Equity recommendation processing method and device

Abstract

Embodiments of the present specification provide a benefit recommendation processing method and device, wherein a benefit recommendation processing method comprises: acquiring feature data of a user interacting with an automatic vending terminal; inputting the feature data into a value stratification model to calculate a value stratification parameter, and outputting a value stratification parameter of the user; determining a predicted value label of the user according to the value stratification parameter, and determining a statistical label under the predicted value label in a private label library of a terminal merchant; selecting a target label hit by the feature data in a label set containing the statistical label, and performing benefit recommendation to the user according to a benefit recommendation strategy corresponding to the target label.

Description

TECHNICAL FIELD

[0001] The present document relates to the technical field of data processing, and in particular to a benefit recommendation processing method and device. BACKGROUND

[0002] With the continuous development of Internet technology, digital consumption based on the Internet has been widely popularized, and more and more merchants choose to sell goods in a digital or intelligent way. In the digital scenario of offline merchants, there is a self-service selling scenario, that is, by placing self-service vending machines or self-service cabinets in sales stores, shopping malls, stations and other places, users can select and purchase goods and automatically check out through self-service vending machines without the guidance of sales personnel. For merchants who place automatic vending machines, how to improve the experience of users purchasing goods through automatic vending machines becomes an important concern for merchants in the process of selling goods. SUMMARY

[0003] One or more embodiments of the present specification provide a benefit recommendation processing method, comprising: obtaining feature data of a user interacting with an automatic vending terminal. The feature data is input into a value stratification model to calculate a value stratification parameter, and the value stratification parameter of the user is output. The predicted value label of the user is determined according to the value stratification parameter, and the statistical label under the predicted value label in the private label library of the terminal merchant is determined. The target label hit by the feature data is selected in the label set containing the statistical label, and the benefit recommendation is made to the user according to the benefit recommendation strategy corresponding to the target label.

[0004] One or more embodiments of the present specification provide a benefit recommendation processing device, comprising: a feature data acquisition module configured to obtain feature data of a user interacting with an automatic vending terminal. A value stratification parameter calculation module configured to input the feature data into a value stratification model to calculate a value stratification parameter, and output the value stratification parameter of the user. A statistical label determination module configured to determine the predicted value label of the user according to the value stratification parameter, and determine the statistical label under the predicted value label in the private label library of the terminal merchant. A benefit recommendation module configured to select the target label hit by the feature data in the label set containing the statistical label, and make a benefit recommendation to the user according to the benefit recommendation strategy corresponding to the target label.

[0005] The one or more embodiments of the specification provide a benefit recommendation processing device, comprising: a processor; and a memory configured to store computer executable instructions which, when executed, cause the processor to: acquire feature data of a user interacting with a vending terminal. input the feature data into a value stratification model for value stratification parameter calculation, and output a value stratification parameter of the user. determine a predicted value label of the user according to the value stratification parameter, and determine a statistical label under the predicted value label in a private label library of a terminal merchant. select a target label hit by the feature data in a label set containing the statistical label, and make a benefit recommendation to the user according to a benefit recommendation strategy corresponding to the target label.

[0006] The one or more embodiments of the specification provide a storage medium for storing computer executable instructions, which, when executed by a processor, implement the following processes: acquiring feature data of a user interacting with a vending terminal. input the feature data into a value stratification model for value stratification parameter calculation, and output a value stratification parameter of the user. determine a predicted value label of the user according to the value stratification parameter, and determine a statistical label under the predicted value label in a private label library of a terminal merchant. select a target label hit by the feature data in a label set containing the statistical label, and make a benefit recommendation to the user according to a benefit recommendation strategy corresponding to the target label. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the one or more embodiments of the specification or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the specification, and those skilled in the art can also obtain other drawings according to these drawings without creative labor;

[0008] Figure 1 A benefit recommendation processing method processing flowchart is provided for the one or more embodiments of the specification;

[0009] Figure 2 A benefit recommendation processing method processing flowchart applied to a self-service selling scene is provided for the one or more embodiments of the specification;

