a target object, and a binding relationship between the corresponding resource and the corresponding target object can be established, so that the corresponding target object can be connected when the corresponding resource is used by a user in the following process. For example, in the case that the resource is a virtual number, specifically, when the user dials a corresponding virtual number, the corresponding target object may be called by calling a real number of the corresponding target object based on a binding relationship between the corresponding virtual number and the corresponding target object. Moreover, when the binding relationship is established, the binding relationship between the corresponding virtual number and the real number of the corresponding target object can also be directly established, so that the real number with the binding relationship is called when the virtual phone is dialed according to the binding relationship directly, and the target object is further called, and the embodiment of the invention is not limited.

The specific value of the preset probability threshold may be set by a user according to a requirement, generally speaking, the value of the preset probability threshold may be a decimal between 0 and 1, for example, the preset probability threshold may be set to 0.8, 0.9, and the like, and the embodiment of the present invention is not limited thereto.

Secondly, in the embodiment of the present invention, for each resource in the resource pool, in order to further improve the resource utilization rate, each resource reuse may be further set, and specifically, for each bound resource, if it is not used within a preset time period after being bound (for example, the virtual number is not dialed), or the number of times of being used within the preset time period after being bound is lower than a preset number, the binding relationship of the corresponding resource may be released, or the binding relationship of the corresponding resource may be cancelled when the bound resource is used for the preset number of times after being bound, so as to release the corresponding resource, so that the corresponding resource may be repeatedly used, and improve the resource utilization rate.

Referring to fig. 2, in the embodiment of the present invention, a resource corresponding to the resource request instruction may be acquired from a preset resource pool in the following manner:

step A1, searching unbound resources from the resource pool, and using any one unbound resource as a resource corresponding to the resource request instruction;

step A2, responding to the resource pool without unbound resource, obtaining the current conversion rate of each binding relationship through the conversion rate prediction model;

and step A3, removing the binding relation with the minimum conversion rate, and taking the resource corresponding to the currently removed binding relation as the resource corresponding to the resource request instruction.

In practical applications, in order to reduce the operation cost of the resource pool, the resources included in the resource pool are generally limited, and therefore, in the process of resource allocation, the resources may be used up, that is, all the resources are bound, and in order to avoid situations such as unavailability or connection errors, the same resource is generally not bound to multiple objects at the same time.

When acquiring the resource corresponding to the resource request instruction from a preset resource pool, first, the unbound resource may be searched from the resource pool, and any unbound resource is used as the resource corresponding to the resource request instruction. Specifically, the unbound resource may be searched from the resource pool, and if an unbound resource is found, the search operation is stopped, and the currently found unbound resource is directly used as the resource corresponding to the resource request instruction. Of course, all the unbound resources may be searched from the resource pool, and any one of the unbound resources may be used as the resource corresponding to the resource request instruction, which is not limited in this embodiment of the present invention.

If there is no unbound resource in the resource pool, that is, each resource is bound, in order to allocate a resource to the current resource request instruction, the bound resource in the resource pool needs to be unbound to reuse the resource, and a new binding relationship is established.

When the current conversion rate of each binding relationship is obtained through the conversion rate prediction model, the user identifier and the object identifier corresponding to the corresponding binding relationship may be obtained, and then the historical behavior data of the corresponding user identifier and the attribute information corresponding to the corresponding object identifier are obtained, so as to obtain the conversion rate corresponding to the corresponding binding relationship according to the historical behavior data and the attribute information, which is similar to the step 120 described above and is not repeated here.

In addition, in the embodiment of the present invention, it may also be set that the conversion rate of the released binding relationship needs to be not greater than the conversion rate of the currently received resource request instruction, at this time, before the binding relationship is released, it may also be compared whether the conversion rate of the binding relationship in which the conversion rate is the smallest is not greater than the conversion rate of the currently received resource request instruction, if so, step a3 is executed, otherwise, the binding relationship does not need to be released, and resources may not be allocated to the corresponding resource request instruction.

Referring to fig. 3, in the embodiment of the present invention, if a plurality of resource pools with different priorities are preset, a resource corresponding to the resource request instruction may also be acquired from a preset resource pool in the following manner:

step B1, generating a resource pool identifier of the resource request instruction according to the request parameter and a data format condition of a preset resource pool identifier;

step B2, according to the resource pool identification, according to the preset priority of each resource pool, obtaining a target resource pool corresponding to the resource pool identification from the resource pool, and obtaining a resource corresponding to the resource request instruction from the target resource pool; the data format condition comprises at least one of a data type of a resource pool identifier, service parameters contained in the resource pool identifier, a data length of each service parameter in the resource pool identifier and a sequence of each service parameter in the resource pool identifier; the request parameter comprises at least one of a service category, a request channel type, a flow source identifier, a city identifier and a user identifier.

