Cycling card recommendation method, device, computer equipment and readable storage medium
By calculating the card score and cross score of the cycling card, combining user tags and historical data, the problem of low accuracy in cycling card recommendations in the existing technology is solved, and a more accurate and personalized cycling card recommendation is achieved.
Patent Information
- Application Number
- CN202410733018.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-07
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-06-07
AI Technical Summary
The existing riding card recommendation methods are sorted only by price, with single considerations, resulting in low recommendation accuracy.
By obtaining the target user's historical card resource usage data and user tags, the card score and cross score of the riding card are calculated, and the weights of each dimension are weighted to generate a total score, thereby realizing personalized recommendations of the riding card.
It improves the accuracy and fit of riding card recommendations, meets users' personalized needs, and enhances the effectiveness of recommendations.
Smart Images

Figure CN118313905B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of shared vehicle technology, and in particular to a method, device, computer equipment, computer-readable storage medium, and computer program product for recommending a riding card. Background Art
[0002] With the continuous development of the shared bicycle field, shared vehicle operators will recommend various riding cards to users based on the riding card recommendation method for users to purchase, thereby increasing the income and user experience of shared bicycle operators.
[0003] The current method for recommending cycling cards sorts the cycling cards in descending order of their prices to obtain a cycling card sequence, and displays the cycling card sequence to the user.
[0004] However, the current cycling card recommendation method only recommends cycling cards to users based on price factors, which is a single factor. Therefore, the current cycling card recommendation method has low accuracy. Summary of the invention
[0005] Based on this, it is necessary to provide a cycling card recommendation method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.
[0006] In a first aspect, the present application provides a cycling card recommendation method, comprising:
[0007] Obtain each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage dataset of the target user;
[0008] Performing card score calculation processing on the resource usage data corresponding to each of the riding cards to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set;
[0009] The total score of the riding card is determined according to the card score and the cross score, and the riding card recommendation result is determined according to the total score of each riding card.
[0010] In one embodiment, before obtaining each riding card corresponding to the target user group to which the target user belongs and the historical card resource usage data set of the target user, the method further includes:
[0011] Determine a user label for each user based on the city where each user is located and the number of accumulated riding orders;
[0012] The users are grouped based on the user tags to obtain user groups, and the discount data of each user group is matched.
[0013] In one embodiment, determining the user tag of each user according to the city where each user is located and the accumulated number of riding orders includes:
[0014] For each user, determining a user city tag of the user according to the city where the user is located;
[0015] Determine a user frequency tag of the user based on the cumulative number of riding orders of the user and a preset frequency tag rule;
[0016] A user tag for the user is constructed based on the user city tag and the user frequency tag.
[0017] In one embodiment, obtaining each riding card corresponding to the target user group to which the target user belongs includes:
[0018] Obtain the historical cumulative order data set of the target user group to which the target user belongs;
[0019] Based on the historical accumulated order data set, determine the average number of orders of the target user group in different time periods;
[0020] Determine each resource usage data based on each of the time periods and each of the average number of orders;
[0021] Each riding card is generated according to the resource usage data and the discount data corresponding to the target user group.
[0022] In one embodiment, the resource usage data includes the number of days available for riding, the number of times available for riding, and the resource value, and the resource usage data is determined based on each of the time periods and each of the average number of orders, including:
[0023] For the average number of orders in each time period, the time period is determined as the number of days available for riding, and the average number of orders is determined as the number of available rides;
[0024] The resource value is determined according to the average number of orders of a preset single resource value.
[0025] In one embodiment, the riding card corresponds to resource usage data of different dimensions, and the card score calculation processing is performed on the resource usage data corresponding to each riding card to obtain the card score of the riding card, including:
[0026] For each dimension of resource usage data, determine the maximum resource usage data and the minimum resource usage data in the resource usage data corresponding to each of the riding cards;
[0027] For each of the riding cards, the maximum resource usage data, the minimum resource usage data and the resource usage data corresponding to the riding card are normalized to obtain a card score of the riding card in the dimension.
[0028] In one embodiment, the historical card resource usage data set includes historical card resource usage data of different dimensions, and determining the cross score of the cycling card according to the resource usage data and the historical card resource usage data set includes:
[0029] For each dimension of the historical card resource usage data, determine target resource usage data of the same dimension as the historical card resource usage data from the resource usage data corresponding to each riding card;
[0030] Performing difference processing on the historical card resource usage data and each of the target resource usage data to obtain each first difference, and determining a maximum first difference and a minimum first difference among each of the first differences;
[0031] The maximum first difference, the minimum first difference and the historical card resource usage data are normalized to obtain the cross-characteristic value of the riding card.
[0032] In a second aspect, the present application also provides a cycling card recommendation device, comprising:
[0033] An acquisition module, used to acquire each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage data set of the target user;
[0034] A calculation module, used for performing card score calculation processing on the resource usage data corresponding to each riding card to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set;
[0035] The determination module is used to determine the total score of the riding card according to the card score and the cross score, and determine the riding card recommendation result according to the total score of each riding card.
