Gas station commodity automatic recommendation method and device and electronic equipment

Abstract

The embodiment of the invention discloses a gas station commodity automatic recommendation method and device and electronic equipment. The method comprises the following steps: acquiring historical consumption data of a target user, and generating date-associated historical refueling data and historical shopping data based on the data to obtain an associated data set; and then, constructing a user behavior portrait corresponding to the associated data set based on a feature recognition algorithm. Furthermore, after the current refueling data of the target user is obtained, the current refueling data and the user behavior portrait are processed based on a machine learning algorithm, and a commodity recommendation list is obtained. Different commodity recommendation lists are generated by analyzing the historical consumption data of each target user, personalized requirements of different customer users are met, the purpose of improving the commodity purchase rate is achieved, a commodity recommendation model can be automatically optimized after each recommendation is completed, and the commodity recommendation efficiency is improved. And the accuracy and the user satisfaction of the gas station commodity automatic recommendation method are further improved.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of data analysis technology, and more particularly, to a method, device, and electronic device for automatically recommending products at a gas station. Background Art

[0002] With the rapid development of artificial intelligence and big data analysis technology, self-service is becoming more and more popular in all walks of life. Especially in the new gas station model that has emerged, self-service gas station vending machines have become an important facility for the convenience of customers. Therefore, a gas station commodity automatic recommendation method is needed to automatically recommend commodities when customers complete vehicle refueling. However, the existing gas station commodity automatic recommendation methods mostly use static fixed commodity display, lack of responsiveness to customers' personalized needs, resulting in customers lacking personalized service guidance when choosing commodities, missing the opportunity to increase sales, and failing to effectively improve customer purchase rate and satisfaction. Summary of the invention

[0003] The embodiments of this specification provide a method, device and electronic device for automatically recommending products at a gas station, and the technical solution thereof is as follows: In a first aspect, an embodiment of the present specification provides a method for automatically recommending products at a gas station, the method comprising: Acquire historical consumption data of the target user, and associate historical refueling data and historical shopping data based on the data generation date to obtain an associated data set, wherein the historical consumption data includes the historical refueling data and the historical shopping data, the historical refueling data includes the refueling amount and the refueling type, and the historical shopping data includes the shopping quantity and the shopping type; Constructing a user behavior profile corresponding to the associated data set based on a feature recognition algorithm, wherein the user behavior profile is used to describe the user's consumption preference; The current refueling data of the target user is obtained, and the current refueling data and the user behavior profile are processed based on a machine learning algorithm to obtain a product recommendation list.

[0004] In a second aspect, a gas station commodity automatic recommendation device is provided, the device comprising: an acquisition module, used to acquire historical consumption data of a target user, and associate historical refueling data and historical shopping data based on a data generation date to obtain an associated data set, wherein the historical consumption data includes the historical refueling data and the historical shopping data, the historical refueling data includes a refueling amount and a refueling type, and the historical shopping data includes a shopping quantity and a shopping type; A construction module, used to construct a user behavior portrait corresponding to the associated data set based on a feature recognition algorithm, wherein the user behavior portrait is used to describe the user's consumption preference; The recommendation module is used to obtain the current refueling data of the target user, process the current refueling data and the user behavior profile based on a machine learning algorithm, and obtain a product recommendation list.

[0005] In a third aspect, an electronic device is provided, including a device processor and a memory; The device processor is connected to the memory; The memory is used to store executable program code; The device processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0006] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a device processor, cause the computer or the device processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0007] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: In one or more embodiments of the present specification, a related data set is obtained by acquiring the historical consumption data of the target user, and associating the historical refueling data and the historical shopping data based on the data generation date. Then, a user behavior portrait corresponding to the related data set is constructed based on a feature recognition algorithm. Furthermore, after acquiring the current refueling data of the target user, the current refueling data and the user behavior portrait are processed based on a machine learning algorithm to obtain a product recommendation list. By generating different product recommendation lists based on the analysis of the historical consumption data of each target user, the personalized needs of different customer users are met, thereby achieving the purpose of increasing the purchase rate of goods, and the product recommendation model can be automatically optimized after each recommendation is completed, further improving the accuracy and user satisfaction of the automatic recommendation method for gas station goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 A schematic diagram of the system architecture of a method for automatically recommending gas station products provided in an embodiment of this specification; Figure 2A flowchart of a method for automatically recommending gas station merchandise provided in an embodiment of this specification; Figure 3 A schematic diagram of the structure of a gas station commodity automatic recommendation device provided in an embodiment of this specification; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0011] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0012] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present specification. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described with respect to some examples may be combined in other examples.

