Recommendation method and device of maintenance network points, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a recommendation method and device of a maintenance network, electronic equipment and a storage medium, and the electronic equipment and the storage medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: generating a website feature factor and an object feature factor based on vehicle accident data, obtaining an object preference score of each candidate maintenance website by using the object feature factor and the website feature factor, and obtaining target gap data corresponding to a target output value of the candidate maintenance website; and obtaining a website output value score of each candidate maintenance website by using the target gap data, and determining a recommended maintenance website according to the object preference score and the website output value score. According to the method, object feature factors and network feature factors are utilized to carry out recommendation at a client level, recommendation at a service level is carried out based on output value related data of actual services, a weighting mode is utilized to balance the client level and the service level, a recommended maintenance network meeting client requirements and actual service output value distribution is obtained, the accuracy of a recommendation result is improved, and the recommendation efficiency is improved. The maintenance efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method and device for recommending maintenance outlets, electronic equipment, and storage media. Background Art

[0002] In the auto insurance claims process, recommending a suitable repair shop to the damaged vehicle is a key step, the purpose of which is to ensure that the vehicle can receive timely and appropriate repair services. Currently, many recommendation systems recommend repair shops mainly based on geographic location and car brand, by identifying repair shops close to the accident site or providing professional services for a specific brand to provide convenient repair services.

[0003] However, the recommendation mechanism in the related technology only considers the customer's perspective and does not combine the specific business needs of the insurance company, so there are obvious limitations and inconveniences. Usually, after receiving the recommended repair shop, some repair shops still need manual judgment and adjustment based on the actual business situation. Such a recommendation method has a low accuracy rate, resulting in low overall maintenance efficiency. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method and device for recommending maintenance outlets, an electronic device and a storage medium, and an electronic device and a storage medium, aiming to improve the accuracy of the recommendation.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for recommending a maintenance outlet, the method comprising:

[0006] Acquire a target object, vehicle damage data and accident location from the vehicle accident data, determine a plurality of candidate repair outlets based on the accident location, and generate outlet characteristic factors corresponding to the candidate repair outlets;

[0007] Acquiring object preference data corresponding to the target object, and generating an object characteristic factor according to the object preference data and the vehicle damage data;

[0008] Inputting the object characteristic factor and the network point characteristic factor into a pre-trained object network point preference prediction model for data prediction to obtain an object preference score for each candidate maintenance network point;

[0009] Obtaining the target output value of the candidate maintenance outlets, generating target gap data of the candidate maintenance outlets based on the target output value and a preset time node, inputting the target gap data into a pre-trained target control model for data prediction, and obtaining an outlet output value score for each of the candidate maintenance outlets;

[0010] A weighted calculation is performed based on the object preference score and the outlet output value score to obtain an outlet recommendation score for the candidate maintenance outlets, and a recommended maintenance outlet is determined from the candidate maintenance outlets based on the outlet recommendation score.

[0011] In some embodiments, obtaining the target output value of the candidate maintenance outlets includes:

[0012] Obtain premium data, holiday data and forecast weather data for the target area within a preset time;

[0013] Inputting the premium data, the holiday data and the predicted weather data into a pre-trained output value calculation model to perform output value prediction, and obtaining the overall output value corresponding to the target area within the preset time;

[0014] Obtaining outlet premiums of cooperative maintenance outlets in the target area within the preset time, the candidate maintenance outlets belonging to the cooperative maintenance outlets;

[0015] The overall output value is allocated based on the outlet premium to obtain the target output value of each of the cooperative maintenance outlets.

[0016] In some embodiments, allocating the overall output value based on the outlet premium to obtain the target output value of each of the cooperative maintenance outlets includes:

[0017] Obtain the preset production-insurance ratio of the cooperative maintenance outlet;

[0018] Pre-allocating the overall output value to obtain the pre-allocated output value of the cooperative maintenance outlets, and calculating the distribution output-insurance ratio of the pre-allocated output value and the corresponding outlet premium;

[0019] The pre-allocated output value is adjusted until each of the allocated output-guarantee ratios is not greater than the preset output-guarantee ratio, and the pre-allocated output value is used as the target output value.

[0020] In some embodiments, generating the target gap data of the candidate maintenance outlets based on the target output value and the preset time node includes:

[0021] Obtain a preset time node according to the current time, and obtain the case closing output value and damage assessment output value of the candidate maintenance outlet before the preset time node;

[0022] The target output value is subtracted from the case closing output value and the loss assessment output value to obtain the target gap data.

[0023] In some embodiments, inputting the target gap data into a pre-trained target control model for data prediction to obtain the network point output value score of each candidate maintenance network point includes:

[0024] Acquire maintenance volume data and network type data of the candidate maintenance network;

[0025] The outlet business data is obtained according to the preset time node, the outlet type data, the maintenance volume data and the target gap data, the outlet business data is input into the target control model for data prediction to obtain the outlet estimated gap, and the outlet output value score is obtained according to the outlet estimated gap.

[0026] In some embodiments, the acquiring object preference data corresponding to the target object and generating an object characteristic factor according to the object preference data and the vehicle damage data includes:

[0027] Acquire the target object's outlet type preference, outlet service preference, maintenance time preference, outlet distance preference, and historical maintenance relationship data between the target object and each of the candidate maintenance outlets;

[0028] At least obtaining a target vehicle type and a vehicle damage location based on the vehicle damage data;

[0029] The object characteristic factor is obtained according to the network point type preference, the network point service preference, the maintenance time preference, the network point distance preference, the historical maintenance relationship data, the target vehicle type and the vehicle damage location.

