Product channel recommendation method and device, equipment and storage medium

Through asynchronous delay queue and heartbeat mechanism, user data is processed in real time and product recommendation solutions are generated, which solves the problem of slow response speed of traditional recommendation algorithms, and achieves more accurate and timely product push to adapt to changes in user needs.

CN119090570APending Publication Date: 2024-12-06CHINA PING AN PROPERTY INSURANCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411193931.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Traditional recommendation algorithms are slow to respond when facing the variability of user behavior and preferences, cannot respond to changes in user needs in a timely manner, and cannot push product information through appropriate channels in a timely manner.

Method used

Using asynchronous delay queue and heartbeat mechanism, obtain the target user's personal information data, perform feature extraction and sorting, and generate product recommendation plans based on preset product recommendation models, including push channel plans and product information plans, detect data update status in real time and adjust it Recommendation strategy.

Benefits of technology

It improves the accuracy and real-timeness of product channel recommendations, enhances the multidimensionality and availability of recommendation results, and can respond more accurately and timely to changes in user needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090570A_ABST
    Figure CN119090570A_ABST
Patent Text Reader

Abstract

The invention discloses a product channel recommendation method and device, equipment and a storage medium, provides more accurate, real-time and multi-dimensional recommendation of products and push channels by utilizing an asynchronous delay queue and a heartbeat mechanism and combining with business processes and characteristics of industries, improves the accuracy and real-time performance of channel recommendation, and improves the user experience. The multi-dimensionality and availability of recommendation results are improved, and the problem that a traditional recommendation algorithm needs a large amount of user behavior data for training and optimization is solved. However, data collection and processing often need a long time, resulting in slow response speed of a recommendation system, incapability of timely responding to changes of user demands, and incapability of timely pushing data to the user through a proper channel.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of product recommendation, and in particular to a product channel recommendation method, device, equipment and storage medium. Background Art

[0002] In the insurance industry, recommendation algorithms are one of the key technologies to improve user experience and increase sales conversion rates. Although traditional recommendation algorithms have achieved certain success in some aspects, they also expose some obvious shortcomings in practical applications, especially when faced with the variability of user behavior and preferences.

[0003] User behaviors and preferences are not static, but change with time, environment, emotions and other factors. Traditional recommendation algorithms often rely on users' past data, but ignore the timeliness and dynamics of these data. For example, a user may be interested in a certain type of insurance product at a certain time, but over time, his interest may shift, and the recommendation system fails to capture this change in time.

[0004] Users' decisions are not only influenced by personal preferences, but may also be affected by external environments, such as social media, friend recommendations, news events, etc. These external factors may have a significant impact on users' decisions in a short period of time, and traditional recommendation algorithms find it difficult to take these complex external factors into account.

[0005] Traditional recommendation algorithms require a large amount of user behavior data for training and optimization. However, data collection and processing often takes a long time, which results in a slow response speed of the recommendation system and an inability to respond to changes in user needs in a timely manner. In the insurance industry, this delay may result in missing out on the best sales opportunities. Summary of the invention

[0006] The present application provides a product channel recommendation method, device, equipment and storage medium, which solves the problem that traditional recommendation algorithms require a large amount of user behavior data for training and optimization. However, data collection and processing often takes a long time, resulting in a slow response speed of the recommendation system, which cannot respond to changes in user needs in a timely manner, and at the same time, cannot be pushed to users through appropriate channels in a timely manner.

[0007] In view of this, the first aspect of the present application provides a method, the method comprising:

[0008] Step S1, obtaining personal information data of the target user;

[0009] Step S2, performing feature extraction processing on the personal information data to obtain target feature data;

[0010] Step S3, storing the target feature data in an asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target feature data;

[0011] Step S4: acquiring the target feature data from the asynchronous delay queue according to a preset recommendation rule, and generating a product recommendation plan based on a preset product recommendation model, wherein the product recommendation plan includes a push channel plan and a product information plan;

[0012] Step S5: recommending the product information solution to the target user according to the push channel solution.

