Resource allocation method and device based on distributed constraint optimization and electronic equipment

Abstract

The application discloses a resource allocation method and device based on distributed constraint optimization and electronic equipment, and relates to the technical field of data processing. The method comprises the following steps: matching historical service data of a target user with a knowledge graph of resource allocation to obtain at least two basic entities, constructing and displaying an initial network based on key entities to which the basic entities belong and edge relationships between different basic entities, obtaining a target network in response to an editing operation on the initial network, constructing a distributed constraint optimization model according to the target network and the historical service data, and solving the distributed constraint optimization model to obtain a resource allocation scheme of the target user. The technical scheme improves the accuracy and efficiency of resource allocation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly to the field of data processing technology, specifically to a resource allocation method, apparatus, and electronic device based on distributed constraint optimization. Background Technology

[0002] In complex business scenarios, resource allocation often faces the challenge of coordinating and scheduling multiple types of resources. Different resource types have complex and diverse constraints, such as limitations on the ratio of computing power to storage, and the dynamic coupling of network bandwidth and power supply. Furthermore, resource demand fluctuates with business activity, exhibiting time-varying characteristics. This intertwining of multidimensional constraints and dynamic demands makes traditional centralized allocation strategies inadequate, often sacrificing overall efficiency for localized optimization, and exacerbating resource fragmentation and supply-demand mismatch problems.

[0003] Taking wealth management as an example, user resources need to be allocated across various resource types, such as stocks, bonds, wealth management products, and gold derivatives. The risk-return characteristics, liquidity constraints, and market correlations of different resources form a complex allocation constraint network. How to achieve real-time response and global optimization of resource allocation through dynamic modeling has become a key challenge in improving management efficiency. Summary of the Invention

[0004] This application provides a resource allocation method, apparatus, and electronic device based on distributed constraint optimization to improve the accuracy of anomaly location.

[0005] According to one aspect of this application, a resource allocation method based on distributed constraint optimization is provided, comprising:

[0006] The historical business data of the target user is matched with the knowledge graph of resource allocation to obtain at least two basic entities. Based on the key entities to which the basic entities belong and the edge relationships between different basic entities, an initial network is constructed and displayed.

[0007] The target network is obtained in response to the editing operation on the initial network;

[0008] A distributed constraint optimization model is constructed based on the target network and the historical business data;

[0009] Solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user.

[0010] According to another aspect of this application, a resource allocation apparatus based on distributed constraint optimization is provided, the apparatus comprising:

[0011] The initial network module is used to match the target user's historical business data with the knowledge graph of resource allocation to obtain at least two basic entities, and to construct and display the initial network based on the key entities to which the basic entities belong and the edge relationships between different basic entities.

[0012] A target network module is used to obtain a target network in response to an editing operation on the initial network;

[0013] A distributed constraint optimization module is used to construct a distributed constraint optimization model based on the target network and the historical service data.

[0014] The resource allocation scheme module is used to solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user.

[0015] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0016] One or more processors;

[0017] Memory, used to store one or more programs;

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods provided in the embodiments of this application.

[0019] According to another aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements any of the methods provided in the embodiments of this application.

[0020] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the methods provided in the embodiments of this application.

[0021] This application matches the historical business data of the target user with the basic entities in the knowledge graph of resource allocation. Based on the successfully matched basic entities and the key entities to which they belong, an initial network is constructed, which can present the logic of resource constraints. Furthermore, the initial network can be flexibly adjusted through a visual network editing function to obtain the target network, further improving the accuracy and flexibility of the target network. A distributed constraint optimization model is constructed and solved for the target network and the historical business data of the target user to obtain the resource allocation scheme for the target user. This scheme can take into account the integrity of the global optimal solution and the constraint changes caused by business fluctuations, making the resource allocation scheme both theoretically optimal and practically feasible, significantly improving decision-making efficiency and business response speed. Attached Figure Description

[0022] Figure 1aThis is a flowchart of a resource allocation method based on distributed constraint optimization provided in Embodiment 1 of this application;

[0023] Figure 1b This is a schematic diagram of the structure of the initial network provided according to Embodiment 1 of this application;

[0024] Figure 2 This is a flowchart of a resource allocation method based on distributed constraint optimization provided in Embodiment 2 of this application;