In the embodiment of the present invention, in order to flexibly and quickly assign different resource pools according to request parameters of service logic and context to allocate resources such as virtual numbers to a currently received resource request instruction, a plurality of resource pools may be preset, and resource pool identifiers (resource pool IDs) and priorities of the resource pools may be set according to application ranges and the like of the resource pools, and in a case where a resource request instruction is received, a resource pool identifier of the resource request instruction may be generated according to the request parameters and according to data format conditions of the resource pool identifiers, and further, according to the resource pool identifier, according to preset priorities of the resource pools, a target resource pool corresponding to the resource pool identifier may be sequentially searched from the resource pools of different priorities, and a resource corresponding to the resource request instruction may be searched from the target resource pool, and at this time, the resources corresponding to the resource request instruction may be obtained from a plurality of target resource pools respectively, and then in order to determine the final resource, the resource with the highest priority of the target resource pool may be further obtained from the searched resources as the final resource corresponding to the resource request instruction.

For example, in the case that the service application scenario is a virtual telephone system, the number of the merchant issuing the post needs to be covered with an intermediate number to achieve the purpose of protecting the merchant, or the number of the user of the takeaway ordering user needs to be covered with an intermediate number to achieve the purpose of protecting the user. Therefore, a plurality of resource pools can be set, and the resource contained in each resource pool is the middle number. The intermediate number is a virtual number used by the virtual operator to cover the real number of the merchant.

The virtual number included in each resource pool, the priority of each resource pool, the data format condition of the resource pool identifier, the content specifically included in the request parameter, and the like may be set and adjusted in a user-defined manner according to the requirements, and the embodiment of the present invention is not limited thereto.

For example, in a service application scenario of a virtual phone system, a plurality of different users may request to acquire an intermediary number of a merchant, and in order to provide a sufficient intermediary number for each merchant, at least one dedicated resource pool, that is, a dedicated pool of the merchant, may be set for each merchant, and in addition, a resource pool available to the merchant in a corresponding province, that is, a province shared pool, may be set for each province according to a region where the merchant is located, and a resource pool available to all nationwide merchants, that is, a nationwide shared pool, may be set, and priorities of different types of resource pools may be sequentially the dedicated pool of the merchant, the province shared pool, and the nationwide shared pool. In the embodiment of the invention, one or more special merchant pools can be set for the same merchant, one or more special merchant pools can be set for the same province, one or more common national pools can be set, and of course, one or more of the special merchant pools, the common province pools and the common national pools can be set, and the resource pool identifications of different resource pools can be different from each other so as to distinguish different resource pools. Generally speaking, resources included in different resource pools do not overlap with each other to improve resource utilization, and of course, according to special requirements, there may be partially overlapped resources in some resource pools, which is not limited in this embodiment of the present invention.

Secondly, in practical applications, for a part of resource request instructions, due to the lack of request parameters or the fact that resources in each resource pool are occupied, the resources cannot be acquired based on the resource pool, and the efficiency of resource allocation may be affected. Therefore, in the embodiment of the present invention, in order to avoid the above problem, at least one resource pool serving as a bottom may be additionally set according to a requirement, and the priority of the corresponding resource pool may be set to be the lowest.

In the embodiment of the present invention, the user may trigger the resource request instruction in any available manner, and may obtain the request parameter of the resource request instruction in any available manner, which is not limited in the embodiment of the present invention. Furthermore, the data format condition may include, but is not limited to, at least one of a data type of the resource pool identifier, a service parameter included in the resource pool identifier, a data length of each of the service parameters in the resource pool identifier, and an ordering of each of the service parameters in the resource pool identifier.

For example, the data type of the resource pool identifier may be set to be int (integer, integer type) type of 32 bits (4 bytes), or the data type of the resource pool identifier may also be set to be Long (Long integer type), Short (Short integer type), or the like; the service parameters that can be set in the resource pool identification include, but are not limited to, redundancy parameters, context extension parameters (rankId), region parameters, service type parameters, and the like.

Furthermore, where the resource pool ID is a 32-bit int type, the data type can be viewed as 32 grids, and each interval can define a corresponding service parameter. For example, the service type parameter may be located at 0 to 5 bits of the int type, and may support at most 32 service type parameters, and the service type parameters corresponding to different service types may be set by user according to requirements, which is not limited in the embodiment of the present invention. For example, the business type parameter of the merchant-specific pool may be set to 1, the business type parameter of the common pool may be set to 2, and so on. The regional parameters can be 6-11 bits in the resource pool identifier, at this time, 64 kinds of regional parameters can be supported at most, for example, the national regional parameters can be set to 0, and the like; the context extension parameters can be 12-18 bits in the resource pool identifier, and at this time, at most 128 context extension parameters can be supported; the redundant parameter can be used for subsequent expansion, the redundant parameter can be 19-31 bits in the resource pool identification, for example, if a resource pool of a region with finer granularity needs to be supported subsequently, for example, a resource pool in a city or a county, the resource pool ID of different resource pools can be expanded from the redundant parameter. Fig. 4 is a diagram of a resource pool ID of int type of 32 bits. Of course, in the embodiment of the present invention, service parameters included in the resource pool identifier, the data length of each service parameter in the resource pool identifier, the ordering of each service parameter in the resource pool identifier, and the like may be set by a user according to requirements, which is not limited in the embodiment of the present invention.

