Service pushing method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a service pushing method and device, equipment, a medium and a program product. Comprising the steps of obtaining user behavior data and a user portrait corresponding to the user behavior data, inputting the user behavior data and the user portrait into a key feature extraction model, and determining key behavior features; inputting the key behavior characteristics into a service prediction model, and determining target service information; sending the target service information to the user terminal, so that the user terminal performs service push configuration according to the target service information; wherein the user behavior data comprises at least one of in-application behavior data, search records, click behaviors and transaction history. The user behavior data and the user portrait are combined to improve the accuracy of the predicted target service information, and the target service information is sent to the user terminal corresponding to the user behavior data, so that the user terminal can complete service push configuration related to the target service required by the accurate user according to the target service information.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a service push method, device, equipment, medium and program product. Background Art

[0002] With the development and progress of society, businesses in various fields have gradually shifted from offline to online operations. In response to development needs, mobile banking has emerged. Mobile banking can provide services that are almost the same as offline services, which should provide great convenience for users.

[0003] Traditional mobile banking applications usually exist as independent service platforms, which are out of touch with users' daily mobile phone usage habits. According to statistics and user feedback, mobile banking services are often difficult to effectively reach users, making users less enthusiastic about downloading mobile banking. Currently, the user experience functionality of mobile banking applications is often improved to attract users to actively download and use them; or the popularity of mobile banking is increased through advertising, marketing activities, etc., so as to attract more potential users.

[0004] However, simply improving user experience and functionality is unlikely to fundamentally solve the problem of services being difficult to reach users, because users may not understand or know what services mobile banking can provide; secondly, although advertising and marketing activities can increase brand awareness, it is often difficult to accurately reach the target customer group, resulting in high marketing costs and limited results, making it difficult to provide users with convenient and accurate services. Summary of the invention

[0005] The present invention provides a service push method, apparatus, equipment, medium and program product, which adopts richer user behavior data and models with different applicable scenarios to extract behavior features and predict target service information, so that the predicted target service information is more in line with the user's expected needs, and then completes the service push configuration in the user terminal based on the target service information, so that when the user needs mobile banking services, the user terminal can timely and effectively identify the user's needs and provide effective service push, so as to provide users with convenient and accurate services and achieve better promotion of mobile banking applications.

[0006] In a first aspect, an embodiment of the present invention provides a service push method, including:

[0007] Obtain user behavior data and a user profile corresponding to the user behavior data, input the user behavior data and the user profile into a pre-trained key feature extraction model, and determine the key behavior features;

[0008] Input key behavior features into the pre-trained service prediction model to determine the target service information;

[0009] Sending the target service information to the user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information;

[0010] Among them, user behavior data includes at least one of in-application behavior data, search records, click behavior and transaction history.

[0011] In a second aspect, an embodiment of the present invention further provides a service push device, including:

[0012] A key feature determination module is used to obtain user behavior data and a user profile corresponding to the user behavior data, input the user behavior data and the user profile into a pre-trained key feature extraction model, and determine the key behavior features;

[0013] A service information determination module is used to input key behavior features into a pre-trained service prediction model to determine target service information;

[0014] A service push module, used to send target service information to a user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information;

[0015] Among them, user behavior data includes at least one of in-application behavior data, search records, click behavior and transaction history.

[0016] In a third aspect, an embodiment of the present invention further provides a service push device, the service push device comprising:

[0017] at least one processor; and a memory communicatively coupled to the at least one processor;

[0018] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can implement the service push method of any embodiment of the present invention.

[0019] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the service push method of any embodiment of the present invention.

[0020] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which is used to execute the service push method of any embodiment of the present invention when executed by a processor.

