Information pushing method and device, electronic equipment and storage medium
The pre-trained push model extracts the interactive characteristics of the target user and the target product, and performs weighted fusion to determine the demand score, which solves the problem that the existing information push strategy cannot meet the large-scale customer group, and achieves accurate matching, reduces marketing costs and increases transaction volume.
Patent Information
- Application Number
- CN202411802534.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-09
- Publication Date
- 2025-05-13
AI Technical Summary
The existing market information push strategy cannot flexibly fit the large-scale customer base, resulting in high marketing costs but low product transaction volume.
By inputting the target user information and target product information into the pre-trained push model, relevant interactive features are extracted, and weighted and fused these features based on preset assignment rules to determine the score of the target product to represent the target user's demand for the target product, and push product information to the target user based on the score.
It has achieved accurate matching between large-scale target customers and target products, reduced marketing costs, and increased product transaction volume.
Smart Images
Figure CN119996503A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to an information push method, device, electronic device and storage medium. Background Art
[0002] Information push is an information dissemination technology that delivers specific information to the target audience through specific channels and methods. In the marketing field, information push technology is used to increase product sales, but the information push strategy currently adopted by the market mainly relies on the company's own experience and simple data statistics, which cannot flexibly fit large-scale customer groups, resulting in high marketing costs but low product sales. Summary of the invention
[0003] The present disclosure provides a method, apparatus, device and storage medium for information push.
[0004] According to a first aspect of the present disclosure, there is provided an information push method, comprising:
[0005] Input the target user information and target product information into the pre-trained push model;
[0006] Extracting multiple interaction features related to the target product information from the target user information through the push model;
[0007] The interactive features are weighted and integrated based on a preset assignment rule to determine the score of the target product; wherein the score is used to represent the target user's demand for the target product;
[0008] The corresponding target product information is pushed to the target user according to the score.
[0009] According to a second aspect of the present disclosure, there is provided an information push device, comprising:
[0010] An acquisition module, used to input target user information and target product information into a pre-trained push model;
[0011] A feature extraction module, used to extract a plurality of interaction features related to the target product information from the target user information through the push model;
[0012] A calculation module, used for weighted fusion of the interaction features based on a preset assignment rule to determine the score of the target product; wherein the score is used to represent the target user's demand for the target product;
[0013] A push module is used to push the corresponding target product information to the target user according to the score.
[0014] According to the third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information push method described in the first aspect of the present disclosure.
[0015] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the information push method according to the first aspect of the present disclosure.
[0016] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the information push method according to the first aspect of the present disclosure.
[0017] According to the technology provided by the present disclosure, the problem that the information push strategy in the current market cannot flexibly fit the large-scale customer groups, resulting in high marketing costs but low product transaction volume is solved; accurate matching of large-scale target customers and target products is achieved, thereby reducing marketing costs and increasing product transaction volume.
[0018] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0020] Figure 1 It is a flowchart of the information push method provided by the embodiment of the present disclosure;
[0021] Figure 2 The embodiment of the present disclosure provides a weight allocation schematic diagram;
[0022] Figure 3 is a structural block diagram of an information push device provided by an embodiment of the present disclosure;
[0023] Figure 4 It is a block diagram of an electronic device used to implement the information push method of the embodiment of the present disclosure. DETAILED DESCRIPTION
[0024] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0025] The following describes the information push method, device, electronic device and storage medium provided by the present disclosure with reference to the accompanying drawings.
[0026] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0027] According to an embodiment of the present disclosure, the present disclosure provides a method for information push, as shown in the attached Figure 1 As shown, the following steps are included:
[0028] Step 101: input target user information and target product information into a pre-trained push model.
[0029] As an optional implementation, the method further includes:
[0030] The big data of the target user is labeled through a user profiling tool to obtain the target user information.
[0031] For example, firstly, we can obtain big data related to the target user from a public big data platform. The big data here includes user attribute data, such as user personal information, family information, account information, etc., as well as user offline preference data, such as user authorized transaction information, 365 transaction information, and 9-minute transaction information.
[0032] The big data of the above target users is labeled through user profiling tools to generate target user information related to consumption.
