Behavior information recommendation method and device, equipment and medium

Abstract

The application provides a behavior information recommendation method and device, equipment and a medium. The method comprises the following steps: calculating the similarity between a target user and each user in a user set through the feature data of the target user; the user set comprises feature data and behavior data corresponding to a plurality of users; calculating the behavior score corresponding to each behavior data according to the similarity between the user and the target user in the user set and the preference score corresponding to each behavior data; and recommending behavior information to the target user according to the behavior score corresponding to the behavior data, so as to improve the timeliness of the user obtaining a maintenance scheme through the recommended behavior information.

Description

Technical Field

[0001] This application relates to the field of information recommendation technology, and in particular to a method, apparatus, device and medium for recommending behavioral information. Background Technology

[0002] The rapid development of the internet has brought many conveniences to people's lives, but it has also generated massive amounts of data. In recommendation scenarios, content that users are interested in can be provided based on this information. For example, when a vehicle malfunctions or operates abnormally, users always want to know the vehicle's condition as soon as possible, such as what malfunctions have occurred, the causes of the malfunctions, and solutions.

[0003] Currently, for specific product recommendations, users need to know the corresponding after-sales department to obtain the relevant recommendations. For example, when a vehicle malfunctions or operates abnormally, the owner needs to drive the vehicle to the after-sales department to obtain a repair plan. However, there is a lack of transparency regarding the parts that may need to be repaired for the owner, and the after-sales department cannot notify the owner in a timely manner. Summary of the Invention

[0004] This application provides a method, apparatus, device, and medium for recommending behavioral information, which improves the timeliness of users obtaining maintenance solutions by recommending behavioral information to users.

[0005] In a first aspect, a method for recommending behavioral information is provided, comprising: calculating the similarity between the target user and each user in a user set using feature data of the target user; the user set including feature data and behavioral data corresponding to multiple users respectively; calculating a behavioral score corresponding to each behavioral data based on the similarity between the users in the user set and the target user, and the preference scores of the users in the user set for each behavioral data respectively; and recommending behavioral information to the target user based on the behavioral scores corresponding to the behavioral data.

[0006] Preferably, the step of calculating the behavioral score corresponding to each behavioral data point based on the similarity between users in the user set and the target user, and the preference score corresponding to each behavioral data point for each user in the user set, includes:

[0007] The behavioral score for each behavioral data point is calculated using the following formula:

[0008]

[0009] Where, p j Let sim(u, U) be the behavior score of all users in the user set for the j-th behavior data. i Let w be the similarity between the target user and the i-th user in the user set. ijLet be the preference score of the i-th user in the user set for the j-th behavior data, and n be the number of users in the user set.

[0010] Preferably, the method further includes: obtaining the after-sales interval time in the behavioral data; and calculating the preference score for each user in the user set for each behavioral data based on the after-sales interval time in the behavioral data.

[0011] Preferably, the step of calculating the preference score for each user in the user set for each behavioral data point based on the after-sales interval time in the behavioral data includes:

[0012] The preference score for each behavioral data point is calculated using the following formula:

[0013] w ij =1 / (1+t) ij );

[0014] Among them, w ij Let t be the preference score of the i-th user in the user set corresponding to the j-th behavior data. ij The after-sales interval time is the time corresponding to the j-th behavior data of the i-th user in the user set.

[0015] Preferably, the after-sales interval is the time interval between the time of vehicle malfunction and the corresponding after-sales processing time.

[0016] Preferably, before calculating the behavior score corresponding to each behavior data based on the similarity between users in the user set and the target user, and the preference scores of users in the user set for each behavior data, the method further includes: identifying users in the user set whose similarity to the target user is greater than a preset value as candidate users; correspondingly, calculating the behavior score corresponding to each behavior data based on the similarity between users in the user set and the target user, and the preference scores of users in the user set for each behavior data, includes: calculating the behavior score corresponding to each behavior data based on the similarity between the candidate users and the target user, and the preference scores of the candidate users for each behavior data.

[0017] Preferably, the feature data includes: driving behavior feature data, vehicle location feature data, vehicle fault feature data, and vehicle usage feature data.

