Staged value reduction information pushing method, device, equipment, medium and product

Abstract

The embodiment of the invention discloses a staging value reduction information pushing method and device, equipment, a medium and a product. A specific embodiment of the method comprises the steps of generating a user feature vector according to user feature information of a target user; generating a staging value reduction feature vector set according to the staging value reduction feature information set corresponding to the staging value reduction information set; according to the user feature vector and the staging value reduction feature vector set, selecting staging value reduction information meeting a preset push condition from the staging value reduction information set; and pushing the selected staging value reduction information to the user account of the target user. The implementation mode is related to big data, so that the pushed value reduction information can be suitable for a scene of payment orders by stages, and warehouse article accumulation is reduced.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, equipment, medium, and product for pushing installment value reduction information. Background Art

[0002] With the development of computer and Internet technology, users can pay for orders online. When users pay for orders, the value of the user's current order can be reduced, so that users can choose to pay with the reduced value to improve the transaction rate. At present, when the value of the user's order is reduced, the method usually adopted is: push the value reduction information that can reduce the total value of the order once to the user.

[0003] However, the inventors have found that when the above method is used, the following technical problems often occur: the pushed value reduction information cannot be applied to the scenario of installment payment orders, resulting in a low utilization rate of the pushed value reduction information, which in turn leads to a low order conversion rate and causes a large amount of items to pile up in the warehouse.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a method, device, electronic device, computer-readable medium and computer program product for pushing installment value reduction information to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a method for pushing installment value reduction information, the method comprising: generating a user feature vector based on user feature information of a target user; generating an installment value reduction feature vector set based on an installment value reduction feature information set corresponding to the installment value reduction information set; selecting installment value reduction information that meets preset push conditions from the installment value reduction information set based on the above user feature vector and the above installment value reduction feature vector set; and pushing the selected installment value reduction information to the user account of the above target user.

[0008] Optionally, the above-mentioned selecting the installment value reduction information satisfying the preset push conditions from the above-mentioned installment value reduction information set includes: generating an installment probability information set corresponding to the above-mentioned installment value reduction information set according to the above-mentioned user feature vector, the above-mentioned installment value reduction feature vector set and a pre-trained installment probability prediction model; for each installment value reduction information in the above-mentioned installment value reduction information set, generating value reduction expectation information according to the installment probability information corresponding to the above-mentioned installment value reduction information in the above-mentioned installment probability information set; and selecting the installment value reduction information satisfying the preset push conditions from the above-mentioned installment value reduction information set according to the obtained respective value reduction expectation information.

[0009] Optionally, the above-mentioned generation of an installment probability information set corresponding to the above-mentioned installment value reduction information set based on the above-mentioned user feature vector, the above-mentioned installment value reduction feature vector set and the pre-trained installment probability prediction model includes: for each installment value reduction feature vector in the above-mentioned installment value reduction feature vector set, performing the following steps: combining the above-mentioned user feature vector and the above-mentioned installment value reduction feature vector into an input feature vector; inputting the above-mentioned input feature vector into the above-mentioned installment probability prediction model to obtain installment probability information, wherein the above-mentioned installment probability information includes an installment probability set, and each installment probability in the above-mentioned installment probability set corresponds to an installment period number.

[0010] Optionally, the above-mentioned installment probability prediction model includes a multi-layer neural network, a short-circuit connection layer and an output layer, the above-mentioned short-circuit connection layer is used to add the output result of the above-mentioned multi-layer neural network and the above-mentioned input feature vector, and the above-mentioned output layer is used to generate installment probability information according to the sum of the above-mentioned output result and the above-mentioned input feature vector.

[0011] Optionally, the above-mentioned generating expected value reduction information based on the installment probability information corresponding to the above-mentioned installment value reduction information in the above-mentioned installment probability information set includes: for each installment probability in the installment probability set included in the above-mentioned installment probability information, performing the following steps: determining the installment number of the above-mentioned installment probability as the target installment number; generating expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number; generating an expected installment value reduction value based on the above-mentioned installment probability and the above-mentioned expected installment value reduction information; and determining the sum of the generated expected installment value reduction values ​​as the expected value reduction information.

[0012] Optionally, the above-mentioned generation of expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number includes: determining the total installment value corresponding to the above-mentioned target user; determining the installment rate corresponding to the above-mentioned target installment number; determining the value reduction rate corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number; generating the expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number based on the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value reduction rate.