[0033] As an optional implementation, the target user information includes but is not limited to: user preference tags, user behavior tags, user attribute tags, and user transaction tags.
[0034] User preference tags can help us understand user needs more accurately, provide personalized recommendations and services, improve user satisfaction and marketing effectiveness, and thus optimize product design and product push strategies.
[0035] User behavior tags include click behavior and browsing behavior on the target product page.
[0036] Target product information includes target product category labels, target product parameter labels, etc., which can be obtained through manual classification and multi-level label classification. For example, products can be divided into three levels: large, medium and small, fruit-tropical fruit-mango, and can also be obtained through machine learning.
[0037] Step 102: extract multiple interaction features related to the target product information from the target user information through the push model.
[0038] As an optional implementation manner, extracting multiple interaction features related to the target product information from the target user information through the push model includes:
[0039] Firstly, based on the push model, the target user information and the target product information are respectively mapped into vector elements.
[0040] Then, the vector elements corresponding to the target product information in the target user information are combined to obtain a plurality of the interaction features.
[0041] As an optional implementation, the interaction feature includes but is not limited to at least one of the following:
[0042] The type, quantity, depth, and frequency of the target user’s interactions with the target product during the target time period.
[0043] Type: refers to the different forms or ways in which target users interact with target products, such as clicks, slides, voice input, etc. By analyzing different types of interactive behaviors, we can learn about different user intentions and operating habits.
[0044] Quantity: It refers to the number of interactions between the target user and the target product within a certain period of time. By analyzing this parameter, we can obtain the target user's activity and the frequency of use of the system.
[0045] Depth: refers to the complexity and amount of information in the interaction between the target user and the target product. For example, a simple click may have a shallow depth, while an operation involving multiple steps and inputs may have a deep depth. By analyzing this parameter, we can learn the degree of interest of the target user in the target product.
[0046] Frequency: It refers to the frequency of a certain type of interaction between the target user and the target product. By analyzing this parameter, we can understand the user's preferences and habits.
[0047] During the target time period, the type, quantity, depth, and frequency of interaction between users and products are most representative for analyzing users' demand for products.
[0048] In actual applications, one or more parameters of the type, quantity, depth, and frequency of the above interactive behaviors can be used, but using the above four parameters at the same time is most conducive to analyzing the target user's demand for the target product, thereby more accurately matching the target user with the target product.
[0049] Step 103, weighted fusion of the interaction features is performed based on a preset assignment rule to determine a score of the target product; wherein the score is used to represent the target user's demand for the target product.
[0050] As an optional implementation, the assignment rule includes:
[0051] An adaptive weight of each of the interactive behaviors is determined according to the type, quantity, depth and frequency of the interactive behaviors within a target time period.
[0052] The depth of the interactive behavior is determined by the number of commodities involved in a preset time period, and the frequency of the interactive behavior is determined by the number of commodities involved.
[0053] For example, according to the importance of interaction behavior in contributing to the transaction success rate, the weight assignment rules are set. Figure 2 In this embodiment, the weight of click behavior is set to 30%, the weight of browsing behavior is set to 60%, the weight of user behavior data is 30%, the weight of user transaction order data is 60%, and the big data label score is 10%. The depth weight is 20%, and the frequency weight is 40%.
[0054] As an optional implementation, the assignment rule includes:
[0055] A time decay coefficient of the interactive behavior is determined according to the occurrence time of the interactive behavior.
[0056] The time decay coefficient indicates how the probability of an interactive behavior decays over time. When calculating the impact of interactive behaviors on label scores, behaviors that occurred earlier should have less impact on the corresponding label scores, while behaviors that occurred closer to the current time should have a greater impact on the corresponding label scores. For example, if a customer browsed a sports shoe interface a year ago and browsed it again within a day, it means that the user is more likely to buy the product in the near future, but if he has not browsed it again within a month, it means that the user is unlikely to buy the product in the near future. Using the time decay coefficient is helpful to analyze the possibility of users purchasing target products in the near future, so as to optimize product push information.
[0057] Each of the above assignment configuration items is stored in the database table and can be adjusted according to actual needs.
