Group resource interaction amount prediction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a group resource interaction amount prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring initial resource interaction data and group attribute characteristics of a target group in a first resource interaction period; determining a group service structure category of the target group based on the group attribute features and a preset service structure category; obtaining key influence factors and candidate influence factors based on the group business structure category; determining a factor resource prediction model based on the factor characteristics of the key influence factors; extracting key resource interaction data from the initial resource interaction data based on the key influence factors; predicting a group key resource interaction amount based on a factor resource prediction model; and determining the target resource interaction amount of the next period based on the initial resource interaction data, the candidate influence factors and the group key resource interaction amount prediction. According to the embodiment of the invention, the prediction accuracy and efficiency of the group resource interaction amount can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method and device for predicting group resource interaction volume, an electronic device, and a storage medium. Background Art

[0002] Group resource interaction volume refers to the amount of resources that resource interactors (such as insurance companies, traffic suppliers, etc.) interact with in groups. For example, in the insurance field of FinTech, group resource interaction volume can be the premium of group insurance. For another example, group resource interaction volume can also be the total traffic obtained from traffic suppliers. However, the targets of group resource interaction volume are more diverse, there are many types of business, and there is no obvious pattern overall, which makes the relevant technology poor in predicting group resource interaction volume.

[0003] At present, related technologies usually use manual reporting and predict the group resource interaction volume of the next cycle based on experience. However, this method has low efficiency in predicting group risks and does not conduct in-depth analysis of the group resource interaction volume of different target types, resulting in low prediction accuracy of group resource interaction volume. Therefore, how to improve the prediction accuracy and efficiency of group resource interaction volume has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a method and device for predicting the amount of group resource interaction, an electronic device, and a storage medium, aiming to improve the accuracy and efficiency of predicting the amount of group resource interaction.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for predicting the amount of group resource interaction, the method comprising:

[0006] Acquire initial resource interaction data and group attribute characteristics of a target group in a first resource interaction cycle, wherein the target group is a group that performs resource interaction with a resource interaction party;

[0007] Performing business structure matching on the target group based on the group attribute characteristics and the preset business structure category to determine the group business structure category;

[0008] Acquire key influencing factors and candidate influencing factors based on the group business structure category, wherein the key influencing factors have a higher degree of influence on predicting the resource interaction amount of the target group than the candidate influencing factors;

[0009] Determining a factor resource prediction model based on the factor characteristics of the key influencing factors;

[0010] extracting key resource interaction data from the initial resource interaction data based on the key influencing factors;

[0011] Based on the factor resource prediction model, the key resource interaction amount is predicted for the key resource interaction data to obtain the group key resource interaction amount;

[0012] A resource interaction amount prediction is performed based on the initial resource interaction data, the candidate influencing factors and the group's key resource interaction amount to determine a target resource interaction amount, wherein the target resource interaction amount is the predicted resource interaction amount between the target group and the resource interaction party in a second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle.

[0013] In some embodiments, the predicting of resource interaction amount based on the initial resource interaction data, the candidate influencing factors and the group key resource interaction amount to determine the target resource interaction amount includes:

[0014] Acquire the key factor weight of the key influencing factor based on the initial resource interaction data;

[0015] Adjusting the group key resource interaction amount based on the key factor weight to obtain an optimized key resource interaction amount;

[0016] Obtain a historical resource interaction amount prediction function of the resource interaction party;

[0017] The resource interaction amount is predicted based on the historical resource interaction amount prediction function, the candidate influencing factors and the optimized key resource interaction amount to obtain the target resource interaction amount.

[0018] In some embodiments, the method further comprises:

[0019] Acquire an actual resource interaction amount of the target group, where the target resource interaction amount is an actual resource interaction amount between the target group and the resource interaction party in the second resource interaction period;

[0020] Calculating the difference between the target resource interaction amount and the actual resource interaction amount to obtain a resource interaction amount error;

[0021] Model parameters of the factor resource prediction model are adjusted based on the resource interaction amount error to update the factor resource prediction model.

[0022] In some embodiments, the preset business structure category includes a first-level structure category and a second-level structure category included in the first-level structure category, and the business structure matching of the target group based on the group attribute characteristics and the preset business structure category to determine the group business structure category includes:

[0023] Acquire group application data and group resource demand data of the target group from the group attribute characteristics;

[0024] selecting a candidate business structure category of the target group from the first level structure category based on the group application data;

[0025] The group business structure category of the target group is selected from the second-level structure categories of the candidate business structure categories based on the group resource demand data.

[0026] In some embodiments, obtaining key influencing factors and candidate influencing factors based on the group business structure category includes:

[0027] Acquire category characteristic data of the group business structure category, wherein the category characteristic data is used to indicate characteristic data that needs to be considered when predicting the resource interaction amount of the group business structure category;

[0028] Factor splitting is performed based on the category characteristic data and the historical resource quantity prediction function of the group business structure category to obtain the key influencing factors and the candidate influencing factors.