[0013] Optionally, before step S3, the step further includes:

[0014] Build an asynchronous delay queue;

[0015] Determine the corresponding delay time in the asynchronous delay queue according to the update frequency of the data source of the personal information data;

[0016] The sorting method after entering the asynchronous delay queue is determined based on the preset weight of the target feature data.

[0017] Optionally, it also includes:

[0018] The data update status of the data source of the target user's personal information data is periodically detected based on the heartbeat mechanism. If the data update status of the target user is abnormal, the exception handling mechanism is executed.

[0019] Optionally, the exception handling mechanism includes:

[0020] According to the data source of the personal information data of the target user having an abnormal data update status, the weight of the target feature data corresponding to the target user in the asynchronous delay queue is reduced, and the asynchronous delay queue is reordered.

[0021] Optionally, the personal information data of the target user includes: basic information data and behavior information data.

[0022] Optionally, before step S4, the step further includes:

[0023] The preset product recommendation model is trained by training data, wherein the training data includes personal information data of historical users, information data of actually purchased products of the historical users, and channel information data of the historical users.

[0024] Optionally, the number of the asynchronous delay queue is at least one;

[0025] When there are two or more asynchronous delay queues, the target feature data of the target user is stored in the corresponding asynchronous delay queue according to the user tag information of the target user.

[0026] A second aspect of the present application provides a product channel recommendation device, the device comprising:

[0027] An acquisition unit, used to acquire personal information data of a target user;

[0028] A data processing unit, used to perform feature extraction processing on the personal information data to obtain target feature data;

[0029] A storage unit, used for storing the target characteristic data into an asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target characteristic data;

[0030] A recommendation unit, configured to obtain the target feature data from the asynchronous delay queue according to a preset recommendation rule, and generate a product recommendation plan based on a preset product recommendation model, wherein the product recommendation plan includes a push channel plan and a product information plan;

[0031] A push unit is used to recommend the product information solution to the target user according to the push channel solution.

[0032] Optionally, a construction unit is further included for:

[0033] Build an asynchronous delay queue;

[0034] Determine the corresponding delay time in the asynchronous delay queue according to the update frequency of the data source of the personal information data;

[0035] The sorting method after entering the asynchronous delay queue is determined based on the preset weight of the target feature data.

[0036] Optionally, a monitoring unit is further included, for:

[0037] The data update status of the data source of the target user's personal information data is periodically detected based on the heartbeat mechanism. If the data update status of the target user is abnormal, the exception handling mechanism is executed.

[0038] Optionally, the exception handling mechanism includes:

[0039] According to the data source of the personal information data of the target user having an abnormal data update status, the weight of the target feature data corresponding to the target user in the asynchronous delay queue is reduced, and the asynchronous delay queue is reordered.

[0040] Optionally, the personal information data of the target user includes: basic information data and behavior information data.

[0041] Optionally, a training unit is further included, for:

[0042] The preset product recommendation model is trained by training data, wherein the training data includes personal information data of historical users, information data of actually purchased products of the historical users, and channel information data of the historical users.

[0043] Optionally, the number of the asynchronous delay queue is at least one;

[0044] When there are two or more asynchronous delay queues, the target feature data of the target user is stored in the corresponding asynchronous delay queue according to the user tag information of the target user.

[0045] A third aspect of the present application provides a product channel recommendation device, the device comprising a processor and a memory:

[0046] The memory is used to store program code and transmit the program code to the processor;

[0047] The processor is used to execute the steps of the product channel recommendation method as described in the first aspect according to the instructions in the program code.

[0048] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the method described in the first aspect above.

[0049] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0050] In this application, a product channel recommendation method, device, equipment and storage medium are provided, which utilizes an asynchronous delay queue and heartbeat mechanism, combines the business processes and characteristics of the industry, and provides more accurate, real-time and multi-dimensional product and push channel recommendations, improves the accuracy and real-time performance of channel recommendations, and improves the multi-dimensionality and availability of recommendation results, solving the problem that traditional recommendation algorithms require a large amount of user behavior data for training and optimization. However, data collection and processing often take a long time, resulting in a slow response speed of the recommendation system, which cannot respond to changes in user needs in a timely manner, and at the same time, cannot be pushed to users through appropriate channels in a timely manner. Technical problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A method flow chart of the product channel recommendation method in the embodiment of the present application;

