Resource allocation method and device and electronic equipment

Abstract

The embodiment of the invention provides a resource allocation method and device and electronic equipment, and the method comprises the steps: determining the first sensitive information of a target object to a first type of resources according to the object attribute of the target object and the historical matching information of the target object and the first type of resources; wherein when the use of the first type of resources by the target object meets a first preset condition, a second type of resources is allocated to the target object, and the historical matching information comprises whether the use of the first type of resources by the target object meets the first preset condition or not and information of the second type of resources allocated to the target object under the condition that the first preset condition is met; the first sensitive information indicates whether the target object is sensitive to the first type of resources in a scene of allocating the second type of resources to the target object based on the use of the first type of resources; and allocating the first type of resources to the target object according to a resource allocation strategy matched with the first sensitive information. The problem of waste of resources allocated to the objects is improved, and the resource utilization rate can be improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a resource allocation method, device, and electronic device. Background Art

[0002] In order to facilitate the use of resources by users, various resources can be allocated to users. When allocating various resources to multiple objects, resources can be allocated to different objects according to the same allocation strategy.

[0003] However, different objects have different requirements for resources and use different resources. Some users, although allocated resources, do not use them, resulting in ineffective resource utilization. Therefore, allocating resources to different objects according to the same allocation strategy may lead to low resource utilization and waste of resources. Summary of the invention

[0004] Embodiments of the present disclosure provide a resource allocation method, device, and electronic device.

[0005] In a first aspect, an embodiment of the present disclosure provides a resource allocation method, comprising: determining first sensitive information of the target object for the first category of resources based on object attributes of the target object and historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets a first preset condition, second category resources associated with the first category of resources are allocated to the target object; the historical matching information includes the first category information historically allocated to the target object, the historical use information of the first category of resources, and the information of the second category resources historically allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in a scenario where the second category of resources is allocated to the target object based on the use of the first category of resources; and the first category of resources are allocated to the target object according to a resource allocation policy that matches the first sensitive information.

[0006] In a second aspect, an embodiment of the present disclosure provides a resource allocation device, comprising: a determination unit, for determining first sensitive information of the target object for the first category of resources based on object attributes of the target object and historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets a first preset condition, second category resources associated with the first category of resources are allocated to the target object; the historical matching information includes the first category information historically allocated to the target object, the historical use information of the first category of resources, and the information of the second category resources historically allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in a scenario where the second category of resources is allocated to the target object based on the use of the first category of resources; an allocation unit, for allocating the first category of resources to the target object according to a resource allocation policy that matches the first sensitive information.

[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0008] The memory stores computer-executable instructions;

[0009] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect and various possible designs of the first aspect.

[0010] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method described in the first aspect and various possible designs of the first aspect are implemented.

[0011] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect and various possible designs of the first aspect.

[0012] The resource allocation method, device and electronic device provided in this embodiment determine the first sensitive information of the target object to the first category of resources according to the object attribute of the target object and the historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets the first preset condition, the second category of resources associated with the first category of resources are allocated to the target object; the historical matching information includes the first category of information historically allocated to the target object, the historical use information of the first category of resources, and the information of the second category of resources historically allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in the scenario where the second category of resources is allocated to the target object based on the use of the first category of resources; and the first category of resources is allocated to the target object according to the resource allocation strategy matching the first sensitive information, so as to realize the allocation of the first category of resources to the target object based on the sensitive information of the target object to the first category of resources. Since the first category of resource information allocated to the object is related to the sensitive information of the object to the first category of resources, the object has a certain demand for the allocated first category of resources, which improves the problem of waste of resources allocated to the object and improves resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 Schematic flow chart of the resource allocation method provided in the embodiment of the present disclosure Figure 1 ;

[0015] Figure 2 Schematic flow chart of the resource allocation method provided in the embodiment of the present disclosure Figure 2 ;

[0016] Figure 3 for Figure 2 A schematic flow chart of the illustrated embodiment;

[0017] Figure 4 A schematic structural diagram of a resource allocation device provided in an embodiment of the present disclosure;

[0018] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0020] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0021] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using user information, so that the user can autonomously choose whether to provide information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0022] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide information to the electronic device.

[0023] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0024] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0025] In order to facilitate the use of resources by objects, resources can be allocated to different objects. Resources can be allocated to one or more objects according to the same resource allocation strategy. The resources here can include, for example: content service resources, product introduction resources, etc., product introduction resources associated with other resources, etc. The above products can include physical products and / or virtual products.