[0010] Figure 3 A benefit recommendation processing device schematic diagram is provided for the one or more embodiments of the specification;

[0011] Figure 4 A structure schematic diagram of a benefit recommendation processing device is provided for the one or more embodiments of the specification. DETAILED DESCRIPTION

[0012] In order to better understand the technical solutions in the one or more embodiments of the present specification, the technical solutions in the one or more embodiments of the present specification will be clearly and completely described in the present specification in conjunction with the drawings in the one or more embodiments of the present specification. Obviously, the described embodiments are only a part of the embodiments of the present specification, rather than all the embodiments. Based on the one or more embodiments of the present specification, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present document.

[0013] An embodiment of the benefit recommendation processing method provided in the present specification is as follows:

[0014] The benefit recommendation processing method described in the present embodiment, after the user interacts with the automatic vending terminal, the characteristic data of the user is input into the value stratification model to calculate the value stratification parameter, and the predicted value label of the user is determined according to the value stratification parameter obtained by calculation, so as to evaluate the transaction value of the user in the transaction process with the automatic vending terminal, determine the value stratification where the transaction value of the user is located, and then determine the statistical label under the predicted value label of the current user in the private label library of the terminal merchant of the automatic vending terminal, that is, determine the transaction related label of the user under the currently determined value stratification, further determine the label hit by the characteristic data of the user, and finally recommend the corresponding benefit to the user according to the benefit recommendation strategy corresponding to the hit label, so as to combine the transaction value of the user in the transaction process with the automatic vending terminal with the benefit recommendation of the automatic vending terminal, so as to realize the accurate recommendation marketing in the transaction process of the user and the automatic vending terminal, and help to improve the recommendation marketing effect of the automatic vending terminal, so as to improve the sales situation of the automatic vending terminal on the basis of improving the recommendation marketing effect.

[0015] Step S102, obtaining the characteristic data of the user interacting with the automatic vending terminal.

[0016] The automatic vending terminal described in the present embodiment can be various forms of terminal equipment for automatic vending placed in stores or public places, such as self-service vending machines, intelligent vending cabinets, etc.

[0017] In an actual application scenario, users are more willing to spend time to understand and try the poster information and video marketing activities displayed by the vending terminal. In this embodiment, the user identity is determined by the user cooperating with the vending terminal to perform corresponding interactive actions during the self-service shopping process of the user at the vending terminal, the feature data of the user is obtained based on the determined user identity, and then subsequent benefit recommendation processing is performed according to the obtained feature data of the user, so as to improve the recommendation marketing effect of the vending terminal and then improve the single customer volume of the vending terminal.

[0018] In an optional implementation provided by the embodiment, after detecting the interactive action of the user, the identity information of the user is determined based on the interactive data obtained by performing the interactive action, and the identity information is uploaded by calling a recommendation interface, so as to obtain the feature data of the user according to the identity information.

[0019] Optionally, the interactive action includes at least one of the following: the user scans a transaction identification code of the vending terminal, the vending terminal collects an identity image of the user, the user inputs identity identification information through the vending terminal, and the vending terminal collects an identity identification code of the user.

[0020] The transaction identification code refers to an identification code used to initiate a transaction with the vending terminal, or an identification code used to access a product list of the vending terminal. The identity image refers to an image that can represent or uniquely determine the identity of the user, such as a face image, an iris image, a palm print image, a fingerprint image, etc. The identity identification information can be a user's communication number or a user's ID card code.

[0021] The feature data described in the embodiment includes data related to the identity feature, behavior feature, consumption feature, and / or occupation feature of the user.

[0022] In step S104, the feature data is input into a value stratification model to calculate a value stratification parameter, and the value stratification parameter of the user is output.

