Repair information determination method and device, equipment, storage medium and program product

Abstract

The invention provides a repair pushing information determination method and device, equipment, a storage medium and a program product. The method comprises the following steps: determining a first repair factory according to a fault location of a fault vehicle and fault vehicle information; determining a first repair score of the first repair plant based on the historical repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair plant; based on the first repair score of the first repair plant and a target score of the first repair plant for the fault vehicle, a second repair score of the first repair plant is determined, and the target score is obtained through historical repair feedback data and historical evaluation data of the first repair plant; and determining a target repair plant and a target recommendation sequence corresponding to the target repair plant in the first repair plant based on the numerical value of the second repair score of the first repair plant. According to the method provided by the invention, the accuracy of the second repair pushing information can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment, storage medium and program product for determining recommended repair information. Background Art

[0002] When a vehicle breaks down, the insurance company will generally provide recommended repair shops for the customer to choose from. Sometimes, if the customer is not satisfied with the recommended repair shop, the insurance company will make a second recommendation and provide a new recommended repair shop for the customer to choose from.

[0003] However, most of the repair shops recommended for the second time are still screened and recommended based on the profit perspective of the insurance company. For example, only the premium or the assessed loss amount is considered, and a repair shop different from the first recommended one is screened to obtain the second recommended repair shop. This process is not designed based on the actual needs of the customer, resulting in the second recommended repair shop still being unable to meet the needs of the customer and the repair recommendation failing. Summary of the invention

[0004] The present application provides a method, device, equipment, storage medium and program product for determining recommended repair information, so as to solve the problem of low accuracy of recommended repair information for a second recommended repair.

[0005] In a first aspect, the present application provides a method for determining recommended repair information, comprising:

[0006] Determining a first repair shop according to the fault location and the faulty vehicle information of the faulty vehicle, wherein the first repair shop is a repair shop with repair authority that meets the faulty vehicle information;

[0007] Determining a first recommended repair score of the first repair shop based on historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop, wherein the historical recommended repair feedback data is feedback data of historical recommended repair information of the faulty vehicle;

[0008] determining a second recommended repair score for the first repair shop based on a first recommended repair score for the first repair shop and a target score for the first repair shop for the faulty vehicle, wherein the target score is obtained by using the historical recommended repair feedback data and the historical evaluation data of the first repair shop;

[0009] Based on the numerical value of the second recommended repair score of the first repair shop, a target repair shop and a target recommendation sequence corresponding to the target repair shop are determined in the first repair shop.

[0010] In one achievable manner, determining the first repair shop according to the fault location and fault vehicle information of the faulty vehicle includes:

[0011] Determine a target area where the fault location of the faulty vehicle is located, and determine an initial first repair shop within the target area;

[0012] A repair shop having maintenance authority matching the faulty vehicle information is matched among the initial first repair shops to determine the first repair shop.

[0013] In an achievable manner, determining the first recommended repair score of the first repair shop based on the historical recommended repair feedback data of the faulty vehicle and the preset repair efficiency value of the first repair shop includes:

[0014] Determine, based on the historical recommended repair feedback data, a first weight coefficient of the first repair shop for the preset repair efficiency value and a second weight coefficient of the first repair shop for the damage assessment amount index value of the faulty vehicle;

[0015] Determine a first product between the first weight coefficient and the preset repair efficiency value, and determine a second product between the second weight coefficient and the damage assessment amount index value;

[0016] The sum of the first product and the second product is determined as the first inference score.

[0017] In an implementable manner, determining the first weight coefficient of the first repair shop for the preset repair efficiency value and the second weight coefficient of the first repair shop for the damage assessment amount index value of the faulty vehicle according to the historical recommended repair feedback data includes:

[0018] Inputting the historical recommended repair feedback data into a preset deep neural network to determine first feature data of the historical recommended repair feedback data;

[0019] Calculating a first characteristic distance between the first characteristic data and the repair efficiency characteristic data corresponding to the preset repair efficiency value, and calculating a second characteristic distance between the first characteristic data and the damage amount characteristic data corresponding to the damage amount index value;

[0020] The first weight coefficient is determined according to the first feature distance, and the second weight coefficient is determined according to the second feature distance.

[0021] In an achievable manner, before determining the second recommended repair score of the first repair shop based on the first recommended repair score of the first repair shop and the target score of the first repair shop for the faulty vehicle, the method further includes:

[0022] Determine the similarity value between the historical recommendation and repair feedback data and the historical evaluation data as a third weight coefficient;

[0023] The target score is determined as a product of the third weight coefficient and a first score of the first repair shop, where the first score is a satisfaction score of the first repair shop.