[0026] Resources allocated to different objects according to the same resource allocation strategy enable different objects to obtain the same resources. However, due to different requirements for resources and different resource usage of different objects, some objects may not use the allocated resources or only use a small amount of resources, resulting in low resource utilization and resource waste. Resource waste includes the waste of the allocated resources themselves and the waste of transmission resources caused by the transmission of the allocated resources.

[0027] In order to improve the above-mentioned problem, the solution provided by the present invention determines the sensitive information of the object to the first category of resources in the scenario of allocating the second category of resources for the use of the first category of resources according to the object attributes of the object and the historical matching information with the first category of resources, and allocates the first category of resources to the object according to the resource allocation strategy that matches the above-mentioned sensitive information. Therefore, the first category of resources allocated to the object is related to the sensitive information of the object to the first category of resources, that is, the object has a certain demand for the first category of resources, which can improve resource utilization and help improve the problem of resource waste.

[0028] Please refer to Figure 1 , Figure 1 Schematic flow of the resource allocation method provided by the present disclosure Figure 1 ;like Figure 1 As shown, the method comprises the following steps:

[0029] S101: Determine first sensitive information of the target object for the first category of resources based on the object attributes of the target object and historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets a first preset condition, allocate second category resources associated with the first category of resources to the target object; the historical matching information includes information on the first category of resources historically allocated to the target object, historical use information of the first category of resources, and historical information on the second category of resources allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in a scenario where the second category of resources is allocated to the target object based on the use of the first category of resources.

[0030] The executor of the resource allocation method (such as a server or a terminal device) can obtain the object attributes of the target object and the historical matching information between the target object and the first category of resources, and then determine the first sensitive information of the target object for the first category of resources based on the object attribute information and the above historical matching information.

[0031] The target object here can be any one of the multiple objects to which resources are to be allocated. Object attributes may include, for example, object identification, object category, object location, etc. The historical matching information includes information about the first-class resources historically allocated to the target object, information about the target object's use of the first-class resources, information about the second-class resources historically allocated to the target object due to its use of the first-class resources, etc. In addition, the information about the first-class resources historically allocated to the target object includes the number of times the first-class resources were historically allocated to the target object; the use information about the first-class resources may include, for example, the duration of use, the number of uses, etc.

[0032] The information of the second type of resources allocated due to the use of the first type of resources in history includes: the number of times the second type of resources are allocated, the duration of use of the first type of resources when the second type of resources are allocated, and the quantity of the second type of resources allocated each time.

[0033] In this embodiment, the use of the first type of resources by the object may be allocated the second type of resources.

[0034] The first sensitive information may be determined based on the object attribute of the target object and the historical matching information between the target object and the first category of resources. The first sensitive information indicates whether the target object is sensitive to the first category of resources in a scenario where the second category of resources is allocated to the target object based on the use of the first category of resources. The first sensitive information indicates whether the target object is sensitive to the first category of resources or is not sensitive to the first category of resources.

[0035] If the first sensitive information indicates that the target object is sensitive to the first type of resources, that is, the target object needs more first type of resources, or needs more second type of resources associated with the first type of resources.

[0036] The target object is insensitive to the first type of resources, indicating that the target object requires less first type of resources, or requires less second type of resources associated with the first type of resources.

[0037] Here, the first type of resources can be regarded as resources associated with the second type of resources. The first type of resources can include product information. The second type of resources can include equity resources, currency resources, etc.

[0038] The first preset condition may include, for example, that the usage duration is greater than a preset duration threshold.

[0039] The object can use the first category of resources by displaying the first category of resources.

[0040] In some application scenarios, the first-category resources may be associated with content resources and allocated to the target object. For example, the first-category resources may be displayed during the display of content resources. During the display process, the first-category resources may also be prohibited from being displayed.

[0041] S102: Allocate a first type of resource to a target object based on an allocation strategy that matches the first sensitive information.

[0042] Specifically, the above step S102 includes one or more of the following:

[0043] If the first sensitive information indicates that the target object is sensitive to the first type of resources, the first type of resources are allocated to the target object according to the first allocation strategy; wherein the first allocation strategy indicates increasing the number of second type of resources associated with the first type of resources, or increasing the allocation amount or frequency of the first type of resources allocated to the target object;

[0044] If the first sensitive information indicates that the target object is not sensitive to the first type of resources, the first type of resources are allocated to the target object according to the second allocation strategy, and the second allocation strategy indicates reducing the allocation amount or frequency of the first type of resources allocated to the target object.

[0045] In some application scenarios, the first sensitive information indicates that the target object is sensitive to the first category of resources, indicating that the target object needs more first category resources, or needs more second category resources associated with the first category of resources. The above allocation strategy may, for example, include associating more second category resources with the first category resources allocated to the target object. The allocation amount of the first category resources allocated to the target object may also be increased, for example, the number of allocated first category resources may be increased, or a single first category resource may be larger (for example, if it is a product introduction video, the video may be longer). The frequency of allocating the first category of resources to the target object may also be increased, so that the target object is allocated more first category resources.

