WO2020077889A1 - 基于大数据信息推送方法、装置、计算机设备及存储介质 - Google Patents
基于大数据信息推送方法、装置、计算机设备及存储介质 Download PDFInfo
- Publication number
- WO2020077889A1 WO2020077889A1 PCT/CN2019/070365 CN2019070365W WO2020077889A1 WO 2020077889 A1 WO2020077889 A1 WO 2020077889A1 CN 2019070365 W CN2019070365 W CN 2019070365W WO 2020077889 A1 WO2020077889 A1 WO 2020077889A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- recommendation
- value
- attribute
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Recommending goods or services
Definitions
- the present application relates to the field of information push technology. Specifically, the present application relates to a method, device, computer equipment, and storage medium for pushing information based on big data.
- the recommendation is based on the customer ’s previous browsing data, which is usually based on the data browsed in the most recent period, and the data collection is usually in a specific scene and field, and is not suitable for multiple application scenarios. It is only limited to online product push, and the applicable scenarios and scope are limited.
- the purpose of this application is to solve at least one of the above technical defects, and to disclose a method, device, computer equipment and storage medium based on big data information push, which can accurately obtain the recommendation list according to the user's identity attributes and behavior data, and at the same time according to The current location information of the user is selected from the recommendation list and the recommended information that matches the current location information is pushed to meet the current needs of the user.
- the present application also discloses a device for pushing information based on big data, including: a first acquisition module: configured to perform acquisition of first location information and a recommendation list of a target terminal, the recommendation list including mapping of account information logged on the target terminal A set of recommended information obtained from the statistics of historical behavior data of the first; the first processing module: configured to perform filtering out the second position information to which the recommended information belongs in the recommended list at a preset distance from the first position information The recommended information within the scope is used as pre-push information; the first execution module: is configured to execute pushing the pre-push information to the target terminal for display.
- the present application also discloses a computer device, which includes a memory and a processor.
- the memory stores computer-readable instructions.
- the processor is executed The following steps of the data information pushing method: obtaining the first location information and the recommendation list of the target terminal, the recommendation list includes a collection of recommended information obtained by statistically collecting historical behavior data mapped to the user's account information on the target terminal; Filtering recommended information in the preset distance range between the second position information to which the recommended information belongs and the first position information in the recommended list as pre-push information; pushing the pre-push information to the target terminal display.
- the second position information to which the push information belongs is obtained from the recommendation list that meets the user's interests and needs, and the difference between the second position information and the first position information is within a preset distance Recommended information within the scope, and promptly push the account information corresponding to the user in order to facilitate the user to obtain relevant information that may be used immediately.
- the method of sorting the recommended values is used to obtain the recommended information for the user. The degree of interest, and push the user according to this sort of recommendation value, in order to ensure that the pushed information is the user's preference.
- Figure 1 is a general flow chart of the application based on big data information push method
- FIG. 3 is a flowchart of a method for obtaining recommended values of behavior attributes of the application
- FIG. 4 is a flowchart of a recommendation list method based on personal attributes listed in the application
- FIG. 5 is a flowchart of a method for obtaining a recommendation list in the second embodiment of the application.
- FIG. 6 is a flowchart of a method for pushing pre-push information in this application.
- FIG. 7 is a block diagram of a module for pushing a device based on big data information of the present application.
- FIG. 8 is a block diagram of the basic structure of the computer device of the present application.
- terminal and “terminal device” used here include not only devices with wireless signal receivers, but only devices with wireless signal receivers that do not have transmitting capabilities, but also devices that receive and transmit hardware.
- Such devices may include: cellular or other communication devices with single-line displays or multi-line displays or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service, personal communication system), which can combine voice and data processing, facsimile and / or data communications capabilities; PDA (personal digital Assistant, personal digital assistants), which may include network access to a radio frequency receiver, a pager, Internet / web browser, notepad, calendar and / or GPS (Global Positioning System (Global Positioning System) receiver; conventional laptop and / or palmtop computer or other device that has and / or includes a conventional radio frequency receiver and / or palmtop computer or other device.
- GPS Global Positioning System
- terminal and “terminal equipment” may be portable, transportable, installed in a vehicle (aeronautical, maritime, and / or terrestrial), or suitable and / or configured to operate locally, and / or In a distributed form, it operates at any other location on the earth and / or space.
- the "terminal” and “terminal device” used herein may also be a communication terminal, an Internet terminal, a music / video playback terminal, for example, may be a PDA, MID (Mobile Internet Device, mobile Internet device) and / or have music / video playback
- Functional mobile phones can also be smart TVs, set-top boxes and other devices.
- FIG. 1 This application discloses a method for pushing information based on big data.
- FIG. 1 mainly includes the following steps:
- the target terminal is a terminal device with user account information logged in, such as a mobile phone, a tablet, an electronic wristband, a computer, and the like, and is preferably a mobile smart terminal.
- the current location information can be obtained through the IP address, which is defined as the first location information here, or the current location information of the target terminal can be obtained through the GPS positioning information on the smart terminal.
- Historical behavior data is the behavior data before the current time node.
- API Application Programming Interface
- API Application Programming Interface
- the API can be used to obtain the browser in the terminal device to start Before the network device reports the behavior data, the behavior data generated by the user performing network access through his account information and stored on the network side.
- the recommendation list includes a collection of recommendation information obtained by statistics of historical behavior data mapped to account information on the login target terminal.
- Historical behavior data in this application can be related data recorded for the account information to perform web browsing, commenting, buying objects, favorites, likes and other actions on the terminal. Through these operations and the number of operations, it is possible to speculate that the user may feel
- the type of information of interest, and this kind of information that may be of interest is defined as recommendation information, and according to a certain rule, the recommendation information is combined together to form a recommendation list.
- the method for obtaining the recommendation list includes:
- the data within a certain period of time is usually designated as valid data, and the data within this period of time is collected as the target data for analysis.
- This preset period of time can be one week, one quarter, or six months , One year, etc.
- the preset time may also be obtained according to certain rules. For example, for a certain period of time, when the activity is high, a time period with a short time interval is selected as the preset time period. If the activity level is low, a longer time period is selected as the preset time period. For example, account information A, you have logged in to your account twice within a year, and the number of views does not exceed 10, you can collect historical data for account information A The preset time period is extended to two years or even longer. If account information B is logged in and browsed every day, the preset time period can be set to the most recent half year, and the historical behavior log within the past half year can be obtained. The historical behavior log is a collection of data recording each operation of the account information, and is usually recorded in a timeline manner.
- the behavior attribute label is the classification information set in order to distinguish the type of behavior or the category to which the behavior belongs, such as browsing, commenting, buying objects, favorites, likes, etc. are the types of behavior, and the content of the page corresponding to the execution of the above actions will be mapped differently Categories, such as daily necessities, financial insurance, clothing, cosmetics, etc.
- categories such as daily necessities, financial insurance, clothing, cosmetics, etc.
- multiple sub-tags can be further set, for example, under the wealth management and insurance attribute tags, fund tags, insurance tags, stock tags, etc. can also be included, and the next level can be set under the specific sub-tags.
- Sub-labels, such as under the insurance label can also set up life insurance, property insurance, sickness insurance, etc. Not only that, but can continue to be further subdivided until the specific product name and the batch under the product, etc.
- each product can be classified to facilitate the collection of specific data.
- the specific behavior attribute label the amount of information corresponding to each behavior attribute label within a preset time period can be obtained, such as in The total browsing information quantity, total collection quantity, total likes quantity, etc. in the wealth management behavior behavior attribute label, as well as the specific corresponding fund label browsing quantity, insurance label browsing quantity, stock label browsing quantity, etc.
- the recommended value of the behavior attribute is based on the statistics of historical behavior traces, which is usually calculated according to the frequency of occurrence in the historical behavior data within a preset time period, or the type of user operation corresponding to the account information, for example, the type of user operation "Favorite” or “Follow” means that the user is more concerned about the content corresponding to the attribute tag, but a simple browsing means that the user only has a little understanding of the relevant content; the more the user pays attention to the same type of content If it is more, it means that the user is more interested in the type. According to the above rules, it can be determined where the user is interested in the point of interest, and the higher the recommended value for the content of the same type that meets the user's interest or attention.
- the method for calculating the behavior recommendation value characterizing the preference of the information in the behavior attribute label according to the number of the behavior attribute labels includes:
- the weight value represents the weight value of the behavior attribute label of the category.
- different user operation types have different meanings. For example, if the user operation type is "favorite" or "follow", it means that the user The content corresponding to the attribute label is more concerned, but a simple browsing indicates that the user has only a little understanding of the relevant content; therefore, the weight value of the behavior attribute label mapped to the content information corresponding to the user's "favorite” can be set to a higher value , And the weight value of the behavior attribute tag mapped to the content information corresponding to "Browse" is set to a low value.
