User determination method, device, computer equipment and storage medium

Abstract

The present application discloses a user determination method, apparatus, computer device, and storage medium, belonging to the technical field of data analysis. The method includes: receiving a target instruction for indicating that a target behavior occurs in the business premises of a first user; determining a plurality of users; obtaining first location data of the business premises, second location data of the plurality of users within a target time period, and at least one selected from the consumption behavior data and user portrait data of the plurality of users within the target time period; and determining a second user corresponding to the target behavior among the plurality of users according to the first location data, the second location data of the plurality of users, and at least one selected from the consumption behavior data and the user portrait data of the plurality of users. The present application can accurately determine suspicious users who have consumed in the store but have not redeemed coupons, with low consumption of computing resources and high applicability.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and particularly relates to a user determination method, apparatus, computer device, and storage medium. Background Art

[0002] In order to attract users to consume in the store, merchants generally issue consumption vouchers to users through e-commerce platforms. When users consume in the store, they can show the consumption vouchers to the cashier, and the cashier will verify the vouchers. However, due to the mistakes of cashiers or the malicious behavior of users to avoid paying, there may be situations where users consume but the vouchers are not verified. How to identify such users is a problem worthy of attention.

[0003] Currently, related technologies generally collect images in the store through cameras and perform face recognition to obtain face recognition result data of users in the store. The face recognition result data includes the IDs of users and the time periods when the users are photographed. Based on the face recognition result data, the arrival behaviors of each user in the store are analyzed, including the arrival time and departure time of the users, and then, in combination with the time period when the behavior of non-verified vouchers provided by the merchant occurs, the suspicious users who consume in the store but have not had their vouchers verified are determined. Then, the suspicious users are provided to the merchant, so that the merchant can call the suspicious users to confirm.

[0004] The above-mentioned technology determines suspicious users who consume in the store but have not had their vouchers verified based on face recognition, which has a high technical difficulty, requires a lot of computing resources, and has poor applicability. Summary of the Invention

[0005] Embodiments of this application provide a user determination method, apparatus, computer device, and storage medium, which can solve the problem of poor applicability of related technologies. The technical solutions are as follows:

[0006] In a first aspect, a user determination method is provided, including:

[0007] Receiving a target instruction, where the target instruction is used to indicate that a target behavior has occurred in the business premises of a first user, and the target behavior refers to the behavior of consuming but not verifying the electronic vouchers issued by the first user;

[0008] Determining a plurality of users whose accounts are currently bound with the un-verified electronic vouchers;

[0009] Obtaining first location data of the business premises, second location data of the plurality of users during a target time period, and at least one selected from the consumption behavior data of the plurality of users during the target time period and the user portrait data of the plurality of users;

[0010] Determine the second user corresponding to the target behavior among the multiple users according to the first position data, the second position data of the multiple users, and at least one selected from the consumption behavior data and the user portrait data of the multiple users.

[0011] In a possible implementation manner, the determining the second user corresponding to the target behavior among the multiple users according to the first position data, the second position data of the multiple users, and at least one selected from the consumption behavior data and the user portrait data of the multiple users includes:

[0012] Determine the second user according to the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users;

[0013] Wherein, the first feature data is obtained according to the first position data and the second position data, the second feature data is obtained according to the first position data and the consumption behavior data, the first feature data is used to represent the minimum distance among the distances between different positions of the user and the business premises within the target time period, and the second feature data is used to represent whether the user has a consumption behavior within the first distance range of the business premises within the target time period.

[0014] In a possible implementation manner, the determining the second user according to the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users includes:

[0015] Input the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users into a scoring model, and output the scoring information of the multiple users, where the scoring information is used to represent the possibility that the user is the second user;

[0016] Determine the second user according to the scoring information of the multiple users.

[0017] In a possible implementation manner, the second position data includes the position data within the occurrence time period of the target behavior;

[0018] The obtaining process of the second position data of any user includes:

[0019] Obtain the third position data uploaded by the terminal of the any user within the target time period;

[0020] If the third location data includes location data within the occurrence time period of the target behavior, use the third location data as the second location data of any user.

[0021] In a possible implementation manner, after obtaining the third location data uploaded by the terminal of any user within the target time period, the method further includes:

[0022] If the third location data does not include location data within the occurrence time period of the target behavior, perform a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior;

[0023] Use the location data within the occurrence time period of the target behavior and the third location data as the second location data of any user.

[0024] In a possible implementation manner, the step of if the third location data does not include location data within the occurrence time period of the target behavior, perform a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior includes:

[0025] If the third location data does not include location data within the occurrence time period of the target behavior, obtain the third feature data of any user, where the third feature data is used to represent the possibility that the user appears within the second distance range of the business premises;

[0026] If the third feature data of any user indicates the possibility that the user appears within the second distance range, perform a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior.

[0027] In a possible implementation manner, the step of obtaining the third feature data of any user includes:

[0028] Obtain the third feature data of any user according to the third location data, the time information of the third location data, the first location data, the occurrence time period, and the way of passing from the location indicated by the third location data to the business premises.

