Resource evaluation method and device
By constructing a risk parameter mapping table and a cardinal resource table, the number of resources users participate in the target business is automatically calculated, which solves the problem of low manual evaluation efficiency in the existing technology, and achieves efficient and accurate resource evaluation and configuration.
Patent Information
- Application Number
- CN202411160742.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-13
AI Technical Summary
In the prior art, manual evaluation of the resources required by users to participate in the target business is costly and inefficient, making it difficult to respond quickly to market demand, and effectively reducing the negative impact of different business risks on resources.
By constructing a risk parameter mapping table, the risk parameters and cardinal resources of users when participating in the target business are determined based on the business historical data, the number of resources that users need to provide is automatically calculated, and the evaluation efficiency and accuracy are improved.
Automatic resource evaluation based on historical data is realized, which reduces the need for manual intervention, shortens decision-making time, improves evaluation efficiency and resource allocation accuracy, and can respond to business changes more quickly.
Smart Images
Figure CN119130134A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present specification relate to the field of computer technology, and in particular to a resource evaluation method. Background Art
[0002] With the development of technology, the impact of different risks on target businesses facing users is becoming more and more obvious. The increase in high-risk factors of users will lead to an increase in the overall risk level of the business. Therefore, different treatment methods need to be adopted for different risks to effectively reduce the negative impact of risks on the business.
[0003] Currently, the risk consideration angles and the number of business-related risks for different businesses are different. Manually assessing the risk of each user to determine the resources each user needs to provide to participate in the target business is costly and inefficient. In order to quickly respond to market demand, reduce the cost of user assessment and improve the efficiency of user assessment, a resource assessment method is urgently needed to meet the risk configuration needs of different businesses. Summary of the invention
[0004] In view of this, an embodiment of this specification provides a resource evaluation method. One or more embodiments of this specification also relate to a resource evaluation device, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.
[0005] According to a first aspect of an embodiment of this specification, a resource evaluation method is provided, comprising:
[0006] Receiving a target service selected by a user and at least one service configuration information;
[0007] Determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, and generate the risk parameters corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameters corresponding to each business configuration information are determined according to the historical business configuration information and the historical business results corresponding to each historical business in the business history data, and the risk sub-parameters corresponding to each business configuration information represent the influence of each business configuration information on the business result corresponding to the target business;
[0008] Determine the cardinality resource corresponding to the target business, and determine the participation resource corresponding to the user according to the risk parameter and the cardinality resource, wherein the participation resource is the amount of resources that the user needs to provide when participating in the target business.
[0009] According to a second aspect of an embodiment of this specification, a resource evaluation device is provided, including:
[0010] A receiving module, configured to receive a target service selected by a user and at least one service configuration information;
[0011] A generating module is configured to determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, and generate the risk parameters corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameters corresponding to each business configuration information are determined according to the historical business configuration information and the historical business results corresponding to each historical business in the business history data, and the risk sub-parameters corresponding to each business configuration information represent the influence of each business configuration information on the business result corresponding to the target business;
[0012] The determination module is configured to determine the cardinality resources corresponding to the target business, and determine the participation resources corresponding to the user according to the risk parameters and the cardinality resources, wherein the participation resources are the amount of resources that the user needs to provide when participating in the target business.
[0013] According to a third aspect of an embodiment of this specification, a computing device is provided, including:
[0014] Memory and processor;
[0015] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above resource evaluation method are implemented.
[0016] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned resource evaluation method are implemented.
[0017] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instruction, which implements the steps of the above-mentioned resource evaluation method when executed by a processor.
[0018] An embodiment of the present specification implements the following steps: receiving a target business selected by a user and at least one business configuration information; determining a risk sub-parameter corresponding to each business configuration information according to a risk parameter mapping table, and generating a risk parameter corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameter corresponding to each business configuration information is determined according to historical business configuration information and historical business results corresponding to each historical business in business history data, and the risk sub-parameter corresponding to each business configuration information characterizes the impact of each business configuration information on the business result corresponding to the target business; determining a cardinality resource corresponding to the target business, and determining a participating resource corresponding to the user according to the risk parameter and the cardinality resource, wherein the participating resource is the amount of resources that the user needs to provide when participating in the target business.
