Service distribution method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a service distribution method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for the field of financial science and technology. The method comprises the steps of obtaining object interaction data and performing node construction to obtain an object node; performing graph construction on the object nodes according to the object interaction data to obtain an object relation graph; determining an original node from the object nodes based on the object type, and extracting a candidate relation chain containing the original node from the object relation graph; performing relation type identification on each connection edge of the candidate relation chain to obtain a relation type between the object nodes, and performing matching degree evaluation on the candidate relation chain according to the relation type and the object type to obtain a matching score; and screening out a target execution node from the candidate relation chain according to the matching score, and matching an original node for the target execution node. According to the embodiment of the invention, the matching degree between a customer and a salesman can be improved during business development.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology and is applicable to the field of financial technology, and in particular to a business distribution method and device, electronic equipment and storage medium. Background Art

[0002] In the process of promoting insurance business, corporate customers with potential insurance value usually need to be assigned to appropriate sales representatives for contact and follow-up to improve customer conversion efficiency. In related technologies, customer information is often distributed to a group of sales representatives through platform broadcasting, and the sales representatives claim it independently. However, this method may cause multiple sales representatives to contact the same customer at the same time or repeatedly, reducing the customer experience. It may also cause sales representatives with real related backgrounds or resource advantages to not get priority contact opportunities, thereby affecting the accuracy and conversion rate of customer contact. Therefore, how to improve the matching degree between customers and sales representatives when conducting business has become a technical problem that needs to be solved urgently. Summary of the Invention

[0003] The main purpose of the embodiments of the present application is to propose a business allocation method and device, an electronic device and a storage medium, aiming to improve the matching degree between customers and salesmen when conducting business.

[0004] To achieve the above objectives, a first aspect of an embodiment of the present application provides a service allocation method, the method comprising:

[0005] Get object interaction data between business objects;

[0006] Performing node construction on the business object to obtain an object node; wherein the object node has an object type, and the object type is used to indicate that the business object is a customer object or a service object;

[0007] Constructing a graph of the object nodes according to the object interaction data to obtain an object relationship graph;

[0008] Determining an original node from the object nodes based on the object type, and extracting a candidate relationship chain including the original node from the object relationship graph; wherein the original node represents the customer object;

[0009] Identifying the relationship type of each connecting edge of the candidate relationship chain to obtain the relationship type between the object nodes, and evaluating the matching degree of the candidate relationship chain based on the relationship type and the object type to obtain a matching score;

[0010] A target execution node is screened out from the candidate relationship chain according to the matching score, and the original node is matched to the target execution node; wherein the target execution node represents the service object.

[0011] In some embodiments, evaluating the degree of matching of the candidate relationship chain according to the relationship type and the object type to obtain a matching score includes:

[0012] Filtering an intermediate relationship chain from the candidate relationship chains according to the object type, wherein the starting node of the intermediate relationship chain is the original node, and the ending node of the intermediate relationship chain represents the service object;

[0013] According to the relationship type of each intermediate connection edge in the intermediate relationship chain, performing a relationship value evaluation on the intermediate connection edge to obtain a relationship score;

[0014] Score calculation is performed on all the relationship scores of the intermediate relationship chain to obtain the matching score.

[0015] In some embodiments, calculating the scores of all the relationships in the intermediate relationship chain to obtain the matching score includes:

[0016] Obtaining target weight data for each of the relationship scores;

[0017] Multiplying the relationship score and the target weight data to obtain an intermediate score;

[0018] All the intermediate scores are summed up to obtain the matching score.

[0019] In some embodiments, obtaining target weight data for each relationship score includes:

[0020] Filtering the object interaction data according to the intermediate relationship chain to obtain intermediate interaction data;

[0021] Performing behavior recognition on the intermediate interaction data to obtain a behavior stage type of each intermediate connection edge;

[0022] The original weight data of each intermediate connection edge is determined according to the behavior stage type of the intermediate connection edge, and the original weight data is used as the target weight data of the relationship score.

[0023] In some embodiments, obtaining target weight data for each relationship score includes:

[0024] Sequentially numbering the intermediate connection edges of each intermediate relationship chain to obtain connection edge sequence identifiers;

[0025] Querying a preset scoring mapping relationship table according to the connection edge sequence identifier to obtain the importance factor of the intermediate connection edge;

[0026] The importance factor is used as the weight data.

[0027] In some embodiments, filtering out a target execution node from the candidate relationship chain according to the matching score includes:

[0028] Arranging the matching scores in descending order to obtain a score sequence;

[0029] Selecting a preset number of target scores from the score sequence;

[0030] A target relationship chain is determined from the intermediate relationship chains according to the target score, and a terminal node of the target relationship chain is used as the target execution node.