After the resource pool identifier of the current resource request instruction is generated, a target resource pool corresponding to the resource pool identifier may be obtained from the resource pools according to the resource pool identifier and the preset priority of each resource pool, and a resource corresponding to the resource request instruction may be obtained from the target resource pool.

For example, if the priority of the resource pool is set as a merchant exclusive pool, a province shared pool, and a national shared pool in sequence, as shown in fig. 5, a merchant exclusive pool corresponding to the resource pool identifier of the current resource request instruction may be first searched in each merchant exclusive pool, and then a resource corresponding to the corresponding resource request instruction may be searched in the merchant exclusive pool corresponding to the resource pool identifier, if a resource corresponding to the corresponding resource request instruction is found in the corresponding merchant exclusive pool, the current resource allocation process may be ended, and if a resource corresponding to the corresponding resource request instruction is not found in the corresponding merchant exclusive pool, a province shared pool corresponding to the resource pool identifier of the current resource request instruction may be continuously searched in each province shared pool of the next priority, and then a resource corresponding to the corresponding resource request instruction may be searched in the province shared pool corresponding to the resource pool identifier, if the resource corresponding to the corresponding resource request instruction is found in the corresponding provincial shared pool, the current resource allocation process can be ended, if the resource corresponding to the corresponding resource request instruction is not found in the corresponding provincial shared pool, the global shared pool corresponding to the resource pool identifier of the current resource request instruction can be continuously found in each global shared pool of the next priority, and then the resource corresponding to the corresponding resource request instruction is found in the global shared pool corresponding to the resource pool identifier, if the virtual number corresponding to the corresponding resource request instruction is found in the corresponding global shared pool, the current resource allocation process can be ended, if the resource corresponding to the corresponding resource request instruction is not found in the corresponding global shared pool, the resource corresponding to the corresponding resource request instruction can be found in the resource pool as the bottom of pocket, and then the current resource allocation flow is ended.

Or, the merchant exclusive pool, the province shared pool and the national shared pool corresponding to the current resource pool identifier can be directly and simultaneously searched from each merchant exclusive pool, province shared pool and national shared pool of different priorities, so that the resource corresponding to the current resource request instruction is searched from the merchant exclusive pool, the province shared pool and the national shared pool corresponding to the current resource pool identifier, the resource with the highest priority of the resource pool to which the resource belongs can be obtained from the searched resource, the resource is used as the resource finally corresponding to the corresponding resource request instruction, and the current resource allocation process is ended.

For example, if the resources corresponding to the current resource request instruction are respectively searched from the merchant exclusive pool, province shared pool and national shared pool corresponding to the current resource pool identifier and are sequentially resource a, resource b and resource c, the resource a searched from the merchant exclusive pool with the highest priority can be used as the final corresponding resource of the corresponding resource request instruction.

If the resources corresponding to the current resource request instruction are not searched in the merchant exclusive pool, the province shared pool and the national shared pool corresponding to the current resource pool identifier, the resources corresponding to the corresponding resource request instruction can be searched in the resource pool serving as the bottom of the pocket by referring to the above, and then the current resource allocation process is ended.

Optionally, in this embodiment of the present invention, a specific process of generating a resource pool identifier may include the following steps:

step C1, according to the data type of the resource pool identifier and the mapping relationship between the request parameter and the service parameter contained in the resource pool identifier, for any one of the service parameters, converting the request parameter having the mapping relationship with the service parameter into a parameter representation form supported by the data type;

step C2, according to the data length of each service parameter in the resource pool identifier and the sequence of each service parameter in the resource pool identifier, combining the parameter representation form of each service parameter to obtain the resource pool identifier of the resource request instruction.

In practical application, the data form of the request parameter corresponding to the resource request instruction may not satisfy the data form required by the data type of the resource pool identifier, for example, when the data type of the resource pool identifier is an int type, the request parameter may be represented by a non-binary character, and then the request parameter needs to be converted into a binary representation form under the int type. For example, under the condition that the service parameter includes a context extension parameter, and the request parameter includes a service category, a request channel type, and a traffic source identifier, in order to obtain a representation form of the context extension parameter in the resource pool identifier, a specific value of the current context extension parameter needs to be determined according to the service category, the request channel type, the traffic source identifier, and the like in the request parameter and a corresponding relationship between the preset request parameter and the context extension parameter, such as the service category, the request channel type, the traffic source identifier, and the like, instead of directly converting the representation form of the request parameter, such as the service category, the request channel type, the traffic source identifier, and the like, into a binary representation form.

In practical application, in order to determine a specific value of each service parameter, a mapping relationship between each request parameter and each service parameter included in the resource pool identifier may be predefined according to a requirement, and then, for any service parameter included in the resource pool identifier, a request parameter having a mapping relationship with a corresponding service parameter may be determined according to the mapping relationship between the request parameter and the service parameter included in the resource pool identifier, and then, according to the mapping relationship between the request parameter and the service parameter, the corresponding request parameter may be converted into a parameter representation form supported by the data type of the resource pool identifier. The mapping relationship between the request parameter and the service parameter included in the resource pool identifier may be set by user according to requirements, and the embodiment of the present invention is not limited.