[0025] Figure 3 This is a flowchart of a resource allocation method based on distributed constraint optimization provided in Embodiment 2 of this application;

[0026] Figure 4 This is a schematic diagram of the structure of a resource allocation device based on distributed constraint optimization according to Embodiment 3 of this application;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the resource allocation method based on distributed constraint optimization according to the embodiments of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Furthermore, it should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of data related to email address blacklists and emails to be detected in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0031] Example 1

[0032] Figure 1a This is a flowchart of a resource allocation method based on distributed constraint optimization according to Embodiment 1 of this application. This embodiment is applicable to the allocation of user resources and can be executed by a resource allocation device based on distributed constraint optimization. This resource allocation device can be implemented in hardware and / or software and can be configured in a computer device. Figure 1a As shown, the method includes:

[0033] S110. Match the historical business data of the target user with the knowledge graph of resource allocation to obtain at least two basic entities. Based on the key entities to which the basic entities belong and the edge relationships between different basic entities, construct and display the initial network.

[0034] S120. Obtain the target network in response to the editing operation on the initial network;

[0035] S130. Construct a distributed constraint optimization model based on the target network and the historical service data;

[0036] S140. Solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user.

[0037] In the process of allocating resources to a specific user, this user is designated as the target user. The target user's historical business data can be retrieved from the business system using their identifier. This historical business data may include historical transaction records, risk preference questionnaires, health monitoring data, family structure data, etc. The knowledge graph for resource allocation may include different basic entities and their attributes. The attributes of a basic entity include the identifier of the key entity to which it belongs; each basic entity uniquely belongs to a key entity.

[0038] For example, key fields of the target user are extracted from the target user's historical business data. The relevance between these key fields and basic entity fields in the knowledge graph under the resource allocation scenario is calculated, and the successfully matched basic entities are obtained based on the relevance. An initial network is constructed based on the key entities to which the basic entities belong, and the edge relationships between different basic entities. This allows for the differentiation and display of different types of edge relationships and different key entities. (Reference) Figure 1bThe initial network may include a first key entity, a second key entity, a third key entity, and a fourth key entity. The first key entity may include four different basic entities, the second key entity may include two different basic entities, the third key entity may include three different key entities, and the fourth key entity may include two different basic entities. Different line segments (e.g., line segments of different colors) can be used to distinguish and display the corresponding edge relationships. Each key entity includes its subordinate basic entities in the form of a container; that is, the spatial nesting between basic entities and their subordinate key entities represents the hierarchical relationship between basic entities and key entities. It should be noted that all relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data comply with the relevant laws, regulations, and standards of the relevant regions.

[0039] By semantically matching the target user's historical business data with the knowledge graph of resource allocation, various basic entities related to resource allocation can be accurately extracted. Combining the edge relationships between different basic entities and the key entities to which each basic entity belongs, a visualized initial network is constructed. This initial network's topology reveals the interaction logic of multiple types of constraints in resource allocation, laying the foundation for parametric modeling of subsequent distributed constraint optimization algorithms. Furthermore, by introducing the relationships between basic entities and key entities, it is convenient to dynamically adjust basic entities through key entities, thereby improving the adjustment efficiency and accuracy of distributed constraint optimization.

[0040] Users can add or delete basic entities in the initial network, and also edit edge relationships, such as adjusting the type of edge relationship or modifying the constraint parameters within it. For example, when there is an optimal ratio constraint edge relationship between two basic entities, the corresponding optimal ratio can be adjusted from a first ratio value to a second ratio value; when there is a reverse constraint edge relationship between two basic entities, the ratio of one basic entity can be decreased while the ratio of the other basic entity is increased. By updating the basic entities and edge relationships in the initial network in response to editing operations on the initial network to obtain the target network, the matching degree between the target network and the user's resource allocation needs can be further improved, reducing the number of resource allocation adjustments and thus improving resource allocation efficiency.