[0031] In some embodiments, determining a target relationship chain from the intermediate relationship chains according to the target score, and using the terminal node of the target relationship chain as the target execution node, includes:

[0032] Determine a target relationship chain from the intermediate relationship chains according to the target score, and use the terminal node of the target relationship chain as a candidate execution node;

[0033] Acquiring the number of allocated objects of the candidate execution node, and determining that the candidate execution node is an overloaded execution node based on the number of allocated objects;

[0034] Eliminating overloaded execution nodes from the candidate execution nodes, and sequentially selecting a reference number of candidate scores from the score sequence, where the reference number is the number of the overloaded execution nodes;

[0035] The candidate execution node is updated according to the candidate score, and the candidate execution node is used as the target execution node.

[0036] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a service distribution device, the device comprising:

[0037] The acquisition module is used to obtain object interaction data between business objects;

[0038] A node construction module, configured to construct a node for the business object to obtain an object node; wherein the object node has an object type, and the object type is used to indicate whether the business object is a customer object or a service object;

[0039] A graph construction module, configured to construct a graph of the object nodes according to the object interaction data to obtain an object relationship graph;

[0040] a relationship chain extraction module, configured to determine an original node from the object node based on the object type, and extract a candidate relationship chain including the original node from the object relationship graph; wherein the original node represents the customer object;

[0041] a matching degree evaluation module, configured to identify the relationship type of each connecting edge of the candidate relationship chain, obtain the relationship type between the object nodes, and evaluate the matching degree of the candidate relationship chain based on the relationship type and the object type to obtain a matching score;

[0042] An allocation module is configured to screen out a target execution node from the candidate relationship chain according to the matching score, and match the original node to the target execution node; wherein the target execution node represents the service object.

[0043] 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 the processor implements the method described in the first aspect when executing the computer program.

[0044] To achieve the above-mentioned purpose, the fourth aspect of the embodiments 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 described in the first aspect.

[0045] The business allocation method and device, electronic device, and storage medium proposed in this application fully restore the historical connections and potential social paths between business objects by acquiring object interaction data and constructing object nodes and object relationship graphs. This allows the candidate relationship chain starting with the customer object to be identified in the graph structure, and relationship type identification and matching degree assessment are performed. Ultimately, based on the matching score, the service object that best suits the customer object is selected as the target execution node. Compared to traditional business allocation solutions, the embodiments of this application, through graph structured modeling and relationship chain assessment, can accurately depict the potential associations and matching relationships between customers and salespeople. Salespeople with genuine association backgrounds or service advantages can be mined from historical data, allowing them to be paired with target customers first, ultimately improving the matching degree between customers and salespeople. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a flow chart of the service allocation method provided in an embodiment of the present application;

[0047] Figure 2 yes Figure 1 Flowchart of step S105 in FIG.

[0048] Figure 3 yes Figure 2 Flowchart of step S203 in FIG.

[0049] Figure 4 yes Figure 3 Flowchart of step S301 in FIG.

[0050] Figure 5 yes Figure 1 Flowchart of step S106 in FIG.

[0051] Figure 6 yes Figure 5 Flowchart of step S503 in FIG.

[0052] Figure 7 This is a schematic diagram of the structure of the service distribution device provided in an embodiment of the present application;

[0053] Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0055] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0057] First, let’s analyze some of the terms used in this application:

[0058] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thinking. It also encompasses the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0059] In the insurance promotion process, especially for corporate clients with potential insurance value in the group insurance market, it's often necessary to use platform systems to assign customer information to sales representatives for subsequent effective customer outreach and conversion. Common existing approaches include using platforms to distribute customer resources in bulk, with sales representatives independently claiming them, or setting unified allocation rules for initial allocation of customer resources. However, these approaches have exposed numerous shortcomings in practice, failing to meet the requirements for refined customer management and high-quality service. For one thing, current customer allocation rules are relatively simplistic, often relying solely on static matching based on basic attributes such as sales representatives' region, rank, or historical performance. These factors overlook the dynamic matching relationship between customer characteristics and sales representatives, such as whether the sales representative possesses relevant professional background in the customer's industry, whether the customer groups they have previously followed up on are related to the customer, and the sales representative's historical conversion rate for specific customer profiles. This low-precision matching mechanism can make it difficult for assigned sales representatives to effectively reach customers. It can even lead to a loss of customer trust due to poor communication or a lack of industry understanding, ultimately impacting insurance success rates. On the other hand, most current customer distribution methods adopt a platform broadcast model, that is, the same batch of customers are pushed to multiple sales representatives at the same time, and the sales representatives are the first to claim them in the system. Although this mechanism improves response speed, it also causes many problems. For example, multiple sales representatives may contact the same customer repeatedly or in an unordered manner, causing frequent interruptions to the customer, affecting the customer experience and corporate brand image. Some sales representatives may take advantage of their response speed or system authority to prioritize claiming high-quality customers, resulting in unfair resource allocation. At the same time, the "most suitable" sales representatives who have potential social relationships with customers, industry resources or historical follow-up experience cannot obtain corresponding customer resources first, thus wasting potential high-conversion opportunities. Therefore, how to improve the matching degree between customers and sales representatives when conducting business has become a technical problem that needs to be solved urgently.