[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0037] Obtain each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage dataset of the target user;
[0038] Performing card score calculation processing on the resource usage data corresponding to each of the riding cards to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set;
[0039] The total score of the riding card is determined according to the card score and the cross score, and the riding card recommendation result is determined according to the total score of each riding card.
[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0041] Obtain each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage dataset of the target user;
[0042] Performing card score calculation processing on the resource usage data corresponding to each of the riding cards to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set;
[0043] The total score of the riding card is determined according to the card score and the cross score, and the riding card recommendation result is determined according to the total score of each riding card.
[0044] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0045] Obtain each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage dataset of the target user;
[0046] Performing card score calculation processing on the resource usage data corresponding to each of the riding cards to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set;
[0047] The total score of the riding card is determined according to the card score and the cross score, and the riding card recommendation result is determined according to the total score of each riding card.
[0048] The above-mentioned riding card recommendation method, device, computer equipment, computer-readable storage medium and computer program product obtain each riding card corresponding to the target user group to which the target user belongs and the historical card resource usage data set of the target user; perform card score calculation processing on the resource usage data corresponding to each riding card to obtain the card score of the riding card, and determine the cross score of the riding card according to the resource usage data and the historical card resource usage data set; determine the total score of the riding card according to the card score and the cross score, and determine the riding card recommendation result according to the total score of each riding card. Using this method, each riding card is obtained according to the target user group to which the target user belongs, and each riding card that needs to be recommended to the user is determined. And based on the card score and cross score of each riding card, the total score of the riding card is determined, and the fit between each riding card and the user is clarified. Then, recommending each riding card to the user based on each total score realizes personalized recommendation of riding cards and improves the accuracy of the riding card recommendation method. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0050] Figure 1 A schematic diagram of a flow chart of a cycling card recommendation method in one embodiment;
[0051] Figure 2 A schematic diagram of a process for determining each user group in an embodiment;
[0052] Figure 3 A schematic diagram of a process for determining a user tag in one embodiment;
[0053] Figure 4 A schematic diagram of a process of obtaining a cycling card in one embodiment;
[0054] Figure 5 A schematic diagram of a process for determining resource usage data in one embodiment;
[0055] Figure 6 A schematic diagram of a process for determining a card score in one embodiment;
[0056] Figure 7 A schematic diagram of a process for determining a crossover score in one embodiment;
[0057] Figure 8 is a structural block diagram of a cycling card recommendation device in one embodiment;
[0058] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0060] In one embodiment, Figure 1 As shown, a method for recommending a cycling card is provided. The embodiment of the present application takes the method applied to a computer device as an example for explanation. The embodiment of the present application does not limit the execution device of the method for recommending a cycling card, and includes the following steps 102 to 106:
[0061] Step 102, obtaining each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage dataset of the target user.
[0062] The user group is determined based on the user tag of the user. The cycling card recommendation request contains the target user ID of the target user. The historical card resource dataset represents the historical purchase of cycling cards by the target user.
[0063] In implementation, when the target user wants to purchase a cycling card, the target user initiates a cycling card recommendation request to the computer device through the user terminal. Based on the target user identifier, the computer device obtains the historical cumulative order data set of the target user group to which the target user belongs, and generates each cycling card based on the historical cumulative order data set. At the same time, the computer device obtains the historical card resource usage data set of the target user from the database based on the target user identifier.
[0064] Optionally, the historical card resource usage data includes the average number of days for the target user to purchase a card in the last m days, the average number of times the target user purchased a card in the last m days, the average price of the target user's card purchase in the last m days, the number of days for the last card purchase, the number of times the target user purchased a card in the last m days, and the price of the last card purchase. The average number of days for the target user to purchase a card in the last m days is the average number of days that the target user can ride on the cycling card purchased in the last m days. Wherein, m is a natural number greater than 1, and m is preferably greater than 30. Exemplarily, m can be 90. The embodiment of the present application does not limit m.
[0065] Step 104, performing card score calculation processing on the resource usage data corresponding to each cycling card to obtain the card score of the cycling card, and determining the cross score of the cycling card based on the resource usage data and the historical card resource usage data set.
[0066] The cycling card corresponds to resource usage data of different dimensions. The first difference is the difference between the historical card resource data and the target resource usage data.
[0067] In implementation, the computer device determines the maximum resource usage data and the minimum resource usage data of each dimension in the resource usage data corresponding to each riding card. Then, the computer device normalizes the resource usage data, the maximum resource usage data and the minimum resource usage data for each dimension of each riding card to obtain the card score of the riding card. Then, the computer device determines the maximum first difference and the minimum second difference for the historical card resource data of each dimension according to the historical card resource usage data and the target resource usage data corresponding to the historical card resource usage data. Then, the computer device normalizes the maximum first difference, the minimum first difference and the historical card resource usage data to obtain the cross score of the riding card.