[0013] See also Figure 1 , Figure 1 A schematic diagram of the system architecture of a gas station commodity automatic recommendation method provided in an embodiment of this specification is shown.

[0014] like Figure 1 As shown, the system architecture of the gas station commodity automatic recommendation method may include at least a terminal 10 , a server 20 and a network 30 .

[0015] The terminal 10 includes but is not limited to electronic devices such as smart phones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, smart wearable devices, etc., and may also be software running on the above electronic devices, such as applications, etc. Optionally, the operating system running on the electronic device may include but is not limited to Android system, IOS system, Linux, Windows, etc. Optionally, the terminal 10 provides the user with an automatic recommendation service for gas station products. The terminal 10 may obtain an automatic recommendation instruction for gas station products from an application program interface and send an automatic recommendation request for gas station products to the server 20.

[0016] The server 20 can provide background services for the terminal 10. According to the gas station commodity automatic recommendation request sent by the terminal 10, the server 20 will obtain a series of gas station commodity automatic recommendation instructions, and the server 20 transmits the gas station commodity automatic recommendation instructions to other terminals 10 through the network 30. Specifically, the server 20 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0017] The network 30 is used to provide a medium for a communication link between the terminal 10 and the server 20. The network 30 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0018] In addition, it should be noted that Figure 1 What is shown is only one system provided by the present disclosure. In practical applications, other systems may also be included, for example, more terminals may be included.

[0019] In the embodiments of the present specification, the terminal 10 and the server 20 may be directly or indirectly connected via wired or wireless communication, which is not limited in the present disclosure.

[0020] See next Figure 2 , Figure 2 The overall flow chart of a method for automatically recommending gas station products provided in an embodiment of the present specification is shown. The method for automatically recommending gas station products can be used in the server 20.

[0021] like Figure 2 As shown, the gas station commodity automatic recommendation method may at least include the following steps: Step 201: Obtain historical consumption data of a target user, and associate historical refueling data and historical shopping data based on a data generation date to obtain an associated data set.

[0022] The historical consumption data includes the historical refueling data and the historical shopping data. The historical refueling data includes the refueling amount and the refueling type. The historical shopping data includes the shopping quantity and the shopping type.

[0023] In the embodiments of this specification, a gas station user generally has historical consumption records at the gas station, and when using the gas station commodity automatic recommendation method, it is usually necessary to connect regional or chain gas stations online to achieve the purpose of sharing data resources. Therefore, before the target user consumes at the gas station, the target user's historical consumption data can be obtained from the online system after obtaining the target user's consent and obtaining access rights. Among them, gas station users mostly refuel and shop when consuming at the gas station, so the historical consumption data on the same date may include historical refueling data and historical shopping data. Furthermore, the historical refueling data and historical shopping data can be associated based on the data generation date to obtain an associated data set.

[0024] Each historical refueling data in the associated data set has a corresponding historical shopping data on the same data generation date. The historical refueling data may include the refueling amount and refueling type, and the historical shopping data may include the shopping quantity and shopping type.

[0025] In one possible implementation, the acquiring of historical consumption data of the target user includes: Obtain the target user's identity information; The historical consumption data corresponding to the identity information is queried based on the consumption information database.

[0026] In the embodiment of this specification, when obtaining the historical consumption data of the target user from the gas station online system, the identity information of the target user can be obtained by inputting the user membership code or identifying the user portrait after obtaining the consent of the target user. Then, the obtained identity information is input into the consumption information database for query to obtain the historical consumption data corresponding to the identity information. Among them, the consumption information database can be constructed by statistically analyzing the historical data information after each consumption of the gas station user, and the consumption information database can be updated in real time after the gas station user consumes again. In the consumption information database, each identity information has a corresponding historical consumption data.

[0027] In one possible implementation, after acquiring the historical consumption data of the target user, the method further includes: Removing abnormal data and incomplete data from the historical consumption data to obtain preprocessed data; The preprocessed data is format converted and normalized to obtain standard data.