[0060] Based on this, the embodiments of the present application provide a business allocation method and device, an electronic device and a storage medium, which aim to improve the matching degree between customers and salesmen when conducting business.

[0061] The service allocation method and device, electronic device, and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the service allocation method in the embodiments of the present application is described.

[0062] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. 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 achieve optimal results.

[0063] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0064] The business allocation method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The business allocation method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the 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 distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the business allocation method, etc., but is not limited to the above forms.

[0065] 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, and the like. 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, and the like 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 via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0066] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0067] Figure 1 This is an optional flowchart of the service allocation method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0068] Step S101: Acquire object interaction data between business objects.

[0069] Step S102: construct a node for the business object to obtain an object node.

[0070] Step S103: constructing a graph of object nodes according to the object interaction data to obtain an object relationship graph.

[0071] Step S104: determining the original node from the object nodes based on the object type, and extracting a candidate relationship chain including the original node from the object relationship graph, wherein the original node represents the customer object.

[0072] Step S105 , performing relationship type identification on each connection edge of the candidate relationship chain to obtain the relationship type between the object nodes, and performing matching evaluation on the candidate relationship chain according to the relationship type and the object type to obtain a matching score.

[0073] Step S106: Filter out a target execution node from the candidate relationship chain based on the matching score, and match the target execution node with an original node, wherein the target execution node represents a service object.

[0074] Steps S101 to S106 shown in the embodiment of the present application completely restore the historical connections and potential social paths between business objects by acquiring object interaction data and constructing object nodes and object relationship graphs, and then identify candidate relationship chains starting with the customer object in the graph structure, perform relationship type identification and match degree assessment, and finally, based on the matching score, select the service object that best suits the customer object as the target execution node. Compared with traditional business allocation solutions, the embodiment of the present application can accurately depict the potential associations and matching relationships between customers and salespeople through graph structured modeling and relationship chain assessment, and mine salespeople with real related backgrounds or service advantages from historical data, giving them priority in pairing with target customers, ultimately improving the matching degree between customers and salespeople.

[0075] In step S101 of some embodiments, object interaction data refers to information about interactions or contacts between customers and sales representatives, such as telephone conversation records, online consultation records, historical insurance application records, meeting attendance records, social platform interaction data, email communication records, or referral sources from the same customer. Object interaction data is typically stored in a customer relationship management system, an intelligent sales platform, or an external data access module.

[0076] In step S102 of some embodiments, constructing nodes for business objects refers to abstractly representing the business objects as nodes in a graph structure and assigning attribute labels related to their business attributes to each node. In this embodiment, the object node has an object type, which indicates whether the business object is a customer object or a service object. A customer object is a customer group currently requiring business development, and a service object is a salesperson.

[0077] Node construction can be achieved by uniformly mapping the business object's identity information, role identification, behavioral characteristics, and other characteristics into a standardized structured node. For example, if a business object is corporate customer A in the insurance system, and this customer has attributes such as corporate identification, registration information, and historical insurance records on the platform, then this customer is constructed as a customer node. Alternatively, if another business object is salesperson B, and this salesperson has agency qualifications, industry service records, and historical transaction information, then this person is constructed as a service node.

[0078] In step S103 of some embodiments, graph construction refers to establishing a connection relationship between object nodes based on the constructed object nodes and the interaction data between them, forming an object relationship graph with a node-edge structure. The implementation method of graph construction is: for each pair of object nodes with interaction data, a connection edge is established between them according to the type, frequency or historical timeliness of the interaction behavior, and the relationship attribute information is recorded on the edge. For example, if the policy salesperson on the historical insurance policy of customer node A is service node B, then an edge is established between node A and node B, and marked as a "historical policy" relationship. If customer node A and customer node C are parent-child enterprises, then an edge is established between node A and node C, and marked as a "parent-child enterprise" relationship.