[0030] In some embodiments, generating a network point characteristic factor corresponding to the candidate maintenance network point includes:

[0031] Obtaining network point distance data according to the accident location and the object address data of the target object, and acquiring network point type data, network point service data and maintenance timeliness data of the candidate maintenance network point;

[0032] The network point characteristic factor is obtained according to the network point distance data, the network point type data, the network point service data and the maintenance timeliness data.

[0033] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a maintenance point recommendation device, the device comprising:

[0034] Network point characteristic factor acquisition module: used to obtain the target object, vehicle damage data and accident location from the vehicle accident data, determine multiple candidate maintenance network points based on the accident location, and generate network point characteristic factors corresponding to the candidate maintenance network points;

[0035] An object characteristic factor acquisition module is used to acquire object preference data corresponding to the target object, and generate an object characteristic factor according to the object preference data and the vehicle damage data;

[0036] Object preference score prediction module: used for inputting the object characteristic factor and the network point characteristic factor into a pre-trained object network point preference prediction model for data prediction to obtain the object preference score of each candidate maintenance network point;

[0037] The outlet output value score prediction module is used to obtain the target output value of the candidate maintenance outlets, generate the target gap data of the candidate maintenance outlets based on the target output value and the preset time node, input the target gap data into the pre-trained target control model for data prediction, and obtain the outlet output value score of each candidate maintenance outlet;

[0038] Recommendation result generation module: used to perform weighted calculation according to the object preference score and the outlet output value score to obtain the outlet recommendation score of the candidate maintenance outlet, and determine the recommended maintenance outlet from the candidate maintenance outlets based on the outlet recommendation score.

[0039] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0040] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0041] The method and device for recommending maintenance outlets, electronic equipment and storage medium, electronic equipment and storage medium proposed in the present application obtain target objects, vehicle damage data and accident locations from vehicle accident data, determine multiple candidate maintenance outlets based on the accident locations, generate outlet feature factors corresponding to the candidate maintenance outlets, obtain object preference data corresponding to the target object, generate object feature factors according to the object preference data and vehicle damage data, input the object feature factors and outlet feature factors into a pre-trained object outlet preference prediction model for data prediction, obtain the object preference score of each candidate maintenance outlet, obtain the target output value of the candidate maintenance outlet, generate target gap data of the candidate maintenance outlet based on the target output value and preset time nodes, input the target gap data into a pre-trained target control model for data prediction, obtain the outlet output value score of each candidate maintenance outlet, finally perform weighted calculation according to the object preference score and the outlet output value score to obtain the outlet recommendation score of the candidate maintenance outlet, and determine the recommended maintenance outlet from the candidate maintenance outlets based on the outlet recommendation score. In the embodiment of the present application, a preliminary screening is first performed to obtain candidate maintenance outlets, and then an object characteristic factor related to the target object and an outlet characteristic factor related to the candidate maintenance outlets are generated. The object characteristic factor and the outlet characteristic factor are used to make customer-level recommendations to obtain the object preference score of each candidate maintenance outlet. At the same time, based on the output value-related data of the actual business, each candidate maintenance outlet is recommended at the business level to obtain the corresponding outlet output value score. Then, based on a weighted method, the customer level and the business level are balanced to generate a recommended maintenance outlet that can meet both customer needs and the actual business output value distribution, thereby improving the accuracy of the recommendation results and the efficiency of the maintenance process. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is an optional flow chart of the method for recommending maintenance outlets provided in an embodiment of the present application.

[0043] Figure 2 It is a flowchart of generating network point characteristic factors corresponding to candidate maintenance network points provided in an embodiment of the present application.

[0044] Figure 3 It is a partial schematic diagram of the principle of the method for recommending maintenance outlets provided in an embodiment of the present application.

[0045] Figure 4 It is a flowchart of obtaining object preference data corresponding to a target object and generating an object characteristic factor according to the object preference data and vehicle damage data provided by an embodiment of the present application.

[0046] Figure 5 It is a structural diagram of the object network point preference prediction model provided in the embodiment of the present application.

[0047] Figure 6This is a flow chart for obtaining the target output value of candidate maintenance outlets provided in an embodiment of the present application.

[0048] Figure 7 It is a flowchart provided in an embodiment of the present application for allocating the overall output value based on the outlet premiums to obtain the target output value of each cooperative maintenance outlet.

[0049] Figure 8 It is a flowchart of generating target gap data of candidate maintenance outlets based on target output value and preset time nodes provided in an embodiment of the present application.

[0050] Fig. 9 It is a partial schematic diagram of the principle of the method for recommending maintenance outlets provided in an embodiment of the present application.

[0051] Fig.10 The embodiment of the present application provides a flowchart for inputting target gap data into a pre-trained target control model for data prediction to obtain the network output value score of each candidate maintenance network.

[0052] Fig.11 It is a schematic diagram of calculating the network point recommendation score provided in an embodiment of the present application.

[0053] Fig.12 It is an overall flow chart of the method for recommending maintenance outlets provided in an embodiment of the present application.

[0054] Fig.13 It is a structural diagram of a recommended device for a maintenance outlet provided in an embodiment of the present application.

[0055] Fig.14 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0059] First, some nouns involved in this application are analyzed:

[0060] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0061] In the auto insurance claims process, recommending a suitable repair shop to the damaged vehicle is a key step, the purpose of which is to ensure that the vehicle can receive timely and appropriate repair services. Currently, many recommendation systems recommend repair shops mainly based on geographic location and car brand, by identifying repair shops close to the accident site or providing professional services for a specific brand to provide convenient repair services.