[0052] Figure 2 This is a schematic diagram of the structure of a product channel recommendation device in an embodiment of the present application;

[0053] Figure 3 This is a schematic diagram of the structure of the product channel recommendation device in the embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] This application designs a product channel recommendation method, device, equipment and storage medium, which solves the problem that traditional recommendation algorithms require a large amount of user behavior data for training and optimization. However, data collection and processing often takes a long time, resulting in a slow response speed of the recommendation system, which cannot respond to changes in user needs in a timely manner, and at the same time, cannot be pushed to users through appropriate channels in a timely manner.

[0056] For easier understanding, see Figure 1 , Figure 1 Flow chart of the method for product channel recommendation in the embodiment of the present application, as shown in FIG. Figure 1 As shown, specifically:

[0057] Step S1, obtaining personal information data of the target user;

[0058] It should be noted that the collection of basic information and behavior data of users provides a data basis for subsequent recommendations. Specifically, data can be obtained through channels such as user registration information, online behavior records, and historical purchase records.

[0059] For example: basic information such as name, age, gender, occupation, etc. filled in by users when registering on an insurance website; behavioral data such as the types of insurance products users browse on the website and browsing time.

[0060] Step S2: extracting features from the personal information data to obtain target feature data;

[0061] It should be noted that key features are extracted from the original data and used as input for the recommendation algorithm.

[0062] For the personal information data obtained, the collected data can also be cleaned, converted and normalized before feature extraction to make the feature extraction more accurate.

[0063] Use data mining techniques, such as text analysis and cluster analysis, to extract features such as user interests and purchasing tendencies.

[0064] For example: extract keywords such as "health insurance" and "travel insurance" from the descriptions of insurance products browsed by users as recommendation features.

[0065] Step S3, storing the target feature data into an asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target feature data;

[0066] It should be noted that the processed target feature data is stored in an asynchronous delay queue according to certain rules. This queue can be a distributed data storage system that can store a large amount of user behavior data and sort it through a certain sorting algorithm. Asynchronous processing is based on improving the efficiency and flexibility of data processing.

[0067] For example: store the user's feature data in a queue according to the user ID and timestamp, and set the delay time to 30 minutes to wait for more data to accumulate.

[0068] Step S4: acquiring target feature data from the asynchronous delay queue according to preset recommendation rules, and generating a product recommendation plan based on a preset product recommendation model, wherein the product recommendation plan includes a push channel plan and a product information plan;

[0069] It should be noted that according to the recommendation rules and recommendation models, data is extracted from the queue to generate a recommendation plan. For example, recommendation algorithms such as collaborative filtering and deep learning are used to calculate the matching degree between the user's target feature data and each product, and generate a recommended product information plan.

[0070] For example: If the user characteristics show a high interest in “health insurance”, the recommendation system will extract relevant data from the queue and recommend related health insurance products.

[0071] Step S5: recommend product information solutions to target users based on the push channel solution.

[0072] Furthermore, before step S3, the following steps are also included:

[0073] Build an asynchronous delay queue;

[0074] It should be noted that you can use tools such as Redis to build queues and set the capacity and delay time of each queue.

[0075] Determine the corresponding delay time in the asynchronous delay queue according to the update frequency of the data source of the personal information data;

[0076] It should be noted that the corresponding delay time is set according to the update frequency of the data source (such as daily, weekly, etc.). For example, if the user behavior data is updated once a day, the delay time is set to 24 hours.

[0077] The sorting method after entering the asynchronous delay queue is determined based on the preset weight of the target feature data.

[0078] It should be noted that the weight is set according to the importance of the feature data and the ranking is performed accordingly. The preset weight can be a fixed value or can be optimized and adjusted according to the user's personal information data. For example, if the user is more interested in a certain type of insurance product, the weight of the feature data is increased to give priority to it in the queue.

[0079] Furthermore, it also includes:

[0080] The data update status of the data source of the target user's personal information data is periodically detected based on the heartbeat mechanism. If the data update status of the target user is abnormal, the exception handling mechanism is executed.