[0019] By applying the solution of the embodiments of this specification, the amount of resources that a user needs to provide when participating in a target business is automatically determined through a risk parameter mapping table constructed from historical data, thereby improving the efficiency of user evaluation based on historical data while ensuring the accuracy of user evaluation. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 is a flow chart of a resource evaluation method provided by an embodiment of this specification;
[0021] Figure 2 is a process flow chart of an insurance resource evaluation method provided by an embodiment of this specification;
[0022] Figure 3 is a schematic diagram of the structure of a resource evaluation device provided by an embodiment of this specification;
[0023] Figure 4 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION
[0024] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.
[0025] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.
[0026] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0027] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0028] In this specification, a resource evaluation method is provided. This specification also relates to a resource evaluation device, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.
[0029] In a wide range of business areas, different risk factors will lead to different resource requirements. The more high-risk factors there are, the higher the overall risk is, so resources need to be reasonably allocated according to the specific risks. In addition, different business types involve different risk considerations and quantities, and professionals usually need to invest a lot of time and energy in manual calculations to ensure the reasonable allocation of resources.
[0030] In the insurance field, different risks mean different claims rates. The more high-risk customers there are, the higher the risk of claims rate, so different premiums need to be set for different risks. In addition, different insurance products have different risk consideration angles and quantities. The cost of manual premium calculation by insurance actuaries is huge, which leads to low efficiency in project completion.
[0031] In multi-party computing collaboration, computing power allocation not only considers the resource capabilities of each party, but also must comprehensively assess the risk level of each participant. By matching the importance of the task with the risk tolerance of each party, dynamically adjusting the task allocation, ensuring that high-risk tasks are undertaken by participants with sufficient security and stability, and at the same time, the cost of effective monitoring and control through manual computing load, technical uncertainty, and data security is huge, which leads to low efficiency in project completion.
[0032] See also Figure 1 , Figure 1 A flow chart of a resource evaluation method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.
[0033] Step 102: Receive a target service selected by a user and at least one service configuration information.
[0034] In actual applications, the target business is a project involving multiple parties, which is a business that can be jointly realized by utilizing the resources of different parties. The business configuration information is the key parameters and setting information required to evaluate user participation in the business, which is used to ensure the normal execution of the business and optimize the results of the business execution.
[0035] For example, the target business can be understood as a business or project jointly participated by all parties in a specific field or environment. It not only includes specific service content in traditional business fields, such as insurance-type businesses such as "accidental medical treatment" and "accidental disability", but also covers a wider range of technical application scenarios, such as "federated learning" and "distributed computing" and other computing tasks involving multiple parties. The target business usually involves the collaboration and resource integration of multiple parties in order to achieve common business goals or technical achievements.
[0036] It should be noted that, taking federated learning as an example, different participants contribute their computing power to jointly train and optimize the model, ensuring higher model accuracy without sharing data. In the "accidental medical" related business, different participants participate in and support the medical insurance service by providing resources (such as premiums), thereby sharing risks and ensuring the effective operation of the service. These examples illustrate that the target business not only includes specific services in the traditional business field, but also involves complex computing and resource integration tasks involving multi-party collaboration.
[0037] Business configuration information can be understood as all the key parameters and setting information required to evaluate users when they participate in a certain business. This information is used to conduct a more comprehensive analysis of the user's characteristics, behaviors and related conditions to ensure the normal operation and optimal configuration of the business. Taking the insurance category of business as an example, the business configuration information includes "waiting period", "insurance period", "age", etc., which are used to evaluate the user's risk status and needs. Taking the multi-party computing category of business as an example, the business configuration information is "device memory", "device idle computing power" and other parameters, which are used to evaluate the user's contribution to the computing task. By analyzing and integrating this information, more accurate business configuration and more efficient resource utilization can be achieved.
[0038] Furthermore, receiving the target business selected by the user includes receiving an evaluation request sent by the user, the evaluation request including at least one business to be evaluated and at least one business configuration information corresponding to each business to be evaluated; determining any one business to be evaluated among the businesses to be evaluated as the target business, and determining the business configuration information corresponding to the target business.
[0039] In actual applications, the device used by the user to send the evaluation request can be a browser, an APP (Application), or a web application such as H5 (HyperText Markup Language 5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client 100 can be based on the software development kit (SDK, Software Development Kit) of the corresponding service provided by the server 200, such as based on the real-time communication (RTC, Real Time Communication) SDK development and acquisition. The device used by the user to send the evaluation request can be deployed in an electronic device, and needs to rely on the operation of the device or some APPs in the device to operate. For example, the electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, mailbox clients, social platform software, etc.