[0021] The embodiment of the present invention provides a service push method, device, equipment, medium and program product, which obtains user behavior data and a user portrait corresponding to the user behavior data, inputs the user behavior data and the user portrait into a pre-trained key feature extraction model to determine the key behavior features; inputs the key behavior features into a pre-trained service prediction model to determine the target service information; sends the target service information to the user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information; wherein the user behavior data includes at least one of the in-application behavior data, search records, click behaviors and transaction history. By adopting the above technical solution, when obtaining user behavior data, in addition to obtaining the in-application behavior data, a variety of data such as search records, click behaviors and transaction history that can indicate user needs and directions of interest can also be obtained as user behavior data, and then the user behavior data is combined with the user portrait to complete the extraction of key behavior features through an independently set key feature extraction model, and the target service information is obtained through the pre-trained service prediction model. Since the key behavior features input to the service prediction model are the features extracted by combining the user behavior data with the user portrait, the accuracy of the predicted target service information is improved. By sending the target service information to the user terminal corresponding to the user behavior data, the user terminal can complete the service push configuration related to the target service with precise user needs based on the target service information, so that when it is predicted through the user behavior data that the user needs mobile banking services, the user terminal can timely and effectively identify the user needs and provide effective service push, so as to provide users with convenient and accurate services and achieve better promotion of mobile banking applications.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a service push method provided in Embodiment 1 of the present invention;

[0025] Figure 2 A flowchart of a service push method provided in Embodiment 2 of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a service push device provided in Embodiment 3 of the present invention;

[0027] Figure 4 A structural diagram of a service push device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. 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 necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flow chart of a service push method provided in the first embodiment of the present invention. The embodiment of the present invention can be applied to predicting the user's demand for mobile banking services and intelligently recommending mobile banking services. The method can be executed by a service push device, which can be implemented by software and / or hardware, and the service push device can be configured in a service push device. Optionally, the service push device can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, a mobile terminal, etc., and the embodiment of the present invention does not limit this.

[0032] like Figure 1 As shown, a service push method provided by an embodiment of the present invention specifically includes the following steps:

[0033] S101. Obtain user behavior data and a user portrait corresponding to the user behavior data, input the user behavior data and the user portrait into a pre-trained key feature extraction model, and determine key behavior features.

[0034] Among them, user behavior data includes at least one of in-application behavior data, search records, click behavior and transaction history.

[0035] In this embodiment, user behavior data can be specifically understood as data collected by the mobile terminal used by the user and related to the user's operations on the mobile terminal. User portrait can be specifically understood as information that comprehensively describes multi-dimensional information such as user characteristics, preferences and behaviors. The key feature extraction model can be specifically understood as a lightweight machine learning model that is used to extract features from the input data that are highly correlated with user needs and can be used to predict the services required by the user. Key behavior features can be specifically understood as features extracted from the user portrait of the user behavior data set, which are related to user demand characteristics and can be used to predict the services required by the user.

[0036] In this embodiment, the in-application behavior can be specifically understood as the operation behavior performed by the user in the bank-related application installed in the mobile terminal; illustratively, this part of data mainly comes from various operation records generated by the user when using the mobile banking application, such as the user's login frequency, login time, browsed pages, clicked buttons, initiated transactions, etc. It can be understood that these data can directly reflect the user's usage habits and interest preferences in the mobile banking application. illustratively, the in-application behavior can be extracted through the software development kit (SDK) of the application software embedded in the user's mobile terminal.

[0037] In this embodiment, the search record can be specifically understood as the record generated when the user uses the mobile terminal to perform a search operation. It is understandable that the user's search behavior on the mobile terminal often contains their immediate needs and focus. By collecting the user's search record, the user's real-time intention and interest points can be captured.

[0038] In this embodiment, the click behavior can be specifically understood as a click operation of the user on the content displayed in the mobile terminal used by the user. It is understandable that by analyzing the links, advertisements, applications, etc. clicked by the user, the user's interests and possible needs can be inferred.

[0039] In this embodiment, the transaction history can be specifically understood as the transaction information completed by the user within a period of time. It is understandable that the user's transaction history data is crucial to understanding the user's financial status, consumption habits, and credit status. By analyzing the user's transaction amount, transaction frequency, transaction type, etc., more personalized and accurate financial services can be provided to the user.