- the category of the user's execution of certain information and the behavior attribute label can be obtained, so the first weight value of the information is obtained.
- the behavior attribute recommendation value A The acquisition method is obtained by the following formula:
- the type corresponding to the same behavior attribute tag is not limited to one type, and there may be multiple types, such as browsing and following, etc.
- the method for obtaining the recommended value A is obtained by the following formula:
- n the quantity value of the operation type of the behavior attribute label.
- the weight value of the "Browse” type is defined as 0.2
- the weight value of the "Follow” type is 0.6
- account information browses a total of 30 insurance products and pays attention to 5 insurance products, then the total recommended value of the insurance products
- a first preset condition is set, and recommendation information mapped to behavior attribute recommendation values that satisfy the first preset condition is stored in a recommendation list.
- the first preset condition can be that the behavior attribute recommendation value is ranked within a certain threshold, for example, the behavior attribute recommendation value ranking in the top 10 information is stored in the recommendation list for pushing the account information, this method ensures that The products pushed to the account information are the ones the user likes.
- the second location information is location information to which the recommendation information belongs. For example, when the information is coupon information about a store, the second location information is the location of the store. When the store has multiple branches, and multiple branches can use the coupon, then all the second location information that matches the coupon is used as alternative address information, and the first location information of the target terminal match. Select the recommended information within the preset distance range as pre-push information.
- the selected pre-push information is pushed to the target terminal for display.
- One feasible way is to select the closest pre-push information for pushing according to the matching distance above, or the distance ranking is within a certain threshold, such as the top 3 nearest The pieces of pre-push information are pushed in turn.
- the other is to push the information that ranks first or ranks within a certain range according to the ranking of the recommended value of the pre-pushed information within a preset range.
- the above are only several publicly displayed push display methods, but are not limited to the above several types, and may also be other push selection methods.
- the behavior attribute recommendation value can be combined with other recommendation values to obtain more accurate recommendation ranking information, such as personal attribute information combined with account information. Therefore, in an embodiment, the recommendation list further includes a set of predicted user preference information listed based on the user's personal attribute information, please refer to FIG. 4, the set of predicted user preference information listed based on the user's personal attribute information
- the acquisition methods include:
- the identity attribute label is a label that represents the user's personal identity, such as the user's age stage, user's gender, family situation, investment risk level, etc. These information can be obtained directly from the user information that the user fills in when opening the account, or through management The business personnel of the user's account information are obtained by manually entering relevant tags.
- the identity attribute labels are divided into multiple different categories, and different recommendation information is mapped according to different categories, for example, the identity attribute labels are divided into age categories, gender categories, family status categories, personal preferences, and investment risks
- the age class is divided into under 30 years old, 31-45 years old, 46-65 years old and over 65 years old and other sub-classes
- the gender class is divided into male and female sub-classes
- the family status is divided into married and unmarried ⁇ Children below 2 children, children 3 and above and other small categories
- investment risk level includes low risk, general risk and high risk and other small categories
- personal preferences include sports, shopping, catering and other small categories
- Each sub-category is mapped with the recommendation information of the person who meets the sub-category.
- the recommended information mapped by each sub-category can be the relevant recommendation information entered by the business personnel according to the business needs, or it can be based on Information of the historical behavior data of the user who meets the above identity attribute tag meets the user's needs or the information that the user may be interested in.
- the identity attribute recommendation value corresponding to the recommendation information may also be obtained at the same time, the recommendation value may be a value given when the recommendation information is entered, when the identity-based
- the method for obtaining the recommended value of the identity attribute may also be the same as the method of step S1300 above.
- step S1500 the method of acquiring the information mapped with the identity attribute label is disclosed, so there is a lot of information mapped with the identity attribute label, which needs to be selected according to certain rules.
- This application will meet the second preset condition
- the information mapped by the identity attribute tag of is stored in a recommendation list, and the second preset condition includes that the identity attribute recommendation values are sorted within a preset range value in order from high to low.
- the recommendation information in the top 10 according to the identity attribute recommendation value is included in the recommendation list.
- the size of the identity attribute recommendation value may be within a preset range, such as when the identity attribute recommendation value is greater than 9. Recommended information is included in the recommended list.
- the method for obtaining the recommended list of account information is obtained by steps S1100-S1400.
- the recommended list and identity attributes obtained from historical behavior data need to be obtained
- the obtained recommendation list is combined to obtain the summarized recommendation list. For details, please refer to FIG. 5.
- the method for obtaining the collected recommendation list includes:
- the recommendation information of the above two categories can be integrated according to certain rules.
- a second weight value is respectively set for the recommendation information of the attribute label set
- a third weight value is set for the recommendation information of the identity attribute set, in order to distinguish the specific weight values of the two.
- the recommendation information in the behavior attribute label collection is obtained through the user's own operation behavior within a preset time period, which can relatively reflect the user's preferences more accurately, while the recommendation information in the identity attribute collection is only based on business needs , Or the recommendation information of the user's preference preset according to the preference trend of the group satisfying an identity characteristic, so the second weight value of the behavior attribute label set can be assigned to a higher value, while the identity attribute set label third The weight value is assigned to a lower value, and in turn, the data in the behavior attribute tag is limitedly obtained.
- step S1320 the method for obtaining the behavior attribute recommendation A is disclosed as:
- the recommended information corresponding to the list may be sorted according to the sizes of the first recommended value and the second recommended value to form a recommended list.
- step S2000 it is necessary to match the acquired second position information with the first position information to select within a preset distance range
- the recommended information is used as pre-push information.
- the matching method is to determine whether the first position information and the second position information are within a preset distance range, for example, when the preset distance range is 500 meters, it is in the recommendation list , Select the recommended information of the second position information and the first position information within 500 meters as the pre-push information to push.
- FIG. 6 further includes the following steps:
- the preset threshold value is a range of conditions regarding the selection of recommended values. In one embodiment, the preset threshold value is that the recommended values of the pre-push information are sorted within a certain range.
- the top 10 is targeted information.
- the target information is selected information for pushing the target terminal where the user's account information is logged in.
- the target information is sent to the target terminal for display.
- This application also discloses a device for pushing information based on big data. Its block diagram is shown in FIG. 7 and includes:
- the first acquiring module 1000 configured to perform acquiring the first position information and the recommendation list of the target terminal, the recommendation list including a set of recommended information obtained by statistically collecting historical behavior data mapped to the user's account information on the target terminal;
- the target terminal is a terminal device with account information logged in, such as a mobile phone, a tablet, an electronic wristband, a computer, and the like, and a mobile intelligent terminal is preferred.
- the current location information can be obtained through the IP address, which is defined as the first location information here, or the current location information of the target terminal can be obtained through the GPS positioning information on the smart terminal.
- the historical behavior data is the behavior data before the current time node.
- API Application Programming
- the recommendation list includes a collection of recommendation information obtained by statistically collecting historical behavior data mapped to account information on the login target terminal.
- Historical behavior data in this application can be related data recorded for the account information to perform web browsing, commenting, buying objects, favorites, likes and other actions on the terminal. Through these operations and the number of operations, it is possible to speculate that the user may feel
- the type of information of interest, and this kind of information that may be of interest is defined as recommendation information, and according to a certain rule, the recommendation information is combined together to form a recommendation list.
- the first processing module 2000 configured to perform filtering out in the recommendation list the second position information to which the recommendation information belongs and the recommendation information within a preset distance range of the first position information as pre-push information;
- the second location information is location information to which the recommendation information belongs. For example, when the information is coupon information about a store, the second location information is the location of the store. When the store has multiple branches, and multiple branches can use the coupon, then all the second location information that matches the coupon is used as alternative address information, and the first location information of the target terminal match. Select the recommended information within the preset distance range as pre-push information.
- the first execution module 3000 is configured to execute pushing the pre-push information to the target terminal for display.
- the selected pre-push information is pushed to the target terminal for display.
- One feasible way is to select the closest pre-push information for pushing according to the matching distance above, or the distance ranking is within a certain threshold, such as the top 3 nearest The pieces of pre-push information are pushed in turn.
- the other is to push the information that ranks first or ranks within a certain range according to the ranking of the recommended value of the pre-pushed information within a preset range.
- the above are only several publicly displayed push display methods, but are not limited to the above several types, and may also be other push selection methods.