[0029] In some embodiments, determining a factor resource prediction model based on the factor characteristics of the key influencing factors includes:

[0030] Acquire a preset model library, wherein the preset model library includes candidate resource prediction models and prediction features of the candidate resource prediction models;

[0031] Calculating feature similarity between the factor feature and the prediction feature to obtain feature similarity;

[0032] The factor resource prediction model is determined from the candidate resource prediction models based on the feature similarity.

[0033] In some embodiments, the key resource interaction data includes first resource interaction data based on a time series and second resource interaction data based on a historical rule, and the factor resource prediction model includes a first prediction model for predicting the first resource interaction data and a second prediction model for predicting the second resource interaction data;

[0034] The step of predicting the key resource interaction amount of the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount includes:

[0035] Predicting the resource interaction amount of the first resource interaction data based on the first prediction model to obtain a first key resource interaction amount;

[0036] Performing resource interaction amount prediction on the second resource interaction data based on the second prediction model to obtain a second key resource interaction amount;

[0037] The community key resource interaction amount is determined based on the first key resource interaction amount and the second key resource interaction amount.

[0038] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a device for predicting group resource interaction volume, the device comprising:

[0039] A first acquisition module is used to acquire initial resource interaction data and group attribute characteristics of a target group in a first resource interaction cycle, wherein the target group is a group that performs resource interaction with a resource interaction party;

[0040] A matching module, used to match the business structure of the target group based on the group attribute characteristics and the preset business structure category, and determine the group business structure category;

[0041] A second acquisition module is used to acquire key influencing factors and candidate influencing factors based on the group business structure category, wherein the key influencing factors have a higher degree of influence on predicting the resource interaction amount of the target group than the candidate influencing factors;

[0042] A model determination module, used for determining a factor resource prediction model based on the factor characteristics of the key influencing factors;

[0043] An extraction module, configured to extract key resource interaction data from the initial resource interaction data based on the key influencing factors;

[0044] A first prediction module is used to predict the key resource interaction amount of the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount;

[0045] The second prediction module is used to predict the resource interaction amount based on the initial resource interaction data, the candidate influencing factors and the group's key resource interaction amount, and determine the target resource interaction amount, where the target resource interaction amount is the predicted resource interaction amount between the target group and the resource interaction party in the second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle.

[0046] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements a method for predicting the amount of group resource interaction described in the first aspect.

[0047] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method for predicting the amount of group resource interaction described in the first aspect.

[0048] The present application proposes a method and device for predicting the amount of group resource interaction, an electronic device, and a storage medium. The method obtains initial resource interaction data and group attribute characteristics of a target group in a first resource interaction cycle, wherein the target group is a group that interacts with a resource interaction party; further, the target group is matched with a business structure based on the group attribute characteristics and a preset business structure category to determine the group business structure category, and key influencing factors and candidate influencing factors are obtained based on the group business structure category, wherein the degree of influence of the key influencing factors on predicting the amount of resource interaction of the target group is higher than that of the candidate influencing factors; further, a factor resource prediction model is determined based on the factor characteristics of the key influencing factors; key resource interaction data is extracted from the initial resource interaction data based on the key influencing factors; key resource interaction amount is predicted for the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount; further, a resource interaction amount is predicted based on the initial resource interaction data, the candidate influencing factors, and the group key resource interaction amount to determine the target resource interaction amount, wherein the target resource interaction amount is the predicted amount of resource interaction between the target group and the resource interaction party in a second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle. Compared to the method of predicting resource interaction volume based on experience in related technologies, this application will first divide the target group based on the business structure, and then determine the key influencing factors and candidate influencing factors related to the prediction of the target group resource interaction volume based on the divided categories. In this way, an in-depth analysis of the group resource interaction volume of different target types can be achieved, thereby improving the prediction accuracy of the group resource interaction volume in subsequent resource interaction cycles. Therefore, this application can effectively improve the prediction accuracy and efficiency of the group resource interaction volume by combining models and in-depth analysis of influencing factors to achieve automated prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of a method for predicting the amount of group resource interaction provided by an embodiment of the present application;

[0050] Figure 2 yes Figure 1 A flowchart of step S120 in FIG.

[0051] Figure 3 yes Figure 1 A flowchart of step S130 in FIG.

[0052] Figure 4 yes Figure 1 A flowchart of step S140 in FIG.

[0053] Figure 5 yes Figure 1 A flowchart of step S160 in FIG.

[0054] Figure 6 yes Figure 1 A flowchart of step S170 in FIG.

[0055] Figure 7 is another flow chart of the method for predicting the amount of group resource interaction provided by an embodiment of the present application;

[0056] Figure 8 It is a structural schematic diagram of a device for predicting the amount of group resource interaction provided in an embodiment of the present application;

[0057] Fig. 9 It is a hardware structure diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0061] First, some nouns involved in this application are analyzed:

[0062] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0063] Group resource interaction volume refers to the amount of resources that resource interactors (such as insurance companies, traffic suppliers, etc.) interact with in groups. For example, in the insurance field of FinTech, group resource interaction volume can be the premium of group insurance. For another example, group resource interaction volume can also be the total traffic obtained from traffic suppliers. However, the targets of group resource interaction volume are more diverse, there are many types of business, and there is no obvious pattern overall, which makes the relevant technology poor in predicting group resource interaction volume.