[0023] The value stratification parameter calculation described in the embodiment refers to calculating the value stratification parameter of the user, which is used to calculate the user value of the user in the marketing recommendation level during the self-service shopping process of the user at the vending terminal, i.e., the marketing recommendation value. The possibility of realizing single customer conversion after marketing recommendation is higher for users with higher marketing recommendation value, and the possibility of realizing single customer conversion after marketing recommendation is lower for users with lower marketing recommendation value. After the value stratification parameter calculation, the value stratification parameter is obtained, such as the transaction quantity and the retention period.

[0024] The marketing recommendation value can be represented by a life time value (LTV), and the value stratification parameter includes a calculation parameter for calculating the life time value.

[0025] For example, the life time value is divided into five value stratifications.

[0026] The first value stratification is a potential user stratification, such as a user who is active around the vending machine but has not purchased a membership of the merchant;

[0027] The second value stratification is a new user stratification, which refers to a user who has a purchase behavior at the vending machine and becomes a member of the merchant;

[0028] The third value stratification is an active user stratification, which refers to a user who participates in the purchase behavior at the vending machine multiple times within a period of time;

[0029] The fourth value stratification is a lost user stratification, which refers to a user who has not conducted any transaction at any vending machine of the merchant for more than three months;

[0030] The fifth value stratification is a return user stratification, which refers to a user who becomes an active user stratification after being determined as a lost user.

[0031] In a specific implementation, in the process of calculating the value stratification parameter of the user, the feature data is input into a value stratification model to calculate the value stratification parameter, and the value stratification parameter of the user is output.

[0032] It should be noted that the value stratification model is obtained through pre-model training. In the model training process, a to-be-trained model can be constructed based on a DNN (Deep-Learning Neural Network, deep neural network), and then the training data set provided by the terminal merchant based on the private label library is used for model training, and finally the value stratification model is obtained.

[0033] In addition, in order to improve the model training effect, a training data set can also be constructed based on public labels, and the to-be-trained model is trained into an intermediate model using the constructed training data set, and then the intermediate model is trained using the training data set provided by each terminal merchant based on the private label library, and the value stratification model of each terminal merchant is obtained.

[0034] In step S106, the predicted value label of the user is determined according to the value stratification parameter, and a statistical label under the predicted value label in the private label library of the terminal merchant is determined.

[0035] As described above, the value stratification parameter includes a calculation parameter for calculating the life cycle value, based on which, in an optional implementation provided by the embodiment, determining the predicted value label of the user according to the value stratification parameter includes: calculating the life cycle value of the user according to the calculation parameter, and taking the value period label corresponding to the value interval in which the life cycle value is located as the predicted value label.

[0036] Specifically, a corresponding value interval can be set for each value period label, and after the value of the life cycle value of the user is calculated according to the calculation parameter of the life cycle value, the value period label corresponding to the value interval in which the calculated value of the life cycle value is located is taken as the predicted value label of the user.

[0037] For example, according to the calculation parameter of the life cycle value of the user, it is calculated that the value of the life cycle value of the user is in the value interval corresponding to the active user stratification, and then the active user label corresponding to this value interval is determined as the value label of the user in the dimension of the life cycle value.

[0038] The private label library described in the embodiment refers to a label library with access permission and update permission belonging to a terminal merchant. Optionally, the private label library is obtained by merging the private domain label uploaded by the terminal merchant calling the label synchronization interface and the pre-generated public domain label.

[0039] The private domain label refers to a label private to a merchant terminal. The public domain label refers to a label accumulated from the perspective of a platform. The label accumulated by the platform can be open to all terminal merchants, and each terminal merchant can combine the public domain label with its own private label to obtain a private label library with more comprehensive label coverage.

[0040] In the specific execution process, in order to avoid the risk of leakage after the private label of the terminal merchant is uploaded, the security of the label can be enhanced by performing mask processing on the label of the terminal merchant, and in an optional implementation provided by the embodiment, the label synchronization interface, in response to the calling of the terminal merchant, reads the attribute label from the customer management system of the terminal merchant, performs mask processing on the read attribute label, and uploads the private domain label obtained by the mask processing.