[0068] Step 106, determining the total score of the riding card according to the card score and the cross score, and determining the riding card recommendation result according to the total score of each riding card.
[0069] In implementation, the weights of the card score and cross score of each dimension are pre-set in the computer device. For each riding card, the computer device performs weighted processing on the card score and cross score of the riding card according to the weights of the card score of each dimension and the weights of the cross score of each dimension to obtain the total score of the riding card. Then, the computer device sorts the riding cards in descending order of the total score to obtain a riding card sequence. Then, the computer device sends the riding card sequence to the terminal of the target user, so that the terminal displays the riding card sequence.
[0070] In an exemplary embodiment, the card score includes the card scores of the dimensions of available riding days, available riding times, card selling price, and card discount. The cross score includes the cross score of the dimensions of the average number of days for card purchases in the past 90 days, the average number of times for card purchases in the past 90 days, the average selling price for card purchases in the past 90 days, the number of days for the most recent card purchase, the number of times for the most recent card purchase, and the most recent selling price. The weights of the card score and cross score of each dimension are pre-set in the computer device, and the weights of the card score and cross score of each dimension are shown in Table 1 below:
[0071] Table 1
[0072]
[0073] For each riding card, the computer device performs weighted processing on the weights of the card scores of each dimension, the weights of the cross scores of each dimension, each card score and each cross score according to the total score algorithm to obtain the total score of the riding card. The total score algorithm is shown in the following formula (1):
[0074] (1)
[0075] In the above formula (1), For the A cycling card, For the dimensions. For the The weight of the dimension, For the Cycling Card The scores of each dimension include cross scores and card scores.
[0076] In an optional embodiment, a display quantity threshold is pre-set in the computer device. After obtaining the riding card sequence, the computer device determines the target riding card sequence in the riding card sequence according to the display quantity threshold, and sends the target riding card sequence to the terminal of the target user. The terminal displays the target riding card sequence to complete the riding card recommendation for the target user. Among them, the target riding card sequence is displayed in a list combination of [(card name, card price, card order), ...].
[0077] In the above-mentioned cycling card recommendation method, each cycling card is obtained according to the target user group to which the target user belongs, and each cycling card that needs to be recommended to the user is determined. And based on the card score and cross score of each cycling card, the total score of the cycling card is determined, and the fit between each cycling card and the user is clarified. Then, each cycling card is recommended to the user based on each total score, so as to realize personalized recommendation of cycling cards and improve the accuracy of the cycling card recommendation method.
[0078] In an exemplary embodiment, before recommending a cycling card to a target user, it is necessary to first determine the user group to which each user belongs. Figure 2 As shown, before step 102 is executed, the specific processing process of the riding card recommendation method also includes steps 202 to 204. Among them:
[0079] Step 202, determine the user tag of each user according to the city where each user is located and the cumulative number of riding orders.
[0080] The user is an initial user who has ridden within the preset first time range. The user data includes the city where the user is located and the cumulative number of riding orders of the user.
[0081] In implementation, the computer device obtains user data of each user and determines a user tag of each user based on the city where the user is located and the cumulative number of riding orders of the user.
[0082] In an exemplary embodiment, the first time range is 180 days. The computer device obtains user data of each initial user. The computer device determines whether each of the initial users has had a riding behavior within 180 days. If the initial user has had a riding behavior within 180 days, the computer device determines the initial user as a user.
[0083] Optionally, the first time range may be limited to 180 days, or may be 90 days. The embodiment of the present application does not limit the preset time range.
[0084] Step 204: group the users based on their tags to obtain user groups, and match discount data for each user group.
[0085] In implementation, the computer device groups users with the same user tag into the same user group to obtain user groups. Then, the computer device matches the discount data of each user group.
[0086] In an exemplary embodiment, the discount data is the discount rate of the cycling card, and the discount rate is the same for the same user group. The discount rate is determined with the purpose of maximizing the order penetration rate and the average card revenue per order. The expression of the discount rate is shown in the following formula (2):
[0087] (2)
[0088] In the above formula (2), the selling price is the selling price of the cycling card, and the original price is the original price of the cycling card. The expression of order penetration rate is shown in the following formula (3):
[0089] (3)
[0090] In the above formula (3), the number of card orders on the day is the number of cycling cards used on the day, and the total number of orders on the day is the number of order cards purchased on the day. The expression of the average card face value revenue data is shown in the following formula (4):
[0091] (4)
[0092] In the above formula (4), the average card revenue per unit is the revenue value brought by each cycling card. Generally speaking, the smaller the discount rate, the higher the order penetration rate, and the lower the average card revenue per unit. Conversely, the larger the discount rate, the lower the order penetration rate, and the higher the average card revenue per unit.