[0013] Optionally, the above-mentioned expected information on installment value reduction corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number is generated based on the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value reduction rate, including: determining the difference between a preset value and the above-mentioned value reduction rate as the value acquisition rate; determining the product of the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value acquisition rate as the expected information on installment value reduction corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number.

[0014] Optionally, the above-mentioned selecting the installment value reduction information satisfying the preset push conditions from the above-mentioned installment value reduction information set based on the obtained individual value reduction expected information includes: selecting the value reduction expected information satisfying the preset numerical conditions from the above-mentioned individual value reduction expected information as the target value reduction expected information; and determining the installment value reduction information corresponding to the above-mentioned target value reduction expected information in the above-mentioned installment value reduction information set as the installment value reduction information satisfying the above-mentioned preset push conditions.

[0015] Optionally, the above-mentioned pushing the selected installment value reduction information to the user account of the above-mentioned target user includes: sending the above-mentioned installment value reduction information to a terminal device logged in with the above-mentioned user account.

[0016] In a second aspect, some embodiments of the present disclosure provide a device for pushing installment value reduction information, the device comprising: a first generating unit, configured to generate a user feature vector based on user feature information of a target user; a second generating unit, configured to generate an installment value reduction feature vector set based on an installment value reduction feature information set corresponding to the installment value reduction information set; a selecting unit, configured to select installment value reduction information that meets preset push conditions from the installment value reduction information set based on the above-mentioned user feature vector and the above-mentioned installment value reduction feature vector set; and a pushing unit, configured to push the selected installment value reduction information to the user account of the above-mentioned target user.

[0017] Optionally, the selection unit is further configured to: generate an installment probability information set corresponding to the above-mentioned installment value reduction information set based on the above-mentioned user feature vector, the above-mentioned installment value reduction feature vector set and the pre-trained installment probability prediction model; for each installment value reduction information in the above-mentioned installment value reduction information set, generate value reduction expectation information based on the installment probability information corresponding to the above-mentioned installment value reduction information in the above-mentioned installment probability information set; and select the installment value reduction information that meets the preset push conditions from the above-mentioned installment value reduction information set based on the obtained respective value reduction expectation information.

[0018] Optionally, the selection unit is further configured to: for each installment value reduction feature vector in the above-mentioned installment value reduction feature vector set, perform the following steps: combine the above-mentioned user feature vector and the above-mentioned installment value reduction feature vector into an input feature vector; input the above-mentioned input feature vector into the above-mentioned installment probability prediction model to obtain installment probability information, wherein the above-mentioned installment probability information includes an installment probability set, and each installment probability in the above-mentioned installment probability set corresponds to an installment period number.

[0019] Optionally, the above-mentioned installment probability prediction model includes a multi-layer neural network, a short-circuit connection layer and an output layer, the above-mentioned short-circuit connection layer is used to add the output result of the above-mentioned multi-layer neural network and the above-mentioned input feature vector, and the above-mentioned output layer is used to generate installment probability information according to the sum of the above-mentioned output result and the above-mentioned input feature vector.

[0020] Optionally, the selection unit is further configured to: for each installment probability in the installment probability set included in the above-mentioned installment probability information, perform the following steps: determine the installment number of the above-mentioned installment probability as the target installment number; generate expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number; generate an expected installment value reduction value based on the above-mentioned installment probability and the above-mentioned expected installment value reduction information; and determine the sum of the generated expected installment value reduction values ​​as the expected value reduction information.

[0021] Optionally, the selection unit is further configured to: determine the total installment value corresponding to the above-mentioned target user; determine the installment rate corresponding to the above-mentioned target installment number; determine the value reduction rate corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number; and generate the expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number based on the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value reduction rate.

[0022] Optionally, the selection unit is further configured to: determine the difference between a preset value and the above-mentioned value reduction rate as the value acquisition rate; and determine the product of the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value acquisition rate as the expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number.

[0023] Optionally, the selection unit is further configured to: select the expected value reduction information that meets the preset numerical conditions from the above-mentioned individual expected value reduction information as the target expected value reduction information; and determine the installment value reduction information in the above-mentioned installment value reduction information set that corresponds to the above-mentioned target expected value reduction information as the installment value reduction information that meets the above-mentioned preset push conditions.

[0024] Optionally, the push unit is further configured to: send the above-mentioned installment value reduction information to a terminal device logged in with the above-mentioned user account.

[0025] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0026] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0027] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation manner of the above-mentioned first aspect when executed by a processor.