[0041] Distributed constraint optimization is a common technique for solving distributed system modeling and collaborative optimization problems. In this embodiment, high parallelism and fault tolerance are achieved through the interaction between agents, leading to global optimum. For example, agents and variables within agents can be determined based on the key entities to which the basic entities in the target network belong. For each agent, a local constraint cost is constructed based on the edge relationships between different basic entities within that agent; and a global constraint cost is constructed based on the edge relationships across agents, resulting in a distributed constraint optimization model. During the solution process, each agent not only independently calculates its local constraint cost and updates its local variables accordingly, but also communicates with other agents to exchange variable state information and constraints in real time, dynamically adjusting neighborhood variable values ​​based on a global consensus protocol. By minimizing the local constraint costs of each agent and the global constraint costs across agents, the values ​​of each basic variable are obtained, and a resource allocation scheme for the target user is derived based on these values.

[0042] The technical solution provided in this application semantically matches the historical business data of the target user with the knowledge graph of resource allocation, extracts basic entities related to resource constraints, and constructs a visualized initial network by combining the edge relationships between basic entities and the key entities to which the basic entities belong. This initial network can present the interaction logic of multiple types of resource constraints, laying the foundation for the parameterized modeling of subsequent distributed constraint optimization algorithms. Furthermore, in response to interactive editing operations on the initial network, the entity nodes and edge relationships are updated in real time to form the target network, further improving the matching degree between the target network and the user's actual needs and effectively reducing the number of solution iterations. Moreover, through a dual mechanism of each agent independently calculating the local constraint cost and collaboratively optimizing the global constraint cost, the optimal values ​​of each basic variable are efficiently determined under the distributed solution framework, thereby generating a resource allocation scheme that combines theoretical optimality and practical feasibility, improving the accuracy and efficiency of resource allocation.

[0043] Example 2

[0044] Figure 2 This is a flowchart of a resource allocation method based on distributed constraint optimization according to Embodiment 2 of this application. See also... Figure 2 Based on the above embodiments, the resource allocation method based on distributed constraint optimization in this embodiment may include:

[0045] S210. Match the historical business data of the target user with the knowledge graph of resource allocation to obtain at least two basic entities. Based on the key entities to which the basic entities belong and the edge relationships between different basic entities, construct and display the initial network.

[0046] S220. Obtain real-time business data from the business system, and generate at least two candidate adjustment strategies for resource allocation based on the real-time business data;

[0047] S230. Match the candidate adjustment strategies with the initial network respectively, and select the target adjustment strategy from the at least two candidate adjustment strategies according to the matching results;

[0048] S240. The target network is obtained by interacting with the user according to the target adjustment strategy and editing the initial network according to the user's interaction operation.

[0049] S250. Construct a distributed constraint optimization model based on the target network and the historical service data;

[0050] S260. Solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user.

[0051] Among them, the historical business data of the target user refers to the static information such as the user's long-term accumulated behavior records, preference characteristics, and transaction history, which is used to characterize the individual behavior patterns and stable characteristics of the target user; while the real-time business data of the business system comes from the external environment or the global operation system outside the target user, such as market fluctuation indicators, policy change signals, and early warning of emergencies, which is used to characterize the real-time situation in the business field and provide a basis for dynamic adjustment of resource allocation strategies in response to sudden changes in industry trends or crisis events.

[0052] For example, semantic analysis is performed on real-time business data from the business system to determine whether market volatility indicators or policy change signals exist, thereby obtaining the target dynamic information present in the business system. If real-time business data contains terms such as "reserve requirement ratio cut," "interest rate cut," "industry correction," or "market index returning to...point," then market volatility indicators are triggered; if real-time business data contains terms such as "tax incentives" or "subsidies," then policy change signals are triggered. The target dynamic information is then matched with strategy rules in the rule base to obtain at least two successfully matched candidate adjustment strategies.

[0053] For each candidate adjustment strategy, the node coverage rate of the candidate adjustment strategy on the initial network can be determined, and the candidate adjustment strategy with the highest node coverage rate is selected as the target adjustment strategy. For example, the candidate adjustment strategy can be semantically encoded to obtain a semantic encoding result, and the semantic encoding result can be matched with the basic entities, key entities, or edge relationships in the initial network to obtain the matching degree of the candidate adjustment strategy; where the matching degree is used to characterize the node coverage rate. Furthermore, candidate editing operations are generated using the target adjustment strategy, and the target editing operation is obtained by interacting with the user based on the candidate editing operation. The target editing operation is then used to update the initial network to obtain the target network; that is, the target network is obtained by updating the initial network based on the target adjustment strategy. By processing real-time business data from the business system to obtain at least two candidate adjustment strategies, and determining the node coverage rate of each candidate adjustment strategy on the initial network, the candidate adjustment strategy with the highest node coverage rate is selected as the target adjustment strategy. This simplifies the editing operation of the initial network and improves the efficiency of determining the target network; furthermore, it ensures that the target network not only contains the individual behavioral patterns of the target users but also takes into account the dynamics of industry trends, thereby improving the reliability of the target network.