[0062] However, the recommendation mechanism in the related technology only considers the customer's perspective and does not combine the specific business needs of the insurance company, so there are obvious limitations and inconveniences. Usually, after receiving the recommended repair shop, some repair shops still need manual judgment and adjustment based on the actual business situation. Such a recommendation method has a low accuracy rate, resulting in low overall maintenance efficiency.

[0063] Based on this, the embodiments of the present application provide a method and device for recommending maintenance outlets, an electronic device and a storage medium, an electronic device and a storage medium. First, a preliminary screening is performed to obtain candidate maintenance outlets. Next, object characteristic factors related to the target object and outlet characteristic factors related to the candidate maintenance outlets are generated. The object characteristic factors and outlet characteristic factors are used to make customer-level recommendations to obtain an object preference score for each candidate maintenance outlet. At the same time, based on the actual business output value-related data, each candidate maintenance outlet is recommended at the business level to obtain a corresponding outlet output value score. Then, based on a weighted approach, the customer level and the business level are balanced to generate recommended maintenance outlets that can meet both customer needs and the actual business output value distribution, thereby improving the accuracy of the recommendation results and the efficiency of the maintenance process.

[0064] The recommendation 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 recommendation method in the embodiments of the present application is described.

[0065] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0066] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0067] The method for recommending maintenance outlets provided in the embodiment of the present application relates to the field of artificial intelligence technology. The method for recommending maintenance outlets provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can 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 method for recommending maintenance outlets, etc., but is not limited to the above forms.

[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0069] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user 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 these 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.

[0070] The following describes a method for recommending maintenance outlets in an embodiment of the present application.

[0071] Figure 1 is an optional flow chart of the method for recommending maintenance outlets provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps 110 to 150. It can also be understood that this embodiment Figure 1 The order of step 110 to step 150 is not specifically limited, and the order of steps can be adjusted or some steps can be reduced or added according to actual needs.

[0072] Step 110: Obtain the target object, vehicle damage data and accident location from the vehicle accident data, determine multiple candidate repair outlets based on the accident location, and generate outlet feature factors corresponding to the candidate repair outlets.

[0073] In one embodiment, if a vehicle is damaged, the target object can report the vehicle insurance through telephone, software platform, etc., and after the relevant person in charge of the insurance company conducts an on-site or online survey, the vehicle accident data can be generated. The vehicle accident data includes at least the target object's personal information, vehicle damage data, and the accident location after the accident. The vehicle damage data may include vehicle type, damaged location, damage degree, vehicle age, vehicle registration information, etc. Therefore, in this embodiment, the target object, vehicle damage data, and accident location can be obtained from the vehicle accident data.

[0074] In the operating model of the insurance industry, insurance companies usually establish cooperative relationships with multiple maintenance service outlets, that is, insurance companies have at least multiple cooperative maintenance outlets. At this time, based on the location of the accident, they first conduct an initial distance screening and select multiple cooperative maintenance outlets with closer distances as candidate maintenance outlets to quickly respond to maintenance requests.

[0075] In one embodiment, after obtaining the candidate maintenance outlets, the outlet feature factors corresponding to the candidate maintenance outlets are generated for use in the subsequent recommendation process. Figure 2 , Figure 2 This is a flowchart of generating a network point characteristic factor corresponding to a candidate maintenance network point provided in an embodiment of the present application, which specifically includes the following steps:

[0076] Step 210: Obtain network point distance data based on the accident location and the object address data of the target object, and obtain network point type data, network point service data and maintenance timeliness data of the candidate maintenance network point.

[0077] In one embodiment, referring to Figure 3 , Figure 3 This is a partial schematic diagram of the maintenance network recommendation method provided in the embodiment of the present application. After the target object is determined, the target object's home address or workplace address data can be determined based on the pre-registered object information, so that the network distance data of each candidate maintenance network can be calculated in combination with the accident location. Among them, the network distance data includes: the distance to the accident location, the distance to the target object's address, the distance to the target object's workplace, etc.

[0078] Furthermore, the outlet type data, outlet service data and maintenance timeliness data of the candidate maintenance outlets are obtained. Among them, the outlet type data is used to indicate the maintenance service type of the candidate maintenance outlet, including at least 4S stores, comprehensive repair shops (repairs of all brands), specialized repair shops of a certain brand, return repair shops, etc. The outlet service data can be the number of maintenance personnel at the outlet and the outlet premium, etc. The maintenance timeliness data can be the average maintenance time of the outlet for different types of damage and the real-time maintenance idle status of the outlet, etc. It can be understood that the outlet type data, outlet service data and maintenance timeliness data are all set according to actual conditions.

[0079] Step 220: Obtaining a network point characteristic factor according to the network point distance data, network point type data, network point service data and maintenance timeliness data.

[0080] In one embodiment, after obtaining the network point distance data, network point type data, network point service data and maintenance time data, these data are quantified and expressed in numerical form to obtain the network point characteristic factor in vector form to facilitate the subsequent calculation process.

[0081] Step 120: Obtain object preference data corresponding to the target object, and generate an object characteristic factor according to the object preference data and the vehicle damage data.

[0082] In one embodiment, considering that the target object may have certain preferences for the selection of maintenance outlets, in order to improve customer service satisfaction, it is necessary to combine the object preference data of the target object itself when recommending maintenance outlets.

[0083] In one embodiment, referring to Figure 4 , Figure 4 The flowchart of obtaining object preference data corresponding to a target object and generating an object characteristic factor according to the object preference data and vehicle damage data provided by an embodiment of the present application specifically includes the following steps:

[0084] Step 410: Obtain the target object's outlet type preference, outlet service preference, maintenance time preference, outlet distance preference, and historical maintenance relationship data between the target object and each candidate maintenance outlet.

