Recommendation method and device based on artificial intelligence, computer equipment and storage medium
By using artificial intelligence technology in the auto insurance claims recommendation system, identifying the maintenance intentions of car owners, screening and sorting the repair shops, the problem of lack of personalization and intelligence recommendations in the existing system is solved, and the accuracy of the repair shop recommendations is improved and Intelligence.
Patent Information
- Application Number
- CN202411170614.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-12-03
AI Technical Summary
The existing auto insurance claims recommendation system lacks personalization and intelligence, and cannot fully consider the personalized needs and preferences of car owners, resulting in low accuracy of the repair shop recommendations.
Using an artificial intelligence-based recommendation method, we receive maintenance requests from the car owner, call the intent analysis model for intent identification, filter the matching repair shop, calculate scores based on the recommendation algorithm, filter and sort, and generate a personalized recommendation list.
It improves the accuracy and intelligence of the repair shop recommendations, can better meet the personalized needs of car owners and improve data accuracy.
Smart Images

Figure CN119066241A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence development technology and the field of financial technology, and in particular to artificial intelligence-based recommendation methods, devices, computer equipment and storage media. Background Art
[0002] Car insurance claims are one of the important businesses of insurance companies, involving damage assessment, compensation, repair and other aspects of vehicle damage. In the vehicle repair phase, insurance companies usually recommend some designated or cooperative repair shops to car owners based on the wishes and cooperative relationship of the car owners, so that car owners can quickly find a suitable repair location.
[0003] However, the current car insurance claim recommendation of nearby vehicle repair shops lacks personalization and intelligence. The current recommendation system usually recommends repair shops to car owners based on pre-set recommendation rules. Since the recommendation rules are fixed, the repair shop recommendations based on the recommendation rules are also fixed, and cannot fully consider the personalized needs and preferences of car owners, resulting in low accuracy of repair shop recommendations. Summary of the invention
[0004] The purpose of the embodiments of the present application is to propose a recommendation method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problem that the existing recommendation system usually recommends repair shops to car owners based on pre-set recommendation rules. Since the recommendation rules are fixed, the repair shop recommendations based on the recommendation rules are also fixed, and cannot fully consider the personalized needs and preferences of car owners, resulting in low accuracy of repair shop recommendations.
[0005] In order to solve the above technical problems, the present application embodiment provides a recommendation method based on artificial intelligence, which adopts the following technical solutions:
[0006] Receiving a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information;
[0007] Calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information;
[0008] Screening out candidate repair shops matching the target intent from a preset database;
[0009] Calculating scores for the candidate repair shops based on a preset recommendation algorithm to obtain scores for each of the candidate repair shops;
[0010] Screening the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop;
[0011] Sorting the target repair shops based on preset rules to obtain a corresponding recommendation list;
[0012] The recommendation list is pushed to the target vehicle owner.
[0013] Furthermore, the step of calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information specifically includes:
[0014] Performing word segmentation processing and irrelevant word filtering processing on the maintenance information to obtain a corresponding word set;
[0015] Determine the mutual information corresponding to each word included in the word set to obtain a mutual information vector for each word;
[0016] Based on the mutual information vector, generating a mutual information matrix corresponding to the maintenance information;
[0017] Performing identification processing on the mutual information matrix based on the intention analysis model, and outputting the confidence of each intention label corresponding to the maintenance information;
[0018] A designated intention label whose confidence is greater than a preset confidence threshold is obtained from the intention labels, and the designated intention label is used as the target intention of the maintenance information.
[0019] Furthermore, the step of selecting candidate repair shops matching the target intent from a preset database specifically includes:
[0020] calling the database;
[0021] Performing query processing on the database based on the target intent to filter out a first repair shop matching the target intent from the database;
[0022] The first repair shop is used as the candidate repair shop.
[0023] Furthermore, the step of calculating the scores of the candidate repair shops based on a preset recommendation algorithm specifically includes:
[0024] Acquire distance data, price data, quality data, service data, and reputation data of a second repair shop; wherein the second repair shop is any one of all the candidate repair shops;
[0025] determining a first weight corresponding to the distance data, a second weight corresponding to the price data, a third weight corresponding to the quality data, a fourth weight corresponding to the service data, and a fifth weight corresponding to the reputation data;
[0026] Based on the first weight, the second weight, the third weight, the fourth weight and the fifth weight, a preset calculation formula is called to calculate and process the distance data, the price data, the quality data, the service data and the reputation data to obtain a corresponding calculation result;
[0027] The calculation result is used as the score of the second repair shop.
