WO2017045256A1 - 推荐方法、装置、设备及非易失性计算机存储介质 - Google Patents
推荐方法、装置、设备及非易失性计算机存储介质 Download PDFInfo
- Publication number
- WO2017045256A1 WO2017045256A1 PCT/CN2015/093570 CN2015093570W WO2017045256A1 WO 2017045256 A1 WO2017045256 A1 WO 2017045256A1 CN 2015093570 W CN2015093570 W CN 2015093570W WO 2017045256 A1 WO2017045256 A1 WO 2017045256A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- entity object
- route
- obtaining
- target entity
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Definitions
- the present disclosure relates to the field of Internet technologies, and in particular, to a recommended method, apparatus, device, and non-volatile computer storage medium.
- Information recommendation mainly relies on the Internet to recommend products, stores, resources and other information to users to help users efficiently find valuable information.
- aspects of the present disclosure provide a recommendation method, apparatus, device, and non-volatile computer storage medium for improving the pertinence and accuracy of information recommendation.
- a recommendation method including:
- the target entity object is recommended to the user.
- the obtaining potential needs of the user includes:
- the obtaining the route traveled by the user includes:
- the recommending the target entity object to the user includes:
- the target entity object is tagged to recommend the target entity object to the user.
- the obtaining, from the entity objects located in the specified range of the route, the target entity objects that meet the potential requirements of the user including:
- a recommendation apparatus including:
- An information acquisition module configured to acquire a potential demand of the user and a route that the user travels
- An object obtaining module configured to acquire, from an entity object located within a specified range of the route, a target entity object that meets a potential requirement of the user;
- a recommendation module for recommending the target entity object to the user.
- the information acquisition module is specifically configured to:
- the information acquisition module is specifically configured to:
- the recommendation module is specifically configured to:
- the target entity object is tagged to recommend the target entity object to the user.
- the object acquisition module is specifically configured to:
- an apparatus comprising:
- One or more processors are One or more processors;
- One or more programs the one or more programs being stored in the memory, When executed by the one or more processors:
- the target entity object is recommended to the user.
- a non-volatile computer storage medium storing one or more programs when the one or more programs are executed by one device causes The device:
- the target entity object is recommended to the user.
- the entity object that meets the potential needs of the user and within the specified range of the route traveled by the user is recommended to the user, and on the one hand, the recommendation is based on the potential needs of the user, and the user is recommended.
- the probability of the entity object of interest is high, and on the other hand, the entity object within the specified range of the route of the route is recommended to the user, so that the user can go to/acquire the recommended entity object, and the information recommendation is more targeted and accurate.
- FIG. 1 is a schematic flowchart diagram of a recommendation method according to an embodiment of the present disclosure
- FIG. 2 is a schematic diagram of an interface of a recommended target entity object according to an embodiment of the present disclosure
- FIG. 3 is a schematic structural diagram of a recommendation apparatus according to an embodiment of the present disclosure.
- FIG. 1 is a schematic flowchart diagram of a recommendation method according to an embodiment of the present disclosure. As shown in Figure 1, the method includes:
- This embodiment provides a recommendation method.
- the main principle is to recommend the entity object located within the specified range of the route traveled by the user in combination with the potential needs of the user and the route traveled by the user, so as to improve the pertinence and accuracy of the information recommendation. To improve the conversion benefits of recommendation information.
- the recommendation device acquires a potential requirement of the user and a route traveled by the user; determines an entity object located within a specified range of the route traveled by the user, and obtains, from the determined entity object, an entity object that meets a potential requirement of the user as a target entity. Object, recommend the item to the user Standard entity object.
- the method for obtaining the potential demand of the user may be: the recommendation device mines the search log in the specified time period of the user to obtain the potential demand of the user. Specifically, the recommendation device may obtain a search log within a specified time period of the user, for example, the search engine may be used to obtain a search log of the user within a specified time period; and then, the search log in the specified time period of the user may be mined to obtain the potential demand of the user. .
- the method for mining the search log may be: extracting a user's search term from the search log, sorting the search words according to the search frequency and search time of the extracted search words, and sorting according to the sorting.
- the top N search terms determine the potential needs of the user, and N is a natural number.
- the method for mining the search log may be: obtaining a page clicked by the user from the search log, determining a page that the user is more interested according to the number of clicks and time of the page, and a title of the page that is of interest to the user. And / or the body of the word processing, according to the result of the word to determine the potential needs of the user.
- the method for mining the search log may be: extracting a user's search term from the search log, and obtaining a page that the user clicks, combining the user's search term and the page that the user clicks to determine the potential demand of the user.
- the user frequently searches for restaurants, foods, and the like in the near future, and can determine that the user may need to have a meal with friends or family members in the near future.