[0028] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the installment value reduction information push method of some embodiments of the present disclosure, the pushed value reduction information can be applied to the scenario of the installment payment order, reducing the accumulation of warehouse items. Specifically, the reason for the accumulation of more warehouse items is that the pushed value reduction information cannot be applied to the scenario of the installment payment order, resulting in a low utilization rate of the pushed value reduction information, thereby resulting in a low order transaction rate, resulting in more warehouse items. Based on this, the installment value reduction information push method of some embodiments of the present disclosure first generates a user feature vector according to the user feature information of the target user. Thus, the user feature vector can represent the features of each dimension of the target user. Then, according to the installment value reduction feature information set corresponding to the installment value reduction information set, an installment value reduction feature vector set is generated. Thus, each installment value reduction feature vector can characterize the features of each dimension of the installment value reduction information. Afterwards, according to the above-mentioned user feature vector and the above-mentioned installment value reduction feature vector set, the installment value reduction information that meets the preset push conditions is selected from the above-mentioned installment value reduction information set. Finally, the selected installment value reduction information is pushed to the user account of the target user. Thus, the installment value reduction information applicable to installment payment can be pushed to the user. Thus, the utilization rate of the pushed value reduction information can be improved, and the order completion rate can be increased. Thus, the accumulation of warehouse items can be reduced. Thus, the pushed value reduction information can be applied to the scenario of installment payment orders, and the accumulation of warehouse items can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0030] Figure 1 is a schematic diagram of an application scenario of the method for pushing information on installment value reduction according to some embodiments of the present disclosure;

[0031] Figure 2 is a flow chart of some embodiments of the method for pushing installment value reduction information according to the present disclosure;

[0032] Figure 3 is a flow chart of other embodiments of the method for pushing installment value reduction information according to the present disclosure;

[0033] Figure 4 It is a structural schematic diagram of an installment probability prediction model according to the installment value reduction information push method disclosed in the present invention;

[0034] Figure 5It is a schematic diagram of the structure of some embodiments of the instalment value reduction information push device according to the present disclosure;

[0035] Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0036] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0037] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0038] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0039] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0040] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0041] With regard to the collection, storage, and use of user personal information (such as user feature information) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0042] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0043] Figure 1 It is a schematic diagram of an application scenario of the method for pushing installment value reduction information according to some embodiments of the present disclosure.

[0044] exist Figure 1In the application scenario, first, the computing device 101 can generate a user feature vector 103 according to the user feature information 102 of the target user. Then, the computing device 101 can generate an installment value reduction feature vector set 106 according to the installment value reduction feature information set 105 corresponding to the installment value reduction information set 104. After that, the computing device 101 can select the installment value reduction information 107 that meets the preset push conditions from the above-mentioned installment value reduction information set 104 according to the above-mentioned user feature vector 103 and the above-mentioned installment value reduction feature vector set 106. Finally, the computing device 101 can push the selected installment value reduction information 107 to the user account 108 of the above-mentioned target user.

[0045] It should be noted that the computing device 101 can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0046] It should be understood that Figure 1 The number of computing devices in the embodiment is only illustrative. Any number of computing devices may be provided according to implementation requirements.

[0047] Continue to refer Figure 2 , shows a process 200 of some embodiments of the method for pushing information on the reduction of installment value according to the present disclosure. The method for pushing information on the reduction of installment value includes the following steps:

[0048] Step 201: Generate a user feature vector according to user feature information of a target user.

[0049] In some embodiments, the execution subject (eg Figure 1The computing device 101 shown in the figure can generate a user feature vector according to the user feature information of the target user. Among them, the above-mentioned target user can be a user who currently needs to push the value reduction related information (such as coupons). The above-mentioned user feature information can be information that can characterize the user's characteristics. For example, the above-mentioned user feature information can include but is not limited to at least one of the following: user attribute information, item browsing information, item to be circulated information, item circulation information, installment behavior information, value reduction use information. The above-mentioned user attribute information can be information related to the user's own attributes. For example, the above-mentioned user attribute information can include but is not limited to at least one of the following: age, gender. The above-mentioned item browsing information can be relevant information when the user browses the item page. For example, the above-mentioned item browsing information can include but is not limited to: the number of views for each category of items within a preset time period. The above-mentioned item to be circulated information can be relevant information about items to be circulated (such as items added to a shopping cart). The above-mentioned item to be circulated information can include but is not limited to: the number of items to be circulated within a preset time period. The above-mentioned item circulation information can be relevant information about the circulated items. For example, the above-mentioned item circulation information can include but is not limited to: the historical average order value, the maximum order value within a preset time period. The installment behavior information may be information related to installment payment behavior. For example, the installment behavior information may include but is not limited to at least one of the following: the installment payment order value and the number of installment payment orders for each installment period in each preset time period. The value reduction usage information may be information related to the user's payment using the value after value reduction. For example, the value reduction usage information may include but is not limited to at least one of the following: the average order value of the value reduction within the preset time period and the proportion of the orders with value reduction.

