Resource management method and device, equipment, storage medium and product

Abstract

The invention discloses a resource management method and device, equipment, a storage medium and a product, and relates to the technical field of computers, and the resource management method comprises the steps: determining a resource score according to the current state and historical performance information of a target resource; determining a resource service party score of each resource service party based on the resource score; and when a resource application is received, determining a target recommendation resource according to a resource demand, the resource score and the resource service party score. As the target resource is recommended to the user according to the score of the resource and the score of the service party, compared with an existing mode of recommending the resource to the user only according to the resource demand, the mode can more accurately and scientifically predict the reliability degree of the resource, improve the matching degree of the resource and the demand, and promote the completion of performance.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to resource management methods, devices, equipment, storage media and products. Background Art

[0002] The computing power network is a new type of information infrastructure that allocates and flexibly schedules computing resources, storage resources, and network resources between clouds, networks, and edges according to business needs. It realizes the flexible and on-demand use of computing power, connects scattered and isolated computing power nodes through the network, and forms a three-dimensional ubiquitous computing power cluster, realizing the collaboration, intensiveness, and inclusiveness of computing power. Traditional computing power resources are mainly provided by cloud vendors or large computing power centers, but the computing power network is also trying to make full use of idle social ubiquitous computing power. The former is characterized by concentrated resources, stable performance, and standardized specifications; the latter is characterized by time and space dispersion, multiple types, and widespread existence. At present, there is a phenomenon of regional imbalance in the demand for computing power in society, and it changes periodically over time. The stable computing power provided by cloud vendors and large computing power centers alone is not enough to efficiently support this tidal demand, or it requires a high price. At this time, the addition of social ubiquitous computing power can give full play to the advantages of the sharing economy and alleviate computing power pressure to a large extent. However, due to the complex types and poor performance stability of social ubiquitous computing power, it is necessary to establish a sound mechanism at the operational level to supervise and manage these computing powers.

[0003] In the grid connection process that has been disclosed so far, the computing network platform plays the role of matchmaking transactions. The computing power provider sets its own price to rent computing power, and the computing power consumer independently selects computing power resources to finally reach a transaction. The performance, SLA and other indicators of computing power resources can only be determined by the parameters provided by the resource provider at the time of grid connection, or by the verification data at that time, which is static and lagging. If this information is used to schedule computing network resources, it is easy to cause computing tasks to fail, damage the interests of consumers, and ultimately lead to the loss of computing network platform users. Therefore, how to improve the resource management efficiency of the ubiquitous computing network and ensure the interests of computing power consumers has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of this application is to provide a resource management method, device, equipment, storage medium and product, aiming to solve the technical problem of low efficiency of existing ubiquitous computing network resource management.

[0005] To achieve the above objectives, the present application proposes a resource management method, which includes:

[0006] Determine resource scores based on the current status and historical performance information of the target resource;

[0007] Determine a resource service provider score of each resource service provider based on the resource score;

[0008] When a resource application is received, a target recommended resource is determined based on the resource demand, the resource score, and the resource service provider score.

[0009] Optionally, the step of determining the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving the resource application includes:

[0010] When receiving a resource application, determining resource requirements based on the resource application;

[0011] The resource demand, the resource score, the resource service provider score and basic resource information are input into a preset resource recommendation model to obtain target recommended resources.

[0012] Optionally, before the step of inputting the resource demand, the resource score, the resource service provider score and the basic resource information into a preset resource recommendation model to obtain the target recommended resource, the step further includes:

[0013] Acquire sample data, wherein the sample data includes sample resource requirements, actual allocated resources, user satisfaction, and resource rating information;

[0014] The initial deep learning model is trained based on the sample data to obtain a preset resource recommendation model.

[0015] Optionally, the step of determining a resource score according to the current status and historical performance information of the target resource includes:

[0016] Determine the average score of the target resource based on the time decay algorithm, the current status of the target resource and the historical performance information;

[0017] The average score is normalized to obtain a resource score of the target resource.