[0081] It should be noted that the heartbeat mechanism is used to monitor the user's activity status in real time and synchronize the changes in the activity status to the recommendation system. This heartbeat mechanism can be a real-time monitoring system that can regularly detect the user's activity status and feed the results back to the recommendation system.

[0082] Furthermore, the exception handling mechanism includes:

[0083] According to the data source of the personal information data of the target user with abnormal data update status, the weight of the target feature data corresponding to the target user in the asynchronous delay queue is reduced, and the asynchronous delay queue is reordered.

[0084] It should be noted that in order to improve the robustness and user experience of the recommendation system, when abnormal data updates are found, the recommendation strategy is adjusted to reduce the weight of abnormal data.

[0085] For example: If a user's behavior data has not been updated for a period of time, the recommendation system will reduce the weight of this data and re-rank it to reduce its impact on the recommendation results.

[0086] Furthermore, the personal information data of the target user includes: basic information data and behavior information data.

[0087] Furthermore, before step S4, the following steps are also included:

[0088] The preset product recommendation model is trained through training data, and the training data includes personal information data of historical users, information data of historical users' actual purchased products, and channel information data of historical users.

[0089] It should be noted that in order to improve the accuracy and applicability of the recommendation model, historical data is used to train the recommendation model and optimize the model parameters. For example, the recommendation model is trained using the user's historical purchase records and browsing behavior data to improve the model's ability to recognize user preferences.

[0090] Furthermore, the number of the asynchronous delay queues is at least one;

[0091] When there are two or more asynchronous delay queues, the target feature data of the target user is stored in the corresponding asynchronous delay queue according to the user tag information of the target user.

[0092] It should be noted that in order to improve the scalability and flexibility of the system, the number of asynchronous delay queues can be expanded. Multiple queues can be set up as needed, and each queue can process data of different types or priorities. For example, one queue can be set up to process high-priority user data, and another queue can be set up to process normal-priority data.

[0093] In addition, in order to achieve more fine-grained data processing and recommendation, data is stored in different queues according to specific tags of users (such as VIP users, new users, etc.). VIP users' data is stored in a special queue for priority processing and recommendation to improve user experience.

[0094] See also Figure 2 , Figure 2 Schematic diagram of the structure of the product channel recommendation device in the embodiment of the present application. Figure 2 As shown, specifically:

[0095] An acquisition unit 201 is used to acquire personal information data of a target user;

[0096] It should be noted that the collection of basic information and behavior data of users provides a data basis for subsequent recommendations. Specifically, data can be obtained through channels such as user registration information, online behavior records, and historical purchase records.

[0097] For example: basic information such as name, age, gender, occupation, etc. filled in by users when registering on an insurance website; behavioral data such as the types of insurance products users browse on the website and browsing time.

[0098] The data processing unit 202 is used to perform feature extraction processing on the personal information data to obtain target feature data;

[0099] It should be noted that key features are extracted from the original data and used as input for the recommendation algorithm.

[0100] For the personal information data obtained, the collected data can also be cleaned, converted and normalized before feature extraction to make the feature extraction more accurate.

[0101] Use data mining techniques, such as text analysis and cluster analysis, to extract features such as user interests and purchasing tendencies.

[0102] For example: extract keywords such as "health insurance" and "travel insurance" from the descriptions of insurance products browsed by users as recommendation features.

[0103] The storage unit 203 is used to store the target feature data into the asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target feature data;

[0104] It should be noted that the processed target feature data is stored in an asynchronous delay queue according to certain rules. This queue can be a distributed data storage system that can store a large amount of user behavior data and sort it through a certain sorting algorithm. Asynchronous processing is based on improving the efficiency and flexibility of data processing.

[0105] For example: store the user's feature data in a queue according to the user ID and timestamp, and set the delay time to 30 minutes to wait for more data to accumulate.

[0106] The recommendation unit 204 is used to obtain target feature data from the asynchronous delay queue according to a preset recommendation rule, and generate a product recommendation plan based on a preset product recommendation model, the product recommendation plan includes a push channel plan and a product information plan;

[0107] It should be noted that according to the recommendation rules and recommendation models, data is extracted from the queue to generate a recommendation plan. For example, recommendation algorithms such as collaborative filtering and deep learning are used to calculate the matching degree between the user's target feature data and each product, and generate a recommended product information plan.