[0029] In a possible implementation manner, the step of performing a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior includes:

[0030] Obtain fourth location data before the occurrence time period from the third location data;

[0031] Input the fourth position data into a position prediction model to output the position data within the occurrence time period of the target behavior.

[0032] In a second aspect, a user determination device is provided, including:

[0033] A receiving module, configured to receive a target instruction, where the target instruction is used to indicate that a target behavior occurs in the business premises of a first user, and the target behavior refers to the behavior of consuming but not verifying the electronic vouchers issued by the first user;

[0034] A determination module, configured to determine a plurality of users whose accounts are currently bound with the unverified electronic vouchers;

[0035] An acquisition module, configured to acquire first position data of the business premises, second position data of the plurality of users within a target time period, and at least one selected from the consumption behavior data of the plurality of users within the target time period and the user profile data of the plurality of users;

[0036] The determination module is further configured to determine a second user corresponding to the target behavior among the plurality of users according to the first position data, the second position data of the plurality of users, and at least one selected from the consumption behavior data and the user profile data of the plurality of users.

[0037] In a possible implementation manner, the determination module is configured to:

[0038] Determine the second user according to first feature data of the plurality of users and at least one selected from second feature data of the plurality of users and the user profile data;

[0039] Wherein, the first feature data is obtained according to the first position data and the second position data, the second feature data is obtained according to the first position data and the consumption behavior data, the first feature data is used to represent the minimum distance among the distances between different positions of the user within the target time period and the business premises, and the second feature data is used to represent whether the user has a consumption behavior within a first distance range of the business premises within the target time period.

[0040] In a possible implementation manner, the determination module is configured to:

[0041] Input the first feature data of the plurality of users and at least one selected from the second feature data and the user profile data of the plurality of users into a scoring model to output scoring information of the plurality of users, where the scoring information is used to represent the possibility that the user is the second user;

[0042] Determine the second user according to the rating information of the multiple users.

[0043] In a possible implementation manner, the second location data includes location data within the occurrence time period of the target behavior;

[0044] The obtaining module is configured to:

[0045] Obtain third location data uploaded by the terminal of any one of the users within the target time period;

[0046] If the third location data includes location data within the occurrence time period of the target behavior, then use the third location data as the second location data of any one of the users.

[0047] In a possible implementation manner, the obtaining module is further configured to:

[0048] If the third location data does not include location data within the occurrence time period of the target behavior, then perform prediction according to the third location data to obtain location data within the occurrence time period of the target behavior;

[0049] Use the location data within the occurrence time period of the target behavior and the third location data as the second location data of any one of the users.

[0050] In a possible implementation manner, the obtaining module is configured to:

[0051] If the third location data does not include location data within the occurrence time period of the target behavior, then obtain third feature data of any one of the users, where the third feature data is used to represent the possibility that the user appears within a second distance range of the business premises;

[0052] If the third feature data of any one of the users indicates that the any one of the users has the possibility of appearing within the second distance range, then perform prediction according to the third location data to obtain location data within the occurrence time period of the target behavior.

[0053] In a possible implementation manner, the obtaining module is configured to:

[0054] Obtain the third feature data of any one of the users according to the third location data, the time information of the third location data, the first location data, the occurrence time period, and the way of passing from the location indicated by the third location data to the business premises.

[0055] In a possible implementation manner, the obtaining module is configured to:

[0056] Obtain fourth location data before the occurrence time period from the third location data;

[0057] Input the fourth location data into a location prediction model, and output location data within the occurrence time period of the target behavior.

[0058] In a third aspect, a computer device is provided. The computer device includes a processor and a memory. At least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the user determination method according to the first aspect or any implementation manner of the first aspect.

[0059] In a fourth aspect, a computer-readable storage medium is provided. At least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by a processor to implement the user determination method according to any one of claims 1 to 8.

[0060] The beneficial effects brought by the technical solutions provided in the embodiments of the present application at least include:

[0061] By receiving a target instruction, it can be known that a target behavior occurs in the business premises of the first user. Since the target behavior is a behavior of not verifying the electronic coupons already issued by the first user, multiple users whose accounts are currently bound with un-verified electronic coupons can be determined first. Obtain the location data of these multiple users during the target time period, the location data of the business premises, and at least one selected from the consumption behavior data and user portrait data of these multiple users. According to the obtained data, determine the second user who has the target behavior from these multiple users. The above technical solution can accurately determine the suspicious users who have consumed in the store but have not verified the coupons based on the location data, consumption behavior data, user portrait data, etc. of the users, with low consumption of computing resources and high applicability. Description of the Drawings

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0063] Figure 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application;

[0064] Figure 2 is a flowchart of a user determination method provided by an embodiment of the present application;

[0065] Figure 3 is a flowchart of a user determination method provided by an embodiment of the present application;

[0066] Figure 4 is a flowchart of a user determination method provided by an embodiment of the present application;

[0067] Figure 5 is a schematic structural diagram of a user determination device provided by an embodiment of the present application;

[0068] Figure 6 is a schematic structural diagram of a computer device 600 provided by an embodiment of the present application. Detailed implementation manners

[0069] To make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0070] Figure 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application. Refer to Figure 1 , the implementation environment includes a terminal 101 and a server 102.