[0093] The computer device determines the selling price of each cycling card in advance according to different discount rates, and sells each cycling card at each selling price to obtain the order penetration rate and average card revenue data under different discount rates. The discount rate range is [0.1, 0.9]. The computer device matches the discount data corresponding to the user group with the goal of maximizing the order penetration rate and average card revenue data. .
[0094] In this embodiment, the user tag of the user is determined based on the city where the user is located and the cumulative number of riding orders, and the users are grouped according to the user tags to obtain user groups, which facilitates the subsequent determination of the riding card recommended to the user based on the user group, thereby improving the accuracy of the riding card recommendation method.
[0095] In an exemplary embodiment, Figure 3 As shown, the specific processing process of step 202 includes steps 302 to 306. Among them:
[0096] Step 302: for each user, determine the user city tag of the user according to the city where the user is located.
[0097] During implementation, the computer device determines, for each user, a user city tag of the user according to the number of competitors in the city where the user is located.
[0098] Specifically, if the number of competitors is 0, the computer device determines that the user city tag is exclusive. If the number of competitors is 1, the computer device determines that the user city tag is weakly competitive. If the number of competitors is 2 or 3, the computer device determines that the user city tag is moderately competitive. If the number of competitors is greater than 3, the computer device determines that the user city tag is strongly competitive.
[0099] Optionally, the correspondence between the number of competing objects and the user city tags is determined according to the cycling card recommendation requirements, which is not limited in the embodiments of the present application.
[0100] Step 304, determining the user frequency tag of the user based on the user's cumulative number of riding orders and preset frequency tag rules.
[0101] The cumulative number of riding orders is the total number of riding orders placed by the user within a preset second time range. The second time range is shorter than the first time range.
[0102] In implementation, a frequency label rule is pre-set in the computer device, and the frequency label rule includes different cumulative riding order number ranges and user frequency labels corresponding to the cumulative riding order number ranges. The computer device determines the target cumulative riding order number range in which the cumulative riding order number is located, and determines the user frequency label corresponding to the target cumulative riding order number range as the user frequency label of the user.
[0103] Specifically, the cumulative riding order number range and the user frequency label corresponding to the cumulative riding order number range are shown in Table 2 below:
[0104] Table 2
[0105]
[0106] If the user's cumulative number of riding orders is 0, the computer device determines that the cumulative number of riding orders of the user's target is in the range of 0, and determines that the user's user frequency label is resurrection. If the user's cumulative number of riding orders is 2, the computer device determines that the cumulative number of riding orders of the user's target is in the range of [1,5], and determines that the user's user frequency label is low frequency. If the user's cumulative number of riding orders is 8, the computer device determines that the cumulative number of riding orders of the user's target is in the range of [6,15], and determines that the user's user frequency label is medium frequency. If the user's cumulative number of riding orders is 18, the computer device determines that the cumulative number of riding orders of the user's target is in the range of [16,30], and determines that the user's user frequency label is high frequency. If the user's cumulative number of riding orders is 35, the computer device determines that the cumulative number of riding orders of the user's target is in the range of >30, and determines that the user's user frequency label is ultra-high frequency.
[0107] Step 306: construct a user tag for the user based on the user city tag and the user frequency tag.
[0108] In implementation, the computer device splices the user city tag and the user frequency tag to obtain the user tag of the user. For example, if the user city tag of the user is exclusive and the user frequency tag is medium frequency, the user tag of the user is exclusive medium frequency.
[0109] In an exemplary embodiment, user city tags include exclusive, weak competition, medium competition and strong competition. User frequency tags include resurrection, low frequency, medium frequency, high frequency and ultra-high frequency. Therefore, the user tags of the user include a total of 20 categories, namely exclusive resurrection, exclusive low frequency, exclusive medium frequency, exclusive high frequency, exclusive ultra-high frequency, weak competition resurrection, weak competition low frequency, weak competition medium frequency, weak competition high frequency, weak competition ultra-high frequency, medium competition resurrection, medium competition low frequency, medium competition medium frequency, medium competition high frequency, medium competition ultra-high frequency, strong competition resurrection, strong competition low frequency, strong competition medium frequency, strong competition high frequency and strong competition ultra-high frequency. The user tags are calculated offline by the computer device every day.
[0110] In this embodiment, the user city tag is determined by the city where the user is located, and the user frequency tag is determined according to the cumulative number of riding orders of the user, so that the user tags in different dimensions are obtained and the granularity of the user tags is refined. Then, the user tag is determined according to the user city tag and the user frequency tag, and the user's personalized information is obtained.
[0111] In an exemplary embodiment, Figure 4 As shown, the specific processing process of obtaining each riding card corresponding to the target user group to which the target user belongs in step 102 includes steps 402 to 408. Among them:
[0112] Step 402: Obtain a historical cumulative order data set of the target user group to which the target user belongs.
[0113] During implementation, the computer device obtains a historical cumulative order data set of the target user group to which the target user belongs.
[0114] Step 404: Determine the average number of orders of the target user group in different time periods based on the historical cumulative order data set.