[0064] At present, related technologies usually use manual reporting and predict the group resource interaction volume of the next cycle based on experience. However, this method has low efficiency in predicting group risks and does not conduct in-depth analysis of the group resource interaction volume of different target types, resulting in low prediction accuracy of group resource interaction volume. Therefore, how to improve the prediction accuracy and efficiency of group resource interaction volume has become a technical problem that needs to be solved urgently.

[0065] Based on this, the embodiments of the present application provide a method and device for predicting the amount of group resource interaction, an electronic device, and a storage medium, which can improve the accuracy and efficiency of predicting the amount of group resource interaction.

[0066] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0067] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0068] The method for predicting the amount of group resource interactions provided in the embodiment of the present application relates to the field of artificial intelligence technology. The method for predicting the amount of group resource interactions provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN) and cloud servers that provide basic cloud computing services such as big data and artificial intelligence platforms; the software can be an application that implements the method for predicting the amount of group resource interactions, etc., but is not limited to the above forms.

[0069] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on the group information corresponding to the group, group resource interaction data, group attribute characteristics and other data related to the identity or characteristics of the group object, the permission or consent of the object will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiment of the present application needs to obtain the sensitive personal information of the object, the separate permission or consent of the object will be obtained through a pop-up window or jump to a confirmation page. After clearly obtaining the separate permission or consent of the object, the necessary object-related data for the normal operation of the embodiment of the present application will be obtained.

[0071] See also Figure 1 , Figure 1 is an optional flow chart of a method for predicting the amount of group resource interaction provided in an embodiment of the present application. In some embodiments, Figure 1 The method may include but is not limited to steps S110 to S170:

[0072] Step S110, obtaining initial resource interaction data and group attribute characteristics of the target group in the first resource interaction cycle;

[0073] Step S120, matching the target group's business structure based on the group's attribute characteristics and the preset business structure category, and determining the group's business structure category;

[0074] Step S130, obtaining key influencing factors and candidate influencing factors based on the group business structure category;

[0075] Step S140, determining a factor resource prediction model based on the factor characteristics of the key influencing factors;

[0076] Step S150, extracting key resource interaction data from the initial resource interaction data based on key influencing factors;

[0077] Step S160, predicting the key resource interaction amount of the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount;

[0078] Step S170 , predicting the resource interaction amount based on the initial resource interaction data, the candidate influencing factors and the group key resource interaction amount, and determining the target resource interaction amount.

[0079] In step S110 of some embodiments, the target group is a group that interacts with the resource interaction party. The resource interaction party can represent an object that provides the required resources to the target group, and the target group and the resource interaction party can use different resources to interact to meet their own needs. For example, in the insurance field of financial technology, the resource interaction party can be an insurance company, and the target group can be an enterprise, institution, community, etc. that interacts with the insurance company as a group. At this time, the group resource interaction amount can be the premium of the group insurance.

[0080] It should be noted that the resource interaction cycle can represent the period of resource interaction between the target group and the resource interaction party, such as one month, one quarter, one year, etc. The first resource interaction cycle refers to the period in which the target group is currently interacting with resources. The initial resource interaction data refers to the data on resource interaction that the target group has completed with the resource interaction party in the current first resource interaction cycle, which may include the total number of resource interactions (such as total premiums) and data on resource interaction subcategories (such as premiums corresponding to different categories, which may be vehicle insurance, equipment insurance, etc.).

[0081] It should be noted that the group attribute characteristics are used to characterize the basic attributes of the target group, such as the target group's business type, industry scale, group geographical location, etc.

[0082] It should be noted that the solution provided in the embodiment of the present application can be used to predict the resource interaction volume of the target group in the next resource interaction cycle. Thus, by counting the resource interaction volumes of all target groups associated with the resource interaction party, the resource interaction party can be helped to predict its own operating conditions in the next resource interaction cycle, facilitating timely adjustments.

[0083] In step S120 of some embodiments, the preset business structure category refers to the category divided by the resource interaction party according to the different business structure divisions of its own. The preset business structure category may include Internet category, platform category, vehicle category and regular premium category, etc. Since the resource interaction between the resource interaction party and the target group is also related to the attributes of the target group itself, the business structure of the target group is matched based on the group attribute characteristics and the preset business structure category to determine the group business structure category to which the target group belongs. The group business structure category is used to characterize the preset business structure category with the highest degree of match with the group attribute characteristics of the target object. For example, if the target group is mainly engaged in online sales, then its main business structure is Internet-related, and the corresponding group business structure category is the Internet category.

