Object selection method and device based on claim settlement order, electronic equipment and medium

Abstract

The embodiment of the invention provides an object selection method and device based on a claim settlement order, electronic equipment and a medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring a claim settlement order of a target maintenance article, wherein the claim settlement order comprises article position data and maintenance item data of the target maintenance article; obtaining candidate maintenance data of the candidate maintenance object based on the claim settlement order, wherein the candidate maintenance data comprises candidate position data, object score data, candidate maintenance quotation data and historical maintenance quotation data; performing distance detection based on the article position data and the candidate position data to obtain candidate distance data; performing quotation change evaluation based on the historical maintenance quotation data and the candidate maintenance quotation data to obtain maintenance quotation change data; a target maintenance object is selected based on the maintenance offer change data, the candidate distance data, the object score data, and the candidate maintenance offer data. The embodiment of the invention can improve the selection accuracy of the maintenance object based on the claim settlement order.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method and device, electronic device and medium for selecting an object based on a claim order. Background Art

[0002] A claim order refers to a document for items that need to be repaired, issued after a detailed inspection of the insured items for claim settlement. For example, after a traffic accident, the owner of a vehicle can apply for a claim from the insurance company. At this time, the insurance company's damage assessor will issue a claim order based on the items that need to be repaired after a detailed inspection of the accident vehicle. In the vehicle claim and repair scenario of financial technology, after receiving the claim order, the owner can choose a suitable repair object to repair the accident vehicle and issue a document with detailed records of repair items, expenses and other information to the insurance company to obtain the corresponding compensation; or, the insurance company can choose a suitable repair object to repair the accident vehicle. However, for the first method, since the insurance company is not clear about the specific repair details, it is easy to make excessive compensation. For the second method, since the relevant technology usually uses a fixed scoring method to select the repair object, the repair object selected by the insurance company is not necessarily suitable for the repair of the accident vehicle, resulting in a low accuracy in the selection of the repair object based on the claim order. Therefore, how to improve the accuracy of the selection of the repair object based on the claim order, so as to select the most suitable object for performing the repair operation on the claim order, 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 method and device, electronic device and medium for object selection based on claim orders, aiming to improve the accuracy of selecting maintenance objects based on claim orders, thereby selecting the object that is most suitable for performing maintenance operations on the claim orders.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes an object selection method based on a claim settlement order, the method comprising:

[0005] Obtaining a claim settlement order for a target repair item; wherein the claim settlement order includes item location data and repair item data of the target repair item, and the repair item data includes candidate repair items;

[0006] Acquire candidate maintenance data of the candidate maintenance object based on the claim settlement order; wherein the candidate maintenance data includes candidate location data, object scoring data, candidate maintenance quotation data and historical maintenance quotation data of the candidate maintenance object, the candidate maintenance quotation data is used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the target maintenance object, and the historical maintenance quotation data is used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the historical maintenance items;

[0007] Perform distance detection based on the object position data and the candidate position data to obtain candidate distance data;

[0008] Performing a quotation change evaluation based on the historical maintenance quotation data and the candidate maintenance quotation data to obtain maintenance quotation change data;

[0009] The candidate maintenance objects are selected based on the maintenance quotation change data, the candidate distance data, the object scoring data and the candidate maintenance quotation data to determine a target maintenance object, where the target maintenance object is used to indicate an object that repairs the target maintenance item.

[0010] In some embodiments, the object scoring data includes maintenance feedback data and object value feedback data, and the step of selecting the candidate maintenance objects based on the maintenance quotation change data, the candidate distance data, the object scoring data, and the candidate maintenance quotation data to determine the target maintenance object includes:

[0011] Performing a change score calculation based on the maintenance quotation change data and a first preset weight to obtain a quotation change score;

[0012] Performing distance score calculation based on the candidate distance data and a second preset weight to obtain a distance score;

[0013] Calculate the feedback score based on the maintenance feedback data and the third preset weight to obtain a maintenance feedback score;

[0014] Calculate the object value score based on the object value feedback data and the fourth preset weight to obtain the object value score;

[0015] Calculate a quotation score based on the candidate repair quotation data and a fifth preset weight to obtain a quotation score;

[0016] The candidate maintenance objects are selected based on the quotation change score, the distance score, the maintenance feedback score, the object value score and the quotation score to determine a target maintenance object.

[0017] In some embodiments, the object value feedback data includes first value feedback sub-data and second value feedback sub-data, wherein the first value feedback sub-data is used to characterize the value feedback data of the object cooperating with the candidate maintenance object to the candidate maintenance object, and the second value feedback sub-data is used to characterize the value feedback data of the object not cooperating with the candidate maintenance object to the candidate maintenance object;

[0018] The object value score is calculated based on the object value feedback data and the fourth preset weight to obtain the object value score, including:

[0019] Obtain the value feedback preference of the claims and repair platform;

[0020] Based on the value feedback preference degree, the fourth preset weight is weight-divided to obtain a first sub-weight and a second sub-weight;

[0021] Performing weighted calculation on the first value feedback sub-data and the first sub-weight to obtain a first value feedback score;

[0022] Performing weighted calculation on the second value feedback sub-data and the second sub-weight to obtain a second value feedback score;

[0023] The object value score is determined based on the first value feedback score and the second value feedback score.

[0024] In some embodiments, the selecting the candidate maintenance objects based on the quotation change score, the distance score, the maintenance feedback score, the object value score and the quotation score to determine the target maintenance object includes:

[0025] Obtaining maintenance object preference data of the claim order;

[0026] Performing a quotation score calculation based on the maintenance object preference data and a sixth preset weight to obtain an object preference score;

[0027] determining a target score based on the object preference score, the quote change score, the distance score, the repair feedback score, the object value score, and the quote score;

[0028] The candidate maintenance objects are selected based on the target scores to determine a target maintenance object.

[0029] In some embodiments, the calculating of the feedback score based on the maintenance feedback data and the third preset weight to obtain the maintenance feedback score includes:

[0030] extracting claim feedback text from the maintenance feedback data;

[0031] Performing text scoring on the claim feedback text based on a pre-trained text scoring model to obtain a candidate text score;

[0032] Performing score preprocessing on the candidate text scores to obtain a target text score;

[0033] A feedback score is calculated based on the target text score and the third preset weight to obtain the maintenance feedback score.