[0054] In one optional implementation, the step of matching the candidate adjustment strategies with the initial network respectively, and selecting a target adjustment strategy from the at least two candidate adjustment strategies based on the matching results, includes: matching the candidate adjustment strategies with the initial network respectively to obtain successfully matched candidate subnetworks; determining the importance of the candidate subnetworks based on the number of basic entities and constraint edges in the candidate subnetworks, as well as the number of historical edits made by the target user to the candidate subnetworks; and selecting a target adjustment strategy from the at least two candidate adjustment strategies based on the importance.

[0055] For each candidate adjustment strategy, semantic encoding is performed to obtain the semantic encoding result. The similarity between the semantic encoding result of the candidate adjustment strategy and the encoding results of each basic entity and edge relationship in the initial network is calculated. Basic entities and edge relationships with similarity greater than a similarity threshold are used to obtain candidate sub-networks. The importance of the candidate sub-network is determined by combining the number of basic entities, the number of constraint edges, and the number of historical edits by the target user. For example, the importance of the candidate sub-network can be obtained by weighting the number of basic entities, the number of constraint edges, and the number of historical edits. The candidate adjustment strategy corresponding to the candidate sub-network with the highest importance is selected as the target adjustment strategy. By performing semantic encoding and similarity calculation on the candidate adjustment strategies, candidate sub-networks corresponding to the candidate adjustment strategies are accurately selected. The importance of the candidate sub-network is determined by combining the number of basic entities, the number of constraint edges, and the number of historical edits. This allows for efficient and accurate determination of the target adjustment strategy, thereby further improving the efficiency and accuracy of resource allocation.

[0056] In one optional implementation, the step of interacting with the user according to the target adjustment strategy and editing the initial network according to the user's interaction to obtain the target network includes: determining a first entity associated with the target adjustment strategy from the initial network, and obtaining a second entity with an edge relationship to the first entity; generating and displaying candidate editing operations based on the edge relationship between the first entity and the second entity; wherein the edge relationship includes at least one of the following: optimal allocation constraint, reverse constraint, or conditionally optimal configuration constraint; and updating the constraint relationship between the first entity and the second entity according to the interaction processing of the candidate editing operations to obtain the target network.

[0057] For example, the semantic encoding result of the target adjustment strategy is obtained by semantically encoding the target adjustment strategy; the similarity between the semantic encoding result of the target adjustment strategy and the encoding result of each basic entity in the initial network is calculated, and the basic entity with the highest similarity is taken as the first entity; other basic entities connected to the first entity are also obtained from the initial network as the second entity; based on the edge relationship between the first entity and the second entity, and according to the type of edge relationship, candidate editing operations are generated and displayed; in response to the interactive operation of the candidate editing operation, the constraint relationship between the first entity and the second entity is updated to obtain the target network.

[0058] The edge relationships between the first entity and the second entity include, but are not limited to, optimal ratio constraints, inverse constraints, or conditionally optimal configuration constraints. If the edge relationship is an optimal ratio constraint, an optimal configuration adjustment control can be displayed in the interactive interface to adjust the ratio between the first and second entities in response to user actions. If the edge relationship is an inverse constraint, an adjustment control for the first entity can be displayed in the interactive interface, allowing users to increase or decrease the number of the first entity. If the edge relationship is a conditionally optimal configuration constraint, a condition input box can be displayed in the interactive interface, allowing users to define conditions such as the time range, resource threshold, or priority for the constraint to take effect. By using the base entity in the initial network that is most similar to the result of the target adjustment strategy as the first entity, and providing candidate editing operations based on the constraint type between the first and second entities, the target user can update the constraint relationship between them to obtain the target network, further improving the efficiency and accuracy of network adjustment.