[0085] In one embodiment, in combination Figure 3First, the target object's preference for the type of maintenance outlets, outlet service preference, maintenance time preference, and outlet distance preference are obtained, wherein the outlet type preference indicates which type of maintenance outlets the target object tends to choose, the outlet service preference indicates the number of service personnel of the maintenance outlets the target object tends to choose, etc., the maintenance time preference indicates the target object's tolerance for the maintenance time, and the outlet distance preference indicates the target object's tolerance for the maintenance distance. It is understandable that these data can be judged based on questionnaire forms such as satisfaction surveys of the target object or its historical selection results, and this embodiment does not limit the acquisition method.

[0086] Next, historical maintenance relationship data of the target object is obtained based on historical data. The historical maintenance relationship data here includes family maintenance outlets and historical maintenance outlets. Among them, family maintenance outlets can be some maintenance outlets marked by the target object in advance that can obtain lower maintenance prices, and historical maintenance outlets are maintenance outlets selected by the target object during previous accidents.

[0087] It is understandable that if the above data cannot be obtained, it will be set as a default value.

[0088] Step 420: Obtain at least the target vehicle type and the vehicle damage location based on the vehicle damage data.

[0089] In one embodiment, at least the target vehicle type and the vehicle damage location are obtained from the vehicle damage data. Since some maintenance outlets may only be able to handle the corresponding target vehicle type or vehicle damage location, this data is highly important in the maintenance outlet recommendation process.

[0090] Step 430: Obtain object characteristic factors according to the outlet type preference, outlet service preference, maintenance time preference, outlet distance preference, historical maintenance relationship data, target vehicle type and vehicle damage location.

[0091] In one embodiment, after obtaining the outlet type preference, outlet service preference, maintenance time preference, outlet distance preference, historical maintenance relationship data, target vehicle type and vehicle damage location, these data are quantified and expressed in numerical form to obtain object characteristic factors that can characterize personalized preferences.

[0092] Step 130: Input the object characteristic factor and the network point characteristic factor into a pre-trained object network point preference prediction model for data prediction to obtain the object preference score of each candidate maintenance network point.

[0093] In one embodiment, referring to Figure 3 After obtaining the object characteristic factor and the network point characteristic factor, they are spliced ​​and input into the pre-trained object network point preference prediction model for data prediction, thereby obtaining the object preference score of each candidate maintenance network point. Figure 3 In the example, the object preference score of candidate maintenance network A is 0.5, the object preference score of candidate maintenance network B is 0.6, ..., the object preference score of candidate maintenance network N is 0.35, and so on.

[0094] In one embodiment, the object network point preference prediction model may be a Wide & Deep model. Figure 5 , Figure 5 : is a structural diagram of the object outlet preference prediction model provided by the embodiment of the present application. The object outlet preference prediction model specifically includes an input layer, a wide linear model layer (Wide), a deep model layer (Deep), a fusion layer and an output layer. Among them, the input layer receives two sets of feature factors as input data, namely object feature factors and outlet feature factors. The wide linear model layer is a linear model that quickly captures the global feature vector in the input data through linear combination and cross features. The deep model layer is composed of multiple hidden layers, such as a fully connected layer, and uses a nonlinear activation function (such as ReLU) to automatically learn high-level abstract features from the input data to obtain a high-level feature vector. Next, the fusion layer: the global feature vector and the high-level feature vector are spliced ​​together to form a unified fusion feature vector. Finally, the output layer, such as a fully connected layer, maps the fused feature vector and normalizes it using a softmax activation function to obtain the object preference score of each candidate maintenance outlet. The object preference score can reflect the degree of preference of the target object for each candidate maintenance outlet. The higher the score, the stronger the preference of the target object for the candidate maintenance outlet.

[0095] Step 140: Obtain the target output value of the candidate maintenance outlets, generate target gap data for the candidate maintenance outlets based on the target output value and the preset time node, input the target gap data into the pre-trained target control model for data prediction, and obtain the outlet output value score of each candidate maintenance outlet.

[0096] In one embodiment, the insurance company needs to reasonably allocate the output value of the cooperative maintenance outlets during the operation process. In the process of recommending maintenance outlets, the output value structure of each maintenance outlet is balanced as much as possible to avoid the situation where some maintenance outlets have insufficient output value while others have insufficient output value, thereby avoiding waste of resources and uneven benefits. Therefore, the embodiment of the present application not only takes into account the customer orientation by using the object preference points, but also takes into account the business operation orientation of the insurance company by using the outlet output value points.

[0097] In one embodiment, the insurance company will pre-allocate a target output value for the cooperative repair outlets, where the output value can be understood as the amount of compensation that the cooperative repair outlets can pay. Figure 6 , Figure 6 This is a flow chart of obtaining the target output value of candidate maintenance outlets provided in an embodiment of the present application, which specifically includes the following steps:

[0098] Step 610: Obtain premium data, holiday data, and forecast weather data for the target area within a preset time.

[0099] In one embodiment, the target output value can usually be allocated according to time periods such as years, quarters or months, so the preset time is the selected time period, such as a certain month. The target area refers to the selected insurance coverage area, which can be selected according to actual conditions. After having the target area and the preset time, the total premium data of the target area within the preset time, as well as the holiday data within the preset time and the predicted weather data within the preset time can be obtained. Among them, the predicted weather data can be obtained based on the historical weather data for the same period in the target area, or it can be predicted possible weather data. The embodiment of the present application takes into account that weather and holidays will affect the frequency of auto insurance claims, so the influence of these two factors is considered in the process of allocating the target output value.

[0100] Step 620: Input the premium data, holiday data and weather data into the pre-trained output value estimation model to perform output value prediction, and obtain the corresponding overall output value of the target area within a preset time.

