Business recommendation information generation method and device, equipment, storage medium and product

Abstract

The embodiment of the invention provides a service recommendation information generation method and device, equipment, a storage medium and a product. The method comprises the following steps: acquiring user attribute information, user position information and historical behavior information of a target user; performing feature extraction on text information in the user attribute information to obtain a static feature vector corresponding to the target user, and performing feature extraction on interaction information of the historical behavior information to obtain a dynamic feature vector corresponding to the target user; performing multi-dimensional feature fusion on the static feature vector and the dynamic feature vector to obtain a fusion feature vector corresponding to the target user, calling a machine learning model according to the fusion feature vector, and determining business demand information corresponding to the target user; and generating service recommendation information of the target user according to the service demand information and the user position information of the target user. According to the method, the user demand can be predicted in real time, personalized recommendation of the service recommendation information is realized, and thus the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a method, apparatus, device, storage medium, and product for generating business recommendation information. Background Technology

[0002] During the interaction between users and financial institutions through online channels (such as mobile banking, online banking, customer service systems, etc.), the online channel system can provide users with business recommendation information to quickly meet their business needs and thus improve user experience.

[0003] In related technologies, online channel systems can trigger business recommendation information based on preset business rules. For example, when a customer accesses a "loan" related page through mobile banking, the mobile banking system can push a "loan calculator" tool to the user to meet their loan needs.

[0004] However, since the business recommendation information triggered by preset business rules is relatively fixed, it cannot meet the personalized needs of different users, resulting in low accuracy of the business recommendation information. Summary of the Invention

[0005] This application provides a method, apparatus, device, storage medium, and product for generating business recommendation information, which can predict user needs in real time and achieve personalized and accurate recommendations, thereby improving user experience.

[0006] In a first aspect, embodiments of this application provide a method for generating business recommendation information, including:

[0007] Obtain target user attribute information, user location information, and historical behavior information, including user interaction information on online channels;

[0008] Feature extraction is performed on the text information in the user attribute information to obtain the corresponding static feature vector of the target user, and feature extraction is performed on the interaction information of the historical behavior information to obtain the corresponding dynamic feature vector of the target user. The interaction information includes one or more of the following: access path information, access frequency information, search text information, and consultation text information.

[0009] Static and dynamic feature vectors are fused in multiple dimensions to obtain a fused feature vector corresponding to the target user. Based on the fused feature vector, a machine learning model is invoked to determine the business requirement information corresponding to the target user. The machine learning model is used as input to the fused feature vector and outputs the business requirement information.

[0010] Based on the target user's business needs and location information, generate business recommendation information for the target user.

[0011] In one possible implementation, static and dynamic feature vectors are fused using multi-dimensional feature fusion to obtain a fused feature vector corresponding to the target user, including:

[0012] Determine the first weight parameter corresponding to the static feature vector and the second weight parameter corresponding to the dynamic feature vector; obtain the fused feature vector corresponding to the target user based on the product of the static feature vector and the first weight parameter, and the product of the dynamic feature vector and the second weight parameter.

[0013] In one possible implementation, a machine learning model is invoked based on the fused feature vector to determine the business needs information corresponding to the target user, including:

[0014] The machine learning model is invoked based on the fused feature vector to determine the user classification information and the target business category of the target user's needs; based on the user classification information and the target business category, the business requirement information corresponding to the target user is generated.

[0015] In one possible implementation, business requirement information corresponding to the target user is generated based on user classification information and target business category, including: determining multiple candidate business requirement information corresponding to the target business category from the correspondence between business category and business requirement information based on the target business category; and selecting business requirement information that matches the user classification information from the multiple candidate business requirement information based on user classification information, and determining it as the business requirement information corresponding to the target user.

[0016] In one possible implementation, user classification information includes one or more of account level information, credit rating information, and user preference information.

[0017] In one possible implementation, business recommendation information for the target user is generated based on the target user's business needs information and user location information, including:

[0018] Based on the user's location information, obtain multiple candidate service recommendations for the area where the user's location information is located; filter out the service recommendations that meet the service requirements from the multiple candidate service recommendations. The service recommendations include one or more of the following: service introduction information, service processing channel information, and service guidance information.