For example, assuming that the service parameters include a context extension parameter, a region parameter, and the like, the request parameters include a city identifier, a service category, a request channel type, a traffic source identifier, and the like, a mapping relationship exists between the region parameter and the city identifier, a mapping relationship exists between the context extension parameter and the service category, the request channel type, and the traffic source identifier, and the data type of the resource pool identifier is an int type, assuming that the city identifier obtained currently is 20 in decimal representation and represents beijing, the city identifier may be converted into a parameter representation form supported by the int type for obtaining, for example, the binary representation form described above, to obtain the region parameter.

For the context extension parameters, it is assumed that the mapping relationship between the set context extension parameters and the service category, the request channel type, and the traffic source identifier includes the following contents:

rankId (decimal representation)	spm (flow source mark)	clientType (request channel type)	cateId (Business class)
				1	cst_thhz.*	2	29
2	escand_oppo\|escand_vivo	3	4929

The traffic source identifier may represent an identifier of a traffic source of the corresponding triggered resource request instruction, for example, "cst _ thhz" represents that the traffic source of the triggered resource request instruction is an advertisement slot common to the car owners, and "escand _ OPPO | escand _ VIVO" represents that the traffic source of the triggered resource request instruction is an advertisement slot of the fast application OPPO or VIVO, and the like; the request channel type may be understood as a channel type triggering a corresponding resource request triggering instruction, such as a model, a brand, an operating system of a client triggering the corresponding resource request triggering instruction, and the like, and the service category may be understood as a service type to which the resource request triggering instruction belongs, such as a used car (29), a truck (4929), a rental house, a part-time, and the like.

Under the condition that the service type, the request channel type and the traffic source identifier are known, the corresponding rankId can be obtained by referring to the mapping relation, and the obtained rankId which may be represented by a decimal system can be further converted into a parameter representation form required by the data type meeting the resource pool identifier, such as the binary representation form.

After obtaining the parameter representation forms of the service parameters, the parameter representation forms of the service parameters may be combined according to the data length of each service parameter in the resource pool identifier and the sequence of each service parameter in the resource pool identifier, so as to obtain the resource pool identifier of the resource request instruction.

For example, assuming that the data length of each service parameter in the resource pool identifier and the sequence of each service parameter in the resource pool identifier are as shown in fig. 4, the parameter representation form of each service parameter may be inserted into the 32 grids shown in fig. 4 according to the corresponding position to obtain the resource pool identifier of int type.

Optionally, in an embodiment of the present invention, the step C2 further includes:

step C21, according to the data length of each service parameter in the resource pool identification and the sequence of each service parameter in the resource pool identification, combining the parameter representation form of each service parameter to obtain the character sequence of the resource pool identification meeting the data type;

step C22, converting the character sequence into a resource pool identifier in a specified format, and obtaining the resource pool identifier of the resource request instruction.

In the embodiment of the invention, in order to meet business requirements when performing multi-dimensional warehouse-sharing storage on resources, that is, when setting resource pools, resource pools under different dimensions supporting different businesses, different merchants, different cities, different provinces and the like are set, and it is convenient to quickly locate currently required resources in subsequent use processes, different resource pool identifiers need to be set for different resource pools, and in order to improve the dimensions supported by the resource pool identifiers, the resource pool identifiers can be set to 32-bit int types to support the naming range of each resource pool during multi-dimensional warehouse-sharing storage.

In addition, in the embodiment of the present invention, in the process of dividing the resource pools and setting the resource pool identifiers of the resource pools, the resource pool identifiers of the corresponding resource pools may also be set with reference to request parameters, service parameters, and the like, which are applicable to the corresponding resource pools, and the embodiment of the present invention is not limited thereto.

However, when resource pool identifiers of respective resource pools are set, if the resource pool identifiers are expressed by 32-bit int types, since the numerical values contained therein may only be 0 or 1 and the data length is long, matching errors are likely to occur when appropriate target resource pools are screened from the respective resource pools according to the resource pool identifiers of the resource request instructions in the following, thereby affecting the efficiency and accuracy of the resource pool search process.

Therefore, in the embodiment of the present invention, in the process of generating the resource pool identifier of the resource request instruction, after the character sequence of the resource pool identifier that satisfies the data type is obtained by combining the parameter representation forms of each service parameter, the character sequence is further converted into the resource pool identifier in the specified format, so as to obtain the resource pool identifier of the resource request instruction.

The specified format can be set by self-definition according to requirements, and the embodiment of the invention is not limited. For example, the designated format may be set to be a decimal format, and then, in the case that the data type of the initially set resource pool identifier is an int type of 32 bits, the data type is converted into decimal data, so that the data length of the resource pool identifier may be effectively shortened, and the included numerical value may be an integer between 0 and 9, so that the error rate after the subsequent resource pool searching process may be effectively reduced, and the resource pool searching efficiency may be improved.

For example, assuming that the resource pool ID is an int type with 32 bits, the service type parameter is located at 0-5 bits, the region parameter is 6-11 bits, the context extension parameter is 12-18 bits, and the redundancy parameter is 19-31 bits, under the condition that each service parameter is known, the specified format is a decimal format, and the final resource pool identifier can be obtained as shown in the following table.