[0115] During implementation, the computer device processes the historical cumulative order data set according to the average order number algorithm to obtain the average order number of the user group in different time periods.
[0116] Specifically, the average order number algorithm is shown in the following formula (5):
[0117] (5)
[0118] In the above formula (5), the time period includes 3 days, 5 days, 7 days, 10 days, 15 days, 20 days and 30 days. For the Daily target user group All users of . 30 days for history, Indicates User's recent Daily cumulative orders. belong .
[0119] The computer equipment processes the historical cumulative order data set through an average algorithm, and can obtain the average number of orders of the target user group on 3 days, 5 days, 7 days, 10 days, 15 days, 20 days and 30 days.
[0120] Step 406, determining resource usage data based on each time period and each average number of orders.
[0121] Among them, resource usage data includes the number of days that can be ridden, the number of times that can be ridden and the resource value.
[0122] In implementation, the computer device determines the number of rideable orders according to each time period, and determines the number of rideable times according to each average number of orders. Then, the computer device determines the resource value according to the preset single resource value and the average number of orders.
[0123] Step 408, generating each riding card according to each resource usage data and the discount data corresponding to the target user group.
[0124] In implementation, the computer device updates the resource values in the resource usage data according to the discount data corresponding to the target user group. Then, the computer device generates each riding card according to the updated resource values, the number of riding days and the number of riding times.
[0125] In an exemplary embodiment, the resource value is the original price of the cycling card, and the computer device performs a product operation on the resource value and the discount data to obtain an updated resource value. The updated resource value is the selling price of the cycling card.
[0126] In an exemplary embodiment, the computer device generates each riding card based on the riding card generation algorithm, the updated resource value, the riding days and the riding times. The riding card generation algorithm is shown in the following formula (6):
[0127] (6)
[0128] In the above formula (6), Target user group Cycling card, Belongs to (1, 2, 3), indicating the single deduction amount of the cycling card. For example, a cycling card for 4 rides in 3 days has a single deduction of 1 yuan, and the original price is 4 yuan. The number of days you can ride. The number of times you can ride.
[0129] For example, if the time period is 3 days, the corresponding average number of orders is 5, and the discount data for the target user group is 0.8. The computer device determines that the number of days available for riding is 3 and the number of times available for riding is 5. Then, the computer device determines the value of each resource based on the number of times available for riding and the amount of a single deduction, and the obtained resource values are 5, 10, and 15, respectively. Then, the computer device updates the value of each resource based on the discount data, and obtains updated resource values of 4, 8, and 12. The computer device generates each riding card based on the updated resource value, the number of days available for riding, and the number of times available for riding. The riding cards are riding card A {number of days available for riding: 3; number of times available for riding: 5; resource value: 4}, B {number of days available for riding: 3; number of times available for riding: 5; resource value: 8}, C {number of days available for riding: 3; number of times available for riding: 5; resource value: 12}.
[0130] In this embodiment, the riding cards corresponding to the target user group are generated through the historical cumulative order data set of the target user group, so that the riding cards are customized according to the information of the target user group, and the riding cards that better meet the user needs are obtained, thereby improving the accuracy of the riding card recommendation method.
[0131] In an exemplary embodiment, the resource usage data includes the number of days available for riding, the number of times available for riding, and the resource value, such as Figure 5 As shown, the specific processing process of step 406 includes steps 502 to 504. Among them:
[0132] Step 502, for the average number of orders in each time period, the time period is determined as the number of days that can be ridden, and the average number of orders is determined as the number of times that can be ridden.
[0133] In implementation, the computer device determines the time period as the number of rideable orders based on the average number of orders in each time period. At the same time, the computer device determines the average number of orders in the time period as the number of rideable times.
[0134] Step 504, determining the resource value according to the preset single resource value and the average number of orders.
[0135] In implementation, the computer device is pre-set with each single resource value, and the computer device performs a product operation on each single resource value and the average number of orders to obtain the resource value.
[0136] In an exemplary embodiment, the single resource value is a single deduction amount, and the single deduction amount is 1, 2, and 3. The average number of orders is 5. The computer device multiplies the average number of orders and each single deduction amount to obtain resource values of 5, 10, and 15. The resource values are the original prices of the cycling card, which are 5, 10, and 15 respectively.
[0137] In this embodiment, the resource usage data of the cycling card is determined based on each time period and each average number of orders, so that the cycling card can be customized according to the information of the target user group, thereby obtaining a cycling card that better meets the user's needs and improving the accuracy of the cycling card recommendation method.
[0138] In an exemplary embodiment, the riding card corresponds to resource usage data of different dimensions, such as Figure 6 As shown, the specific processing process of performing card score calculation processing on the resource usage data corresponding to each cycling card in step 104 to obtain the card score of the cycling card includes steps 602 to 604. Among them:
[0139] Step 602, for each dimension of resource usage data, determine the maximum resource usage data and the minimum resource usage data in the resource usage data corresponding to each riding card.