[0024] In an achievable manner, determining the second recommended repair score of the first repair shop based on the first recommended repair score of the first repair shop and the target score of the first repair shop for the faulty vehicle includes:

[0025] Determining a first sum value between the target score and a preset basic value;

[0026] The product of the first sum and the first inferred repair score is determined as the second inferred repair score.

[0027] In an implementable manner, there are multiple first repair shops; and determining a target repair shop and a target recommendation sequence corresponding to the target repair shop among the first repair shops based on the numerical values ​​of the second recommended repair scores of the first repair shops includes:

[0028] Arrange the first repair shops from large to small according to the corresponding second recommended repair scores to obtain a first sequence;

[0029] The first repair shop in the first sequence that is within a preset sequence range is determined as the target repair shop, and the target repair shops are arranged from large to small according to the numerical values ​​of the corresponding second recommended repair scores to obtain the target recommendation sequence.

[0030] In a second aspect, the present application provides a device for determining recommended repair information, including: a first repair shop determining module, for determining a first repair shop according to a fault location of a faulty vehicle and faulty vehicle information, wherein the first repair shop is a repair shop that has repair authority that meets the faulty vehicle information;

[0031] A first recommended repair score determination module is used to determine a first recommended repair score of the first repair shop based on historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop, wherein the historical recommended repair feedback data is feedback data of historical recommended repair information of the faulty vehicle;

[0032] A second recommended repair score determination module is used to determine a second recommended repair score of the first repair shop based on the first recommended repair score of the first repair shop and a target score of the first repair shop for the faulty vehicle, wherein the target score is obtained by using the historical recommended repair feedback data and the historical evaluation data of the first repair shop;

[0033] The recommended repair data acquisition module is used to determine a target repair shop and a target recommendation sequence corresponding to the target repair shop in the first repair shop based on the numerical value of the second recommended repair score of the first repair shop.

[0034] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory; the memory is used to store instructions; the processor is used to execute the instructions in the memory, so that the electronic device executes the method described in the first aspect.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0036] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0037] The method, device, equipment, storage medium and program product for determining recommended repair information provided by the present application predetermine a first repair shop based on the fault location and the faulty vehicle information. The first repair shop set can meet the faulty vehicle's requirement for the distance to the repair shop so that the vehicle can quickly reach the repair shop for repair; and meet the repair authority of the faulty vehicle and can adapt to the vehicle's fault scenario; at the same time, a second recommended repair score for the first repair shop is recalculated based on historical recommended repair feedback data, and the second recommended repair score can be adaptively adjusted with reference to the historical recommended repair feedback data. The calculated second recommended repair score refers to the feedback data of customers who are dissatisfied with the historical recommended repair information, so that the target repair shop obtained through the second recommended repair score is more in line with the customer's subjective needs when selecting a repair shop, thereby providing accurate second recommended repair information to customers and improving customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] Figure 1 This is an implementation scenario diagram shown for an exemplary embodiment;

[0040] Figure 2 A flowchart of a method for determining recommended repair information is shown as an exemplary embodiment;

[0041] Figure 3 A flowchart of a method for determining recommended repair information is shown as another exemplary embodiment;

[0042] Figure 4The structure diagram of a device for determining recommended repair information is shown as an exemplary embodiment;

[0043] Figure 5 The present invention is a block diagram of an electronic device showing an exemplary embodiment.

[0044] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0045] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0046] It should be noted that the faulty vehicle information, repair shop information, historical repair feedback data and other data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data that are understood and authorized by the relevant users or fully authorized by all parties, and the collection, use, processing, transmission, provision, disclosure and application of the relevant data comply with the laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and comply with the principles of legality, legitimacy and necessity.

[0047] The present embodiment provides a method, device, apparatus, storage medium and program product for determining recommended repair information, aiming to solve the problem that the recommended repair information of the second recommended repair cannot meet customer needs, resulting in failure of the second recommended repair.

[0048] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0049] The method for determining recommended repair information provided by the present application can be implemented in any electronic device with data processing capabilities, or in a recommended repair information determination system. It should be noted that the recommended repair information determination system can be deployed separately on an electronic device in any environment (for example, separately deployed on an edge server in an edge environment), or can be deployed entirely in a cloud environment, or can be deployed in a distributed manner in different environments.