Service type parameter	Regional parameters	rankId	Computing&Combined process	Character sequence	Conversion result
							1	1	1	0<<18\|1<<11\|1<<5\|1	100000100001	2081
2	1	1	0<<18\|1<<11\|1<<5\|2	100000100010	2082
						2	0	1	0<<18\|1<<11\|0<<5\|2	100000000010	2050

It should be noted that, in the above table, the representation forms of the service type, the region parameter, and the context extension parameter are decimal forms, and may be converted into binary forms meeting the int type in the calculation and combination processes, or may be converted into binary forms before combination, which is not limited in the embodiment of the present invention.

Optionally, in the embodiment of the present invention, the service parameter includes at least one of a redundancy parameter, a context extension parameter, a region parameter, and a service type parameter, and the request parameter includes at least one of a service category, a request channel type, a traffic source identifier, a city identifier, and a user identifier.

The redundant parameters may include any other required parameters, where the content included in the redundant parameters may be set by a user according to a requirement, for example, in order to support a resource pool of a finer-grained region, the redundant parameters may include the city and county identifier described above, so as to expand a resource pool ID of the city and county resource pool, and so on; the regional parameter can be understood as a parameter for characterizing a region, such as a parameter for characterizing a province of a merchant, a parameter for characterizing a province of a user, and the like; the service type parameter may be a parameter characterizing a service type, for example, a parameter characterizing a service to which the resource request instruction belongs, and the like.

When the request parameter is known, for example, when cateId (service type), clientType (request channel type), spm (traffic source identifier), cityId (city identifier), userId (user identifier), etc. are known, the resource pool ID of the resource pool can be calculated.

For example, the request parameters may be as shown in the following table:

cateId	29 (second hand vehicle)
		spm	cst_thhz_db_record
clientType	2(iOS)
		cityId	1 (Beijing)

Optionally, in this embodiment of the present invention, in a case that the service parameter includes a context extension parameter, the request parameter includes at least one of a service category, a request channel type, and a traffic source identifier, and the step C1 further includes: and acquiring a parameter representation form of the context expansion parameter in the resource pool identifier according to at least one of the service category, the request channel type and the flow source identifier.

In the embodiment of the present invention, if the target resource pools corresponding to the resource pool identifiers are all searched from the resource pools with different priorities at the same time to further determine the resource corresponding to the resource request instruction, it may happen that multiple resources belonging to the target resource pools with different priorities are found, but in the actual application process, only one of the resources may need to be returned, for example, the resource found from the target resource pool with the highest priority is finally obtained and returned, then the resources found from the target resource pools with other priorities do not actually play a role at this time, and it is not necessary to obtain the target resource pools with other priorities, and it is also not necessary to find the resource from the target resource pools with other priorities. Therefore, resource waste is caused, and the time consumption of the resource searching process is long.

Therefore, in this embodiment of the present invention, optionally, in order to further improve the efficiency of resource allocation and allocate the most appropriate resource for the resource request instruction, when obtaining a target resource pool corresponding to the resource pool identifier from the resource pools according to the resource pool identifiers and preset priorities of the resource pools, and searching for a resource corresponding to the resource request instruction from the target resource pool, the following steps may be executed to obtain a final resource by referring to the priorities of the resource pools:

s1, aiming at the resource pool identification, searching a target resource pool corresponding to the resource pool identification from the resource pool with the highest priority which is not traversed currently, if the target resource pool corresponding to the resource pool identification is searched, executing the step S2, if the target resource pool corresponding to the resource pool identification is not searched, returning to the step S1 until the resource pools with all priorities are traversed;

s2, searching the resources corresponding to the resource request instruction from the currently searched target resource pool, responding to the acquisition of the resources corresponding to the resource request instruction from the target resource pool, executing the step S3, responding to the non-acquisition of the resources corresponding to the resource request instruction from the target resource pool, returning to the step S1 until the resource pools with all priorities are traversed and finished, and finishing the process;

s3, returning to the resource, and ending the process.

For example, assuming that the priority of the resource pool is, from high to low, a merchant exclusive pool, a province shared pool, and a country shared pool in sequence, after the resource pool identifier is generated, the process shown in fig. 5 may be executed to obtain the resource, specifically, after the request parameter is obtained, the current resource pool identifier may be obtained based on the request parameter, and then a target resource pool corresponding to the corresponding resource pool identifier is searched in each merchant exclusive pool and a resource corresponding to the resource request instruction is searched from the target resource pool, if the resource corresponding to the resource request instruction is obtained by searching, the process is ended and the corresponding resource is returned; if the resource is not found, that is, the target resource pool corresponding to the corresponding resource pool identifier is not found in each dedicated merchant pool, or the target resource pool corresponding to the corresponding resource pool identifier is found in each dedicated merchant pool, but the resource corresponding to the resource request instruction is not found in the current target resource pool, the target resource pool corresponding to the corresponding resource pool identifier can be further found in each province shared pool and the resource corresponding to the resource request instruction is found in the corresponding target resource pool, and if the resource corresponding to the resource request instruction is found, the process is ended and the corresponding resource is returned; if the resource is not found, that is, the target resource pool corresponding to the corresponding resource pool identifier is not found in each province shared pool, or the target resource pool corresponding to the corresponding resource pool identifier is found in each province shared pool, but the resource corresponding to the resource request instruction is not found in the current target resource pool, the target resource pool corresponding to the corresponding resource pool identifier can be further found in each country shared pool and the resource corresponding to the resource request instruction is found in the corresponding target resource pool, and if the resource corresponding to the resource request instruction is found, the process is ended and the corresponding resource is returned; if the resources are not found, the process can be directly ended and prompt information for finding the resources can be returned.