[0084] It should be noted that the Internet category means that the resource interaction between the resource interaction party and the corresponding group is carried out through the Internet channel, which may include online sales, digital services, online advertising, etc. The platform category means that the resource interaction between the resource interaction party and the corresponding group is carried out through an intermediary or market (that is, a business model that allows multiple participants to trade or interact on it), such as e-commerce platforms, sharing economy platforms, etc. The vehicle category means that the resource interaction between the resource interaction party and the corresponding group is related to the vehicle, such as vehicle insurance, vehicle maintenance services, etc. The conventional premium category means that the resource interaction between the resource interaction party and the corresponding group is a traditional insurance expense, which is usually related to traditional insurance products such as motor vehicle insurance and life insurance.

[0085] It should be noted that the preset business structure categories may include the first-level structure categories and the second-level structure categories contained in the first-level structure categories. That is to say, when dividing the preset business structure categories, a hierarchical division method can be adopted to refine the business structure categories and improve the prediction accuracy of the resource interaction volume. For example, the first-level structure categories of the preset business structure categories may include Internet categories, platform categories, vehicle categories, and regular premium categories, etc. The second-level structure categories contained in the platform categories may include head platforms, new signing platforms, other platforms, etc. The second-level structure categories contained in the regular premium categories may include new insurance and renewal. Among them, for different resource interaction parties, the preset business structure categories can be flexibly adjusted according to their actual business structure conditions without limitation.

[0086] It should be noted that business structure refers to the organizational, management and operational methods adopted by resource interacting parties (such as insurance companies, financial institutions, etc.) when conducting business, as well as the overall layout of how these methods are interrelated and supportive of each other.

[0087] In some embodiments, see Figure 2 , step S120 may specifically include steps S210 to S230:

[0088] Step S210, obtaining group application data and group resource demand data of the target group from group attribute characteristics;

[0089] Step S220, selecting a candidate business structure category of the target group from the first-level structure category based on the group application data;

[0090] Step S230: Selecting a group business structure category of the target group from the second-level structure categories of the candidate business structure categories based on the group resource demand data.

[0091] In step S210 of some embodiments, group application data refers to the main application methods of the target group in its business operations, such as the Internet, vehicles, platforms, etc. These data help understand the operation methods of the target group in the current market environment. Group resource demand data refers to the various resources (such as human resources, physical equipment, etc.) required by the target group in its operation process. These data help identify the resource requirements of the team in achieving business goals, thereby determining the type of resource interaction with the resource interaction party.

[0092] In step S220 of some embodiments, since the scope of group application data is greater than the scope of group resource demand data, the application scope of the target group is considered from a broad perspective, so a candidate business structure category matching the target group can be selected from the first-level structure category based on the group application data. The candidate business structure category is a preset business structure category under the first-level structure category.

[0093] In step S230 of some embodiments, further, in order to refine and determine the business structure of the target group, the present application may further screen out the final group business structure category from the second-level structure category of the selected candidate business structure category. The second-level structure category may provide more subdivisions (such as business sub-classifications for specific markets or fields), and the selection process is intended to accurately identify the business structure category that is consistent with the actual needs and applications of the target group. For example, if the target group needs to use a lot of vehicles in the actual business implementation process, then its target group business structure category may include an auto insurance category. Among them, there can be more than one target group business structure category, that is, it can include all business structure categories involved by the target group.

[0094] In the above embodiment, the present application first clearly divides the business structure of the target group, so that in the subsequent resource interaction volume prediction, different prediction methods can be used according to different business structures to improve the accuracy of resource interaction volume prediction. In other words, the present application can identify the business structure category suitable for the target group through in-depth analysis of the group attribute characteristics and the preset business structure category, so that the subsequent resource allocation and strategy formulation can be more accurate and effective.

[0095] In step S130 of some embodiments, after the group business structure category is determined, the key influencing factors can be further separated for prediction based on the resource interaction volume characteristics of each business structure. Specifically, based on the group business structure category, the key influencing factors and candidate influencing factors are obtained from the influencing factors involved in predicting the resource interaction volume under the group business structure category. The key influencing factors refer to the factors that need to be predicted, and the candidate influencing factors refer to the remaining influencing factors after excluding the key influencing factors, and the numerical values ​​corresponding to the candidate influencing factors can be fixed numerical values ​​or linearly changing numerical values. Among them, the degree of influence of the key influencing factors on the resource interaction volume of the predicted target group is higher than the degree of influence of the candidate influencing factors. For example, in the insurance field of financial technology, if the group business structure category is the vehicle premium category, the vehicle premium corresponding to this category (i.e., the target resource interaction volume) = the number of vehicle logos * vehicle recommendation rate * average premium per case. In this way, the influencing factors of the regular renewal category (the number of vehicle logos, the vehicle recommendation rate and the average premium per case) can be decomposed, and the key influencing factors can be determined as the vehicle recommendation rate and the average premium per case, and the candidate influencing factors are the number of vehicle logos. Among them, the vehicle recommendation rate and the average premium per case can be predicted based on the factor resource prediction model trained based on historical data, and the number of vehicle logos can be manually input or identified by a computer based on uploaded data.