[0050] For example, the repair information determination system can be logically divided into multiple parts, each with different functions. The various parts of the repair information determination system can be deployed in any two or three of the electronic device (located on the user side, such as the client), the edge environment, and the cloud environment. The edge environment is an environment that includes a collection of edge electronic devices that are close to the electronic device. The edge electronic devices include: edge servers, edge stations with computing power, etc. The various parts of the repair information determination system deployed in different environments or devices work together to realize the functions of the data processing platform.

[0051] It should be understood that this application does not make any restrictive division on which parts of the repair information determination system are deployed and in what specific environment. In actual application, it can be adaptively deployed according to the computing power of the electronic device, the resource availability of the edge environment and the cloud environment, or the specific application requirements.

[0052] like Figure 1 1 is an implementation scenario diagram showing an exemplary embodiment. The recommended repair information determination system corresponding to the implementation scenario includes a client 10 and a server 11. The client 10 and the server 11 are connected via network communication.

[0053] The execution subject of the method of the embodiment of the present application is the server 11, and the client 10 can receive the fault location and faulty vehicle information of the faulty vehicle. The client 10 sends the fault location and faulty vehicle information of the faulty vehicle to the server 11 through the network. The server 11 determines the recommended repair information, obtains the target repair shop set and the target recommended sequence, and can feed back the target repair shop set and the target recommended sequence to the client 10 through the network. The client 10 has a graphic user interface, and the target repair shop and the target recommended sequence can be displayed on the graphic user interface.

[0054] In some embodiments, after receiving the fault location and faulty vehicle information of the faulty vehicle, the server 11 determines a first repair shop according to the fault location and faulty vehicle information of the faulty vehicle, where the first repair shop is a repair shop that has maintenance authority in accordance with the faulty vehicle information; determines a first recommended repair score for the first repair shop based on historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop, where the historical recommended repair feedback data is feedback data on historical recommended repair information for the faulty vehicle; determines a second recommended repair score for the first repair shop based on the first recommended repair score of the first repair shop and a target score of the first repair shop for the faulty vehicle, where the target score is obtained through the historical recommended repair feedback data and the historical evaluation data of the first repair shop; determines a target repair shop and a target recommendation sequence corresponding to the target repair shop in the first repair shop based on the numerical value of the second recommended repair score of the first repair shop.

[0055] It is understandable that the repair information determination device can be set at Figure 1 In the server 11, but the example shown in this embodiment Figure 1 The implementation environment shown is only exemplary. In other embodiments, the method for determining recommended repair information may also be applied to other implementation environments, and the device for determining recommended repair information may also be set in other structures in other implementation environments, which is not specifically limited here.

[0056] In this embodiment, the client 10 is an electronic device on the user side, which can be a wired terminal with a visualization structure or a wireless terminal. In other embodiments, the terminal can be an electronic device with a visualization structure such as a mobile phone, a computer, a tablet, and a vehicle-mounted device.

[0057] The server 11 can be an edge environment and a cloud environment, such as a physical server, a server cluster, and a cloud server, etc., and no specific limitations are made here.

[0058] Figure 2 is a flowchart of a method for determining recommended repair information, shown in an exemplary embodiment, and applied to Figure 1 The server 11 in Figure 2 As shown, the method includes steps S210 to S270, which are described in detail as follows:

[0059] Step S210: determining a first repair shop according to the fault location and the faulty vehicle information of the faulty vehicle, wherein the first repair shop is a repair shop with maintenance authority in accordance with the faulty vehicle information.

[0060] In some embodiments, after a faulty vehicle is reported, the insurance company provides recommended repair information for the first time. The customer is not satisfied with the recommended repair information provided for the first time and provides feedback data. The feedback data is historical recommended repair feedback data. The recommended repair information provided for the first time is historical recommended repair information. After obtaining the historical recommended repair feedback data, step S210 is triggered to determine the recommended repair information for the second time, and the target repair shop and target recommendation sequence in step S270 are obtained. The target repair shop and target recommendation sequence are the recommended repair information provided to the customer for the second time.

[0061] In some embodiments, the recommended repair information determination device may be set in the terminal of the insured party. The insured party may input the fault location and faulty vehicle information in the terminal to complete the corresponding recommended repair information determination in the terminal of the insured party and the server corresponding to the terminal.

[0062] In some embodiments, the recommended repair information determination device may be set in the internal service equipment of the insurance company, and the corresponding recommended repair information is determined by inputting the fault location and faulty vehicle information in the internal service equipment and the corresponding server of the internal service equipment.

[0063] In some embodiments, the fault location may be obtained by manually entering information or by selecting location information in a map preset in the repair information determination system.

[0064] The fault location is the location of the faulty vehicle.