Optionally, in an embodiment of the present invention, the method may further include: and aiming at any resource pool, acquiring a request parameter corresponding to the resource pool according to the resource pool identifier of the resource pool and the data format condition of the resource pool identifier.

In addition, in practical applications, for any resource pool, there may be a case where it is necessary to know the applicable range of each resource pool. For example, after each resource pool is migrated, the relevant personnel after migration needs to know the application range of each resource pool to confirm whether the resource pool needs to be adjusted or not.

In addition, when the resource pools are set, the resource pool identifiers of the resource pools are set at the same time, so that the resource pools can be conveniently searched according to the request parameters obtained by the resource request instruction. Specifically, for any resource pool, the request parameter corresponding to the resource pool may be obtained according to the resource pool identifier of the resource pool and the data format condition of the resource pool identifier. Therefore, in the subsequent service process of taking resources such as the intermediate number and the like, the service property of the current resource pool can be quickly positioned by using the reverse logic.

And when the resource pool identifier calculates the request parameter in the reverse direction, the reverse logic can be performed to obtain the request parameter corresponding to each resource pool by referring to each step after the forward calculation of the resource pool ID according to the request parameter.

For example, assuming that the resource pool ID is an int type with 32 bits, the service type parameter is located at 0-5 bits of the int type, the region parameter is located at 6-11 bits of the int type, the context extension parameter is located at 12-18 bits of the int type, and the redundancy parameter is located at 19-31 bits of the int type, when the resource pool ID is 2081, the service parameters can be calculated as follows:

the redundancy parameter is 2081> >18&0x1FFF ═ 0,

the context extension parameter is 2081> >11&0x7F ═ 1,

the regional parameter is 2081> >5&0x3F ═ 1,

the service type parameter is 2081&0x1F ═ 1.

After the service parameters are determined, each request parameter can be further back-calculated according to the mapping relationship between the service parameters and the request parameters.

For example, for the region parameter 1, assuming that the region parameter having a mapping relationship with the region parameter in the mapping relationship between the service parameter and the request parameter is a city identifier, and the region parameter 1 corresponds to the city beijing in the mapping relationship between the region parameter and the city identifier, the city identifier of the current request parameter being beijing can be obtained (for example, 20); for the context extension parameter 1, according to the mapping relationship between the context extension parameter and the service type, the request channel type, and the traffic source identifier, the service type, the request channel type, and the traffic source identifier at this time can be obtained as 29 (second-hand vehicle), 2 (operating system is iOS), and cst _ thhz in sequence; and so on.

Of course, as can be seen from the above, both the request parameter and the service parameter can reflect the application range of the resource pool to a certain extent, and therefore, in the embodiment of the present invention, the service parameter corresponding to the resource pool can be obtained according to the resource pool identifier of the resource pool and the data format condition of the resource pool identifier, only for any resource pool, according to the requirement, without obtaining the corresponding request parameter, which is not limited in the embodiment of the present invention.

Correspondingly, the step of obtaining the resource corresponding to the resource request instruction from the target resource pool may specifically include:

step B21, searching unbound resources from the resource pool, and using any one unbound resource as the resource corresponding to the resource request instruction;

step B22, responding to the target resource pool without unbound resources, obtaining the current conversion rate of each binding relationship through the conversion rate prediction model;

and step B23, removing the binding relation with the minimum conversion rate, and taking the resource corresponding to the currently removed binding relation as the resource corresponding to the resource request instruction.

Accordingly, the specific process of obtaining the resource corresponding to the resource request instruction from the resource pools with different priorities or obtaining the resource corresponding to the resource request instruction from the target resource pool may be similar to the above steps a1-A3, which may specifically refer to the above contents, and is not described herein again.

Referring to fig. 2, in the embodiment of the present invention, before the step 120, the method may further include:

step 101, acquiring historical behavior data of each sample user, and performing data cleaning on the historical behavior data of the sample user;

step 102, extracting data characteristics of historical behavior data after data cleaning, and training a preset machine learning model through the data characteristics;

and 103, responding to the trained machine learning model passing a preset performance test, and taking the machine learning model as the conversion rate prediction model, wherein the performance test comprises at least one of an off-line test and an on-line test.

In the embodiment of the invention, in order to improve the accuracy of the conversion rate prediction result of the conversion rate prediction model after training and improve the training efficiency of the conversion rate prediction model, the historical behavior data of each sample user can be obtained, the historical behavior data of the sample user is subjected to data cleaning, and the data characteristics of the historical behavior data after the data cleaning are extracted. In the embodiment of the present invention, data cleaning may be performed in any available manner, and the embodiment of the present invention is not limited thereto. And then the conversion rate prediction model can be trained by using the extracted data characteristics.