[0071] Among them, the terminal 101 may be a user device such as a mobile phone or a computer. A target application may be installed on the terminal 101, and the target application may be a group-buying application, a food delivery application, etc. During the process of running the target application, the terminal 101 may implement various functions based on the target application. The server 102 may be a single server or a server cluster composed of multiple servers. The server 102 may be the background server of the target application installed on the terminal 101, and the server 102 may provide services to the terminal 101 through the target application installed on the terminal 101, including e-voucher issuance services, consumption services, etc.

[0072] Figure 2 is a flowchart of a user determination method provided by an embodiment of the present application. This method is executed by a computer device, and the computer device may be Figure 1 the server in the corresponding embodiment. Refer to Figure 2 , this method includes:

[0073] 201. Receive a target instruction, where the target instruction is used to indicate that a target behavior has occurred in the business premises of a first user, and the target behavior refers to a behavior of consuming but not verifying the e-vouchers issued by the first user.

[0074] 202. Determine a plurality of users whose accounts are currently bound with the un-verified e-vouchers.

[0075] 203. Obtain first location data of the business premises, second location data of the plurality of users within a target time period, and at least one selected from the consumption behavior data of the plurality of users within the target time period and the user portrait data of the plurality of users;

[0076] 204. Determine a second user corresponding to the target behavior among the multiple users according to the first location data, the second location data of the multiple users, and at least one selected from the consumption behavior data and the user portrait data of the multiple users.

[0077] In the method provided by the embodiments of the present application, by receiving a target instruction, it can be known that a target behavior occurs in the business place of the first user. Since the target behavior is an act of not verifying the electronic vouchers already issued by the first user, multiple users whose accounts are currently bound with un-verified electronic vouchers can be determined first. Obtain the location data of the business place, the location data of the multiple users during the target time period, and at least one selected from the consumption behavior data and the user portrait data of the multiple users. According to the obtained data, determine a second user who has performed the target behavior among the multiple users. The above technical solution can accurately determine suspicious users who have consumed in the store but have not verified the vouchers based on the location data, consumption behavior data, user portrait data, etc. of the users, with low consumption of computing resources and high applicability.

[0078] In a possible implementation manner, the determining a second user corresponding to the target behavior among the multiple users according to the first location data, the second location data of the multiple users, and at least one selected from the consumption behavior data and the user portrait data of the multiple users includes:

[0079] Determine the second user according to the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users;

[0080] Wherein, the first feature data is obtained according to the first location data and the second location data, the second feature data is obtained according to the first location data and the consumption behavior data, the first feature data is used to represent the minimum distance among the distances between different locations of the user within the target time period and the business place, and the second feature data is used to represent whether the user has performed a consumption behavior within a first distance range of the business place within the target time period.

[0081] In a possible implementation manner, the determining a second user according to the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users includes:

[0082] Input the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users into a scoring model, and output the scoring information of the multiple users. The scoring information is used to represent the possibility that the user is the second user;

[0083] Determine the second user according to the rating information of the multiple users.

[0084] In a possible implementation, the second location data includes location data within the occurrence time period of the target behavior;

[0085] The process of obtaining the second location data of any user includes:

[0086] Obtain third location data uploaded by the terminal of any user within the target time period;

[0087] If the third location data includes location data within the occurrence time period of the target behavior, then use the third location data as the second location data of any user.

[0088] In a possible implementation, after obtaining the third location data uploaded by the terminal of any user within the target time period, the method further includes:

[0089] If the third location data does not include location data within the occurrence time period of the target behavior, then make a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior;

[0090] Use the location data within the occurrence time period of the target behavior and the third location data as the second location data of any user.

[0091] In a possible implementation, if the third location data does not include location data within the occurrence time period of the target behavior, then making a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior includes:

[0092] If the third location data does not include location data within the occurrence time period of the target behavior, then obtain third feature data of any user, where the third feature data is used to represent the possibility that the user appears within the second distance range of the business premises;

[0093] If the third feature data of any user indicates that the user has the possibility of appearing within the second distance range, then make a prediction based on the third location data to obtain location data within the occurrence time period of the target behavior.

[0094] In a possible implementation, the process of obtaining the third feature data of any user includes:

[0095] Obtain the third feature data of any user according to the third location data, the time information of the third location data, the first location data, the occurrence time period, and the mode of access from the location indicated by the third location data to the business premises.

[0096] In a possible implementation, predicting based on the third location data to obtain location data within the occurrence time period of the target behavior includes:

[0097] Obtaining fourth location data before the occurrence time period from the third location data;

[0098] Inputting the fourth location data into a location prediction model and outputting location data within the occurrence time period of the target behavior.

[0099] The method provided by the embodiments of the present application can learn that a target behavior occurs in the business premises of the first user by receiving a target instruction. Since the target behavior is an act of consuming without verifying the electronic vouchers issued by the first user, it is possible to first determine multiple users whose accounts are currently bound with un-verified electronic vouchers, obtain at least one of the location data, consumption behavior data, user portrait data of the multiple users, or the location data of the first user within the target time period, and determine a second user who has performed the target behavior from the multiple users according to the obtained data. The above technical solution can accurately determine suspicious users who have consumed in the store but have not verified the vouchers based on the user's location data, consumption behavior data, user portrait data, etc., with low consumption of computing resources and high applicability.