[0050] In practice, the execution entity may combine various items of information included in the user feature information as vector elements of various dimensions into a user feature vector.

[0051] It should be noted that the execution subject may be a server. The user characteristic information may be obtained through a wired connection or a wireless connection. The wireless connection may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0052] Step 202: Generate an installment value reduction feature vector set based on the installment value reduction feature information set corresponding to the installment value reduction information set.

[0053] In some embodiments, the above-mentioned execution entity may generate an installment value reduction feature vector set based on the installment value reduction feature information set corresponding to the installment value reduction information set. Among them, the above-mentioned installment value reduction information set may be information on each order that can be value-reduced for installment payment. For example, the installment value reduction information may include an installment value reduction identifier (installment payment coupon identifier) ​​and installment value reduction feature information. The installment value reduction feature information may be feature information on which the value of an order that can be paid in installments can be reduced. The installment value reduction feature information may include value reduction information for each installment period. The installment period value reduction information may include the number of installments, the installment rate corresponding to the number of installments, and the value reduction rate (discount rate). For example, the installment period value reduction information may be "number of installments: 6, installment rate: 2%, value reduction rate: 5%". In practice, for each installment value reduction characteristic information in the above-mentioned installment value reduction characteristic information set, the above-mentioned execution entity may use the installment period numbers included in the above-mentioned installment value reduction characteristic information as vector elements to form an installment value reduction characteristic vector.

[0054] Step 203: Select the installment value reduction information that meets the preset push condition from the installment value reduction information set according to the user feature vector and the installment value reduction feature vector set.

[0055] In some embodiments, the execution subject may select the installment value reduction information that meets the preset push conditions from the installment value reduction information set according to the user feature vector and the installment value reduction feature vector set. In practice, first, for each installment value reduction feature vector in the installment value reduction feature vector set, the execution subject may input the user feature vector and the installment value reduction feature vector into the pre-fitted installment value reduction expectation prediction model to obtain the installment value reduction expectation value. The installment value reduction expectation prediction model may be a regression model pre-fitted by sample data with the installment value reduction expectation value as the dependent variable. Each sample in the sample data may include a sample user feature vector, a sample installment value reduction feature vector, and a sample installment value reduction expectation value. The installment value reduction expectation value may be the expected value (e.g., profit) obtained by pushing the installment value reduction information corresponding to the installment value reduction feature vector to the user. Then, the execution subject may select the installment value reduction information whose corresponding installment value reduction expectation value meets the preset push conditions from the installment value reduction information set. The above-mentioned preset push condition may be that the expected value of installment value reduction corresponding to the installment value reduction information is the maximum value among all the expected values ​​of installment value reduction obtained.

[0056] Step 204: Push the selected installment value reduction information to the user account of the target user.

[0057] In some embodiments, the execution entity may push the selected installment value reduction information to the user account of the target user. In practice, the execution entity may store the selected installment value reduction information in the push resource pool of the user account. The push resource pool may be used to store various information to be pushed to the user. After the user logs in to the user account, the terminal device logged in to the user account may receive various information in the push resource pool.

[0058] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the installment value reduction information push method of some embodiments of the present disclosure, the pushed value reduction information can be applied to the scenario of the installment payment order, reducing the accumulation of warehouse items. Specifically, the reason for the accumulation of more warehouse items is that the pushed value reduction information cannot be applied to the scenario of the installment payment order, resulting in a low utilization rate of the pushed value reduction information, thereby resulting in a low order transaction rate, resulting in more warehouse items. Based on this, the installment value reduction information push method of some embodiments of the present disclosure first generates a user feature vector according to the user feature information of the target user. Thus, the user feature vector can represent the features of each dimension of the target user. Then, according to the installment value reduction feature information set corresponding to the installment value reduction information set, an installment value reduction feature vector set is generated. Thus, each installment value reduction feature vector can characterize the features of each dimension of the installment value reduction information. Afterwards, according to the above-mentioned user feature vector and the above-mentioned installment value reduction feature vector set, the installment value reduction information that meets the preset push conditions is selected from the above-mentioned installment value reduction information set. Finally, the selected installment value reduction information is pushed to the user account of the target user. Thus, the installment value reduction information applicable to installment payment can be pushed to the user. Thus, the utilization rate of the pushed value reduction information can be improved, and the order completion rate can be increased. Thus, the accumulation of warehouse items can be reduced. Thus, the pushed value reduction information can be applied to the scenario of installment payment orders, and the accumulation of warehouse items can be reduced.