[0028] In the embodiment of the present specification, the historical consumption data of the target user may include a part of abnormal data and incomplete data. Among them, in the process of uploading historical consumption data, abnormal data and incomplete data may be generated due to various reasons such as network interruption or manual cancellation of payment after invalid selection of goods. Therefore, after obtaining the rated historical consumption data of the target user, the historical consumption data can be cleaned to remove the abnormal data and incomplete data in the historical consumption data, obtain pre-processed data, and save computing resources in the subsequent data processing process. Then, in order to ensure that the pre-processed data can be correctly read and processed later, and to improve the efficiency and accuracy of model training, the pre-processed data can be parsed first, the data source and format of the pre-processed data can be analyzed, and the pre-processed data can be converted into a data structure suitable for a machine learning library or framework, and then the non-numeric field can be converted into a numeric type using label encoding. Further, the data after format conversion is compressed to a smaller range using standardized scaling, thereby completing the normalization process and obtaining standard data.

[0029] Step 202: construct a user behavior profile corresponding to the associated data set based on a feature recognition algorithm.

[0030] Among them, the user behavior portrait is used to describe the user's consumption preferences.

[0031] In the embodiments of this specification, after obtaining the associated data set through historical consumption data, in order to better provide personalized gas station product recommendations for target users, the key features in the associated data set can be extracted based on the feature recognition algorithm. As an example, the key features may include refueling data features and shopping data features, etc., so as to construct a user behavior portrait to describe the user's consumption preferences. Among them, when constructing the user behavior portrait corresponding to the associated data set, the data features of different types of data in the key data set can be extracted, and then the behavioral preference levels of different data features can be obtained. Finally, the behavioral preference levels are aggregated to obtain the overall user behavior portrait. In addition, new features of the associated data set can also be created based on the feature recognition algorithm. As an example, the new features may include the frequency of buying specific products, the average consumption quantity, the length of time since the last purchase, etc. Then, the user behavior portraits corresponding to all new features are constructed.

[0032] In one possible implementation, the user behavior portrait corresponding to the associated data set is constructed based on a feature recognition algorithm, and the user behavior portrait is used to describe the user's consumption preference, including: Extracting historical consumption features corresponding to the associated data set based on a feature recognition algorithm, the historical consumption features including a first feature and a second feature, the first feature being a feature corresponding to the historical refueling data, and the second feature being a feature corresponding to the historical shopping data; A user behavior profile corresponding to the historical consumption characteristics is constructed, and the user behavior profile is used to describe the user's consumption preferences.

[0033] In the embodiments of this specification, the features corresponding to the historical refueling data in the associated data set can be extracted first and used as the first features, and then the features corresponding to the historical shopping data in the associated data set can be extracted as the second features. Then, the first feature and the second feature are fused and merged based on the feature fusion algorithm to obtain the historical consumption feature. Furthermore, the consumption preference degree corresponding to the historical consumption feature is determined, and a user behavior profile is constructed based on this, and the user behavior profile is used to describe the user's consumption preference.

[0034] Step 203: Acquire the current refueling data of the target user, process the current refueling data and the user behavior profile based on a machine learning algorithm, and obtain a product recommendation list.

[0035] In the embodiments of this specification, in order to save time, gas station users usually consume gas first and then go shopping, and develop fixed consumption habits. Therefore, in order to automatically recommend gas station products to the target user, the current refueling data generated when the target user enters the gas station this time can be obtained first, and a product recommendation model corresponding to the user behavior profile of the target user can be constructed through a machine learning algorithm. Furthermore, the product recommendation model and the current refueling data obtained previously are combined to obtain a product recommendation list, and the product recommendation list is displayed on the target terminal display screen to complete the automatic recommendation of gas station products to the target user.

[0036] In one possible implementation, the acquiring the current refueling data of the target user, processing the current refueling data and the user behavior profile based on a machine learning algorithm, and obtaining a product recommendation list includes: Building a product recommendation model corresponding to the user behavior profile based on a machine learning algorithm; The current refueling data of the target user is obtained, and a commodity recommendation list corresponding to the current refueling data is determined based on the commodity recommendation model.