[0041] It should be noted that, for the attribute label of the terminal merchant private domain and the public domain label accumulated by the platform party, both are obtained by data statistical analysis on user data, therefore, both belong to the label from the statistical perspective; distinguished from the predicted value label, the predicted value label is to predict the value calculation parameter of the user from the feature data of the user, and calculate the life cycle value of the user according to the value calculation parameter to determine the predicted value label, which is essentially to predict the value of the user by using the feature data of the user, and determine the value label of the user according to the predicted value of the user, which belongs to the label from the prediction perspective.

[0042] In specific implementation, on the basis of the value stratification of the user, the statistical label in the private label library of the terminal merchant can be divided into each value stratification, that is, the statistical label in the private label library of the terminal merchant is taken as the secondary label of the value label corresponding to each value stratification, so that on the basis of predicting the value of the user, the statistical label level can be further deepened to determine the statistical label suitable for the user, and the target label determined in this way not only conforms to the current user value stratification of the user, but also conforms to the user attributes from the statistical perspective, thereby providing a data basis for more accurately and comprehensively determining the target label of the user in the future.

[0043] In addition, the above determination of the statistical label under the predicted value label in the private label library of the terminal merchant can be replaced by determination of the target label hit by the feature data in the private label library of the terminal merchant, and combined with other corresponding steps of the present embodiment to form a new implementation mode.

[0044] Step S108, selecting the target label hit by the feature data from the label set containing the statistical label, and performing benefit recommendation to the user according to the benefit recommendation strategy corresponding to the target label.

[0045] After determining the statistical label under the predicted value label in the private label library of the terminal merchant, in this step, the target label hit by the feature data of the user is further selected from the label set containing the statistical label. In an optional implementation mode provided by the present embodiment, in the case where the label set is composed of the statistical label, the target label hit by the feature data is selected from the label set containing the statistical label, comprising:

[0046] For any one of the statistical labels contained in the statistical label, the following operations are performed:

[0047] Detecting whether the feature data contains sub-data satisfying the label condition of the any one statistical label;

[0048] If yes, selecting the any one statistical label as the target label;

[0049] If not, the detection process is performed on other statistical tags except any one of the statistical tags.

[0050] The tag condition refers to a numerical range or value condition that needs to be met for user data in a statistical perspective. For example, the statistical tag A is a male tag, and the tag condition of the statistical tag A is a male user. Therefore, the statistical tag A can be selected as the target tag of the user only when the male user information is recorded in the field included in the feature data of the user. For another example, the statistical tag B is a student tag, and the tag condition of the statistical tag B is that the user type is a student type. Therefore, the statistical tag B can be selected as the target tag of the user only when the type recorded in the user type field included in the feature data of the user is a student type.

[0051] In addition to the above-mentioned case in which the label set is composed of statistical tags, the label set can also be composed of statistical tags and predicted value tags. In this case, the predicted value tag is also included in the selection range of the target tag of the user. In this way, by expanding the selection range of the target tag of the user, the richness of the target tag is increased, and the diversity of the subsequent benefit recommendation based on the target tag is improved. Specifically, in an optional implementation provided by the embodiment, in the case where the label set is composed of statistical tags and predicted value tags, the target tag hit by the feature data is selected from the label set including the statistical tags, and the method comprises the following steps.

[0052] If the feature data includes sub-data satisfying the tag condition of the predicted value tag, the predicted value tag is selected as the target tag.

[0053] If the feature data does not include sub-data satisfying the tag condition of the predicted value tag, it is detected whether the feature data includes sub-data satisfying the tag condition of any one of the statistical tags included in the statistical tags. If yes, the any one of the statistical tags is selected as the target tag. If not, the detection process is performed on other statistical tags except any one of the statistical tags.

[0054] In specific implementation, after the target tag hit by the feature data is selected from the label set, the benefit recommendation is performed on the user according to the benefit recommendation strategy corresponding to the target tag. Specifically, in the benefit recommendation process, the transaction benefit of the benefit type is recommended to the user according to the benefit type or the transaction benefit included in the benefit recommendation strategy, or the transaction benefit is recommended to the user.