[0018] Optionally, the step of determining the resource service provider score of each resource service provider based on the resource score includes:

[0019] Determine resource type information of the resource service provider, wherein the resource type information includes resource type and weight information corresponding to the resource type;

[0020] The resource service provider score of each resource service provider is determined according to the resource type information and the resource score.

[0021] Optionally, after the step of determining the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving the resource application, the method further includes:

[0022] Acquire a target computing resource selected by a user based on the target recommended resource;

[0023] The resource request is responded to based on the target computing resource.

[0024] In addition, to achieve the above purpose, the present application also proposes a resource management device, the resource management device comprising:

[0025] A resource score determination module, used to determine the resource score based on the current status and historical performance information of the target resource;

[0026] A resource service provider score determination module, used to determine the resource service provider score of each resource service provider based on the resource score;

[0027] The resource recommendation module is used to determine the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving the resource application.

[0028] In addition, to achieve the above objectives, the present application also proposes a resource management device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the resource management method described above.

[0029] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the resource management method described above are implemented.

[0030] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the resource management method described above are implemented.

[0031] This application determines the resource score based on the current status of the target resource and historical performance information; determines the resource service provider score of each resource service provider based on the resource score; and when receiving a resource application, determines the target recommended resource based on the resource demand, the resource score, and the resource service provider score. Since this application recommends target resources to users based on the resource score and the service provider score, compared to the existing method of recommending resources to users based only on resource demand, the above method of this application can more accurately and scientifically predict the reliability of resources, improve the matching degree of resources and demand, and promote the completion of performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0033] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0034] Figure 1 A flowchart of the first embodiment of the resource management method of the present application is provided;

[0035] Figure 2 A schematic diagram of a social ubiquitous computing power management process provided in Example 1 of the resource management method of this application;

[0036] Figure 3 A schematic diagram of a normalized function curve provided in Example 1 of the resource management method of this application;

[0037] Figure 4 A flowchart of the second embodiment of the resource management method of the present application is provided;

[0038] Figure 5 A flowchart of the third embodiment of the resource management method of the present application is provided;

[0039] Figure 6 A schematic diagram of the model training process provided in Example 3 of the resource management method of this application;

[0040] Figure 7 The overall process diagram provided for the third embodiment of the resource management method of this application;

[0041] Figure 8 This is a schematic diagram of the module structure of the resource management device according to an embodiment of the present application;

[0042] Fig. 9 Schematic diagram of the device structure of the hardware operating environment involved in the resource management method in the embodiment of the present application.

[0043] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0046] The main solution of the embodiment of the present application is: determine the resource score according to the current status of the target resource and the historical performance information; determine the resource service provider score of each resource service provider based on the resource score; when receiving a resource application, determine the target recommended resource according to the resource demand, the resource score and the resource service provider score. Since the present application recommends target resources to users based on the resource score and the service provider score, compared with the existing method of recommending resources to users based only on resource demand, the above method of the present application can more accurately and scientifically predict the reliability of resources, improve the matching degree of resources and demand, and promote the completion of performance.

[0047] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a resource management device, etc. The following takes the resource management device as an example to illustrate this embodiment and the following embodiments.

[0048] Based on this, the present application embodiment provides a resource management method, referring to Figure 1 , Figure 1 A flowchart of the first embodiment of the resource management method of the present application is provided.

[0049] In this embodiment, the resource management method includes the following steps:

[0050] Step S10, determining a resource score according to the current status and historical performance information of the target resource;

[0051] It should be noted that the target resource may be the computing power resource of the ubiquitous computing power of society itself. The current state may include the state of the current resource being available or unavailable. The historical fulfillment information may be the historical fulfillment of the target resource, including the number of fulfillments, whether each fulfillment was successful, and other information. The resource score may be the current score of the target resource determined based on the current state and historical fulfillment information. For example, when the current state of the target resource is available, and the historical fulfillment information is 10 fulfillments and 8 successes, the resource score may be 8 / 10+1. The specific strategy for determining the resource score based on the current state of the target resource and the historical fulfillment information may also be reasonably set according to the actual situation, and this embodiment is not limited here.