[0040] Exemplarily, search records, click behaviors and transaction histories may be obtained through an application programming interface (API) in a mobile terminal used by the user or a log file generated by a related application.

[0041] Specifically, when it is necessary to push banking-related services to users, multiple types of interfaces set up on the mobile terminals used by users will obtain user behavior data in real time, and determine the user profile corresponding to the user based on the user behavior data, or directly determine the user profile of the user corresponding to the mobile terminal based on the mobile terminal that obtains the user behavior data. The obtained user behavior data and user profile are used as input parameters of the pre-trained key feature extraction model, and the key feature extraction model extracts features in the user behavior data that are related to user demand characteristics and can be used to predict the services required by the user, thereby obtaining key behavior features.

[0042] In an embodiment of the present invention, by obtaining rich and multi-dimensional user behavior data including in-application behavior data, and combining it with a user portrait that can reflect multi-dimensional information such as user feature preferences as the input of a key feature extraction model, the obtained key behavior features can better reflect the user's interests and needs, providing a solid data foundation for service prediction.

[0043] S102: Input key behavior features into a pre-trained service prediction model to determine target service information.

[0044] In this embodiment, the service prediction model can be specifically understood as a neural network model that combines the behavioral features input therein with the user's historical behavior sequence, captures the long-term dependencies in the sequence, and predicts the demand points that the user may be interested in. The target service information can be specifically understood as information about services related to the demand points that the user is interested in, and can also include information about services associated with the services related to the demand points that the user is interested in. Exemplarily, the service prediction model can be a recurrent neural network (RNN) model, or it can be other neural network models suitable for processing sequence data and used to mine potential patterns and long-term dependencies in user behavior sequences, and the embodiments of the present invention are not limited to this.

[0045] Specifically, the key behavior features are used as input parameters of the pre-trained service prediction model, and the service prediction model captures the long-term dependencies of the historical behavior sequences corresponding to the input key behavior features, obtains the demand points of interest corresponding to the key behavior features, and determines the target service information based on the determined demand points of interest.

[0046] It is understandable that the target service information may only include services in the mobile banking software determined based on the demand points of interest, or may include service recommendation information associated with services related to the demand points of interest to the user, which are generated based on the user's behavior patterns and preferences mined based on the user's key behavior characteristics. The embodiments of the present invention do not limit this.

[0047] In the embodiment of the present invention, since the key behavioral features input into the service prediction model include information extracted from the user profile, the user profile can be used to assist the service prediction model in deep mining and prediction, so as to more accurately infer the mobile banking services that the user may need.

[0048] S103: Send the target service information to the user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information.

[0049] Specifically, after determining the target service information, it can be considered that the target service information is a service that the user terminal needs to use in the near future for collecting user behavior data. At this time, the target service information can be sent to the user terminal, so that after receiving the target service information, the user terminal can push the predicted service that the user needs to use to the user based on the information contained therein, so that the user can obtain the corresponding service more easily, and the service push configuration in the user terminal is completed.

[0050] The technical solution of this embodiment obtains user behavior data and a user portrait corresponding to the user behavior data, inputs the user behavior data and the user portrait into a pre-trained key feature extraction model to determine the key behavior features; inputs the key behavior features into a pre-trained service prediction model to determine the target service information; sends the target service information to the user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information; wherein the user behavior data includes at least one of in-application behavior data, search records, click behaviors, and transaction histories. By adopting the above technical solution, when obtaining user behavior data, in addition to obtaining in-application behavior data, a variety of data such as search records, click behaviors, and transaction histories that can indicate user needs and directions of interest can also be obtained as user behavior data, and then the user behavior data is combined with the user portrait to complete the extraction of key behavior features through an independently set key feature extraction model, and the target service information is obtained through processing by the pre-trained service prediction model. Since the key behavior features input into the service prediction model are features extracted by combining the user behavior data with the user portrait, the accuracy of the predicted target service information is improved. By sending the target service information to the user terminal corresponding to the user behavior data, the user terminal can complete the service push configuration related to the target service with precise user needs based on the target service information, so that when it is predicted through the user behavior data that the user needs mobile banking services, the user terminal can timely and effectively identify the user needs and provide effective service push, so as to provide users with convenient and accurate services and achieve better promotion of mobile banking applications.