[0101] In one embodiment, the obtained premium data, holiday data and weather data are input into a pre-trained output value calculation model to perform output value prediction, and the overall output value corresponding to the target area within a preset time is obtained. This overall output value can represent the possible claim amount of the target area within the preset time. The output value calculation model is a neural network model or other machine learning model, which is not limited in this embodiment.

[0102] Step 630: Obtain the outlet premiums of the cooperative maintenance outlets in the target area within a preset time.

[0103] In one embodiment, the outlet premium corresponding to each cooperative maintenance outlet in the target area within a preset time is obtained. The outlet premium refers to the car insurance premium paid by the customer received by the maintenance outlet.

[0104] Step 640: Allocate the overall output value based on the outlet premiums to obtain the target output value of each cooperative maintenance outlet.

[0105] In one embodiment, after the overall output value is obtained, the insurance company needs to distribute the output value according to the outlet premium of each cooperative maintenance outlet, which can be understood as a cake-dividing process. It is necessary to determine the amount of claims that each cooperative maintenance outlet can pay. Figure 7 , Figure 7 The flow chart of allocating the overall output value based on the outlet premium provided in the embodiment of the present application to obtain the target output value of each cooperative maintenance outlet specifically includes the following steps:

[0106] Step 710: Obtain the preset production-insurance ratio of the cooperative maintenance outlet.

[0107] In one embodiment, the production insurance ratio refers to the ratio between the output value and the premium. If the production insurance ratio is 1, it means that the premium is equal to the amount of claims paid. If the production insurance ratio is high, it means that the amount of claims paid is more than the premium received, and the insurance company has poor profits. If the production insurance ratio is low, it means that the amount of claims paid is less than the premium received, and the insurance company has good profits. Therefore, the embodiment of the present application sets a preset production insurance ratio for each cooperative maintenance outlet to evaluate the profits that the cooperative maintenance outlet can bring.

[0108] It is understandable that a same preset production and insurance ratio can be set for each cooperative maintenance outlet, for example, the preset production and insurance ratio is 1. Different preset production and insurance ratios can also be set for different cooperative maintenance outlets according to the actual operating conditions and operating strategies of the cooperative maintenance outlets, which is not limited in this embodiment.

[0109] Step 720: pre-allocate the overall output value, obtain the pre-allocated output value of the cooperative maintenance outlets, and calculate the distribution output-insurance ratio of the pre-allocated output value and the corresponding outlet premium.

[0110] In one embodiment, the overall output value is pre-allocated, and a corresponding pre-allocated output value is allocated to each cooperative maintenance outlet. At this time, the allocated output-insurance ratio of the cooperative maintenance outlet is calculated based on the pre-allocated output value and the corresponding outlet premium.

[0111] Step 730: Adjust the pre-allocated output value until each allocated output-guarantee ratio is not greater than the preset output-guarantee ratio, and use the pre-allocated output value as the target output value.

[0112] In one embodiment, the pre-allocated output value is dynamically adjusted until the allocated output-insurance ratio of each cooperative maintenance outlet is no greater than the preset output-insurance ratio. At this time, the allocation can be considered reasonable. At this time, the final pre-allocated output value of each cooperative maintenance outlet is used as the target output value of the maintenance outlet.

[0113] In one embodiment, after obtaining the target output value of each cooperative maintenance outlet, since the candidate maintenance outlet is part of the cooperative maintenance outlets, the target output value of each candidate maintenance outlet can also be obtained. Next, the target gap data of the candidate maintenance outlets is generated based on the target output value and the preset time nodes. The preset time nodes here can be time nodes divided by the beginning of the month, the middle of the month, the end of the month, etc., or they can be divided by days, weeks, etc. Since the actual maintenance conditions of maintenance outlets are different in different time periods, the embodiment of the present application needs to determine the target gap data of candidate maintenance outlets at different preset time nodes. Refer to Figure 8 , Figure 8The flowchart of generating target gap data of candidate maintenance outlets based on target output value and preset time nodes provided by the embodiment of the present application specifically includes the following steps:

[0114] Step 810: Obtain a preset time node according to the current time, and obtain the case closing output value and damage assessment output value of the candidate maintenance outlets before the preset time node.

[0115] Step 820: Subtract the closed output value and the assessed loss value from the target output value to obtain the target gap data.

[0116] In one embodiment, referring to Fig. 9 , Fig. 9 It is a partial principle schematic diagram of the method for recommending maintenance outlets provided in an embodiment of the present application. First, select a preset time node closest to the current time, and the preset time node needs to be before the current time. For example, the preset time nodes are divided according to the week, and the preset time nodes are: 7th, 14th, 21st and 28th. At this time, the current time is 15th, and the preset time node is 14th. Next, the case closing output value and the damage assessment output value of the candidate maintenance outlets before the preset time node are obtained, wherein the case closing output value refers to the claim amount that has been processed and paid, and the damage assessment output value refers to the claim amount that has been determined to be paid, but has not yet been paid. Therefore, after obtaining the case closing output value and the damage assessment output value, the target output value is subtracted from the case closing output value and the damage assessment output value to obtain the target gap data of the candidate maintenance outlet. For example, the target output value of a candidate maintenance outlet is 1 million, the preset time node is 14th, the case closing output value is 360,000, and the damage assessment output value is 210,000. At this time, the target gap data is 430,000.

[0117] In one embodiment, one of the purposes of the business operation-oriented recommendation process is to balance the output value of each cooperative maintenance outlet to avoid excess output value of some cooperative maintenance outlets or insufficient output value of some cooperative maintenance outlets. Therefore, the candidate maintenance outlets with larger target gap data need to have their priority increased in the recommendation results.