[0140] During implementation, the computer device determines the maximum resource usage data and the minimum resource usage data in the resource usage data of each riding card for each dimension of resource usage data.
[0141] Step 604, for each cycling card, normalize the maximum resource usage data, the minimum resource usage data and the resource usage data corresponding to the cycling card to obtain the card score of the cycling card in the dimension.
[0142] In implementation, the computer device performs data normalization processing on the maximum resource usage data, the minimum resource usage data and the resource usage data according to the first normalization algorithm for each resource usage data of each cycling card, and obtains the card score of the cycling card in the dimension. Among them, the expression of the maximum resource usage data is shown in the following formula (7):
[0143] (7)
[0144] In the above formula (7), For the Maximum resource usage data in each dimension. is the maximum function. For the first card Resource usage data in 3 dimensions, For the Card No. Resource usage data in 3 dimensions, is the number of cycling cards. The expression of the minimum resource usage data is shown in the following formula (8):
[0145] (8)
[0146] In the above formula (8), For the Minimum resource usage data in each dimension. is the minimum function. For the first card Resource usage data in 3 dimensions, For the Card No. Resource usage data in 3 dimensions, is the number of cycling cards. The first normalization algorithm is shown in the following formula (9):
[0147] (9)
[0148] In the above formula (9), No. The maximum resource usage data in each dimension, For the Minimum resource usage data in each dimension. For the Zhang Cardi Dimensional resource usage data. For the Zhang Cardi The card scores for each dimension.
[0149] In this embodiment, by performing card score calculation processing on the resource usage data of each cycling card, the card score in the cycling card dimension is obtained, which is convenient for subsequent determination of the total score, clarifies the fitness of the cycling card for the target user, and improves the accuracy of the cycling card recommendation method.
[0150] In an exemplary embodiment, the historical card resource usage data set includes historical card resource usage data of different dimensions, such as Figure 7 As shown, the specific process of determining the cross score of the cycling card according to the resource usage data and the historical card resource usage data set in step 104 includes steps 702 to 706. Among them:
[0151] Step 702: for each dimension of the historical card resource usage data, determine the target resource usage data of the same dimension as the historical card resource usage data from the resource usage data corresponding to each riding card.
[0152] During implementation, the computer device determines, for each dimension of the historical card resource usage data, target resource usage data of the same dimension as the historical card resource usage data from among the resource usage data corresponding to each riding card.
[0153] In an exemplary embodiment, the historical card resource usage data includes the average number of days for card purchases in the past 90 days, the average number of times the card is purchased in the past 90 days, the average price of the card purchases in the past 90 days, the number of days for the most recent card purchase, the number of times the card is purchased in the most recent card purchase, and the price of the most recent card purchase. The computer device determines the number of days that can be ridden in the same dimension as the average number of days for card purchases in the past 90 days in the corresponding resource usage data in each riding card as the target resource usage data for the average number of times the card is purchased in the past 90 days. The computer device determines the number of times that can be ridden in the same dimension as the average number of times the card is purchased in the past 90 days in the corresponding resource usage data in each riding card as the target resource usage data for the average number of times the card is purchased in the past 90 days. The computer device determines the card price in the same dimension as the average price of the card purchase in the past 90 days in the corresponding resource usage data in each riding card as the target resource usage data for the average price of the card purchase in the past 90 days. The computer device determines the number of days that can be ridden in the same dimension as the average number of days for card purchases in the past 90 days in the corresponding resource usage data in each riding card as the target resource usage data for the average price of the card purchase in the past 90 days. The computer device determines the number of days that can be ridden in the same dimension as the average number of days for card purchases in the past 90 days in the corresponding resource usage data in each riding card as the target resource usage data for the number of days for the most recent card purchase. The computer device determines the number of available rides in the same dimension as the number of recent card purchases from each resource usage data corresponding to each cycling card as the target resource usage data. The computer device determines the card price in the same dimension as the price of the recent card purchase from each resource usage data corresponding to each cycling card as the target resource usage data.
[0154] Step 704: perform difference processing on the historical card resource usage data and each target resource usage data to obtain each first difference, and determine the maximum first difference and the minimum first difference among each first difference.
[0155] In implementation, the computer device performs difference processing on the historical card resource usage data and each target resource usage data according to the difference formula to obtain each first difference. Then, the computer device determines the maximum first difference and the minimum first difference among each first difference. The difference formula is shown in the following formula (10):
[0156] (10)
[0157] In the above formula (10), A function that finds the absolute value of data. For the Cycling Card Historical card resource usage data in 3 dimensions The corresponding target resource usage data. For the Cycling Card The first difference of the dimension. The expression of the maximum first difference is shown in the following formula (11):
[0158] (11)
[0159] In the above formula (11), For the Cycling Card The first difference in dimensions. For the The maximum first difference in dimensions. is the maximum function. The expression of the minimum first difference is shown in the following formula (12):
[0160] (12)
[0161] In the above formula (12), For the Cycling Card The first difference in dimensions. For the The smallest first difference in dimensions. is the minimum function.