[0019] Secondly, embodiments of this application provide a device for generating business recommendation information, comprising:

[0020] The acquisition module is used to acquire the target user's user attribute information, user location information, and historical behavior information. The historical behavior information includes the user's interaction information on online channels.

[0021] The feature extraction module is used to extract features from the text information in the user attribute information to obtain the corresponding static feature vector of the target user, and to extract features from the interaction information of the historical behavior information to obtain the corresponding dynamic feature vector of the target user. The interaction information includes one or more of the following: access path information, access frequency information, search text information and consultation text information.

[0022] The determination module is used to perform multi-dimensional feature fusion of static and dynamic feature vectors to obtain the fused feature vector corresponding to the target user, and to call the machine learning model based on the fused feature vector to determine the business requirement information corresponding to the target user.

[0023] The generation module is used to generate business recommendation information for the target user based on the target user's business needs and user location information.

[0024] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0025] The memory stores instructions that the computer executes;

[0026] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0027] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0028] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0029] The present application provides a method, apparatus, device, storage medium, and product for generating business recommendation information. The method includes: acquiring user attribute information, user location information, and historical behavior information of a target user, whereby the historical behavior information includes user interaction information on online channels; extracting features from the text information in the user attribute information to obtain a static feature vector corresponding to the target user, and extracting features from the interaction information in the historical behavior information to obtain a dynamic feature vector corresponding to the target user, wherein the interaction information includes one or more of access path information, access frequency information, search text information, and consultation text information; fusing the static and dynamic feature vectors in a multi-dimensional manner to obtain a fused feature vector corresponding to the target user; calling a machine learning model based on the fused feature vector to determine the business demand information corresponding to the target user, whereby the machine learning model is used as input to the fused feature vector and outputs the business demand information; and generating business recommendation information for the target user based on the target user's business demand information and user location information. In this embodiment, a dynamically updated feature vector and a static feature vector are first constructed using customer behavior data and static attribute data. Then, the dynamically updated feature vector and the static feature vector are fused. Through multi-dimensional dynamic feature fusion technology, customer behavior data and static attribute data are fused. The fused feature vector is used to generate business demand information for the target user using a deep learning model. Finally, personalized service recommendation content is generated based on the business demand information and user location information. This method achieves real-time prediction and accurate recommendation of customer needs, enabling business recommendation information to meet the personalized business needs of different users, thereby improving the user experience. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0031] Figure 1 A schematic diagram illustrating a method for generating business recommendation information provided in this application;

[0032] Figure 2 A flowchart illustrating the method for generating business recommendation information provided in this application embodiment;

[0033] Figure 3 A schematic diagram of the structure of the device for generating business recommendation information provided in the embodiments of this application;

[0034] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0035] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0036] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0037] During the interaction between users and financial institutions through online channels (such as mobile banking, online banking, customer service systems, etc.), the online channel system can provide users with business recommendation information to quickly meet their business needs and thus improve user experience.

[0038] In related technologies, online channel systems can trigger business recommendation information based on preset business rules. For example, when a customer accesses a "loan" related page through mobile banking, the mobile banking system can push a "loan calculator" tool to the user to meet their loan needs.

[0039] However, since the business recommendation information triggered by preset business rules is relatively fixed, it cannot meet the personalized needs of different users, resulting in low accuracy of the business recommendation information.

[0040] To address the aforementioned technical issues, this application proposes the following concept: Based on a machine learning model that integrates multi-dimensional dynamic features, by analyzing customer behavior patterns and preferences, it can capture real-time dynamic changes in customer behavior, accurately predict users' business needs, and achieve personalized services through intelligent recommendations.

[0041] The specific steps may include: acquiring the target user's user attribute information, user location information, and historical behavior information, including the user's interaction information on online channels; fusing the user attribute information and historical behavior information into multi-dimensional features to obtain a fused feature vector corresponding to the target user; calling a machine learning model based on the fused feature vector to determine the business demand information corresponding to the target user, where the machine learning model is used as input to the fused feature vector and outputs the business demand information; and generating business recommendation information for the target user based on the target user's business demand information and user location information.