[0100] All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be elaborated here one by one.

[0101] Figure 3 is a flowchart of a user determination method provided by the embodiments of the present application. This method is executed by a computer device, and the computer device can be Figure 1 the server in the corresponding embodiment, see Figure 3 , and this method includes:

[0102] 301. Receiving a target instruction, where the target instruction is used to indicate that a target behavior occurs in the business premises of the first user, and the target behavior refers to an act of consuming without verifying the electronic vouchers issued by the first user.

[0103] Among them, the first user can be a merchant, and the business premises can be the merchant's store.

[0104] The first user can issue e-vouchers to multiple users based on a target application. Then, any one of the multiple users can use the e-vouchers issued by the first user to consume at the business premises of the first user. When consuming, the cashier of the first user verifies the e-vouchers presented by any one of the users. If any one of the users has consumed but not verified the e-vouchers, that is, any one of the users has obtained the goods or services provided by the first user but has not verified the e-vouchers issued by the first user, it indicates that a target behavior has occurred, that is, a behavior of skipping payment. Taking the business premises of the first user as a restaurant, the e-voucher as a lunch voucher, and any one of the users as User A as an example, User A can present the lunch voucher in the restaurant of the first user, and the cashier of the restaurant can verify the lunch voucher. Due to the mistake of the cashier, the voucher verification was not successful, but the cashier mistakenly thought the verification was successful and notified the service staff in the restaurant to provide lunch for User A. After User A finished dining and left the restaurant, the cashier later found that the voucher verification was not successful at that time, and then could inform the first user that the target behavior had occurred. After the first user confirms the occurrence of the target behavior, the first user can operate on the target application to trigger the target instruction. The first user can also call the back-end administrator of the target application, and the administrator can trigger the target instruction through the operation, so that the computer device can receive the target instruction. The embodiments of the present application do not limit the manner of triggering the target instruction.

[0105] 302. Determine multiple users whose accounts are currently bound with the un-verified e-vouchers.

[0106] After receiving the target instruction, the computer device can determine the user corresponding to the target behavior for the first user, that is, the user who has committed the target behavior. For the sake of distinction, the user to be determined by the computer device is called the second user. Since the first user has issued the e-vouchers to multiple users, it can be determined that the second user is a user among the multiple users and whose account is currently bound with the un-verified e-vouchers. Therefore, the computer device can first determine multiple users whose accounts are currently bound with the un-verified e-vouchers, and then determine the second user from among the multiple users. For example, the computer device can query the accounts of each user according to the number of the e-voucher. If the account of any one user is currently bound with the un-verified e-voucher, then that user is regarded as one of the multiple users.

[0107] 303. Obtain the first location data of the business premises, the second location data of the multiple users during the target time period, consumption behavior data, and the user portrait data of the multiple users.

[0108] Among them, the first location data of the business premises is used to indicate the location of the business premises. For any one of the multiple users, the second location data of the any one user is used to indicate the location of the any one user during the target time period. The consumption behavior data of the any one user is used to indicate the consumption behavior of the any one user during the target time period. The consumption behavior refers to the behavior of purchasing goods or services, where the services include but are not limited to dining services, accommodation services, entertainment services, etc. The consumption behavior data can be obtained according to the bill (or called the bill list) of the any one user. The user portrait data of the any one user includes attributes of multiple dimensions of the any one user, including income level, occupation, preference sensitivity, etc. The user portrait data of the any one user can be obtained and stored by a computer device when the any one user registers for the target application, so that the computer device can obtain the stored user portrait data. The target time period can be the day when the target behavior occurs, or a period of time before the occurrence time period of the target behavior. The embodiments of the present application do not make any limitations on this.

[0109] In a possible implementation manner, the second location data includes the location data during the occurrence time period of the target behavior. The obtaining process of the second location data of any one user includes: obtaining the third location data uploaded by the terminal of the any one user during the target time period; if the third location data includes the location data during the occurrence time period of the target behavior, then use the third location data as the second location data of the any one user.

[0110] The terminal of any one user can upload its current location data to the computer device. For example, when any one user opens the target application on the terminal, the terminal can perform positioning to obtain the current location data and upload the current location data to the computer device. The computer device can use the location data uploaded by the terminal during the target time period as the third location data. Furthermore, the computer device can determine whether the third location data includes the location data during the occurrence time period of the target behavior. If the third location data uploaded by the terminal includes the location data of the user during the occurrence time period of the target behavior, then the computer device can obtain the third location data as the second location data of the any one user.

[0111] In a possible implementation manner, after obtaining the third location data uploaded by the terminal of the any one user during the target time period, the method further includes: if the third location data does not include the location data during the occurrence time period of the target behavior, then make a prediction according to the third location data to obtain the location data during the occurrence time period of the target behavior; use the location data during the occurrence time period of the target behavior and the third location data as the second location data of the any one user.

[0112] If the third location data uploaded by the terminal does not include the location data of the user during the occurrence time period of the target behavior, the computer device may perform location prediction to obtain the location data during the occurrence time period of the target behavior, and supplement the location data during the occurrence time period of the target behavior into the third location data to obtain the second location data of any one user.