[0059] The technical solution provided in this application's embodiments obtains at least two candidate adjustment strategies by processing real-time business data from the business system, determines the node coverage of each candidate adjustment strategy on the initial network, and selects the one with the highest coverage as the target adjustment strategy. This not only simplifies the editing operation of the initial network and improves the efficiency of determining the target network, but also integrates industry trend dynamics into the target network, enhancing its reliability. Furthermore, by matching the candidate adjustment strategies with the initial network to obtain candidate sub-networks, and combining the number of basic entities, the number of constraint edges, and the number of historical edits in the candidate sub-networks to determine the target adjustment strategy, the technical solution further optimizes the efficiency and accuracy of network adjustment by setting the basic entity in the initial network most similar to the target adjustment strategy as the first entity and providing candidate editing operations based on constraint types for the target user to update constraint relationships.

[0060] Figure 3 This is a flowchart of a resource allocation method based on distributed constraint optimization according to Embodiment 2 of this application. See also... Figure 3 Based on the above embodiments, the resource allocation method based on distributed constraint optimization in this embodiment may include:

[0061] S310. Match the historical business data of the target user with the knowledge graph of resource allocation to obtain at least two basic entities. Based on the key entities to which the basic entities belong and the edge relationships between different basic entities, construct and display the initial network.

[0062] S320. In response to the editing operation on the initial network, the target network is obtained;

[0063] S330. Treat each key entity in the target network as an intelligent agent, treat the basic entities connected to the key entities as variables of the corresponding intelligent agents, and determine the target constraint relationship between different variables based on the edge relationship between different basic entities.

[0064] S340. Extract the value range of the variables and the parameter values ​​of the target constraint relationship from the historical business data, and determine the target constraint cost function between different variables based on the parameter values;

[0065] S350. Based on the intelligent agent, the variables, the value range, and the objective constraint cost function, construct the distributed constraint optimization model;

[0066] S360. Solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user.

[0067] In this embodiment of the invention, the distributed constraint model can be represented as a quadruple.<A,X,D,F> The model is defined as follows: A represents the set of agents, where each key entity in the target network can be considered as an agent. For example, if four key entities are included, then four agents will be constructed. X represents the set of variables, where each agent controls multiple variables. The base entities connected to the key entities are used as the variables of the corresponding agents. For example, if a key entity is connected to four base entities, the corresponding agent will have four variables. D represents the set of value ranges, where each variable takes a value from its value range. F represents the set of constraint costs. Local constraint costs within an agent are constructed based on the edge relationships between different base entities within the same agent; global constraint costs are constructed based on the edge relationships between different base entities across agents. In other words, the set of constraint costs includes both local and global constraint costs.

[0068] The range of variables and the parameter values ​​of the target constraint relationship can both be extracted from the historical business data of the target user. The target constraint relationship may include at least one of the following: optimal allocation constraint, reverse constraint, or conditionally optimal configuration constraint. For example, if the proportion of the first variable is a and the proportion of the second variable is b, the cost function z = (x - a1) 2 +(y-b1) 2The minimum value is reached, i.e., the lowest point is (a1, b1). The constraint relationship between the first and second variables can then be described as an optimal allocation constraint. If, as the value of the second variable increases, the proportion of the first variable gradually decreases, the constraint cost between them is defined by the formula -a2x - b2y + c2 = z, where a2, b2, and c2 are constants. In this case, the constraint relationship between the first and second variables can be called an inverse proportion constraint or a negative correlation constraint. For example, considering the properties of gold, it is a safe-haven resource; the further away from retirement time, the lower the proportion of the gold variable. Therefore, there is an inverse constraint between the environmental variable and the retirement time variable.

[0069] Conditional optimal configuration constraints refer to the definition or rule of finding the optimal configuration scheme that satisfies specific constraints by adjusting configuration variables to minimize or maximize a certain objective function under given conditions. For example, based on the customer type (e.g., growth-oriented) and the evaluation coefficient y (normalized to [1,10]), a golden ratio configuration is performed, resulting in the conditional optimal configuration constraint z = y × |xI|, where x ∈ [1,10], y ∈ [1,10], and I is the extreme value corresponding to minimization or maximization. Taking the constraint relationship between heritage planning variables and golden ratio variables as an example, if the golden ratio configuration for the target user is optimal at 5%, normalizing to 5% yields I with a value of 1.45, resulting in the constraint z = y × |x - 1.45|, where x ∈ [1,10], y ∈ [1,10].