[0108] For example: If the user characteristics show a high interest in “health insurance”, the recommendation system will extract relevant data from the queue and recommend related health insurance products.

[0109] The push unit 205 is used to recommend product information solutions to target users according to the push channel solution.

[0110] Furthermore, it also includes a construction unit for:

[0111] Build an asynchronous delay queue;

[0112] It should be noted that you can use tools such as Redis to build queues and set the capacity and delay time of each queue.

[0113] Determine the corresponding delay time in the asynchronous delay queue according to the update frequency of the data source of the personal information data;

[0114] It should be noted that the corresponding delay time is set according to the update frequency of the data source (such as daily, weekly, etc.). For example, if the user behavior data is updated once a day, the delay time is set to 24 hours.

[0115] The sorting method after entering the asynchronous delay queue is determined based on the preset weight of the target feature data.

[0116] It should be noted that the weight is set according to the importance of the feature data and the ranking is performed accordingly. The preset weight can be a fixed value or can be optimized and adjusted according to the user's personal information data. For example, if the user is more interested in a certain type of insurance product, the weight of the feature data is increased to give priority to it in the queue.

[0117] Furthermore, a monitoring unit is included, which is used to:

[0118] The data update status of the data source of the target user's personal information data is periodically detected based on the heartbeat mechanism. If the data update status of the target user is abnormal, the exception handling mechanism is executed.

[0119] It should be noted that the heartbeat mechanism is used to monitor the user's activity status in real time and synchronize the changes in the activity status to the recommendation system. This heartbeat mechanism can be a real-time monitoring system that can regularly detect the user's activity status and feed the results back to the recommendation system.

[0120] Furthermore, the exception handling mechanism includes:

[0121] According to the data source of the personal information data of the target user with abnormal data update status, the weight of the target feature data corresponding to the target user in the asynchronous delay queue is reduced, and the asynchronous delay queue is reordered.

[0122] It should be noted that in order to improve the robustness and user experience of the recommendation system, when abnormal data updates are found, the recommendation strategy is adjusted to reduce the weight of abnormal data.

[0123] For example: If a user's behavior data has not been updated for a period of time, the recommendation system will reduce the weight of this data and re-rank it to reduce its impact on the recommendation results.

[0124] Furthermore, the personal information data of the target user includes: basic information data and behavior information data.

[0125] Furthermore, a training unit is included, which is used to:

[0126] The preset product recommendation model is trained through training data, and the training data includes personal information data of historical users, information data of historical users' actual purchased products, and channel information data of historical users.

[0127] It should be noted that in order to improve the accuracy and applicability of the recommendation model, historical data is used to train the recommendation model and optimize the model parameters. For example, the recommendation model is trained using the user's historical purchase records and browsing behavior data to improve the model's ability to recognize user preferences.

[0128] Furthermore, the number of the asynchronous delay queues is at least one;

[0129] When there are two or more asynchronous delay queues, the target feature data of the target user is stored in the corresponding asynchronous delay queue according to the user tag information of the target user.

[0130] It should be noted that in order to improve the scalability and flexibility of the system, the number of asynchronous delay queues can be expanded. Multiple queues can be set up as needed, and each queue can process data of different types or priorities. For example, one queue can be set up to process high-priority user data, and another queue can be set up to process normal-priority data.

[0131] In addition, in order to achieve more fine-grained data processing and recommendation, data is stored in different queues according to specific tags of users (such as VIP users, new users, etc.). VIP users' data is stored in a special queue for priority processing and recommendation to improve user experience.