[0113] In a possible implementation manner, if the third location data does not include the location data during the occurrence time period of the target behavior, prediction is performed based on the third location data to obtain the location data during the occurrence time period of the target behavior, including: if the third location data does not include the location data during the occurrence time period of the target behavior, the third feature data of any one user is obtained, and the third feature data is used to represent the possibility that the user appears within the second distance range of the business premises; if the third feature data of any one user indicates that the any one user has the possibility of appearing within the second distance range, prediction is performed based on the third location data to obtain the location data during the occurrence time period of the target behavior.

[0114] Among them, the second distance range of the business premises may be a POI (Point of Interest) range. The computer device may first determine the possibility that any one user appears within the second distance range of the business premises of the first user. The computer device may use the third feature data to represent this possibility, and the third feature data may be a first value or a second value. The first value indicates that any one user has the possibility of appearing within the second distance range, and the second value indicates that any one user does not have the possibility of appearing within the second distance range. For example, the first value may be 1, and the second value may be 0. Of course, the 1 and 0 are only examples, and the computer device may also use other values to represent whether there is such a possibility, and the embodiments of the present application do not limit this.

[0115] If the third feature data of any one user indicates that the any one user has the possibility of appearing within the second distance range, it indicates that the any one user may be the user corresponding to the target behavior, so the location data of the user can be predicted. If the third feature data of any one user indicates that the any one user does not have the possibility of appearing within the second distance range, it can be determined that the user is not the user corresponding to the target behavior, so the user can be excluded.

[0116] In a possible implementation manner, the obtaining of the third feature data of any one user includes: obtaining the third feature data of any one user according to the third location data, the time information of the third location data, the first location data, the occurrence time period, and the way of passing from the location indicated by the third location data to the business premises.

[0117] According to the way of traveling from the position indicated by the third position data to the business premises of the first user, the computer device can set the average speed of the user from the position indicated by the fourth position to the business premises, and then calculate the first duration required for the user to travel from the position indicated by the fourth position to the business premises based on the distance between the position indicated by the fourth position and the business premises and the average speed, and calculate the second duration between the time information of the third position data and the end time of the occurrence time period. According to the magnitude relationship between the first duration and the second duration, the third characteristic data is obtained. For example, if the first duration is less than or equal to the second duration, the third characteristic data can be obtained as the first value, and if the first duration is greater than the second duration, the third characteristic data can be obtained as the second value.

[0118] In a possible implementation manner, predicting based on the third position data to obtain the position data within the occurrence time period of the target behavior includes: obtaining, from the third position data, the fourth position data before the occurrence time period; inputting the fourth position data into a position prediction model, and outputting the position data within the occurrence time period of the target behavior.

[0119] Among them, the position prediction model can be an HMM (Hidden Markov Model), and the HMM model can predict the position data in a subsequent time period based on the position data in a previous time period. The position prediction model can be trained based on the position data in the first time period and the position data in the second time period, where the first time period is the time period before the second time period.

[0120] By using the position data uploaded by the user terminal as the position data of the user, an accurate and effective way to obtain position data is provided. When the position data uploaded by the user terminal does not include the position data within the occurrence time period of the target behavior, position prediction and position supplementation are performed, which can ensure the integrity of the position data and improve the accuracy of user determination. Among them, using a position prediction model for position prediction can simply and efficiently obtain the position data within the occurrence time period of the target behavior.

[0121] It should be noted that, in the embodiments of the present application, a computer device obtaining the above-mentioned multiple data (first location data, second location data, consumption behavior data, and user profile data) is taken as an example for illustration. In an alternative embodiment, the computer device may obtain the first location data of the business premises, the second location data of the multiple users within a target time period, and at least one selected from the consumption behavior data and the user profile data of the multiple users within the target time period. For example, the computer device may obtain the first location data of the business premises, the second location data of the multiple users within the target time period, the consumption behavior data, and the consumption behavior data of the multiple users, or the computer device may obtain the first location data of the business premises, the second location data of the multiple users within the target time period, and the user profile data of the multiple users.

[0122] 304. Obtain first feature data and second feature data of the multiple users according to the first location data of the business premises, the second location data of the multiple users within the target time period, and the consumption behavior data.

[0123] Among them, the first feature data is obtained according to the first location data and the second location data, and the second feature data is obtained according to the first location data and the consumption behavior data. The first feature data is used to represent the minimum distance among the distances between different locations of the user and the business premises within the target time period, that is, the shortest distance between the user and the business premises of the first user. The second feature data is used to represent whether the user has a consumption behavior within the first distance range of the business premises within the target time period, that is, whether the user has a consumption behavior near the business premises of the first user.

[0124] For the first feature data of each user, the first location data of the business premises is used to indicate the location of the business premises, and the second location data of the user can be used to indicate at least one location of the user within the target time period. The computer device can determine the distance between each of the at least one location and the location of the business premises according to the at least one location of the user and the location of the business premises, obtain at least one distance, and select the minimum distance from the at least one distance as the first feature data.