[0065] In some implementations, the faulty vehicle information may include one or more of the faulty vehicle's brand information, vehicle age information, vehicle insurance information, etc.

[0066] In some embodiments, the first repair shop is a repair shop with repair authority that meets the faulty vehicle information, that is, the first repair shop has repair authority for the corresponding brand of the faulty vehicle. Therefore, a target repair shop that meets customer needs and can repair the faulty vehicle can be determined in the first repair shop later.

[0067] In some embodiments, the first repair shop should be close to the fault location, so as to meet the fault location's demand for the repair shop location and facilitate the faulty vehicle to quickly arrive at the repair shop for repair.

[0068] In one embodiment, a target area where the fault location of the faulty vehicle is located is determined, and an initial first repair shop in the target area is determined; a repair shop with maintenance authority that meets the faulty vehicle information is matched among the initial first repair shops to determine the first repair shop.

[0069] In some embodiments, the target area can be the administrative area where the fault site is located, or it can be an area with the fault site as the center point and within a certain numerical range from the fault site. The certain numerical range from the fault site can be set according to empirical parameters and is not specifically limited here.

[0070] In some embodiments, the repair shop in the target area may be used as an alternative repair shop for screening of subsequent repair shops. In this case, the repair shop in the target area may be determined as the initial first repair shop.

[0071] In some embodiments, the initial first repair shop meets the distance requirement, but some repair shops may not have the authority to repair the faulty vehicle. Therefore, the repair shop with the repair authority that meets the faulty vehicle information is matched among the initial first repair shops to determine the first repair shop.

[0072] The faulty vehicle information may include the brand of the faulty vehicle, and the repair shop that has the repair authority corresponding to the faulty vehicle information is the repair shop that has the repair authority for the brand of the faulty vehicle.

[0073] In some embodiments, the number of the first repair shop set should meet a first preset value. If the first repair shop in the currently determined target area cannot meet the first preset value, the scope of the target area can be expanded. For example, when the current target area is the administrative area of ​​the fault location, the target area can be expanded to also include the administrative area closest to the current fault location; when the target area is an area within a certain numerical range from the fault location, the target area can be expanded to also include an area centered on the fault location and within another numerical range from the fault location. It can be understood that in a plane map, the distance value of any point in the second area from the fault location is greater than the distance value in the first area from the fault location.

[0074] Step S230: Determine a first recommended repair score of the first repair shop based on the historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop.

[0075] In some embodiments, the historical repair recommendation feedback data is feedback data on historical repair recommendation information of the faulty vehicle.

[0076] The historical recommended repair information is the first recommended repair information for the faulty vehicle, and the customer is not satisfied with the historical recommended repair information. The target repair shop and target recommendation sequence obtained subsequently are actually the second recommended repair data.

[0077] The historical recommended repair information may include historical repair shops and historical recommendation sequences. The historical recommended repair feedback data includes customer feedback on the historical recommended repair information, such as reasons for dissatisfaction, information about recommended repair shops that customers care about, etc. (such as the historical repair shop corresponding to the historical recommended repair information is far away, etc.).

[0078] In some embodiments, a first weight coefficient of the first repair shop for a preset repair efficiency value and a second weight coefficient of the first repair shop for a damage assessment amount index value of the faulty vehicle are determined based on historical recommended repair feedback data; a first product between the first weight coefficient and the preset repair efficiency value is determined, and a second product between the second weight coefficient and the damage assessment amount index value is determined; and the sum of the first product and the second product is determined as a first recommended repair score.

[0079] Step S250: Determine a second recommended repair score for the first repair shop based on the first recommended repair score for the first repair shop and the target score of the first repair shop for the faulty vehicle.

[0080] In some embodiments, the target score is obtained by using historical recommended repair feedback data and historical evaluation data of the first repair shop.

[0081] In some embodiments, the similarity value between the historical repair recommendation feedback data and the historical evaluation data is determined as the third weight coefficient; the product of the third weight coefficient and the first score of the first repair shop is determined as the target score, and the first score is the satisfaction score of the first repair shop.

[0082] In this embodiment, the third weight coefficient is the degree to which the customer of the faulty vehicle cares about the repair shop satisfaction score, and the third weight coefficient is used to adjust the degree of influence of the customer of the faulty vehicle on the first score in the second recommended repair score.

[0083] The first rating is a value between 0 and 1, indicating the historical customer's satisfaction with the repair service of the first repair shop, which can be obtained through questionnaires or other methods, or through the ratings given to the first repair shop by customers on relevant websites.