[0059] Further references Figure 3 , which shows a process 300 of another embodiment of the method for pushing information on the reduction of installment value. The process 300 of the method for pushing information on the reduction of installment value includes the following steps:

[0060] Step 301: Generate a user feature vector according to user feature information of a target user.

[0061] Step 302: Generate an installment value reduction feature vector set based on the installment value reduction feature information set corresponding to the installment value reduction information set.

[0062] In some embodiments, the specific implementation of steps 301-302 and the technical effects brought about can be referred to Figure 2 The corresponding steps 201-202 in the embodiments are not described in detail here.

[0063] Step 303, generating an installment probability information set corresponding to the installment value reduction information set according to the user feature vector, the installment value reduction feature vector set and the pre-trained installment probability prediction model.

[0064] In some embodiments, the execution subject (eg Figure 1 The computing device 101 shown can generate an installment probability information set corresponding to the above-mentioned installment value reduction information set according to the above-mentioned user feature vector, the above-mentioned installment value reduction feature vector set and the pre-trained installment probability prediction model. Among them, the above-mentioned installment probability prediction model can be a neural network model with the user feature vector and the installment value reduction feature vector as input data and the installment probability information as output data. The above-mentioned installment probability information can be the probability related information of the predicted user selecting each installment period for payment. Here, the neural network model can be a multi-layer neural network model. Each sample used to train the above-mentioned installment probability prediction model can be a combination of a user feature vector and an installment value reduction feature vector, the feature is the total feature composed of the user feature vector and the installment value reduction feature vector, and the label can be the user's installment period. For example, if there are three fixed installment periods of 3 periods, 6 periods, and 12 periods, the label can take four values ​​of "no installment", "3 installments", "6 installments" or "12 installments", forming a multi-classification task. In practice, the training set and the test set can be divided from the historical data set to train the installment probability prediction model.

[0065] In practice, for each installment value reduction feature vector in the above-mentioned installment value reduction feature vector set, the above-mentioned execution subject may perform the following steps:

[0066] The first step is to combine the user feature vector and the installment value reduction feature vector into an input feature vector. In practice, the execution entity may combine the user feature vector and the installment value reduction feature vector into an input feature vector.

[0067] The second step is to input the input feature vector into the installment probability prediction model to obtain installment probability information. The installment probability information includes an installment probability set. Each installment probability in the installment probability set corresponds to an installment period number.

[0068] Optionally, the above-mentioned staging probability prediction model may include a multi-layer neural network, a short-circuit connection layer and an output layer. The above-mentioned multi-layer neural network may be a multi-layer fully connected neural network. Here, there is no limitation on the specific network structure of the multi-layer neural network. The above-mentioned short-circuit connection layer may be used to add the output result of the above-mentioned multi-layer neural network and the above-mentioned input feature vector. The above-mentioned output layer may be used to generate staging probability information according to the sum of the above-mentioned output result and the above-mentioned input feature vector. As an example, the model structure of the staging probability prediction model may refer to Figure 4 . Figure 4 In the embodiment, the installment probability prediction model takes an input feature vector including user features and installment value reduction features as input, and the installment probability prediction model includes a multi-layer neural network, a short-circuit connection layer and an output layer.

[0069] Specifically, for the i-th installment number v i The output layer can sum the output result and the input feature vector z 1 Enter the number of installments v i The corresponding multi-layer neural network g i (·),get After the sigmoid function, we can get the installment probability for the i-th installment period. Here, we can assume i = 1, 2, 3, ..., n. v represents the installment period. n represents the number of installment periods. x represents the input feature vector. When the user does not pay in installments, v is 0. At this time, the installment probability can be expressed as:

[0070]

[0071]

[0072]

[0073] The loss function of the above-mentioned stage probability prediction model can be expressed as:

[0074]

[0075]

[0076] Among them, k represents the kth sample.