[0046] In some application scenarios, the first sensitive information indicates that the target object is not sensitive to the first type of resources, indicating that the target object requires less first type of resources, or requires less second type of resources associated with the first type of resources. The above allocation strategy may, for example, include reducing the amount of the first type of resources allocated to the target object, and may also reduce the frequency of allocating the first type of resources to the target object.

[0047] In this embodiment, the first sensitive information of the object to the first category of resources is determined according to the object attributes and the historical matching information between the object and the first category of resources, and the first category of resources is allocated to the target object according to the resource allocation strategy matching the first sensitive information. Since the first category of resource information allocated to the object is related to the sensitive information of the object to the first category of resources, the object has a certain demand for the allocated first category of resources, which improves the problem of waste of resources allocated to the object and can improve resource utilization.

[0048] Please refer to Figure 2 , Figure 2 Schematic flow chart of the resource allocation method provided in the embodiment of the present disclosure Figure 2 .like Figure 2 As shown, in addition to including Figure 1 In addition to step S204 which is the same as step S102 shown, the method includes the following steps:

[0049] S201: Input the object attributes of the target object and the historical matching information between the target object and the first category of resources into a pre-trained sensitivity recognition model to obtain the second sensitive information of the target object to the first category of resources.

[0050] The historical matching information includes information about the first-category resources historically allocated to the target object, historical usage information of the first-category resources, and information about the second-category resources historically allocated to the target object due to the usage of the first-category resources.

[0051] In this embodiment, the sensitive information of the target object to the first category of resources can be determined in advance based on the object attributes of the target object and the historical matching information between the target object and the first category of resources, through the sensitive information output by the sensitivity recognition model and the sensitive information determined by clustering multiple objects.

[0052] Specifically, the object attributes of the target object and the historical matching information can be input into the sensitivity recognition model. The sensitivity recognition model can determine the second sensitive information of the target object to the first category of resources based on the object attributes of the target object and the historical matching information between the target object and the first category of resources input therein.

[0053] The second sensitive information indicates that the target object is sensitive to the first category of resources, or indicates that the target object is not sensitive to the first category of resources.

[0054] The sensitivity recognition model may be various classification models, such as a logistic regression model, a support vector machine model, a decision tree model, a naive Bayes model, and the like.

[0055] S202: Cluster multiple objects including the target object according to their respective corresponding object attributes and historical matching information for the first category of resources; determine the third sensitive information of the target object for the first category of resources based on the obtained clustering results; wherein the multiple objects include objects that are sensitive to the first category of resources, objects that are not sensitive to the first category of resources, and objects that are not determined to be sensitive to the first category of resources.

[0056] The target object may be an object for which it is not determined whether it is sensitive to the first category of resources.

[0057] For each of the multiple objects, the object attributes of the object and the historical matching information of the first type of resources may be encoded according to a preset encoding rule to obtain an encoding result of each object. For example, the object attributes of the object and the historical matching information of the first type of resources may be encoded using a One-Hot encoding method to obtain an encoding result of each object.

[0058] Various clustering methods may be used to cluster multiple objects according to their respective encoding results. The above clustering methods may include, for example, K-means clustering algorithm, hierarchical clustering, and the like.

[0059] In some implementations, the above step S202 includes the following sub-steps:

[0060] First, a target clustering result where the target object is located is obtained from the clustering results obtained by clustering multiple objects.

[0061] By clustering multiple objects according to the object attributes and the historical matching information between the objects and the first type of resources, multiple clustering results can be obtained. The clustering result where the target object is located is used as the target clustering result.

[0062] Secondly, according to the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering result, the third sensitive information of the target object to the first category of resources is determined.

[0063] The target clustering result includes one or more objects that are sensitive to the first type of resources, one or more objects that are not sensitive to the first type of resources, and objects whose sensitivity to the first type of resources is not determined. Among them, the objects whose sensitivity to the first type of resources is not determined include the above target objects.

[0064] The third sensitive information of the target object to the first category of resources may be determined according to the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering result.

[0065] Specifically, if in the target clustering result, the number of objects that are sensitive to the first type of resources is greater than or equal to the number of objects that are not sensitive to the first type of resources, third sensitive information indicating that the target object is sensitive to the first type of resources is generated;

[0066] If, in the target clustering result, the number of objects that are sensitive to the first type of resources is less than the number of objects that are not sensitive to the first type of resources, third sensitive information indicating that the target object is not sensitive to the first type of resources is generated.