[0052] It should be understood that ubiquitous social computing power refers to the ubiquitous and readily available distribution of computing resources in every corner of society through technologies such as cloud computing, edge computing, and the Internet of Things. In this computing resource ecosystem, personal computers, smart devices, data centers, etc. work together to provide efficient and flexible computing services, supporting various applications from smart homes to smart cities, from personalized medicine to industry. However, due to the wide distribution and dynamic changes of resources, social ubiquitous computing power faces the problem of low service level agreement (SLA) guarantees, resulting in unstable service reliability and performance. Therefore, improving SLA guarantees is an important issue that needs to be urgently addressed in this field. The SLA scoring algorithm is used to evaluate and quantify the performance of service providers in the service level agreement (SLA). The algorithm compares the actual service performance with the SLA agreement by monitoring key performance indicators (such as availability, response time, failure rate, etc.) and calculates a comprehensive score. This score helps users and service providers understand the quality of service, identify problems and optimize them, thereby ensuring service reliability and customer satisfaction.

[0053] It should be understood that in the relevant scheme, the process of the computing power network managing the ubiquitous computing power of society can refer to Figure 2 , Figure 2 A schematic diagram of the social ubiquitous computing power management process provided in Example 1 of the resource management method of this application. The entire process is divided into three stages: Grid connection stage: The social ubiquitous computing power integrates its own computing power resources into the computing network system. During the grid connection registration process, the resource provider needs to provide the parameters of the resource (including resource address, type, region, validity period, SLA commitment, etc.), and the computing network platform verifies the resources based on these parameters, including SLA verification. After the verification, the resources are officially put on the shelves and sold at a price (resource use rights are rented); Transaction and use stage: Social ubiquitous computing power is rented and used on the trading platform. In this stage, users will rent resources on the computing network trading platform, and provide rental time period information at the same time. The computing power provider will reserve resources in the specified time period, and the computing power scheduling platform will start to execute computing tasks after scheduling the user's computing needs to the resource. When the resource use period expires, the computing power provider (resource party) will offline the resource or stop the user's use rights; Settlement stage: After the transaction is completed, the account is issued and settled, and the resource rental and sale process ends.

[0054] Furthermore, in order to avoid scheduling the computing task of the user to a computing device without quality assurance, which may cause the computing task to fail and damage the interests of the consumer, the step S10 may include: determining the average score of the target resource according to the time decay algorithm, the current state of the target resource and the historical performance information;

[0055] The average score is normalized to obtain a resource score of the target resource.

[0056] It should be noted that the average score of the target resource determined according to the time decay algorithm, the current state of the target resource and the historical fulfillment information can be simply divided into two levels: the fulfillment success (succ) score is 1, and the fulfillment failure (fail) score is -1, and the following single fulfillment score calculation formula is obtained:

[0057]

[0058] Among them, s n Indicates the score of the nth fulfillment. In particular, when n is equal to 0, it indicates the current status of the target resource. If the current target resource is available, it is 1, and if it is unavailable, it is -1.

[0059] The average score of the target resource is then calculated according to the following time decay algorithm:

[0060]

[0061] Among them, x represents the unnormalized score obtained by adding up the resource's previous fulfillment scores after decaying them in time sequence, and then taking the average, which is the average score of the target resource. Among them, N represents the total number of fulfillments, and as a coefficient, it means that the more successful fulfillments are, the greater the comprehensive score is; s n is the score of a single fulfillment, a is the attenuation coefficient, which is a number between (0, 1), the larger the value (1-a) N-n The smaller it is, the faster the score contribution decays. In general, Represents the total score, divided by Get the average score.

[0062] It should be noted that the normalization of the average score to obtain the resource score of the target resource may be performed by normalizing the average score using the following formula:

[0063]

[0064] Among them, Score is used to represent the resource score of the target resource. The above formula normalizes the average score of the target resource to the range of (-1, 1), and finally obtains the resource score in the range of (-1, 1), which is also called the resource SLA comprehensive score Score. Figure 3 , Figure 3 A schematic diagram of a normalized function curve provided for Example 1 of the resource management method of this application.