[0070] Taking the constraint relationship between insurance purchase decisions and estate planning variables as an example, the optimal insurance purchase needs of the target user can be calculated using the following formula:

[0071]

[0072] Where I represents the optimal insurance purchase demand, N represents estate planning demand [0, 1 million], R represents the risk tolerance level assessment coefficient obtained from the business system, V0 represents the actual estate value, and V A To determine the target value for estate planning, and considering the different value ranges of various variables, their ranges can be normalized. Taking retirement time as an example, its value ranges from [0, 40], and this range can be updated in real time according to retirement policies. The following normalization formula can be used to normalize retirement time to integers 1, 2, ..., 10:

[0073]

[0074] Furthermore, distributed constraint optimization algorithms (such as ant colony optimization and distributed constraint satisfaction algorithms) can be used to solve the problem and obtain the variable values ​​of each agent when the local constraint cost and the global constraint cost are minimized. That is, the values ​​of various candidate resource variables are obtained based on different investment preferences, risk tolerance, and real-time dynamic information, which serve as the resource allocation scheme for the target user. The resource allocation scheme can be recommended and displayed in real time through relevant platform interfaces.

[0075] The technical solution provided in this application uses key entities in the target network as intelligent agents and basic entities connecting the key entities as variables. By determining the target constraint relationship between variables, the value range of variables and parameter values ​​of constraints are extracted from the historical business data of the target user, and a distributed constraint optimization model is constructed accordingly. This can flexibly cope with complex and ever-changing business needs and improve resource allocation efficiency.

[0076] In one alternative implementation, the initial network includes at least two key entities: resource allocation, time decision, risk management decision, or inheritance decision. The resource allocation key entity includes basic entities of at least two candidate resources. The time decision key entity includes retirement time or investment period. The risk management decision key entity includes at least one of insurance purchase decision, medical expense budget, or risk tolerance level. The inheritance decision key entity includes estate planning or grandchildren's education fund.

[0077] For example, the distributed constrained optimization model may include a resource allocation agent, and at least one of a time decision-making agent, a risk management decision-making agent, or a succession decision-making agent. The resource allocation agent may include at least one candidate resource variable: stock investment, bond investment, investment in wealth management products, gold, or other derivatives. The time decision-making agent may include a retirement time or investment period variable. The risk management decision-making agent may include at least one variable: insurance purchase decision, medical expense budget, or risk tolerance level. The succession decision-making agent may include estate planning or grandchildren's education fund variable. By constructing and solving the distributed constrained optimization model, the values ​​of each candidate variable can be obtained, serving as the resource allocation scheme for the target user.

[0078] Example 4

[0079] Figure 4 This is a schematic diagram of a resource allocation device based on distributed constraint optimization according to Embodiment 4 of this application. It is applicable to the allocation of user resources and can be executed by the resource allocation device based on distributed constraint optimization. This resource allocation device can be implemented in hardware and / or software and can be configured in a computer device. Figure 4As shown, the device includes:

[0080] The initial network module 410 is used to match the historical business data of the target user with the knowledge graph of resource allocation to obtain at least two basic entities, and to construct and display the initial network based on the key entities to which the basic entities belong and the edge relationships between different basic entities.

[0081] Target network module 420 is used to obtain a target network in response to an editing operation on the initial network;

[0082] The distributed constraint optimization module 430 is used to construct a distributed constraint optimization model based on the target network and the historical service data.

[0083] The resource allocation scheme module 440 is used to solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user.

[0084] In one alternative implementation, the target network module 420 includes:

[0085] The candidate strategy submodule is used to acquire real-time business data from the business system and generate at least two candidate adjustment strategies for resource allocation based on the real-time business data.

[0086] The target policy submodule is used to match the candidate adjustment policies with the initial network respectively, and select the target adjustment policy from the at least two candidate adjustment policies according to the matching results;

[0087] The target network submodule is used to interact with the user based on the target adjustment strategy and to edit the initial network based on the user's interaction to obtain the target network.