[0051] Embodiment 2

[0052] Figure 2The flowchart of a service push method provided in the second embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions. When obtaining user behavior data, the user behavior data is desensitized to ensure that sensitive information has been processed before the data leaves the user device or during transmission, thereby protecting the privacy of the user. Then, the obtained user behavior data is preprocessed, including data cleaning, format conversion, and preliminary feature extraction, to simplify and convert the user behavior data, obtain preprocessed user behavior data that is more suitable for input into the key feature extraction model, combine the quantitative features of the user portrait with the preprocessed user behavior data, and extract key behavior features through a lightweight key feature extraction model as comprehensive preprocessed data, so that the user portrait can be used to assist the service prediction model for deep mining and prediction, so as to more accurately infer the mobile banking services that the user may need. After the determined target service information is sent to the user terminal, the user terminal can perform search index updates, intelligent recommendation list configuration, and application configuration according to the received target service information, so that the user terminal can display the inferred user-required services to a location that is easy for the user to obtain based on the predicted user's current needs or potential points of interest, so that the user can obtain the required services in the first place, thereby improving the visibility and convenience of service acquisition.

[0053] like Figure 2 As shown, a service push method provided by an embodiment of the present invention specifically includes the following steps:

[0054] S201. Obtain user behavior data and a user portrait corresponding to the user behavior data, and perform data desensitization processing on the user behavior data.

[0055] Among them, user behavior data includes at least one of in-application behavior data, search records, click behavior and transaction history.

[0056] In this embodiment, data desensitization can be specifically understood as a process of converting sensitive data into non-sensitive data by means of replacement, deformation and deletion. It can be understood that the data desensitization in the embodiment of the present invention is mainly aimed at user behavior data that does not require deep mining but contains sensitive information, such as the user's name, telephone number, address and other personal information. The desensitization algorithm used for data desensitization can be selected according to the type and sensitivity of various types of data in the user behavior data. Common desensitization methods include replacement method (such as replacing part of the sensitive information with asterisks or random characters), disturbance method (such as randomly rearranging the data or adding noise) and hash method, etc. The embodiment of the present invention does not limit the desensitization algorithm for data desensitization processing of user behavior data.

[0057] S202: Perform data cleaning, format conversion, and preliminary feature extraction on the user behavior data to determine the pre-processed user behavior data.

[0058] Among them, the user behavior data is encrypted through an encryption algorithm during data cleaning, format conversion and preliminary feature extraction.

[0059] In this embodiment, data cleaning can be specifically understood as a data processing method for removing duplicate, invalid and erroneous data in user behavior data to ensure data accuracy and consistency. Format conversion can be specifically understood as a data processing method for converting different formats of data in user behavior data into a unified format. Preliminary feature extraction can be specifically understood as a data processing method for identifying and extracting information related to service prediction needs from user behavior data. Its main purpose is to simplify and convert data so that the preprocessed user behavior data after preliminary feature extraction is more suitable for the input of the key feature extraction model.

[0060] Specifically, after obtaining the user behavior data, in order to convert it into the form required for the input of the key feature extraction model, the user behavior data needs to be preprocessed. The preprocessing may include data cleaning, format conversion, and preliminary feature extraction. After the above processing methods are executed in sequence, the preprocessed user behavior data suitable for the input of the key feature extraction model can be obtained. It can be understood that the above processing of user behavior data can be collectively referred to as preprocessing. In this preprocessing stage, in order to ensure that the sensitive data in the user behavior data is properly processed, the processed data can be encrypted by encryption technology during the processing process, so that even if the encrypted data is intercepted by a third party during transmission or storage, it cannot be easily decrypted to obtain the content. Exemplarily, encryption technology includes but is not limited to symmetric encryption, asymmetric encryption, and hybrid encryption, etc., and the embodiments of the present invention are not limited to this.