[0028] Furthermore, the step of screening the candidate repair shops based on the scores of the candidate repair shops to obtain the target repair shop specifically includes:
[0029] Get the preset score threshold;
[0030] Filtering out a designated score greater than the score threshold from all the scores;
[0031] Selecting a third repair shop corresponding to the specified score from all the candidate repair shops;
[0032] The third repair shop is used as the target repair shop.
[0033] Furthermore, the step of sorting the target repair shops based on preset rules to obtain a corresponding recommendation list specifically includes:
[0034] Arrange all the target repair shops in descending order according to their scores to obtain corresponding designated data;
[0035] Filling the specified data into a preset initial list to obtain a specified list;
[0036] The designated list is used as the recommendation list.
[0037] Furthermore, after the step of pushing the recommendation list to the target car owner, the method further includes:
[0038] receiving feedback information returned by the target vehicle owner regarding the recommendation list;
[0039] Adjusting the recommendation list based on the feedback information to obtain a target recommendation list;
[0040] The target recommendation list is returned to the target vehicle owner.
[0041] In order to solve the above technical problems, the embodiment of the present application further provides a recommendation device based on artificial intelligence, which adopts the following technical solution:
[0042] A first receiving module is used to receive a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information;
[0043] An identification module, used to call a preset intention analysis model to perform intention identification on the maintenance information to obtain a target intention corresponding to the maintenance information;
[0044] A first screening module is used to screen out candidate repair shops matching the target intention from a preset database;
[0045] A calculation module, used to calculate the scores of the candidate repair shops based on a preset recommendation algorithm to obtain the scores of each candidate repair shop;
[0046] A second screening module, used for screening the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop;
[0047] A sorting module, used to sort the target repair shops based on preset rules to obtain a corresponding recommendation list;
[0048] A push module is used to push the recommendation list to the target car owner.
[0049] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:
[0050] Receiving a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information;
[0051] Calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information;
[0052] Screening out candidate repair shops matching the target intent from a preset database;
[0053] Calculating scores for the candidate repair shops based on a preset recommendation algorithm to obtain scores for each of the candidate repair shops;
[0054] Screening the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop;
[0055] Sorting the target repair shops based on preset rules to obtain a corresponding recommendation list;
[0056] The recommendation list is pushed to the target vehicle owner.
[0057] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:
[0058] Receiving a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information;
[0059] Calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information;
[0060] Screening out candidate repair shops matching the target intent from a preset database;
[0061] Calculating scores for the candidate repair shops based on a preset recommendation algorithm to obtain scores for each of the candidate repair shops;
[0062] Screening the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop;
[0063] Sorting the target repair shops based on preset rules to obtain a corresponding recommendation list;
[0064] The recommendation list is pushed to the target vehicle owner.
[0065] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0066] After receiving the vehicle maintenance request input by the target vehicle owner, the embodiment of the present application performs intent recognition on the maintenance information by calling a preset intent analysis model to obtain a target intent corresponding to the maintenance information; then, candidate repair shops matching the target intent are screened out from a preset database; then, scores are calculated for the candidate repair shops based on a preset recommendation algorithm to obtain a score for each candidate repair shop; subsequently, the candidate repair shops are screened based on the scores of each candidate repair shop to obtain a target repair shop; further, the target repair shops are sorted based on preset rules to obtain a corresponding recommendation list; and finally, the recommendation list is pushed to the target vehicle owner. The embodiment of the present application uses an intent analysis model to identify the intent of the vehicle maintenance request input by the target vehicle owner, obtain the target intent corresponding to the maintenance information, and screen out candidate repair shops matching the target intent from a database. Subsequently, the candidate repair shops are screened based on a preset recommendation algorithm to obtain the target repair shops, and a recommendation list obtained after sorting the target repair shops is pushed to the target vehicle owner, so as to push a recommendation list including the target repair shops that meets the personalized needs and preferences of the target vehicle owner to the target vehicle owner, thereby effectively improving the data accuracy of the target repair shops and facilitating improving the accuracy and intelligence of repair shop recommendations. BRIEF DESCRIPTION OF THE DRAWINGS
[0067] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0068] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;
[0069] Figure 2 A flowchart of an embodiment of an artificial intelligence-based recommendation method according to the present application;
[0070] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based recommendation device according to the present application;
[0071] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION
[0072] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.
[0073] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0074] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0075] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0076] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.
[0077] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.
[0078] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .
