Information recommendation method and device, equipment and storage medium

Abstract

The application relates to the fields of Internet and financial technology, and discloses an information recommendation method, device, equipment and storage medium. The method comprises the following steps: when a first click event of a user on a mobile terminal is acquired, acquiring current positioning information of the user; when a second click event of the user on the mobile terminal is acquired, acquiring real-time behavior data and historical behavior data of the user; comparing the real-time behavior data with the historical behavior data, and judging whether the real-time behavior data and the historical behavior data have the same target content type; if yes, adjusting the proportion of the target content type in a preset first recommendation type proportion, and determining target recommendation information according to the adjusted first recommendation type proportion and the current positioning information. In the above manner, the application can determine the recommendation information in combination with the current positioning information, the real-time behavior data and the historical behavior data of the user, can realize all-round and multi-dimensional integration of the recommendation information, and has high recommendation accuracy.

Description

Technical Field

[0001] This invention relates to the fields of internet technology and fintech, and in particular to an information recommendation method, apparatus, device, and storage medium. Background Technology

[0002] With the rapid development of internet technology, supporting functions such as shopping, social networking, interactive games, and resource transfer, people have entered an era of information explosion. People's lives are inevitably influenced by various types of information. While information brings convenience to users, it also affects their behavioral habits. In this context, various information providers are doing their utmost to display and recommend information to users.

[0003] With the development of science and technology, acquiring data and using data modeling to solve corresponding problems has become a very common technical approach. For example, e-commerce platforms collect data such as users' product browsing history and build product recommendation models based on the collected data to recommend products to users. However, existing information recommendations rely solely on users' current location or historical behavior data, resulting in insufficient accuracy and low activity and retention rates on shopping platforms. Summary of the Invention

[0004] This invention provides an information recommendation method, apparatus, device, and storage medium that can achieve automated and accurate recommendations, solving the problem that existing information recommendations rely solely on the user's current location or historical behavior data, resulting in insufficient accuracy and low activity and retention rates on shopping platforms.

[0005] To solve the above-mentioned technical problems, one technical solution adopted by the present invention is to provide an information recommendation method, comprising:

[0006] When the user's first click event on the mobile terminal is received, the user's current location information is obtained;

[0007] When acquiring the user's second click event on the mobile terminal, real-time and historical behavior data of the user are acquired;

[0008] The real-time behavior data is compared with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type;

[0009] If so, adjust the proportion of the target content type in the preset first recommendation type proportion, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information.

[0010] According to an embodiment of the present invention, after comparing the real-time behavior data with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type, the method further includes:

[0011] If not, the target recommendation information is determined based on the preset proportion of the first recommendation type and the current location information.

[0012] According to an embodiment of the present invention, before acquiring the user's real-time behavior data and historical behavior data when acquiring the user's second click event on the mobile terminal, the method further includes:

[0013] Determine whether the user's second click event on the mobile terminal has been obtained;

[0014] The step of determining whether a second click event by the user on the mobile terminal has been obtained includes:

[0015] If so, proceed with the steps to obtain the user's real-time and historical behavior data;

[0016] If not, then obtain the user's historical behavior data, and determine the target recommendation information based on the preset proportion of the second recommendation type, the historical behavior data, and the current location information.

[0017] According to one embodiment of the present invention, the second recommendation type includes multiple content types, and determining the target recommendation information based on the preset proportion of the second recommendation type, the historical behavior data, and the current location information includes:

[0018] Recommendation information for each content type is determined based on the historical behavior data;

[0019] Based on the preset proportion of the second recommendation type and the current location information, target recommendation information is filtered from the recommendation information of each content type.

[0020] According to an embodiment of the present invention, the first recommendation type includes a first content type and a second content type, and the step of determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes:

[0021] Determine the preset dimension type proportion and preset dimension type factor for each content type;

[0022] Recommendation information for each content type is determined based on the preset dimension type proportion and preset dimension type factor;

[0023] Based on the adjusted proportion of the first recommendation type and the current location information, target recommendation information is filtered from the recommendation information of the content type.

[0024] According to an embodiment of the present invention, the first recommendation type includes a third content type, and determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes:

[0025] A user profile is determined based on the real-time behavior data and / or the historical behavior data;

[0026] Query the database to find customer profiles that match the user profile and extract the consumption data of the customer profiles;

[0027] Based on the consumption data, the recommendation information for the third content type is determined, and target recommendation information is filtered from the recommendation information for the third content based on the adjusted proportion of the first recommendation type and the current location information.