[0084] The historical evaluation data is the evaluation of the first repair shop by the historical customers of the first repair shop, which can be text data. The historical evaluation data can be obtained through the evaluation text of the first repair shop by the historical customers on the relevant website or the client.

[0085] In some embodiments, a first sum value between the target score and a preset basic value is determined; and a product of the first sum value and the first recommended score value is determined as a second recommended score value.

[0086] The preset basic value can be any value, such as 1, 5, 10, etc., and is not specifically limited here.

[0087] In some embodiments, the second correction score Y can be calculated by:

[0088] Y=y+(a+x 3 *CS)

[0089] Among them, y is the first recommended score, a is the preset basic value, and x 3 is the third weight coefficient, and CS is the first score.

[0090] Step S270: Based on the numerical value of the second recommended repair score of the first repair shop, a target repair shop and a target recommendation sequence corresponding to the target repair shop are determined in the first repair shop.

[0091] In some embodiments, there are multiple first repair shops.

[0092] In some embodiments, each first repair shop is arranged from large to small according to the numerical value of the corresponding second recommended repair score to obtain a first sequence; the first repair shop in the first sequence that is within a preset sequence range is determined as a target repair shop, and the target repair shop is arranged from large to small according to the numerical value of the corresponding second recommended repair score to obtain a target recommendation sequence.

[0093] It can be understood that the target repair shop and the target recommendation sequence are the data of the second repair recommendation to the customer corresponding to the faulty vehicle, and the historical repair recommendation information is the data of the first repair recommendation to the customer corresponding to the faulty vehicle. The target repair shop and the target recommendation sequence are the recommended repair information obtained by recalculating based on the feedback information from the customer regarding the historical recommended repair information, i.e., the historical recommended repair feedback data, when the historical recommended repair information is unsuccessful.

[0094] In this embodiment, according to the numerical value of the second recommended repair score of the first repair shop, the first repair shop with a higher score is selected as the target repair shop. The preset sequence range can be determined by empirical parameters. For example, if a certain number of target repair shops are required, the first repair shop in the first sequence that is located before the target repair shop is selected as the target repair shop. The sequence that is located before the target repair shop is the preset sequence range.

[0095] The target repair shops are also arranged from large to small according to the numerical values ​​of the corresponding second recommended repair scores to obtain a target recommendation sequence.

[0096] In some embodiments, the target repair shop and the target recommendation sequence are fed back to the customer. If the customer selects a repair shop from the target repair shops, the selection result is returned to the recommended repair information determination system, and the system triggers SMS for the selected repair shop and the customer.

[0097] In some embodiments, if there is still no repair shop that satisfies the customer in the target repair shop and the target recommendation sequence, the customer's preferred repair shop can still be selected by manually entering the selection, and the relevant repair SMS trigger can be directly executed for the repair shop selected by the customer.

[0098] In an embodiment of the present application, a method for determining recommended repair information is proposed, in which a first repair shop is pre-determined based on the fault location and the faulty vehicle information. The first repair shop set can meet the faulty vehicle's requirement for the distance to the repair shop so that the vehicle can quickly reach the repair shop for repair; and meet the repair authority of the faulty vehicle and can adapt to the vehicle's fault scenario; at the same time, a second recommended repair score of the first repair shop is recalculated based on historical recommended repair feedback data, and the second recommended repair score can be adaptively adjusted with reference to the historical recommended repair feedback data. The calculated second recommended repair score is more in line with the customer's subjective needs when selecting a repair shop, so that the target repair shop and target recommendation sequence that meet the customer's needs can be accurately obtained, so as to provide accurate second recommended repair information based on the historical recommended repair feedback data and improve customer satisfaction.

[0099] Figure 3 is a flowchart of a method for determining recommended repair information shown in another exemplary embodiment. Figure 3 As shown, Figure 2Step S230 includes steps S310 to S350, which are described in detail as follows:

[0100] Step S310: determining a first weight coefficient of the first repair shop for a preset repair efficiency value and a second weight coefficient of the first repair shop for a damage assessment amount index value of the faulty vehicle based on historical recommended repair feedback data.

[0101] In some embodiments, the first weight coefficient indicates the degree to which the customer of the faulty vehicle cares about the repair efficiency, and the second weight coefficient indicates the degree to which the customer of the faulty vehicle cares about the damage assessment amount index value.

[0102] In some embodiments, historical recommended repair feedback data is input into a preset deep neural network to determine first feature data of the historical recommended repair feedback data; a first feature distance between the first feature data and the repair efficiency feature data corresponding to a preset repair efficiency value is calculated, and a second feature distance between the first feature data and the damage amount feature data corresponding to the damage amount index value is calculated; a first weight coefficient is determined based on the first feature distance, and a second weight coefficient is determined based on the second feature distance.