[0018] Secondly, a device for recommending behavioral information is provided, comprising: a first calculation module, configured to calculate the similarity between the target user and each user in a user set using feature data of the target user; the user set includes feature data and behavioral data corresponding to multiple users respectively; a second calculation module, configured to calculate a behavioral score corresponding to each behavioral data based on the similarity between the users in the user set and the target user, and the preference scores of the users in the user set for each behavioral data respectively; and a recommendation module, configured to recommend behavioral information to the target user based on the behavioral scores corresponding to the behavioral data.

[0019] Thirdly, an electronic device is provided, comprising: a processor and a memory for storing a computer program, the processor for calling and running the computer program stored in the memory, and performing the methods as described in the first aspect or its various implementations.

[0020] Fourthly, a computer-readable storage medium is provided for storing a computer program that causes a computer to perform the methods described in the first aspect or its various implementations.

[0021] Fifthly, a computer program product is provided, including computer program instructions that cause a computer to perform the methods as described in the first aspect or its various implementations.

[0022] Sixthly, a computer program is provided that causes a computer to perform the methods described in the first aspect or its various implementations.

[0023] The technical solution provided in this application first calculates the similarity between the target user and each user in a user set based on the target user's feature data. This user set includes feature data and behavioral data corresponding to multiple users. Then, based on the similarity between users in the user set and the target user, and the preference scores of users in the user set for each behavioral data point, a behavioral score is calculated for each behavioral data point. Finally, behavioral information is recommended to the target user based on the behavioral scores. Compared to existing technologies that require users to visit after-sales service departments to obtain repair solutions, this application's solution, by calculating the similarity between the target user and the user set, and the preference scores of users in the user set for each feature behavioral data point, can recommend corresponding behavioral information to the target user. Therefore, the behavioral information recommended by this application can improve the timeliness of users obtaining repair solutions. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 An application scenario diagram provided for an embodiment of this application;

[0026] Figure 2 A flowchart illustrating a method for recommending behavioral information provided in an embodiment of this application;

[0027] Figure 3 A flowchart illustrating another method for recommending behavioral information provided in this application embodiment;

[0028] Figure 4 A flowchart for calculating preference scores provided in this application embodiment;

[0029] Figure 5 Example diagram of behavior score calculation provided in the embodiments of this application;

[0030] Figure 6 A flowchart illustrating yet another method for recommending behavioral information provided in this application embodiment;

[0031] Figure 7 A schematic diagram of a behavior information recommendation device provided in an embodiment of this application;

[0032] Figure 8 This is a schematic block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0035] It should be understood that the technical solution of this application can be applied to the following scenarios, but is not limited to:

[0036] In some possible ways, Figure 1 An application scenario diagram provided for an embodiment of this application, such as... Figure 1 As shown, this application scenario may include electronic device 110 and network device 120. Electronic device 110 can establish a connection with network device 120 through a wired network or a wireless network.

[0037] For example, electronic device 110 may be a center console installed in a car, a mobile phone terminal associated with the car, or a terminal device such as a desktop computer, laptop computer, or tablet computer, but is not limited thereto. Network device 120 may be a terminal device or a server, but is not limited thereto.

[0038] also, Figure 1 An electronic device and a network device are given as examples, but in practice, other numbers of electronic devices and network devices may be included, and this application does not limit this.

[0039] In other possible implementations, the technical solution of this application may also be executed by the aforementioned electronic device 110, or by the aforementioned network device 120, and this application does not impose any restrictions on this.

[0040] After introducing the application scenarios of the embodiments of this application, the technical solution of this application will be described in detail below:

[0041] Figure 2 A flowchart illustrating a method for recommending behavioral information provided in this application embodiment is available. This method can be implemented by, for example... Figure 2 The electronic device 110 shown performs, but is not limited to, its functions. For example... Figure 2 As shown, the method may include the following steps:

[0042] S210: Calculate the similarity between the target user and each user in the user set using the target user's feature data.

[0043] In this context, the target user refers to the user who requires recommendation behavior information. The target user's characteristic data includes their usage data, operational data, and basic data of the corresponding physical object. In this embodiment, the user can specifically be a vehicle user, mobile phone user, home appliance user, or any user of the physical object; this embodiment does not specifically limit this. For example, if the target user is a mobile phone user, their characteristic data could specifically include the user's operational data on the mobile phone, the phone's operating data, and the phone's appearance data.