[0096] It should be noted that, for example, since the Internet premium category is based on traffic, the average daily platform premium can be separated as a key influencing factor; for example, the regular new insurance premium category is more in line with the characteristics of time series, and the premium and premium growth rate of the same period can be separated as key influencing factors for resource interaction volume prediction; for example, the regular renewal premium category can be separated into the monthly renewal premium and premium renewal rate as key influencing factors for resource interaction volume prediction. In this way, the influencing factors related to the business structure category can be separated.

[0097] In some embodiments, see Figure 3 , step S130 may specifically include steps S310 to S320:

[0098] Step S310, obtaining category characteristic data of the group business structure category;

[0099] Step S320 , factor splitting is performed based on the category characteristic data and the resource quantity prediction function of the group business structure category to obtain key influencing factors and candidate influencing factors.

[0100] In step S310 of some embodiments, the category feature data is used to indicate feature data that needs to be considered when predicting the resource interaction volume of the group business structure category. The category feature data may include the business background, resource configuration, resource standardization data, etc. of the category. These category feature data will help to consider all influencing factors when predicting the resource interaction volume of a specific group business structure category, ensuring that the prediction model not only relies on static historical data, but also dynamically reflects the context and changes related to the characteristics of the category.

[0101] In step S320 of some embodiments, statistical analysis techniques or model algorithms may be further used to decompose the resource quantity prediction function corresponding to the group business structure category, so as to identify key influencing factors and candidate influencing factor risk factors with different degrees of influence on the prediction of resource interaction quantity.

[0102] In the above embodiment, the present application comprehensively analyzes the category characteristic data of the group business structure category to ensure that all relevant influencing factors are fully considered when predicting the resource interaction volume, and divides the influencing factors based on the degree of influence, thereby improving the accuracy and efficiency of the resource interaction volume prediction.

[0103] In step S140 of some embodiments, after the key influencing factors are determined, the corresponding factor resource prediction model can be determined based on the factor characteristics of each key influencing factor. This is because the data characteristics corresponding to different key influencing factors are different, and the prediction methods will be different, so different factor resource prediction models are used to predict the resource interaction amount. Among them, the factor resource prediction model can be constructed in different ways based on machine learning (such as random forest, support vector machine, etc.), deep learning, historical laws, etc.

[0104] It should be noted that, for example, key influencing factors may include premium growth rate, average daily platform premium, vehicle recommendation rate, and monthly renewal premium, among which premium growth rate is an influencing factor that conforms to the characteristics of time series, so the corresponding factor resource prediction model can be constructed based on the linear regression model; average daily platform premium and vehicle recommendation rate are influencing factors that need to be learned based on historical data, so the corresponding factor resource prediction model can be learned from historical data based on a machine learning model; the monthly renewal premium can be obtained through the group renewal list, and the corresponding factor resource prediction model can be obtained by training the group renewal list based on a machine learning model.

[0105] In the above embodiment, the present application can divide the target group according to different business structures, and different business structures will have their own influencing factors. Therefore, for each target group, according to the degree of influence of the influencing factors on the prediction results, the respective methods can be selected for estimation (some are regression model estimations, and some are based on historical laws), and the group key resource interaction volume and group candidate resource interaction volume are obtained, and the final target resource interaction volume is further determined. In this way, the accuracy of resource interaction volume prediction can be effectively improved.

[0106] In some embodiments, see Figure 4 , step S140 may specifically include steps S410 to S430:

[0107] Step S410, obtaining a preset model library;

[0108] Step S420, calculating feature similarity between the factor feature and the prediction feature to obtain feature similarity;

[0109] Step S430: determining a factor resource prediction model from the candidate resource prediction models based on feature similarity.

[0110] In step S410 of some embodiments, the preset model library is a pre-set model library for storing different types of candidate resource prediction models and prediction features of candidate resource prediction models. Each prediction feature is used to indicate the data features of the candidate resource prediction model for prediction, so as to facilitate factor matching of the corresponding prediction model. These models may be established based on historical data and actual cases, covering a variety of prediction methods, such as linear regression, time series analysis, machine learning models (such as random forests, support vector machines, etc.).

[0111] In step S420 of some embodiments, further, the key influencing factors are vectorized to obtain factor features, and feature similarity is calculated between the factor features and the prediction features to obtain feature similarity. The feature similarity calculation method includes cosine similarity, Euclidean distance or other statistical analysis tools to quantify the similarity between the factor features and the prediction features, so as to determine which candidate resource prediction model has the closest relationship between the prediction features and the actual key factor features.

[0112] In step S430 of some embodiments, the most suitable factor resource prediction model for the key influencing factor is selected from the candidate resource prediction models according to the feature similarity calculated in the previous step. In this way, the accuracy of data prediction corresponding to the key influencing factor can be improved, thereby improving the accuracy of prediction of the target resource interaction amount.

[0113] In step S150 of some embodiments, after the key influencing factors are determined, key resource interaction data associated with the key influencing factors may be extracted from the initial resource interaction data to facilitate subsequent calculations.