[0042] In the above technical solution, by acquiring customer behavior data and static attribute data, and using multi-dimensional dynamic feature fusion technology, the customer behavior data and static attribute data are combined to generate a unified feature vector representing the customer's intent. The feature vector is then processed using a machine learning model to output customer business demand information, and personalized service recommendations are generated based on the business demand information and user location information. The entire process, through the combination of dynamic feature fusion and machine learning models, achieves real-time prediction of customer needs and accurate personalized recommendations, thus improving the user experience.

[0043] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0044] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0045] Figure 1 A schematic diagram illustrating a scenario for the method of generating business recommendation information provided in this application. For example... Figure 1 In this scenario, the components include: server 101 and terminal 102.

[0046] In the specific implementation process, server 101 and terminal 102 can be implemented using a cluster of one or more servers with more powerful processing capabilities and higher security. Where possible, computers or laptops with strong computing power can also be used as alternatives.

[0047] The connection between server 101 and terminal 102 can be either wired or wireless. For example, users can log in to online banking applications or mini-programs through terminal 102 to view, process, or inquire about related services. Server 101 corresponding to the online banking application or mini-program can generate service recommendation information for users using the service recommendation information generation method provided in this application, and return the service recommendation information to terminal 102 for display.

[0048] It is understood that the scenarios illustrated in the embodiments of this application do not constitute a specific limitation on the method for generating business recommendation information. In other feasible embodiments of this application, the above scenarios may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and are not limited here. Figure 1 The scenario shown can be implemented by hardware, software, or a combination of both.

[0049] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0050] Figure 2 This is a flowchart illustrating the method for generating business recommendation information provided in this application embodiment. The execution entity of this application embodiment may be... Figure 1 The server 101 in this embodiment can also be a computer and / or a mobile phone, etc., and this embodiment does not impose any special restrictions on it. Figure 2 As shown, the method includes:

[0051] S201. Obtain the target user's user attribute information, user location information, and historical behavior information. The historical behavior information includes the user's interaction information on online channels.

[0052] In this embodiment of the disclosure, user attribute information includes basic user information, such as age and occupation. User location information may include the user's city information and / or the user's coordinate location information.

[0053] Optionally, user interaction information on online channels may include one or more of the following: access path information, access frequency information, search text information, and inquiry text information. The online channel can be any online platform, such as a shopping platform, an online banking application, or an online banking mini-program.

[0054] The access path information can include any information related to page access, such as the user's page navigation sequence in the system, the time spent on each page, and the number of navigations. The search text information can include information such as the user's entered search keywords, the number of searches, and click behavior on search results. The consultation text information can include information such as the content of the consultation sent by the user through customer service or message board, the consultation duration, and the consultation topic.

[0055] S202. Extract features from the text information in the user attribute information to obtain the static feature vector corresponding to the target user, and extract features from the interaction information of the historical behavior information to obtain the dynamic feature vector corresponding to the target user. The interaction information includes one or more of the following: access path information, access frequency information, search text information, and consultation text information.

[0056] In this embodiment of the disclosure, the text information in the user attribute information includes text information describing user attributes such as user age, occupation, gender, education level, and region. The user attribute information is static data corresponding to the user; the interaction information is dynamic data corresponding to the user.

[0057] Optionally, the interaction information includes one or more of the following: user access path information, access frequency information, search text information, and consultation text information within a preset time period. In this embodiment, the value of the preset time period is not specifically limited; it can be one week or one month, etc.

[0058] In some embodiments, a preset language model can be used to extract features from the textual information in user attribute information to obtain the corresponding static feature vector of the target user. Similarly, a preset language model can be used to extract features from the interaction information of historical behavior information to obtain the corresponding dynamic feature vector of the target user. The preset language model is not specifically limited in this embodiment. Optionally, the preset semantic model can be a large language model, an LSTM (Long Short-Term Memory) model, or a BERT (Bidirectional Encoder Representations from Transformers) model, etc.

[0059] S203. Perform multi-dimensional feature fusion on the static feature vector and dynamic feature vector to obtain the fused feature vector corresponding to the target user. Call the machine learning model based on the fused feature vector to determine the business requirement information corresponding to the target user. The machine learning model is used to input the fused feature vector and output the business requirement information.

[0060] In some embodiments, multi-dimensional feature fusion of static feature vectors and dynamic feature vectors is performed to obtain a fused feature vector corresponding to the target user, including: concatenating static feature vectors and dynamic feature vectors to obtain a fused feature vector corresponding to the target user.