[0088] In one alternative implementation, the target strategy submodule includes:

[0089] A candidate subnetwork unit is used to match the candidate adjustment strategy with the initial network to obtain a successfully matched candidate subnetwork.

[0090] The importance unit is used to determine the importance of a candidate subnetwork based on the number of basic entities and constraint edges in the candidate subnetwork, as well as the number of times the target user has edited the candidate subnetwork in history.

[0091] The target strategy unit is used to select a target adjustment strategy from the at least two candidate adjustment strategies based on the importance.

[0092] In one alternative implementation, the target network submodule includes:

[0093] An entity determination unit is used to determine a first entity associated with the target adjustment strategy from the initial network, and to obtain a second entity that has an edge relationship with the first entity;

[0094] An editing operation unit is used to generate and display candidate editing operations based on the edge relationship between the first entity and the second entity; wherein the edge relationship includes at least one of the following: optimal ratio constraint, reverse constraint, or conditionally optimal configuration constraint;

[0095] The target network unit is used to update the constraint relationship between the first entity and the second entity based on the interactive processing of the candidate editing operation, so as to obtain the target network.

[0096] In one optional implementation, the distributed constraint optimization module 430 includes:

[0097] The model transformation submodule is used to treat each key entity in the target network as an intelligent agent, the basic entities connected to the key entities as variables of the corresponding intelligent agents, and to determine the target constraint relationship between different variables based on the edge relationship between different basic entities.

[0098] The parameter extraction submodule is used to extract the value range of the variables and the parameter values ​​of the target constraint relationship from the historical business data, and to determine the target constraint cost function between different variables based on the parameter values;

[0099] The model building submodule is used to build the distributed constraint optimization model based on the agent, the variables, the value range, and the objective constraint cost function.

[0100] In one alternative implementation, the initial network includes at least two key entities: resource allocation, time decision, risk management decision, or inheritance decision. The resource allocation key entity includes basic entities of at least two candidate resources. The time decision key entity includes retirement time or investment period. The risk management decision key entity includes at least one of insurance purchase decision, medical expense budget, or risk tolerance level. The inheritance decision key entity includes estate planning or grandchildren's education fund.

[0101] The resource allocation device based on distributed constraint optimization provided in this application can execute the resource allocation method based on distributed constraint optimization provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing each resource allocation method based on distributed constraint optimization.

[0102] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0103] Example 5

[0104] Figure 5 This is a schematic diagram of the structure of an electronic device 510 implementing the resource allocation method based on distributed constraint optimization according to embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0105] like Figure 5 As shown, the electronic device 510 includes at least one processor 511 and a memory, such as a read-only memory (ROM) 512 or a random access memory (RAM) 513, communicatively connected to the at least one processor 511. The memory stores computer programs executable by the at least one processor. The processor 511 can perform various appropriate actions and processes based on the computer program stored in the ROM 512 or loaded from storage unit 518 into the RAM 513. The RAM 513 can also store various programs and data required for the operation of the electronic device 510. The processor 511, ROM 512, and RAM 513 are interconnected via a bus 514. An input / output (I / O) interface 515 is also connected to the bus 514.

[0106] Multiple components in electronic device 510 are connected to I / O interface 515, including: input unit 516, such as keyboard, mouse, etc.; output unit 517, such as various types of displays, speakers, etc.; storage unit 518, such as disk, optical disk, etc.; and communication unit 519, such as network card, modem, wireless transceiver, etc. Communication unit 519 allows electronic device 510 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0107] Processor 511 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 511 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 511 performs the various methods and processes described above, such as resource allocation methods based on distributed constraint optimization.