[0132] The present application embodiment also provides another product channel recommendation device, such as Figure 3 For the sake of convenience, only the parts related to the embodiments of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The terminal can be any terminal device including a mobile phone, a tablet computer, a personal digital assistant (English full name: Personal Digital Assistant, English abbreviation: PDA), a sales terminal (English full name: Point of Sales, English abbreviation: POS), a car computer, etc., taking the terminal as a mobile phone as an example:

[0133] Figure 3 FIG. 1 is a block diagram showing a partial structure of a mobile phone related to a terminal provided in an embodiment of the present application. Figure 3The mobile phone includes: a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a wireless fidelity (WiFi) module 1070, a processor 1080, and a power supply 1090. Those skilled in the art can understand that Figure 3 The mobile phone structure shown in the figure does not constitute a limitation on the mobile phone, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0134] Combine the following Figure 3 A detailed introduction to the various components of the mobile phone:

[0135] The RF circuit 1010 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 1080 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 1010 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (full name: Low Noise Amplifier, English abbreviation: LNA), a duplexer, etc. In addition, the RF circuit 1010 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communications can use any communication standard or protocol, including but not limited to Global System of Mobile communications (Global System of Mobile communication, English abbreviation: GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, English abbreviation: CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (Long Term Evolution, English abbreviation: LTE), e-mail, Short Messaging Service (SMS), etc.

[0136] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 1020. The memory 1020 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 1020 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0137] The input unit 1030 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 1030 may include a touch panel 1031 and other input devices 1032. The touch panel 1031, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 1031 or near the touch panel 1031 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 1031 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 1080, and can receive and execute commands sent by the processor 1080. In addition, the touch panel 1031 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 1031, the input unit 1030 may further include other input devices 1032. Specifically, the other input devices 1032 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0138] The display unit 1040 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 1040 may include a display panel 1041. Optionally, the display panel 1041 may be configured in the form of a liquid crystal display (full name in English: Liquid Crystal Display, English abbreviation: LCD), an organic light-emitting diode (full name in English: Organic Light-Emitting Diode, English abbreviation: OLED), etc. Further, the touch panel 1031 may cover the display panel 1041. When the touch panel 1031 detects a touch operation on or near it, it is transmitted to the processor 1080 to determine the type of touch event. Subsequently, the processor 1080 provides a corresponding visual output on the display panel 1041 according to the type of touch event. Although in Figure 3 In the embodiment, the touch panel 1031 and the display panel 1041 are used as two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 1031 and the display panel 1041 can be integrated to realize the input and output functions of the mobile phone.

[0139] The mobile phone may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1041 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 1041 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0140] The audio circuit 1060, the speaker 1061, and the microphone 1062 can provide an audio interface between the user and the mobile phone. The audio circuit 1060 can transmit the received audio data to the speaker 1061 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 1062 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1060 and converted into audio data, and then the audio data is output to the processor 1080 for processing, and then sent to another mobile phone through the RF circuit 1010, or the audio data is output to the memory 1020 for further processing.

[0141] WiFi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages and access streaming media through the WiFi module 1070. It provides users with wireless broadband Internet access. Figure 3 A WiFi module 1070 is shown, but it is understandable that it is not an essential component of the mobile phone and can be omitted as needed without changing the essence of the invention.

[0142] The processor 1080 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 1020 and calling data stored in the memory 1020, it executes various functions of the mobile phone and processes data, thereby monitoring the mobile phone as a whole. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1080.

[0143] The mobile phone also includes a power supply 1090 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0144] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0145] In the embodiment of the present application, the processor 1080 included in the terminal also has the following functions:

[0146] Step S1, obtaining personal information data of the target user;

[0147] It should be noted that the collection of basic information and behavior data of users provides a data basis for subsequent recommendations. Specifically, data can be obtained through channels such as user registration information, online behavior records, and historical purchase records.

[0148] For example: basic information such as name, age, gender, occupation, etc. filled in by users when registering on an insurance website; behavioral data such as the types of insurance products users browse on the website and browsing time.

[0149] Step S2: extracting features from the personal information data to obtain target feature data;

[0150] It should be noted that key features are extracted from the original data and used as input for the recommendation algorithm.

[0151] For the personal information data obtained, the collected data can also be cleaned, converted and normalized before feature extraction to make the feature extraction more accurate.

[0152] Use data mining techniques, such as text analysis and cluster analysis, to extract features such as user interests and purchasing tendencies.