[0061] In other embodiments, the static feature vector and the dynamic feature vector are fused in multiple dimensions to obtain the fused feature vector corresponding to the target user, including: determining the first weight parameter corresponding to the static feature vector and the second weight parameter corresponding to the dynamic feature vector; and obtaining the fused feature vector corresponding to the target user based on the product of the static feature vector and the first weight parameter and the product of the dynamic feature vector and the second weight parameter.

[0062] Optionally, the first weighting parameter and the second weighting parameter are preset parameters. In undisclosed embodiments, the values ​​of the first weighting parameter and the second weighting parameter are not specifically limited. For example, the first weighting parameter is preset to 0.7 and the second weighting parameter to 0.3.

[0063] In this embodiment of the disclosure, the machine learning model can be a neural network model, an artificial intelligence model, etc. This machine learning model is used to take a fused feature vector as input and output business requirement information.

[0064] In one possible implementation, a machine learning model is invoked based on the fused feature vector to determine the business requirement information corresponding to the target user. This includes: invoking the machine learning model based on the fused feature vector to determine the user classification information and the target business category of the target user's needs; and generating the business requirement information corresponding to the target user based on the user classification information and the target business category.

[0065] Optionally, the correspondence between business categories and business requirement information can be pre-stored. Accordingly, based on user classification information and target business category, business requirement information corresponding to the target user is generated, including: determining multiple candidate business requirement information corresponding to the target business category from the correspondence between business categories and business requirement information; and filtering out the business requirement information that matches the user classification information from the multiple candidate business requirement information based on user classification information, and determining it as the business requirement information corresponding to the target user.

[0066] Optionally, user classification information may include one or more of account level information, credit rating information, and user preference information.

[0067] For example, based on the fused feature vector, a machine learning model is invoked to predict the target business category of the user's demand as "needing to conduct deposit-related business." The business demand information corresponding to the target business category includes "conservative deposit business" and "income-generating deposit business." The user classification information corresponding to the target user is "customer with low risk appetite." In this case, the generated business demand information matching the business demand information is "conservative deposit business."

[0068] S204. Generate business recommendation information for the target user based on the target user's business needs information and user location information.

[0069] In this embodiment of the disclosure, business recommendation information for the target user is generated based on the target user's business needs information and user location information, including: obtaining multiple candidate business recommendation information for the area where the user's location information is located based on the user's location information; and filtering out business recommendation information that meets the business needs information from the multiple candidate business recommendation information.

[0070] Optionally, different services can be offered to users in different cities. In this case, based on the user's location information, recommendation information for multiple candidate services in the city where the user's location is located can be obtained, and then service recommendations that can meet the user's personalized needs can be selected from the recommendations of multiple candidate services.

[0071] For example, the recommended information for multiple candidate services in city A where the user is located includes: recommended information for candidate service 1, recommended information for candidate service 2, and recommended information for candidate service 3. In this case, based on the service requirement information "conservative deposit service," the recommended information for candidate service 1, which meets the user's personalized needs, is selected.

[0072] In this embodiment of the disclosure, the business recommendation information includes one or more of the following: business introduction information, business processing channel information, and business guidance information.

[0073] In one possible implementation, the recommended information could be business-related advertising slogans. In this case, advertising slogan reminders can be triggered based on the reminder range set by the business. For example, if the business sets a specific region or a specific group of people, and if the user's location or group is identified as being within that range, the advertising slogan will be automatically displayed on the user's login page. Linking advertising slogan reminders to the user's geographical location or group characteristics improves the relevance of the information, making the advertising content more aligned with the user's actual needs and interests.

[0074] In one possible implementation, the business recommendation information could be a prompt indicating how to handle a business transaction. In this case, user needs can be predicted based on user electronic channel behavior data. Real-time data analysis allows for rapid response to changes in user behavior, supporting the construction of personalized predictive models for different user groups to improve the relevance, accuracy, and timeliness of predictions.

[0075] For example, the server analyzes user behavior data across various channels, including websites, social media, and customer service records, searching historical and past consultation records to predict potential user needs. Combining this with domain expert knowledge, the server adjusts the algorithm to better understand the needs of users in specific industries and provides targeted prompts when users access the service. For instance, if the server determines that a user has consulted about "Business A" elsewhere, it will generate a service processing prompt: "Dear user, if you encounter a problem with 'Business A,' please handle it through the XX channel of mobile banking."