[0044] In one embodiment of the present invention, the target user is a vehicle user, and the target user's feature data may specifically include: driving behavior feature data, vehicle location feature data, vehicle fault feature data, and vehicle usage feature data. Specifically, driving behavior feature data represents the user's driving behavior, such as driving style and habits; vehicle location feature data represents the vehicle's operating locations, specifically location coordinates, and then determines the corresponding location attributes based on the location coordinates, such as city, mountainous area, plateau, etc.; vehicle fault feature data represents the vehicle's faults, such as headlight malfunctions and brake malfunctions; and vehicle usage feature data represents the user's usage of the vehicle, specifically the frequency and duration of use of vehicle components. It is understood that this embodiment is merely an exemplary description of feature data and does not represent all forms of feature data.

[0045] In this embodiment, the user set includes feature data and behavioral data corresponding to multiple users. The behavioral data is used to represent the after-sales behavior or handling method adopted after the physical object used by the user malfunctions or is abnormal. Specifically, the behavioral data can be after-sales interval time, after-sales behavior, etc.

[0046] In this embodiment, the user set can be represented as a feature matrix, which contains feature data and behavioral data corresponding to each user. For example, the user set can be represented as:

[0047]

[0048] Where t represents the time when the fault occurred, score represents the user's driving style rating, pos1 and pos2 represent the vehicle location, w1...wn represent n parts, ser represents the vehicle series, f1...fn represent the faults corresponding to the n parts, inter represents the after-sales interval (in hours or days), and M represents the after-sales action, which is represented by a numerical value. Different values ​​represent different after-sales actions, such as 0.075 indicating that the user repaired the brake fault.

[0049] It should be noted that the behavioral data in this embodiment includes not only maintenance or repair suggestions, but also information on purchased products. For example, for a user of a certain brand of vehicle, after the mileage reaches a certain value, the seller launches a maintenance promotion. When the target user meets the seller's requirements (mileage and vehicle brand meet the requirements), the corresponding maintenance promotion will be recommended to them.

[0050] Specifically, the feature matrix is ​​obtained in this embodiment as follows: First, user after-sales data is obtained, and then data that affects after-sales behavior is extracted from the user after-sales data, such as driving style rating, location, parts usage, vehicle series, fault light, repair time, etc. After that, the extracted data features are processed. This processing includes reducing the impact of excessively large values ​​on the weights, and processing text and character data.

[0051] For example, driving style ratings are converted into numerical data of 1-5, location data is continuous GPS data, and part usage is represented by values ​​of 0 and 1. Therefore, continuous numerical data needs to be normalized to map all data to the (0, 1) interval, reducing the influence of numerical values ​​on the results. For text data, TFIDF (term frequency – inverse document frequency) is used for feature processing. This involves converting text data into numerical data, and after processing all data, a feature matrix is ​​built to represent the feature data and behavioral data corresponding to each user.

[0052] S220: Calculate the behavior score corresponding to each behavior data based on the similarity between the users in the user set and the target user, and the preference scores of the users in the user set for each behavior data.

[0053] Specifically, this embodiment can use algorithms such as KNN (K-Nearest Neighbor), cosine similarity, and Euclidean distance to calculate the similarity between each user in the user set and the target user. This embodiment does not limit the specific calculation method of similarity.

[0054] The preference score is used to represent the degree of importance a user attaches to a fault problem (the feature data corresponding to the fault problem). This degree of importance can be determined by the time interval between the occurrence of the problem and the reporting of the problem, or by the time interval between the occurrence of the problem and the handling of the problem. This embodiment does not make specific limitations on this.

[0055] In an optional embodiment of the invention, the step of calculating the behavior score corresponding to each behavior data based on the similarity between users in the user set and the target user, and the preference score corresponding to each user in the user set for each behavior data, includes:

[0056] The behavioral score for each behavioral data point is calculated using the following formula:

[0057]

[0058] Where, p j Let U be the behavior score of all users in the user set for the j-th behavior data, and n be the target user. i For the i-th user in the user set, sim(u,U) i Let w be the similarity between the target user and the i-th user in the user set. ij Let be the preference score of the i-th user in the user set corresponding to the j-th behavior data, n be the number of users in the user set, j∈(1,m), and m be the number of types of feature data.

[0059] In this embodiment, the preference score w ij The preference score can be determined by the time corresponding to the i-th user's processing of the j-th behavior data, which is based on the time interval between the occurrence of the problem and its resolution.