[0028] According to an embodiment of the present invention, the first recommendation type includes a fourth content type, and determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes:

[0029] The recommendation information for the fourth content type is determined according to the publication time;

[0030] Based on the adjusted proportion of the first recommendation type and the current location information, target recommendation information is filtered from the recommendation information of the fourth content.

[0031] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is: to provide an information recommendation device, comprising:

[0032] The first acquisition module is used to acquire the user's current location information when the user's first click event on the mobile terminal is acquired;

[0033] The second acquisition module is used to acquire the user's real-time behavior data and historical behavior data when acquiring the user's second click event on the mobile terminal;

[0034] The judgment module is used to compare the real-time behavior data with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type;

[0035] The determination module is used to adjust the proportion of the target content type in the preset first recommendation type proportion if the condition is met, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information.

[0036] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is to provide a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the information recommendation method.

[0037] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is to provide a computer storage medium on which a computer program is stored, wherein the computer program implements the above-mentioned information recommendation method when executed by a processor.

[0038] The beneficial effects of this invention are as follows: when acquiring the user's first click event on the mobile terminal, the user's current location information is acquired; when acquiring the user's second click event on the mobile terminal, the user's real-time behavior data and historical behavior data are acquired; the real-time behavior data and historical behavior data are compared to determine whether the real-time behavior data and historical behavior data have the same target content type; if so, the proportion of the target content type in the preset first recommendation type proportion is adjusted, and the target recommendation information is determined based on the adjusted first recommendation type proportion and the current location information. This invention can combine the user's current location information, real-time behavior data, and historical behavior data to determine the recommendation information, achieving comprehensive and multi-dimensional integration of recommendation information with high recommendation accuracy. This solves the problem that existing information recommendations only rely on the user's current location or historical behavior data, resulting in insufficient recommendation accuracy and low activity and retention rates on shopping platforms. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating the information recommendation method according to the first embodiment of the present invention;

[0040] Figure 2 This is a flowchart illustrating step S104 in an information recommendation method according to an embodiment of the present invention.

[0041] Figure 3 This is a flowchart illustrating step S104 in the information recommendation method of another embodiment of the present invention;

[0042] Figure 4 This is a flowchart illustrating step S104 in the information recommendation method of another embodiment of the present invention;

[0043] Figure 5 This is a flowchart illustrating the information recommendation method according to the second embodiment of the present invention;

[0044] Figure 6 This is a flowchart illustrating the information recommendation method according to the third embodiment of the present invention;

[0045] Figure 7 This is a schematic diagram of the information recommendation device according to an embodiment of the present invention;

[0046] Figure 8 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention;

[0047] Figure 9This is a schematic diagram of the structure of a computer storage medium according to an embodiment of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0049] The terms "first," "second," and "third" used in this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this invention are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0050] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0051] Figure 1 This is a flowchart illustrating the information recommendation method according to the first embodiment of the present invention. It should be noted that if substantially the same result is obtained, the method of the present invention is not necessarily identical. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, the method includes the following steps:

[0052] Step S101: When the user's first click event on the mobile terminal is obtained, the user's current location information is obtained.

[0053] In step S101, the first click event is the click action when the user enters the platform. This embodiment utilizes LBS (Location Based Service) to obtain the location information of the mobile terminal user, i.e., the current location information.

[0054] Step S102: When the user's second click event on the mobile terminal is obtained, the user's real-time behavior data and historical behavior data are obtained.

[0055] In step S102, the second click event refers to the user's click behavior such as searching or browsing on the shopping platform after entering the platform. Real-time behavior data and historical behavior data can be user purchase data. Real-time behavior data includes at least the content information searched or browsed by the user, while historical behavior data includes at least historical browsing behavior data, historical search behavior data, purchase records, and basic user data.

[0056] Step S103: Compare real-time behavior data with historical behavior data to determine whether the real-time behavior data and historical behavior data have the same target content type.

[0057] In step S103, in the financial application scenario, the shopping platform includes four preset recommended content types: car service functions, physical goods, insurance products, and local information. Therefore, the target content type can include one or more of these four types. For example, if a user searches for "car service functions" in real-time behavior data and also searches for "car service functions" in historical browsing behavior data, then the real-time behavior data and historical behavior data are considered to have the same target content type, and the target content type in this case is "car service functions".