[0034] In some embodiments, obtaining candidate maintenance data of a candidate maintenance object based on the claim settlement order includes:

[0035] Acquire initial maintenance data of an initial maintenance object based on the claim settlement order; wherein the initial maintenance data includes initial maintenance quotation data, and the initial maintenance quotation data is used to represent the maintenance quotation of the initial maintenance object for the candidate maintenance item;

[0036] The initial maintenance object is selected based on the initial maintenance quotation data and the preset quotation threshold data to obtain a candidate maintenance object, and the initial maintenance quotation data of the candidate maintenance object is used as the candidate maintenance data.

[0037] In some embodiments, the method further comprises:

[0038] Obtaining a target comprehensive score of a preset repair object and a target repair object of the claim order;

[0039] Based on the pre-trained claim scoring model, a claim scoring is performed on the preset maintenance object to obtain a predicted comprehensive score;

[0040] Calculating the difference between the predicted comprehensive score and the target comprehensive score to obtain a target score difference;

[0041] Performing order matching detection on the claim order based on the preset score difference threshold data and the target score difference value to obtain an order matching status, where the order matching status is used to indicate the matching degree between the preset maintenance object and the claim order;

[0042] If the order matching status is a mismatching status, an abnormal prompt message is returned to the claim settlement and repair platform.

[0043] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes an object selection device based on a claim settlement order, the device comprising:

[0044] An order acquisition module, used to acquire a claim settlement order for a target repair item; wherein the claim settlement order includes item location data and repair item data of the target repair item, and the repair item data includes candidate repair items;

[0045] A maintenance data acquisition module, configured to acquire candidate maintenance data of a candidate maintenance object based on the claim settlement order; wherein the candidate maintenance data includes candidate location data, object scoring data, candidate maintenance quotation data, and historical maintenance quotation data of the candidate maintenance object, the candidate maintenance quotation data being used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the target maintenance object, and the historical maintenance quotation data being used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the historical maintenance object;

[0046] A distance detection module, used to perform distance detection based on the object position data and the candidate position data to obtain candidate distance data;

[0047] A change evaluation module, used to evaluate the price change based on the historical maintenance price data and the candidate maintenance price data, and obtain maintenance price change data;

[0048] A selection module is used to select the candidate maintenance objects based on the maintenance quotation change data, the candidate distance data, the object scoring data and the candidate maintenance quotation data, and determine a target maintenance object, wherein the target maintenance object is used to indicate an object that repairs the target maintenance item.

[0049] 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, the memory stores a computer program, and when the processor executes the computer program, it implements the object selection method based on the claim order described in the first aspect above.

[0050] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the object selection method based on the claim order described in the first aspect above.

[0051] The present application proposes a method and device for selecting an object based on a claim order, an electronic device and a medium, which evaluates candidate repair objects from multiple dimensional data to select the most suitable target repair object, thereby improving the accuracy of selecting repair objects based on claim orders. Specifically, a claim order of a target repair item is first obtained, the claim order includes item location data and repair item data of the target repair item, the repair item data includes candidate repair items; further, candidate repair data of a candidate repair object is obtained based on the claim order, the candidate repair data includes candidate location data, object scoring data, candidate repair quotation data and historical repair quotation data of the candidate repair object, the candidate repair quotation data is used to characterize the repair quotation of the candidate repair object for the candidate repair items of the target repair item, and the historical repair quotation data is used to characterize the repair quotation of the candidate repair object for the candidate repair items of the historical repair item; further, distance detection is performed based on the item location data and the candidate location data to obtain candidate distance data; quotation change evaluation is performed based on the historical repair quotation data and the candidate repair quotation data to obtain repair quotation change data; further, object selection is performed on the candidate repair object based on the repair quotation change data, the candidate distance data, the object scoring data and the candidate repair quotation data to determine the target repair object, the target repair object is used to indicate the object that repairs the target repair item. Compared with the related art that usually adopts a fixed scoring method to select maintenance objects, the present application can select candidate maintenance objects from multiple dimensional data that can be updated in real time, thereby improving the accuracy of selecting maintenance objects based on claim orders, thereby selecting the most suitable object to perform maintenance operations on the claim order. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of a method for selecting an object based on a claim settlement order provided in an embodiment of the present application;

[0053] Figure 2 yes Figure 1 A flowchart of step S120 in FIG.

[0054] Figure 3 yes Figure 1 A flowchart of step S150 in FIG.

[0055] Figure 4 yes Figure 3 A flowchart of step S330 in FIG.

[0056] Figure 5 yes Figure 3 A flowchart of step S340 in FIG.

[0057] Figure 6 yes Figure 3 A flowchart of step S360 in FIG.

[0058] Figure 7 is a detailed flow chart of the object selection method based on the claim settlement order provided in the embodiment of the present application;

[0059] Figure 8 is another flow chart of the object selection method based on the claim settlement order provided in an embodiment of the present application;

[0060] Fig. 9 It is a structural schematic diagram of an object selection device based on a claim settlement order provided in an embodiment of the present application;

[0061] Fig.10 It is a hardware structure diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0062] 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.

[0063] 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.

[0064] 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.

[0065] First, some nouns involved in this application are analyzed:

[0066] 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 intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language 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.

[0067] A claim order refers to a document for items that need to be repaired, issued after a detailed inspection of the insured items for claim settlement. For example, after a traffic accident, the owner of a vehicle can apply for a claim from the insurance company. At this time, the insurance company's damage assessor will issue a claim order based on the items that need to be repaired after a detailed inspection of the accident vehicle. In the vehicle claim and repair scenario of financial technology, after receiving the claim order, the owner can choose a suitable repair object to repair the accident vehicle and issue a document with detailed records of repair items, expenses and other information to the insurance company to obtain the corresponding compensation; or, the insurance company can choose a suitable repair object to repair the accident vehicle. However, for the first method, since the insurance company is not clear about the specific repair details, it is easy to make excessive compensation. For the second method, since the relevant technology usually uses a fixed scoring method to select the repair object, the repair object selected by the insurance company is not necessarily suitable for the repair of the accident vehicle, resulting in a low accuracy in the selection of the repair object based on the claim order. Therefore, how to improve the accuracy of the selection of the repair object based on the claim order, so as to select the most suitable object for performing the repair operation on the claim order, has become a technical problem that needs to be solved urgently.