[0079] It should be noted that the artificial intelligence-based recommendation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based recommendation device is generally set in the server / terminal device.
[0080] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0081] Continue to refer Figure 2, showing a flowchart of an embodiment of an artificial intelligence-based recommendation method according to the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. The artificial intelligence-based recommendation method provided in the embodiment of the present application can be applied to any scenario where product recommendations are required, and the artificial intelligence-based recommendation method can be applied to products in these scenarios, for example, product recommendations in the financial insurance field. The artificial intelligence-based recommendation method comprises the following steps:
[0082] Step S201, receiving a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information.
[0083] In this embodiment, the electronic device (e.g. Figure 1 The server / terminal device shown in the figure) can obtain maintenance information through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi-Fi Band) connection, and other wireless connection methods currently known or to be developed in the future. Among them, the above maintenance information is information that represents the maintenance needs of the target car owner input by natural language, and the maintenance information at least includes information such as maintenance location, budget, time, etc.
[0084] Step S202: calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information.
[0085] In this embodiment, the above-mentioned intention analysis model is a pre-trained AI large model with intention recognition function. The model has large-scale parameters and deep structure, can learn general and professional knowledge from massive data, and adaptively adjust parameters according to input data. Among them, the above-mentioned calling of the preset intention analysis model to perform intent recognition on the maintenance information and obtain the specific implementation process of the target intention corresponding to the maintenance information will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.
[0086] Step S203, selecting candidate repair shops matching the target intent from a preset database.
[0087] In this embodiment, the specific implementation process of selecting candidate repair shops matching the target intent from a preset database will be described in further detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0088] Step S204: Calculate the scores of the candidate repair shops based on a preset recommendation algorithm to obtain the scores of the candidate repair shops.
[0089] In this embodiment, the specific implementation process of calculating the scores of the candidate repair shops based on the preset recommendation algorithm to obtain the scores of each candidate repair shop will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0090] Step S205: Screening the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop.
[0091] In this embodiment, the specific implementation process of screening the candidate repair shops based on the scores of each candidate repair shop to obtain the target repair shop will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0092] Step S206: sorting the target repair shops based on preset rules to obtain a corresponding recommendation list.
[0093] In this embodiment, the specific implementation process of sorting the target repair shops based on preset rules to obtain the corresponding recommendation list will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0094] Step S207: Push the recommendation list to the target vehicle owner.
[0095] In this embodiment, the recommendation list can be generated in natural language and displayed to the target vehicle owner in natural language, and explanations and bases corresponding to the recommendation list can be provided at the same time.
[0096] After receiving a vehicle maintenance request input by a target vehicle owner, the present application performs intent recognition on the maintenance information by calling a preset intent analysis model to obtain a target intent corresponding to the maintenance information; then, candidate repair shops matching the target intent are screened out from a preset database; then, scores are calculated for the candidate repair shops based on a preset recommendation algorithm to obtain a score for each candidate repair shop; subsequently, the candidate repair shops are screened based on the scores of each candidate repair shop to obtain a target repair shop; further, the target repair shops are sorted based on preset rules to obtain a corresponding recommendation list; and finally, the recommendation list is pushed to the target vehicle owner. The present application uses an intent analysis model to identify the intent of a vehicle maintenance request input by a target vehicle owner, obtains a target intent corresponding to the maintenance information, and screens out candidate repair shops that match the target intent from a database. Subsequently, the candidate repair shops are screened based on a preset recommendation algorithm to obtain a target repair shop, and a recommendation list obtained after sorting the target repair shops is pushed to the target vehicle owner, so as to push a recommendation list including the target repair shops that meets the personalized needs and preferences of the target vehicle owner to the target vehicle owner, thereby effectively improving the data accuracy of the target repair shops and facilitating improving the accuracy and intelligence of repair shop recommendations.
[0097] In some optional implementations, step S202 includes the following steps:
[0098] The maintenance information is processed by word segmentation and irrelevant word filtering to obtain a corresponding word set.
[0099] In this embodiment, the maintenance information can be segmented by calling a general segmentation tool to obtain a word set containing multiple words. There is no limitation on the selection of the above-mentioned segmentation tool, for example, the jieba segmentation tool can be used. In addition, the irrelevant word filtering process can be performed by matching and filtering the irrelevant words of the maintenance information after the segmentation process using a preset word table. The above-mentioned word table is a pre-constructed data table storing irrelevant words, such as modal particles, greeting words, and the like. Exemplarily, if the content of the maintenance information is "a vehicle repair shop near A with a budget less than B and meeting the conditions for car insurance claims", the words contained in the word set obtained after the segmentation process and irrelevant word filtering process of the maintenance information include: A, budget, B, car insurance claims conditions, and vehicle repair shop.