[0055] In addition, in order to improve the recommendation marketing effect of the vending terminal, in an optional implementation manner, a recommendation level can be set in the benefit recommendation strategy. Based on this, in the process of recommending benefits to the user according to the benefit recommendation strategy, the user is recommended the transaction benefits corresponding to the recommendation level according to the recommendation level in the benefit recommendation strategy.

[0056] The transaction benefits can be related benefits that can be used in the transaction process between the user and the vending terminal, such as discount benefits of goods in the vending machine, and marketing-related benefits for marketing purposes, such as new product reservation benefits and new user registration benefits of new services promoted through the vending machine. The recommendation level can reflect the benefit strength of the recommended transaction benefits, such as the discount strength of the four discount benefits of single-coupon, single-coupon, full-reduction coupon, and package discount coupon, which increases in turn, and the recommendation level also increases accordingly.

[0057] In actual application, after the user and the vending terminal complete the above-mentioned benefit recommendation to the user, in an optional implementation manner provided by the embodiment, in the case where the transaction benefit recommended to the user is detected, the transaction order of the user for the transaction object of the vending terminal is settled based on the transaction benefit.

[0058] Further, after the order settlement, the user feedback of the benefit recommendation can be analyzed, so as to make more accurate and effective recommendation marketing through the analysis of the user feedback. In an optional implementation manner provided by the embodiment, the benefit recommendation analysis is performed in the following manner: generating the recommendation record, access record and / or cancellation record of the transaction benefit, to perform the benefit recommendation analysis processing of the vending terminal.

[0059] The following takes the application of the benefit recommendation processing method provided by the embodiment in the self-service vending scene as an example, combined with Figure 2 The benefit recommendation processing method provided by the embodiment is further described with reference to Figure 2 The benefit recommendation processing method applied in the self-service vending scene specifically includes the following steps.

[0060] Before the benefit recommendation to the user, the terminal merchant of the vending terminal calls a label synchronization interface to upload a private domain label. Correspondingly, the label synchronization interface responds to the call of the terminal merchant, reads the attribute label from the customer management system of the terminal merchant, performs mask processing on the read attribute label, and uploads the private domain label obtained by the mask processing to the platform side. After receiving the private domain label uploaded by the terminal merchant calling the label synchronization interface, the platform side fuses the private domain label with the public domain label stored by the platform side itself, obtains the private domain label library of the terminal merchant and stores it.

[0061] Step S202, according to the identity information of the user who transacts with the vending terminal, the characteristic data of the user is obtained.

[0062] Step S204, the characteristic data is input into the life cycle value model to calculate the life cycle value parameter, and the life cycle value parameter of the user is output.

[0063] Step S206, the life cycle value of the user is calculated according to the life cycle value parameter of the user, and the value period label corresponding to the value interval where the life cycle value is located is determined.

[0064] Step S208, the statistical label under the value period label in the private label library of the terminal merchant is determined.

[0065] Step S210, the target label hit by the characteristic data is selected in the determined statistical label.

[0066] Step S212, the benefit recommendation is made to the user according to the benefit recommendation strategy corresponding to the target label.

[0067] The benefit recommendation processing device provided in the specification implements, for example:

[0068] In the above embodiment, a benefit recommendation processing method is provided, and a corresponding benefit recommendation processing device is also provided, which will be described below with reference to the accompanying drawings.

[0069] Reference Figure 3 It shows a schematic diagram of a benefit recommendation processing device provided in the embodiment.

[0070] Since the device embodiment corresponds to the method embodiment, it is described more simply, and the related parts can be referred to the above-mentioned corresponding description of the method embodiment. The device embodiment described below is only schematic.