[0077] Therefore, the role of the installment value reduction feature can be highlighted through the short-circuit connection layer. It is also possible to achieve ordered multi-classification through the above-mentioned method of predicting the installment probability, reflecting the order between the installment periods.

[0078] Step 304: for each installment value reduction information in the installment value reduction information set, value reduction expectation information is generated according to the installment probability information corresponding to the installment value reduction information in the installment probability information set.

[0079] In some embodiments, for each installment value reduction information in the installment value reduction information set, the execution entity may generate value reduction expectation information according to the installment probability information corresponding to the installment value reduction information in the installment probability information set. The value reduction expectation information may be the value (e.g., profit) expected to be obtained by pushing the installment value reduction information to the user.

[0080] In practice, first, for each installment probability in the installment probability set included in the installment probability information, the execution subject may perform the following steps:

[0081] The first step is to determine the installment period number of the above installment probability as the target installment period number.

[0082] The second step is to generate expected information on the reduction of installment value corresponding to the above-mentioned information on the reduction of installment value and the above-mentioned target number of installments.

[0083] The third step is to generate the expected value of installment value reduction according to the installment probability and the expected information of installment value reduction. In practice, the execution entity may determine the expected value of installment value reduction by multiplying the installment probability and the expected information of installment value reduction.

[0084] Then, the sum of the generated expected values ​​of value reduction of each installment is determined as the expected value reduction information.

[0085] In some optional implementations of some embodiments, the execution subject may generate the expected information of the installment value reduction corresponding to the installment value reduction information and the target installment period number through the following steps:

[0086] The first step is to determine the total installment value corresponding to the target user, wherein the total installment value may be the total value of the order that the target user needs to pay in installments.

[0087] The second step is to determine the installment rate corresponding to the target installment period. The installment rate can be the rate per installment required for reference when paying with the target installment period.

[0088] The third step is to determine the value reduction rate corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment period.

[0089] The fourth step is to generate the expected information on installment value reduction corresponding to the installment value reduction information and the target installment number according to the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value reduction rate. In practice, first, the above-mentioned execution entity may determine the difference between the preset value and the above-mentioned value reduction rate as the value acquisition rate. Among them, the above-mentioned preset value may be 1. Then, the product of the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value acquisition rate may be determined as the expected information on installment value reduction corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number. Therefore, the expected information on installment value reduction may be characterized as the value (profit) that the platform may obtain when the user pays the order according to the above-mentioned installment value reduction information and the target installment number.

[0090] Step 305: Select the installment value reduction information that meets the preset push conditions from the installment value reduction information set according to the obtained value reduction expectation information.

[0091] In some embodiments, the execution subject may select the installment value reduction information that meets the preset push conditions from the installment value reduction information set based on the obtained value reduction expectation information. In practice, first, the execution subject may select the value reduction expectation information that meets the preset numerical conditions from the various value reduction expectation information as the target value reduction expectation information. The preset numerical condition may be that the value reduction expectation information is the maximum value among the various value reduction expectation information. Then, the installment value reduction information corresponding to the target value reduction expectation information in the installment value reduction information set may be determined as the installment value reduction information that meets the preset push conditions.

[0092] Step 306: Push the selected installment value reduction information to the user account of the target user.

[0093] In some embodiments, the execution entity may push the selected installment value reduction information to the user account of the target user. In practice, the execution entity may send the installment value reduction information to a terminal device logged in with the user account. Thus, the target user may view the installment value reduction information through the terminal device to make installment payments.

[0094] from Figure 3 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 3The process 300 of the installment value reduction information push method in some corresponding embodiments reflects the steps of expanding the installment probability prediction model. Therefore, the scheme described in these embodiments can predict the probability of the user paying in each installment under each installment value reduction information through the installment probability prediction model, so that it can be used to screen the installment value reduction information to be pushed to the user. The use of the installment probability prediction model improves the utilization rate of the pushed installment value reduction information. In turn, it improves the order completion rate and reduces the accumulation of items in the warehouse.

[0095] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a device for pushing information on installment value reduction, and these device embodiments are similar to Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0096] like Figure 5 As shown, the installment value reduction information push device 500 of some embodiments includes: a first generation unit 501, a second generation unit 502, a selection unit 503 and a push unit 504. The first generation unit 501 is configured to generate a user feature vector according to the user feature information of the target user; the second generation unit 502 is configured to generate an installment value reduction feature vector set according to the installment value reduction feature information set corresponding to the installment value reduction information set; the selection unit 503 is configured to select the installment value reduction information that meets the preset push condition from the installment value reduction information set according to the user feature vector and the installment value reduction feature vector set; the push unit 504 is configured to push the selected installment value reduction information to the user account of the target user.