[0058] In this embodiment, vehicle-related services include online traffic management services, offline car service and maintenance store services, and online car sales services. Online traffic management services include checking traffic violations, one-click vehicle relocation, and driver's license point checks. Offline car service and maintenance store services include car washing, repair, disinfection, airport parking, paint spraying and touch-up, car disinfection, breakdown towing, parking payment, chauffeur services, refueling, tire maintenance, servicing, roadside assistance, and charging. Online car sales services include selling cars at high prices, car price evaluation, online auto shows, and curated car selections. Physical goods include product information uploaded by merchants who support platform registration. Insurance products include health insurance, accident insurance, car insurance, property insurance, and travel insurance. Local information includes content, activities, and trending news published by local operators or local KOLs (Key Opinion Leaders).

[0059] Step S104: If yes, adjust the proportion of the target content type in the preset first recommendation type proportion, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information.

[0060] In step S104, in this embodiment, the first recommendation type includes four content types: vehicle function services, physical goods, insurance products, and local information. The recommendation ratio of the four content types, i.e., the ratio of the first recommendation type, is a preset value and can be adjusted according to the actual situation. For example, if real-time behavior data and historical behavior data have the same target content type, the ratio of the target content type is increased, and the ratio of other content types is decreased. In one embodiment, assuming the ratio of vehicle function services: physical goods: insurance products: local information is 60%:10%:10%:20%, if the real-time behavior data and historical behavior data have the same target content type, which is vehicle function services, then the ratio of vehicle function services is increased to 70%, and the ratio of local information is decreased to 10%.

[0061] This embodiment first determines the priority order of recommended information for each content type based on the current location information, then determines the number of target recommended information based on the adjusted proportion of the first recommended type, and recommends information according to the priority order.

[0062] In one feasible embodiment, the first recommendation type includes a first content type and a second content type. The first content type is a vehicle function service or a physical product, and the second content type is a vehicle function service or a physical product. The first content type and the second content type are different; please refer to [link to relevant documentation]. Figure 2 Step S104 may also include the following steps:

[0063] Step S201: Determine the preset dimension type proportion and preset dimension type factor for each content type.

[0064] In step S201, the preset dimension type proportion and preset dimension type factor are used to determine the recommendation information for the corresponding content type.

[0065] If the content type is a car-related service, the preset dimension types include service point location, star rating, and high-quality reviews. The preset dimension type ratio is: service point location : star rating : high-quality reviews = 60% : 20% : 20%. In service point location, the preset dimension type factor increases as the distance between the service point and the user decreases. For example, the preset dimension type factor is 10 for locations within 500m, 8 for locations within 1000m, 6 for locations within 2000m, 5 for locations within 5000m, and 2 for locations beyond 5000m. In star rating, the preset dimension type factor is 8 for a 5-star rating, 6 for a 4-star rating, 4 for a 3-star rating, 2 for a 2-star rating, and 1 for a 1-star rating. In high-quality reviews, the preset dimension type factor is 5 for more than 5 reviews, and 3 for more than 0 but less than 5 high-quality reviews. This embodiment determines the recommended vehicle function services based on the weighted sum of preset dimension type factors and the corresponding preset dimension type proportions.

[0066] If the content type is physical goods, the preset dimension types include sales volume, products recommended by operations, products on promotional activities, and newly listed products. The preset dimension type proportions are: sales volume: products recommended by operations: products on promotional activities: newly listed products = 50%: 30%: 15%: 5%. Specifically, the preset dimension type factor for the product with the highest sales volume in the past 7 days is 10, for products recommended by operations it is 8, for products on promotional activities it is 6, and for products listed in the most recent 30 days it is 4. In this embodiment, the platform's physical goods are classified according to four dimensions: sales volume, products recommended by operations, products on promotional activities, and newly listed products. Each physical goods is tagged based on the classification results. A recommendation score is calculated for each physical goods based on the tag results. The recommended physical goods are then determined based on the recommendation score. Specifically, the recommendation score is the weighted sum of the preset dimension type factor and the preset dimension type proportion corresponding to the tag of the same physical goods. The preset dimension type factor for untagged products is 0.

[0067] Step S202: Determine the recommendation information for each content type based on the preset dimension type proportion and preset dimension type factor.