[0037] In the embodiments of this specification, an initial product recommendation model can be first constructed based on a machine learning algorithm. In the initial product recommendation model, the current refueling model data is used as input and the product recommendation model data is used as output. Next, the user behavior profile is used as a training set to train the initial product recommendation model to obtain a trained product recommendation model. Furthermore, after determining that the target user uses the gas station product automatic recommendation system, the current refueling data of the target user is obtained, and the current refueling data is converted into a model format and input into the trained product recommendation model. After obtaining the model recommendation output, the data format type is converted to obtain a product recommendation list corresponding to the current refueling data, and the product recommendation list is displayed on the target terminal display screen to complete the automatic recommendation of gas station products for the target user.

[0038] In one possible implementation, determining the commodity recommendation list corresponding to the current refueling data based on the commodity recommendation model includes: Determine an interest list corresponding to the current refueling data based on the product recommendation model; Determine the similarity list corresponding to the target similar users based on the collaborative filtering algorithm; The interest list and the similarity list are combined to obtain a product recommendation list.

[0039] In the embodiment of the present specification, in order to improve the accuracy of the recommendation list and user satisfaction, when determining the commodity recommendation list corresponding to the current refueling data through the commodity recommendation model, in addition to directly obtaining the commodity recommendation list, the interest list corresponding to the current refueling data can also be determined based on the commodity recommendation model. The interest list is a list of interest recommendations for the target user when shopping after completing the refueling consumption based on the historical consumption data of the target user. Then, the target similar users with similar consumption habits as the target user are determined through the collaborative filtering algorithm. As an example, when the refueling amount and refueling type in the historical refueling data of two gas station users are the same, or the shopping amount and shopping type in the historical shopping data of the two gas station users are the same, the two gas station users can be marked as similar users. Further, the historical recommendation list of the target similar user, that is, the similarity list, is determined. Finally, the determined interest list and the similarity list are subjected to the union optimization process to obtain the final required commodity recommendation list, and the commodity recommendation list is displayed on the display screen of the target terminal to complete the automatic recommendation of gas station commodities for the target user.

[0040] In one possible implementation, after the current refueling data and the user behavior profile are processed based on a machine learning algorithm to obtain a product recommendation list, the method further includes: Acquire user feedback information generated when the target user performs a selection action on the product recommendation list; The product recommendation model is optimized based on the user feedback information.

[0041] In the embodiment of the present specification, when the target user selects a product from the displayed product recommendation list, user feedback information will be generated after the selection action is completed. The user feedback information may include the target user's shopping quantity information, shopping category information, and satisfaction feedback information of the product recommendation. Then, the shopping quantity information and shopping category information in the user feedback information are merged with the historical shopping data, and the associated data set of the target user is updated in real time. When the satisfaction feedback information indicates that the product recommendation model is not satisfactory, new data features can be constructed to optimize the product recommendation model to improve the accuracy of the automatic recommendation system and user satisfaction.

[0042] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0043] See next Figure 3 , Figure 3 The structure diagram of a gas station commodity automatic recommendation device provided in the embodiment of this specification is shown. It should be noted that: Figure 3 The gas station commodity automatic recommendation device shown is used to implement this application Figure 2 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2 The embodiment shown.

[0044] like Figure 3 As shown, the gas station commodity automatic recommendation device may at least include: An acquisition module 301 is used to acquire historical consumption data of a target user, and associate historical refueling data and historical shopping data based on a data generation date to obtain an associated data set, wherein the historical consumption data includes the historical refueling data and the historical shopping data, the historical refueling data includes a refueling amount and a refueling type, and the historical shopping data includes a shopping quantity and a shopping type; A construction module 302 is used to construct a user behavior profile corresponding to the associated data set based on a feature recognition algorithm, wherein the user behavior profile is used to describe the user's consumption preference; The recommendation module 303 is used to obtain the current refueling data of the target user, process the current refueling data and the user behavior profile based on a machine learning algorithm, and obtain a product recommendation list.

[0045] In one possible implementation, the acquisition module 301 is specifically used for: Obtain the target user's identity information; The historical consumption data corresponding to the identity information is queried based on the consumption information database.

[0046] In one possible implementation, the acquisition module 301 is further specifically used for: Removing abnormal data and incomplete data from the historical consumption data to obtain preprocessed data; The preprocessed data is format converted and normalized to obtain standard data.