[0065] In the specific implementation, for example, a GPU resource provided by company A has been fulfilled 10 times in history, represented by numbers 1-10 in ascending time order. Assume that the second fulfillment failed, and the rest were successful. Currently, this GPU is powered off. If the attenuation coefficient a is 0.4, then (1-a) is 0.6. Then x can be obtained as:

[0066]

[0067] The final result of x is 2.5.

[0068] Then, based on the final result of x being 2.5, the normalized score is:

[0069]

[0070] The normalized score is 0.85, that is, the resource score of this GPU resource is 0.85.

[0071] Step S20, determining a resource service provider score of each resource service provider based on the resource score;

[0072] It should be noted that the resource service provider score of each resource service provider is determined based on the resource score, which may be obtained by accumulating the resource scores of the target resources corresponding to each resource service provider.

[0073] Step S30, when receiving a resource application, determining a target recommended resource according to resource demand, the resource score and the resource service provider score.

[0074] It should be noted that the resource application may be a request including resource requirements submitted by a user (computing power purchaser) applying for resources. The resource requirements include rental time period information and required resource basic information. The resource basic information may include resource type, scale, region, SLA commitment, etc. The target recommended resources determined according to the resource requirements, the resource score, and the resource service provider score may be to determine the qualified resources according to the resource requirements, and then select the target recommended resources with higher comprehensive scores from the qualified resources according to the resource score and the resource service provider score. For example, a resource service provider with a higher score is first selected, and then a resource with a higher score is selected from the resource service provider as the target recommended resource. The target recommended resource is then displayed to the user, and the target computing resource selected by the user based on the displayed target recommended resource is obtained, and the resource application is responded to based on the target computing resource, that is, the computing task corresponding to the user's resource application is executed according to the target computing resource.

[0075] This embodiment determines the resource score based on the current status of the target resource and historical performance information; determines the resource service provider score of each resource service provider based on the resource score; and determines the target recommended resource based on the resource demand, the resource score, and the resource service provider score when receiving a resource application. Since this embodiment recommends target resources to users based on the resource score and the service provider score, compared to the existing method of recommending resources to users based only on resource demand, the above method of this embodiment can more accurately and scientifically predict the reliability of resources, improve the matching degree of resources and demand, and promote the completion of performance.

[0076] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 , Figure 4 The flowchart provided in the second embodiment of the resource management method of the present application, step S20, further includes the following steps:

[0077] Step S201: Determine resource type information of a resource service provider, wherein the resource type information includes resource type and weight information corresponding to the resource type;

[0078] It should be noted that the weight information corresponding to the resource type can be customized according to the price of the resource, the timeliness and stability of the resource. The resource type can be obtained by classifying the resources owned by the resource service provider.

[0079] Step S202: determining the resource service provider score of each resource service provider according to the resource type information and the resource score.

[0080] It should be noted that the resource service provider score of each resource service provider determined according to the resource type information and the resource score may be determined by the following formula:

[0081]

[0082] Among them, M represents the number of resource types; Score r represents the comprehensive SLA score of the r-th resource of the resource service provider (i.e., the resource scores of the r-th resources of the resource service provider are added together to obtain the comprehensive SLA score of the r-th resource), c r is the weight of the rth resource, which is a number greater than 0. The simplest way to determine it is by the price, timeliness, and stability of the resource. It represents the weighted sum of all resource scores, and the denominator represents the sum of weights, divided by the denominator It represents the weighted average score of all resources.p This score is used to evaluate the SLA score of the resource service provider, that is, the resource service provider score.

[0083] Because Score r The value range of is (-1, 1), so when all values ​​are -1, The value is the smallest; when all values ​​are 1, The value is the largest. So we can conclude that Score p The value range of is also (-1, 1), that is, the resource party SLA score is also normalized.