[0067] In addition, the second confidence level corresponding to the third sensitive information may be determined from the distribution of objects that are sensitive to the first type of resources and objects that are not sensitive to the first type of resources in the above target clustering results.

[0068] For example, in the target clustering result A1, the total number of objects is 100, the number of objects sensitive to the first category of resources is 51, the number of objects insensitive to the first category of resources is 20, and 29 objects are objects whose sensitivity to the first category of resources is not determined. In the above clustering result A1, the number of objects sensitive to the first category of resources (51) is greater than the number of objects insensitive to the first category of resources (20), then it is determined that the third sensitive information indicates that the target object (the above 29 objects whose sensitivity to the first category of resources is not determined include the above target object) is sensitive to the first category of resources, and at the same time, the second confidence level corresponding to the third sensitive information is determined to be 51 / 100=0.51.

[0069] For another example, in the cluster result A2 where the target object is located, the total number of objects is 100, the number of objects that are sensitive to the first type of resources is 30, the number of objects that are not sensitive to the first type of resources is 50, and 20 objects are users whose sensitivity to the first type of resources is unknown. Then the third sensitive information corresponding to the target object (the above 20 objects whose sensitivity to the first type of resources is not determined include the above target object) indicates that the target object is not sensitive to the first type of resources; the corresponding second confidence is 50 / 100=0.5.

[0070] In these embodiments, different objects with similar object attributes and / or similar historical matching information with the first category of resources are likely to have the same sensitivity to the first category of resources. Therefore, the third sensitive information of the target object can be determined based on the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering results, so that it is possible to infer whether the target object is sensitive to the first category of resources through the clustering results to which the target object belongs, and the obtained third sensitive information can have a certain degree of accuracy.

[0071] S203: Determine the first sensitive information based on the second sensitive information and the third sensitive information.

[0072] The second sensitive information and the third sensitive information may be merged to obtain the first sensitive information.

[0073] In some embodiments, the sensitivity identification model also outputs a first confidence level corresponding to the second sensitive information; determines the third sensitive information of the target object to the first category of resources based on the distribution of objects sensitive to the first category of resources and objects insensitive to the first category of resources in the target clustering results, and also includes: determining a second confidence level of the third sensitive information based on the distribution.

[0074] The above step S203 includes:

[0075] If the second sensitive information and the third sensitive information are the same, the second sensitive information is used as the first sensitive information; and the first confidence of the second sensitive information and the second confidence of the third sensitive information are fused, and the fused target confidence is used as the confidence of the first sensitive information;

[0076] If the second sensitive information and the third sensitive information are different, the target confidence is determined according to the first confidence and the second confidence; the second sensitive information or the third sensitive information corresponding to the target confidence is used as the first sensitive information.

[0077] Here, the second sensitive information is the same as the third sensitive information, including that both the second sensitive information and the third sensitive information indicate that the target object is sensitive to the first type of resources, or that both the second sensitive information and the third sensitive information indicate that the target object is not sensitive to the first type of resources.

[0078] In some application scenarios, the second sensitive information is the same as the third sensitive information, and the first confidence level and the second confidence level can be fused according to a preset confidence fusion algorithm. The target confidence level obtained after fusion of the first confidence level and the second confidence level can be greater than the first confidence level and the second confidence level.

[0079] By fusing the first confidence and the second confidence, the target confidence obtained is greater than the first confidence and also greater than the second confidence. That is, if the second sensitive information and the third sensitive information are the same, the second sensitive information and the third sensitive information determined by different means realize the mutual verification of the sensitive information of the target object to the first category of resources, and the credibility of the target object's sensitive information to the first category of resources being the above-mentioned second sensitive information is increased. When the second sensitive information and the third sensitive information are the same, the above-mentioned confidence is fused to change the confidence of the target object to the sensitive information of the first category of resources, so that the target confidence matches the real scene.

[0080] In some application scenarios, the second sensitive information is different from the third sensitive information, and a confidence with a larger value can be determined from the first confidence and the second confidence as the target confidence. One of the second sensitive information and the third sensitive information corresponding to the target confidence is used as the first sensitive information. In these application scenarios, the one with a larger corresponding confidence between the second sensitive information and the third sensitive information is used as the first sensitive information, so that the determined first sensitive information has a higher credibility.

[0081] S204: Allocate the first type of resources to the target object based on the allocation strategy matching the first sensitive information.