[0040] Step 104: Determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, and generate the risk parameters corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameters corresponding to each business configuration information are determined based on the historical business configuration information and historical business results corresponding to each historical business in the business history data, and the risk sub-parameters corresponding to each business configuration information represent the impact of each business configuration information on the business results corresponding to the target business.
[0041] In actual applications, the risk parameter mapping table is a data table that stores the risk sub-parameters corresponding to each business configuration information. The risk sub-parameters are the numerical values corresponding to the impact of each business configuration information on the business results. The risk parameters are the risk level of user participation in the overall target business. The business historical data are the relevant data accumulated in the past business corresponding to the target business. The historical business configuration information is the setting information used for evaluation and user targeting the target business risks in the business that has been executed in the past. The historical business results refer to the final results or effects achieved in the past business.
[0042] Exemplarily, risk sub-parameters can be understood as different configuration information and their potential impact on the business results of the target business. Risk parameters can be understood as weighted values or indexes obtained by integrating all risk sub-parameters, reflecting the current user's risk level in the overall business. They are calculated based on the different configuration information selected by the user and their potential impact on the business results. Specifically, risk parameters can be formed into a quantitative indicator by weighted averaging, accumulation or other algorithm processing of each risk sub-parameter to represent the user's risk level in the target business. This parameter directly affects the accuracy of subsequent resource allocation and decision-making. In federated learning, suppose we have a risk parameter mapping table that maps the risk impact of different configuration items on model accuracy, privacy protection, computing resources, etc. based on the business configuration information and business results in historical data.
[0043] Taking the target business of federated learning as an example, the business configuration information selected by a certain participant includes device computing power: 1.2TFLOPS (trillion floating-point operations per second), network stability: 60% (that is, network availability or uptime is 95%), and data quality: 0.25 (based on the integrity and accuracy of data in historical data, the full score is 1.0). According to the risk parameter mapping table obtained from historical data, the risk sub-parameter corresponding to the device computing power of 1.2TFLOPS is 0.7; the risk sub-parameter corresponding to the network stability of 60% is 1.1; the risk sub-parameter corresponding to the data quality of 0.25 is 1.3. It is then determined that the risk parameter of the participant can be calculated by multiplication to obtain the risk parameter of the participant as 1.001, which means that the risk of the participant is medium, and the participant can provide 1.001 times the base number of computing resources as a guarantee for the target business.
[0044] Taking the target business as accidental medical insurance as an example, the business configuration information selected by a user includes waiting period: 0 days (indicating the time when the insurance takes effect), insurance period: 180 days (indicating the duration of the insurance), age: 26, and insurance amount: 1000. According to the risk parameter mapping table obtained from historical data, the risk sub-parameter corresponding to the waiting period of 0 days is 1.05, the risk sub-parameter corresponding to the insurance period of 180 days is 0.7, the risk sub-parameter corresponding to the age of 26 is 0.5, and the risk sub-parameter corresponding to the insurance amount of 1000 is 1.0. Subsequently, it is determined that the risk parameter of the participant can be calculated by the multiplication method to obtain the risk parameter of the participant as 0.3675, which means that the risk of the participant is relatively low, and thus the user provides 0.3675 times the base amount of resources as a guarantee when participating in the target business.
[0045] It should be noted that the risk parameter mapping table can be stored using any data storage method, such as text file txt, table file csv and relational database, etc., and this manual does not impose any restrictions on this.
[0046] By accurately assessing the risk level of users when participating in the business, we can ensure the rationality and effectiveness of resource allocation, while reducing the impact of potential risks to achieve stable operation and overall optimization of the business.
[0047] Considering that in order to improve the accuracy of resource evaluation for users, it is necessary to improve the accuracy of determining the risk sub-parameters corresponding to each business configuration selected by the user, before determining the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, the method further includes:
[0048] Acquire at least one business history data corresponding to the target business;
[0049] Constructing a target business risk parameter mapping table corresponding to the target business according to the historical data of each business;
[0050] A risk parameter mapping table is obtained based on a target business risk parameter mapping table corresponding to at least one target business.
[0051] In practical applications, the target business risk parameter mapping table is a data table storing risk sub-parameters corresponding to each business configuration in the target business. The target business risk parameter mapping table can be understood as a data table storing the potential impact of each business configuration information on the business execution result obtained when the target business is completed.