[0079] In step S104 of some embodiments, to match all customers with appropriate sales representatives, all nodes whose object type is a customer object are treated as origin nodes. Starting from this origin node, the object relationship graph is searched for all subgraph structures that have paths connecting to this origin node. The resulting set of paths is the candidate relationship chain. For example, if customer node A is connected to service node B via the "previously served the same enterprise" relationship, and service node B is further connected to service node C via the "belonging to the same industry group" relationship, the candidate relationship chain starting from A may include path AB or path ABC.

[0080] In step S105 of some embodiments, the specific method of implementing relationship type identification may be: classifying the interaction behavior to which the connection edge belongs according to the record source, interaction content, time node and business context in the object interaction data, and then identifying the relationship attributes of the connection edge, that is, the relationship attribute information in the embodiment of step S103.

[0081] For the implementation of the matching degree evaluation process, please refer to Figure 2 In some embodiments, step S105 may include but is not limited to steps S201 to S203:

[0082] Step S201 : screening out intermediate relationship chains from candidate relationship chains according to object types, wherein the starting node of the intermediate relationship chain is the original node, and the ending node of the intermediate relationship chain represents the service object.

[0083] Step S202 : performing a relationship value evaluation on each intermediate connection edge in the intermediate relationship chain according to the relationship type of each intermediate connection edge to obtain a relationship score.

[0084] Step S203: Calculate the scores of all relationships in the intermediate relationship chain to obtain a matching score.

[0085] In step S201 of some embodiments, an intermediate relationship chain refers to a path in a candidate relationship chain whose starting node is a customer object and whose ending node is a service object. The screening of the intermediate relationship chain is implemented by traversing each path in the candidate relationship chain in sequence, determining whether the starting node of the path is the original node (i.e., the customer who currently needs to be assigned a salesperson), and determining whether the ending node of the path is a service object. If both conditions are met, the path is marked as an intermediate relationship chain. For example, if the starting node of a candidate relationship chain is corporate customer B, the ending node is salesperson A, and the intermediate path nodes are, in sequence, the affiliated companies B1 and B2 of the company B, then the path meets the screening conditions and is determined to be an intermediate relationship chain.

[0086] Because candidate relationship chains are based on the set of all reachable paths from the original node in the object relationship graph, they may contain a large number of invalid paths where the starting point is not the target customer object and the end point is not the service object. For example, all nodes in the path are corporate customers, or the path ends at a customer node. If such paths are directly included in the subsequent matching evaluation, it will lead to confusion in the matching between customers and sales representatives. Screening out intermediate relationship chains ensures that only paths where the starting node is the original node and the end node clearly represents the service object are retained. This clarifies the business direction represented by the path, that is, the potential business connectivity relationship from customer to service, thereby ensuring the effectiveness of relationship identification and the clarity of matching logic.

[0087] In step S202 of some embodiments, relationship value assessment involves assigning a numerical score to each edge in the intermediate relationship chain based on the relationship type of the edge, to represent the business value of the edge between the customer object and the service object. An intermediate edge refers to any edge in the intermediate relationship chain.

[0088] The implementation method of relationship value assessment can be: setting predefined relationship types and their corresponding relationship scores, identifying the relationship types of the intermediate connecting edges, querying the matching scores and assigning them. The score setting can refer to the empirical judgment of the importance of various relationships in the actual business logic. For example, if the connection edge relationship type is "historical insurance policy salesperson", the score is 0.5; if the connection edge relationship type is "business owner association", the score is 0.8; if the connection edge relationship type is "historical inquiry and quotation salesperson", the score is 0.2. For example, a certain intermediate relationship chain contains three connection edges, and the corresponding relationship types are "parent-child enterprise association", "business owner association" and "historical insurance policy salesperson", then the relationship scores corresponding to the three edges are 0.6, 0.8 and 0.5 respectively, which are assigned to these three edges. In this embodiment, the correspondence between the relationship types and relationship scores between object nodes can be referred to Table 1. This table is only for explanation and example, and does not represent a strict limitation on the specific score of the relationship score:

[0089]

[0090] Table 1

[0091] In step S203 of some embodiments, the matching score is used to measure the matching strength between the customer object to be currently assigned and the service object.

[0092] The matching score can be calculated by directly weighting the relationship score of each intermediate link or using a predefined formula. For example, if an intermediate relationship chain contains four links, connecting node B1 (representing enterprise B1), node C1 (representing individual C1, who is the owner of enterprise B1), node C2 (representing individual C2, who is related to individual C1), node B2 (representing enterprise B2, who is a business contact of enterprise B2), and node A1 (representing salesperson A1, who is a historical insurance salesperson for enterprise B2), and the corresponding relationship scores are 0.8, 0.7, 0.6, and 0.5, the matching score can be set as the product of these four (i.e., all weight parameters default to 1), which is 0.168. It can also be calculated based on the average, maximum, or other strategies. The higher the matching score, the stronger the business relationship between the customer object and the service object reflected in the path, indicating a higher priority for it as a service matching path.