[0082] Specifically, the above step S204 includes one or more of the following:

[0083] If the first sensitive information indicates that the target object is sensitive to the first type of resources, the first type of resources are allocated to the target object according to the first allocation strategy; wherein the first allocation strategy indicates increasing the number of second type of resources associated with the first type of resources, or increasing the allocation amount or frequency of the first type of resources allocated to the target object;

[0084] Alternatively, if the first sensitive information indicates that the target object is not sensitive to the first type of resources, the first type of resources are allocated to the target object according to the second allocation strategy, and the second allocation strategy indicates reducing the allocation amount or frequency of the first type of resources allocated to the target object.

[0085] For target objects that are sensitive to first-class resources, by using the first allocation strategy to allocate first-class resources associated with more second-class resources to the target objects, the target objects can obtain more second-class resources if they use the first-class resources. Therefore, the frequency of use of the first-class resources by the target objects will also increase, which can improve the utilization rate of the first-class resources. In addition, when the target object is sensitive to the first-class resources, it needs more first-class resources, or needs more second-class resources associated with the first-class resources. Therefore, increasing the number of second resources associated with the first-class resources, or allocating the allocation amount or frequency of the first-class resources to the target objects can better meet the needs of the objects.

[0086] If the first sensitive information indicates that the target object is not sensitive to the first type of resources, the first type of resources are allocated to the target object according to the second allocation strategy, wherein the second allocation strategy indicates reducing the allocation amount or frequency of the first type of resources allocated to the target object, which can improve resource utilization. In addition, when the target object is not sensitive to the first type of resources, less first type of resources are required, or less second type of resources associated with the first type of resources are required. Therefore, reducing the allocation amount or frequency of the first type of resources allocated to the target object can better meet the needs of the object and save resources.

[0087] Figure 3 A principle flow chart of the resource allocation method provided in the embodiment of the present disclosure. Figure 3 As shown, the execution subject determines the sensitivity label 31 of each object among the multiple objects according to the object's historical usage information of the first category of resources. The sensitivity label includes sensitive to the first category of resources, insensitive to the first category of resources, or unable to determine whether it is sensitive to the first category of resources.

[0088] Any object that is not determined to be sensitive to the first type of resources is taken as a target object, and the object attributes of the target object and the historical matching information between the target object and the first type of resources are input into a pre-trained sensitivity recognition model, and the sensitivity recognition model outputs the second sensitive information 32 of the target object. The sensitivity recognition model also outputs a first confidence level corresponding to the second sensitive information.

[0089] For multiple objects with the above sensitivity labels, the multiple objects are clustered according to the object attributes of the multiple objects and the historical matching information of each object with the first category of resources to obtain n clustering results. For each clustering result, according to the distribution of objects labeled as sensitive to the first category of resources and objects labeled as insensitive to the first category of resources in the clustering result, the third sensitive information of the objects in the clustering result that are not determined to be sensitive to the first category of resources and the second confidence 33 corresponding to the third sensitive information are determined.

[0090] For each target object that is not determined to be sensitive to the first type of resources, the first sensitive information 34 can be determined based on the second sensitive information and the third sensitive information of the target object. In addition, the target confidence of the first sensitive information can also be determined based on the first confidence of the second sensitive information and the second confidence of the third sensitive information.

[0091] A push strategy corresponding to the first sensitive information is used to allocate the first type of resources to the target object.

[0092] In this embodiment, it is described that the sensitivity identification model is used to process the object attributes of the target object and the usage information of the first category of resources to obtain the second sensitive information; multiple objects including the target object are clustered according to their respective object attributes and the usage information of the first category of resources to obtain multiple clustering results, and the third sensitive information of the target object is determined according to the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering results including the target object, and the first sensitive information of the target object is determined according to the second sensitive information and the third sensitive information. The above content combines different data processing methods to determine the final first sensitive information of the target object, which helps to improve the accuracy of determining the first sensitive information of the target object, and can improve the utilization rate of the first category of resources allocated to the target object by the first sensitive information, which is conducive to better meeting the needs of the object.

[0093] In some optional implementations of this embodiment, the method further includes:

[0094] First, object attributes of multiple objects and historical matching information between the objects and first-category resources are obtained, and sensitivity labels of the multiple objects are determined according to the object attributes and the historical matching information; the sensitivity labels indicate whether the objects are sensitive to the first-category resources or are insensitive to the first-category resources.

[0095] Specifically, for each object, a sensitivity label of the object is determined according to the object attributes of the object and the historical matching information between the object and the first category of resources.

[0096] Secondly, the positive training data is composed of the object attributes of multiple objects whose sensitivity labels are sensitive to the first type of resources and the historical matching information between the multiple objects and the first type of resources; the negative training data is composed of the object attributes of multiple objects whose sensitivity labels are insensitive to the first type of resources and the historical matching information between the multiple objects and the first type of resources. The training data set is composed of multiple positive training data and negative training data.