[0068] In step S202, recommendation information for each content type is determined based on the weighted sum of the preset dimension type factor and the corresponding preset dimension type proportion.

[0069] Step S203: Filter target recommendation information from the content type recommendation information based on the adjusted proportion of the first recommendation type and the current location information.

[0070] In step S203, the priority order of recommended information for each content type is first determined based on the current location information. Then, the number of target recommended information is determined based on the adjusted proportion of the first recommended type, and recommendations are made according to the priority order.

[0071] In one feasible embodiment, the first recommendation type includes a third content type, which is an insurance product; please refer to [link to relevant documentation]. Figure 3 Step S104 may also include the following steps:

[0072] Step S301: Determine user profiles based on real-time behavior data and / or historical behavior data.

[0073] In step S301, the user profile can be used to represent user information, such as user age group, user gender, user occupation, and user hobbies.

[0074] Step S302: Query the database for customer profiles that match the user profiles and extract the consumption data of the customer profiles.

[0075] In step S302, a customer profile similar to the user profile is queried from the database, the consumption data of the customer profile is extracted, and the recommendation information for the current user is determined based on the consumption data of the similar customer profile.

[0076] Step S303: Determine the recommendation information for the third content type based on the consumption data, and filter the target recommendation information from the recommendation information for the third content type based on the adjusted proportion of the first recommendation type and the current location information.

[0077] In step S302, recommendation information of a third content type is determined based on consumption data, such as recommending the best-selling insurance products purchased in the past week from the consumption data.

[0078] In one feasible embodiment, the first recommendation type includes a fourth content type, which is local information; see [link to relevant documentation]. Figure 4 Step S104 may also include the following steps:

[0079] Step S401: Determine the recommended information for the fourth content type based on the publication time.

[0080] Specifically, we recommend local information released in the past week.

[0081] Step S402: Based on the adjusted proportion of the first recommendation type and the current location information, filter the target recommendation information from the fourth content recommendation information.

[0082] Specifically, the priority order of recommended information for the fourth content type is determined based on the current location information. Then, the number of recommended information for the fourth content type is determined based on the adjusted proportion of the first recommendation type, and recommendations are made according to the priority order.

[0083] The information recommendation method of the first embodiment of the present invention determines the recommendation information by combining the user's current location information, real-time behavior data and historical behavior data, so as to achieve comprehensive and multi-dimensional integration of recommendation information, and the recommendation accuracy is high. It solves the problem that the existing information recommendation only relies on the user's current location or historical behavior data, which is not accurate enough and leads to low activity and retention rate of shopping platforms.

[0084] Figure 5 This is a flowchart illustrating the information recommendation method according to the second embodiment of the present invention. It should be noted that if substantially the same result is obtained, the method of the present invention does not necessarily require further clarification. Figure 5 The illustrated process sequence is limited. For example... Figure 5 As shown, the method includes the following steps:

[0085] Step S501: When the user's first click event on the mobile terminal is obtained, the user's current location information is obtained.

[0086] In this embodiment, Figure 5 Step S501 and Figure 1 The steps in step S101 are similar and will not be repeated here for the sake of simplicity.

[0087] Step S502: When the user's second click event on the mobile terminal is obtained, the user's real-time behavior data and historical behavior data are obtained.

[0088] In this embodiment, Figure 5 Step S502 and Figure 1 Step S102 is similar and will not be repeated here for the sake of simplicity.

[0089] Step S503: Compare real-time behavior data with historical behavior data to determine whether the real-time behavior data and historical behavior data have the same target content type.

[0090] In this embodiment, Figure 5 Step S503 and Figure 1 Step S103 is similar and will not be repeated here for the sake of simplicity.

[0091] Step S504: If yes, adjust the proportion of the target content type in the preset first recommendation type proportion, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information.

[0092] In this embodiment, Figure 5Step S504 and Figure 1 Step S104 is similar and will not be repeated here for the sake of simplicity.

[0093] Step S505: If not, determine the target recommendation information based on the preset proportion of the first recommendation type and the current location information.

[0094] In step S505, the proportion of the first recommendation type is a preset value, which can be adjusted according to the actual situation. If the real-time behavior data and historical behavior data do not have the same target content type, then there is no need to adjust the proportion of the first recommendation type. This embodiment first determines the priority order of the recommendation information for each content type based on the current location information, then determines the number of target recommendation information based on the proportion of the first recommendation type, and recommends them according to the priority order.