[0071] The embodiment provides a benefit recommendation processing device, which comprises:

[0072] The characteristic data acquisition module 302 is configured to acquire the characteristic data of the user who interacts with the vending terminal;

[0073] The value layering parameter calculation module 304 is configured to input the characteristic data into the value layering model to calculate the value layering parameter, and output the value layering parameter of the user;

[0074] The statistical label determination module 306 is configured to determine the predicted value label of the user according to the value layering parameter, and determine the statistical label of the predicted value label in the private label library of the terminal merchant;

[0075] The equity recommendation module 308 is configured to select a target label hit by the feature data in a label set containing the statistical label, and perform equity recommendation to the user according to an equity recommendation strategy corresponding to the target label.

[0076] The equity recommendation processing device provided in the specification implements, for example:

[0077] Corresponding to the above description, based on the same technical concept, one or more embodiments of the specification also provide an equity recommendation processing device for executing the equity recommendation processing method provided above, Figure 4 A structural schematic diagram of an equity recommendation processing device provided for one or more embodiments of the specification.

[0078] The equity recommendation processing device provided in the embodiment includes:

[0079] As Figure 4 indicated, the equity recommendation processing device can have relatively large differences due to different configurations or performances, and can include one or more processors 401 and memories 402, and the memories 402 can store one or more storage applications or data. Among them, the memory 402 can be temporary storage or persistent storage. The application stored in the memory 402 can include one or more modules (not shown in the figure), and each module can include a series of computer executable instructions in the equity recommendation processing device. Further, the processor 401 can be configured to communicate with the memory 402 and execute a series of computer executable instructions in the memory 402 on the equity recommendation processing device. The equity recommendation processing device can also include one or more power supplies 403, one or more wired or wireless network interfaces 404, one or more input / output interfaces 405, one or more keyboards 406, etc.

[0080] In one specific embodiment, the equity recommendation processing device includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and one or more programs can include one or more modules, and each module can include a series of computer executable instructions in the equity recommendation processing device, and the one or more programs configured to be executed by the one or more processors include computer executable instructions for:

[0081] Obtaining feature data of a user interacting with the vending terminal;

[0082] Inputting the feature data into a value stratification model to calculate value stratification parameters, and outputting value stratification parameters of the user;

[0083] determine a predicted value label of the user according to the value stratification parameter, and determine a statistical label of the predicted value label in a private label library of a terminal merchant;

[0084] select a target label hit by the feature data in a label set containing the statistical label, and perform benefit recommendation to the user according to a benefit recommendation strategy corresponding to the target label.

[0085] The storage medium provided in the specification implements, for example:

[0086] According to the same technical concept, one or more embodiments of the specification also provide a storage medium corresponding to the above-described benefit recommendation processing method.

[0087] The storage medium provided in the embodiment is used to store computer executable instructions, and the computer executable instructions implement the following processes when executed by a processor:

[0088] Obtain feature data of a user interacting with an automatic vending terminal;

[0089] Input the feature data into a value stratification model to calculate a value stratification parameter, and output the value stratification parameter of the user;

[0090] determine a predicted value label of the user according to the value stratification parameter, and determine a statistical label of the predicted value label in a private label library of a terminal merchant;

[0091] select a target label hit by the feature data in a label set containing the statistical label, and perform benefit recommendation to the user according to a benefit recommendation strategy corresponding to the target label.

[0092] It should be noted that the embodiments of the storage medium in the specification and the embodiments of the benefit recommendation processing method in the specification are based on the same inventive concept, so the specific implementation of the embodiments can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0093] The above describes specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0094] In the 1930s, it was clear to distinguish whether an improvement in a technology was in hardware (e.g., improvement in circuit structure of diodes, transistors, switches, etc.) or in software (e.g., improvement in method flow). However, as technology has evolved, many improvements in method flow today can be considered as direct improvements in hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented by a hardware entity module. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A digital system is "integrated" on a PLD by the designer programming it, rather than by asking a chip manufacturer to design and fabricate a custom integrated circuit chip. Moreover, instead of manually fabricating an integrated circuit chip, this programming is now mostly implemented by "logic compiler" software, which is similar to software compilers used in program development, and the original code to be compiled is written in a specific programming language, called a hardware description language (HDL), of which there are many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., the most commonly used being VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should be clear to those skilled in the art that, by simply logically programming a method flow in one of the above hardware description languages and programming it into an integrated circuit, a hardware circuit implementing the logical method flow can be easily obtained.