[0162] Step 706, normalize the maximum first difference, the minimum first difference and the historical card resource usage data to obtain the cross-characteristic value of the riding card.
[0163] In implementation, the computer device performs data normalization processing on the maximum first difference, the minimum first difference and the historical card resource usage data according to the second normalization algorithm to obtain the cross-characteristic value of the riding card. The second normalization algorithm is shown in the following formula (13):
[0164] (13)
[0165] In the above formula (13), For the The maximum first difference in dimensions, For the The smallest first difference in dimensions. For the Zhang Cardi Historical resource usage data in three dimensions. For the Zhang Cardi The cross-score of the dimensions.
[0166] In this embodiment, by normalizing the resource usage data of each cycling card and the resource usage data, the cross-score of the cross-dimension of the cycling card and the target user is obtained, which facilitates the subsequent determination of the total score, clarifies the fitness of the cycling card for the target user, and improves the accuracy of the cycling card recommendation method.
[0167] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0168] Based on the same inventive concept, the embodiment of the present application also provides a cycling card recommendation device for implementing the cycling card recommendation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more cycling card recommendation device embodiments provided below can refer to the limitations of the cycling card recommendation method above, and will not be repeated here.
[0169] In an exemplary embodiment, Figure 8As shown, a cycling card recommendation device 800 is provided, comprising: an acquisition module 801, a calculation module 802 and a determination module 803, wherein:
[0170] The acquisition module 801 is used to acquire each riding card corresponding to the target user group to which the target user belongs and the target user's historical card resource usage data set.
[0171] The operation module 802 is used to perform card score operation processing on the resource usage data corresponding to each riding card to obtain the card score of the riding card, and determine the cross score of the riding card based on the resource usage data and the historical card resource usage data set.
[0172] The determination module 803 is used to determine the total score of the riding card according to the card score and the cross score, and determine the riding card recommendation result according to the total score of each riding card.
[0173] In an exemplary embodiment, the cycling card recommendation device 800 further includes:
[0174] The second determination module is used to determine the user tag of each user based on the city where each user is located and the cumulative number of riding orders.
[0175] The grouping module is used to group users based on their tags to obtain user groups and match discount data for each user group.
[0176] In an exemplary embodiment, the second determining module includes:
[0177] The first determination submodule is used to determine the user city tag of each user according to the city where the user is located.
[0178] The second determination submodule is used to determine the user frequency label of the user based on the user's cumulative number of riding orders and a preset frequency label rule.
[0179] The first construction submodule is used to construct a user tag for the user based on the user city tag and the user frequency tag.
[0180] In an exemplary embodiment, the acquisition module 801 includes a first acquisition submodule and a second acquisition submodule. The first acquisition submodule includes:
[0181] The third acquisition submodule includes acquiring a historical accumulated order data set of the target user group to which the target user belongs.
[0182] The third determination submodule is used to determine the average number of orders of the target user group in different time periods based on the historical accumulated order data set.
[0183] The fourth determination submodule is used to determine each resource usage data based on each time period and each average number of orders.
[0184] The first generation submodule is used to generate each riding card according to each resource usage data and discount data corresponding to the target user group.
[0185] In an exemplary embodiment, the resource usage data includes the number of days available for riding, the number of times available for riding, and the resource value, and the fourth determination submodule includes:
[0186] The fifth determination submodule is used to determine the time period as the number of rideable days and the average number of orders as the number of rideable times based on the average number of orders in each time period.
[0187] The sixth determination submodule is used to determine the resource value according to a preset average number of orders for a single resource value.
[0188] In an exemplary embodiment, the cycling card corresponds to resource usage data of different dimensions, and the operation module 802 includes a first operation submodule and a seventh determination submodule. Among them, the first operation submodule includes:
[0189] The eighth determination submodule is used to determine the maximum resource usage data and the minimum resource usage data in the resource usage data corresponding to each riding card for each dimension of resource usage data.
[0190] The first processing submodule is used to normalize the maximum resource usage data, the minimum resource usage data and the resource usage data corresponding to the cycling card for each cycling card to obtain the card score of the cycling card in the dimension.
[0191] In an exemplary embodiment, the historical card resource usage data set includes historical card resource usage data of different dimensions, and the operation module 802 includes a first operation submodule and a seventh determination submodule. The seventh determination submodule includes:
[0192] The ninth determination submodule is used to determine, for each dimension of the historical card resource usage data, target resource usage data of the same dimension as the historical card resource usage data in the resource usage data corresponding to each riding card.
[0193] The second processing submodule is used to perform difference processing on the historical card resource usage data and each target resource usage data to obtain each first difference, and determine the maximum first difference and the minimum first difference among each first difference.