[0060] S230: Recommend behavioral information to the target user based on the behavioral score corresponding to the behavioral data.

[0061] In this embodiment, after calculating the scores corresponding to each behavioral data through similarity and preference scores, the scores can be sorted first, and then the top 3 users with the highest scores can be obtained from the user set. That is, users with high similarity and high importance to the target user can be obtained, and then behavioral information can be recommended to the target user based on the behavioral data of the top 3 users.

[0062] This embodiment provides a method for recommending behavioral information. First, it calculates the similarity between the target user and each user in a user set, using the target user's feature data. This user set includes feature data and behavioral data corresponding to multiple users. Then, based on the similarity between users in the user set and the target user, and the preference scores of users in the user set for each behavioral data point, it calculates the behavioral score for each behavioral data point. Finally, based on the behavioral scores, it recommends behavioral information to the target user. Compared to existing technologies that require customers to visit after-sales service departments to obtain repair solutions, this application's solution, by calculating the similarity between the target user and the user set, and the preference scores of users in the user set for each feature behavioral data point, can recommend corresponding behavioral information to the target user. Therefore, the behavioral information recommended by this application can improve the timeliness of users obtaining repair solutions.

[0063] Figure 3 A flowchart illustrating another method for recommending behavioral information provided in this application embodiment, the method of which can be derived from, for example... Figure 3 The electronic device 110 shown performs, but is not limited to, its functions. For example... Figure 3 As shown, the method may include the following steps:

[0064] S310: Calculate the similarity between the target user and each user in the user set using the target user's feature data.

[0065] The user set includes feature data and behavioral data corresponding to multiple users.

[0066] S320: Identify users in the user set whose similarity to the target user is greater than a preset value as candidate users.

[0067] The preset value can be set according to actual needs, such as 80%, 85%, 90%, etc.; of course, in this embodiment, the top m users in similarity ranking can also be determined as candidate users, where m can be 3, 5, 10, etc., and this embodiment does not make specific limitations on this.

[0068] S330: Calculate the behavioral score corresponding to each behavioral data based on the similarity between the candidate user and the target user and the preference score of the candidate user for each behavioral data.

[0069] It should be noted that the calculation method for behavior scores in this embodiment is different from... Figure 2 The content described in step S220 is the same, and will not be repeated here in this embodiment.

[0070] Figure 4 The flowchart for calculating preference scores provided in this application embodiment includes the following calculation process:

[0071] S410: Obtain the after-sales interval time from the behavioral data.

[0072] The after-sales interval is the time interval between the occurrence of a vehicle malfunction and the corresponding after-sales processing time. The occurrence of a vehicle malfunction can be the time when the malfunction indicator light illuminates or the time when the user reports the malfunction to after-sales service.

[0073] S420: Based on the after-sales interval time in the behavioral data, calculate the preference score for each user in the user set for each behavioral data.

[0074] In an optional embodiment of the present invention, the step of calculating the preference score for each user in the user set for each behavioral data based on the after-sales interval time in the behavioral data includes:

[0075] The preference score for each behavioral data point is calculated using the following formula:

[0076] w ij =1 / (1+t) ij );

[0077] Among them, w ij Let t be the preference score of the i-th user in the user set corresponding to the j-th behavior data. ij The after-sales interval time is the time corresponding to the j-th behavior data of the i-th user in the user set.

[0078] S430: Recommend behavioral information to target users based on the behavioral scores corresponding to the behavioral data.

[0079] In this embodiment, the behavior scores corresponding to the behavior data can be sorted first, and then behavior data that meets preset conditions can be selected from the sorting results to recommend behavior information to the target user. For example, the behavior data with the highest scores can be selected from the behavior scores to recommend behavior information to the target user.

[0080] For example, Figure 5The example diagram for calculating the behavior score provided in this embodiment shows that the number of candidate users obtained through similarity calculation is 3, namely user 1, user 2, and user 3. The similarity between the target user and user 1 is 0.6, the similarity between the target user and user 2 is 0.5, and the similarity between the target user and user 3 is 0.8. All three users generated behavior data A, behavior data B, and behavior data C. User 1's preference for behavior data A is 0.8, user 2's preference for behavior data A is 0.6, and user 3's preference for behavior data A is 0.9. User 1's preference for behavior data B is 0.2, user 2's preference for behavior data B is 0.3, and user 3's preference for behavior data B is 0.9. User 1's preference for behavior data C is 0.8, user 2's preference for behavior data C is 0.3, and user 3's preference for behavior data C is 0.7.