[0100] The mutual information corresponding to each word included in the word set is determined to obtain a mutual information vector for each word.
[0101] In this embodiment, the mutual information is used to characterize the degree of association between a word and an intent tag. By sorting multiple mutual information of the same word according to the preset order of the intent tags, the mutual information vector of the word can be obtained. There is no specific limitation on the selection of the sorting order, which can be set according to actual usage requirements.
[0102] Based on the mutual information vector, a mutual information matrix corresponding to the maintenance information is generated.
[0103] In this embodiment, the mutual information matrix is used to characterize the degree of association between the maintenance information and each intention label. Specifically, the mutual information vectors of each word can be combined according to the arrangement order of each word in the maintenance information to obtain the corresponding mutual information matrix.
[0104] The mutual information matrix is identified based on the intention analysis model, and the confidence of each intention label corresponding to the maintenance information is output.
[0105] In this embodiment, the mutual information matrix can be input into the intention analysis model, and the mutual information matrix can be identified and processed by the intention analysis model, so as to output the confidence of each intention label corresponding to the maintenance information.
[0106] A designated intention label whose confidence is greater than a preset confidence threshold is obtained from the intention labels, and the designated intention label is used as the target intention of the maintenance information.
[0107] In this embodiment, there is no specific limitation on the value of the above confidence threshold, which can be set according to actual intent analysis requirements.
[0108] The present application obtains a corresponding word set by performing word segmentation and irrelevant word filtering on the maintenance information; then determines the mutual information corresponding to each word contained in the word set to obtain the mutual information vector of each word; then generates a mutual information matrix corresponding to the maintenance information based on the mutual information vector; subsequently, performs recognition processing on the mutual information matrix based on the intention analysis model, and outputs the confidence of each intention label corresponding to the maintenance information; finally, obtains a designated intention label whose confidence is greater than a preset confidence threshold from the intention label, and uses the designated intention label as the target intention of the maintenance information. The present application obtains a corresponding word set by performing word segmentation and irrelevant word filtering on the maintenance information, then extracts the mutual information vector of the maintenance information, and then uses the intention analysis model to predict the intention label of the maintenance information based on the mutual information matrix, which can effectively improve the accuracy of the intention recognition of the maintenance information.
[0109] In some optional implementations of this embodiment, step S203 includes the following steps:
[0110] The database is called.
[0111] In this embodiment, the database is a pre-built database storing description information of various vehicle repair shops, wherein the description information of the vehicle repair shops at least includes location information, cost information, business hours information and other information of the vehicle repair shops.
[0112] The database is queried based on the target intent to filter out a first repair shop matching the target intent from the database.
[0113] In this embodiment, the target intent can be used to match the descriptive information of various vehicle repair shops stored in the database to filter out the specified descriptive information that matches the target intent from all the descriptive information, and then the specified vehicle repair shop corresponding to the specified descriptive information can be filtered out from the database and used as the first repair shop.
[0114] The first repair shop is used as the candidate repair shop.
[0115] The present application calls the database; then performs query processing on the database based on the target intent to screen out a first repair shop that matches the target intent from the database; and subsequently uses the first repair shop as the candidate repair shop. The present application can quickly and accurately screen out a first repair shop that matches the target intent and use it as the candidate repair shop by using a database, thereby improving the efficiency of obtaining candidate repair shops and ensuring the accuracy of the obtained candidate repair shops.
[0116] In some optional implementations, step S204 includes the following steps:
[0117] Obtain distance data, price data, quality data, service data, and reputation data of a second repair shop; wherein the second repair shop is any one of all the candidate repair shops.
[0118] In this embodiment, the identification information of the second repair shop can be obtained, and then based on the identification information, a data query is performed on a preset repair shop database to query the distance data, price data, quality data, service data and reputation data of the second repair shop. The repair shop database is a pre-built database storing distance data, price data, quality data, service data and reputation data of multiple repair shops.
[0119] A first weight corresponding to the distance data, a second weight corresponding to the price data, a third weight corresponding to the quality data, a fourth weight corresponding to the service data, and a fifth weight corresponding to the reputation data are determined.
[0120] In this embodiment, there is no specific limitation on the values of the first weight, the second weight, the third weight, the fourth weight and the fifth weight, and they can be set according to actual usage requirements.