- the present application further includes: a second acquiring module: configured to perform acquiring the behavior attribute recommendation value of the pre-push information; the behavior attribute recommendation value is a value characterizing the degree of preference of the pre-push information; and the second processing Module: configured to execute pre-push information with the recommended value of the behavior attribute within a preset threshold as target information; second execution module: configured to execute sending the target information to the target terminal for display.
- a second acquiring module configured to perform acquiring the behavior attribute recommendation value of the pre-push information
- the behavior attribute recommendation value is a value characterizing the degree of preference of the pre-push information
- the second processing Module configured to execute pre-push information with the recommended value of the behavior attribute within a preset threshold as target information
- second execution module configured to execute sending the target information to the target terminal for display.
- the present application further includes: a third acquisition module: configured to perform acquisition of historical behavior logs to which account information is mapped within a preset time period; a reading module: configured to perform reading of historical behavior logs Behavior attribute label of each piece of information and count the number of information in the same behavior attribute label; the first calculation module: configured to perform calculation according to the number of the behavior attribute label to obtain the characterization degree of the information in the behavior attribute label Behavior attribute recommendation value; first generation module: configured to execute storing the recommendation information of the behavior recommendation value mapping that meets the first preset condition in the recommendation list in the order of the behavior attribute recommendation value size.
- a third acquisition module configured to perform acquisition of historical behavior logs to which account information is mapped within a preset time period
- a reading module configured to perform reading of historical behavior logs Behavior attribute label of each piece of information and count the number of information in the same behavior attribute label
- the first calculation module configured to perform calculation according to the number of the behavior attribute label to obtain the characterization degree of the information in the behavior attribute label Behavior attribute recommendation value
- the method further includes: a fourth obtaining module: configured to perform obtaining the first weight value of the behavior attribute label; a second calculating module: configured to perform according to the first weight value and the behavior attribute label The product of the quantity values gives the recommended value of the behavior attribute.
- the recommendation list further includes a set of predicted user preference information listed according to the user's personal attribute information, and further includes: a matching module: configured to perform matching of the user's identity attribute tag through the user's account information and obtain The recommended value of the identity attribute of the recommended information mapped by the identity attribute tag; storing the information mapped by the second generation module: configured to execute the identity attribute tag that meets the second preset condition in the recommendation list.
- the second preset condition includes that the recommended values of the identity attributes are sorted within a preset range in descending order.
- a fifth acquisition module configured to perform acquisition of a second weight value characterizing the behavior attribute label set and a third weight value characterizing the identity attribute set label
- a third calculation module configured to perform calculation of the The product of the second weight value and the behavior attribute recommendation value obtains the first recommendation value; at the same time, the product of the third weight value and the identity attribute recommendation value is calculated to obtain the second recommendation value
- the third generation module is configured to perform The first recommendation value and the second recommendation value are sorted in size and list corresponding information to form a recommendation list.
- the above-mentioned big data-based information pushing device is a module corresponding to the big data information pushing method, and each functional module executes the corresponding big data information pushing method, and the specific function implementation method is also the same, which is no longer the most familiar here.
- the present application also discloses a computer device including a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor is caused to perform any of the above The push method based on big data information.
- FIG. 8 for a block diagram of the basic structure of a computer device provided by an embodiment of this application.