[0125] For the second feature data of each user, the consumption behavior data of the user is used to indicate at least one consumption behavior of the user within the target time period. Each consumption behavior includes location data. The computer device can determine whether the at least one consumption behavior occurs within the first distance range of the business premises based on the at least one consumption behavior of the user and the location of the business premises. The second feature data can be represented by a third value or a fourth value. The third value indicates that the user has had a consumption behavior within the first distance range of the business premises within the target time period, and the fourth value indicates that the user has not had a consumption behavior within the first distance range of the business premises within the target time period. The third value or the fourth value can be the same as or different from the first value or the second value.

[0126] 305. Determine the second user according to the first feature data, the second feature data of the multiple users, and the user portrait data.

[0127] Among them, the second user is a suspicious user who has performed the target behavior among the multiple users.

[0128] In a possible implementation manner, the process of determining the second user may include the following Step 1 and Step 2:

[0129] Step 1: Input the first feature data, the second feature data, and the user portrait data of the multiple users into a scoring model, and output the scoring information of the multiple users. The scoring information is used to represent the possibility that the user is the second user.

[0130] Among them, the scoring model is used to output corresponding scoring information according to the input first feature data, second feature data, and user portrait data. The scoring model can be an LR (Logistic Regression) model.

[0131] The training process of the scoring model may include: obtaining a first training data set, where the first training data set includes the feature sets of multiple first sample users and the scoring information of each first sample user, and the sample set includes first feature data, second feature data, and user portrait data; training based on the first training data set to obtain a first scoring model; if the scoring accuracy of the first scoring model is less than the accuracy threshold, obtaining a second training set, where the second training data set includes the feature sets of multiple second sample users and the scoring information of each second sample user; training based on the first training data set and the second training data set to obtain a second scoring model, and if the scoring accuracy of the second scoring model is less than the accuracy threshold, continue to obtain training data sets and train based on the obtained training data sets until the scoring accuracy of the trained scoring model is equal to or greater than the accuracy threshold. Among them, the parameters of the scoring model can be optimized after each training. For the LR model, the weights of each feature are optimized, so that the optimal weights of each feature can be obtained through continuous training.

[0132] Step 2: Determine the second user according to the scoring information of the multiple users.

[0133] After the computer device obtains the scoring information of multiple users by using the scoring model, it can sort the multiple users in descending order according to the scores. The computer device can determine the users in the top target number of positions in the sorting as the second user. The target number can be equal to 1 or greater than 1. For example, the target number can be 5.

[0134] It should be noted that in the embodiments of the present application, it is described by taking the computer device determining the second user according to the above-mentioned multiple data (first feature data, second feature data, and user portrait data) as an example. In an alternative embodiment, the computer device can determine the second user according to the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data. For example, the computer device can determine the second user according to the first feature data and the second feature data of the multiple users, or can determine the second user according to the first feature data and the user portrait data of the multiple users. Correspondingly, the process of determining the second user may include: inputting the first feature data of the multiple users and at least one selected from the second feature data or the user portrait data into the scoring model to output the scoring information of the multiple users; determining the second user according to the scoring information of the multiple users. The specific determination process is the same as that of determining the second user according to the first feature data, the second feature data, and the user portrait data, and will not be elaborated here.

[0135] After obtaining the first feature data and the second feature data based on the first location data of the business premises of the first user, the second location data of multiple users, and the consumption behavior data, the user portrait data is combined as a feature set to determine the second user. The data in the feature set can accurately determine the user's in-store scenario, thus improving the accuracy of determining the second user. In addition, by using a scoring model for scoring, the second user can be determined simply and efficiently.

[0136] Steps 304 and 305 are a possible implementation manner for determining the second user corresponding to the target behavior among the multiple users based on the first location data, the second location data of the multiple users, the consumption behavior data, and the user portrait data. In an optional embodiment, the computer device may determine the second user corresponding to the target behavior among the multiple users based on the first location data, the second location data of the multiple users, and at least one selected from the consumption behavior data and the user portrait data of the multiple users. Specifically, the computer device may determine the second user based on the first feature data of the multiple users and at least one selected from the second feature data and the user portrait data of the multiple users. For example, the computer device may determine the second user based on the first location data, the second location data of the multiple users, and the consumption behavior data. Specifically, the computer device may obtain the first feature data and the second feature data of the multiple users based on the first location data, the second location data of the multiple users, and the consumption behavior data, and then determine the second user based on the first feature data and the second feature data of the multiple users. Alternatively, the computer device may determine the second user based on the first location data, the second location data of the multiple users, and the user portrait data. Specifically, the computer device may obtain the first feature data based on the first location data and the second location data of the multiple users, and then determine the second user based on the first feature data and the user portrait data of the multiple users. The specific process is the same as that of Steps 304 and 305 and will not be elaborated here.