[0052] Exemplarily, there are many situations for the target business. For example, in the category of business that requires the participation of multiple parties, the target business includes collaborative tasks in multiple fields such as federated learning and distributed computing; in the category involving insurance business, the target business includes accidental medical treatment, accidental disability and other insurance services. This specification does not impose any restrictions on the comparison. Since the target business has many situations, different target businesses may have different business configuration information, and the same business configuration information has different potential impacts on different target businesses. Therefore, the parameter mapping table stores the target business parameter mapping table corresponding to each target business.
[0053] It should be noted that the method of obtaining the risk parameter mapping table based on the target business risk parameter mapping tables corresponding to multiple target businesses can be direct splicing. Considering the limitation of storage space, the business configuration information can be weighted and integrated for each target business configuration information to generate an overall parameter mapping table for the above-mentioned multiple target business types, and so on. This manual does not impose any restrictions on the method of obtaining the risk parameter mapping table.
[0054] In one embodiment provided in this specification, taking insurance-type business as an example, the risk parameter mapping table is shown in Table 1:
[0055] Table 1
[0056] Target Business Business Configuration Category Business configuration information Risk sub-parameters Accidental medical treatment Waiting period Day 0 1.05 Accidental medical treatment Waiting period 15 days 0.96 Accidental medical treatment Insurance Period 180, 365 days 0.70 Accidental medical treatment Insurance Period 15. 30 days 0.10 Accidental Disability Waiting period Day 0 1.15 Accidental Disability Waiting period 15 days 0.99 Accidental Disability Insurance Period 180, 365 days 0.60 Accidental Disability Insurance Period 15. 30 days 0.30 Accidental Death Waiting period Day 0 1.46 Accidental Death Waiting period 15 days 1.01 Accidental Death Insurance Period 180, 365 days 0.80 Accidental Death Insurance Period 15. 30 days 0.20
[0057] By configuring a target business risk parameter mapping table for each target business, you can accurately assess and quantify various risks in the business, ensuring that reasonable decisions can be made based on objective data in different situations, thereby optimizing resource allocation, improving business stability, and effectively controlling potential risks in complex environments, thereby improving the efficiency and reliability of overall business operations.
[0058] Furthermore, a target business risk parameter mapping table corresponding to the target business is constructed according to the historical data of each business, including:
[0059] Parsing the target service history data to obtain the history service result, history participating resources and at least one history service configuration information, wherein the target service history data is any one of the history data of each service corresponding to the target service;
[0060] Determine the historical impact factor corresponding to each historical service configuration information according to the historical service results and the historical participating resources;
[0061] According to the historical impact factors corresponding to each historical business configuration information in each business historical data, the risk sub-parameters corresponding to each historical business configuration information are determined, and a target business risk parameter mapping table is constructed according to the risk sub-parameters corresponding to each historical business configuration information.
[0062] In practical applications, the historical impact factor is the impact of the business configuration information on the business results in the historical data of the target business corresponding to a certain historical business. Exemplarily, the historical impact factor can be understood as the contribution of specific business configuration information to the final business results in historical data. In the case of insurance business, it is the impact of the insurance period on the customer's risk exposure, and it can also be understood as the weight of the impact of the customer's age on the claim ratio; in federated learning, the contribution of the computing power of different devices to the model training time can also be understood as the impact of network stability on the model convergence speed, and it can also be understood as the weight of the impact of data quality on the final model accuracy. These are specific manifestations of historical impact factors, and this manual does not impose any restrictions on this.
[0063] It should be noted that there are many methods for determining the historical impact factors corresponding to each historical business configuration information based on historical business results and historical participating resources. The regression analysis method can be used to quantitatively evaluate the impact of each business configuration information on the final result using the business results and participating resources in the historical data. The decision tree or random forest model can also be used to analyze the contribution of different configuration information combinations to the business results and extract key influencing factors from them. The Bayesian network-based method can also be used to establish a probabilistic association between configuration information and business results, and then determine the impact weight of each configuration information. The specific selection of these methods depends on the business scenario and data characteristics, and this manual does not impose any restrictions on this.
[0064] It should be noted that there are multiple methods for determining the risk sub-parameters corresponding to each historical business configuration information based on the historical impact factors corresponding to each historical business configuration information in the historical data of each business. The historical impact factors can be combined with the sensitivity of the business results through a linear weighted method to calculate the risk sub-parameters of each configuration information. Cluster analysis can also be used to classify similar situations in historical data, and divide the risk levels according to the performance of different categories to determine the risk sub-parameters. Monte Carlo simulation can also be used to iterate historical data multiple times using random sampling methods to observe the risk performance of different configuration information under various circumstances, thereby deriving the corresponding risk sub-parameters. These methods can be selected and adjusted according to specific needs, and this manual does not impose any restrictions on this.