[0118] In one embodiment, after obtaining the target gap data, the output value priority prediction process can be performed based on the target gap data. Fig.10 , Fig.10 The present invention provides an embodiment of the present invention, which provides a flow chart for inputting target gap data into a pre-trained target control model for data prediction to obtain the network output value of each candidate maintenance network point, and specifically includes the following steps:

[0119] Step 1010: Obtain maintenance volume data and network type data of candidate maintenance network points.

[0120] In one embodiment, in order to balance the output value of each cooperative maintenance outlet, it is also necessary to consider the maintenance volume data and outlet type data. Among them, the maintenance volume data indicates the number of repairs that the cooperative maintenance outlet can currently undertake. A small volume means that it has many orders, so it is necessary to lower its priority to avoid order accumulation. The consideration of the outlet type data is that, for example, the vehicle that needs to be repaired is a specific brand, and a candidate maintenance outlet is a specialized repair outlet for the brand, and another candidate maintenance outlet is a comprehensive brand maintenance outlet. Since the comprehensive repair outlet can easily obtain orders from other brands to make up for the output value gap, and the number of orders for the specialized repair outlet is relatively small, if it is at the end of the month, it is more inclined to assign the repair order to the specialized repair outlet, increase its priority, and avoid the situation where the specialized repair outlet lacks orders later and causes excess output value.

[0121] Step 1020: Obtain the outlet business data according to the preset time node, outlet type data, maintenance volume data and target gap data, input the outlet business data into the target control model for data prediction, obtain the outlet estimated gap, and obtain the outlet output value score according to the outlet estimated gap.

[0122] In one embodiment, referring to Fig. 9 , quantify the preset time nodes, outlet type data, maintenance volume data and target gap data, express them in numerical form, and splice them to obtain the outlet business data, which can reflect the actual output value of the candidate maintenance outlet. Then input the outlet business data into the target control model for data prediction, so as to obtain the estimated outlet gap for each candidate maintenance outlet. The larger the estimated outlet gap, the higher the order priority of the candidate maintenance outlet. Then normalize all the outlet estimated gaps to obtain the corresponding outlet output value score. That is to say, the larger the outlet output value score, the greater the probability that the candidate maintenance outlet needs to be recommended in terms of business operation orientation. For example Fig. 9 In the example, the network output value of candidate maintenance network A is 0.8, the network output value of candidate maintenance network B is 0.9, ..., the network output value of candidate maintenance network N is 0.5, etc. It can be understood that the target control model is a neural network model or other machine learning model, which is not limited in this embodiment.

[0123] Step 150: Perform a weighted calculation based on the object preference score and the outlet output value score to obtain an outlet recommendation score for the candidate maintenance outlets, and determine a recommended maintenance outlet from the candidate maintenance outlets based on the outlet recommendation score.

[0124] In one embodiment, referring to Fig.11 , Fig.11: is a schematic diagram of calculating the recommended points of the network provided by the embodiment of the present application. Among them, the object preference score is obtained by customer orientation, and the network output value score is obtained by business operation orientation. Therefore, in order to take into account both customer orientation and business operation orientation, a weighted calculation is performed based on the object preference score and the network output value score using a predefined weight to obtain the network recommendation score of each candidate maintenance network. Finally, the candidate maintenance network corresponding to the maximum value is selected from the network recommendation score as the recommended maintenance network.

[0125] In one embodiment, referring to Fig.12 , Fig.12 It is an overall flow chart of the method for recommending maintenance outlets provided in an embodiment of the present application.

[0126] First, the cooperative maintenance outlets report their outlet premiums corresponding to the preset time to the insurance business platform, and then the insurance business platform inputs the obtained premium data, holiday data and weather data into the pre-trained output value calculation model for output value prediction, and obtains the overall output value corresponding to the target area within the preset time. Then, the overall output value is allocated based on the outlet premiums to obtain the target output value of each cooperative maintenance outlet, and the target output value is sent to each cooperative repair outlet.

[0127] Next, after the vehicle is damaged, the target object reports the vehicle insurance through telephone, software platform, etc., and finally reports the vehicle accident data to the insurance business platform. The insurance business platform generates the outlet characteristic factors corresponding to the candidate repair outlets based on the vehicle accident data, and generates the object characteristic factors based on the object preference data and the vehicle damage data. At the same time, some cooperative repair outlets report the case closing output value and damage assessment output value to the target gap data as candidate repair outlets, and then obtain the outlet business data based on the preset time node, outlet type data, maintenance volume data and target gap data. The outlet business data is input into the target control model for data prediction to obtain the outlet estimated gap, and the outlet output value score is obtained based on the outlet estimated gap. Weighted calculation is performed based on the object preference score and the outlet output value score to obtain the outlet recommendation score of the candidate repair outlet, and the recommended repair outlet is determined from the candidate repair outlets based on the outlet recommendation score. Finally, the recommended repair outlet is sent to the target object and the corresponding cooperative repair outlet respectively for vehicle repair and claims settlement. In this way, the overall resource allocation structure of the insurance company becomes more reasonable, the amount of output value overflow decreases, the proportion of unrepaired resources decreases, and resource utilization is improved.