[0095] The information recommendation method of the second embodiment of the present invention determines the recommendation information by combining the user's current location information, real-time behavior data and historical behavior data, so as to achieve comprehensive and multi-dimensional integration of recommendation information, and the recommendation accuracy is high. This solves the problem that the existing information recommendation only relies on the user's current location or historical behavior data, which is not accurate enough and leads to low platform activity and retention rate.

[0096] Figure 6 This is a flowchart illustrating the information recommendation method according to the third embodiment of the present invention. It should be noted that if substantially the same result is obtained, the method of the present invention is not necessarily identical. Figure 6 The illustrated process sequence is limited. For example... Figure 6 As shown, the method includes the following steps:

[0097] Step S601: When the user's first click event on the mobile terminal is obtained, the user's current location information is obtained.

[0098] In this embodiment, Figure 6 Step S601 and Figure 1 The steps in step S101 are similar and will not be repeated here for the sake of simplicity.

[0099] Step S602: Determine whether the user's second click event on the mobile terminal has been obtained.

[0100] Specifically, the second click event is a user's click behavior such as searching or browsing on the platform after entering the platform. If the user performs a search or browsing click behavior on the platform after entering the platform, step S603 is executed; if the user does not perform a search or browsing click behavior on the platform after entering the platform, step S606 is executed.

[0101] Step S603: If so, obtain the user's real-time behavior data and historical behavior data.

[0102] In this embodiment, Figure 6 Step S603 and Figure 1 Step S102 is similar and will not be repeated here for the sake of simplicity.

[0103] Step S604: Compare the real-time behavior data with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type.

[0104] In this embodiment, Figure 6 Step S604 and Figure 1 Step S103 is similar and will not be repeated here for the sake of simplicity.

[0105] Step S605: If yes, adjust the proportion of the target content type in the preset first recommendation type proportion, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information.

[0106] In this embodiment, Figure 6 Step S605 and Figure 1 Step S104 is similar and will not be repeated here for the sake of simplicity.

[0107] Step S606: If not, obtain the user's historical behavior data, and determine the target recommendation information based on the preset proportion of the second recommendation type, the historical behavior data, and the current location information.

[0108] In step S606, recommendation information for each content type is determined based on historical behavior data; target recommendation information is then filtered from the recommendation information for each content type based on a preset second recommendation type percentage and the current location information. In this embodiment, the second recommendation type is the same as the first recommendation type, but the percentage of the second recommendation type may be the same as or different from the percentage of the first recommendation type. The percentage of the second recommendation type is a preset value and can be adjusted according to actual circumstances.

[0109] The information recommendation method of the third embodiment of the present invention, based on the first embodiment, determines the target recommendation information offline by using historical behavior data and current location information when no second click event of the user on the mobile terminal is obtained, thereby achieving automated and accurate recommendation. This solves the problem that existing information recommendation methods rely solely on the user's current location or historical behavior data, resulting in insufficient recommendation accuracy and low platform activity and retention rates.

[0110] Figure 7 This is a schematic diagram of the information recommendation device according to an embodiment of the present invention. Figure 7 As shown, the device 70 includes a first acquisition module 71, a second acquisition module 72, a judgment module 73, and a determination module 74.

[0111] The first acquisition module 71 is used to acquire the user's current location information when acquiring the user's first click event on the mobile terminal;

[0112] The second acquisition module 72 is used to acquire the user's real-time behavior data and historical behavior data when acquiring the user's second click event on the mobile terminal;

[0113] The judgment module 73 is used to compare real-time behavior data with historical behavior data to determine whether the real-time behavior data and historical behavior data have the same target content type;

[0114] If so, module 74 is used to adjust the proportion of the target content type in the preset first recommendation type proportion, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information.

[0115] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Figure 8 As shown, the computer device 80 includes a processor 81 and a memory 82 coupled to the processor 81.

[0116] The memory 82 stores program instructions for implementing the information recommendation method described in any of the above embodiments.

[0117] Processor 81 is used to execute program instructions stored in memory 82 to provide information.