[0103] In some embodiments, the repair efficiency characteristic data is characteristic data corresponding to preset feedback data related to the repair efficiency, which can be obtained by first acquiring feedback data related to the repair efficiency and inputting the feedback data related to the repair efficiency into a preset deep neural network, thereby obtaining the repair efficiency characteristic data.

[0104] Feedback data related to repair efficiency can be obtained by screening historical repair recommendation feedback data from other customers, such as through manual screening, or by inputting historical repair recommendation feedback data from other customers into a classification model to obtain data related to the repair efficiency category, and determine it as feedback data related to repair efficiency.

[0105] In some embodiments, the damage assessment amount characteristic data is characteristic data corresponding to preset feedback data related to the damage assessment amount. The damage assessment amount characteristic data can be obtained by first acquiring feedback data related to the damage assessment amount and inputting the feedback data related to the damage assessment amount into a preset deep neural network.

[0106] Feedback data related to the assessed damage amount can be obtained by screening historical feedback data on repair recommendations from other customers, such as through manual screening, or by inputting historical feedback data on repair recommendations from other customers into a classification model to obtain data related to the assessed damage amount category, and determine it as feedback data related to the assessed damage amount.

[0107] The preset deep neural network model is a pre-trained neural network model used to extract feature data.

[0108] In some embodiments, the smaller the value of the first characteristic distance, the more concerned the customers of the faulty vehicle are about the repair efficiency, and the corresponding first weight coefficient is larger; the smaller the second characteristic distance, the more concerned the customers of the faulty vehicle are about the damage assessment amount index value, and the corresponding second weight coefficient is larger.

[0109] In this way, the correspondence between the first characteristic distance and the first weight coefficient can be preset as a negative correlation between the first characteristic distance and the first weight coefficient, such as a linear function or a nonlinear function; the correspondence between the second characteristic distance and the second weight coefficient can be preset as a negative correlation between the second characteristic distance and the second weight coefficient, such as a linear function or a nonlinear function. Thus, the first weight coefficient is determined according to the first characteristic distance, and the second weight coefficient is determined according to the second characteristic distance.

[0110] In some embodiments, the first weight coefficient and the second weight coefficient are values ​​between 0 and 1, and the sum of the first weight coefficient and the second weight coefficient may be 1.

[0111] Step S330, determine a first product between the first weight coefficient and the preset repair efficiency value, and determine a second product between the second weight coefficient and the damage amount index value.

[0112] Step S350: Determine the sum of the first product and the second product as the first correction score.

[0113] In some embodiments, the first correction score y may be calculated in the following manner:

[0114] y=x 1 *D+x 2 *E

[0115] Among them, x 1 is the first weight coefficient, D is the preset repair efficiency value, E is the damage amount index value, x 2 is the second weight coefficient.

[0116] In some embodiments, the damage amount index value can be the damage amount value calculated by the insurance company, or it can be a value obtained by subtracting the damage amount value calculated by the insurance company from a preset basic value, both of which are related to the damage amount value calculated by the insurance company.

[0117] In some embodiments, the preset repair efficiency value represents the ability of the first repair shop to complete repair work within a unit time (such as one hour, one day, or one month), and can be set based on the repair time of each historical faulty vehicle by the first repair shop or the average level of each repair shop. For example, the number of vehicles that can be repaired by the first repair shop within a unit time is used as the preset repair efficiency value. The preset repair efficiency value may not be an integer.

[0118] In this embodiment, a method for calculating the first recommended repair score is proposed. When performing the second recommended repair, reference is made to the customer's feedback data regarding the dissatisfied first recommended repair data, that is, the historical recommended repair feedback data, and the customer's concern is determined in the historical recommended repair feedback data. The score of the first repair shop for the second recommended repair is calculated based on the historical recommended repair feedback data, so that a target repair shop that meets the customer's needs can be obtained.