- the computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected through a system bus.
- the non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions.
- the database may store a sequence of control information.
- the processor may implement a A push method based on big data information.
- the processor of the computer device is used to provide computing and control capabilities, and support the operation of the entire computer device.
- the memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may cause the processor to execute a method based on big data information push.
- the network interface of the computer device is used to connect and communicate with the terminal.
- FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or less components than shown in the figure, or combine certain components, or have a different arrangement of components.
- the computer device receives status information of the prompting behavior sent by the associated client, that is, whether the associated terminal enables the prompting and whether the account information closes the prompting task. By verifying whether the above task conditions are met, and then sending a corresponding preset instruction to the associated terminal, so that the associated terminal can perform corresponding operations according to the preset instruction, thereby achieving effective supervision of the associated terminal.
- the server controls the associated terminal to continue ringing to prevent the prompting task of the associated terminal from automatically ending after a period of time.
- the present application also provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform any of the foregoing embodiments based on big data Information push method method.
- the computer program may be stored in a computer-readable storage medium, When executed, it may include the processes of the foregoing method embodiments.
- the aforementioned storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.
- steps in the flowchart of the drawings are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order limitation for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the order of execution is also It is not necessarily carried out sequentially, but may be executed in turn or alternately with at least a part of other steps or sub-steps or stages of other steps.
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
本申请揭示了一种基于大数据信息推送方法、装置、计算机设备及存储介质。所述方法包括:获取目标终端的第一位置信息和推荐列表,推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在推荐列表中筛选出推荐信息所属的第二位置信息与第一位置信息在预设距离范围内的推荐信息作为预推送信息;将预推送信息推送至目标终端中显示。通过监控目标终端第一位置信息,从符合用户兴趣和需求的推荐列表中获取推送信息所属的第二位置信息,获取第二位置信息与第一位置信息的差值在预设距离范围内的推荐信息,并及时对用户对应的账户信息进行推送,以便于用户及时获取可能马上会用到的相关信息。
Description
本申请要求于2018年10月15日提交中国专利局、申请号为201811198424.8,发明名称为“基于大数据信息推送方法、装置、计算机设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及信息推送技术领域,具体而言,本申请涉及一种基于大数据信息推送方法、装置、计算机设备及存储介质。
随着互联网的发展,电子商务平台因其智能、便捷等优势成为主流的媒介,拥有大量的客户资源与信息。目前无论在网页阅读或者购买平台,都实现了根据客户的浏览内容进行喜好推荐,以便于节省客户的产品挑选时间。
但是发明人发现推荐的基础在于客户以往的浏览数据,通常是根据最近一段时间浏览的数据进行推荐,且数据的采集通常是在某一特定场景和领域,不适用于多个应用场景,推荐方式仅限于线上的产品推送,适用场景和范围有限。
发明内容
本申请的目的旨在至少能解决上述的技术缺陷之一,公开一种基于大数据信息推送方法、装置、计算机设备及存储介质,能够准确根据用户的身份属性和行为数据获取推荐列表,同时根据用户当前的位置信息,在推荐列表中选取符合当前位置信息的推荐信息进行推送,以满足用户当前的需求。
为了达到上述目的,本申请公开一种基于大数据信息推送方法,包括:获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;将所述预推送信息推送至所述目标终端中显示。
本申请还公开一种基于大数据信息推送装置,包括:第一获取模块:被配置为执行获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上的账户信息所映射的历史行为数据统计得到的推荐信息的集合;第一处理模块:被配置为执行在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;第一执行模块:被配置为执行将所述预推送信息推送至所述目标终端中显示。
本申请还公开一种计算机设备,包括存储器和处理器,所述存储器中存储有计算机可读指令,所述计算机可读指令被所述处理器执行时,使得所述处理器执行一种基于大数据信息推送方法的下述步骤:获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;将所述预推送信息推送至所述目标终端中显示。
本申请还公开一种存储有计算机可读指令的存储介质,所述计算机可读指令被一个或多个处理器执行时,使得一个或多个处理器执行一种基于大数据信息推送方法的下述步骤:获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;将所述预推送信息推送至所述目标终端中显示。
本申请实施例通过监控目标终端第一位置信息,从符合用户兴趣和需求的推荐列表中获取推送信息所属的第二位置信息,获取第二位置信息与第一位置信息的差值在预设距离范围内的推荐信息,并及时对用户对应的账户信息进行推送,以便于用户及时获取可能马上会用到的相关信息;另一实施例中,采用推荐值排序的方法,获取推荐信息对于用户的感兴趣程度,并根据这种推荐值的排序对用户进行推送,以便于确保推送的信息是用户所喜好的。
本申请附加的方面和优点将在下面的描述中部分给出,这些将从下面的描述中变得明显,或通过本申请的实践了解到。
本申请上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解,其中:
图1为本申请基于大数据信息推送方法总流程图;
图2为本申请第一实施例中推荐列表获取方法流程图;
图3为本申请行为属性推荐值获取方法流程图;
图4为本申请基于个人属性罗列的推荐列表方法流程图;
图5为本申请第二实施例中推荐列表获取方法流程图;
图6为本申请预推送信息推送方法流程图;
图7为本申请基于大数据信息推送装置模块框图;
图8为本申请计算机设备基本结构框图。
下面详细描述本申请的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,仅用于解释本申请,而不能解释为对本申请的限制。
本技术领域技术人员可以理解,除非特意声明,这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。应该进一步理解的是,本申请的说明书中使用的措辞“包括”是指存在所述特征、整数、步骤、操作、元件和/或组件,但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元件、组件和/或它们的组。应该理解,当我们称元件被“连接”或“耦接”到另一元件时,它可以直接连接或耦接到其他元件,或者也可以存在中间元件。此外,这里使用的“连接”或“耦接”可以包括无线连接或无线耦接。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的全部或任一单元和全部组合。
本技术领域技术人员可以理解,除非另外定义,这里使用的所有术语(包括技术术语和科学术语),具有与本申请所属领域中的普通技术人员的一般理解相同的意义。还应该理解的是,诸如通用字典中定义的那些术语,应该被理解为具有与现有技术的上下文中的意义一致的意义,并且除非像这里一样被特定定义,否则不会用理想化或过于正式的含义来解释。
本技术领域技术人员可以理解,这里所使用的“终端”、“终端设备”既包括无线信号接收器的设备,其仅具备无发射能力的无线信号接收器的设备,又包括接收和发射硬件的设备,其具有能够在双向通信链路上,执行双向通信的接收和发射硬件的设备。这种设备可以包括:蜂窝或其他通信设备,其具有单线路显示器或多线路显示器或没有多线路显示器的蜂窝或其他通信设备;PCS(Personal Communications Service,个人通信系统),其可以组合语音、数据处理、传真和/或数据通信能力;PDA(Personal Digital Assistant