[0095] The controller can be implemented in any suitable way, e.g. the controller can take the form of a microprocessor or processor and a computer readable medium storing computer readable program code, e.g. software or firmware, executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller and an embedded microcontroller, examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91 SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to being implemented in pure computer readable program code form, the controller can perfectly well be implemented by means of logic programmed into logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers, etc. to perform the same functions. The controller can thus be considered a hardware component, and the means comprised therein for performing various functions can be considered structures within the hardware component. Alternatively, or even additionally, the means for performing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0096] The systems, apparatuses, modules or units illustrated by the above embodiments can be implemented by computer chips or entities, or products with certain functions. A typical implementation device is a computer. Specifically, the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0097] For the sake of description, the above apparatuses are described in various units by functions respectively. Of course, the functions of each unit can be implemented in the same or multiple software and / or hardware in the implementation of the embodiments of the present specification.

[0098] Those skilled in the art will appreciate that one or more embodiments of the present specification can be provided as a method, a system or a computer program product. Therefore, one or more embodiments of the present specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0099] The specification is presented with reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing element or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more flow or multiple flows and / or blocks Figure 1 one or more flow or multiple flows and / or blocks

[0100] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more flow or multiple flows and / or blocks Figure 1 one or more flow or multiple flows and / or blocks

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more flow or multiple flows and / or blocks Figure 1 one or more flow or multiple flows and / or blocks

[0102] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0103] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer-readable media.

[0104] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0105] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, such that processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0106] One or more embodiments of the specification can be described in the general context of computer-executable instructions being executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the specification can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0107] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment focuses on the difference from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0108] The above merely provides the example of the present document and is not intended to limit the present document. For those skilled in the art, the present document can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present document shall be included in the scope of claims of the present document.

Claims

1. A benefit recommendation processing method, comprising: obtaining feature data of a user interacting with a vending terminal; inputting the feature data into a value stratification model to perform value stratification parameter calculation, and outputting a calculation parameter of a life cycle value of the user; calculating the life cycle value of the user according to the calculation parameter, and taking a value period label corresponding to a value interval in which the life cycle value is located as a predicted value label, and determining a statistical label under the predicted value label in a private label library of a terminal merchant; selecting a target label hit by the feature data from a label set composed of the statistical label and the predicted value label, and recommending a transaction benefit related to the vending terminal to the user according to a benefit recommendation strategy corresponding to the target label.

2. The benefit recommendation processing method of claim 1, wherein the private label library is obtained by merging private domain labels uploaded by the terminal merchant calling a label synchronization interface and public domain labels generated in advance.

3. The benefit recommendation processing method of claim 2, wherein the label synchronization interface reads attribute labels from a customer management system of the terminal merchant in response to a call of the terminal merchant, performs mask processing on the read attribute labels, and uploads the private domain labels obtained by the mask processing.

4. The benefit recommendation processing method of claim 1, wherein the label set is composed of the statistical label; the selecting of the target label hit by the feature data from the label set containing the statistical label comprises: for any one of the statistical labels, performing the following operations: detecting whether the feature data contains sub-data satisfying a label condition of the any one of the statistical labels; if yes, selecting the any one of the statistical labels as the target label.

5. The benefit recommendation processing method of claim 1, wherein the label set is composed of the statistical label and the predicted value label; the selecting of the target label hit by the feature data from the label set containing the statistical label comprises: if the feature data contains sub-data satisfying a label condition of the predicted value label, selecting the predicted value label as the target label; if the feature data does not contain sub-data satisfying the label condition of the predicted value label, detecting whether the feature data contains sub-data satisfying a label condition of any one of the statistical labels, and if yes, selecting the any one of the statistical labels as the target label.