[0065] Obtaining the risk sub-parameters corresponding to each historical business configuration information through historical data is actually mining the objective laws of the association between the results of historical business configuration information in the data, revealing the long-term impact of different business configuration information on the final business results. For example, a shorter waiting period may lead to a higher frequency of claims, while a longer insurance period may correspond to a more stable risk management effect. By analyzing these data, the degree of impact of different configuration information on business results in historical data can be quantified. In addition, the statistical relationship between business configuration information and risk level is revealed by analyzing historical data. For example, some business configuration information exhibits high-risk or low-risk characteristics under certain conditions. By analyzing these historical data, the key factors affecting risk can be found, thereby generating more accurate risk sub-parameters. In addition, the data also reflects the long-term impact of specific configuration information combinations on business stability and results. Through regression analysis or machine learning models of large-scale data, the interaction effects between different configuration information can be captured, and which combinations have historically led to higher risks or lower volatility can be found. By mining these laws, it is ensured that decisions that conform to objective laws can be made based on historical data in the new business environment, and ultimately the optimal allocation of resources and effective control of risks can be achieved. The mining of these rules provides data support for the generation of risk sub-parameters, ensuring that the business decision-making process is more in line with historical experience and actual needs, and improving the stability and efficiency of the business.
[0066] Further, the risk sub-parameters corresponding to each business configuration information are determined according to the risk parameter mapping table, including:
[0067] Determine a target business risk parameter mapping table corresponding to the target business in the risk parameter mapping table;
[0068] The risk sub-parameters corresponding to each business configuration information are determined according to the target business risk parameter mapping table.
[0069] Since there are many cases for target businesses, different target businesses may have different business configuration information, and the same business configuration information may have different potential impacts on different target businesses. Therefore, when determining the risk sub-parameters corresponding to each business configuration information, it is necessary to determine the target business parameter mapping table corresponding to the target business selected by the user in the parameter mapping table, thereby improving the stability and efficiency of the business.
[0070] Step 106: Determine the cardinality resources corresponding to the target business, and determine the participation resources corresponding to the user according to the risk parameter and the cardinality resources, wherein the participation resources are the amount of resources that the user needs to provide when participating in the target business.
[0071] In actual applications, the base resource is a reference value of resources required to participate in the target service, and the participating resource is the resource required to be provided by the user to participate in the target service according to the service configuration information provided by the user.
[0072] Exemplarily, the cardinality resource can be understood as the basic amount of resources required to participate in the target business, that is, the resources that the user must provide without considering any risk factors. This is a baseline value used to ensure that the participating parties have the resources to meet the basic needs of the target business. In actual applications, the cardinality resources will be adjusted according to the risk parameters of each user to ensure that the resource allocation is both reasonable and effective. Since the risk parameter can be less than 1, the resources that the end user needs to provide may be lower than the cardinality resources, reflecting the lower risk of the user.
[0073] Participation resources can be understood as the responsibilities or commitments that users or participants must assume to support the successful operation of the target business. This is not just the investment of physical resources or funds, but also includes guarantees for business results, support for business stability, and the ability to take higher risks when necessary. For example, in insurance projects, users provide corresponding insurance coverage when participating in the target business to guarantee the correct execution of the target business. In multi-party computing projects, participants provide corresponding computing power or storage space when participating in the target business to guarantee the correct execution of the target business, etc. Participation resources reflect the contribution and risk-taking level of the participants in the target business to ensure that the entire business process can proceed smoothly and achieve the expected goals.
[0074] Further, determining the cardinality resource corresponding to the target service includes:
[0075] Acquire at least one business history data corresponding to the target business;
[0076] The cardinality resources corresponding to the target business are determined according to the historical data of each business.
[0077] In an embodiment provided in this specification, insurance-type businesses are used as target businesses and the cardinality resources corresponding to each target business are shown in Table 2:
[0078] Table 2
[0079] Target Project Base resources Accidental medical treatment 188.888 Accidental Disability 3.333 Accidental Death 0.465 Accidental Death / Disability 7.777
[0080] Since target businesses have various situations, different target businesses will have different base resources due to the complexity of the business, the risk level of the participants and the differences in resource requirements. The corresponding resource baseline values of different types of target businesses will be adjusted according to the business historical data of the business results obtained during the operation to ensure the effectiveness and stability of the business.