[0114] In step S160 of some embodiments, since the data types of key influencing factors are different, the key resource interaction data may include resource interaction data of multiple different data types. For example, the key resource interaction data includes first resource interaction data based on a time series and second resource interaction data based on historical rules. The first resource interaction data is used to characterize the resource interaction data corresponding to the influencing factors that conform to the characteristics of the time series. The second resource interaction data is used to characterize the resource interaction data corresponding to the influencing factors that can be obtained through historical rules. Based on this, the factor resource prediction model includes a first prediction model for predicting the first resource interaction data and a second prediction model for predicting the second resource interaction data, wherein the model structures of the first prediction model and the second prediction model may be the same or different, without specific limitation.

[0115] In some embodiments, see Figure 5 , step S160 may specifically include steps S510 to S530:

[0116] Step S510, predicting the resource interaction amount of the first resource interaction data based on the first prediction model to obtain the first key resource interaction amount;

[0117] Step S520, predicting the resource interaction amount of the second resource interaction data based on the second prediction model to obtain the second key resource interaction amount;

[0118] Step S530: determining the group key resource interaction amount based on the first key resource interaction amount and the second key resource interaction amount.

[0119] In steps S510 to S530 of some embodiments, the input first resource interaction data is analyzed and calculated using a previously established first prediction model (such as linear regression, time series analysis, or machine learning model), and the output result is a first key resource interaction amount, which represents the expected resource interaction amount under given conditions. Similarly, the input second resource interaction data is analyzed and calculated using a second prediction model, and the output result is a second key resource interaction amount. Further, the first key resource interaction amount and the second key resource interaction amount are integrated. Specifically, the first factor weight corresponding to the first key resource interaction amount and the second factor weight corresponding to the second key resource interaction amount can be obtained, and further, the weighted calculation result of the first key resource interaction amount and the first factor weight, and the weighted calculation result of the second key resource interaction amount and the second factor weight are added together to obtain the group key resource interaction amount.

[0120] It should be noted that if the key resource interaction data also includes third resource interaction data, the resource interaction amount of the third resource interaction data can be predicted based on the corresponding third prediction model to obtain the third key resource interaction amount, and the group key resource interaction amount can be further updated based on the third key resource interaction amount. The specific calculation process can be referred to the above process, and will not be repeated here.

[0121] In step S170 of some embodiments, further, a resource interaction amount prediction is performed based on the initial resource interaction data, candidate influencing factors, and group key resource interaction amount to determine the target resource interaction amount. The target resource interaction amount is the predicted resource interaction amount between the target group and the resource interaction party in the second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle. For example, if the resource interaction cycle is one month, then the present application is equivalent to predicting the target resource interaction amount for the next month based on the initial resource interaction data of the current month, and the candidate influencing factors and group key resource interaction amounts determined based on the data of the current month.

[0122] In some embodiments, see Figure 6 , step S170 may specifically include steps S610 to S640:

[0123] Step S610, obtaining key factor weights of key influencing factors based on initial resource interaction data;

[0124] Step S620, adjusting the group key resource interaction amount based on the key factor weight to obtain an optimized key resource interaction amount;

[0125] Step S630, obtaining a historical resource interaction amount prediction function of a resource interaction party;

[0126] Step S640 , predicting resource interaction amount based on the historical resource interaction amount prediction function, candidate influencing factors and optimized key resource interaction amount to obtain the target resource interaction amount.

[0127] In step S610 of some embodiments, the present application can determine the key factor weights of the key influencing factors based on the proportion of the resource interaction data corresponding to the key influencing factors in the initial resource interaction data. In addition, the key factor weights can also be determined by regression analysis, feature selection algorithms (such as LASSO regression, decision tree feature importance) or other methods. The key factor weights reflect the relative importance of each key influencing factor to resource interaction.

[0128] In step S620 of some embodiments, the key resource interaction amount of the group may be further adjusted according to the weight of the key factor, specifically by weighted average or other adjustment methods, so as to more accurately reflect the actual resource interaction situation.

[0129] In step S630 and step S640 of some embodiments, the present application may obtain historical resource interaction volume data of the resource interaction party, and analyze these data to establish a historical resource interaction volume prediction function. Models for establishing the historical resource interaction volume prediction function may include linear regression, ARIMA model, neural network, etc., and these functions are fitted based on the trend and periodic characteristics of historical data. Furthermore, the historical resource interaction volume prediction function, candidate influencing factors, and optimized key resource interaction volume can be combined as inputs, and the historical resource interaction volume prediction function can be used for calculation to generate the final resource interaction volume prediction result. The target resource interaction volume finally obtained reflects the comprehensive prediction of future resource interaction situations, and provides data support for decision makers to carry out strategic planning and resource allocation.

[0130] For example, in the insurance field of financial technology, since insurance companies can include multiple institutions and multiple insurance branches, each institution can predict the insurance situation of the group in the next cycle based on the prediction method of group resource interaction provided by this application to guide the scheduling of premiums for the group in the next cycle. Furthermore, it can assist the superior institution to intuitively see the estimated results of the institutions under its jurisdiction and the next month's estimates of each structure and line, so as to assist the superior institution in issuing goals.