,个人数字助理),其可以包括射频接收器、寻呼机、互联网/内联网访问、网络浏览器、记事本、日历和/或GPS(Global Positioning System,全球定位系统)接收器;常规膝上型和/或掌上型计算机或其他设备,其具有和/或包括射频接收器的常规膝上型和/或掌上型计算机或其他设备。这里所使用的“终端”、“终端设备”可以是便携式、可运输、安 装在交通工具(航空、海运和/或陆地)中的,或者适合于和/或配置为在本地运行,和/或以分布形式,运行在地球和/或空间的任何其他位置运行。这里所使用的“终端”、“终端设备”还可以是通信终端、上网终端、音乐/视频播放终端,例如可以是PDA、MID(Mobile Internet Device,移动互联网设备)和/或具有音乐/视频播放功能的移动电话,也可以是智能电视、机顶盒等设备。
本申请公开一种基于大数据信息推送方法,具体的,请参阅图1,主要包括以下步骤:
S1000、获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;
目标终端为登陆有用户的账号信息的终端设备,为手机、平板、电子手环、计算机等设备,而优选的为一种可移动的智能终端。智能终端连接网络,即可通过IP地址获得当前的位置信息,此处定义为第一位置信息,或者通过智能终端上的GPS定位信息得到目标终端的当前位置信息。
历史行为数据为在当前时间节点之前的行为数据,可以利用API(Application Programming Interface)接口从网络侧采集账户信息所映射的行为数据,具体的,可以利用API获取到终端设备中的浏览器开始向网络设备上报行为数据之前,用户通过其账户信息执行网络访问所产生并存储在网络侧的行为数据。
推荐列表包括登陆目标终端上的账户信息所映射的历史行为数据统计得到的推荐信息的集合。历史行为数据在本申请中可以为该账户信息在终端上执行网页浏览、评论、购买物件、收藏、点赞等动作而记录的相关数据,通过这些操作以及操作的次数,可推测出用户可能感兴趣的信息的类型,并将这种可能感兴趣的同类信息定义为推荐信息,按照某一种规则,将这种推荐信息组合在一起形成推荐列表。在一实施例中,请参阅图2,推荐列表的获取方法包括:
S1100、获取所述账户账户信息在某一预设时间段内所映射的历史行为日志;
为了便于统计,在选取历史行为数据时通常会指定某一个时间段内的数据为有效数据,采集这个时间段内的数据作为目标数据进行分析,这个预设时间段可以是一周、一个季度、半年、一年等。
在另一实施例中,还可将这种预设时间按照一定的规则进行获取,比如对于在一定时间内,活跃度较高的,选取时间间隔较短的时间段作为预设时间段,对于活跃度较低的,则选取较长的时间段作为预设时间段,比如账户信息A,一年内登陆过账户2次,浏览数量不超过10条,则可对该账户信息A收集历史数据的预设时 间段延长至两年,甚至更长,若账户信息B每天都会登入浏览,则可将预设时间段设置为最近的半年,并获取在近半年内的历史行为日志。历史行为日志为记载有账户信息每一个操作的数据的集合,通常按照时间轴方式进行记录。
S1200、读取所述历史行为日志中每条信息的行为属性标签并统计同一行为属性标签中信息的数量;
行为属性标签为为了区分行为的类型或者行为所属的类别设定的归类信息,比如浏览、评论、购买物件、收藏、点赞等为行为的类型,而执行上述动作对应的页面内容会映射不同的类别,比如生活用品类、理财保险类、服装类、化妆品类等等。对于不同页面内容属性标签还可进一步设置多个子标签,比如在理财保险类属性标签下面,还可包括基金标签、保险标签、股票标签等等,而在具体的子标签下面还可设置下一级子标签,比如保险标签下面,还可以设置人寿保险、财产保险、疾病保险等等,不仅如此,还可继续进一步细分,直至到具体的产品名称和该产品下面的批次等等。
按照上述属性标签,可对每一款产品进行归类,从而便于采集具体的数据,根据具体的行为属性标签,可获取在预设时间段内对应每一个行为属性标签中信息的数量,比如在理财保险类行为属性标签中的总浏览信息数量、总收藏数量、总点赞数量等,以及具体的对应的基金标签中的浏览数量、保险标签中的浏览数量、股票标签中的浏览数量等。
S1300、依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值;
行为属性推荐值为根据历史行为痕迹统计得到的,通常会根据在预设时间段内在历史行为数据中出现的频次,或者账户信息所对应的用户操作对应的类型来进行统计,比如,用户操作类型为“收藏”或者“关注”,则表示用户对该属性标签对应的内容比较受关注,而只是简单的浏览则表示用户只是稍微了解了下相关的内容;用户对同一类型的内容关注的数量越多,则表示用户对该类型比较感兴趣,根据上述规则,可判断出用户关注感兴趣的点在哪里,对符合用户感兴趣或关注的同类型的内容其推荐值就越高。
比如用户登陆其账户信息浏览过基金类别、股票类别和保险类别三种属性标签的内容,而股票类别只有浏览的操作,基金类别有收藏过5篇文章,且购买过2个,而保险类收藏了的10篇,购买了5次,则可以从上述数据中了解到用户对保险类产品更为关注,且购买的可能性更大,基金类产品是继保险类产品之后关注的内容, 此时推荐值最高的是保险类产品,第二高的是基金类产品,而股票类型排在后面。
在一实施例中,请参阅图3,所述依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为推荐值的方法包括:
S1310、获取所述行为属性标签的第一权重值;
权重值表示该类别的行为属性标签的比重值,在上述步骤提到了,不同的用户操作类型其表示的含义不一样的,比如用户操作类型为“收藏”或者“关注”,则表示用户对该属性标签对应的内容比较受关注,而只是简单的浏览则表示用户只是稍微了解了下相关的内容;因此可将用户“收藏”对应的内容信息所映射的行为属性标签权重值设置为较高值,而“浏览”对应的内容信息所映射的行为属性标签权重值设置为低值。
通过上述步骤中读取了历史行为日志,则可获取用户针对某一信息执行的类别以及所述的行为属性标签,故因此得到该信息的第一权重值。
S1320、根据所述第一权重值与所述行为属性标签的数量值的乘积得到行为属性推荐值。
根据步骤S1310步骤获取了行为属性标签的第一权重值之后,还需进一步获取同一种行为属性标签的数量值,以此得到行为属性推荐值,在一实施例中国年,行为属性推荐值A的获取方法通过以下公式获得:
A=KX
其中,A为行为属性推荐值,K为第一权重值,X为对应该权重值的属性行为标签信息的数量值;比如设置收藏的权重值为0.9,账户信息收藏了保险类产品的数量为10,则该保险类产品的推荐值为0.9*10=9。
进一步的,同一行为属性标签所对应的类型不局限于一种,还可以有多种,比如还包括浏览和关注等,此时,推荐值A的获取方法通过以下公式获得:
A=(K1X1+K2X2+K3X3……KnXn)/n
其中,n表示行为属性标签的操作类型的数量值。例如,定义“浏览”类型的权重值为0.2,“关注”类型的权重值为0.6,账户信息共浏览了30篇保险类产品,关注了5篇保险类产品,则保险类产品的总推荐值为账户信息收藏的推荐值与“浏览”的推荐值以及“关注”的权重值之和除以总的操作类型的数量,即为(0.9*10+0.2*30+0.6*5)/3=9。
S1400、按照推荐值大小的顺序将符合第一预设条件的所述行为推荐值映射的推荐信息存储在推荐列表中。
根据步骤S1300得到对应的行为属性推荐值后,行为属性推荐值越大,表示该信息的类型是用户最喜欢的,故可按照行为属性推荐值的大小进行排序。在一实施例中,为了统一管理,设定第一预设条件,将满足第一预设条件的行为属性推荐值所映射的推荐信息存储在推荐列表中。第一预设条件,可以为行为属性推荐值排序在某一阈值范围内的,比如行为属性推荐值排序在前10的信息存储在推荐列表中以供对账户信息进行推送,以此方法,确保向账户信息推送的产品为用户喜欢的。
S2000、在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;
第二位置信息为所述推荐信息所属的位置信息,比如当信息为关于店铺的优惠券信息时,则第二位置信息为该店铺的位置。当该店铺有多个分店时,且多个分店都可以使用这个优惠券时,则将符合该优惠券的所有第二位置信息都作为备选的地址信息,与目标终端的第一位置信息进行匹配。选取符合预设距离范围内的推荐信息作为预推送信息。
S3000、将所述预推送信息推送至所述目标终端中显示。
根据上述步骤获取了预推送信息后,则将选取的预推送信息推送至所述目标终端中进行显示。
需要说明的是,推送的方式有多种,一种可行的方式是,按照上述匹配的距离,选取距离最近的预推送信息进行推送,或者距离排名在一定阈值范围内,比如距离最近的前3条预推送信息依次进行推送。另一种为根据在预设范围内的预推送信息的推荐值的排名,将排名最靠前或者排名在某一范围内的信息进行推送。以上只是公开的几种推送显示的方式,但是不局限于以上几种,还可以是其他的推送选取方法。
进一步为了增加准确性,还可将行为属性推荐值结合其他的推荐值得到一个更为精准的推荐排名信息,比如结合账户信息的个人属性信息。因此,在一实施例中,推荐列表还包括根据用户个人属性信息所罗列的预测用户喜好的信息的集合,请参阅图4,所述根据用户个人属性信息所罗列的预测用户喜好的信息的集合的获取方法包括:
S1500、通过用户的账户信息匹配用户的身份属性标签,并获取所述身份属性标签所映射的推荐信息的身份属性推荐值;
身份属性标签为表征用户个人身份的标签,比如用户的年龄阶段,用户的性别、家庭情况,投资风险等级等,这些信息可以直接从用户在开通账号时填写的用户信 息获得,也可以是通过管理该用户的账户信息的业务人员手动录入相关标签而获得。
本申请中,将身份属性标签分成多个不同的类别,按照不同的类别,分别映射不同的推荐信息,比如,将身份属性标签分成年龄类、性别类、、家庭状况类、个人喜好和投资风险等级多个大类,年龄类分成30岁以下,31-45岁、46-65岁和65岁以上等多个小类,性别类分成男、女两个小类,家庭状况分成已婚、未婚、小孩2个以下,小孩3个及以上等多个小类,投资风险等级包括低风险、一般风险和高风险等多个小类,个人喜好包括运动类、购物类、餐饮类等多个小类,每个小类都映射有符合该小类的人员的推荐信息,需要说明的是,每个小类所映射的推荐信息可以是业务人员根据业务需求录入的相关推荐信息,还可以是根据符合上述身份属性标签的用户的历史行为数据统计出来的符合用户需求或者用户可能感兴趣的信息。
进一步的,在获取到基于身份属性标签所映射的推荐信息后,还可同时获取该推荐信息对应的身份属性推荐值,所述推荐值可以是在推荐信息的录入是赋予的值,当基于身份属性标签的推荐信息来自于不同分类的账户信息的历史行为数据获得时,其身份属性推荐值的获取方法也可按照上述步骤S1300的方法一样。
S1600、获取符合第二预设条件的身份属性标签所映射的信息存储在推荐列表中。
在步骤S1500中公开了与身份属性标签所映射的信息的获取方法,故,但是与身份属性标签所映射的信息有很多,需要按照一定的规则进行选取,本申请中将符合第二预设条件的身份属性标签所映射的信息存储在推荐列表中,所述第二预设条件包括所述身份属性推荐值按照从高到低的顺序排序在预设范围值内。比如,按照身份属性推荐值的排序在前10的推荐信息列入推荐列表中,进一步的,还可以是身份属性推荐值的大小在预设范围之类,比如在身份属性推荐值大于9所对应的推荐信息列入到推荐列表中。
需要说明的是,当没有设置身份属性标签的,账户信息的推荐列表的获取方法由步骤S1100-S1400获得,但是,当存在身份属性标签时,则需要将历史行为数据获取的推荐列表与身份属性获得的推荐列表结合得到汇总后的推荐列表,具体的,请参阅图5,汇总后的推荐列表的获取方法包括:
S1700、获取表征行为属性标签集合的第二权重值和表征身份属性集合标签的第三权重值;
当需要两种方式结合起来获取推荐列表时,可按照一定的规则对上述两种类别的推荐信息进行整合。本申请中,分别对属性标签集合的推荐信息设置一个第二权重值,对身份属性集合的推荐信息设置一个第三权重值,依次来区分二者的比重值,在一实施例中,有与行为属性标签集合内的推荐信息是通过在预设时间段内用户自己的操作行为获取的,相对而言能够更准确地反映用户的喜好,而身份属性集合内的推荐信息是只是根据业务的需求,或者根据满足某一身份特性的人群的喜好趋势获取的预设该用户的喜好的推荐信息,故可将行为属性标签集合的第二权重值赋予较高值,而身份属性集合标签的第三权重值赋予较低值,依次有限获取行为属性标签中的数据。