[0081] The degree of preference is determined based on the after-sales interval corresponding to behavioral data A, i.e., according to formula w. ij =1 / (1+t) ij Calculate the degree of preference of the three users for behavioral data A.

[0082] After calculating the similarity and preference levels, the behavioral score is calculated using the following formula:

[0083]

[0084]

[0085]

[0086] The above formula is used to calculate the behavioral scores of three users for behavioral data A, behavioral data B, and behavioral data C, respectively. From the three behavioral scores, behavioral data A with the highest score is selected as the recommended behavioral information for the target user.

[0087] This embodiment provides another method for recommending behavioral information. First, based on the similarity between candidate users and target users, and the preference scores of candidate users for each behavioral data point, a behavioral score is calculated for each behavioral data point. Then, behavioral information is recommended to the target user based on the behavioral scores. Since the candidate users in this embodiment are users in the user set whose similarity to the target user is greater than a preset value, the calculated behavioral scores can reflect the handling methods of other users who encountered similar problems to the target user. Therefore, based on the behavioral scores, corresponding behavioral information can be accurately recommended to the target user, thereby improving the accuracy of the recommendation.

[0088] Figure 6A flowchart illustrating another method for recommending behavioral information provided in this application embodiment, the method can be derived from, for example... Figure 6 The electronic device 110 shown performs, but is not limited to, its functions. For example... Figure 6 As shown, the method may include the following steps:

[0089] S610: Calculate the similarity between the target user and each user in the user set using the target user's feature data.

[0090] The user set includes feature data and behavioral data corresponding to multiple users.

[0091] S620: Identify users in the user set whose similarity to the target user is greater than a preset value as candidate users.

[0092] S630: Calculate the behavioral score corresponding to each behavioral data and / or the user score corresponding to each candidate user based on the similarity between the candidate user and the target user, the preference score of the candidate user in each behavioral data, and / or the preference score of the candidate user in the corresponding behavioral data.

[0093] Specifically, this embodiment can calculate the behavioral score corresponding to each behavioral data point based on the similarity between users in the user set and the target user, and the preference scores of users in the user set for each behavioral data point. The specific calculation method for the behavioral score corresponding to each behavioral data point is as follows... Figure 1 and Figure 3 The corresponding steps are the same, and will not be repeated here in this embodiment; the user score corresponding to each candidate user can be calculated based on the similarity between the candidate user and the target user and the preference score of the candidate user's corresponding behavioral data.

[0094] More specifically, this embodiment calculates the user score corresponding to each candidate user using the following formula:

[0095] q i =sim(u,U) i )*w i

[0096] w i =1 / (1+t) i )

[0097] Where, q i For the user score of the i-th candidate user, sim(u,U) i ) represents the similarity between the target user and the i-th candidate user, w i Let t be the preference score of the i-th candidate user's corresponding behavioral data. iLet t be the after-sales interval time for the i-th candidate user across all behavioral data. It should be noted that in this implementation, each user in the user set corresponds to one or more behavioral data points, which may have the same or different after-sales interval times. If multiple behavioral data points correspond to different after-sales interval times, their average value can be calculated as the after-sales interval time for all behavioral data, or the longest after-sales interval time can be used as t. i .

[0098] S640: Recommend behavioral information to the target user based on the behavioral score corresponding to the behavioral data and / or the user score corresponding to each candidate user.

[0099] In this embodiment, after obtaining the behavior values ​​and / or user scores, the behavior values ​​and / or user scores can be sorted. Then, based on the top few behavior values ​​and / or user scores in the sorting results, behavior information is recommended to the target user. For behavior values, behavior information can be recommended to the target user based on the behavior data corresponding to the top few behavior values ​​in the sorting results; for user scores, behavior information can be recommended to the target user based on the behavior data of the users corresponding to the top few user scores in the sorting results.

[0100] For behavior values ​​and user scores, firstly, the users corresponding to the top M user scores are obtained from the sorting results. Then, the same behavior data as the behavior data corresponding to the top N behavior values ​​is obtained from the obtained users. Finally, behavior information is recommended to the target user based on the obtained behavior data.