[0097] Optionally, the selection unit 503 can be further configured to: generate an installment probability information set corresponding to the above-mentioned installment value reduction information set based on the above-mentioned user feature vector, the above-mentioned installment value reduction feature vector set and the pre-trained installment probability prediction model; for each installment value reduction information in the above-mentioned installment value reduction information set, generate value reduction expectation information based on the installment probability information corresponding to the above-mentioned installment value reduction information in the above-mentioned installment probability information set; and select the installment value reduction information that meets the preset push conditions from the above-mentioned installment value reduction information set based on the obtained value reduction expectation information.

[0098] Optionally, the selection unit 503 can be further configured to: for each installment value reduction feature vector in the above-mentioned installment value reduction feature vector set, perform the following steps: combine the above-mentioned user feature vector and the above-mentioned installment value reduction feature vector into an input feature vector; input the above-mentioned input feature vector into the above-mentioned installment probability prediction model to obtain installment probability information, wherein the above-mentioned installment probability information includes an installment probability set, and each installment probability in the above-mentioned installment probability set corresponds to an installment period number.

[0099] Optionally, the above-mentioned installment probability prediction model includes a multi-layer neural network, a short-circuit connection layer and an output layer, the above-mentioned short-circuit connection layer is used to add the output result of the above-mentioned multi-layer neural network and the above-mentioned input feature vector, and the above-mentioned output layer is used to generate installment probability information according to the sum of the above-mentioned output result and the above-mentioned input feature vector.

[0100] Optionally, the selection unit 503 can be further configured to: for each installment probability in the installment probability set included in the above-mentioned installment probability information, perform the following steps: determine the installment number of the above-mentioned installment probability as the target installment number; generate expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number; generate an expected installment value reduction value based on the above-mentioned installment probability and the above-mentioned expected installment value reduction information; and determine the sum of the generated expected installment value reduction values ​​as the expected value reduction information.

[0101] Optionally, the selection unit 503 can be further configured to: determine the total installment value corresponding to the above-mentioned target user; determine the installment rate corresponding to the above-mentioned target installment number; determine the value reduction rate corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number; and generate the expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number based on the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value reduction rate.

[0102] Optionally, the selection unit 503 can be further configured to: determine the difference between the preset value and the above-mentioned value reduction rate as the value acquisition rate; and determine the product of the above-mentioned total installment value, the above-mentioned installment rate, the above-mentioned target installment number and the above-mentioned value acquisition rate as the expected installment value reduction information corresponding to the above-mentioned installment value reduction information and the above-mentioned target installment number.

[0103] Optionally, the selection unit 503 can be further configured to: select the expected value reduction information that meets the preset numerical conditions from the above-mentioned various expected value reduction information as the target expected value reduction information; and determine the installment value reduction information corresponding to the above-mentioned target expected value reduction information in the above-mentioned installment value reduction information set as the installment value reduction information that meets the above-mentioned preset push conditions.

[0104] Optionally, the push unit 504 may be further configured to: send the installment value reduction information to a terminal device logged in with the user account.

[0105] It is understood that the units described in the device 500 are similar to those described in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 500 and the units included therein, and will not be described in detail here.

[0106] Reference below Figure 6 , which shows an electronic device 600 (eg, Figure 1 Schematic diagram of the structure of the computing device 101). Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0107] like Figure 6 As shown, the electronic device 600 may include a processing device 601 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0108] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0109] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0110] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0111] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0112] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: generates a user feature vector based on the user feature information of the target user; generates an installment value reduction feature vector set based on the installment value reduction feature information set corresponding to the installment value reduction information set; selects installment value reduction information that meets the preset push conditions from the installment value reduction information set based on the user feature vector and the installment value reduction feature vector set; and pushes the selected installment value reduction information to the user account of the target user.

[0113] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The units described may also be provided in a processor, for example, may be described as: a processor including a first generation unit, a second generation unit, a selection unit, and a push unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the first generation unit may also be described as "a unit for generating a user feature vector based on user feature information of a target user".

[0116] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0117] Some embodiments of the present disclosure also provide a computer program product, including a computer program, which implements any of the above-mentioned installment value reduction information push methods when executed by a processor.