[0093] In steps S201 to S203 shown in the embodiment of the present application, an intermediate relationship chain is screened out from the candidate relationship chain according to the object type, and the relationship value of each intermediate connection edge in the intermediate relationship chain is evaluated according to the relationship type to obtain a relationship score; all relationship scores of the intermediate relationship chain are scored to obtain a matching score. In this way, the embodiment of the present application extracts the intermediate relationship chain with the customer object as the starting point and the service object as the end point by performing structured screening on the candidate relationship chain, and further introduces a relationship type identification and relationship value evaluation mechanism to assign a score to each connection edge in the intermediate relationship chain. On this basis, by calculating and processing the relationship scores of multiple intermediate relationship chains, a matching score reflecting the overall matching value is finally obtained, thereby achieving the optimal path screening and precise allocation between the customer object and the service object.

[0094] See also Figure 3 In some embodiments, step S203 may include but is not limited to steps S301 to S303:

[0095] Step S301: Obtain target weight data for each relationship score.

[0096] Step S302: multiply the relationship score and the target weight data to obtain an intermediate score.

[0097] Step S303: sum up all the intermediate scores to obtain a matching score.

[0098] In step S301 of some embodiments, obtaining target weight data can be achieved according to the following specific steps: First, the intermediate connection edges of each intermediate relationship chain are numbered in sequence to obtain a connection edge sequence identifier. For example, if an intermediate relationship chain consists of three connection edges, the first, second, and third connection edges are numbered 1, 2, and 3, respectively, based on the direction from the terminal node to the original node.

[0099] Then, the preset scoring mapping table is queried based on the connection sequence identifier to obtain the importance factor of the intermediate connection. For example, after querying the scoring mapping table, the importance factors 0.7, 0.2, and 0.1 are obtained respectively. Finally, the corresponding importance factors are used as the weight data of the intermediate connection.

[0100] In other embodiments, the weight data of the intermediate connection edge can be flexibly adjusted according to the recent interactive activity between two object nodes. Figure 4 Step S301 may include but is not limited to steps S401 to S403:

[0101] Step S401 : filtering object interaction data according to the intermediate relationship chain to obtain intermediate interaction data.

[0102] Step S402: Perform behavior recognition on the intermediate interaction data to obtain the behavior stage type of each intermediate connection edge.

[0103] Step S403 : determining original weight data of each intermediate connection edge according to the behavior stage type of the intermediate connection edge, and using the original weight data as target weight data of the relationship score.

[0104] In step S401 of some embodiments, intermediate interaction data refers to historical interaction records between object nodes involved in the intermediate relationship chain, which correspond one-to-one to the connection edges in the intermediate relationship chain. The content of the intermediate interaction data may include, but is not limited to, records of telephone conversations, offline visits, meeting minutes, inquiry submissions, document push, and cooperation intention registrations.

[0105] From all collected object interaction data, the interaction records between object nodes on the intermediate relationship chain path are extracted.

[0106] In step S402 of some embodiments, the behavior stage type is a classification label used to characterize the life cycle stage of the interactive behavior between business objects, reflecting the current state and activity level of the interactive relationship. The behavior stage type may include, but is not limited to, the initial contact stage, the intention communication stage, the in-depth communication stage, the transaction execution stage, and the silent stage. Behavior recognition of intermediate interaction data can be achieved in the following ways: setting an interaction frequency threshold, a time window, and a set of behavioral keywords, combining the timestamp, interaction content, and behavior label in the intermediate interaction data, determining the stage of the interactive behavior of each intermediate connection edge, and outputting the corresponding behavior stage type. For example, if there are multiple document transfers and on-site visit records between the object nodes corresponding to a certain connection edge in the past 30 days, then the connection edge is judged to be in the "in-depth communication stage" according to the rules.

[0107] Judgment can also be made through a pre-trained classification model. For example, the structures that can be used include a state classification network based on time series modeling, such as a long short-term memory network (LSTM), a bidirectional GRU network, or a staged logic recognition framework built based on an interactive event rule engine.

[0108] In step S403 of some embodiments, after obtaining the behavior stage type, a pre-set table of correspondences between behavior stage types and original weights is queried to obtain original weight data. For example, the initial contact stage corresponds to a weight of 0.2, the in-depth communication stage corresponds to a weight of 0.6, the transaction execution stage corresponds to a weight of 0.9, and the inactive and dormant stage corresponds to a weight of 0.1.