[0097] Finally, the sensitivity recognition model is trained using the training data set to obtain a trained sensitivity recognition model.

[0098] In some implementations of this embodiment, multiple objects each have their own sensitivity label, and the sensitivity label of each object includes one of the following: a first label that is sensitive to a first category of resources, a second label that is not sensitive to the first category of resources, and a third label that is not determined to be sensitive to the first category of resources; for any first object among the multiple objects, the sensitivity label of the first object is determined based on the following steps:

[0099] First, obtain the first number of allocations of the first type of resources to the first object within a preset time period, a first statistical number determined based on the number of second type resources associated with each allocation of the first type of resources, the first number of uses of the first type of resources by the first object within the preset time period, a second statistical number determined based on the number of second type resources allocated due to each use of the first type of resources, and the duration of use of the first type of resources.

[0100] Secondly, according to one or more of the first allocation times, the first statistical number, the first usage times, the second statistical number and the usage duration, and thresholds corresponding to the one or more of the first allocation times, a sensitivity label of the first object is determined, wherein:

[0101] The threshold corresponding to the first allocation times is determined based on the first allocation times corresponding to multiple objects respectively; the threshold corresponding to the first statistical quantity is determined based on the first statistical quantities corresponding to multiple objects respectively; the threshold corresponding to the first usage times is determined based on the first usage times corresponding to multiple objects respectively; the threshold corresponding to the second statistical quantity is determined based on the second statistical quantities corresponding to multiple objects respectively; the threshold corresponding to the usage time is determined by the usage time of the first type of resources by multiple objects within a preset time period.

[0102] When determining the sensitivity label of any first object, the parameters of multiple dimensions such as the first allocation times, the first statistical quantity, the first usage times, the second statistical quantity and the usage duration are referred to. Therefore, the sensitivity label of the first object determined by the information of these multiple dimensions is more accurate. Training the sensitivity recognition model using training data obtained based on the object attributes of multiple objects with the above sensitivity labels and the information on the objects' usage of the first category of resources helps to improve the accuracy of the prediction of the sensitivity recognition model obtained by training.

[0103] Corresponding to the above Figure 1-2 The resource allocation method of the illustrated embodiment, Figure 3 A schematic structural block diagram of a resource allocation device provided in an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 4 , the device 40 includes: a determination unit 401 and an allocation unit 402. Among them,

[0104] A determination unit 401 is used to determine first sensitive information of the target object to the first category of resources according to the object attribute of the target object and the historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets the first preset condition, the second category of resources associated with the first category of resources are allocated to the target object; the historical matching information includes the first category of information historically allocated to the target object, the historical use information of the first category of resources, and the information of the second category of resources historically allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in the scenario where the second category of resources is allocated to the target object based on the use of the first category of resources;

[0105] The allocation unit 402 is used to allocate the first type of resources to the target object according to the resource allocation strategy matching the first sensitive information.

[0106] In some embodiments, the first sensitive information of the first category of resources indicates that the target object is sensitive to the first category of resources, or is not sensitive to the first category of resources.

[0107] In some embodiments, the determining unit 401 is further configured to:

[0108] Input the object attributes and historical matching information into a pre-trained sensitivity recognition model to obtain the second sensitive information of the target object to the first category of resources;

[0109] Clustering multiple objects including the target object according to their corresponding object attributes and historical matching information; determining the third sensitive information of the target object to the first category of resources according to the obtained clustering results; wherein the multiple objects include objects sensitive to the first category of resources, objects insensitive to the first category of resources, and objects not determined to be sensitive or insensitive to the first category of resources;

[0110] The first sensitive information is determined based on the second sensitive information and the third sensitive information.

[0111] In some embodiments, the determining unit 401 is further configured to:

[0112] Obtaining a target clustering result where a target object is located from clustering results obtained by clustering multiple objects;

[0113] According to the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering result, the third sensitive information of the target object to the first category of resources is determined.

[0114] In some embodiments, the determining unit 401 is further configured to:

[0115] If, in the target clustering result, the number of objects that are sensitive to the first type of resources is greater than or equal to the number of objects that are not sensitive to the first type of resources, generating third sensitive information indicating that the target object is sensitive to the first type of resources;

[0116] If, in the target clustering result, the number of objects that are sensitive to the first type of resources is less than the number of objects that are not sensitive to the first type of resources, third sensitive information indicating that the target object is not sensitive to the first type of resources is generated.