[0131] In some embodiments, see Figure 7 After step S170, the method for predicting the amount of group resource interaction provided in the embodiment of the present application may further include steps S710 to S730:

[0132] Step S710, obtaining the actual resource interaction amount of the target group;

[0133] Step S720, performing a difference calculation between the target resource interaction amount and the actual resource interaction amount to obtain a resource interaction amount error;

[0134] Step S730: adjusting model parameters of the factor resource prediction model based on the resource interaction amount error to update the factor resource prediction model.

[0135] In steps S710 to S730 of some embodiments, the actual resource interaction amount of the target group refers to the actual resource interaction amount between the target group and the resource interaction party in the second resource interaction cycle. The superior organization of the resource interaction party can perform a difference calculation between the target resource interaction amount and the actual resource interaction amount to obtain a resource interaction amount error, thereby helping the superior organization of the resource interaction party to determine whether the current resource interaction party has an abnormal reporting situation. In addition, the resource interaction party can also adjust the resource prediction model based on this error factor and perform gradient fine-tuning to improve the accuracy of the next prediction.

[0136] It should be noted that the non-Company software tools or components appearing in the embodiments of the present application are merely examples and do not represent actual use.

[0137] A method for predicting the amount of group resource interaction provided by an embodiment of the present application, by dividing the group resource interaction business structure and then using different methods to estimate the amount of resource interaction according to different business structures, integrates configuration, data integration, machine learning, experience adjustment, visualization page and deviation analysis, and can estimate the future amount of resource interaction (i.e., the target amount of resource interaction) through objective historical data (i.e., initial resource interaction data), which has the significance of guiding the subordinate organizations of the enterprise to schedule the amount of group resource interaction and disassemble and issue the target. In other words, the present application can decouple the data used by each business module during the design process, and use an indexed implementation method to extract each module separately, which can be used separately by each module. In this way, an in-depth analysis of the amount of group resource interaction of different target types can be achieved, thereby improving the prediction accuracy of the amount of group resource interaction in the subsequent resource interaction cycle. Therefore, the present application realizes automated prediction by combining the model and in-depth analysis of the influencing factors, which can effectively improve the prediction accuracy and efficiency of the amount of group resource interaction.

[0138] See also Figure 8 The embodiment of the present application further provides a prediction device for group resource interaction volume, which can implement the above-mentioned prediction method for group resource interaction volume, and the device includes:

[0139] A first acquisition module 810 is used to acquire initial resource interaction data and group attribute characteristics of a target group in a first resource interaction cycle, where the target group is a group that interacts with a resource interaction party;

[0140] A matching module 820 is used to match the business structure of the target group based on the group attribute characteristics and the preset business structure category to determine the group business structure category;

[0141] The second acquisition module 830 is used to acquire key influencing factors and candidate influencing factors based on the group business structure category, wherein the key influencing factors have a higher degree of influence on the predicted resource interaction amount of the target group than the candidate influencing factors;

[0142] A model determination module 840 is used to determine a factor resource prediction model based on the factor characteristics of the key influencing factors;

[0143] An extraction module 850 is used to extract key resource interaction data from the initial resource interaction data based on key influencing factors;

[0144] The first prediction module 860 is used to predict the key resource interaction amount of the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount;

[0145] The second prediction module 870 is used to predict the resource interaction amount based on the initial resource interaction data, candidate influencing factors and the group's key resource interaction amount, and determine the target resource interaction amount. The target resource interaction amount is the predicted resource interaction amount between the target group and the resource interaction party in the second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle.

[0146] The specific implementation of the device for predicting the group resource interaction amount is substantially the same as the specific implementation of the method for predicting the group resource interaction amount described above, and will not be described in detail herein.

[0147] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned group resource interaction amount prediction method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0148] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0149] The processor 910 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0150] The memory 920 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 920, and the processor 910 calls and executes the prediction method of the group resource interaction amount in the embodiment of this application;

[0151] Input / output interface 930, used to implement information input and output;

[0152] Communication interface 940, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0153] bus 950 , which transmits information between the various components of the device (e.g., processor 910 , memory 920 , input / output interface 930 , and communication interface 940 );

[0154] The processor 910 , the memory 920 , the input / output interface 930 , and the communication interface 940 are connected to each other in communication within the device via a bus 950 .

[0155] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for predicting the amount of group resource interaction is implemented.