[0084] In the specific implementation, for example, Company A provides three types of resources: GPU1, GPU2, and GPU3, each of which has fulfilled 10 times. The weights are set to 0.3, 0.3, and 0.4 according to the resource specifications. GPU1 failed to fulfill the second contract and is currently in a power-off state; GPU1 failed to fulfill the third contract and is currently available; GPU3 fulfilled all contracts successfully and is currently available. According to the score of a single resource, the normalized scores of the three resources can be obtained as follows: 0.85, 0.99, and 1. The comprehensive score of the resource party is obtained:

[0085]

[0086] It can be seen that the resource service provider score of Company A is 0.95.

[0087] This embodiment determines the resource type information of the resource service provider, and the resource type information includes the resource type and the weight information corresponding to the resource type; and determines the resource service provider score of each resource service provider based on the resource type information and the resource score. This embodiment determines the resource score of the target resource based on the real-time status and performance history of the resource, and determines the resource service provider score of the resource service provider based on the resource score of the target resource. When recommending resources to users, it can recommend more matching resources to users based on the performance of the resource service provider and the resources, thereby improving the user experience.

[0088] Based on the above embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 5 , Figure 5 The flowchart provided in the second embodiment of the resource management method of the present application, step S30, further includes the following steps:

[0089] Step S301: upon receiving a resource application, determining resource requirements according to the resource application;

[0090] It should be noted that the resource demand may include the rental time submitted by the resource purchaser as well as the resource type, scale, region, SLA commitment and other information.

[0091] Step S302: input the resource demand, the resource score, the resource service provider score and basic resource information into a preset resource recommendation model to obtain target recommended resources.

[0092] It should be noted that the preset resource recommendation model may be a pre-trained model for recommending target resources based on resource requirements, the resource rating, the resource service provider rating, and basic resource information.

[0093] Furthermore, in order to reasonably recommend target resources to users, before step S302, the method further includes: obtaining sample data, the sample data including sample resource requirements, actual allocated resources, user satisfaction and resource rating information;

[0094] The initial deep learning model is trained based on the sample data to obtain a preset resource recommendation model.

[0095] It should be noted that the initial deep learning model is trained based on the sample data to obtain the preset resource recommendation model as follows: Step 1: Convert the user's resource demand into features (vectors) and input them into the initial deep learning model. The resource demand includes at least the characteristics of resource type, quantity, region, SLA guarantee, price tendency, and rental time.

[0096] Step 2: Convert the resource rating information into features (vectors) and input them into the initial deep learning model. For example, convert the user's likes, five-star reviews, favorites and other data into integers between 1 and 10.

[0097] Step 3: Convert the user's evaluation (i.e., user satisfaction) after the final fulfillment of the resources corresponding to steps 1 and 2 into the target features of model training (also a vector, used for calculating the loss function during the training process) and input it into the initial deep learning model.

[0098] Step 4: Use the features input in the above three steps to train the model. The model type can be selected from various deep learning models.

[0099] In the specific implementation, please refer to Figure 6 , Figure 6A schematic diagram of the model training process provided for the third embodiment of the resource management method of this application. For example, the score of the GPU resource provided by Company A is 0.85, the score of the resource party is 0.95, the number of resources is 1, located in Beijing, the SLA level is S-level, the price range tends to be 1000-1500, and the rental time is Wednesday. Without loss of generality, the attributes can be converted into feature vectors: [85, 95, 1, 100190, 5, 100, 3], where the first two items are obtained by multiplying the attribute value by 100, the third item uses the original data, the fourth item uses the postal code, the fifth item divides the SLA into 5 levels from 1-5, the sixth item is obtained by dividing the actual price by 10, and the last item 1-7 represents from Monday to Sunday. Corresponding to this resource, the user gave a five-star rating and collected it, but did not forward it. It can be considered that the target feature is equal to 5+1+1=7. Input a batch of training data like <[85, 95, 1, 100190, 5, 100, 3], 7> into the model, such as GNN. The GNN parameters can be set to train 10 times, use mean square error as the calculation loss function, and use the stochastic gradient descent algorithm. Finally, a relatively stable preset resource recommendation model is obtained. In order to make the recommendation effect of the preset resource recommendation model better, the user's satisfaction with the resources recommended by the preset resource recommendation model during the model service process can also be obtained, and the preset resource recommendation model can be further iteratively trained based on the satisfaction, resource demand and resource score.