[0047] In one possible implementation, the construction module 302 is specifically used to: Extracting historical consumption features corresponding to the associated data set based on a feature recognition algorithm, the historical consumption features including a first feature and a second feature, the first feature being a feature corresponding to the historical refueling data, and the second feature being a feature corresponding to the historical shopping data; A user behavior profile corresponding to the historical consumption characteristics is constructed, and the user behavior profile is used to describe the user's consumption preferences.

[0048] In one possible implementation, the recommendation module 303 is specifically used for: Building a product recommendation model corresponding to the user behavior profile based on a machine learning algorithm; The current refueling data of the target user is obtained, and a commodity recommendation list corresponding to the current refueling data is determined based on the commodity recommendation model.

[0049] In one possible implementation, the recommendation module 303 is further configured to: Determine an interest list corresponding to the current refueling data based on the product recommendation model; Determine the similarity list corresponding to the target similar users based on the collaborative filtering algorithm; The interest list and the similarity list are combined to obtain a product recommendation list.

[0050] In one possible implementation, the recommendation module 303 is further configured to: Acquire user feedback information generated when the target user performs a selection action on the product recommendation list; The product recommendation model is optimized based on the user feedback information.

[0051] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0052] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0053] See next Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0054] like Figure 4 As shown, the electronic device 400 may include: at least one device processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0055] The communication bus 402 may be used to realize the connection and communication among the above-mentioned components.

[0056] The user interface 403 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0057] The network interface 404 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0058] Among them, the device processor 401 may include one or more processing cores. The device processor 401 uses various interfaces and lines to connect various parts within the entire electronic device 400, and executes various functions and processes data of the electronic device 400 by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the device processor 401 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The device processor 401 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the device processor 401, and it can be implemented separately through a chip.

[0059] The memory 405 may include a RAM or a ROM. Optionally, the memory 405 includes a non-transitory computer-readable medium. The memory 405 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 405 may optionally be at least one storage device located away from the aforementioned device processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0060] Specifically, the device processor 401 may be used to call the gas station commodity automatic recommendation application stored in the memory 405, and specifically perform the following operations: Acquire historical consumption data of the target user, and associate historical refueling data and historical shopping data based on the data generation date to obtain an associated data set, wherein the historical consumption data includes the historical refueling data and the historical shopping data, the historical refueling data includes the refueling amount and the refueling type, and the historical shopping data includes the shopping quantity and the shopping type; Constructing a user behavior profile corresponding to the associated data set based on a feature recognition algorithm, wherein the user behavior profile is used to describe the user's consumption preference; The current refueling data of the target user is obtained, and the current refueling data and the user behavior profile are processed based on a machine learning algorithm to obtain a product recommendation list.

[0061] As an optional embodiment of this specification, it is characterized in that the acquiring the historical consumption data of the target user includes: Obtain the target user's identity information; The historical consumption data corresponding to the identity information is queried based on the consumption information database.

[0062] As an optional embodiment of the present specification, it is characterized in that after obtaining the historical consumption data of the target user, it also includes: Removing abnormal data and incomplete data from the historical consumption data to obtain preprocessed data; The preprocessed data is format converted and normalized to obtain standard data.

[0063] As an optional embodiment of this specification, it is characterized in that the user behavior portrait corresponding to the associated data set is constructed based on the feature recognition algorithm, and the user behavior portrait is used to describe the user's consumption preference, including: Extracting historical consumption features corresponding to the associated data set based on a feature recognition algorithm, the historical consumption features including a first feature and a second feature, the first feature being a feature corresponding to the historical refueling data, and the second feature being a feature corresponding to the historical shopping data; A user behavior profile corresponding to the historical consumption characteristics is constructed, and the user behavior profile is used to describe the user's consumption preferences.

[0064] As an optional embodiment of this specification, it is characterized in that the acquiring the current refueling data of the target user, processing the current refueling data and the user behavior portrait based on a machine learning algorithm, and obtaining a product recommendation list includes: Building a product recommendation model corresponding to the user behavior profile based on a machine learning algorithm; The current refueling data of the target user is obtained, and a commodity recommendation list corresponding to the current refueling data is determined based on the commodity recommendation model.