[0109] Steps S401 to S403, as illustrated in this embodiment of the present application, utilize a weight adjustment method based on the behavioral stage type identification mechanism to dynamically adjust the evaluation weights of the connecting edges in the intermediate relationship chain, thereby enhancing the business interpretation and responsiveness of path scoring. This method, in the absence of direct interaction between customer and service objects, allows the identification of the service object with the highest conversion value based on the path behavior state, thereby improving resource matching efficiency and customer reach accuracy, effectively addressing the issues of insufficient coverage and low adaptability associated with traditional matching mechanisms based on static attributes.

[0110] In step S302 of some embodiments, the relationship score corresponding to each intermediate link is multiplied by the target weight data of the link to obtain an intermediate score for comprehensive evaluation. For example, if the relationship score between node B2 (representing enterprise B2, and individual C2 is the corporate contact of enterprise B2) and node A1 (representing salesperson A1, who is the historical insurance salesperson of enterprise B2) is 0.5 and the target weight is 0.7, then the intermediate score corresponding to the link is 0.35.

[0111] In step S303 of some embodiments, all intermediate scores are summed to obtain a matching score representing the overall matching strength between the customer object and the service object. For example, if the intermediate scores of the three intermediate connecting edges of an intermediate relationship chain are 0.4, 0.3, and 0.2, respectively, then the final matching score between the customer and the salesperson is 0.9.

[0112] Steps S301 to S303 shown in the embodiment of the present application, by introducing target weight data and performing weighted calculations, can effectively distinguish the importance of different relationships in the paths when there are multiple indirect relationship paths between the customer object and the service object, thereby improving the credibility and practicality of the overall matching score; by superimposing and summarizing the intermediate scores, a matching score result reflecting the rationality of the business structure is formed, and accurate docking of customer resources and service resources is achieved, solving the problem of poor matching effect of traditional static allocation methods, and having significant practical value in customer conversion-oriented scenarios such as insurance business development.

[0113] In step S106 of some embodiments, matching the original node with the target execution node refers to establishing a business binding relationship between the original node and the target execution node, to indicate that the customer object will be responsible for contacting, following up and servicing the customer object by the service object.

[0114] Specifically, see Figure 5 In some embodiments, step S106 may also include but is not limited to steps S501 to S503:

[0115] Step S501: Arrange the matching scores in descending order to obtain a score sequence.

[0116] Step S502: Select a preset number of target scores from the score sequence.

[0117] Step S503: determine a target relationship chain from the intermediate relationship chains according to the target score, and use the terminal node of the target relationship chain as the target execution node.

[0118] In step S501 of some embodiments, the matching scores corresponding to all intermediate relationship chains are reordered in descending order to form an ordered score sequence.

[0119] In step S502 of some embodiments, a screening number parameter is preset according to business requirements, and the first several matching scores are sequentially selected from the sorted score sequence as target scores. In this embodiment, the preset number is 1.

[0120] In step S503 of some embodiments, based on the selected target score, intermediate relationship chains corresponding to the target score are searched, and the terminal node of each target relationship chain is extracted as the service object represented by the target relationship chain, i.e., determined as the target execution node. For example, if a matching score of 0.92 corresponds to a relationship chain of Customer Object B1 - Business Owner C1 - Salesperson A1, and a matching score of 0.88 corresponds to a relationship chain of Customer Object B1 - Holding Company B2 - Contact Person C2 - Salesperson A2, then Salesperson A1 is matched to serve Customer Object B1.

[0121] See also Figure 6 In some embodiments, step S503 includes but is not limited to steps S601 to S604:

[0122] Step S601 : determining a target relationship chain from the intermediate relationship chains according to the target score, and taking the terminal node of the target relationship chain as a candidate execution node.

[0123] Step S602 : obtaining the number of allocated objects of the candidate execution node, and determining that the candidate execution node is an overloaded execution node based on the number of allocated objects.

[0124] Step S603 : Eliminate the overloaded execution nodes from the candidate execution nodes, and select a reference number of candidate scores from the score sequence in sequence, where the reference number is the number of overloaded execution nodes.

[0125] Step S604: update the candidate execution node according to the candidate score, and use the candidate execution node as the target execution node.

[0126] In step S601 of some embodiments, based on a pre-selected target score, an intermediate relationship chain corresponding to the score value is searched, and a terminal node is extracted from the intermediate relationship chain as a candidate execution node.

[0127] In step S602 of some embodiments, an overloaded execution node refers to a node whose assigned number of service objects exceeds a set threshold within the current task allocation cycle. Specifically, the number of bound customers to a candidate execution node is counted and compared with a preset load threshold. If the number exceeds the threshold, the node is determined to be an overloaded execution node. For example, if service object A1 has been assigned 10 customer objects within the current cycle, and the platform's per-service-person load limit is 8, service object A1 is determined to be an overloaded execution node.