[0081] Further, determining the cardinality resource corresponding to the target service according to the historical data of each service includes:
[0082] Analyze the historical data of each business to obtain the historical business results and historical participating resources corresponding to the historical data of each business;
[0083] The cardinality resources corresponding to the target business are generated according to the historical business results and historical participating resources corresponding to the historical data of each business.
[0084] It should be noted that there are many methods to determine the cardinality resources corresponding to the target business based on historical business results and historical participating resources. The regression analysis method can be used to quantitatively evaluate the basic resource volume required for each business in history using the business results and participating resources in historical data. The decision tree or random forest model can be used to analyze the basic requirements of different business types and extract key resource elements from them. The Bayesian network-based method can also be used to establish a probabilistic association between resources and business results, and then determine the cardinality resources of each target business. The specific selection of these methods depends on the business scenario and data characteristics, and this manual does not impose any restrictions on this.
[0085] In one embodiment provided in this specification, the target business is the insurance business, and the cardinal resources are determined by analyzing the relationship between the processing results of historical insurance policies and the premium amount. The historical data are the compensation amount and premium amount of each insurance policy in the past five years. Through the analysis of these data, we found that the average actual income of each insurance policy (i.e., the premium amount minus the compensation amount) is 300 yuan. At the same time, according to the compensation amount and premium amount of each insurance policy, the average actual yield of each policy can be calculated to be 15%, that is, the actual income accounts for 15% of the premium amount. In order to ensure that the insurance company can maintain this level of income in the current business, the cardinal resources can be calculated as follows: cardinal resources = actual income / actual yield = 300 yuan / 0.15 = 2000 yuan. This 2000 yuan is the cardinal resource of each insurance policy, which is the minimum premium amount set by the company to ensure the expected income.
[0086] In another embodiment provided in this specification, the target business is a federated learning business, and the cardinality resources are determined by analyzing the relationship between the computing contribution of each participant in history and the model performance. Assume that the historical data contains the computing power input of each participant (historical participating resources) and the corresponding model accuracy improvement (historical business results). After analyzing the above historical data, it is determined that each participant needs to provide at least 300TFLOPS of computing power to ensure that the model accuracy is improved by 1%. Assuming that the model accuracy is required to be improved by 5% in the new target business, the cardinality resources are calculated as follows: cardinality resources = 300TFLOPS × 5 = 1500TFLOPS. This 1500TFLOPS is the minimum computing power contribution that each participant must provide in the target business to ensure that the model can achieve the expected level of accuracy.
[0087] Obtaining the cardinality resources of each target business through historical data is actually to explore the objective laws between business needs and results in the data, and reveal the amount of basic resources required by different businesses in historical data. For example, in the insurance business, cardinality resources reflect the relationship between the premium amount and the actual income in the historical data, while in multi-party calculations, cardinality resources reflect the relationship between the calculation contribution of the participants and the improvement of model accuracy. By analyzing these data, the basic demand for resources of different business types in historical data can be quantified. In addition, the statistical relationship between business demand and resource level is revealed through the analysis of historical data. For example, some businesses show high or low demand characteristics under specific conditions. By analyzing these historical data, the key factors affecting resource demand can be found, thereby generating more accurate cardinality resources.
[0088] In addition, the data also reflects the long-term impact of specific business types on resource demand and stability results. Through regression analysis or machine learning models of large-scale data, it is possible to capture the interaction effects between different business needs and find out which combinations have historically led to higher resource demand or lower volatility. By mining these rules, we can ensure that in the new business environment, we can make decisions that conform to objective laws based on historical data, and ultimately achieve optimal resource allocation and effective control of the business. The mining of these rules makes the generation of cardinal resources data-supported, ensuring that the business decision-making process is more in line with historical experience and actual needs, and improving the stability and efficiency of the business.
[0089] By applying the solution of the embodiments of this specification, the amount of resources that users need to provide when participating in the target business is automatically determined through the risk parameter mapping table constructed from historical data, and the efficiency of user evaluation is improved based on historical data while ensuring the accuracy of user evaluation. This not only reduces the need for manual intervention, but also greatly shortens the decision-making time, allowing enterprises to respond to changes in the target business more quickly, thereby further improving the efficiency of user evaluation.
[0090] The following combination Figure 2 Taking the application of the resource evaluation method provided in this specification in insurance resource evaluation as an example, the resource evaluation method is further explained. Figure 2 A processing flow chart of an insurance resource evaluation method provided in an embodiment of the present specification is shown, which specifically includes the following steps.
[0091] Step 202: Obtain the risk parameter mapping table and the cardinality resources corresponding to each insurance product.