[0065] As an optional embodiment of this specification, it is characterized in that the determining the commodity recommendation list corresponding to the current refueling data based on the commodity recommendation model includes: Determine an interest list corresponding to the current refueling data based on the product recommendation model; Determine the similarity list corresponding to the target similar users based on the collaborative filtering algorithm; The interest list and the similarity list are combined to obtain a product recommendation list.

[0066] As an optional embodiment of this specification, it is characterized in that after the current refueling data and the user behavior portrait are processed based on the machine learning algorithm to obtain the product recommendation list, it also includes: Acquire user feedback information generated when the target user performs a selection action on the product recommendation list; The product recommendation model is optimized based on the user feedback information.

[0067] The embodiments of this specification also provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0068] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0069] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0070] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0073] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0074] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0075] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for automatically recommending products at a gas station, characterized in that: The method comprises: Acquire historical consumption data of the target user, and associate historical refueling data and historical shopping data based on the data generation date to obtain an associated data set, wherein the historical consumption data includes the historical refueling data and the historical shopping data, the historical refueling data includes the refueling amount and the refueling type, and the historical shopping data includes the shopping quantity and the shopping type; Constructing a user behavior profile corresponding to the associated data set based on a feature recognition algorithm, wherein the user behavior profile is used to describe the user's consumption preference; The current refueling data of the target user is obtained, and the current refueling data and the user behavior profile are processed based on a machine learning algorithm to obtain a product recommendation list.

2. The method according to claim 1, characterized in that The obtaining of the historical consumption data of the target user includes: Obtain the target user's identity information; The historical consumption data corresponding to the identity information is queried based on the consumption information database.

3. The method according to claim 1, characterized in that After obtaining the historical consumption data of the target user, the method further includes: Removing abnormal data and incomplete data from the historical consumption data to obtain preprocessed data; The preprocessed data is format converted and normalized to obtain standard data.

4. The method according to claim 1, characterized in that: The user behavior portrait corresponding to the associated data set is constructed based on the feature recognition algorithm, and the user behavior portrait is used to describe the user's consumption preference, including: Extracting historical consumption features corresponding to the associated data set based on a feature recognition algorithm, the historical consumption features including a first feature and a second feature, the first feature being a feature corresponding to the historical refueling data, and the second feature being a feature corresponding to the historical shopping data; A user behavior profile corresponding to the historical consumption characteristics is constructed, and the user behavior profile is used to describe the user's consumption preferences.

5. The method according to claim 1, characterized in that: The step of acquiring the current refueling data of the target user, and processing the current refueling data and the user behavior profile based on a machine learning algorithm to obtain a product recommendation list includes: Building a product recommendation model corresponding to the user behavior profile based on a machine learning algorithm; The current refueling data of the target user is obtained, and a commodity recommendation list corresponding to the current refueling data is determined based on the commodity recommendation model.

6. The method according to claim 5, characterized in that The determining, based on the product recommendation model, a product recommendation list corresponding to the current refueling data includes: Determine an interest list corresponding to the current refueling data based on the product recommendation model; Determine the similarity list corresponding to the target similar users based on the collaborative filtering algorithm; The interest list and the similarity list are combined to obtain a product recommendation list.

7. The method according to claim 6, characterized in that After the current refueling data and the user behavior profile are processed based on the machine learning algorithm to obtain a product recommendation list, the method further includes: Acquire user feedback information generated when the target user performs a selection action on the product recommendation list; The product recommendation model is optimized based on the user feedback information.

8. An automatic product recommendation device for a gas station, characterized in that: The device comprises: an acquisition module, used to acquire historical consumption data of a target user, and associate historical refueling data and historical shopping data based on a data generation date to obtain an associated data set, wherein the historical consumption data includes the historical refueling data and the historical shopping data, the historical refueling data includes a refueling amount and a refueling type, and the historical shopping data includes a shopping quantity and a shopping type; A construction module, used to construct a user behavior portrait corresponding to the associated data set based on a feature recognition algorithm, wherein the user behavior portrait is used to describe the user's consumption preference; The recommendation module is used to obtain the current refueling data of the target user, process the current refueling data and the user behavior profile based on a machine learning algorithm, and obtain a product recommendation list.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images