[0128] In some embodiments, in step S603, after removing the overloaded execution nodes, an equal number of new target scores are added based on the number of remaining candidate execution nodes, in order of highest and lowest scores. Specifically, the number M of overloaded execution nodes to be removed is determined, and M unused matching scores are sequentially extracted backward in the original score sequence as candidate scores.

[0129] In step S604 of some embodiments, the newly added candidate scores are mapped back to the corresponding intermediate relationship chains, the intermediate relationship chain termination nodes matching these scores are re-determined, and these termination nodes are added as new candidate execution nodes, ultimately forming an updated target execution node set.

[0130] Steps S601 to S604, as illustrated in this embodiment of the present application, incorporate a mechanism for identifying allocation load status into the candidate service object screening process. This mechanism determines the current allocation number of candidate execution nodes in real time, identifies overloaded execution nodes that are no longer suitable for customer service tasks, and eliminates these nodes. Furthermore, to maintain consistency in matching quantity and priority, the target execution nodes are updated and replaced by dynamically supplementing candidate scores from the score sequence and tracing back to the corresponding relationship chain, thereby constructing a more business-balanced service object selection solution.

[0131] Steps S501 to S503, as illustrated in the present embodiment, establish a clear path mapping logic from assessment scores to target node determination by introducing matching score sorting, target quantity screening, and score link backtracking mechanisms. This not only ensures the quality priority of the matching results between customer objects and service objects, but also enables the platform to flexibly control the quantity and distribution of service resources. While ensuring the objectivity and accuracy of the assessment results, the method of this embodiment achieves precise control over the service object screening results. It is applicable to business scenarios such as insurance marketing, customer distribution, and resource optimization, and has strong implementation feasibility and business guidance value.

[0132] See also Figure 7 The embodiment of the present application further provides a service distribution device that can implement the above service distribution method, and the device includes:

[0133] Acquisition module 701, used to acquire object interaction data between business objects;

[0134] A node construction module 702 is used to construct a node for a business object to obtain an object node; wherein the object node has an object type, and the object type is used to indicate whether the business object is a customer object or a service object;

[0135] A graph construction module 703 is used to construct a graph of object nodes according to the object interaction data to obtain an object relationship graph;

[0136] The relationship chain extraction module 704 is used to determine the original node from the object node based on the object type, and extract the candidate relationship chain containing the original node from the object relationship graph; wherein the original node represents the customer object;

[0137] Matching degree evaluation module 705 is used to identify the relationship type of each connection edge of the candidate relationship chain, obtain the relationship type between the object nodes, and evaluate the matching degree of the candidate relationship chain based on the relationship type and object type to obtain a matching score;

[0138] The allocation module 706 is configured to select a target execution node from the candidate relationship chain according to the matching score, and match the target execution node with an original node; wherein the target execution node represents a service object.

[0139] The specific implementation of the service distribution device is substantially the same as the specific embodiment of the above service distribution method, and will not be described in detail here.

[0140] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the aforementioned service allocation method when executing the computer program. The electronic device may be any smart terminal, such as a tablet computer or an in-vehicle computer.

[0141] See also Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0142] The processor 801 can be implemented as a general-purpose CPU (Central Processing Unit), 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.

[0143] The memory 802 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 802 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called by the processor 801 to execute the service allocation method of the embodiments of this application.

[0144] Input / output interface 803, used to implement information input and output;

[0145] Communication interface 804, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0146] Bus 805 , which transmits information between various components of the device (e.g., processor 801 , memory 802 , input / output interface 803 , and communication interface 804 );

[0147] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0148] An 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 above-mentioned service allocation method is implemented.

[0149] 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 arranged 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.

[0150] The business allocation method, business allocation device, electronic device, and storage medium provided in the embodiments of the present application fully restore the historical connections and potential social paths between business objects by acquiring object interaction data and constructing object nodes and object relationship graphs, thereby identifying candidate relationship chains starting from the customer object in the graph structure, and performing relationship type identification and matching degree evaluation. Finally, based on the matching score, the service object that best suits the customer object is selected as the target execution node. Compared with traditional business allocation solutions, the embodiments of the present application can accurately depict the potential associations and matching relationships between customers and salespeople through graph structured modeling and relationship chain evaluation, and mine salespeople with real association backgrounds or service advantages from historical data, so that they are paired with target customers first, ultimately improving the matching degree between customers and salespeople.

[0151] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this 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 this application are also applicable to similar technical problems.

[0152] Those skilled in the art will understand 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.

[0153] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0154] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0155] 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 sequential order. 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 variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes 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.

[0156] It should be understood that in this 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 previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items 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.