S1800、计算所述第二权重值与行为推荐值之积得到第一推荐值;同时计算所述第三权重值与所述身份属性推荐值之积得到第二推荐值;
在步骤S1320中公开了行为属性推荐A的获取方法,为:
A=(K1X1+K2X2+K3X3……KnXn)/n
其中,A为行为属性推荐值,K为第一权重值,X为对应该权重值的属性行为标签信息的数量值;n表示行为属性标签的操作类型的数量值。
定义身份属性推荐值为B,定义第二权重值而T,定义第三权重值为S,定义行为属性总喜好程度的第一推荐值为M定义身份属性总喜好程度的第二推荐值为N,则:
M=TA=T[(K1X1+K2X2+K3X3……KnXn)/n]
N=SB。
S1900、根据第一推荐值与第二推荐值的大小排序并罗列对应的信息形成推荐列表。
根据上述步骤S1800的方法获得了第一推荐值M和第二推荐值N的大小后,则可根据第一推荐值与第二推荐值的大小排序罗列对应的推荐信息以形成推荐列表。
进一步的,在另一实施例中,基于上述多种情况下的推荐列表,在执行步骤S2000中,需要将获取的第二位置信息与第一位置信息进行匹配,以选取符合预设距离范围内的推荐信息作为预推送信息,具体的,进行匹配的方法为判断第一位置信息与第二位置信息是否在预设距离范围内,比如,预设距离范围为500米时,则在推荐列表中,选取第二位置信息与第一位置信息在500米范围内的推荐信息作为与预推送信息进行推送。
但是,当在与预设距离范围内的推荐信息较多时,还需要按照一定的规则来确 定所述预推送信息如何进行推送。因此,在本申请的一实施例中,在最终将预推送信息推送至所述目标终端中之前,请参阅图6,还包括以下步骤:
S2100、获取所述预推送信息的推荐值;所述推荐值为表征所述预推送信息的喜好程度的数值;
根据上述步骤S1000计算得到了每条推荐信息的推荐值,故在本步骤中,获取预推送信息的推荐值。
S2200、将所述推荐值在预设阈值范围内的预推送信息作为目标信息;
预设阈值为关于推荐值选取的一种范围条件,在一实施例中,预设阈值为预推送信息的推荐值的排序在某一范围内,比如按照推荐值从大到小排序,选取排名在前10的作为目标信息。所述目标信息为被选中的用于对用户的账户信息所登陆的目标终端进行推送的信息。
在另一实施例中,预设阈值还可以为推荐值的大小在某一个值以内,比如选取的预设阈值为10,则将推荐值大于10的预推送信息作为目标信息。以上只是本申请公开的几种预设阈值的选取方法,但是本申请的阈值选取方法不局限于以上几种,只要能够采对推荐值进行选取的方法都纳入本申请的保护范围。
S2300、将所述目标信息发送至所述目标终端中显示。
根据上述步骤获取了目标信息后,则将上述目标信息发送至所述目标终端中进行显示。
本申请还公开一种基于大数据信息推送装置,其模块框图如图7,包括:
第一获取模块1000:被配置为执行获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;
目标终端为登陆有账户信息的终端设备,为手机、平板、电子手环、计算机等设备,而优选的为一种可移动的智能终端。智能终端连接网络,即可通过IP地址获得当前的位置信息,此处定义为第一位置信息,或者通过智能终端上的GPS定位信息得到目标终端的当前位置信息。
历史行为数据为在当前时间节点之前的行为数据,可以利用API(Application Programming Inerface)接口从网络侧采集用户的行为数据,具体的,可以利用API获取到终端设备中的浏览器开始向网络设备上报行为数据之前,用户执行网络访问所产生并存储在网络侧的行为数据。
推荐列表包括登陆目标终端上的账户信息所映射的历史行为数据统计得到的 推荐信息的集合。历史行为数据在本申请中可以为该账户信息在终端上执行网页浏览、评论、购买物件、收藏、点赞等动作而记录的相关数据,通过这些操作以及操作的次数,可推测出用户可能感兴趣的信息的类型,并将这种可能感兴趣的同类信息定义为推荐信息,按照某一种规则,将这种推荐信息组合在一起形成推荐列表。
第一处理模块2000:被配置为执行在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;
第二位置信息为所述推荐信息所属的位置信息,比如当信息为关于店铺的优惠券信息时,则第二位置信息为该店铺的位置。当该店铺有多个分店时,且多个分店都可以使用这个优惠券时,则将符合该优惠券的所有第二位置信息都作为备选的地址信息,与目标终端的第一位置信息进行匹配。选取符合预设距离范围内的推荐信息作为预推送信息。
第一执行模块3000:被配置为执行将所述预推送信息推送至所述目标终端中显示。
根据上述步骤获取了预推送信息后,则将选取的预推送信息推送至所述目标终端中进行显示。
需要说明的是,推送的方式有多种,一种可行的方式是,按照上述匹配的距离,选取距离最近的预推送信息进行推送,或者距离排名在一定阈值范围内,比如距离最近的前3条预推送信息依次进行推送。另一种为根据在预设范围内的预推送信息的推荐值的排名,将排名最靠前或者排名在某一范围内的信息进行推送。以上只是公开的几种推送显示的方式,但是不局限于以上几种,还可以是其他的推送选取方法。
进一步,本申请还包括:第二获取模块:被配置为执行获取所述预推送信息的行为属性推荐值;所述行为属性推荐值为表征所述预推送信息的喜好程度的数值;第二处理模块:被配置为执行将所述行为属性推荐值在预设阈值范围内的预推送信息作为目标信息;第二执行模块:被配置为执行将所述目标信息发送至所述目标终端中显示。
优选的,本申请还包括:第三获取模块:被配置为执行获取账户信息在某一预设时间段内所映射的历史行为日志;读取模块:被配置为执行读取所述历史行为日志中每条信息的行为属性标签并统计同一行为属性标签中信息的数量;第一计算模块:被配置为执行依据所述行为属性标签的数量计算得到表征该行为属性标签内的 信息的喜好程度的行为属性推荐值;第一生成模块:被配置为执行按照行为属性推荐值大小的顺序将符合第一预设条件的所述行为推荐值映射的推荐信息存储在推荐列表中。
优选的,还包括:第四获取模块:被配置为执行获取所述行为属性标签的第一权重值;第二计算模块:被配置为执行根据所述第一权重值与所述行为属性标签的数量值的乘积得到行为属性推荐值。优选的,所述推荐列表还包括根据用户个人属性信息所罗列的预测用户喜好的信息的集合,还包括:匹配模块:被配置为执行对通过用户的账户信息匹配用户的身份属性标签,并获取所述身份属性标签所映射的推荐信息的身份属性推荐值;将第二生成模块:被配置为执行符合第二预设条件的身份属性标签所映射的信息存储在推荐列表中。
优选的,所述第二预设条件包括所述身份属性推荐值按照从高到低的顺序排序在预设范围值内。
优选的,还包括:第五获取模块:被配置为执行获取表征行为属性标签集合的第二权重值和表征身份属性集合标签的第三权重值;第三计算模块:被配置为执行计算所述第二权重值与行为属性推荐值之积得到第一推荐值;同时计算所述第三权重值与所述身份属性推荐值之积得到第二推荐值;第三生成模块:被配置为执行根据第一推荐值与第二推荐值的大小排序并罗列对应的信息形成推荐列表。
上述基于大数据信息推送装置是基于大数据信息推送方法所对应的模块,每一个功能模块执行对应的大数据信息推送方法,具体的功能实现方式也一样,此处不再最熟。
本申请还公开一种计算机设备,包括存储器和处理器,所述存储器中存储有计算机可读指令,所述计算机可读指令被所述处理器执行时,使得所述处理器执行上述任意一项所述基于大数据信息推送方法。
本申请实施例提供计算机设备基本结构框图请参阅图8。
该计算机设备包括通过系统总线连接的处理器、非易失性存储介质、存储器和网络接口。其中,该计算机设备的非易失性存储介质存储有操作系统、数据库和计算机可读指令,数据库中可存储有控件信息序列,该计算机可读指令被处理器执行时,可使得处理器实现一种基于大数据信息推送方法。该计算机设备的处理器用于提供计算和控制能力,支撑整个计算机设备的运行。该计算机设备的存储器中可存储有计算机可读指令,该计算机可读指令被处理器执行时,可使得处理器执行一种基于大数据信息推送方法。该计算机设备的网络接口用于与终端连接通信。本领域 技术人员可以理解,图8中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的计算机设备的限定,具体的计算机设备可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
计算机设备通过接收关联的客户端发送的提示行为的状态信息,即关联终端是否开启提示以及账户信息是否关闭该提示任务。通过验证上述任务条件是否达成,进而向关联终端发送对应的预设指令,以使关联终端能够根据该预设指令执行相应的操作,从而实现了对关联终端的有效监管。同时,在提示信息状态与预设的状态指令不相同时,服务器端控制关联终端持续进行响铃,以防止关联终端的提示任务在执行一段时间后自动终止的问题。
本申请还提供一种存储有计算机可读指令的存储介质,所述计算机可读指令被一个或多个处理器执行时,使得一个或多个处理器执行上述任一实施例所述基于大数据信息推送方法的方法。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机程序来指令相关的硬件来完成,该计算机程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,前述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)等非易失性存储介质,或随机存储记忆体(Random Access Memory,RAM)等。
应该理解的是,虽然附图的流程图中的各个步骤按照箭头的指示依次显示,但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,其可以以其他的顺序执行。而且,附图的流程图中的至少一部分步骤可以包括多个子步骤或者多个阶段,这些子步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,其执行顺序也不必然是依次进行,而是可以与其他步骤或者其他步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
以上所述仅是本申请的部分实施方式,应当指出,对于本技术领域的普通技术人员来说,在不脱离本申请原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本申请的保护范围。
Claims (20)
- 一种基于大数据信息推送方法,包括:获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;将所述预推送信息推送至所述目标终端中显示。
- 根据权利要求1所述的基于大数据信息推送方法,所述将所述预推送信息推送至所述目标终端中显示还包括:获取所述预推送信息的行为属性推荐值;所述行为属性推荐值为表征所述预推送信息的喜好程度的数值;将所述行为属性推荐值在预设阈值范围内的预推送信息作为目标信息;将所述目标信息发送至所述目标终端中显示。
- 根据权利要求2所述的基于大数据信息推送方法,所述推荐列表的获取方法包括:获取所述账户信息在某一预设时间段内所映射的历史行为日志;读取所述历史行为日志中每条信息的行为属性标签并统计同一行为属性标签中信息的数量;依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值;按照行为属性推荐值大小的顺序将符合第一预设条件的所述行为推荐值映射的推荐信息存储在推荐列表中。
- 根据权利要求3所述的基于大数据信息推送方法,所述依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值的方法包括:获取所述行为属性标签的第一权重值;根据所述第一权重值与所述行为属性标签的数量值的乘积得到行为属性推荐值。