[0092] It should be noted that the risk parameter mapping table and the cardinality resources corresponding to each insurance product are obtained based on the historical data of each insurance product.
[0093] Step 204: Receive the insurance assessment request submitted by the user according to the front-end system.
[0094] Step 206: parse the insurance assessment request, determine that the target service sent by the user is the accidental medical service, and that the two service configuration information corresponding to the accidental medical service have a waiting period of 0 days and an insurance period of 15 days.
[0095] Step 208: Obtain a business risk mapping table corresponding to the accidental medical service in the risk parameter mapping table.
[0096] Step 210: In the above business risk mapping table, determine that the risk sub-parameter corresponding to the waiting period of 0 days is 1.05, and the risk sub-parameter corresponding to the insurance period of 180 days is 0.7.
[0097] Step 212: Multiply the two risk sub-parameters to determine the risk parameter 0.735 corresponding to the user.
[0098] Step 214: Determine that the base premium corresponding to the accidental medical service is 188.
[0099] Step 216: Multiply the base premium 188 and the risk parameter 0.735 to determine that the user needs to provide a premium of 138.18 when participating in 180 days of accidental medical services.
[0100] By applying the solution of the embodiments of this specification, the premium is evaluated according to the risk factors of the user, and the required premium amount is accurately calculated according to the user's historical behavior and other relevant data through an automated risk assessment system. This not only improves the efficiency and accuracy of the assessment, but also optimizes resource allocation for insurance companies, enabling them to manage risks more effectively. At the same time, users can also enjoy more fair and transparent premium pricing, thereby enhancing customer satisfaction and trust.
[0101] Corresponding to the above method embodiment, this specification also provides a resource evaluation device embodiment, Figure 3 FIG. 1 shows a schematic diagram of a resource evaluation device provided by an embodiment of the present specification. Figure 3 As shown, the device comprises:
[0102] The receiving module 302 is configured to receive a target service selected by a user and at least one service configuration information;
[0103] The generating module 304 is configured to determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, and generate the risk parameters corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameters corresponding to each business configuration information are determined according to the historical business configuration information and the historical business results corresponding to each historical business in the business history data, and the risk sub-parameters corresponding to each business configuration information represent the influence of each business configuration information on the business result corresponding to the target business;
[0104] The determination module 306 is configured to determine the cardinality resources corresponding to the target business, and determine the participation resources corresponding to the user according to the risk parameters and the cardinality resources, wherein the participation resources are the amount of resources that the user needs to provide when participating in the target business.
[0105] Optionally, the resource evaluation device further includes a construction module, and the construction module is configured to:
[0106] Acquire at least one business history data corresponding to the target business;
[0107] Constructing a target business risk parameter mapping table corresponding to the target business according to the historical data of each business;
[0108] A risk parameter mapping table is obtained based on a target business risk parameter mapping table corresponding to at least one target business.
[0109] Optionally, the building module is further configured as follows:
[0110] Parsing the target service history data to obtain the history service result, history participating resources and at least one history service configuration information, wherein the target service history data is any one of the history data of each service corresponding to the target service;
[0111] Determine the historical impact factor corresponding to each historical service configuration information according to the historical service results and the historical participating resources;
[0112] According to the historical impact factors corresponding to each historical business configuration information in each business historical data, the risk sub-parameters corresponding to each historical business configuration information are determined, and a target business risk parameter mapping table is constructed according to the risk sub-parameters corresponding to each historical business configuration information.
[0113] Optionally, the generating module 304 is further configured to:
[0114] Determine a target business risk parameter mapping table corresponding to the target business in the risk parameter mapping table;
[0115] The risk sub-parameters corresponding to each business configuration information are determined according to the target business risk parameter mapping table.
[0116] Optionally, the determining module 306 is further configured to:
[0117] Acquire at least one business history data corresponding to the target business;
[0118] The cardinality resources corresponding to the target business are determined according to the historical data of each business.
[0119] Optionally, the determining module 306 is further configured to:
[0120] Analyze the historical data of each business to obtain the historical business results and historical participating resources corresponding to the historical data of each business;
[0121] The cardinality resources corresponding to the target business are generated according to the historical business results and historical participating resources corresponding to the historical data of each business.
[0122] By applying the solution of the embodiments of this specification, the amount of resources that users need to provide when participating in the target business is automatically determined through the risk parameter mapping table constructed from historical data, and the efficiency of user evaluation is improved based on historical data while ensuring the accuracy of user evaluation. This not only reduces the need for manual intervention, but also greatly shortens the decision-making time, allowing enterprises to respond to changes in the target business more quickly, thereby further improving the efficiency of user evaluation.