[0119] Figure 4 4 is a structural diagram of a device for determining recommended repair information, which is shown in an exemplary embodiment. The device for determining recommended repair information 400 includes:

[0120] A first repair shop determining module 410 is used to determine a first repair shop according to the fault location of the faulty vehicle and the faulty vehicle information, wherein the first repair shop is a repair shop with maintenance authority that meets the faulty vehicle information;

[0121] A first recommended repair score determination module 430 is used to determine a first recommended repair score of the first repair shop based on historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop, wherein the historical recommended repair feedback data is feedback data of historical recommended repair information of the faulty vehicle;

[0122] A second recommended repair score determination module 450 is used to determine a second recommended repair score for the first repair shop based on the first recommended repair score of the first repair shop and a target score of the first repair shop for the faulty vehicle, wherein the target score is obtained by using historical recommended repair feedback data and historical evaluation data of the first repair shop;

[0123] The recommended repair data acquisition module 470 is used to determine a target repair shop and a target recommendation sequence corresponding to the target repair shop in the first repair shop based on the numerical value of the second recommended repair score of the first repair shop.

[0124] In one achievable manner, the first repair shop determination module includes:

[0125] An initial repair shop determining unit, used to determine a target area where a fault location of the faulty vehicle is located, and determine an initial first repair shop within the target area;

[0126] The first repair shop determining unit is used to match a repair shop with a repair authority that meets the faulty vehicle information in the initial first repair shop to determine the first repair shop.

[0127] In one possible implementation, the first recommendation and repair score determination module includes:

[0128] A weight determination unit, for determining a first weight coefficient of the first repair shop for a preset repair efficiency value and a second weight coefficient of the first repair shop for a damage assessment amount index value of the faulty vehicle according to historical recommended repair feedback data;

[0129] A product determination unit, used to determine a first product between a first weight coefficient and a preset repair efficiency value, and to determine a second product between a second weight coefficient and a damage assessment amount index value;

[0130] The first inference and correction score determination unit is used to determine the sum of the first product and the second product as the first inference and correction score.

[0131] In one possible implementation, the weight determination unit includes:

[0132] A feature extraction module is used to input the historical recommended repair feedback data into a preset deep neural network to determine the first feature data of the historical recommended repair feedback data;

[0133] The characteristic distance calculation section is used to calculate the first characteristic distance between the first characteristic data and the repair efficiency characteristic data corresponding to the preset repair efficiency value, and calculate the second characteristic distance between the first characteristic data and the damage amount characteristic data corresponding to the damage amount index value;

[0134] The weight determination section is used to determine a first weight coefficient according to a first characteristic distance, and to determine a second weight coefficient according to a second characteristic distance.

[0135] In one possible implementation, the device for determining recommended repair information further includes:

[0136] A third weight coefficient determination module, used to determine the similarity value between the historical recommendation and repair feedback data and the historical evaluation data as a third weight coefficient;

[0137] The target score determination module is used to determine the product of the third weight coefficient and the first score of the first repair shop as the target score, where the first score is the satisfaction score of the first repair shop.

[0138] In one possible implementation, the second recommendation and repair score determination module includes:

[0139] A first sum calculation unit, used to determine a first sum between a target score and a preset basic value;

[0140] The second inference and repair score determination unit is used to determine the product of the first sum and the first inference and repair score as the second inference and repair score.

[0141] In an implementable manner, there are multiple first repair shops; the recommended repair data acquisition module includes:

[0142] A sorting unit, used for arranging the first repair shops from large to small according to the values ​​of the corresponding second recommended repair scores to obtain a first sequence;

[0143] The recommended repair information determination unit is used to determine the first repair shop in the first sequence that is within the preset sequence range as the target repair shop, and arrange the target repair shops from large to small according to the numerical values ​​of the corresponding second recommended repair scores to obtain a target recommendation sequence.

[0144] The device for determining recommended repair information provided in this embodiment can be used to execute the above-mentioned method for determining recommended repair information. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0145] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 The electronic device 500 may include: a processor 51 and a memory 52, wherein the processor 51 and the memory 52 can communicate; illustratively, the processor 51 and the memory 52 communicate via a communication bus 53, the memory 52 is used to store instructions, and the processor 51 is used to call the instructions in the memory to execute the method for determining the recommended repair information shown in any of the above method embodiments.

[0146] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the present application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0147] The present application provides a computer-readable storage medium, on which computer-executable instructions are stored; when the computer-executable instructions are executed by a processor, they are used to implement a method for determining recommended repair information as in any of the above embodiments.

[0148] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned method for determining recommended repair information is implemented.

[0149] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0150] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining recommended repair information, characterized in that: include: Determining a first repair shop according to the fault location and the faulty vehicle information of the faulty vehicle, wherein the first repair shop is a repair shop with repair authority that meets the faulty vehicle information; Determining a first recommended repair score of the first repair shop based on historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop, wherein the historical recommended repair feedback data is feedback data of historical recommended repair information of the faulty vehicle; determining a second recommended repair score for the first repair shop based on a first recommended repair score for the first repair shop and a target score for the first repair shop for the faulty vehicle, wherein the target score is obtained by using the historical recommended repair feedback data and the historical evaluation data of the first repair shop; Based on the numerical value of the second recommended repair score of the first repair shop, a target repair shop and a target recommendation sequence corresponding to the target repair shop are determined in the first repair shop.