[0117] In some embodiments, the sensitivity identification model further outputs a second confidence level corresponding to the second sensitive information; the determination unit 401 is further used to determine the second confidence level of the third sensitive information according to the distribution of objects sensitive to the first type of resources and objects insensitive to the first type of resources in the target clustering result; and the determination unit 401 is further used to:

[0118] If the second sensitive information and the third sensitive information are the same, the second sensitive information is used as the first sensitive information; and the first confidence of the second sensitive information and the second confidence of the third sensitive information are fused, and the fused target confidence is used as the confidence of the first sensitive information;

[0119] If the second sensitive information and the third sensitive information are different, the target confidence is determined according to the first confidence and the second confidence; the second sensitive information or the third sensitive information corresponding to the target confidence is used as the first sensitive information.

[0120] In some embodiments, a plurality of objects respectively have sensitivity labels, and the sensitivity label of each object includes one of the following: a first label that is sensitive to a first category of resources, a second label that is not sensitive to the first category of resources, and a third label that is not determined to be sensitive to the first category of resources;

[0121] The apparatus 40 further includes a label determination unit (not shown in the figure), which is used to determine, for any first object among the multiple objects, a sensitivity label of the first object based on the following steps:

[0122] Obtaining a first number of allocations of a first type of resource to a first object within a preset time period, a first statistical number determined based on the number of second type resources associated with each allocation of the first type of resource, a first number of uses of the first type of resource by the first object within the preset time period, a second statistical number determined based on the number of second type resources allocated due to each use of the first type of resource, and a usage duration of the first type of resource;

[0123] The label of the first object is determined according to one or more of the first allocation times, the second statistical number, the first usage times, the second statistical number and the usage duration, and thresholds corresponding to the one or more respectively, wherein:

[0124] The threshold corresponding to the first allocation times is determined based on the first allocation times corresponding to multiple objects respectively; the threshold corresponding to the first statistical quantity is determined based on the first statistical quantities corresponding to multiple objects respectively; the threshold corresponding to the first usage times is determined based on the first usage times corresponding to multiple objects respectively; the threshold corresponding to the second statistical quantity is determined based on the second statistical quantities corresponding to multiple objects respectively; the threshold corresponding to the usage time is determined by the usage time of the first type of resources by multiple objects within a preset time period.

[0125] In some embodiments, the allocating unit 402 is further configured to allocate the first type of resources to the target object based on one or more of the following:

[0126] If the first sensitive information indicates that the target object is sensitive to the first type of resources, the first type of resources are allocated to the target object according to the first allocation strategy; wherein the first allocation strategy indicates increasing the number of second type of resources associated with the first type of resources, or increasing the allocation amount or frequency of the first type of resources allocated to the target object;

[0127] Alternatively, if the first sensitive information indicates that the target object is not sensitive to the first type of resources, the first type of resources are allocated to the target object according to the second allocation strategy, and the second allocation strategy indicates reducing the allocation amount or frequency of the first type of resources allocated to the target object.

[0128] In order to implement the above embodiment, the embodiment of the present disclosure also provides an electronic device.

[0129] refer to Figure 5, which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present disclosure, and the electronic device 500 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0130] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0131] Typically, the following devices may be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0132] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0133] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program (computer-executable instructions), which may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0134] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0135] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0136] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0138] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0139] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0140] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0142] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0143] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A resource allocation method, comprising: Determine the first sensitive information of the target object to the first category of resources according to the object attribute of the target object and the historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets the first preset condition, the second category of resources associated with the first category of resources are allocated to the target object; the historical matching information includes the information of the first category of resources historically allocated to the target object, the historical use information of the first category of resources, and the information of the second category of resources historically allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in the scenario where the second category of resources is allocated to the target object based on the use of the first category of resources; Allocate first-category resources to the target object according to a resource allocation strategy that matches the first sensitive information.

2. The method according to claim 1, wherein: The first sensitive information of the first category of resources indicates that the target object is sensitive to the first category of resources, or is not sensitive to the first category of resources.

3. The method according to claim 1 or 2, wherein: The determining, according to the object attribute of the target object and the historical matching information between the target object and the first category of resources, the first sensitive information of the target object with respect to the first category of resources comprises: Inputting the object attribute and the historical matching information into a pre-trained sensitivity recognition model to obtain second sensitive information of the target object to the first type of resources; Clustering multiple objects including the target object according to their corresponding object attributes and the historical matching information; determining the third sensitive information of the target object to the first category of resources according to the obtained clustering result; wherein the multiple objects include objects that are sensitive to the first category of resources, objects that are not sensitive to the first category of resources, and objects that are not determined to be sensitive to the first category of resources; The first sensitive information is determined based on the second sensitive information and the third sensitive information.