[0061] It is understandable that the data desensitization and data encryption involved in S201 and S202 are both protection processes for user privacy data. In the above process, the availability of data must be fully considered. Through reasonable desensitization and encryption strategies, ensure that the desensitized data can still be used for data analysis and model training purposes. At the same time, when selecting data desensitization and data encryption algorithms, different encryption and desensitization granularities must be set according to the privacy protection level requirements of different data to meet the privacy protection requirements in different scenarios.

[0062] S203: Combine the quantitative features of the user portrait with the pre-processed user behavior data to determine comprehensive pre-processed data.

[0063] Specifically, based on the basic information, behavior data and feedback data of the user contained in the user portrait, feature extraction and data conversion are performed to obtain quantitative features that can reflect the user's behavior patterns and preferences. The quantitative features are then combined with the pre-processed user behavior data, and the combined data is determined as comprehensive pre-processed data.

[0064] S204: input the comprehensive preprocessed data into a pre-trained key feature extraction model, extract features from the comprehensive preprocessed data through the key feature extraction model, and determine key behavior features.

[0065] Among them, the key feature extraction model is a decision tree model.

[0066] In this embodiment, the decision tree model can be specifically understood as a lightweight machine learning model for classification and regression tasks, which obtains a tree model by learning the characteristics of sample data and its corresponding output results to predict the output of new data input therein. It can be understood that in the model training stage, based on the powerful segmentation ability of the decision tree, the data set can be divided into multiple subsets by recursively selecting the optimal partitioning attribute, each subset corresponds to a decision path, and finally a tree model is constructed, in which each decision result corresponds to a classification; and then in the application process, when the comprehensive pre-processed data is input into the key feature extraction model of the trained decision tree model type, the result will be judged according to the decision node, and the classification result will be quickly obtained along the corresponding decision path, and finally the key behavior feature will be extracted.

[0067] S205: Input key behavior features into a pre-trained service prediction model to determine target service information.

[0068] S206: Send the target service information to the user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information.

[0069] Optionally, the service push configuration includes: updating the service corresponding to the target service information into the search index.

[0070] In this embodiment, the search index can be specifically understood as an information quick retrieval structure of the user's frequently used search functions in the user terminal.

[0071] Specifically, after the target service information is sent to the user terminal corresponding to the user behavior data, the user terminal can determine the target service that the user needs to use in the upcoming operation based on the target service information. In order to improve the visibility and ease of acquisition of the target service, the search software frequently used by the user in the user terminal can update the target service to its search index, so that the service information can be quickly captured by the search engine and displayed in the search results, so that the user can easily find the required target service when searching even if the relevant application is not opened.

[0072] Optionally, the service push configuration also includes: configuring the intelligent recommendation list determined according to the target service information to a preset function area.

[0073] In this embodiment, the intelligent recommendation list can be specifically understood as a personalized service recommendation list suitable for the user, which is comprehensively generated based on the user's behavior pattern and preference and the target service included in the current target service information. The preset function area can be specifically understood as a display area that is pre-set according to actual conditions and is used to recommend services to the user when the user searches and browses.

[0074] Specifically, after the target service information is sent to the user terminal corresponding to the user behavior data, the user terminal can determine the target service that the user needs to use in the upcoming operation based on the target service information. At the same time, the target service information may include the user's behavior patterns and preferences. Based on the above content, a personalized list of services that the user may be interested in can be generated and configured as an intelligent recommendation list in the preset function area of ​​the user terminal.

[0075] Exemplarily, the preset function area may be a recommendation prompt under the search box and a personalized recommendation area on the home page, etc., which is not limited in the embodiment of the present invention.

[0076] Optionally, the service push configuration further includes: prominently configuring the service corresponding to the target service information in the application corresponding to the target service information.

[0077] Specifically, after the target service information is sent to the user terminal corresponding to the user behavior data, the user terminal can determine the target service that the user needs to use in the upcoming operation based on the target service information, and the target service should belong to an application of the user terminal. For the convenience of user use, the target service can be prominently configured in the application corresponding to the target service information, or the start execution order of the target service can be moved to the front of the application, so that the user can obtain the required target service at the first time when opening the application.