[0128] The technical solution provided by the embodiment of the present application obtains the target object, vehicle damage data and accident location from the vehicle accident data, determines multiple candidate maintenance outlets based on the accident location, generates outlet characteristic factors corresponding to the candidate maintenance outlets, obtains the object preference data corresponding to the target object, generates the object characteristic factor according to the object preference data and the vehicle damage data, inputs the object characteristic factor and the outlet characteristic factor into a pre-trained object outlet preference prediction model for data prediction, obtains the object preference score of each candidate maintenance outlet, obtains the target output value of the candidate maintenance outlet, generates the target gap data of the candidate maintenance outlet based on the target output value and the preset time node, inputs the target gap data into the pre-trained target control model for data prediction, obtains the outlet output value score of each candidate maintenance outlet, finally performs weighted calculation according to the object preference score and the outlet output value score, obtains the outlet recommendation score of the candidate maintenance outlet, and determines the recommended maintenance outlet from the candidate maintenance outlets based on the outlet recommendation score. In the embodiment of the present application, a preliminary screening is first performed to obtain candidate maintenance outlets, and then an object characteristic factor related to the target object and an outlet characteristic factor related to the candidate maintenance outlets are generated. The object characteristic factor and the outlet characteristic factor are used to make customer-level recommendations to obtain the object preference score of each candidate maintenance outlet. At the same time, based on the output value-related data of the actual business, each candidate maintenance outlet is recommended at the business level to obtain the corresponding outlet output value score. Then, based on a weighted method, the customer level and the business level are balanced to generate a recommended maintenance outlet that can meet both customer needs and the actual business output value distribution, thereby improving the accuracy of the recommendation results and the efficiency of the maintenance process.

[0129] The present application also provides a maintenance network point recommendation device, which can implement the above maintenance network point recommendation method. Fig.13 , the device comprises:

[0130] The network point characteristic factor acquisition module 1310 is used to obtain the target object, vehicle damage data and accident location from the vehicle accident data, determine multiple candidate maintenance network points based on the accident location, and generate network point characteristic factors corresponding to the candidate maintenance network points.

[0131] The object characteristic factor acquisition module 1320 is used to acquire the object preference data corresponding to the target object, and generate the object characteristic factor according to the object preference data and the vehicle damage data.

[0132] The object preference score prediction module 1330 is used to input the object characteristic factor and the network point characteristic factor into the pre-trained object network point preference prediction model for data prediction to obtain the object preference score of each candidate maintenance network point.

[0133] The outlet output value score prediction module 1340 is used to obtain the target output value of the candidate maintenance outlets, generate the target gap data of the candidate maintenance outlets based on the target output value and the preset time node, input the target gap data into the pre-trained target control model for data prediction, and obtain the outlet output value score of each candidate maintenance outlet.

[0134] The recommendation result generation module 1350 is used to perform weighted calculation based on the object preference score and the outlet output value score to obtain the outlet recommendation score of the candidate maintenance outlets, and determine the recommended maintenance outlets from the candidate maintenance outlets based on the outlet recommendation score.

[0135] The specific implementation of the maintenance outlet recommendation device of this embodiment is basically the same as the specific implementation of the maintenance outlet recommendation method described above, and will not be repeated here.

[0136] The present application also provides an electronic device, including:

[0137] at least one memory;

[0138] at least one processor;

[0139] at least one program;

[0140] The program is stored in the memory, and the processor executes the at least one program to implement the above-mentioned maintenance outlet recommendation method of the present application. The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a car computer, etc.

[0141] See also Fig.14 , Fig.14 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0142] The processor 1401 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0143] The memory 1402 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 1402 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1402, and the processor 1401 calls and executes the recommended method for the maintenance outlet of the embodiment of this application;

[0144] Input / output interface 1403, used to implement information input and output;

[0145] Communication interface 1404, used to realize communication interaction between the device and other devices, which can be realized by wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); and

[0146] A bus 1405 that transmits information between the various components of the device (e.g., the processor 1401, the memory 1402, the input / output interface 1403, and the communication interface 1404);

[0147] The processor 1401 , the memory 1402 , the input / output interface 1403 and the communication interface 1404 are connected to each other in communication within the device via a bus 1405 .

[0148] An embodiment of the present application also provides a storage medium, which is a storage medium that stores a computer program. When the computer program is executed by a processor, the above-mentioned method for recommending maintenance outlets is implemented.

[0149] As a non-transitory storage medium, the memory can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory 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 maintenance outlet recommendation method, device, equipment and storage medium proposed in the embodiments of the present application obtain a target object, vehicle damage data and accident location from vehicle accident data, determine multiple candidate maintenance outlets based on the accident location, generate outlet characteristic factors corresponding to the candidate maintenance outlets, obtain object preference data corresponding to the target object, generate object characteristic factors according to the object preference data and vehicle damage data, input the object characteristic factors and the outlet characteristic factors into a pre-trained object outlet preference prediction model for data prediction, obtain the object preference score of each candidate maintenance outlet, obtain the target output value of the candidate maintenance outlet, generate target gap data of the candidate maintenance outlet based on the target output value and preset time nodes, input the target gap data into a pre-trained target control model for data prediction, obtain the outlet output value score of each candidate maintenance outlet, finally perform weighted calculation according to the object preference score and the outlet output value score to obtain the outlet recommendation score of the candidate maintenance outlet, and determine the recommended maintenance outlet from the candidate maintenance outlets based on the outlet recommendation score. In the embodiment of the present application, a preliminary screening is first performed to obtain candidate maintenance outlets, and then an object characteristic factor related to the target object and an outlet characteristic factor related to the candidate maintenance outlets are generated. The object characteristic factor and the outlet characteristic factor are used to make customer-level recommendations to obtain the object preference score of each candidate maintenance outlet. At the same time, based on the output value-related data of the actual business, each candidate maintenance outlet is recommended at the business level to obtain the corresponding outlet output value score. Then, based on a weighted method, the customer level and the business level are balanced to generate a recommended maintenance outlet that can meet both customer needs and the actual business output value distribution, thereby improving the accuracy of the recommendation results and the efficiency of the maintenance process.