[0153] For example: extract keywords such as "health insurance" and "travel insurance" from the descriptions of insurance products browsed by users as recommendation features.

[0154] Step S3, storing the target feature data into an asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target feature data;

[0155] It should be noted that the processed target feature data is stored in an asynchronous delay queue according to certain rules. This queue can be a distributed data storage system that can store a large amount of user behavior data and sort it through a certain sorting algorithm. Asynchronous processing is based on improving the efficiency and flexibility of data processing.

[0156] For example: store the user's feature data in a queue according to the user ID and timestamp, and set the delay time to 30 minutes to wait for more data to accumulate.

[0157] Step S4: acquiring target feature data from the asynchronous delay queue according to preset recommendation rules, and generating a product recommendation plan based on a preset product recommendation model, wherein the product recommendation plan includes a push channel plan and a product information plan;

[0158] It should be noted that according to the recommendation rules and recommendation models, data is extracted from the queue to generate a recommendation plan. For example, recommendation algorithms such as collaborative filtering and deep learning are used to calculate the matching degree between the user's target feature data and each product, and generate a recommended product information plan.

[0159] For example: If the user characteristics show a high interest in “health insurance”, the recommendation system will extract relevant data from the queue and recommend related health insurance products.

[0160] Step S5: recommend product information solutions to target users based on the push channel solution.

[0161] Furthermore, before step S3, the following steps are also included:

[0162] Build an asynchronous delay queue;

[0163] It should be noted that you can use tools such as Redis to build queues and set the capacity and delay time of each queue.

[0164] Determine the corresponding delay time in the asynchronous delay queue according to the update frequency of the data source of the personal information data;

[0165] It should be noted that the corresponding delay time is set according to the update frequency of the data source (such as daily, weekly, etc.). For example, if the user behavior data is updated once a day, the delay time is set to 24 hours.

[0166] The sorting method after entering the asynchronous delay queue is determined based on the preset weight of the target feature data.

[0167] It should be noted that the weight is set according to the importance of the feature data and the ranking is performed accordingly. The preset weight can be a fixed value or can be optimized and adjusted according to the user's personal information data. For example, if the user is more interested in a certain type of insurance product, the weight of the feature data is increased to give priority to it in the queue.

[0168] Furthermore, it also includes:

[0169] The data update status of the data source of the target user's personal information data is periodically detected based on the heartbeat mechanism. If the data update status of the target user is abnormal, the exception handling mechanism is executed.

[0170] It should be noted that the heartbeat mechanism is used to monitor the user's activity status in real time and synchronize the changes in the activity status to the recommendation system. This heartbeat mechanism can be a real-time monitoring system that can regularly detect the user's activity status and feed the results back to the recommendation system.

[0171] Furthermore, the exception handling mechanism includes:

[0172] According to the data source of the personal information data of the target user with abnormal data update status, the weight of the target feature data corresponding to the target user in the asynchronous delay queue is reduced, and the asynchronous delay queue is reordered.

[0173] It should be noted that in order to improve the robustness and user experience of the recommendation system, when abnormal data updates are found, the recommendation strategy is adjusted to reduce the weight of abnormal data.

[0174] For example: If a user's behavior data has not been updated for a period of time, the recommendation system will reduce the weight of this data and re-rank it to reduce its impact on the recommendation results.

[0175] Furthermore, the personal information data of the target user includes: basic information data and behavior information data.

[0176] Furthermore, before step S4, the following steps are also included:

[0177] The preset product recommendation model is trained through training data, and the training data includes personal information data of historical users, information data of historical users' actual purchased products, and channel information data of historical users.

[0178] It should be noted that in order to improve the accuracy and applicability of the recommendation model, historical data is used to train the recommendation model and optimize the model parameters. For example, the recommendation model is trained using the user's historical purchase records and browsing behavior data to improve the model's ability to recognize user preferences.

[0179] Furthermore, the number of the asynchronous delay queues is at least one;

[0180] When there are two or more asynchronous delay queues, the target feature data of the target user is stored in the corresponding asynchronous delay queue according to the user tag information of the target user.