[0194] The third processing submodule is used to normalize the maximum first difference, the minimum first difference and the historical card resource usage data to obtain the cross characteristic value of the riding card.
[0195] Each module in the above-mentioned cycling card recommendation device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0196] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for recommending a riding card is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0197] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0198] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
[0199] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0200] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0201] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0202] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0203] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0204] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for recommending a cycling card, characterized in that: The method comprises: Obtain each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage dataset of the target user; Performing card score calculation processing on the resource usage data corresponding to each of the riding cards to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set; Determining the total score of the riding card according to the card score and the cross score, and determining the riding card recommendation result according to the total score of each riding card; The step of obtaining the riding cards corresponding to the target user group to which the target user belongs includes: Obtain the historical cumulative order data set of the target user group to which the target user belongs; Based on the historical cumulative order data set, the average number of orders of the target user group in different time periods is determined; the average number of orders is determined based on an average order number algorithm, and the average number of orders is ; Wherein, the time period includes 3 days, 5 days, 7 days, 10 days, 15 days, 20 days and 30 days; For the Daily target user group All users of 30 days for history, Indicates User's recent Daily cumulative orders; belong ; Determine each resource usage data based on each of the time periods and each of the average number of orders; Each riding card is generated according to the resource usage data and the discount data corresponding to the target user group.
2. The method according to claim 1, characterized in that Before obtaining each riding card corresponding to the target user group to which the target user belongs and the historical card resource usage data set of the target user, the method further includes: Determine a user label for each user based on the city where each user is located and the number of accumulated riding orders; The users are grouped based on the user tags to obtain user groups, and the discount data of each user group is matched.
3. The method according to claim 2, characterized in that Determining the user tag of each user according to the city where each user is located and the accumulated number of riding orders includes: For each user, determining a user city tag of the user according to the city where the user is located; Determine a user frequency tag of the user based on the cumulative number of riding orders of the user and a preset frequency tag rule; A user tag for the user is constructed based on the user city tag and the user frequency tag.
4. The method according to claim 1, characterized in that: The resource usage data includes the number of days available for riding, the number of times available for riding, and the resource value. The resource usage data is determined based on each of the time periods and each of the average number of orders, including: For the average number of orders in each time period, the time period is determined as the number of days available for riding, and the average number of orders is determined as the number of available rides; The resource value is determined according to the average number of orders of a preset single resource value.
5. The method according to claim 1, characterized in that The riding card corresponds to resource usage data of different dimensions, and the card score calculation processing is performed on the resource usage data corresponding to each riding card to obtain the card score of the riding card, including: For each dimension of resource usage data, determine the maximum resource usage data and the minimum resource usage data in the resource usage data corresponding to each of the riding cards; For each of the riding cards, the maximum resource usage data, the minimum resource usage data and the resource usage data corresponding to the riding card are normalized to obtain a card score of the riding card in the dimension.
6. The method according to claim 1, characterized in that The historical card resource usage data set includes historical card resource usage data of different dimensions, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set includes: For each dimension of the historical card resource usage data, determine target resource usage data of the same dimension as the historical card resource usage data from the resource usage data corresponding to each riding card; Performing difference processing on the historical card resource usage data and each of the target resource usage data to obtain each first difference, and determining a maximum first difference and a minimum first difference among each of the first differences; The maximum first difference, the minimum first difference and the historical card resource usage data are normalized to obtain the cross-characteristic value of the riding card.
7. The method according to claim 1, characterized in that Determining the total score of the riding card according to the card score and the cross score, and determining the riding card recommendation result according to the total score of each riding card, includes: According to the preset card score weight and cross score weight, the card score and cross score of the riding card are weighted to obtain the total score of the riding card; The riding cards are sorted in descending order of the total scores to obtain a riding card sequence; the riding card sequence is the riding card recommendation result.
8. A cycling card recommendation device, characterized in that: The device comprises: An acquisition module, used to acquire each riding card corresponding to the target user group to which the target user belongs and a historical card resource usage data set of the target user; A calculation module, used for performing card score calculation processing on the resource usage data corresponding to each riding card to obtain the card score of the riding card, and determining the cross score of the riding card according to the resource usage data and the historical card resource usage data set; A determination module, used to determine the total score of the riding card according to the card score and the cross score, and determine the riding card recommendation result according to the total score of each riding card; The acquisition module includes a first acquisition submodule, which is specifically used to acquire a historical cumulative order data set of a target user group to which the target user belongs; based on the historical cumulative order data set, determine the average number of orders of the target user group in different time periods; the average number of orders is determined based on an average order number algorithm, and the average number of orders is ; Wherein, the time period includes 3 days, 5 days, 7 days, 10 days, 15 days, 20 days and 30 days; For the Daily target user group All users of 30 days for history, Indicates User's recent Daily cumulative orders; belong ; Determine each resource usage data based on each time period and each average number of orders; Generate each riding card according to each resource usage data and the discount data corresponding to the target user group.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