[0076] In another possible implementation, the business recommendation information can be business guidance information. For example, if a user's question is vague, relevant business guidance information can be recommended: "I didn't understand what you meant. Are you looking to consult business A?"

[0077] This application provides a method for generating business recommendation information: acquiring user attribute information, user location information, and historical behavior information of a target user, whereby the historical behavior information includes user interaction information on online channels; extracting features from the text information in the user attribute information to obtain a static feature vector corresponding to the target user, and extracting features from the interaction information in the historical behavior information to obtain a dynamic feature vector corresponding to the target user, wherein the interaction information includes one or more of access path information, access frequency information, search text information, and consultation text information; fusing the static and dynamic feature vectors in a multi-dimensional manner to obtain a fused feature vector corresponding to the target user; calling a machine learning model based on the fused feature vector to determine the business demand information corresponding to the target user, whereby the machine learning model is used as input to the fused feature vector and outputs the business demand information; and generating business recommendation information for the target user based on the target user's business demand information and user location information. In this embodiment, by first constructing dynamically updated feature vectors and static feature vectors using customer behavior data and static attribute data, and then fusing the dynamically updated and static feature vectors using multi-dimensional dynamic feature fusion technology, customer behavior data and static attribute data are integrated. The fused feature vectors are then used to generate business demand information for the target user using a deep learning model. Finally, personalized service recommendations are generated based on the business demand information and user location information. This method achieves real-time prediction and accurate recommendation of customer needs, enabling business recommendation information to meet the personalized business needs of different users, thus improving the user experience.

[0078] Figure 3 This is a schematic diagram of the structure of the device for generating business recommendation information provided in an embodiment of this application. Figure 3 As shown, the device for generating the service recommendation information includes:

[0079] The acquisition module 301 is used to acquire the target user's user attribute information, user location information, and historical behavior information. The historical behavior information includes the user's interaction information on online channels.

[0080] The feature extraction module 302 is used to extract features from the text information in the user attribute information to obtain the corresponding static feature vector of the target user, and to extract features from the interaction information of the historical behavior information to obtain the corresponding dynamic feature vector of the target user. The interaction information includes one or more of the following: access path information, access frequency information, search text information and consultation text information.

[0081] The determination module 303 is used to perform multi-dimensional feature fusion of static feature vectors and dynamic feature vectors to obtain the fused feature vector corresponding to the target user, and to call the machine learning model based on the fused feature vector to determine the business requirement information corresponding to the target user.

[0082] The generation module 304 is used to generate business recommendation information for the target user based on the target user's business needs information and user location information.

[0083] In one possible implementation, the feature fusion module 302 performs multi-dimensional feature fusion of static feature vectors and dynamic feature vectors to obtain a fused feature vector corresponding to the target user, including: determining a first weight parameter corresponding to the static feature vector and a second weight parameter corresponding to the dynamic feature vector; and obtaining the fused feature vector corresponding to the target user based on the product of the static feature vector and the first weight parameter, and the product of the dynamic feature vector and the second weight parameter.

[0084] In one possible implementation, the determining module 303 calls a machine learning model based on the fused feature vector to determine the business requirement information corresponding to the target user, including: calling the machine learning model based on the fused feature vector to determine the user classification information and the target business category of the target user's needs; and generating the business requirement information corresponding to the target user based on the user classification information and the target business category.

[0085] In one possible implementation, the determining module 303 generates business requirement information corresponding to the target user based on user classification information and target business category, including: determining multiple candidate business requirement information corresponding to the target business category from the correspondence between business category and business requirement information based on the target business category; and filtering out business requirement information that matches the user classification information from the multiple candidate business requirement information based on user classification information, and determining it as the business requirement information corresponding to the target user.

[0086] In one possible implementation, user classification information includes one or more of account level information, credit rating information, and user preference information.

[0087] In one possible implementation, the generation module 304 generates business recommendation information for the target user based on the target user's business needs information and user location information, including: obtaining multiple candidate business recommendation information for the area where the user's location information is located based on the user's location information; and filtering out business recommendation information that meets the business needs information from the multiple candidate business recommendation information, wherein the business recommendation information includes one or more of business introduction information, business processing channel information, and business guidance information.