[0121] Based on the first weight, the second weight, the third weight, the fourth weight and the fifth weight, a preset calculation formula is called to calculate and process the distance data, price data, quality data, service data and reputation data to obtain corresponding calculation results.
[0122] In this embodiment, the above calculation formula may specifically include: S=(a / u)+(b / v)+c*w+d*x+e*y, wherein S is a score, a is distance data, u is the first weight of distance data, b is price data, v is the second weight of price data, c is quality data, w is the third weight of quality data, d is service data, x is the fourth weight of service data, e is reputation data, and y is the fifth weight of reputation data.
[0123] The calculation result is used as the score of the second repair shop.
[0124] The present application obtains the distance data, price data, quality data, service data and reputation data of the second repair shop; then determines the first weight corresponding to the distance data, the second weight corresponding to the price data, the third weight corresponding to the quality data, the fourth weight corresponding to the service data, and the fifth weight corresponding to the reputation data; then based on the first weight, the second weight, the third weight, the fourth weight and the fifth weight, calls the preset calculation formula to calculate and process the distance data, price data, quality data, service data and reputation data to obtain the corresponding calculation result; and subsequently uses the calculation result as the score of the second repair shop. The present application obtains the distance data, price data, quality data, service data and reputation data of the second repair shop, and then based on the first weight corresponding to the distance data, the second weight corresponding to the price data, the third weight corresponding to the quality data, the fourth weight corresponding to the service data, and the fifth weight corresponding to the reputation data, calls the preset calculation formula to calculate and process the data, so as to realize the rapid and accurate generation of the scores of the candidate repair shops, improve the processing efficiency of the score calculation for the candidate repair shops, and ensure the data accuracy of the scores of the obtained candidate repair shops.
[0125] In some optional implementations, step S205 includes the following steps:
[0126] Get the preset score threshold.
[0127] In this embodiment, there is no specific limitation on the value of the score threshold, which can be set according to actual usage requirements.
[0128] A designated score greater than the score threshold is screened out from all the scores.
[0129] In this embodiment, all the scores may be numerically compared with the score threshold, and a designated score greater than the score threshold may be screened out from all the scores according to the numerical comparison result.
[0130] A third repair shop corresponding to the designated score is selected from all the candidate repair shops.
[0131] In this embodiment, the third repair shop is a repair shop that has a matching relationship with the designated score among all the candidate repair shops.
[0132] The third repair shop is used as the target repair shop.
[0133] The present application obtains a preset score threshold; then selects a designated score greater than the score threshold from all the scores; then selects a third repair shop corresponding to the designated score from all the candidate repair shops; and subsequently uses the third repair shop as the target repair shop. The present application selects a designated score greater than the preset score threshold from all the scores, and then uses the third repair shop corresponding to the designated score among all the candidate repair shops as the final target repair shop. Since the target repair shop is the repair shop with the highest score and the highest comprehensive evaluation among all the candidate repair shops, the subsequent push of the target repair shop to the target car owner can effectively meet the personalized needs and preferences of the target car owner, effectively improves the data accuracy of the target repair shop, and is conducive to improving the accuracy and intelligence of the repair shop recommendation.
[0134] In some optional implementations of this embodiment, step S206 includes the following steps:
[0135] All the target repair shops are arranged in descending order according to their scores to obtain corresponding designated data.
[0136] In this embodiment, the scores of the target repair shops may be obtained, and then the target repair shops may be arranged in descending order according to their scores to obtain corresponding sorting data, which may be used as the designated data.
[0137] The designated data is filled into a preset initial list to obtain a designated list.
[0138] In this embodiment, the initial list is a list template constructed according to the business needs of content recommendation, and the content setting of the processing list is not limited. The designated list can be obtained by determining the filling position corresponding to the designated data in the initial list and then filling the designated data into the filling position in the preset initial list.
[0139] The designated list is used as the recommendation list.
[0140] The present application arranges all the target repair shops in descending order according to their scores to obtain corresponding designated data; then fills the designated data into a preset initial list to obtain a designated list; and subsequently uses the designated list as the recommendation list. The present application arranges all the target repair shops in descending order according to their scores to obtain corresponding designated data; then fills the designated data into a preset initial list to complete the construction of the recommendation list, thereby improving the generation efficiency and intelligence of the recommendation list. In addition, by recommending the target repair shops to the target car owner in the form of a recommendation list, it is beneficial for the target car owner to clearly understand the recommendation priority of each target repair shop based on the recommendation list, which is beneficial to improving the user experience of the target car owner.