[0101] For example, the top 3 users in the ranking results based on user scores are: User A, User B, and User C; the top 2 behavioral data in the ranking results based on behavioral values ​​are: Behavior Data 1 and Behavior Data 2; if User A, User B, and User C all include Behavior Data 1, or if Behavior Data 1 appears most frequently among the 3 users, then behavioral information is recommended to the target user based on Behavior Data 1.

[0102] This embodiment provides another method for recommending behavioral information. First, based on the similarity between candidate users and target users, the preference scores of candidate users for each behavioral data point, and / or the preference scores of candidate users for their corresponding behavioral data points, a behavioral score corresponding to each behavioral data point and / or a user score corresponding to each candidate user is calculated. Then, behavioral information is recommended to the target user based on the behavioral scores of the behavioral data points and / or the user scores of each candidate user. This embodiment comprehensively considers both behavioral scores and / or user scores when recommending behavioral information to the target user; therefore, this embodiment can improve the accuracy of behavioral information recommendation.

[0103] Figure 7 This is a schematic diagram of a behavior information recommendation device 700 provided in an embodiment of this application. Figure 7 As shown, the device 700 includes:

[0104] The first calculation module 701 is used to calculate the similarity between the target user and each user in the user set using the feature data of the target user; the user set includes feature data and behavioral data corresponding to multiple users respectively;

[0105] The second calculation module 702 is used to calculate the behavior score corresponding to each behavior data based on the similarity between the users in the user set and the target user, and the preference scores of the users in the user set for each behavior data.

[0106] The recommendation module 703 is used to recommend behavioral information to the target user based on the behavioral score corresponding to the behavioral data.

[0107] In some implementations, the second calculation module 702 is specifically used to: calculate the behavioral score corresponding to each behavioral data using the following formula:

[0108]

[0109] Where, p j Let sim(u, U) be the behavior score of all users in the user set for the j-th behavior data. i Let w be the similarity between the target user and the i-th user in the user set. ij Let be the preference score of the i-th user in the user set for the j-th behavior data, and n be the number of users in the user set.

[0110] In some implementations, the second calculation module 702 is specifically used to: obtain the after-sales interval time in the behavioral data; and calculate the preference score corresponding to each user in the user set for each behavioral data based on the after-sales interval time in the behavioral data.

[0111] In some implementations, the second computing module 702 is specifically used for:

[0112] The preference score for each behavioral data point is calculated using the following formula:

[0113] w ij =1 / (1+t) ij )

[0114] Among them, w ij Let t be the preference score corresponding to the j-th behavior data of the i-th user in the user set. ij The after-sales interval time is the time corresponding to the j-th behavior data of the i-th user in the user set.

[0115] In some implementations, the after-sales interval is the time interval between the time of vehicle malfunction and the corresponding after-sales processing time.

[0116] In some possible implementations, the apparatus further includes:

[0117] The determination module 704 is used to determine users in the user set whose similarity to the target user is greater than a preset value as candidate users;

[0118] The second calculation module 702 is used to: calculate the behavior score corresponding to each behavior data based on the similarity between the candidate user and the target user and the preference score of the candidate user in each behavior data.

[0119] In some implementations, the feature data includes: driving behavior feature data, vehicle location feature data, vehicle fault feature data, and vehicle usage feature data.

[0120] It should be understood that the device embodiments and the behavior information recommendation method embodiments can correspond to each other, and similar descriptions can be found in the behavior information recommendation method embodiments. To avoid repetition, further details are omitted here. Specifically, Figure 7 The apparatus 700 shown can execute the above-described embodiment of the behavior information recommendation method, and the foregoing and other operations and / or functions of each module in the apparatus 700 are respectively for implementing the corresponding process in the above-described behavior information recommendation method, which will not be described in detail here for the sake of brevity.

[0121] The apparatus 700 of this application embodiment has been described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that this functional module can be implemented in hardware, in software instructions, or in a combination of hardware and software modules. Specifically, the steps of the behavior information recommendation method embodiment in this application can be completed by integrated logic circuits in the processor's hardware and / or by software instructions. The steps of the behavior information recommendation method disclosed in this application embodiment can be directly manifested as execution by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps in the behavior information recommendation method embodiment described above.

[0122] Figure 8 This is a schematic block diagram of the electronic device 800 provided in an embodiment of this application. Figure 8As shown, the electronic device 800 may include a processor 801 and a memory 802. The electronic device 800 may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805.