[0151] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0152] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0153] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

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

[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 sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0156] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0157] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

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

[0159] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[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 is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store programs.

[0161] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for recommending maintenance outlets, characterized in that: The method comprises: Acquire a target object, vehicle damage data and accident location from the vehicle accident data, determine a plurality of candidate repair outlets based on the accident location, and generate outlet characteristic factors corresponding to the candidate repair outlets; Acquiring object preference data corresponding to the target object, and generating an object characteristic factor according to the object preference data and the vehicle damage data; Inputting the object characteristic factor and the network point characteristic factor into a pre-trained object network point preference prediction model for data prediction to obtain an object preference score for each candidate maintenance network point; Obtaining the target output value of the candidate maintenance outlets, generating target gap data of the candidate maintenance outlets based on the target output value and a preset time node, inputting the target gap data into a pre-trained target control model for data prediction, and obtaining an outlet output value score for each of the candidate maintenance outlets; A weighted calculation is performed based on the object preference score and the outlet output value score to obtain an outlet recommendation score for the candidate maintenance outlets, and a recommended maintenance outlet is determined from the candidate maintenance outlets based on the outlet recommendation score.

2. The method for recommending maintenance outlets according to claim 1, characterized in that: The step of obtaining the target output value of the candidate maintenance outlets includes: Obtain premium data, holiday data and forecast weather data for the target area within a preset time; Inputting the premium data, the holiday data and the predicted weather data into a pre-trained output value calculation model to perform output value prediction, and obtaining the overall output value corresponding to the target area within the preset time; Obtaining outlet premiums of cooperative maintenance outlets in the target area within the preset time, the candidate maintenance outlets belonging to the cooperative maintenance outlets; The overall output value is allocated based on the outlet premium to obtain the target output value of each of the cooperative maintenance outlets.

3. The method for recommending maintenance outlets according to claim 2, characterized in that: The allocating the overall output value based on the outlet premium to obtain the target output value of each cooperative maintenance outlet includes: Obtain the preset production-insurance ratio of the cooperative maintenance outlet; Pre-allocating the overall output value to obtain the pre-allocated output value of the cooperative maintenance outlets, and calculating the distribution output-insurance ratio of the pre-allocated output value and the corresponding outlet premium; The pre-allocated output value is adjusted until each of the allocated output-guarantee ratios is not greater than the preset output-guarantee ratio, and the pre-allocated output value is used as the target output value.

4. The method for recommending maintenance outlets according to claim 1, characterized in that: The generating the target gap data of the candidate maintenance outlets based on the target output value and the preset time node includes: Obtain a preset time node according to the current time, and obtain the case closing output value and damage assessment output value of the candidate maintenance outlet before the preset time node; The target output value is subtracted from the case closing output value and the loss assessment output value to obtain the target gap data.

5. The method for recommending maintenance outlets according to claim 1, characterized in that: The step of inputting the target gap data into a pre-trained target control model for data prediction to obtain the network output value score of each candidate maintenance network point includes: Acquire maintenance volume data and network type data of the candidate maintenance network; The outlet business data is obtained according to the preset time node, the outlet type data, the maintenance volume data and the target gap data, the outlet business data is input into the target control model for data prediction to obtain the outlet estimated gap, and the outlet output value score is obtained according to the outlet estimated gap.

6. The method for recommending maintenance outlets according to claim 1, characterized in that: The acquiring object preference data corresponding to the target object and generating an object characteristic factor according to the object preference data and the vehicle damage data includes: Acquire the target object's outlet type preference, outlet service preference, maintenance time preference, outlet distance preference, and historical maintenance relationship data between the target object and each of the candidate maintenance outlets; At least obtaining a target vehicle type and a vehicle damage location based on the vehicle damage data; The object characteristic factor is obtained according to the network point type preference, the network point service preference, the maintenance time preference, the network point distance preference, the historical maintenance relationship data, the target vehicle type and the vehicle damage location.

7. The method for recommending a maintenance outlet according to claim 1, characterized in that: The generating of the network point characteristic factors corresponding to the candidate maintenance network points includes: Obtaining network point distance data according to the accident location and the object address data of the target object, and acquiring network point type data, network point service data and maintenance timeliness data of the candidate maintenance network point; The network point characteristic factor is obtained according to the network point distance data, the network point type data, the network point service data and the maintenance timeliness data.

8. A device for recommending maintenance outlets, characterized in that: The device comprises: Network point characteristic factor acquisition module: used to obtain the target object, vehicle damage data and accident location from the vehicle accident data, determine multiple candidate maintenance network points based on the accident location, and generate network point characteristic factors corresponding to the candidate maintenance network points; An object characteristic factor acquisition module is used to acquire object preference data corresponding to the target object, and generate an object characteristic factor according to the object preference data and the vehicle damage data; Object preference score prediction module: used for inputting the object characteristic factor and the network point characteristic factor into a pre-trained object network point preference prediction model for data prediction to obtain the object preference score of each candidate maintenance network point; The outlet output value score prediction module is used to obtain the target output value of the candidate maintenance outlets, generate the target gap data of the candidate maintenance outlets based on the target output value and the preset time node, input the target gap data into the pre-trained target control model for data prediction, and obtain the outlet output value score of each candidate maintenance outlet; Recommendation result generation module: used to perform weighted calculation according to the object preference score and the outlet output value score to obtain the outlet recommendation score of the candidate maintenance outlet, and determine the recommended maintenance outlet from the candidate maintenance outlets based on the outlet recommendation score.

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 maintenance network recommendation 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 for recommending a maintenance outlet according to any one of claims 1 to 7 is implemented.

Images