[0108] In some embodiments, the resource allocation method based on distributed constraint optimization can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 518. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 510 via ROM 512 and / or communication unit 519. When the computer program is loaded into RAM 513 and executed by processor 511, one or more steps of the resource allocation method based on distributed constraint optimization described above can be performed. Alternatively, in other embodiments, processor 511 can be configured for the resource allocation method based on distributed constraint optimization by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0114] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0115] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A resource allocation method based on distributed constraint optimization, characterized in that, include: The historical business data of the target user is matched with the knowledge graph of resource allocation to obtain at least two basic entities. Based on the key entities to which the basic entities belong and the edge relationships between different basic entities, an initial network is constructed and displayed. The target network is obtained in response to the editing operation on the initial network; A distributed constraint optimization model is constructed based on the target network and the historical business data; Solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user; Wherein, obtaining the target network in response to the editing operation on the initial network includes: The system acquires real-time business data from the business system and generates at least two candidate adjustment strategies for resource allocation based on the real-time business data. The real-time business data from the business system is used to characterize the real-time situation in the business domain and provide a dynamic basis for adjusting resource allocation strategies in response to sudden changes in industry trends or crisis events. The candidate adjustment strategies are matched with the initial network respectively, and the target adjustment strategy is selected from the at least two candidate adjustment strategies based on the matching results; The target network is obtained by adjusting the strategy according to the target and interacting with the user, and by editing the initial network according to the user's interaction.

2. The method according to claim 1, characterized in that, The step of matching the candidate adjustment strategies with the initial network respectively, and selecting the target adjustment strategy from the at least two candidate adjustment strategies based on the matching results, includes: The candidate adjustment strategies are matched with the initial network to obtain successfully matched candidate subnetworks. The importance of a candidate subnetwork is determined based on the number of basic entities and constraint edges in the candidate subnetwork, as well as the number of times the target user has edited the candidate subnetwork in history. Based on the importance level, a target adjustment strategy is selected from the at least two candidate adjustment strategies.

3. The method according to claim 1, characterized in that, The step of interacting with the user based on the target adjustment strategy and editing the initial network according to the user's interaction to obtain the target network includes: From the initial network, a first entity associated with the target adjustment strategy is determined, and a second entity with an edge relationship with the first entity is obtained; Based on the edge relationship between the first entity and the second entity, candidate editing operations are generated and displayed; wherein, the edge relationship includes at least one of the following: optimal ratio constraint, reverse constraint, or conditionally optimal configuration constraint; Based on the interactive processing of the candidate editing operations, the constraint relationship between the first entity and the second entity is updated to obtain the target network.

4. The method according to claim 1, characterized in that, The step of constructing a distributed constrained optimization model based on the target network and the historical business data includes: Each key entity in the target network is treated as an agent, the basic entities connected to the key entities are treated as variables of the corresponding agents, and the target constraint relationship between different variables is determined according to the edge relationship between different basic entities. Extract the value range of the variables and the parameter values ​​of the target constraint relationship from the historical business data, and determine the target constraint cost function between different variables based on the parameter values; The distributed constraint optimization model is constructed based on the agent, the variables, the value range, and the objective constraint cost function.

5. The method according to claim 1, characterized in that, The initial network includes at least two key entities: resource allocation, time decision, risk management decision, or inheritance decision. The resource allocation key entities include basic entities of at least two candidate resources. The time decision key entities include retirement time or investment period. The risk management decision key entities include at least one of insurance purchase decisions, medical expense budgets, or risk tolerance levels. The inheritance decision key entities include estate planning or grandchildren's education funds.

6. A resource allocation device based on distributed constraint optimization, characterized in that, include: The initial network module is used to match the target user's historical business data with the knowledge graph of resource allocation to obtain at least two basic entities, and to construct and display the initial network based on the key entities to which the basic entities belong and the edge relationships between different basic entities. A target network module is used to obtain a target network in response to an editing operation on the initial network; A distributed constraint optimization module is used to construct a distributed constraint optimization model based on the target network and the historical service data. The resource allocation scheme module is used to solve the distributed constraint optimization model to obtain the resource allocation scheme for the target user. The target network module includes: The candidate strategy submodule is used to acquire real-time business data from the business system and generate at least two candidate adjustment strategies for resource allocation based on the real-time business data; wherein, the real-time business data from the business system is used to characterize the real-time situation in the business domain and provide a dynamic adjustment basis for resource allocation strategies in response to sudden changes in industry trends or crisis events. The target policy submodule is used to match the candidate adjustment policies with the initial network respectively, and select the target adjustment policy from the at least two candidate adjustment policies according to the matching results; The target network submodule is used to interact with the user based on the target adjustment strategy and to edit the initial network based on the user's interaction to obtain the target network.

7. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images