[0181] It should be noted that in order to improve the scalability and flexibility of the system, the number of asynchronous delay queues can be expanded. Multiple queues can be set up as needed, and each queue can process data of different types or priorities. For example, one queue can be set up to process high-priority user data, and another queue can be set up to process normal-priority data.

[0182] In addition, in order to achieve more fine-grained data processing and recommendation, data is stored in different queues according to specific tags of users (such as VIP users, new users, etc.). VIP users' data is stored in a special queue for priority processing and recommendation to improve user experience.

[0183] An embodiment of the present application also provides a computer-readable storage medium for storing program code, wherein the program code is used to execute any one of the implementation methods of a product channel recommendation method described in the aforementioned embodiments.

[0184] In the embodiments of the present application, a product channel recommendation method, device, equipment and storage medium are provided, which utilize an asynchronous delay queue and heartbeat mechanism, combine the business processes and characteristics of the industry, and provide more accurate, real-time and multi-dimensional product and push channel recommendations, improve the accuracy and real-time performance of channel recommendations, and improve the multi-dimensionality and availability of recommendation results, thereby solving the problem that traditional recommendation algorithms require a large amount of user behavior data for training and optimization. However, data collection and processing often take a long time, resulting in a slow response speed of the recommendation system, which cannot respond to changes in user needs in a timely manner, and at the same time, cannot be pushed to users through appropriate channels in a timely manner. Technical problems.

[0185] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0186] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application 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 interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0187] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0188] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0189] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0190] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0191] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0192] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A product channel recommendation method, characterized in that: include: Step S1, obtaining personal information data of the target user; Step S2, performing feature extraction processing on the personal information data to obtain target feature data; Step S3, storing the target feature data in an asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target feature data; Step S4: acquiring the target feature data from the asynchronous delay queue according to a preset recommendation rule, and generating a product recommendation plan based on a preset product recommendation model, wherein the product recommendation plan includes a push channel plan and a product information plan; Step S5: recommending the product information solution to the target user according to the push channel solution.

2. The product channel recommendation method according to claim 1, characterized in that: Before step S3, the following steps are also included: Build an asynchronous delay queue; Determine the corresponding delay time in the asynchronous delay queue according to the update frequency of the data source of the personal information data; The sorting method after entering the asynchronous delay queue is determined based on the preset weight of the target feature data.

3. The product channel recommendation method according to claim 2, characterized in that: Also includes: The data update status of the data source of the target user's personal information data is periodically detected based on the heartbeat mechanism. If the data update status of the target user is abnormal, the exception handling mechanism is executed.

4. The product channel recommendation method according to claim 3, characterized in that: The exception handling mechanism includes: According to the data source of the personal information data of the target user having an abnormal data update status, the weight of the target feature data corresponding to the target user in the asynchronous delay queue is reduced, and the asynchronous delay queue is reordered.

5. The product channel recommendation method according to claim 1, characterized in that: The target user's personal information data includes: basic information data and behavior information data.

6. The product channel recommendation method according to claim 1, characterized in that: Before step S4, the following steps are also included: The preset product recommendation model is trained by training data, wherein the training data includes personal information data of historical users, information data of actually purchased products of the historical users, and channel information data of the historical users.

7. The product channel recommendation method according to claim 1, characterized in that: The number of the asynchronous delay queue is at least one; When there are two or more asynchronous delay queues, the target feature data of the target user is stored in the corresponding asynchronous delay queue according to the user tag information of the target user.

8. A product channel recommendation device, characterized in that: include: An acquisition unit, used to acquire personal information data of a target user; A data processing unit, used to perform feature extraction processing on the personal information data to obtain target feature data; A storage unit, used for storing the target characteristic data into an asynchronous delay queue according to a preset storage rule, and the asynchronous delay queue sorts the target characteristic data; A recommendation unit, configured to obtain the target feature data from the asynchronous delay queue according to a preset recommendation rule, and generate a product recommendation plan based on a preset product recommendation model, wherein the product recommendation plan includes a push channel plan and a product information plan; A push unit is used to recommend the product information solution to the target user according to the push channel solution.

9. A product channel recommendation device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the product channel recommendation method according to any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the product channel recommendation method according to any one of claims 1-7.