[0068] Based on this, the embodiments of the present application provide a method and device, an electronic device and a medium for selecting an object based on a claim order, which can improve the accuracy of selecting a maintenance object based on a claim order, thereby selecting the object that is most suitable for performing maintenance operations on the claim order.

[0069] 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 obtain the best results.

[0070] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] The object selection method based on the claim order provided in the embodiment of the present application relates to the field of artificial intelligence technology. The object selection method based on the claim order 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 it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content De l ivery Network, CDN) and big data and artificial intelligence platforms and other basic cloud computing services. Cloud servers; software can be an application that implements an object selection method based on a claim order, etc., but is not limited to the above forms.

[0072] 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.

[0073] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing on data related to the identity or characteristics of the object, such as the claim object information corresponding to the claim order, the claim object feedback information, and the claim object location information, the permission or consent of the object will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiment of the present application needs to obtain the sensitive personal information of the object, the separate permission or separate consent of the object will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the separate permission or separate consent of the object, the necessary object-related data for the normal operation of the embodiment of the present application will be obtained.

[0074] See also Figure 1 , Figure 1 is an optional flow chart of the object selection method based on the claim settlement order provided in the embodiment of the present application. In some embodiments, Figure 1 The method may include but is not limited to steps S110 to S150:

[0075] Step S110, obtaining a claim settlement order for the target repair item;

[0076] Step S120, acquiring candidate maintenance data of the candidate maintenance object based on the claim settlement order;

[0077] Step S130, performing distance detection based on the object location data and the candidate location data to obtain candidate distance data;

[0078] Step S140, performing quotation change evaluation based on historical maintenance quotation data to obtain maintenance quotation change data;

[0079] Step S150 , selecting candidate maintenance objects based on the maintenance quotation change data, the candidate distance data, the object scoring data and the candidate maintenance quotation data, and determining a target maintenance object.

[0080] In step S110 of some embodiments, a claim order refers to an order for an insurance company to repair a target repair item after an accident occurs to the target repair item. The target repair item may be a vehicle, a house, or other item that has purchased insurance related to the claim repair. The claim order includes item location data and repair project data of the target repair item, and the repair project data includes candidate repair projects. Among them, the item location data refers to the current location of the target repair item. For example, when the target repair item is an accident vehicle, the item location data indicates the current location of the accident vehicle. The repair project data refers to the specific project data that needs to be repaired for the target repair item, and the repair project data includes at least one candidate repair project, which refers to accessories that need to be repaired, such as windows, doors, etc.

[0081] It should be noted that when an accident occurs, the insurance company's claims adjuster will conduct claims adjustment on the target repair items in the early stage, determine the project data of the target repair items that need to be repaired for claims, and generate a claim order. Furthermore, the insurance company can upload the claim order to the claim repair platform, so that the third-party candidate repair objects cooperating with the insurance company can view the claim order online.

[0082] It should be noted that the present application can generate multiple claim orders for a target repair item. One claim order will select a target repair object, and at this time, the same target repair object or different repair objects can be selected for multiple claim orders.

[0083] In step S120 of some embodiments, the candidate repair object refers to an object or organization that cooperates with the insurance company and is capable of repairing the target repair object. For example, when the target repair object is a vehicle, the candidate repair object refers to an organization that can repair the vehicle, and when the target repair object is a house, the candidate repair object refers to an organization that can repair the house, that is, the candidate repair object can be flexibly determined according to the type of the target repair object.

[0084] The candidate maintenance data includes candidate location data, object rating data, candidate maintenance quotation data, and historical maintenance quotation data of the candidate maintenance object. The candidate location data refers to the location of the candidate maintenance object, such as the location of the maintenance organization or the location where the candidate maintenance object can perform maintenance on the target maintenance item. The object rating data refers to the rating data of the candidate maintenance object.

[0085] It should be noted that the candidate repair quotation data is used to characterize the repair quotation of the candidate repair object for the candidate repair items of the target repair item, and the candidate repair quotation data includes the candidate repair quotation corresponding to each candidate repair item. On the claim repair platform, each claim order includes a corresponding quotation pool. After the insurance company uploads the claim order to the claim repair platform, it can set a preset quotation deadline for the claim order. At this time, the candidate repair object can upload the repair quotation for each candidate repair item in the target repair item within the preset quotation deadline. However, in order to ensure the fairness of the quotation, the data uploaded by each candidate repair object cannot be seen by other candidate repair objects.

[0086] It should be noted that the historical repair quotation data is used to characterize the repair quotation of the candidate repair object for the candidate repair items of the historical repair items, and the historical repair quotation data may include multiple historical repair candidate quotations of the candidate repair object for the same component (i.e., the candidate repair item), where the multiple here can be all or a preset historical number. In other words, the insurance company can obtain the repair quotation of the candidate repair object for the same item as the candidate repair item, and the historical repair items corresponding to the historical repair quotation data can come from the claim orders uploaded to the claim repair platform in the past, or can be the claim orders of other insurance companies processed by the candidate repair object. In other words, the claim repair platform can include a repair object database for maintaining and collecting basic data of cooperating candidate repair objects (i.e., third-party repair agencies), such as the latitude and longitude address of the repair agency (i.e., candidate location data), brand, agency rating and other information.

[0087] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on the location information and historical maintenance information of the candidate maintenance object and other data related to the identity or characteristics of the candidate maintenance object, the permission or consent of the candidate maintenance object will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiment of the present application needs to obtain sensitive personal information of the object, the separate permission or consent of the object will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the separate permission or consent of the object, the necessary object-related data for the normal operation of the embodiment of the present application will be obtained.

[0088] In some embodiments, see Figure 2 , step S120 may specifically include steps S210 to S220:

[0089] Step S210, obtaining initial maintenance data of the initial maintenance object based on the claim settlement order;

[0090] Step S220 , selecting an initial maintenance object based on the initial maintenance quotation data and the preset quotation threshold data to obtain a candidate maintenance object, and using the initial maintenance quotation data of the candidate maintenance object as the candidate maintenance data.