- 根据权利要求2所述的基于大数据信息推送方法,所述推荐列表还包括根据用户个人属性信息所罗列的预测用户喜好的信息的集合,所述根据用户个人属性信息所罗列的预测用户喜好的信息的集合获取方法包括:通过用户的账户信息匹配用户的身份属性标签,并获取所述身份属性标签所映射的推荐信息的身份属性推荐值;获取符合第二预设条件的身份属性标签所映射的信息存储在推荐列表中。
- 根据权利要求5所述的基于大数据信息推送方法,所述第二预设条件包括所述身份属性推荐值按照从高到低的顺序排序在预设范围值内。
- 根据权利要求5所述的基于大数据信息推送方法,所述推荐列表的获取方法还包括:获取表征行为属性标签集合的第二权重值和表征身份属性集合标签的第三权重值;计算所述第二权重值与行为属性推荐值之积得到第一推荐值;同时计算所述第三权重值与所述身份属性推荐值之积得到第二推荐值;根据第一推荐值与第二推荐值的大小排序并罗列对应的信息形成推荐列表。
- 一种基于大数据信息推送装置,包括:第一获取模块:被配置为执行获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上的账户信息所映射的历史行为数据统计得到的推荐信息的集合;第一处理模块:被配置为执行在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;第一执行模块:被配置为执行将所述预推送信息推送至所述目标终端中显示。
- 一种计算机设备,包括存储器和处理器,所述存储器中存储有计算机可读指令,所述计算机可读指令被所述处理器执行时,使得所述处理器执行一种基于大数据信息推送方法的下述步骤:获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;将所述预推送信息推送至所述目标终端中显示。
- 根据权利要求9所述的计算机设备,所述将所述预推送信息推送至所述目标终端中显示还包括:获取所述预推送信息的行为属性推荐值;所述行为属性推荐值为表征所述预推送信息的喜好程度的数值;将所述行为属性推荐值在预设阈值范围内的预推送信息作为目标信息;将所述目标信息发送至所述目标终端中显示。
- 根据权利要求10所述的计算机设备,所述推荐列表的获取方法包括:获取所述账户信息在某一预设时间段内所映射的历史行为日志;读取所述历史行为日志中每条信息的行为属性标签并统计同一行为属性标签中信息的数量;依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值;按照行为属性推荐值大小的顺序将符合第一预设条件的所述行为推荐值映射的推荐信息存储在推荐列表中。
- 根据权利要求11所述的计算机设备,所述依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值的方法包括:获取所述行为属性标签的第一权重值;根据所述第一权重值与所述行为属性标签的数量值的乘积得到行为属性推荐值。
- 根据权利要求10所述的计算机设备,所述推荐列表还包括根据用户个人属性信息所罗列的预测用户喜好的信息的集合,所述根据用户个人属性信息所罗列的预测用户喜好的信息的集合获取方法包括:通过用户的账户信息匹配用户的身份属性标签,并获取所述身份属性标签所映射的推荐信息的身份属性推荐值;获取符合第二预设条件的身份属性标签所映射的信息存储在推荐列表中。
- 根据权利要求13所述的计算机设备,所述第二预设条件包括所述身份属性推荐值按照从高到低的顺序排序在预设范围值内。
- 根据权利要求13所述的计算机设备,所述推荐列表的获取方法还包括:获取表征行为属性标签集合的第二权重值和表征身份属性集合标签的第三权重值;计算所述第二权重值与行为属性推荐值之积得到第一推荐值;同时计算所述第三权重值与所述身份属性推荐值之积得到第二推荐值;根据第一推荐值与第二推荐值的大小排序并罗列对应的信息形成推荐列表。
- 一种存储有计算机可读指令的非易失性存储介质,所述计算机可读指令被一个或多个处理器执行时,使得一个或多个处理器执行一种基于大数据信息推送方 法的下述步骤:获取目标终端的第一位置信息和推荐列表,所述推荐列表包括登陆目标终端上用户的账户信息所映射的历史行为数据统计得到的推荐信息的集合;在所述推荐列表中筛选出所述推荐信息所属的第二位置信息与所述第一位置信息在预设距离范围内的推荐信息作为预推送信息;将所述预推送信息推送至所述目标终端中显示。
- 根据权利要求16所述的非易失性存储介质,所述将所述预推送信息推送至所述目标终端中显示还包括:获取所述预推送信息的行为属性推荐值;所述行为属性推荐值为表征所述预推送信息的喜好程度的数值;将所述行为属性推荐值在预设阈值范围内的预推送信息作为目标信息;将所述目标信息发送至所述目标终端中显示。
- 根据权利要求17所述的非易失性存储介质,所述推荐列表的获取方法包括:获取所述账户信息在某一预设时间段内所映射的历史行为日志;读取所述历史行为日志中每条信息的行为属性标签并统计同一行为属性标签中信息的数量;依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值;按照行为属性推荐值大小的顺序将符合第一预设条件的所述行为推荐值映射的推荐信息存储在推荐列表中。
- 根据权利要求18所述的非易失性存储介质,所述依据所述行为属性标签的数量计算得到表征该行为属性标签内的信息的喜好程度的行为属性推荐值的方法包括:获取所述行为属性标签的第一权重值;根据所述第一权重值与所述行为属性标签的数量值的乘积得到行为属性推荐值。
- 根据权利要求17所述的非易失性存储介质,所述推荐列表还包括根据用户个人属性信息所罗列的预测用户喜好的信息的集合,所述根据用户个人属性信息所罗列的预测用户喜好的信息的集合获取方法包括:通过用户的账户信息匹配用户的身份属性标签,并获取所述身份属性标签所映射的推荐信息的身份属性推荐值;获取符合第二预设条件的身份属性标签所映射的信息存储在推荐列表中。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811198424.8A CN109582857A (zh) | 2018-10-15 | 2018-10-15 | 基于大数据信息推送方法、装置、计算机设备及存储介质 |
| CN201811198424.8 | 2018-10-15 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020077889A1 true WO2020077889A1 (zh) | 2020-04-23 |
Family
ID=65920052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/070365 Ceased WO2020077889A1 (zh) | 2018-10-15 | 2019-01-04 | 基于大数据信息推送方法、装置、计算机设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109582857A (zh) |
| WO (1) | WO2020077889A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116263924A (zh) * | 2021-12-14 | 2023-06-16 | 中国联合网络通信集团有限公司 | 基于区块链的物品获取方法和装置 |
Families Citing this family (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321475A (zh) * | 2019-05-22 | 2019-10-11 | 深圳壹账通智能科技有限公司 | 数据列表的排序方法、装置、设备及存储介质 |
| CN112241486A (zh) * | 2019-07-17 | 2021-01-19 | 北京达佳互联信息技术有限公司 | 多媒体信息获取方法及装置 |
| CN112241489B (zh) * | 2019-07-18 | 2024-02-06 | 腾讯科技(深圳)有限公司 | 信息推送方法、装置、可读存储介质和计算机设备 |
| CN112051744A (zh) * | 2019-08-15 | 2020-12-08 | 河南紫联物联网技术有限公司 | 智能终端、智能家居应用的推荐方法及系统 |
| CN110610257B (zh) * | 2019-08-15 | 2020-07-21 | 海南太美航空股份有限公司 | 一种航线信息排序方法、系统、存储介质及计算机设备 |
| CN110599255A (zh) * | 2019-09-18 | 2019-12-20 | 重庆动美网络科技有限公司 | 一种商铺信息的推送方法 |
| CN111026979A (zh) * | 2019-11-12 | 2020-04-17 | 恒大智慧科技有限公司 | 一种目标推荐方法及系统、计算机可读存储介质 |
| CN111260391B (zh) * | 2019-12-12 | 2021-09-07 | 上海钧正网络科技有限公司 | 广告推送方法、装置、计算机设备和可读存储介质 |
| CN111083229B (zh) * | 2019-12-24 | 2021-01-08 | 珠海大横琴科技发展有限公司 | 应用信息推送方法、装置、电子设备及存储介质 |
| CN111177563B (zh) * | 2019-12-31 | 2023-06-27 | 北京顺丰同城科技有限公司 | 一种信息推荐方法、装置、电子设备和存储介质 |
| CN111274474A (zh) * | 2020-01-16 | 2020-06-12 | 平安科技(深圳)有限公司 | 对象推荐方法、电子装置及计算机可读存储介质 |
| CN111476595A (zh) * | 2020-03-06 | 2020-07-31 | 深圳壹账通智能科技有限公司 | 产品推送方法、装置、计算机设备和存储介质 |
| CN112287227A (zh) * | 2020-03-20 | 2021-01-29 | 张明 | 在线学习推荐方法及在线学习系统 |
| CN111475719B (zh) * | 2020-03-30 | 2023-04-07 | 招商局金融科技有限公司 | 基于数据挖掘的信息推送方法、装置及存储介质 |
| CN111581518A (zh) * | 2020-05-14 | 2020-08-25 | 北京易数科技有限公司 | 信息推送方法和装置 |
| CN111639259B (zh) * | 2020-05-26 | 2023-11-03 | 上海鲸甲信息科技有限公司 | 基于特征识别的信息推送方法及装置 |
| CN111672130A (zh) * | 2020-06-03 | 2020-09-18 | 西安万像电子科技有限公司 | 游戏玩家的身份认证方法、认证装置和云游戏系统 |
| CN112037073B (zh) * | 2020-09-02 | 2024-01-26 | 中国银行股份有限公司 | 信息获取系统、方法及装置 |
| CN112036986A (zh) * | 2020-09-04 | 2020-12-04 | 烟台冰兔网络科技有限公司 | 一种网上商城的多渠道电商运营平台 |
| CN113158034A (zh) * | 2021-03-19 | 2021-07-23 | 深圳市航际科技有限公司 | 信息推送方法、装置、计算机设备和存储介质 |
| CN113034241B (zh) * | 2021-04-23 | 2024-06-11 | 中国平安人寿保险股份有限公司 | 一种产品信息推荐方法及计算机设备 |
| CN115269964A (zh) * | 2021-05-29 | 2022-11-01 | 广州市万隆证券咨询顾问有限公司 | 一种证券行业的个性化推荐方法、装置、设备及存储介质 |
| CN113392326A (zh) * | 2021-06-28 | 2021-09-14 | 上海明略人工智能(集团)有限公司 | 一种信息推送方法、装置、存储介质及电子设备 |