[0100] When a user requests a resource with a new resource requirement, the latest calculated resource score can be used together with basic information such as the resource's geographical location and resource price to calculate the recommended value of the candidate resource, and the resource with the highest recommended value can be recommended to the user. The user selects the intended resource based on the resources displayed on the front desk and the resource party's score, and then performs a new round of fulfillment. After fulfillment is completed, the user evaluation data will continue to be fed back to the model training system for iteration to continuously improve the effect.

[0101] In the specific implementation, please refer to Figure 7 , Figure 7 The overall process diagram provided for the third embodiment of the resource management method of this application; the overall process of this embodiment is described as follows:

[0102] Step 1: The network front end (the front end display module of the resource management device) registers the resource information of the network connection, including the information of the resource party, the resource type, scale, region, SLA commitment, etc. of this network connection, and transmits this information to the resource information center (the storage module of the resource management device) for storage. This step corresponds to the network connection stage mentioned in the above embodiment.

[0103] Step 2: The ubiquitous computing power connected to the grid is leased and settled, and the fulfillment system (the fulfillment module of the resource management device) tracks the entire life cycle and records the completion degree and quality of fulfillment. This step corresponds to the transaction and use phases mentioned in the above embodiment, as well as the final settlement phase.

[0104] Step 3: The fulfillment system drives the resource scheduling system (scheduling module of the resource management device) to allocate actual resources and execute computing tasks according to the commitment.

[0105] Step 4: The fulfillment system transmits the fulfillment results of this round, the historical fulfillment of the resource, and the historical fulfillment of the resource party to the resource scoring system (the evaluation module of the resource management device).

[0106] Step 5: The resource scheduling system synchronizes the resource status to the resource scoring system in real time or periodically.

[0107] Step 6: The resource scoring system calculates the comprehensive score of the resource based on the latest resource status, previous resource fulfillment, and the latest score of the resource party according to the algorithm that decays over time (see steps S10 and S20 above). The calculated score is fed back to the front desk of the computing network for display; on the other hand, it is synchronized to the resource recommendation system (recommendation module of the resource management device) for the next decision-making.

[0108] Step 7: The resource information center passes the basic information of the resource to the resource recommendation system for use in the next decision-making process.

[0109] Step 8: When a user applies for resources in a new round, the resource recommendation system makes recommendations based on the basic resource information and comprehensive scores delivered in steps 6 and 7. Finally, the first few recommended results are presented to the user for selection.

[0110] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the resource management method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0111] This application also provides a resource management device, please refer to Figure 8 , the resource management device comprises:

[0112] A resource score determination module 10, configured to determine a resource score based on the current status and historical performance information of the target resource;

[0113] A resource service provider score determination module 20, configured to determine a resource service provider score of each resource service provider based on the resource score;

[0114] The resource recommendation module 30 is used to determine the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving a resource application.

[0115] This embodiment determines the resource score based on the current status of the target resource and historical performance information; determines the resource service provider score of each resource service provider based on the resource score; and determines the target recommended resource based on the resource demand, the resource score, and the resource service provider score when receiving a resource application. Since this embodiment recommends target resources to users based on the resource score and the service provider score, compared to the existing method of recommending resources to users based only on resource demand, the above method of this embodiment can more accurately and scientifically predict the reliability of resources, improve the matching degree of resources and demand, and promote the completion of performance.