[0157] In the several embodiments provided in this 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 merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, 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.

[0158] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0160] 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, which is stored in a storage medium and includes multiple instructions for enabling 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: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0161] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A business allocation method, characterized in that: The method comprises: Get object interaction data between business objects; Performing node construction on the business object to obtain an object node; wherein the object node has an object type, and the object type is used to indicate that the business object is a customer object or a service object; Constructing a graph of the object nodes according to the object interaction data to obtain an object relationship graph; Determining an original node from the object nodes based on the object type, and extracting a candidate relationship chain including the original node from the object relationship graph; wherein the original node represents the customer object; Identifying the relationship type of each connecting edge of the candidate relationship chain to obtain the relationship type between the object nodes, and evaluating the matching degree of the candidate relationship chain based on the relationship type and the object type to obtain a matching score; A target execution node is screened out from the candidate relationship chain according to the matching score, and the original node is matched to the target execution node; wherein the target execution node represents the service object.

2. The method according to claim 1, characterized in that The step of evaluating the degree of matching of the candidate relationship chain according to the relationship type and the object type to obtain a matching score includes: Filtering an intermediate relationship chain from the candidate relationship chains according to the object type, wherein the starting node of the intermediate relationship chain is the original node, and the ending node of the intermediate relationship chain represents the service object; According to the relationship type of each intermediate connection edge in the intermediate relationship chain, performing a relationship value evaluation on the intermediate connection edge to obtain a relationship score; Score calculation is performed on all the relationship scores of the intermediate relationship chain to obtain the matching score.

3. The method according to claim 2, characterized in that Calculating all the relationship scores of the intermediate relationship chain to obtain the matching score includes: Obtaining target weight data for each of the relationship scores; Multiplying the relationship score and the target weight data to obtain an intermediate score; All the intermediate scores are summed up to obtain the matching score.

4. The method according to claim 3, characterized in that The obtaining of target weight data for each relationship score includes: Filtering the object interaction data according to the intermediate relationship chain to obtain intermediate interaction data; Performing behavior recognition on the intermediate interaction data to obtain a behavior stage type of each intermediate connection edge; The original weight data of each intermediate connection edge is determined according to the behavior stage type of the intermediate connection edge, and the original weight data is used as the target weight data of the relationship score.

5. The method according to claim 3, characterized in that The obtaining of target weight data for each relationship score includes: Sequentially numbering the intermediate connection edges of each intermediate relationship chain to obtain connection edge sequence identifiers; Querying a preset scoring mapping relationship table according to the connection edge sequence identifier to obtain the importance factor of the intermediate connection edge; The importance factor is used as the weight data.

6. The method according to claim 2, characterized in that The step of selecting a target execution node from the candidate relationship chain according to the matching score includes: Arranging the matching scores in descending order to obtain a score sequence; Selecting a preset number of target scores from the score sequence; A target relationship chain is determined from the intermediate relationship chains according to the target score, and a terminal node of the target relationship chain is used as the target execution node.

7. The method according to claim 6, characterized in that The step of determining a target relationship chain from the intermediate relationship chains according to the target score and using the terminal node of the target relationship chain as the target execution node includes: Determine a target relationship chain from the intermediate relationship chains according to the target score, and use the terminal node of the target relationship chain as a candidate execution node; Acquiring the number of allocated objects of the candidate execution node, and determining that the candidate execution node is an overloaded execution node based on the number of allocated objects; Eliminating overloaded execution nodes from the candidate execution nodes, and sequentially selecting a reference number of candidate scores from the score sequence, where the reference number is the number of the overloaded execution nodes; The candidate execution node is updated according to the candidate score, and the candidate execution node is used as the target execution node.

8. A service distribution device, characterized in that: The device comprises: The acquisition module is used to obtain object interaction data between business objects; A node construction module, configured to construct a node for the business object to obtain an object node; wherein the object node has an object type, and the object type is used to indicate whether the business object is a customer object or a service object; A graph construction module, configured to construct a graph of the object nodes according to the object interaction data to obtain an object relationship graph; a relationship chain extraction module, configured to determine an original node from the object node based on the object type, and extract a candidate relationship chain including the original node from the object relationship graph; wherein the original node represents the customer object; a matching degree evaluation module, configured to identify the relationship type of each connecting edge of the candidate relationship chain, obtain the relationship type between the object nodes, and evaluate the matching degree of the candidate relationship chain based on the relationship type and the object type to obtain a matching score; An allocation module is configured to screen out a target execution node from the candidate relationship chain according to the matching score, and match the original node to the target execution node; wherein the target execution node represents the service object.

9. An electronic device, characterized in that: The electronic device includes 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