[0123] The above is a schematic scheme of a resource evaluation device of this embodiment. It should be noted that the technical scheme of the resource evaluation device and the technical scheme of the resource evaluation method described above are of the same concept, and the details not described in detail in the technical scheme of the resource evaluation device can be found in the description of the technical scheme of the resource evaluation method described above.
[0124] Figure 4 The block diagram of a computing device 400 according to an embodiment of the present specification is shown. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.
[0125] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).
[0126] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.
[0127] The computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 400 may also be a mobile or stationary server.
[0128] The processor 420 is used to execute the following computer executable instructions, which implement the steps of the above resource evaluation method when executed by the processor.
[0129] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the resource evaluation method described above are of the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the resource evaluation method described above.
[0130] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which can implement the steps of the above-mentioned resource evaluation method when executed by a processor.
[0131] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the resource evaluation method described above are of the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the resource evaluation method described above.
[0132] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned resource evaluation method when executed by a processor.
[0133] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the resource evaluation method described above are of the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the resource evaluation method described above.
[0134] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0135] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0136] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.
[0137] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0138] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.
Claims
1. A resource assessment method, characterized in that: include: Receiving a target service selected by a user and at least one service configuration information; Determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, and generate the risk parameters corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameters corresponding to each business configuration information are determined according to the historical business configuration information and the historical business results corresponding to each historical business in the business history data, and the risk sub-parameters corresponding to each business configuration information represent the influence of each business configuration information on the business result corresponding to the target business; Determine the cardinality resource corresponding to the target business, and determine the participation resource corresponding to the user according to the risk parameter and the cardinality resource, wherein the participation resource is the amount of resources that the user needs to provide when participating in the target business.
2. The method according to claim 1, characterized in that Before determining the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, the method further includes: Acquire at least one business history data corresponding to the target business; Constructing a target business risk parameter mapping table corresponding to the target business according to the historical data of each business; A risk parameter mapping table is obtained based on a target business risk parameter mapping table corresponding to at least one target business.
3. The method according to claim 2, characterized in that A target business risk parameter mapping table corresponding to the target business is constructed according to the historical data of each business, including: Parsing the target service history data to obtain the history service result, history participating resources and at least one history service configuration information, wherein the target service history data is any one of the history data of each service corresponding to the target service; Determine the historical impact factor corresponding to each historical service configuration information according to the historical service results and the historical participating resources; According to the historical impact factors corresponding to each historical business configuration information in each business historical data, the risk sub-parameters corresponding to each historical business configuration information are determined, and a target business risk parameter mapping table is constructed according to the risk sub-parameters corresponding to each historical business configuration information.
4. The method according to claim 1, characterized in that Determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, including: Determine a target business risk parameter mapping table corresponding to the target business in the risk parameter mapping table; The risk sub-parameters corresponding to each business configuration information are determined according to the target business risk parameter mapping table.
5. The method according to claim 1, characterized in that Determining the cardinality resources corresponding to the target business includes: Acquire at least one business history data corresponding to the target business; The cardinality resources corresponding to the target business are determined according to the historical data of each business.
6. The method according to claim 5, characterized in that Determining the cardinality resources corresponding to the target business according to the historical data of each business includes: Analyze the historical data of each business to obtain the historical business results and historical participating resources corresponding to the historical data of each business; The cardinality resources corresponding to the target business are generated according to the historical business results and historical participating resources corresponding to the historical data of each business.
7. A resource assessment device, characterized in that: include: A receiving module, configured to receive a target service selected by a user and at least one service configuration information; A generating module is configured to determine the risk sub-parameters corresponding to each business configuration information according to the risk parameter mapping table, and generate the risk parameters corresponding to the user according to each risk sub-parameter, wherein the risk sub-parameters corresponding to each business configuration information are determined according to the historical business configuration information and the historical business results corresponding to each historical business in the business history data, and the risk sub-parameters corresponding to each business configuration information represent the influence of each business configuration information on the business result corresponding to the target business; The determination module is configured to determine the cardinality resources corresponding to the target business, and determine the participation resources corresponding to the user according to the risk parameters and the cardinality resources, wherein the participation resources are the amount of resources that the user needs to provide when participating in the target business.
8. A computing device, characterized in that include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium storing a computer program / instruction, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.