[0091] In step S210 of some embodiments, the initial maintenance object refers to an object or organization that cooperates with the insurance company and has the ability to repair the target maintenance item. At this time, the candidate maintenance object refers to an object or organization that repairs the target maintenance item selected from the initial maintenance data. The specific data structure of the initial maintenance data is the same as the candidate maintenance data in the above embodiment, except that the source object is different, which will not be repeated here. Among them, the initial maintenance data includes initial maintenance quotation data; the initial maintenance quotation data is used to characterize the maintenance quotation of the initial maintenance object for the candidate maintenance item.

[0092] In step S220 of some embodiments, the preset quotation threshold data refers to preset data for limiting abnormal quotation for target maintenance items, and the preset quotation threshold data includes preset quotation threshold sub-data of candidate maintenance project objects, and the preset quotation threshold sub-data is used to limit data for abnormal quotation for candidate maintenance projects. Among them, the preset quotation threshold sub-data can be the maximum quotation of the corresponding candidate maintenance project, or it can be the quotation range interval composed of the minimum quotation value and the maximum quotation value of the corresponding candidate maintenance project. In this way, by comparing the initial maintenance quotation data with the preset quotation threshold data, it is checked whether the initial maintenance quotation data falls within an acceptable range, so that those initial maintenance objects with abnormal quotations (such as quotations that are too high or too low) can be filtered out, and those objects with reasonable costs can be focused on. In this way, at least one candidate maintenance object can be screened and the initial maintenance quotation data of the candidate maintenance object can be used as candidate maintenance data.

[0093] It should be noted that if the candidate repair object is not screened out after the initial repair quotation data and the preset quotation threshold data are numerically compared, the preset quotation threshold data can be further updated according to the initial repair quotation data of the initial candidate object of the current quotation. For example, a median repair quotation data can be determined from multiple initial repair quotation data, and the repair quotation data can be used as the updated preset quotation threshold data; or, the average repair quotation data can be determined from multiple initial repair quotation data, and the average repair quotation data can be used as the updated preset quotation threshold data. The specific update process can be flexibly set according to actual needs.

[0094] It should be noted that the preset quotation threshold sub-data can be set as the maintenance cost estimated based on factors such as materials, working hours, market conditions, etc. during the historical maintenance process of the candidate maintenance items by maintenance personnel. That is, this preset quotation threshold sub-data can meet the price standards or limits of most claim objects (i.e., objects insured by insurance companies) and insurance companies.

[0095] In the above embodiment, the present application selects the initial repair object by comparing the initial repair quotation data with the preset quotation threshold data, and can obtain candidate repair objects with abnormal risk quotations removed, thereby improving the accuracy of selecting repair objects based on claim orders.

[0096] In step S130 of some embodiments, due to the distance between the repair object and the target repair item, it also has a certain impact on the user experience of the claim object. Therefore, this application will perform distance detection on the item location data and the candidate location data to obtain candidate distance data that can reflect the positional relationship between the candidate repair object and the target repair item. The candidate distance data is a specific value. Among them, the process of calculating the candidate distance data can use Euclidean distance (that is, applicable to two points on a plane, and the calculation formula is the straight-line distance between the two points), Manhattan distance (also known as city block distance, only considering the movement along the coordinate axis when calculating, and not considering diagonal movement), Chebyshev distance (that is, considering the maximum value of the absolute value of all coordinate differences between two points), etc. These distance calculation methods have their own characteristics and can be applied to different scenarios and needs, and the calculation method can be flexibly selected considering the dimension of the data, the distribution characteristics of the data, and the accuracy requirements of the calculation.

[0097] In step S140 of some embodiments, the maintenance quotation change data refers to the average change rate data of the historical quotations of the candidate maintenance object for the same component (i.e., the candidate maintenance item), and the degree of change compared with the candidate maintenance quotation data. Further, the maintenance quotation change data can reflect the rationality of the current quotation of the candidate maintenance object to a certain extent.

[0098] It should be noted that the quotation change evaluation is performed based on the historical maintenance quotation data and the candidate maintenance quotation data to obtain the maintenance quotation change data, which may specifically include: calculating the mean of the historical maintenance candidate quotations based on a preset historical quantity to obtain the average historical maintenance quotation; calculating the difference between the average historical maintenance quotation and the candidate maintenance quotation data to obtain the maintenance quotation difference; and numerically comparing the maintenance quotation difference with the average historical maintenance quotation to obtain the maintenance quotation change data. For example, for the same candidate maintenance item, the preset historical quantity is 3, and the historical maintenance candidate quotations include 112, 120, and 107. The historical maintenance candidate quotations are averaged, and the average historical maintenance quotation is (112+120+107) / 3=113. The current candidate maintenance quotation is 130. In this way, the maintenance quotation difference is (113-130=-17) (wherein, since the maintenance quotation difference is the average historical maintenance quotation minus the candidate maintenance quotation data, the current negative sign indicates that the quotation has increased. On the contrary, if the maintenance quotation difference is the candidate maintenance quotation data minus the average historical maintenance quotation, the current negative sign indicates that the quotation has decreased). Further, the maintenance quotation change data is the absolute value of (-17 / 113). In this way, the rationality of the current quotation of the candidate maintenance object can be reflected according to the maintenance quotation change data. The higher the maintenance quotation change data, the more unreasonable the candidate maintenance quotation data of the candidate maintenance object is. The lower the candidate maintenance quotation data, the more reasonable the candidate maintenance quotation data is.

[0099] It should be noted that the maintenance quotation change data of this application is an absolute value, because the positive or negative value of the maintenance quotation change data reflects a reduction or increase in the quotation, and a large change in the magnitude of both will have a certain impact on the selection of the maintenance object, that is, there is a risk of abnormal quotation, therefore, only the degree of change is considered.

[0100] In step S150 of some embodiments, after determining the repair quotation change data and the candidate distance data, object selection can be performed on the candidate repair objects based on the repair quotation change data, the candidate distance data, the object scoring data and the candidate repair quotation data to determine the target repair object, which is used to indicate the object that repairs the target repair item.