[0156] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0157] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0158] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0159] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0161] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0162] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0163] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0164] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0166] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0167] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for predicting the amount of group resource interaction, characterized in that: The method comprises: Acquire initial resource interaction data and group attribute characteristics of a target group in a first resource interaction cycle, wherein the target group is a group that performs resource interaction with a resource interaction party; Performing business structure matching on the target group based on the group attribute characteristics and the preset business structure category to determine the group business structure category; Acquire key influencing factors and candidate influencing factors based on the group business structure category, wherein the key influencing factors have a higher degree of influence on predicting the resource interaction amount of the target group than the candidate influencing factors; Determining a factor resource prediction model based on the factor characteristics of the key influencing factors; extracting key resource interaction data from the initial resource interaction data based on the key influencing factors; Based on the factor resource prediction model, the key resource interaction amount is predicted for the key resource interaction data to obtain the group key resource interaction amount; A resource interaction amount prediction is performed based on the initial resource interaction data, the candidate influencing factors and the group's key resource interaction amount to determine a target resource interaction amount, wherein the target resource interaction amount is the predicted resource interaction amount between the target group and the resource interaction party in a second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle.

2. The method according to claim 1, characterized in that The predicting of resource interaction amount based on the initial resource interaction data, the candidate influencing factors and the group key resource interaction amount to determine the target resource interaction amount includes: Acquire the key factor weight of the key influencing factor based on the initial resource interaction data; Adjusting the group key resource interaction amount based on the key factor weight to obtain an optimized key resource interaction amount; Obtain a historical resource interaction amount prediction function of the resource interaction party; The resource interaction amount is predicted based on the historical resource interaction amount prediction function, the candidate influencing factors and the optimized key resource interaction amount to obtain the target resource interaction amount.

3. The method according to claim 2, characterized in that The method further comprises: Acquire an actual resource interaction amount of the target group, where the target resource interaction amount is an actual resource interaction amount between the target group and the resource interaction party in the second resource interaction period; Calculating the difference between the target resource interaction amount and the actual resource interaction amount to obtain a resource interaction amount error; Model parameters of the factor resource prediction model are adjusted based on the resource interaction amount error to update the factor resource prediction model.

4. The method according to claim 1, characterized in that: The preset business structure category includes a first-level structure category and a second-level structure category included in the first-level structure category, and the business structure matching of the target group based on the group attribute characteristics and the preset business structure category to determine the group business structure category includes: Acquire group application data and group resource demand data of the target group from the group attribute characteristics; selecting a candidate business structure category of the target group from the first level structure category based on the group application data; The group business structure category of the target group is selected from the second-level structure categories of the candidate business structure categories based on the group resource demand data.

5. The method according to claim 1, characterized in that The obtaining of key influencing factors and candidate influencing factors based on the group business structure category includes: Acquire category characteristic data of the group business structure category, wherein the category characteristic data is used to indicate characteristic data that needs to be considered when predicting the resource interaction amount of the group business structure category; Factor splitting is performed based on the category characteristic data and the historical resource quantity prediction function of the group business structure category to obtain the key influencing factors and the candidate influencing factors.

6. The method according to claim 5, characterized in that The factor resource prediction model determined based on the factor characteristics of the key influencing factors includes: Acquire a preset model library, wherein the preset model library includes candidate resource prediction models and prediction features of the candidate resource prediction models; Calculating feature similarity between the factor feature and the prediction feature to obtain feature similarity; The factor resource prediction model is determined from the candidate resource prediction models based on the feature similarity.

7. The method according to any one of claims 1 to 6, characterized in that: The key resource interaction data includes first resource interaction data based on time series and second resource interaction data based on historical rules, and the factor resource prediction model includes a first prediction model for predicting the first resource interaction data and a second prediction model for predicting the second resource interaction data; The step of predicting the key resource interaction amount of the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount includes: Predicting the resource interaction amount of the first resource interaction data based on the first prediction model to obtain a first key resource interaction amount; Performing resource interaction amount prediction on the second resource interaction data based on the second prediction model to obtain a second key resource interaction amount; The community key resource interaction amount is determined based on the first key resource interaction amount and the second key resource interaction amount.

8. A prediction device for group resource interaction volume, characterized in that: The device comprises: A first acquisition module is used to acquire initial resource interaction data and group attribute characteristics of a target group in a first resource interaction cycle, wherein the target group is a group that performs resource interaction with a resource interaction party; A matching module, used to match the business structure of the target group based on the group attribute characteristics and the preset business structure category, and determine the group business structure category; A second acquisition module is used to acquire key influencing factors and candidate influencing factors based on the group business structure category, wherein the key influencing factors have a higher degree of influence on predicting the resource interaction amount of the target group than the candidate influencing factors; A model determination module, used for determining a factor resource prediction model based on the factor characteristics of the key influencing factors; An extraction module, configured to extract key resource interaction data from the initial resource interaction data based on the key influencing factors; A first prediction module is used to predict the key resource interaction amount of the key resource interaction data based on the factor resource prediction model to obtain the group key resource interaction amount; The second prediction module is used to predict the resource interaction amount based on the initial resource interaction data, the candidate influencing factors and the group's key resource interaction amount, and determine the target resource interaction amount, where the target resource interaction amount is the predicted resource interaction amount between the target group and the resource interaction party in the second resource interaction cycle, and the second resource interaction cycle is the next cycle of the first resource interaction cycle.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images