[0118] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for pushing information on installment value reduction, comprising: Generate a user feature vector according to the user feature information of the target user; Generate an installment value reduction feature vector set according to the installment value reduction feature information set corresponding to the installment value reduction information set; According to the user feature vector and the set of feature vectors for the instalment value reduction, select the instalment value reduction information that meets the preset push condition from the set of instalment value reduction information; The selected installment value reduction information is pushed to the user account of the target user.

2. The method according to claim 1, wherein: The step of selecting the installment value reduction information satisfying the preset push condition from the installment value reduction information set includes: Generate an installment probability information set corresponding to the installment value reduction information set according to the user feature vector, the installment value reduction feature vector set and a pre-trained installment probability prediction model; For each installment value reduction information in the installment value reduction information set, generating value reduction expectation information according to the installment probability information corresponding to the installment value reduction information in the installment probability information set; According to the obtained value reduction expectation information, the installment value reduction information that meets the preset push conditions is selected from the installment value reduction information set.

3. The method according to claim 2, wherein: The step of generating an installment probability information set corresponding to the installment value reduction information set according to the user feature vector, the installment value reduction feature vector set and a pre-trained installment probability prediction model comprises: For each installment value reduction feature vector in the installment value reduction feature vector set, the following steps are performed: Combining the user feature vector and the installment value reduction feature vector into an input feature vector; The input feature vector is input into the installment probability prediction model to obtain installment probability information, wherein the installment probability information includes an installment probability set, and each installment probability in the installment probability set corresponds to an installment period number.

4. The method according to claim 3, wherein: The installment probability prediction model includes a multi-layer neural network, a short-circuit connection layer and an output layer. The short-circuit connection layer is used to add the output result of the multi-layer neural network and the input feature vector, and the output layer is used to generate installment probability information based on the sum of the output result and the input feature vector.

5. The method according to claim 3, wherein: The generating value reduction expectation information according to the installment probability information corresponding to the installment value reduction information in the installment probability information set includes: For each installment probability in the installment probability set included in the installment probability information, the following steps are performed: Determining the installment number of the installment probability as the target installment number; Generate expected installment value reduction information corresponding to the installment value reduction information and the target installment period number; Generate an expected value of installment value reduction according to the installment probability and the expected information of installment value reduction; The sum of the generated expected values ​​of value reduction for each installment is determined as expected value reduction information.

6. The method according to claim 5, wherein: The generating of expected installment value reduction information corresponding to the installment value reduction information and the target installment period number includes: Determine the total installment value corresponding to the target user; Determining an installment rate corresponding to the target number of installments; Determine a value reduction rate corresponding to the installment value reduction information and the target installment period number; According to the total installment value, the installment rate, the target number of installments and the value reduction rate, expected installment value reduction information corresponding to the installment value reduction information and the target number of installments is generated.

7. The method according to claim 6, wherein: The generating, according to the total installment value, the installment rate, the target number of installments and the value reduction rate, the expected installment value reduction information corresponding to the installment value reduction information and the target number of installments includes: Determine the difference between the preset value and the value reduction rate as the value acquisition rate; The product of the total installment value, the installment rate, the target number of installments and the value acquisition rate is determined as the expected installment value reduction information corresponding to the installment value reduction information and the target number of installments.

8. The method according to claim 2, wherein: The step of selecting, according to each obtained value reduction expectation information, the installment value reduction information that meets the preset push condition from the installment value reduction information set includes: Selecting, from the various pieces of expected value reduction information, expected value reduction information that meets a preset numerical condition as target expected value reduction information; The installment value reduction information corresponding to the target value reduction expected information in the installment value reduction information set is determined as the installment value reduction information that meets the preset push condition.

9. The method according to any one of claims 1 to 8, wherein: The step of pushing the selected installment value reduction information to the user account of the target user includes: The installment value reduction information is sent to the terminal device logged in with the user account.

10. A device for pushing information on installment value reduction, comprising: A first generating unit is configured to generate a user feature vector according to user feature information of a target user; The second generating unit is configured to generate an installment value reduction feature vector set according to the installment value reduction feature information set corresponding to the installment value reduction information set; A selection unit is configured to select, from the set of installment value reduction information, the installment value reduction information that meets a preset push condition according to the user feature vector and the set of installment value reduction feature vectors; The push unit is configured to push the selected installment value reduction information to the user account of the target user.

11. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 9.

12. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images