[0078] The technical solution of this embodiment performs data desensitization on the user behavior data when the user behavior data is obtained, ensuring that sensitive information has been processed before the data leaves the user device or is in the transmission process, thereby protecting the user's privacy. Then, the obtained user behavior data is preprocessed including data cleaning, format conversion and preliminary feature extraction to simplify and convert the user behavior data, obtain preprocessed user behavior data that is more suitable for the input of the key feature extraction model, combine the quantitative features of the user portrait with the preprocessed user behavior data, and extract key behavior features through a lightweight key feature extraction model as comprehensive preprocessed data, so that the user portrait can be used for deep mining and prediction of the auxiliary service prediction model, so as to more accurately infer the mobile banking services that the user may need. After sending the determined target service information to the user terminal, the user terminal can perform search index update, intelligent recommendation list configuration and application configuration according to the received target service information, so that the user terminal can display the inferred user required services to a location that is convenient for the user to obtain according to the predicted user's current needs or potential points of interest, so that the user can obtain the required services in the first time, thereby improving the visibility and convenience of obtaining services.

[0079] Embodiment 3

[0080] Figure 3 A schematic diagram of the structure of a service push device provided in Embodiment 3 of the present invention is shown in FIG. Figure 3 As shown, the service push device includes a key feature determination module 31, a service information determination module 32 and a service push module 33.

[0081] Among them, the key feature determination module 31 is used to obtain user behavior data and a user portrait corresponding to the user behavior data, input the user behavior data and the user portrait into a pre-trained key feature extraction model, and determine the key behavior features; the service information determination module 32 is used to input the key behavior features into a pre-trained service prediction model to determine the target service information; the service push module 33 is used to send the target service information to the user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information; wherein the user behavior data includes at least one of the in-application behavior data, search records, click behavior and transaction history.

[0082] The technical solution of the embodiment of the present invention, when acquiring user behavior data, in addition to acquiring in-application behavior data, can also acquire a variety of data such as search records, click behaviors, and transaction histories that can indicate user needs and interests as user behavior data, and then combine the user behavior data with the user portrait to complete the extraction of key behavior features through an independently set key feature extraction model, and obtain the target service information through the pre-trained service prediction model. Since the key behavior features input into the service prediction model are the features extracted by combining the user behavior data with the user portrait, the accuracy of the predicted target service information is improved. By sending the target service information to the user terminal corresponding to the user behavior data, the user terminal can complete the service push configuration related to the target service with precise user needs based on the target service information, so that when it is predicted through the user behavior data that the user needs mobile banking services, the user terminal can timely and effectively identify the user needs and provide effective service push, so as to provide users with convenient and accurate services and achieve better promotion of mobile banking applications.

[0083] Optional, service push configuration, including:

[0084] Update the service corresponding to the target service information into the search index.

[0085] Optional, service push configuration also includes:

[0086] The intelligent recommendation list determined according to the target service information is configured to the preset function area.

[0087] Optional, service push configuration also includes:

[0088] The service corresponding to the target service information is prominently configured in the application corresponding to the target service information.

[0089] Optionally, when obtaining user behavior data, it also includes:

[0090] Desensitize user behavior data.

[0091] Optionally, the key feature determination module 31 is specifically used to:

[0092] Perform data cleaning, format conversion and preliminary feature extraction on user behavior data to determine pre-processed user behavior data;

[0093] Combine the quantitative features of the user portrait with the pre-processed user behavior data to determine the comprehensive pre-processed data;

[0094] Input the comprehensive preprocessed data into the pre-trained key feature extraction model, extract features from the comprehensive preprocessed data through the key feature extraction model, and determine key behavioral features;

[0095] Among them, the key feature extraction model is a decision tree model;

[0096] Among them, the user behavior data is encrypted through an encryption algorithm during data cleaning, format conversion and preliminary feature extraction.