[0101] In some embodiments, see Figure 3 Step S150 may specifically include but is not limited to steps S310 to S360:

[0102] Step S310, calculating a change score based on the maintenance quotation change data and a first preset weight to obtain a quotation change score;

[0103] Step S320, calculating a distance score based on the candidate distance data and a second preset weight to obtain a distance score;

[0104] Step S330, calculating a feedback score based on the maintenance feedback data and a third preset weight to obtain a maintenance feedback score;

[0105] Step S340, calculating the object value score based on the object value feedback data and the fourth preset weight to obtain the object value score;

[0106] Step S350, calculating a quotation score based on the candidate maintenance quotation data and a fifth preset weight to obtain a quotation score;

[0107] Step S360 , selecting candidate maintenance objects based on the quotation change score, the distance score, the maintenance feedback score, the object value score and the quotation score, and determining the target maintenance object.

[0108] In step S310 of some embodiments, when determining the target maintenance object, the present application will consider the changes in the historical quotations of the candidate maintenance objects for the same component (i.e., the candidate maintenance items), and assign a first preset weight to it to obtain a quotation change score, that is, the rationality of the object's quotation for the candidate maintenance items can be considered when the target maintenance object is finally selected, thereby improving the accuracy of the selection of maintenance objects based on the claim order, thereby selecting the object that is most suitable for performing maintenance operations on the claim order. Because the higher the maintenance quotation change data, the more unreasonable the current candidate maintenance quotation data of the candidate maintenance object, so the present application can set the first preset weight to a negative number, such as -0.5, -0.3, etc. In this way, the higher the maintenance quotation change data, the larger the absolute value of the corresponding quotation change score, and because it is a negative number, it will affect the final score.

[0109] In step S320 of some embodiments, when determining the target repair object, the present application will also consider the distance between the candidate repair object and the target repair item, and assign a second preset weight to it to obtain a distance score. Because the distance has a greater impact on the experience of the claimant, for example, the closer the distance between the candidate repair object and the target repair item, the better the experience of the claimant and the greater the willingness to go, so the score calculated for the candidate repair object is more reasonable.

[0110] In step S330 and step S340 of some embodiments, the object scoring data includes maintenance feedback data and object value feedback data. The maintenance feedback data refers to the feedback data of the candidate maintenance object's maintenance process from the individual who has had the item repaired by the candidate maintenance object. For example, it can be a subjective evaluation of the candidate maintenance object's service attitude, item maintenance status, feedback text, voice return visit, etc., which can reflect the intuitive experience of the claim object, thereby better affecting the final distribution effect of the claim order. Among them, the object corresponding to the maintenance feedback data can be an insured object, or it can be an object of feedback data obtained through other applications. Object value feedback data refers to the value evaluation of the candidate maintenance object by an external organization. Therefore, the present application assigns corresponding weights to the maintenance feedback data and the object value feedback data, respectively, and can more comprehensively determine the external feedback on the candidate maintenance object from the perspective of personal subjective evaluation and external organization evaluation, thereby improving the accuracy of selecting maintenance objects based on claim orders.

[0111] In some embodiments, see Figure 4 Step S330 may specifically include but is not limited to steps S410 to S440:

[0112] Step S410, extracting claim feedback text from the maintenance feedback data;

[0113] Step S420, performing text scoring on the claim feedback text based on a pre-trained text scoring model to obtain a candidate text score;

[0114] Step S430, performing score preprocessing on the candidate text scores to obtain the target text score;

[0115] Step S440, calculating a feedback score based on the target text score and the third preset weight to obtain a maintenance feedback score.

[0116] In steps S410 to S420 of some embodiments, since the maintenance feedback data can be text or voice, the claim feedback text can be first extracted from the maintenance feedback data, wherein if the maintenance feedback data itself is in text form, the claim feedback text can be directly obtained; if the maintenance feedback data is in voice form, a pre-trained voice recognition model (such as Whisper, DeepSpeech, etc.) can be used to perform voice recognition on the maintenance feedback data to obtain the claim feedback text. Further, the claim feedback text can be scored based on a pre-trained text scoring model (which can be a model built based on a word2vec algorithm, a deep learning algorithm, etc.) to obtain a candidate text score, which represents the evaluation of the candidate claim object represented by the claim feedback text, and the higher the candidate text score, the higher the evaluation of the candidate claim object by the object corresponding to the claim feedback text, that is, the higher the recognition.

[0117] In some embodiments, in step S430 to step S440, in order to eliminate the influence of invalid data, the present application performs score preprocessing on the candidate text score, that is, the maximum score and the minimum score in the candidate text score can be removed, and the remaining score is used as the target text score. Further, the feedback score is calculated based on the remaining at least one target text score and the third preset weight, that is, weighted calculation is performed to obtain the maintenance feedback score.

[0118] It should be noted that the maintenance feedback data can be the maintenance data collected every month, and the speech recognition model is trained and optimized through the latest collected data to improve the recognition accuracy of the model.

[0119] In some embodiments, see Figure 5 Step S340 may specifically include but is not limited to steps S510 to S550:

[0120] Step S510, obtaining the value feedback preference degree of the claim settlement and repair platform;

[0121] Step S520, dividing the fourth preset weight based on the value feedback preference degree to obtain a first sub-weight and a second sub-weight;

[0122] Step S530, performing weighted calculation on the first value feedback sub-data and the first sub-weight to obtain a first value feedback score;

[0123] Step S540, performing weighted calculation on the second value feedback sub-data and the second sub-weight to obtain a second value feedback score;

[0124] Step S550: determining the object value score based on the first value feedback score and the second value feedback score.