[0088] The business recommendation information generation apparatus provided in this application first constructs dynamically updated feature vectors and static feature vectors using customer behavior data and static attribute data; then, it fuses the dynamically updated feature vectors and static feature vectors using multi-dimensional dynamic feature fusion technology to fuse customer behavior data and static attribute data; finally, it generates business demand information for target users using a deep learning model based on the fused feature vectors; and finally, it generates personalized service recommendation content based on the business demand information and user location information. This method achieves real-time prediction and accurate recommendation of customer needs, enabling business recommendation information to meet the personalized business needs of different users, thus improving user experience.

[0089] The business recommendation information generation device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0090] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the electronic device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus.

[0091] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0092] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0093] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0094] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0095] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0096] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0097] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0098] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0099] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0100] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0103] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0104] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0105] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for generating business recommendation information, characterized in that, include: Obtain user attribute information, user location information, and historical behavior information of the target user, wherein the historical behavior information includes the user's interaction information on online channels; Feature extraction is performed on the text information in the user attribute information to obtain the static feature vector corresponding to the target user, and feature extraction is performed on the interaction information of the historical behavior information to obtain the dynamic feature vector corresponding to the target user, wherein the interaction information includes one or more of access path information, access frequency information, search text information and consultation text information; The static feature vector and the dynamic feature vector are fused in multiple dimensions to obtain the fused feature vector corresponding to the target user. The machine learning model is called based on the fused feature vector to determine the business requirement information corresponding to the target user. The machine learning model is used to input the fused feature vector and output the business requirement information. Based on the target user's business needs information and the user's location information, business recommendation information for the target user is generated.

2. The method according to claim 1, characterized in that, The step of fusing the static feature vector and the dynamic feature vector in multiple dimensions to obtain the fused feature vector corresponding to the target user includes: Determine the first weight parameter corresponding to the static feature vector and the second weight parameter corresponding to the dynamic feature vector; The fused feature vector corresponding to the target user is obtained by multiplying the static feature vector by the first weight parameter and the dynamic feature vector by the second weight parameter.

3. The method according to claim 1, characterized in that, The step of calling a machine learning model based on the fused feature vector to determine the business needs information corresponding to the target user includes: Based on the fused feature vector, a machine learning model is invoked to determine the user classification information corresponding to the target user and the target business category of the target user's needs; Based on the user classification information and the target business category, generate business requirement information corresponding to the target user.

4. The method according to claim 3, characterized in that, Based on the user classification information and the target business category, generate business requirement information corresponding to the target user, including: Based on the target business category, multiple candidate business requirement information corresponding to the target business category are determined from the correspondence between business categories and business requirement information; Based on the user classification information, business requirement information that matches the user classification information is selected from the multiple candidate business requirement information and determined as the business requirement information corresponding to the target user.

5. The method according to claim 3 or 4, characterized in that, The user classification information includes one or more of the following: account level information, credit level information, and user preference information.

6. The method according to claim 1, characterized in that, The step of generating business recommendation information for the target user based on the target user's business needs information and the user's location information includes: Based on the user's location information, obtain multiple candidate service recommendation information for the area where the user's location information is located; From the plurality of candidate service recommendation information, service recommendation information that meets the service requirements is selected. The service recommendation information includes one or more of the following: service introduction information, service processing channel information, and service guidance information.

7. A device for generating business recommendation information, characterized in that, include: The acquisition module is used to acquire user attribute information, user location information, and historical behavior information of the target user, wherein the historical behavior information includes the user's interaction information on online channels; The feature extraction module is used to extract features from the text information in the user attribute information to obtain the corresponding static feature vector of the target user, and to extract features from the interaction information of the historical behavior information to obtain the corresponding dynamic feature vector of the target user. The interaction information includes one or more of the following: access path information, access frequency information, search text information, and consultation text information. The determination module is used to perform multi-dimensional feature fusion of the static feature vector and the dynamic feature vector to obtain the fused feature vector corresponding to the target user, and to call a machine learning model based on the fused feature vector to determine the business requirement information corresponding to the target user. The generation module is used to generate business recommendation information for the target user based on the target user's business needs information and the user's location information.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 6.

Images