2. The method according to claim 1, characterized in that The step of determining the first repair shop according to the fault location and information of the faulty vehicle comprises: Determine a target area where the fault location of the faulty vehicle is located, and determine an initial first repair shop within the target area; A repair shop having maintenance authority matching the faulty vehicle information is matched among the initial first repair shops to determine the first repair shop.

3. The method according to claim 1, characterized in that The determining of the first recommended repair score of the first repair shop based on the historical recommended repair feedback data of the faulty vehicle and the preset repair efficiency value of the first repair shop comprises: Determine, based on the historical recommended repair feedback data, a first weight coefficient of the first repair shop for the preset repair efficiency value and a second weight coefficient of the first repair shop for the damage assessment amount index value of the faulty vehicle; Determine a first product between the first weight coefficient and the preset repair efficiency value, and determine a second product between the second weight coefficient and the damage assessment amount index value; The sum of the first product and the second product is determined as the first inference score.

4. The method according to claim 3, characterized in that The determining, based on the historical recommended repair feedback data, a first weight coefficient of the first repair shop for the preset repair efficiency value and a second weight coefficient of the first repair shop for the damage assessment amount index value of the faulty vehicle includes: Inputting the historical recommended repair feedback data into a preset deep neural network to determine first feature data of the historical recommended repair feedback data; Calculating a first characteristic distance between the first characteristic data and the repair efficiency characteristic data corresponding to the preset repair efficiency value, and calculating a second characteristic distance between the first characteristic data and the damage amount characteristic data corresponding to the damage amount index value; The first weight coefficient is determined according to the first feature distance, and the second weight coefficient is determined according to the second feature distance.

5. The method according to any one of claims 1 to 4, characterized in that: Before determining a second recommended repair score of the first repair shop based on the first recommended repair score of the first repair shop and the target score of the first repair shop for the faulty vehicle, the method further includes: Determine the similarity value between the historical recommendation and repair feedback data and the historical evaluation data as a third weight coefficient; The target score is determined as a product of the third weight coefficient and a first score of the first repair shop, where the first score is a satisfaction score of the first repair shop.

6. The method according to any one of claims 1 to 4, characterized in that: The determining, based on the first recommended repair score of the first repair shop and the target score of the first repair shop for the faulty vehicle, a second recommended repair score of the first repair shop comprises: Determining a first sum value between the target score and a preset basic value; The product of the first sum and the first inferred repair score is determined as the second inferred repair score.

7. The method according to claim 1, characterized in that The number of the first repair shops is multiple; and the determining of a target repair shop and a target recommendation sequence corresponding to the target repair shop in the first repair shop based on the numerical value of the second recommended repair score of the first repair shop includes: Arrange the first repair shops from large to small according to the values ​​of the corresponding second recommended repair scores to obtain a first sequence; The first repair shop in the first sequence that is within a preset sequence range is determined as the target repair shop, and the target repair shops are arranged from large to small according to the numerical values ​​of the corresponding second recommended repair scores to obtain the target recommendation sequence.

8. A device for determining recommended repair information, characterized in that: include: A first repair shop determining module, used to determine a first repair shop according to the fault location and faulty vehicle information of the faulty vehicle, wherein the first repair shop is a repair shop with maintenance authority that meets the faulty vehicle information; A first recommended repair score determination module is used to determine a first recommended repair score of the first repair shop based on historical recommended repair feedback data of the faulty vehicle and a preset repair efficiency value of the first repair shop, wherein the historical recommended repair feedback data is feedback data of historical recommended repair information of the faulty vehicle; A second recommended repair score determination module is used to determine a second recommended repair score of the first repair shop based on the first recommended repair score of the first repair shop and a target score of the first repair shop for the faulty vehicle, wherein the target score is obtained by using the historical recommended repair feedback data and the historical evaluation data of the first repair shop; The recommended repair data acquisition module is used to determine a target repair shop and a target recommendation sequence corresponding to the target repair shop in the first repair shop based on the numerical value of the second recommended repair score of the first repair shop.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory; the memory is used to store instructions; the processor is used to execute the instructions in the memory, so that the electronic device executes the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The method comprises a computer program, which implements the method according to any one of claims 1 to 7 when being executed by a processor.

Images