[0058] After determining the weight and time decay coefficient of the interaction behavior, a specific example of weighted fusion of the interaction features based on a preset assignment rule is as follows:
[0059] First calculate the user behavior calculation: (((fv*40%+λv*20%)+Sv-his*G)*30%+((fc*40%+λc*20%)+Sc-his*G)*60%)*30%
[0060] Among them, G is the time decay coefficient, which is set to 0.92 here;
[0061] fv is the number of browsing events on that day, λv is the number of products involved in the browsing events on that day, and Sv-his is the browsing history score.
[0062] fc is the number of click events on the day, λc is the number of products involved in the click events on the day, and Sc-his is the click history score.
[0063] The maximum number of user actions per day is 10.
[0064] Next, perform user transaction calculation: (fo*40%+λo*20%)+So-his*G)*60%
[0065] G is the time decay coefficient 0.92;
[0066] fo is the number of orders on that day, λo is the number of commodities involved in the orders on that day, and So-his is the order history score;
[0067] Then, calculate the big data preference data: score*100*10%
[0068] Finally, calculate the score of the target product: ((((fv*40%+λv*20%)+Sv-his*G)*30%+((fc*40%+λc*20%)+Sc-his*G)*60%)*30%+(fo*40%+λo*20%)+So-his*G)*60%+big data score*100*10%
[0069] In order to facilitate sorting of scores, the calculated scores are saved to 10 decimal places.
[0070] As an optional implementation, this embodiment dynamically updates the scores to improve the accuracy of matching the target user with the target product.
[0071] For user behavior scores:
[0072] The number of times on that day, the corresponding score on that day, and the number of goods involved on that day are updated in real time.
[0073] For historical scores, the daily score is added to the historical score, multiplied by the decay coefficient, and the new historical score is used for batch update.
[0074] For user transaction points:
[0075] The number of times, points, and number of products involved on the day are updated in real time.
[0076] For historical scores, every day the score for the current day is added to the historical score, and the two are multiplied by the attenuation coefficient to obtain the new historical score, and then the batch calculation and update are performed.
[0077] As an optional implementation manner, before pushing the corresponding target product information to the target user according to the score, the method further includes:
[0078] It is determined whether the geographical location information of the target customer and the geographical location information of the pre-pushed current target product simultaneously meet the preset geographical location conditions.
[0079] If not, skip the current target product and select the next target product that meets the geographical location condition as the pre-push object.
[0080] By judging whether the geographical location information of the target customer and the geographical location information of the pre-pushed current target product simultaneously meet the preset geographical location conditions, it is ensured that the target product purchased by the target user can be delivered.
[0081] Step 104: Push the corresponding target product information to the target user according to the score.
[0082] According to the descending order of the score size, the corresponding target product information, such as the product purchase link, is pushed to the target user through methods such as the Dongka Space APP, WeChat advertising page, SMS push link, etc.
[0083] Through the embodiments provided by the present disclosure, the following are achieved:
[0084] 1. Intelligent operation planning: One-stop configuration management of customers, objects, and delivery schedules. Operation personnel can independently innovate and execute marketing plans. The operation is simple and fast. It supports viewing delivery plan conversion rate and other performance data.
[0085] 2. Labels are more real-time: For scenario data such as user behavior and geographic location, the data is collected and updated in real time on T-1 day, and the recommendation model is optimized to identify target users more accurately.
[0086] 3. More precise delivery: Supports user segmentation capabilities, combines user offline tags and time decay effects to match the most appropriate customer groups.
[0087] 4. Support high-concurrency calls: Based on ES customer data processing, it supports massive customer screening and matching, and the delivery effect is stable.
[0088] 5. Multi-dimensional marketing control: Redis is used to cache the delivery plan and the matched target customers, and the screening and delivery are decoupled, providing the system with the ability to cope with multiple tasks, massive data, and high concurrency. Redis distributed locks and customized customer do not disturb policies are used to ensure accurate triggering of marketing and avoid customers being bothered by frequent marketing.