[0137] To more intuitively present the above user determination method of Steps 301 to 305, the user determination method will be introduced by taking multiple users as unvouchered users, the target behavior as the unvouchered behavior, and the first user as the merchant as an example in a sample process. See Figure 4 , a flowchart of a user determination method is provided, as Figure 4As shown in the figure, the computer device can obtain the table of users without ticket verification and user location data, and then determine whether there is location data during the time period when the behavior of not verifying the ticket occurs. If there is location data, it can obtain a feature set (the shortest distance from the merchant, whether there is a consumption behavior nearby, user portrait data), score using the LR model, and rank the users to select the top 5 as suspected users. If there is no location data, it determines the possibility that the user appears within the POI range of the merchant. If there is no possibility, the user is excluded. If there is a possibility, the HMM model is used for location prediction and location supplementation. The above technical solution determines the user's in-store scenario based on user location big data, or in combination with user consumption behavior data and user portrait data, only consuming limited computing resources. In addition, using a scoring model, location prediction, etc. to capture suspected users who evade payment can reduce the average daily call volume of customer service.

[0138] The method provided by the embodiment of the present application can, by receiving a target instruction, know that a target behavior occurs in the business place of the first user. Since the target behavior is the behavior of not verifying the electronic coupon issued by the first user, it can first determine multiple users whose accounts are currently bound with un-verified electronic coupons, obtain the location data of the business place, the location data of these multiple users during the target time period, and at least one selected from the consumption behavior data and user portrait data of these multiple users. According to the obtained data, the second user who has the target behavior is determined from these multiple users. The above technical solution can accurately determine the suspicious users who have consumed in the store but have not verified the coupon based on the user's location data, consumption behavior data, user portrait data, etc., with small consumption of computing resources and high applicability.

[0139] Figure 5 It is a schematic structural diagram of a user determination device provided by an embodiment of the present application. Refer to Figure 5 , the device includes:

[0140] A receiving module 501, configured to receive a target instruction, where the target instruction is used to indicate that a target behavior occurs in the business place of the first user, and the target behavior refers to the behavior of consuming but not verifying the electronic coupon issued by the first user;

[0141] A determining module 502, configured to determine multiple users, and the accounts of these multiple users are currently bound with the un-verified electronic coupon;

[0142] An obtaining module 503, configured to obtain the first location data of the business place, the second location data of these multiple users during the target time period, and at least one selected from the consumption behavior data of these multiple users during the target time period and the user portrait data of these multiple users;

[0143] The determining module 502 is further configured to determine, according to the first location data, the second location data of the multiple users, and at least one item selected from the consumption behavior data and the user profile data of the multiple users, the second user corresponding to the target behavior among the multiple users.

[0144] In a possible implementation manner, the determining module 502 is configured to:

[0145] Determine the second user according to the first feature data of the multiple users and at least one item selected from the second feature data and the user profile data of the multiple users;

[0146] Wherein, the first feature data is obtained according to the first location data and the second location data, the second feature data is obtained according to the first location data and the consumption behavior data, the first feature data is used to represent the minimum distance among the distances between different locations of the user and the business premises within the target time period, and the second feature data is used to represent whether the user has a consumption behavior within the first distance range of the business premises within the target time period.

[0147] In a possible implementation manner, the determining module 502 is configured to:

[0148] Input the first feature data of the multiple users and at least one item selected from the second feature data and the user profile data of the multiple users into a scoring model, and output the scoring information of the multiple users, where the scoring information is used to represent the possibility that the user is the second user;

[0149] Determine the second user according to the scoring information of the multiple users.

[0150] In a possible implementation manner, the second location data includes the location data within the occurrence time period of the target behavior;

[0151] The obtaining module 503 is configured to:

[0152] Obtain the third location data uploaded by the terminal of any user within the target time period;

[0153] If the third location data includes the location data within the occurrence time period of the target behavior, then use the third location data as the second location data of any user.

[0154] In a possible implementation manner, the obtaining module 503 is further configured to:

[0155] If the third location data does not include the location data within the occurrence time period of the target behavior, then make a prediction according to the third location data to obtain the location data within the occurrence time period of the target behavior;

[0156] Use the location data within the occurrence time period of the target behavior and the third location data as the second location data of the any user.

[0157] In a possible implementation manner, the obtaining module 503 is configured to:

[0158] If the third location data does not include the location data within the occurrence time period of the target behavior, obtain the third feature data of the any user, where the third feature data is used to represent the possibility that the user appears within the second distance range of the business premises;

[0159] If the third feature data of the any user indicates that the any user has the possibility of appearing within the second distance range, perform prediction based on the third location data to obtain the location data within the occurrence time period of the target behavior.

[0160] In a possible implementation manner, the obtaining module 503 is configured to:

[0161] Obtain the third feature data of the any user according to the third location data, the time information of the third location data, the first location data, the occurrence time period, and the access mode from the location indicated by the third location data to the business premises.

[0162] In a possible implementation manner, the obtaining module 503 is configured to:

[0163] Obtain fourth location data before the occurrence time period from the third location data;

[0164] Input the fourth location data into a location prediction model, and output the location data within the occurrence time period of the target behavior.

[0165] It should be noted that: when determining a user by the user determination device provided in the above embodiments, only the division of the above functional modules is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the user determination device provided in the above embodiments and the embodiments of the user determination method belong to the same concept, and the specific implementation process is detailed in the method embodiments and will not be repeated here.