[0141] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:
[0142] Receive feedback information returned by the target vehicle owner regarding the recommendation list.
[0143] In this embodiment, after the recommendation list is pushed to the target car owner, the target car owner can also propose and return feedback information on the recommendation list according to his own needs. The feedback information may include selection, modification, rejection and other information.
[0144] The recommendation list is adjusted based on the feedback information to obtain a target recommendation list.
[0145] In this embodiment, the feedback information can be understood and processed in natural language, and then the original recommendation list can be flexibly adjusted and screened according to the real-time needs of the target car owner, thereby obtaining a target recommendation list. The adjustment process may include confirmation, adjustment, re-recommendation and other processes.
[0146] The target recommendation list is returned to the target vehicle owner.
[0147] In this embodiment, the current recommendation system is usually based on a fixed form or voice input, which cannot support the car owner to raise complex queries or feedback in natural language, nor can it be flexibly adjusted and screened according to the real-time needs of the car owner.
[0148] This application receives feedback information on the recommendation list returned by the target car owner; then adjusts and processes the recommendation list based on the feedback information to obtain a target recommendation list; and subsequently returns the target recommendation list to the target car owner. This application improves the interactivity and flexibility of repair shop recommendations, and can intelligently and flexibly adjust and filter the original recommendation list to match the real-time needs of the target car owner based on the feedback information on the recommendation list returned by the user, thereby obtaining a target recommendation list, effectively improving the generation intelligence and accuracy of the target recommendation list and improving the user experience.
[0149] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0150] It should be emphasized that in order to further ensure the privacy and security of the above recommendation list, the above recommendation list can also be stored in a node of a blockchain.
[0151] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.
[0152] 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.
[0153] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.
[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0155] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0156] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a recommendation device based on artificial intelligence, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0157] like Figure 3 As shown, the artificial intelligence-based recommendation device 300 described in this embodiment includes: a first receiving module 301, an identification module 302, a first screening module 303, a calculation module 304, a second screening module 305, a sorting module 306 and a push module 307. Among them:
[0158] The first receiving module 301 is used to receive a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information;
[0159] The recognition module 302 is used to call a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information;
[0160] A first screening module 303 is used to screen candidate repair shops matching the target intent from a preset database;
[0161] A calculation module 304 is used to calculate the scores of the candidate repair shops based on a preset recommendation algorithm to obtain the scores of each candidate repair shop;
[0162] A second screening module 305 is used to screen the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop;
[0163] A sorting module 306 is used to sort the target repair shops based on preset rules to obtain a corresponding recommendation list;
[0164] The push module 307 is used to push the recommendation list to the target car owner.
[0165] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and are not described in detail here.
[0166] In some optional implementations of this embodiment, the identification module 302 includes:
[0167] A word segmentation submodule, used for performing word segmentation processing and irrelevant word filtering processing on the maintenance information to obtain a corresponding word set;
[0168] A first determination submodule is used to determine the mutual information corresponding to each word included in the word set to obtain a mutual information vector for each word;
[0169] A generating submodule, used for generating a mutual information matrix corresponding to the maintenance information based on the mutual information vector;
[0170] A processing submodule, configured to perform identification processing on the mutual information matrix based on the intention analysis model, and output the confidence of each intention label corresponding to the maintenance information;
[0171] The second determination submodule is used to obtain a designated intention label whose confidence is greater than a preset confidence threshold from the intention label, and use the designated intention label as the target intention of the maintenance information.
[0172] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and are not described in detail here.
[0173] In some optional implementations of this embodiment, the first screening module 303 includes:
[0174] A calling submodule, used for calling the database;
[0175] A query submodule, configured to perform query processing on the database based on the target intent, so as to screen out a first repair shop matching the target intent from the database;
[0176] The third determining submodule is configured to select the first repair shop as the candidate repair shop.
[0177] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and will not be repeated here.
[0178] In some optional implementations of this embodiment, the calculation module 304 includes:
[0179] A first acquisition submodule is used to acquire distance data, price data, quality data, service data and reputation data of a second repair shop; wherein the second repair shop is any one of all the candidate repair shops;
[0180] a third determination submodule, configured to determine a first weight corresponding to the distance data, a second weight corresponding to the price data, a third weight corresponding to the quality data, a fourth weight corresponding to the service data, and a fifth weight corresponding to the reputation data;
[0181] a calculation submodule, configured to calculate and process the distance data, price data, quality data, service data, and reputation data based on the first weight, the second weight, the third weight, the fourth weight, and the fifth weight by calling a preset calculation formula to obtain a corresponding calculation result;
[0182] The fourth determining submodule is configured to use the calculation result as the score of the second repair shop.