In addition, in the embodiment of the present invention, after the model training is completed, any one of performance test procedures such as offline index evaluation, online test, online effect analysis, and the like may be further performed on the conversion rate prediction model obtained by the current training, and if the conversion rate prediction model obtained by the current training passes through each performance test procedure, the conversion rate may be estimated by performing online use based on the current conversion rate prediction model. And if the conversion rate prediction model obtained by the current training fails to pass through each performance test process, the historical behavior data of a batch of new sample users can be obtained again, and the

steps

101 and 102 are executed again to train the conversion rate prediction model until the conversion rate prediction model obtained by the final training passes through each performance test process.

Referring to fig. 2, in the embodiment of the present invention, the resource includes a virtual number, and the method may further include:

step 140, receiving a call request, wherein the call request comprises a virtual number;

step 150, obtaining a calling object having a binding relation with the virtual number, and calling the calling object.

Under the condition that the resource is a virtual number, after the binding relationship between the virtual number and the target object is determined, the corresponding target object can be called through the virtual number. Specifically, in the case of receiving a call request, a call object having a binding relationship with a virtual number may be acquired according to the virtual number included in the call request, and the call object may be called.

Referring to fig. 6, a schematic structural diagram of a resource allocation apparatus in an embodiment of the present invention is shown.

The resource allocation device of the embodiment of the invention comprises: an instruction receiving module 210, a conversion rate obtaining module 220 and a resource obtaining module 230.

The functions of the modules and the interaction relationship between the modules are described in detail below.

An instruction receiving module 210, configured to receive a resource request instruction, where the resource request instruction includes a user identifier that triggers the resource request instruction and an identifier of the target object;

a conversion rate obtaining module 220, configured to identify corresponding historical behavior data and attribute information of the target object, and obtain a conversion rate of the resource request instruction according to the historical behavior data and the attribute information through a preset conversion rate prediction model;

a resource obtaining module 230, configured to, in response to that the conversion rate is higher than a preset probability threshold, obtain a resource corresponding to the resource request instruction from a preset resource pool, and establish a binding relationship between the resource and the target object, where the resource pool includes at least one resource; the conversion rate prediction model is obtained by training historical behavior data of a plurality of sample users with known connection states.

Referring to fig. 7, in the embodiment of the present invention, the resource obtaining module 230 may further include:

a first resource obtaining sub-module 231, configured to search an unbound resource from the resource pool, and use any unbound resource as a resource corresponding to the resource request instruction;

the conversion rate obtaining submodule 232 is configured to, in response to that there is no unbound resource in the resource pool, obtain, through the conversion rate prediction model, a current conversion rate of each binding relationship;

the second resource obtaining sub-module 233 is configured to remove the binding relationship with the smallest conversion rate, and use the resource corresponding to the currently removed binding relationship as the resource corresponding to the resource request instruction.

Optionally, in this embodiment of the present invention, the resource obtaining module 230 further includes:

Optionally, in this embodiment of the present invention, the third resource obtaining sub-module may be specifically configured to:

Referring to fig. 7, in an embodiment of the present invention, the apparatus may further include:

the training data processing module 201 is configured to obtain historical behavior data of each sample user, and perform data cleaning on the historical behavior data of the sample user;

the model training module 202 is used for extracting data characteristics of the historical behavior data after data cleaning, and training a preset machine learning model through the data characteristics;

and the model testing module 203 is configured to respond that the trained machine learning model passes a preset performance test, and use the machine learning model as the conversion rate prediction model, where the performance test includes at least one of an online test and an offline test.

Referring to fig. 7, in the embodiment of the present invention, the resource includes a virtual number, and the apparatus may further include:

a call request receiving module 240, configured to receive a call request, where the call request includes a virtual number;

and the call processing module 250 is configured to acquire a call object having a binding relationship with the virtual number, and call the call object.

The resource allocation apparatus provided in the embodiment of the present invention can implement each process implemented in the method embodiments of fig. 1 to fig. 2, and is not described herein again to avoid repetition.

Preferably, an embodiment of the present invention further provides an electronic device, including: the processor, the memory, and the computer program stored in the memory and capable of running on the processor, when executed by the processor, implement each process of the above-mentioned resource allocation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements each process of the foregoing resource allocation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

Fig. 8 is a schematic diagram of a hardware structure of an electronic device implementing various embodiments of the present invention.

The electronic device 500 includes, but is not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, a processor 510, and a power supply 511. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 8 does not constitute a limitation of the electronic device, and that the electronic device may include more or fewer components than shown, or some components may be combined, or a different arrangement of components. In the embodiment of the present invention, the electronic device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal, a wearable device, a pedometer, and the like.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 501 may be used for receiving and sending signals during a message sending and receiving process or a call process, and specifically, receives downlink data from a base station and then processes the received downlink data to the processor 510; in addition, the uplink data is transmitted to the base station. In general, radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 501 can also communicate with a network and other devices through a wireless communication system.