| CN113516538B (zh) * | 2021-07-28 | 2023-04-07 | 云南腾云信息产业有限公司 | 一种信息推送方法、装置及计算机设备 |
| CN114064987B (zh) * | 2021-10-22 | 2025-03-07 | 南方电网数字电网科技(广东)有限公司 | 基于加权的设备元件的型号的推荐方法、控制器及介质 |
| CN114168842A (zh) * | 2021-10-29 | 2022-03-11 | 中国建设银行股份有限公司 | 推荐方法、装置、电子设备及存储介质 |
| CN114385936A (zh) * | 2021-12-17 | 2022-04-22 | 北京达佳互联信息技术有限公司 | 媒体内容收藏列表的更新方法、装置、设备及存储介质 |
| CN114722301B (zh) * | 2022-06-09 | 2022-09-09 | 江西省精彩纵横采购咨询有限公司 | 一种招投标信息推荐方法、装置、存储介质及设备 |
| CN115511539A (zh) * | 2022-10-24 | 2022-12-23 | 平安银行股份有限公司 | 一种活动推送方法、装置、智能终端及存储介质 |
| CN116151910A (zh) * | 2022-11-25 | 2023-05-23 | 珠海格力电器股份有限公司 | 一种商品推荐方法、装置、存储介质及电子设备 |
| CN116304333A (zh) * | 2023-03-13 | 2023-06-23 | 浙江极氪智能科技有限公司 | 用户数据推荐方法、电子设备及计算机可读存储介质 |
| CN115982429B (zh) * | 2023-03-21 | 2023-08-01 | 中交第四航务工程勘察设计院有限公司 | 一种基于流程控制的知识管理方法及系统 |
| CN116668525A (zh) * | 2023-04-10 | 2023-08-29 | 无锡车联天下信息技术有限公司 | 一种车辆信息推送方法、装置、计算机设备及存储介质 |
| CN116955749A (zh) * | 2023-07-28 | 2023-10-27 | 中国第一汽车股份有限公司 | 信息的推送方法、装置和车辆 |
| CN117033803B (zh) * | 2023-10-10 | 2024-01-09 | 山东爱书人家庭教育科技有限公司 | 一种信息推荐方法、系统、装置及介质 |
| CN118827768B (zh) * | 2024-03-14 | 2025-11-21 | 中移物联网有限公司 | 信息推送方法、装置、设备、存储介质及程序产品 |
| CN118350839A (zh) * | 2024-04-27 | 2024-07-16 | 杭州及凌网络科技有限公司 | 一种基于大数据的汽车销售系统、模块以及方法 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100169153A1 (en) * | 2008-12-26 | 2010-07-01 | Microsoft Corporation | User-Adaptive Recommended Mobile Content |
| CN106408365A (zh) * | 2016-08-24 | 2017-02-15 | 潘重光 | 内容推荐方法及装置 |
| CN106534363A (zh) * | 2016-12-15 | 2017-03-22 | 安徽扬能电子科技有限公司 | 一种基于定位分析的车载智慧终端系统 |
| CN106657202A (zh) * | 2015-11-04 | 2017-05-10 | K11集团有限公司 | 一种智能推送信息的方法及系统 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609860A (zh) * | 2012-01-20 | 2012-07-25 | 彭立发 | 一种适用于电子商务的商品与信息分类推荐方法及系统 |
| WO2013138969A1 (en) * | 2012-03-17 | 2013-09-26 | Beijing Haipu Wangju Technology Limited | Method and system for recommending content to a user |
| CN107436893A (zh) * | 2016-05-26 | 2017-12-05 | 北京搜狗科技发展有限公司 | 一种网页推荐方法和装置 |
| CN106557039B (zh) * | 2016-11-09 | 2019-06-28 | 北京安云世纪科技有限公司 | 一种信息推荐方法及电子设备 |
| CN106909629B (zh) * | 2017-01-26 | 2020-05-19 | 武汉奇米网络科技有限公司 | 一种个性化推荐坑位标签的方法及系统 |
| CN106951515A (zh) * | 2017-03-17 | 2017-07-14 | 上海衡修信息科技有限公司 | 一种基于社交软件的联系人匹配方法及装置 |
| CN107766484B (zh) * | 2017-10-16 | 2020-09-29 | 南京师范大学 | 一种学习目标导向的知识链推荐方法 |
| CN108573428A (zh) * | 2018-03-07 | 2018-09-25 | 阿里巴巴集团控股有限公司 | 一种资源推荐方法和装置 |
-
2018
- 2018-10-15 CN CN201811198424.8A patent/CN109582857A/zh active Pending
-
2019
- 2019-01-04 WO PCT/CN2019/070365 patent/WO2020077889A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100169153A1 (en) * | 2008-12-26 | 2010-07-01 | Microsoft Corporation | User-Adaptive Recommended Mobile Content |
| CN106657202A (zh) * | 2015-11-04 | 2017-05-10 | K11集团有限公司 | 一种智能推送信息的方法及系统 |
| CN106408365A (zh) * | 2016-08-24 | 2017-02-15 | 潘重光 | 内容推荐方法及装置 |
| CN106534363A (zh) * | 2016-12-15 | 2017-03-22 | 安徽扬能电子科技有限公司 | 一种基于定位分析的车载智慧终端系统 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116263924A (zh) * | 2021-12-14 | 2023-06-16 | 中国联合网络通信集团有限公司 | 基于区块链的物品获取方法和装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109582857A (zh) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020077889A1 (zh) | 基于大数据信息推送方法、装置、计算机设备及存储介质 | |
| US12254503B2 (en) | Method and system for secure management of inventory and profile information | |
| US10467678B2 (en) | Context-influenced application recommendations | |
| US10423999B1 (en) | Performing personalized category-based product sorting | |
| US9460458B1 (en) | Methods and system of associating reviewable attributes with items | |
| US10032176B2 (en) | Real time statistics extraction from arbitrary advertising audiences | |
| US10769702B2 (en) | Recommendations based upon explicit user similarity | |
| CN119107114A (zh) | 一种基于电商小程序的商品品类推荐管理系统 | |
| US20130036012A1 (en) | Location-based service system | |
| CN108476334A (zh) | 广告投放的跨屏优化 | |
| US20200402129A1 (en) | Configuring food-related information search and retrieval based on a predictive quality indicator | |
| CN111242661A (zh) | 优惠券发放方法和装置以及计算机系统和介质 | |
| WO2015148835A1 (en) | Recommendation system for non-fungible assets | |
| US11216829B1 (en) | Providing online content | |
| CN110555753A (zh) | 基于推荐的排序控制方法、装置、计算机设备及存储介质 | |
| US9565078B1 (en) | Recommended content traffic exchange | |
| US20140032708A1 (en) | Providing online content | |
| US9959562B1 (en) | Method, medium, and system for local item fulfillment in a market hierarchy | |
| US8886799B1 (en) | Identifying a similar user identifier | |
| AU2010212344B2 (en) | Object customization and management system | |
| CN115860869A (zh) | 店铺信息推荐方法、设备及存储介质 | |
| US10530898B1 (en) | Serving a content item based on acceptance of a new feature | |
| US8849804B1 (en) | Distributing interest categories within a hierarchical classification | |
| US20240005340A1 (en) | Automatic identification and creation of affiliates | |
| US20150332343A1 (en) | Behavioral tracking system and method in support of high-engagement communications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19872816 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09.06.2021) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19872816 Country of ref document: EP Kind code of ref document: A1 |