[0097] The service push device provided in the embodiment of the present invention can execute the service push method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0098] Embodiment 4

[0099] Figure 4 A schematic diagram of the structure of a service push device provided for Embodiment 4 of the present invention. The service push device 40 may be intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The service push device 40 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0100] like Figure 4 As shown, the service push device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a programmable program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the programmable program stored in the read-only memory (ROM) 42 or the programmable program loaded from the storage unit 48 to the random access memory (RAM) 43. In RAM 43, various programs and data required for the operation of the service push device 40 can also be stored. The processor 41, ROM 42 and RAM 43 are connected to each other via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44. Optionally, the processor can be an FPGA.

[0101] A number of components in the service push device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the service push device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0102] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the service push method.

[0103] In some embodiments, the service push method may be implemented as a programmable program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the programmable program may be loaded and / or installed on the service push device 40 via the ROM 42 and / or the communication unit 49. When the programmable program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the service push method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the service push method in any other appropriate manner (e.g., by means of firmware).

[0104] Optionally, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the service push method provided by any embodiment of the present invention.

[0105] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more programmable programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] Programmable programs for implementing the method of the present invention may be written in any combination of one or more programming languages. These programmable programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the programmable program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The programmable program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0107] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a programmable program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] To provide interaction with a user, the systems and techniques described herein may be implemented on a service push device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball), through which the user can provide input to the service push device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0109] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0110] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by programmable programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0111] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0112] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A service push method, characterized in that: include: Obtaining user behavior data and a user portrait corresponding to the user behavior data, inputting the user behavior data and the user portrait into a pre-trained key feature extraction model to determine key behavior features; Inputting the key behavior features into a pre-trained service prediction model to determine target service information; Sending the target service information to a user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information; The user behavior data includes at least one of in-application behavior data, search records, click behaviors, and transaction history.

2. The service push method according to claim 1, characterized in that: The service push configuration includes: The service corresponding to the target service information is updated into the search index.

3. The service push method according to claim 2, characterized in that: The service push configuration also includes: The intelligent recommendation list determined according to the target service information is configured to a preset function area.

4. The service push method according to claim 2, characterized in that: The service push configuration also includes: The service corresponding to the target service information is prominently configured in the application corresponding to the target service information.

5. The service push method according to claim 1, characterized in that: When obtaining user behavior data, it also includes: The user behavior data is desensitized.

6. The service push method according to claim 5, characterized in that: The user behavior data and the user profile are input into a pre-trained key feature extraction model to determine key behavior features, including: Performing data cleaning, format conversion, and preliminary feature extraction on the user behavior data to determine pre-processed user behavior data; Combining the quantitative features of the user portrait with the pre-processed user behavior data to determine comprehensive pre-processed data; Inputting the comprehensive preprocessed data into a pre-trained key feature extraction model, performing feature extraction on the comprehensive preprocessed data through the key feature extraction model, and determining key behavior features; Wherein, the key feature extraction model is a decision tree model; Wherein, when performing data cleaning, format conversion and preliminary feature extraction on the user behavior data, the user behavior data is encrypted by using an encryption algorithm.

7. A service push device, characterized in that: include: A key feature determination module, used to obtain user behavior data and a user portrait corresponding to the user behavior data, input the user behavior data and the user portrait into a pre-trained key feature extraction model, and determine the key behavior features; A service information determination module, used to input the key behavior features into a pre-trained service prediction model to determine target service information; A service push module, used to send the target service information to a user terminal corresponding to the user behavior data, so that the user terminal performs service push configuration according to the target service information; The user behavior data includes at least one of in-application behavior data, search records, click behaviors, and transaction history.

8. A service push device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a programmable program that can be executed by the at least one processor, and the programmable program is executed by the at least one processor so that the at least one processor can execute the service push method described in any one of claims 1-6.

9. A storage medium containing computer executable instructions, characterized in that: The executable instructions, when executed by a programmable processor, are used to execute the service push method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the service push method according to any one of claims 1 to 6 is implemented.

Images