[0116] The resource management device provided by the present application adopts the resource management method in the above embodiment, which can solve the technical problem of low efficiency of resource management in the existing ubiquitous computing network. Compared with the prior art, the beneficial effects of the resource management device provided by the present application are the same as the beneficial effects of the resource management method provided by the above embodiment, and the other technical features in the resource management device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0117] The present application provides a resource management device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the resource management method in the above-mentioned embodiment one.

[0118] Reference below Fig. 9 , which shows a schematic diagram of the structure of a resource management device suitable for implementing the embodiment of the present application. The resource management device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The resource management device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0119] like Fig. 9As shown, the resource management device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the resource management device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the resource management device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a resource management device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0120] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a 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, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0121] The resource management device provided by the present application adopts the resource management method in the above embodiment, which can solve the technical problem of low efficiency of resource management in the existing ubiquitous computing network. Compared with the prior art, the beneficial effects of the resource management device provided by the present application are the same as the beneficial effects of the resource management method provided by the above embodiment, and the other technical features in the resource management device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0122] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0123] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0124] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the resource management method in the above-mentioned embodiment.

[0125] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, 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 this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0126] The computer-readable storage medium may be included in the resource management device; or may exist independently without being assembled into the resource management device.

[0127] Computer program code for performing the operations of the present application 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 a separate 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 through 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).

[0128] 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 application. 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 alternative implementations, 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.

[0129] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0130] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned resource management method, and can solve the technical problem of low efficiency of resource management in the existing ubiquitous computing network. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the resource management method provided in the above-mentioned embodiment, and will not be repeated here.

[0131] The present application also provides a computer program product, including a computer program, which implements the steps of the resource management method as described above when executed by a processor.

[0132] The computer program product provided by this application can solve the technical problem of low efficiency of resource management in existing ubiquitous computing networks. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as those of the resource management method provided by the above embodiment, which will not be described in detail here.

[0133] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A resource management method, characterized in that: The resource management method comprises the following steps: Determine resource scores based on the current status and historical performance information of the target resource; Determine a resource service provider score of each resource service provider based on the resource score; When a resource application is received, a target recommended resource is determined based on the resource demand, the resource score, and the resource service provider score.

2. The resource management method according to claim 1, characterized in that: The step of determining the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving the resource application comprises: When receiving a resource application, determining resource requirements based on the resource application; The resource demand, the resource score, the resource service provider score and basic resource information are input into a preset resource recommendation model to obtain target recommended resources.

3. The resource management method according to claim 2, characterized in that: Before the step of inputting the resource demand, the resource score, the resource service provider score and the basic resource information into the preset resource recommendation model to obtain the target recommended resource, the step further includes: Acquire sample data, wherein the sample data includes sample resource requirements, actual allocated resources, user satisfaction, and resource rating information; The initial deep learning model is trained based on the sample data to obtain a preset resource recommendation model.

4. The resource management method according to claim 1, characterized in that: The step of determining a resource score according to the current state and historical performance information of the target resource comprises: Determine the average score of the target resource based on the time decay algorithm, the current status of the target resource and the historical performance information; The average score is normalized to obtain a resource score of the target resource.

5. The resource management method according to any one of claims 1 to 4, characterized in that: The step of determining the resource service provider score of each resource service provider based on the resource score comprises: Determine resource type information of the resource service provider, wherein the resource type information includes resource type and weight information corresponding to the resource type; The resource service provider score of each resource service provider is determined according to the resource type information and the resource score.

6. The resource management method according to any one of claims 1 to 4, characterized in that: After the step of determining the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving the resource application, the method further includes: Acquire a target computing resource selected by a user based on the target recommended resource; The resource request is responded to based on the target computing resource.

7. A resource management device, characterized in that: The resource management device comprises: A resource score determination module, used to determine the resource score based on the current status and historical performance information of the target resource; A resource service provider score determination module, used to determine the resource service provider score of each resource service provider based on the resource score; The resource recommendation module is used to determine the target recommended resource according to the resource demand, the resource score and the resource service provider score when receiving the resource application.

8. A resource management device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the resource management method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the resource management method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the resource management method according to any one of claims 1 to 6 are implemented.

Images