6. The benefit recommendation processing method of claim 1, wherein the vending terminal, after detecting an interaction action of the user, determines identity information of the user based on interaction data obtained by performing the interaction action, and uploads the identity information by calling a recommendation interface to obtain the feature data of the user according to the identity information.

7. The benefit recommendation processing method of claim 6, wherein the interaction action comprises at least one of the following: The user scans a transaction identification code of the vending terminal, the vending terminal collects an identity image of the user, the user inputs identity information through the vending terminal, and the vending terminal collects an identity code of the user.

8. The benefit recommendation processing method of claim 1, wherein the value stratification parameter comprises a calculation parameter for calculating a life cycle value. The determining of the predicted value label of the user according to the value stratification parameter comprises: calculating the life cycle value of the user according to the calculation parameter, and taking a value period label corresponding to a value interval in which the life cycle value is located as the predicted value label.

9. The benefit recommendation processing method of claim 1, wherein the recommending of the benefit to the user according to the benefit recommendation strategy corresponding to the target label comprises: recommending a transaction benefit corresponding to a recommendation level to the user according to the recommendation level in the benefit recommendation strategy.

10. The benefit recommendation processing method of claim 1, further comprising, after the selecting of the target label hit by the feature data from a label set comprising the statistical label and the recommending of the benefit to the user according to the benefit recommendation strategy corresponding to the target label: in a case where a redemption instruction of the transaction benefit recommended to the user is detected, performing order settlement on a transaction order of a transaction object of the vending terminal of the user based on the transaction benefit.

11. The benefit recommendation processing method of claim 10, further comprising, after the performing of the order settlement on the transaction order of the transaction object of the vending terminal of the user based on the transaction benefit in a case where the redemption instruction of the transaction benefit recommended to the user is detected: generating a recommendation record, an access record and / or a redemption record of the transaction benefit, to perform benefit recommendation analysis processing of the vending terminal.

12. A benefit recommendation processing apparatus, comprising: a feature data acquisition module configured to acquire feature data of a user interacting with a vending terminal; a value stratification parameter calculation module configured to input the feature data into a value stratification model to perform value stratification parameter calculation, and output a calculation parameter of a life cycle value of the user; a statistical label determination module configured to calculate the life cycle value of the user according to the calculation parameter, take a value period label corresponding to a value interval in which the life cycle value is located as a predicted value label, and determine a statistical label under the predicted value label in a private label library of a terminal merchant; a benefit recommendation module configured to select a target label hit by the feature data from a label set comprising the statistical label and the predicted value label, and recommend a transaction benefit related to the vending terminal to the user according to a benefit recommendation strategy corresponding to the target label.

13. A benefit recommendation processing device, comprising: a processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to: Obtaining characteristic data of a user interacting with the automatic vending terminal; Inputting the characteristic data into a value stratification model to perform value stratification parameter calculation, and outputting calculation parameters of a life cycle value of the user; Calculating the life cycle value of the user according to the calculation parameters, taking a value period label corresponding to a value interval in which the life cycle value is located as a predicted value label, and determining a statistical label under the predicted value label in a private label library of a terminal merchant; Selecting a target label hit by the characteristic data in a label set composed of the statistical label and the predicted value label, and recommending a transaction benefit related to the automatic vending terminal to the user according to a benefit recommendation strategy corresponding to the target label.

14. A storage medium for storing computer executable instructions, the computer executable instructions, when executed by a processor, implement the following processes: Obtaining characteristic data of a user interacting with the automatic vending terminal; Inputting the characteristic data into a value stratification model to perform value stratification parameter calculation, and outputting calculation parameters of a life cycle value of the user; Calculating the life cycle value of the user according to the calculation parameters, taking a value period label corresponding to a value interval in which the life cycle value is located as a predicted value label, and determining a statistical label under the predicted value label in a private label library of a terminal merchant; Selecting a target label hit by the characteristic data in a label set composed of the statistical label and the predicted value label, and recommending a transaction benefit related to the automatic vending terminal to the user according to a benefit recommendation strategy corresponding to the target label.

Images