[0118] The processor 81 can also be referred to as a CPU (Central Processing Unit). The processor 81 may be an integrated circuit chip with signal processing capabilities. The processor 81 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0119] See Figure 9 , Figure 9This is a schematic diagram of the structure of a computer storage medium according to an embodiment of the present invention. The computer storage medium of this embodiment stores a program file 91 capable of implementing all the above methods. This program file 91 can be stored in the computer storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0120] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0121] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] The above are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An information recommendation method, characterized in that, include: When the user's first click event on the mobile terminal is received, the user's current location information is obtained; When acquiring the user's second click event on the mobile terminal, real-time and historical behavior data of the user are acquired; The real-time behavior data is compared with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type; If so, adjust the proportion of the target content type in the preset first recommendation type proportion, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information; Before acquiring the user's real-time behavior data and historical behavior data when acquiring the user's second click event on the mobile terminal, the method further includes: Determine whether the user's second click event on the mobile terminal has been obtained; The step of determining whether a second click event by the user on the mobile terminal has been obtained includes: If so, proceed with the steps to obtain the user's real-time and historical behavior data; If not, then obtain the user's historical behavior data, and determine the target recommendation information based on the preset proportion of the second recommendation type, the historical behavior data, and the current location information; The first recommendation type includes a first content type and a second content type. Determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes: Determine the preset dimension type proportion and preset dimension type factor for each content type; Recommendation information for each content type is determined based on the preset dimension type proportion and preset dimension type factor; Based on the adjusted proportion of the first recommendation type and the current location information, target recommendation information is filtered from the recommendation information of the content type.

2. The information recommendation method according to claim 1, characterized in that, After comparing the real-time behavior data with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type, the method further includes: If not, the target recommendation information is determined based on the preset proportion of the first recommendation type and the current location information.

3. The information recommendation method according to claim 1, characterized in that, The second recommendation type includes multiple content types, and determining the target recommendation information based on the preset proportion of the second recommendation type, the historical behavior data, and the current location information includes: Recommendation information for each content type is determined based on the historical behavior data; Based on the preset proportion of the second recommendation type and the current location information, target recommendation information is filtered from the recommendation information of each content type.

4. The information recommendation method according to claim 1, characterized in that, The first recommendation type includes a third content type, and determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes: A user profile is determined based on the real-time behavior data and / or the historical behavior data; Query the database to find customer profiles that match the user profile and extract the consumption data of the customer profiles; Based on the consumption data, the recommendation information for the third content type is determined, and target recommendation information is filtered from the recommendation information for the third content based on the adjusted proportion of the first recommendation type and the current location information.

5. The information recommendation method according to claim 4, characterized in that, The first recommendation type includes a fourth content type, and determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes: The recommendation information for the fourth content type is determined according to the publication time; Based on the adjusted proportion of the first recommendation type and the current location information, target recommendation information is filtered from the recommendation information of the fourth content.

6. An information recommendation device, characterized in that, include: The first acquisition module is used to acquire the user's current location information when the user's first click event on the mobile terminal is acquired; The second acquisition module is used to acquire the user's real-time behavior data and historical behavior data when acquiring the user's second click event on the mobile terminal; The judgment module is used to compare the real-time behavior data with the historical behavior data to determine whether the real-time behavior data and the historical behavior data have the same target content type; The determination module is used to adjust the proportion of the target content type in the preset first recommendation type proportion if the condition is met, and determine the target recommendation information based on the adjusted first recommendation type proportion and the current location information. Before acquiring the user's real-time behavior data and historical behavior data when acquiring the user's second click event on the mobile terminal, the method further includes: Determine whether the user's second click event on the mobile terminal has been obtained; The step of determining whether a second click event by the user on the mobile terminal has been obtained includes: If so, proceed with the steps to obtain the user's real-time and historical behavior data; If not, then obtain the user's historical behavior data, and determine the target recommendation information based on the preset proportion of the second recommendation type, the historical behavior data, and the current location information; The first recommendation type includes a first content type and a second content type. Determining the target recommendation information based on the adjusted proportion of the first recommendation type and the current location information includes: Determine the preset dimension type proportion and preset dimension type factor for each content type; Recommendation information for each content type is determined based on the preset dimension type proportion and preset dimension type factor; Based on the adjusted proportion of the first recommendation type and the current location information, target recommendation information is filtered from the recommendation information of the content type.

7. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the information recommendation method as described in any one of claims 1-5.

8. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the information recommendation method as described in any one of claims 1-5.

Images