[0123] The processor 801 controls the overall operation of the electronic device 800 to complete all or part of the steps in the recommended method for the aforementioned behavioral information. The memory 802 stores various types of data to support the operation of the electronic device 800. This data may include, for example, instructions for any application or method operating on the electronic device 800, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 905 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0124] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the recommended method for executing the behavioral information described above.

[0125] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described method for recommending behavioral information. For example, the computer-readable storage medium may be the memory 902 including the program instructions, which may be executed by the processor 801 of the electronic device 800 to complete the above-described method for recommending behavioral information.

[0126] In another exemplary embodiment, a computer-readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-described method for recommending behavioral information are also provided.

[0127] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the recommended method for executing the aforementioned behavioral information when executed by the programmable device.

[0128] In another exemplary embodiment, a computer program is also provided, which causes a computer to perform the method of recommending behavioral information as described above.

[0129] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0131] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. For example, the functional modules in the various embodiments of this application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0132] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for recommending behavioral information, characterized in that, The method includes: The similarity between the target user and each user in the user set is calculated using the target user's feature data; the user set includes feature data and behavioral data corresponding to multiple users respectively. Based on the similarity between the users in the user set and the target user, and the preference scores of the users in the user set for each behavioral data, calculate the behavioral score corresponding to each behavioral data. Based on the behavior scores corresponding to the behavior data, behavioral information is recommended to the target user; The method further includes: Obtain the after-sales interval time from the behavioral data; the after-sales interval time is the time interval between the time of vehicle malfunction and the corresponding after-sales processing time; Based on the after-sales interval time in the behavioral data, calculate the preference score for each user in the user set for each behavioral data.

2. The method according to claim 1, characterized in that, The step of calculating the behavior score corresponding to each behavior data based on the similarity between users in the user set and the target user, and the preference score corresponding to each user in the user set for each behavior data, includes: The behavioral score for each behavioral data point is calculated using the following formula: ； in, Let J be the behavior score of all users in the user set for the j-th behavior data. Let the similarity between the target user and the i-th user in the user set be denoted as . The preference score for the i-th user in the user set corresponding to the j-th behavior data. This represents the number of users in the user set.

3. The method according to claim 1, characterized in that, The step of calculating the preference score for each user in the user set for each behavioral data point based on the after-sales interval time in the behavioral data includes: The preference score for each behavioral data point is calculated using the following formula: ； in, The preference score for the i-th user in the user set corresponding to the j-th behavior data. The after-sales interval time is the time corresponding to the j-th behavior data of the i-th user in the user set.

4. The method according to claim 1, characterized in that, Before calculating the behavior score corresponding to each behavior data based on the similarity between users in the user set and the target user, and the preference scores corresponding to each behavior data for users in the user set, the method further includes: Users in the user set whose similarity to the target user is greater than a preset value are identified as candidate users; Accordingly, the step of calculating the behavioral score corresponding to each behavioral data point based on the similarity between users in the user set and the target user, and the preference scores corresponding to each behavioral data point for users in the user set, includes: Based on the similarity between the candidate user and the target user, and the preference scores of the candidate user for each behavioral data, the behavioral scores corresponding to each behavioral data are calculated.

5. The method according to claim 1, characterized in that, The feature data includes: driving behavior feature data, vehicle location feature data, vehicle fault feature data, and vehicle usage feature data.

6. A device for recommending behavioral information, characterized in that, The device includes: The first calculation module is used to calculate the similarity between the target user and each user in the user set using the feature data of the target user; the user set includes feature data and behavioral data corresponding to multiple users respectively; The second calculation module is used to calculate the behavior score corresponding to each behavior data based on the similarity between the users in the user set and the target user, and the preference scores of the users in the user set for each behavior data. The recommendation module is used to recommend behavioral information to the target user based on the behavioral score corresponding to the behavioral data. The second calculation module is further configured to: obtain the after-sales interval time in the behavioral data; the after-sales interval time is the time interval between the time of the vehicle malfunction and the corresponding after-sales processing time; Based on the after-sales interval time in the behavioral data, calculate the preference score for each user in the user set for each behavioral data.

7. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store a computer program, the processor being used to invoke and run the computer program stored in the memory to perform the method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program that causes a computer to perform the method as described in any one of claims 1-5.

Images