[0125] In step S510 and step S520 of some embodiments, the value feedback preference refers to the preference for the source of value feedback preset by the claim settlement and maintenance platform. Among them, the object value feedback data includes the first value feedback sub-data and the second value feedback sub-data. The first value feedback sub-data is used to characterize the value feedback data of the object (such as an insurance company) cooperating with the candidate maintenance object on the candidate maintenance object, such as the cooperation score of the candidate maintenance object within the insurance company. The second value feedback sub-data is used to characterize the value feedback data of the object (such as an industry management agency, a professional evaluation agency, etc.) that does not cooperate with the candidate maintenance object on the candidate maintenance object, that is, it can be the object brand score made by the industry or relevant agencies based on the overall operating conditions of the candidate maintenance object, including safety, environmental protection, business management and other aspects. Further, the fourth preset weight can be weighted based on the value feedback preference to obtain the first sub-weight and the second sub-weight. For example, if the value feedback preference indicates that the value feedback data of the object cooperating with the candidate maintenance object on the candidate maintenance object is given priority, a higher weight can be set for the first sub-weight corresponding to the first value feedback sub-data, such as the first sub-weight is 0.35 and the second sub-weight is 0.1.

[0126] In steps S530 to S550 of some embodiments, further, the first value feedback sub-data and the first sub-weight can be weightedly calculated to obtain a first value feedback score, the second value feedback sub-data and the second sub-weight can be weightedly calculated to obtain a second value feedback score, and the object value score can be determined based on the first value feedback score and the second value feedback score.

[0127] It should be noted that, when considering the second value feedback sub-data, the present application has pre-processed the second value feedback sub-data, that is, the maximum score and the minimum score have been removed to ensure the rationality of the data, thereby improving the accuracy of selecting maintenance objects based on claim orders.

[0128] In step S350 of some embodiments, when determining the target maintenance object, the present application will consider the impact of the candidate maintenance quotation data on the final object selection, and this candidate maintenance quotation data refers to the data after the abnormal quotation has been removed.

[0129] In step S360 of some embodiments, after obtaining the quotation change score, distance score, maintenance feedback score, object value score and quotation score, these scores can be added up to obtain the target score corresponding to each candidate maintenance object. Further, the candidate maintenance objects are sorted in descending order according to the target score, and the candidate maintenance object with the highest target score is determined as the target maintenance object.

[0130] In the above embodiment, the present application evaluates candidate repair objects from multiple dimensional data when determining the target repair object, thereby selecting the most suitable target repair object, thereby improving the accuracy of selecting the repair object based on the claim order.

[0131] In some embodiments, see Figure 6 Step S360 may specifically include but is not limited to steps S610 to S640:

[0132] Step S610, obtaining the maintenance object preference data of the claim settlement order;

[0133] Step S620, performing quotation score calculation based on the maintenance object preference data and the sixth preset weight to obtain an object preference score;

[0134] Step S630, determining a target score based on the object preference score, the quote change score, the distance score, the maintenance feedback score, the object value score, and the quote score;

[0135] Step S640: selecting candidate maintenance objects based on the target scores to determine target maintenance objects.

[0136] In steps S610 to S640 of some embodiments, in order to make the target maintenance object finally selected more in line with the needs of the insured person corresponding to the claim order, the present application can obtain the maintenance object preference data of the claim order, that is, the insured person can input one or more candidate maintenance objects that he or she wants to select more in the terminal, and then the selected object can be assigned a corresponding preference value, thereby generating maintenance object preference data, and this maintenance object preference data is the preference value. Further, the quotation score calculation can be performed based on the maintenance object preference data and the sixth preset weight to obtain the object preference score, and the object preference score, quotation change score, distance score, maintenance feedback score, object value score and quotation score are added and calculated to obtain the target score corresponding to each candidate maintenance object, and determine the target score. Further, the candidate maintenance objects can be selected based on the target score to determine the target maintenance object.

[0137] It should be noted that the repair object preference data can be set by the insured person corresponding to the claim order, or it can be set by the claim repair platform based on the average preference number, without limitation.

[0138] In the above embodiment, the present application considers the maintenance object preference data when determining the target maintenance object, thereby improving the personalization of the selection of the maintenance object based on the claim order, and thus selecting the most appropriate target maintenance object.

[0139] It should be noted that the sum of the first preset weight, the second preset weight, the third preset weight, the fourth preset weight, the fifth preset weight and the sixth preset weight in the embodiment of the present application can be 1 to ensure that the final score is within a certain range. In addition, the sum of the first preset weight, the second preset weight, the third preset weight, the fourth preset weight, the fifth preset weight and the sixth preset weight may not be 1, so that more considerations can be added later, thereby improving the accuracy of selecting the maintenance object based on the claim order.

[0140] In one specific embodiment, see Figure 7 , Figure 7It is a detailed flow chart of the object selection method based on the claim order provided by the embodiment of the present application. The object selection method based on the claim order can be applied to the claim repair platform, and can specifically include: the initial repair object of the third party applies for access to the claim repair platform. Further, the claim repair platform authenticates the initial repair object applied for, and after the verification is passed, the initial repair object is successfully stored. Further, the insurance company publishes a claim order on the claim repair platform. When the initial repair object obtains the claim order, the initial repair object can quote and place an order for the claim order, and provide the repair quotation for the candidate repair items in the claim order and whether to replace the accessories and other information. Further, the initial repair object is preliminarily screened based on the initial repair quotation data and the preset quotation threshold data to obtain the candidate repair object. Then, the relevant basic data of the candidate repair object is obtained, specifically including distance (i.e. candidate location data), user rating (i.e. repair feedback data), company rating (i.e. first value feedback sub-data), brand rating (i.e. second value feedback sub-data), quotation (i.e. candidate repair quotation data), historical quotation (used to determine the repair quotation change data) and user preference (i.e. repair object preference data). Further, based on the maintenance quotation change data and the first preset weight, a change score is calculated to obtain a quotation change score; based on the candidate distance data and the second preset weight, a distance score is calculated to obtain a distance score; based on the maintenance feedback data and the third preset weight, a feedback score is calculated to obtain a maintenance feedback score; based on the object value feedback data and the fourth preset weight, an object value score is calculated to obtain an object value score; based on the candidate maintenance quotation data and the fifth preset weight, a quotation score is calculated to obtain a quotation score; based on the maintenance object preference data and the sixth preset weight, a quotation score is calculated to obtain an object preference score; based on the object preference score, the quotation change score, the distance score, the maintenance feedback score, the object value score and the quotation score, a target score is determined, and a target maintenance object is determined from the candidate maintenance objects based on the target score. Further, the claim order is sent to the target maintenance object, and the maintenance object that receives the claim order repairs the target maintenance item. Further, after the repair is completed, the latest feedback information of the insured object and the claim company on the maintenance object can be received, and the user score (i.e., maintenance feedback data) and company score (i.e., first value feedback sub-data) in the basic data can be updated according to the feedback information.