4. The method according to claim 3, wherein: clustering a plurality of objects including the target object according to the respective corresponding object attributes and the historical matching information; Determining the third sensitive information of the target object to the first category of resources according to the obtained clustering result includes: Obtaining a target clustering result where the target object is located from the clustering results obtained by clustering the multiple objects; According to the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering result, third sensitive information of the target object to the first category of resources is determined.

5. The method according to claim 4, wherein: The determining, according to the distribution of objects that are sensitive to the first category of resources and objects that are not sensitive to the first category of resources in the target clustering result, third sensitive information of the target object to the first category of resources includes: If, in the target clustering result, the number of objects that are sensitive to the first type of resources is greater than or equal to the number of objects that are not sensitive to the first type of resources, generating third sensitive information indicating that the target object is sensitive to the first type of resources; If, in the target clustering result, the number of objects that are sensitive to the first category of resources is less than the number of objects that are not sensitive to the first category of resources, third sensitive information indicating that the target object is not sensitive to the first category of resources is generated.

6. The method according to claim 4, wherein: The sensitivity identification model further outputs a first confidence level corresponding to the second sensitive information; the determining, based on the distribution of objects sensitive to the first category of resources and objects insensitive to the first category of resources in the target clustering result, third sensitive information of the target object to the first category of resources, further includes: determining a second confidence level of the third sensitive information based on the distribution; And determining the first sensitive information according to the second sensitive information and the third sensitive information includes: If the second sensitive information is the same as the third sensitive information, the second sensitive information is used as the first sensitive information; and the first confidence of the second sensitive information and the second confidence of the third sensitive information are fused, and the fused target confidence is used as the confidence of the first sensitive information; If the second sensitive information and the third sensitive information are different, determine the target confidence level according to the first confidence level and the second confidence level; and use the second sensitive information or the third sensitive information corresponding to the target confidence level as the first sensitive information.

7. The method according to claim 3, wherein: The multiple objects respectively have sensitivity labels, and the sensitivity label of each object includes one of the following: a first label that is sensitive to a first category of resources, a second label that is not sensitive to the first category of resources, and a third label that is not determined to be sensitive to the first category of resources; For any first object among the multiple objects, the method further includes determining a sensitivity label of the first object based on the following steps: obtaining a first number of allocations of the first type of resource to the first object within the preset time period, a first statistical number determined based on the number of the second type of resources associated with each allocation of the first type of resource, a first number of uses of the first type of resource by the first object within the preset time period, a second statistical number determined based on the number of the second type of resources allocated due to each use of the first type of resource, and a usage duration of the first type of resource; The label of the first object is determined according to one or more of the first allocation times, the second statistical number, the first usage times, the second statistical number and the usage duration, and thresholds corresponding to the one or more respectively, wherein: The threshold corresponding to the first allocation times is determined based on the first allocation times corresponding to the multiple objects respectively; the threshold corresponding to the first statistical quantity is determined based on the first statistical quantities corresponding to the multiple objects respectively; the threshold corresponding to the first usage times is determined based on the first usage times corresponding to the multiple objects respectively; the threshold corresponding to the second statistical quantity is determined based on the second statistical quantities corresponding to the multiple objects respectively; the threshold corresponding to the usage time is determined by the usage time of the first type of resources by multiple objects within the preset time period.

8. The method according to claim 1, wherein: The allocating the first type of resource to the target object based on the allocation strategy matching the sensitive information includes one or more of the following: If the first sensitive information indicates that the target object is sensitive to the first type of resources, allocate the first type of resources to the target object according to a first allocation strategy; wherein the first allocation strategy indicates increasing the number of second type resources associated with the first type of resources, or increasing the allocation amount or frequency of the first type of resources allocated to the target object; Alternatively, if the first sensitive information indicates that the target object is not sensitive to the first type of resources, the first type of resources are allocated to the target object according to a second allocation strategy, and the second allocation strategy indicates reducing the allocation amount or frequency of the first type of resources allocated to the target object.

9. A resource allocation device, comprising: A determination unit, configured to determine first sensitive information of the target object to the first category of resources according to an object attribute of the target object and historical matching information between the target object and the first category of resources; wherein, when the use of the first category of resources by the target object meets a first preset condition, a second category of resources associated with the first category of resources is allocated to the target object; the historical matching information includes the first category of information historically allocated to the target object, the historical use information of the first category of resources, and the information of the second category of resources historically allocated due to the use of the first category of resources; the first sensitive information indicates whether the target object is sensitive to the first category of resources in a scenario where the second category of resources is allocated to the target object based on the use of the first category of resources; An allocation unit is used to allocate the first type of resources to the target object according to a resource allocation strategy matching the first sensitive information.

10. An electronic device, wherein: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer-executable instructions, and when a processor executes the computer-executable instructions, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images