[0089] The method provided by the embodiment of the present disclosure solves the problem that the information push strategy in the current market cannot flexibly fit the large-scale customer groups, resulting in high marketing costs but low product transaction volumes; it achieves accurate matching of large-scale target customers and target products, thereby reducing marketing costs and increasing product transaction volumes.
[0090] According to an embodiment of the present disclosure, the present disclosure also provides an information push device 300, as shown in the attached Figure 3 As shown, the device comprises:
[0091] The acquisition module 301 is used to input the target user information and the target product information into the pre-trained push model.
[0092] The feature extraction module 302 is used to extract multiple interaction features related to the target product information from the target user information through the push model.
[0093] The calculation module 303 is used to perform weighted fusion on the interaction features based on a preset assignment rule to determine the score of the target product; wherein the score is used to represent the target user's demand for the target product.
[0094] The push module 304 is used to push the corresponding target product information to the target user according to the score.
[0095] The information push device 300 provided according to the embodiment of the present disclosure solves the problem that the information push strategy in the current market cannot flexibly fit the large-scale customer groups, resulting in high marketing costs but low product transaction volumes; it achieves accurate matching of large-scale target customers and target products, thereby reducing marketing costs and increasing product transaction volumes.
[0096] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0097] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is 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 electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, 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 disclosure described and / or required herein.
[0098] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0099] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0100] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the information push method. For example, in some embodiments, the information push method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the information push method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the information push method in any other appropriate manner (e.g., by means of firmware).
[0101] Various implementations 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 implementations can include: being implemented in one or more computer 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.
[0102] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code 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.
[0103] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. 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.
[0104] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0105] The systems and techniques described herein may be implemented in a computing system that includes back-end 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 front-end 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 back-end components, middleware components, or front-end 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), and the Internet.
[0106] A computer 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 relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0107] 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 recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0108] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. 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 disclosure shall be included in the protection scope of the present disclosure.
Claims
1. An information push method, comprising: Input the target user information and target product information into the pre-trained push model; Extracting multiple interaction features related to the target product information from the target user information through the push model; The interactive features are weighted and integrated based on a preset assignment rule to determine the score of the target product; wherein the score is used to represent the target user's demand for the target product; The corresponding target product information is pushed to the target user according to the score.
2. The method according to claim 1, further comprising: The big data of the target user is labeled through a user profiling tool to obtain the target user information.
3. The method according to claim 2, wherein: The target user information includes but is not limited to: User behavior labels, user transaction labels, user preference labels, and user attribute labels.
4. The method according to claim 1, wherein: The extracting, through the push model, a plurality of interaction features related to the target product information from the target user information includes: Based on the push model, the target user information and the target product information are respectively mapped into vector elements; The vector elements corresponding to the target product information in the target user information are combined to obtain a plurality of the interaction features.
5. The method according to claim 1, wherein: The interactive features include but are not limited to at least one of the following: The type, quantity, depth, and frequency of the target user’s interactions with the target product during the target time period.
6. The method according to claim 5, wherein: The assignment rules include: An adaptive weight of each of the interactive behaviors is determined according to the type, quantity, depth and frequency of the interactive behaviors within a target time period.
7. The method according to claim 1, wherein the assignment rule comprises: A time decay coefficient of the interactive behavior is determined according to the occurrence time of the interactive behavior.
8. The method according to claim 1, before pushing the corresponding target product information to the target user according to the score, the method further comprises: Determine whether the geographic location information of the target customer and the geographic location information of the pre-pushed current target product simultaneously meet the preset geographic location conditions; If not, skip the current target product and select the next target product that meets the geographical location condition as the pre-push object.
9. The method according to claim 1, further comprising: The score is updated according to a preset time interval.
10. An information push device, comprising: An acquisition module, used to input target user information and target product information into a pre-trained push model; A feature extraction module, used to extract a plurality of interaction features related to the target product information from the target user information through the push model; A calculation module, used for weighted fusion of the interaction features based on a preset assignment rule to determine the score of the target product; wherein the score is used to represent the target user's demand for the target product; A push module is used to push the corresponding target product information to the target user according to the score.
11. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.
12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.
13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.