[0183] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and are not described in detail here.
[0184] In some optional implementations of this embodiment, the second screening module 305 includes:
[0185] The second acquisition submodule is used to obtain a preset score threshold;
[0186] A first screening submodule, configured to screen out a designated score greater than the score threshold from all the scores;
[0187] A second screening submodule, used for screening out a third repair shop corresponding to the specified score from all the candidate repair shops;
[0188] The fifth determining submodule is configured to select the third repair shop as the target repair shop.
[0189] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and are not described in detail here.
[0190] In some optional implementations of this embodiment, the sorting module 306 includes:
[0191] A sorting submodule, used to sort all the target repair shops in descending order according to their scores to obtain corresponding designated data;
[0192] An input submodule, used for filling the specified data into a preset initial list to obtain a specified list;
[0193] The sixth determining submodule is configured to use the designated list as the recommendation list.
[0194] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and are not described in detail here.
[0195] In some optional implementations of this embodiment, the recommendation device based on artificial intelligence further includes:
[0196] A second receiving module, configured to receive feedback information returned by the target vehicle owner regarding the recommendation list;
[0197] An adjustment module, configured to adjust the recommendation list based on the feedback information to obtain a target recommendation list;
[0198] The return module is used to return the target recommendation list to the target vehicle owner.
[0199] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based recommendation method in the aforementioned implementation mode, and are not described in detail here.
[0200] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.
[0201] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.
[0202] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.
[0203] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the recommendation method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.
[0204] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based recommendation method.
[0205] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.
[0206] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0207] In an embodiment of the present application, after receiving a vehicle maintenance request input by a target vehicle owner, the maintenance information is subjected to intent recognition by calling a preset intent analysis model to obtain a target intent corresponding to the maintenance information; then, candidate repair shops matching the target intent are screened out from a preset database; then, scores of the candidate repair shops are calculated based on a preset recommendation algorithm to obtain a score for each candidate repair shop; subsequently, the candidate repair shops are screened based on the scores of each candidate repair shop to obtain a target repair shop; further, the target repair shops are sorted based on preset rules to obtain a corresponding recommendation list; and finally, the recommendation list is pushed to the target vehicle owner. The embodiment of the present application uses an intent analysis model to identify the intent of the vehicle maintenance request input by the target vehicle owner, obtain the target intent corresponding to the maintenance information, and screen out candidate repair shops matching the target intent from a database. Subsequently, the candidate repair shops are screened based on a preset recommendation algorithm to obtain the target repair shops, and a recommendation list obtained after sorting the target repair shops is pushed to the target vehicle owner, so as to push a recommendation list including the target repair shops that meets the personalized needs and preferences of the target vehicle owner to the target vehicle owner, thereby effectively improving the data accuracy of the target repair shops and facilitating improving the accuracy and intelligence of repair shop recommendations.
[0208] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the artificial intelligence-based recommendation method as described above.
[0209] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0210] In an embodiment of the present application, after receiving a vehicle maintenance request input by a target vehicle owner, the maintenance information is subjected to intent recognition by calling a preset intent analysis model to obtain a target intent corresponding to the maintenance information; then, candidate repair shops matching the target intent are screened out from a preset database; then, scores of the candidate repair shops are calculated based on a preset recommendation algorithm to obtain a score for each candidate repair shop; subsequently, the candidate repair shops are screened based on the scores of each candidate repair shop to obtain a target repair shop; further, the target repair shops are sorted based on preset rules to obtain a corresponding recommendation list; and finally, the recommendation list is pushed to the target vehicle owner. The embodiment of the present application uses an intent analysis model to identify the intent of the vehicle maintenance request input by the target vehicle owner, obtain the target intent corresponding to the maintenance information, and screen out candidate repair shops matching the target intent from a database. Subsequently, the candidate repair shops are screened based on a preset recommendation algorithm to obtain the target repair shops, and a recommendation list obtained after sorting the target repair shops is pushed to the target vehicle owner, so as to push a recommendation list including the target repair shops that meets the personalized needs and preferences of the target vehicle owner to the target vehicle owner, thereby effectively improving the data accuracy of the target repair shops and facilitating improving the accuracy and intelligence of repair shop recommendations.
[0211] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0212] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.