[0141] In some embodiments, see Figure 8 , Figure 8 is another optional flow chart of the object selection method based on the claim settlement order provided in the embodiment of the present application. The object selection method provided in the embodiment of the present application may also include steps S810 to S850:

[0142] Step S810, obtaining the target comprehensive score of the preset repair object and the target repair object of the claim order;

[0143] Step S820, performing claim scoring on the preset maintenance object based on the pre-trained claim scoring model to obtain a predicted comprehensive score;

[0144] Step S830, calculating the difference between the predicted comprehensive score and the target comprehensive score to obtain the target score difference;

[0145] Step S840, performing order matching detection on the claim order based on the preset score difference threshold data and the target score difference value to obtain the order matching status;

[0146] Step S850: If the order matching status is a mismatching status, an abnormal prompt message is returned to the claim settlement and repair platform.

[0147] In steps S810 to S850 of some embodiments, in actual applications, there may be an insured object specifying a certain maintenance object to repair the target maintenance item. At this time, manual order allocation is required, that is, the claim order is allocated to the preset maintenance object. In order to ensure the safety of allocation, the present application will obtain the target comprehensive score of the preset maintenance object and the target maintenance object of the claim order, and perform a claim score on the preset maintenance object based on the pre-trained claim scoring model to obtain a predicted comprehensive score. Among them, the claim scoring model is a model constructed based on steps S110 to S150 of the present application, that is, by inputting the claim order of the target maintenance item and the candidate maintenance data of the candidate maintenance object, the target score of the candidate maintenance object can be output. Therefore, the predicted comprehensive score is the target score determined based on steps S110 to S150 of the present application. Further, the difference between the predicted comprehensive score and the target comprehensive score is calculated to obtain the target score difference, and the order matching detection is performed on the claim order based on the preset score difference threshold data and the target score difference to obtain the order matching status. If the order matching status is a mismatch state, an abnormal prompt information is returned to the claim maintenance platform.

[0148] It should be noted that the order matching status is used to indicate the matching degree between the preset maintenance object and the claim order, and the order matching status includes the matching status and the non-matching status, wherein the matching status indicates that the target score difference exceeds the preset score difference threshold data, which means that it is not appropriate to use the set maintenance object to repair the target maintenance item. The matching status indicates that the target score difference is within the range of the preset score difference threshold data, which means that it is appropriate to use the set maintenance object to repair the target maintenance item.

[0149] It should be noted that if the order matching status is a matching status, information may not be returned to the claims and repair platform, or appropriate matching prompt information may be returned to the claims and repair platform.

[0150] It should be noted that the present application can be configured in a way that dynamically manages third-party repair organizations and repair orders. For orders for repair of damaged items, orders can also be issued through the configuration of various rules, ensuring that the repair of items is completed in a completely transparent one-stop manner online, greatly avoiding operational risks and loopholes, forming a unified closed-loop management model, and also having better practical significance through a simple claims scoring model.

[0151] The embodiment of the present application provides an object selection method based on a claim order. By collecting basic data samples and performing AI modeling of an intelligent bidding model, the bids can be comprehensively scored more accurately and flexibly. In the later stage, the model is continuously fed with new data samples, so that the model is continuously dynamically optimized and updated, and cost savings, risk control, and user experience can be continuously improved. In other words, compared to the related technology that usually uses a fixed scoring method to select maintenance objects, the present application can select candidate maintenance objects from multiple dimensional data that can be updated in real time, thereby improving the accuracy of selecting maintenance objects based on claim orders, thereby selecting the most suitable object for performing maintenance operations on the claim order.

[0152] See also Fig. 9 The embodiment of the present application further provides an object selection device based on a claim settlement order, which can implement the above-mentioned object selection method based on a claim settlement order, and the device includes:

[0153] An order acquisition module 910 is used to acquire a claim settlement order for a target repair item; wherein the claim settlement order includes item location data and repair item data of the target repair item, and the repair item data includes candidate repair items;

[0154] The maintenance data acquisition module 920 is used to acquire candidate maintenance data of the candidate maintenance object based on the claim settlement order; wherein the candidate maintenance data includes candidate location data, object scoring data, candidate maintenance quotation data and historical maintenance quotation data of the candidate maintenance object, the candidate maintenance quotation data is used to represent the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the target maintenance object, and the historical maintenance quotation data is used to represent the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the historical maintenance item;

[0155] A distance detection module 930 is used to perform distance detection based on the object location data and the candidate location data to obtain candidate distance data;

[0156] A change evaluation module 940 is used to evaluate price changes based on historical maintenance price data and candidate maintenance price data to obtain maintenance price change data;

[0157] The selection module 950 is used to select candidate maintenance objects based on the maintenance quotation change data, candidate distance data, object scoring data and candidate maintenance quotation data, and determine a target maintenance object, where the target maintenance object is used to indicate an object that repairs the target maintenance item.

[0158] The specific implementation of the object selection device based on the claim order is basically the same as the specific implementation of the object selection method based on the claim order mentioned above, and will not be repeated here.

[0159] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned object selection method based on the claim settlement order when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0160] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0161] The processor 1010 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;

[0162] The memory 1020 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 1020 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 1020, and the processor 1010 calls and executes the object selection method based on the claim settlement order in the embodiment of this application;

[0163] Input / output interface 1030, used to implement information input and output;

[0164] The communication interface 1040 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0165] Bus 1050 , which transmits information between various components of the device (e.g., processor 1010 , memory 1020 , input / output interface 1030 , and communication interface 1040 );

[0166] The processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 are connected to each other in communication within the device via a bus 1050 .

[0167] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned object selection method based on the claim order is implemented.

[0168] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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 (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0179] The preferred embodiments of the present application are described above with reference to the accompanying drawings, but the scope of the rights of the present application 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 application should be within the scope of the rights of the present application.