The electronic device provides wireless broadband internet access to the user via the network module 502, such as assisting the user in sending and receiving e-mails, browsing web pages, and accessing streaming media.

The audio output unit 503 may convert audio data received by the radio frequency unit 501 or the network module 502 or stored in the memory 509 into an audio signal and output as sound. Also, the audio output unit 503 may also provide audio output related to a specific function performed by the electronic apparatus 500 (e.g., a call signal reception sound, a message reception sound, etc.). The audio output unit 503 includes a speaker, a buzzer, a receiver, and the like.

The input unit 504 is used to receive an audio or video signal. The input Unit 504 may include a Graphics Processing Unit (GPU) 5041 and a microphone 5042, and the Graphics processor 5041 processes image data of a still picture or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The processed image frames may be displayed on the display unit 506. The image frames processed by the graphic processor 5041 may be stored in the memory 509 (or other storage medium) or transmitted via the radio frequency unit 501 or the network module 502. The microphone 5042 may receive sounds and may be capable of processing such sounds into audio data. The processed audio data may be converted into a format output transmittable to a mobile communication base station via the radio frequency unit 501 in case of the phone call mode.

The electronic device 500 also includes at least one sensor 505, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor includes an ambient light sensor that can adjust the brightness of the display panel 5061 according to the brightness of ambient light, and a proximity sensor that can turn off the display panel 5061 and/or a backlight when the electronic device 500 is moved to the ear. As one type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), detect the magnitude and direction of gravity when stationary, and can be used to identify the posture of an electronic device (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), and vibration identification related functions (such as pedometer, tapping); the sensors 505 may also include fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which are not described in detail herein.

The display unit 506 is used to display information input by the user or information provided to the user. The Display unit 506 may include a Display panel 5061, and the Display panel 5061 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

The user input unit 507 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device. Specifically, the user input unit 507 includes a touch panel 5071 and other input devices 5072. Touch panel 5071, also referred to as a touch screen, may collect touch operations by a user on or near it (e.g., operations by a user on or near touch panel 5071 using a finger, stylus, or any suitable object or attachment). The touch panel 5071 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 510, and receives and executes commands sent by the processor 510. In addition, the touch panel 5071 may be implemented in various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. In addition to the touch panel 5071, the user input unit 507 may include other input devices 5072. In particular, other input devices 5072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein.

Further, the touch panel 5071 may be overlaid on the display panel 5061, and when the touch panel 5071 detects a touch operation thereon or nearby, the touch operation is transmitted to the processor 510 to determine the type of the touch event, and then the processor 510 provides a corresponding visual output on the display panel 5061 according to the type of the touch event. Although in fig. 8, the touch panel 5071 and the display panel 5061 are two independent components to implement the input and output functions of the electronic device, in some embodiments, the touch panel 5071 and the display panel 5061 may be integrated to implement the input and output functions of the electronic device, and is not limited herein.

The interface unit 508 is an interface for connecting an external device to the electronic apparatus 500. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input/output (I/O) port, a video I/O port, an earphone port, and the like. The interface unit 508 may be used to receive input (e.g., data information, power, etc.) from external devices and transmit the received input to one or more elements within the electronic apparatus 500 or may be used to transmit data between the electronic apparatus 500 and external devices.

The memory 509 may be used to store software programs as well as various data. The memory 509 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 509 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The processor 510 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 509 and calling data stored in the memory 509, thereby performing overall monitoring of the electronic device. Processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 510.

The electronic device 500 may further include a power supply 511 (e.g., a battery) for supplying power to various components, and preferably, the power supply 511 may be logically connected to the processor 510 via a power management system, so as to implement functions of managing charging, discharging, and power consumption via the power management system.

In addition, the electronic device 500 includes some functional modules that are not shown, and are not described in detail herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.

While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for resource allocation, comprising:

2. The method according to claim 1, wherein the step of obtaining the resource corresponding to the resource request instruction from a preset resource pool comprises:

3. The method according to claim 1, wherein the resource request instruction further includes a request parameter, and the step of obtaining the resource corresponding to the resource request instruction from a preset resource pool includes:

4. The method according to claim 3, wherein the step of obtaining the resource corresponding to the resource request instruction from the target resource pool comprises:

5. The method according to any one of claims 1 to 4, further comprising, before the step of obtaining the historical behavior data corresponding to the user identifier and the attribute information of the target object, and obtaining the conversion rate of the resource request instruction according to the historical behavior data and the attribute information and through a preset conversion rate prediction model, the step of:

6. The method of any of claims 1-4, wherein the resource comprises a virtual number, the method further comprising:

receiving a call request, wherein the call request comprises a virtual number;

7. A resource allocation apparatus, comprising:

8. The apparatus of claim 7, wherein the resource acquisition module comprises:

9. The apparatus of claim 7, wherein the resource obtaining module comprises:

10. The apparatus of claim 9, wherein the third resource acquisition submodule is specifically configured to:

11. The apparatus according to any one of claims 7-10, further comprising:

12. The apparatus of any of claims 1-4, wherein the resource comprises a virtual number, the apparatus further comprising:

13. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the resource allocation method according to any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the resource allocation method according to any one of claims 1 to 6.