Claims
1. A recommendation method based on artificial intelligence, It is characterized in that The steps include: Receiving a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information; Calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information; Screening out candidate repair shops matching the target intent from a preset database; Calculating scores for the candidate repair shops based on a preset recommendation algorithm to obtain scores for each of the candidate repair shops; Screening the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop; Sorting the target repair shops based on preset rules to obtain a corresponding recommendation list; The recommendation list is pushed to the target vehicle owner.
2. The artificial intelligence-based recommendation method according to claim 1, It is characterized in that The step of calling a preset intention analysis model to perform intention recognition on the maintenance information to obtain a target intention corresponding to the maintenance information specifically includes: Performing word segmentation processing and irrelevant word filtering processing on the maintenance information to obtain a corresponding word set; Determine the mutual information corresponding to each word included in the word set to obtain a mutual information vector for each word; Based on the mutual information vector, generating a mutual information matrix corresponding to the maintenance information; Performing identification processing on the mutual information matrix based on the intention analysis model, and outputting the confidence of each intention label corresponding to the maintenance information; A designated intention label whose confidence is greater than a preset confidence threshold is obtained from the intention labels, and the designated intention label is used as the target intention of the maintenance information.
3. The artificial intelligence-based recommendation method according to claim 1, It is characterized in that The step of selecting candidate repair shops matching the target intention from a preset database specifically includes: calling the database; Performing query processing on the database based on the target intent to filter out a first repair shop matching the target intent from the database; The first repair shop is used as the candidate repair shop.
4. The artificial intelligence-based recommendation method according to claim 1, It is characterized in that The step of calculating the scores of the candidate repair shops based on a preset recommendation algorithm specifically includes: Acquire distance data, price data, quality data, service data, and reputation data of a second repair shop; wherein the second repair shop is any one of all the candidate repair shops; determining a first weight corresponding to the distance data, a second weight corresponding to the price data, a third weight corresponding to the quality data, a fourth weight corresponding to the service data, and a fifth weight corresponding to the reputation data; Based on the first weight, the second weight, the third weight, the fourth weight and the fifth weight, a preset calculation formula is called to calculate and process the distance data, the price data, the quality data, the service data and the reputation data to obtain a corresponding calculation result; The calculation result is used as the score of the second repair shop.
5. The artificial intelligence-based recommendation method according to claim 1, It is characterized in that The step of screening the candidate repair shops based on the scores of the candidate repair shops to obtain the target repair shop specifically includes: Get the preset score threshold; Filtering out a designated score greater than the score threshold from all the scores; Selecting a third repair shop corresponding to the specified score from all the candidate repair shops; The third repair shop is used as the target repair shop.
6. The artificial intelligence-based recommendation method according to claim 1, It is characterized in that The step of sorting the target repair shops based on preset rules to obtain a corresponding recommendation list specifically includes: Arrange all the target repair shops in descending order according to their scores to obtain corresponding designated data; Filling the specified data into a preset initial list to obtain a specified list; The designated list is used as the recommendation list.
7. The artificial intelligence-based recommendation method according to claim 1, It is characterized in that After the step of pushing the recommendation list to the target car owner, the method further includes: receiving feedback information returned by the target vehicle owner regarding the recommendation list; Adjusting the recommendation list based on the feedback information to obtain a target recommendation list; The target recommendation list is returned to the target vehicle owner.
8. A recommendation device based on artificial intelligence, It is characterized in that include: A first receiving module is used to receive a vehicle maintenance request input by a target vehicle owner; wherein the vehicle maintenance request carries maintenance information; An identification module, used to call a preset intention analysis model to perform intention identification on the maintenance information, and obtain a target intention corresponding to the maintenance information; A first screening module is used to screen out candidate repair shops matching the target intention from a preset database; A calculation module, used to calculate the scores of the candidate repair shops based on a preset recommendation algorithm to obtain the scores of each candidate repair shop; A second screening module, configured to screen the candidate repair shops based on the scores of the candidate repair shops to obtain a target repair shop; A sorting module, used to sort the target repair shops based on preset rules to obtain a corresponding recommendation list; A push module is used to push the recommendation list to the target car owner.
9. A computer device, It is characterized in that The invention comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the artificial intelligence-based recommendation method as claimed in any one of claims 1 to 7 when executing the computer-readable instructions.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the artificial intelligence-based recommendation method as described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Vehicle maintenance factory online recommendation method and device, equipment and storage medium
CN110390403A
Helmet, method and system for hairdressing
CN114102674A
Information recommendation method and device based on artificial intelligence, equipment and storage medium
CN116166858A