Claims

1. A method for selecting an object based on a claim order, characterized in that: The method comprises: Obtaining a claim settlement order for a target repair item; wherein the claim settlement order includes item location data and repair item data of the target repair item, and the repair item data includes candidate repair items; Acquire candidate maintenance data of the candidate maintenance object based on the claim settlement order; wherein the candidate maintenance data includes candidate location data, object scoring data, candidate maintenance quotation data and historical maintenance quotation data of the candidate maintenance object, the candidate maintenance quotation data is used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the target maintenance object, and the historical maintenance quotation data is used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the historical maintenance items; Perform distance detection based on the object position data and the candidate position data to obtain candidate distance data; Performing a quotation change evaluation based on the historical maintenance quotation data and the candidate maintenance quotation data to obtain maintenance quotation change data; The candidate maintenance objects are selected based on the maintenance quotation change data, the candidate distance data, the object scoring data and the candidate maintenance quotation data to determine a target maintenance object, where the target maintenance object is used to indicate an object that repairs the target maintenance item.

2. The method according to claim 1, characterized in that The object scoring data includes maintenance feedback data and object value feedback data, and the candidate maintenance object is selected based on the maintenance quotation change data, the candidate distance data, the object scoring data and the candidate maintenance quotation data to determine the target maintenance object, including: Performing a change score calculation based on the maintenance quotation change data and a first preset weight to obtain a quotation change score; Performing distance score calculation based on the candidate distance data and a second preset weight to obtain a distance score; Calculate the feedback score based on the maintenance feedback data and the third preset weight to obtain a maintenance feedback score; Calculate the object value score based on the object value feedback data and the fourth preset weight to obtain the object value score; Calculate a quotation score based on the candidate repair quotation data and a fifth preset weight to obtain a quotation score; The candidate maintenance objects are selected based on the quotation change score, the distance score, the maintenance feedback score, the object value score and the quotation score to determine a target maintenance object.

3. The method according to claim 2, characterized in that The object value feedback data includes first value feedback sub-data and second value feedback sub-data, wherein the first value feedback sub-data is used to represent the value feedback data of the object cooperating with the candidate maintenance object to the candidate maintenance object, and the second value feedback sub-data is used to represent the value feedback data of the object not cooperating with the candidate maintenance object to the candidate maintenance object; The object value score is calculated based on the object value feedback data and the fourth preset weight to obtain the object value score, including: Obtain the value feedback preference of the claims and repair platform; Based on the value feedback preference degree, the fourth preset weight is weight-divided to obtain a first sub-weight and a second sub-weight; Performing weighted calculation on the first value feedback sub-data and the first sub-weight to obtain a first value feedback score; Performing weighted calculation on the second value feedback sub-data and the second sub-weight to obtain a second value feedback score; The object value score is determined based on the first value feedback score and the second value feedback score.

4. The method according to claim 2, characterized in that: The selecting the candidate maintenance objects based on the quotation change score, the distance score, the maintenance feedback score, the object value score and the quotation score to determine the target maintenance object includes: Obtaining maintenance object preference data of the claim order; Calculate the quotation score based on the maintenance object preference data and the sixth preset weight to obtain an object preference score; determining a target score based on the object preference score, the quote change score, the distance score, the repair feedback score, the object value score, and the quote score; The candidate maintenance objects are selected based on the target scores to determine a target maintenance object.

5. The method according to claim 2, characterized in that: The calculating of the feedback score based on the maintenance feedback data and the third preset weight to obtain the maintenance feedback score includes: extracting claim feedback text from the maintenance feedback data; Performing text scoring on the claim feedback text based on a pre-trained text scoring model to obtain a candidate text score; Performing score preprocessing on the candidate text scores to obtain a target text score; A feedback score is calculated based on the target text score and the third preset weight to obtain the maintenance feedback score.

6. The method according to any one of claims 1 to 5, characterized in that: The step of acquiring candidate maintenance data of a candidate maintenance object based on the claim settlement order includes: Acquire initial maintenance data of an initial maintenance object based on the claim settlement order; wherein the initial maintenance data includes initial maintenance quotation data, and the initial maintenance quotation data is used to represent the maintenance quotation of the initial maintenance object for the candidate maintenance item; The initial maintenance object is selected based on the initial maintenance quotation data and the preset quotation threshold data to obtain a candidate maintenance object, and the initial maintenance quotation data of the candidate maintenance object is used as the candidate maintenance data.

7. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Obtaining a target comprehensive score of a preset repair object and a target repair object of the claim order; Based on the pre-trained claim scoring model, a claim scoring is performed on the preset maintenance object to obtain a predicted comprehensive score; Calculating the difference between the predicted comprehensive score and the target comprehensive score to obtain a target score difference; Performing order matching detection on the claim order based on the preset score difference threshold data and the target score difference value to obtain an order matching status, where the order matching status is used to indicate the matching degree between the preset maintenance object and the claim order; If the order matching status is a mismatching status, an abnormal prompt message is returned to the claim settlement and repair platform.

8. An object sorting device based on claim settlement orders, characterized in that: The device comprises: An order acquisition module, used to acquire a claim settlement order for a target repair item; wherein the claim settlement order includes item location data and repair item data of the target repair item, and the repair item data includes candidate repair items; A maintenance data acquisition module, configured to acquire candidate maintenance data of a candidate maintenance object based on the claim settlement order; wherein the candidate maintenance data includes candidate location data, object scoring data, candidate maintenance quotation data, and historical maintenance quotation data of the candidate maintenance object, the candidate maintenance quotation data being used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the target maintenance object, and the historical maintenance quotation data being used to characterize the maintenance quotation of the candidate maintenance object for the candidate maintenance items of the historical maintenance object; A distance detection module, used to perform distance detection based on the object position data and the candidate position data to obtain candidate distance data; A change evaluation module, used to evaluate the price change based on the historical maintenance price data and the candidate maintenance price data, and obtain maintenance price change data; A selection module is used to select the candidate maintenance objects based on the maintenance quotation change data, the candidate distance data, the object scoring data and the candidate maintenance quotation data, and determine a target maintenance object, wherein the target maintenance object is used to indicate an object that repairs the target maintenance item.

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

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

Images