[0166] Figure 6FIG. 0 is a schematic structural diagram of a computer device 600 provided by an embodiment of the present application. The computer device 600 may vary greatly due to different configurations or performances, and may include one or more central processing units (CPUs) 601 and one or more memories 602. Among them, at least one instruction is stored in the memory 602, and the at least one instruction is loaded and executed by the processor 601 to implement the methods provided by the above-mentioned various method embodiments. Of course, the computer device may also have components such as a wired or wireless network interface, a keyboard, and an input / output interface for input and output. The computer device may also include other components for implementing device functions, which will not be elaborated here.

[0167] In an exemplary embodiment, a computer-readable storage medium storing a computer program is also provided. For example, a memory storing a computer program. When the computer program is executed by a processor, the user determination method in the above embodiment is implemented. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0168] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by hardware, or can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk, or an optical disc, etc.

[0169] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A user determination method, characterized in that, the method includes: Receiving a target instruction, where the target instruction is used to indicate that a target behavior has occurred in the business premises of the first user, and the target behavior refers to the behavior of consuming but not verifying the electronic vouchers issued by the first user; Determining a plurality of users, and the accounts of the plurality of users are currently bound with the unverified electronic vouchers; Obtaining first location data of the business premises, second location data of the plurality of users within a target time period, and at least one selected from the consumption behavior data of the plurality of users within the target time period and the user portrait data of the plurality of users; According to the first location data, the second location data of the plurality of users, and at least one selected from the consumption behavior data of the plurality of users and the user portrait data, determining a second user corresponding to the target behavior among the plurality of users.

2. The method according to claim 1, characterized in that, the determining, according to the first location data, the second location data of the plurality of users, and at least one selected from the consumption behavior data of the plurality of users and the user portrait data, a second user corresponding to the target behavior among the plurality of users includes: Determining the second user according to first feature data of the plurality of users and at least one selected from second feature data of the plurality of users and the user portrait data; wherein, the first feature data is obtained according to the first location data and the second location data, the second feature data is obtained according to the first location data and the consumption behavior data, the first feature data is used to represent the minimum distance among the distances between different locations of the user within the target time period and the business premises, and the second feature data is used to represent whether the user has a consumption behavior within a first distance range of the business premises within the target time period.

3. The method according to claim 2, characterized in that, the determining, according to first feature data of the plurality of users and at least one selected from second feature data of the plurality of users and the user portrait data, a second user includes: Inputting the first feature data of the plurality of users and at least one selected from the second feature data of the plurality of users and the user portrait data into a scoring model, and outputting scoring information of the plurality of users, where the scoring information is used to represent the possibility that the user is the second user; Determining the second user according to the scoring information of the plurality of users.

4. The method according to claim 1, characterized in that, the second location data includes location data within the time period when the target behavior occurs; The obtaining process of the second location data of any user includes: Obtaining third location data uploaded by the terminal of the any user within the target time period; If the third location data includes location data within the time period when the target behavior occurs, then using the third location data as the second location data of the any user.

5. The method according to claim 4, It is characterized in that after obtaining the third location data uploaded by the terminal of any one of the users within the target time period, the method further includes: if the third location data does not include the location data within the occurrence time period of the target behavior, predicting according to the third location data to obtain the location data within the occurrence time period of the target behavior; using the location data within the occurrence time period of the target behavior and the third location data as the second location data of any one of the users.

6. The method according to claim 5, It is characterized in that the step of, if the third location data does not include the location data within the occurrence time period of the target behavior, predicting according to the third location data to obtain the location data within the occurrence time period of the target behavior, includes: if the third location data does not include the location data within the occurrence time period of the target behavior, obtaining the third feature data of any one of the users, where the third feature data is used to represent the possibility that the user appears within the second distance range of the business premises; if the third feature data of any one of the users indicates that the user has the possibility of appearing within the second distance range, predicting according to the third location data to obtain the location data within the occurrence time period of the target behavior.

7. The method according to claim 6, It is characterized in that the step of obtaining the third feature data of any one of the users includes: obtaining the third feature data of any one of the users according to the third location data, the time information of the third location data, the first location data, the occurrence time period, and the way of passing from the location indicated by the third location data to the business premises.

8. The method according to claim 6, It is characterized in that the step of predicting according to the third location data to obtain the location data within the occurrence time period of the target behavior includes: obtaining fourth location data before the occurrence time period from the third location data; inputting the fourth location data into a location prediction model and outputting the location data within the occurrence time period of the target behavior.

9. A user determination device, It is characterized in that the device includes: a receiving module, configured to receive a target instruction, where the target instruction is used to indicate that a target behavior occurs within the business premises of a first user, and the target behavior refers to the behavior of consuming but not verifying the electronic vouchers issued by the first user; a determining module, configured to determine a plurality of users whose accounts are currently bound with the unverified electronic vouchers; an obtaining module, configured to obtain the first location data of the business premises, the second location data of the plurality of users within the target time period, and at least one selected from the consumption behavior data of the plurality of users within the target time period and the user portrait data of the plurality of users; The determining module is further configured to determine a second user corresponding to the target behavior among the multiple users according to the first location data, the second location data of the multiple users, and at least one selected from the consumption behavior data and the user profile data of the multiple users.

10. A computer device, characterized in that the computer device includes a processor and a memory, and at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the user determination method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that at least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by a processor to implement the user determination method according to any one of claims 1 to 8.

Images