- the user in addition to knowing that the user frequently searches for restaurants and foods according to the user's search words, the user can be determined according to the user's search words and the pages of interest to the user, and the user frequently searches for the mall, checks the prices and activities of the major clothing brands, and the like. In addition to gathering with friends or family members, you may need to shop.
- the length of the specified time period is not limited, for example, the distance may be current. Engraved for one hour, one day, two days, one week, two weeks, one month or even longer.
- the information is recommended to the user only according to the potential needs of the user, and the recommended information may be inconvenient or acquired by the user.
- the targeted and accurate information is poor, and the conversion rate of the recommended information is low. For example, usually the user goes to work on weekdays, the user company's location is at point A, and the user's home is at point B. If only the user's needs are recommended, the hotel may recommend the hotel or shopping mall that is relatively far away from point A and point B. The targeting and accuracy are poor. The user distance and time are not considered.
- the recommendation device acquires a route traveled by the user, and based on the route traveled by the user, recommends an entity object that meets the potential requirement of the user to the user, not only can satisfy the user requirement, but also the recommended entity object travels in the user.
- the route if the user really needs it, it will not be limited by factors such as time or distance. It can go to the destination or obtain the recommended entity object, which is beneficial to improve the conversion benefit brought by the recommendation information.
- the above route may include a route that the user travels daily, and/or a route that the user is traveling.
- the recommendation device may obtain a route that the user travels daily according to the historical location/navigation data of the user, for example, one or several routes that can be acquired most frequently as a route that the user travels daily, for example, may be a route from the home to the company. The route from home to the school where the child is located.
- the recommending device can obtain the route that the user is traveling according to the current positioning/navigation data of the user.
- the route that the user is traveling may be a route that the user travels daily, or may be a route that the user temporarily travels.
- the recommendation device may acquire historical positioning/navigation data or current positioning/navigation data of the user from various applications having positioning/navigation functions. For example, the recommendation device may obtain historical location/navigation data or current location/navigation data of the user from various map applications, navigation applications, or taxi applications, etc., to determine the route traveled by the user.
- the foregoing obtaining, from the entity object located within the specified range of the route traveled by the user, the target entity object that meets the potential requirement of the user includes: determining the demand expression word according to the potential demand of the user; The requirement expression word is matched in the description information of the entity object located within the specified range of the above route to obtain at least one entity object of the requirement expression word matching degree as the target entity object.
- the recommendation device may determine a requirement expression word capable of expressing the potential requirement according to a potential demand of the user. For example, if the user recently searches for hot pots and spicy hot pots, it can be determined that the user may want to eat hot pot, and the hot pot or spicy hot pot can be expressed as a user's demand. For another example, if the user recently searches for a bank, a cash machine, or the like, it is determined that the user may need to withdraw money, and the bank or the cash machine may be used as a user's demand expression.
- the recommending device determines an entity object located within a specified range of the route traveled by the user, and the entity object within the specified range may be a physical object whose vertical distance to the route is within the specified range, and the specified range may be 50 meters, 100 meters, 200 meters, 500 meters and so on.
- the physical objects may be various shopping malls, movie theaters, bus stations, subway stations, newsstands, and the like.
- the description information of the entity objects is obtained, and the description information includes the name, location, preferential activity, evaluation, and the like of the entity object.
- the recommendation device matches the user's requirement expression words in the description information of the entity objects, and acquires at least one entity object that matches the requirement expression word as the target entity object. For example, one or several entity objects with the highest degree of matching with the demand expression word can be obtained as the target entity object.
- the recommendation device may mark the target object entity that needs to be recommended to the user on the positioning/navigation interface to recommend the target entity object to the user.
- a way to mark the target entity object is shown in Figure 2.
- Shangdi Shijie can be the route that the user travels daily or the route that the user is traveling.
- the target entity object recommended to the user is located near the route traveled by the user and is likely to be an entity object required by the user.
- the recommendation information is highly targeted and accurate, and the user can conveniently go to these entity objects. It is beneficial to improve the conversion efficiency brought by the recommendation information, and meets the user's needs, and also achieves the purpose of recommending the entity object.
- FIG. 3 is a schematic structural diagram of a recommendation apparatus according to an embodiment of the present disclosure. As shown in FIG. 3, the apparatus includes: an information acquisition module 31, an object acquisition module 32, and a recommendation module 33.
- the information obtaining module 31 is configured to acquire a potential demand of the user and a route that the user travels.
- the object obtaining module 32 is configured to acquire, from the entity objects located in the route specification range acquired by the information acquiring module 31, the target entity object that meets the potential requirement of the user acquired by the information acquiring module 31.
- the recommendation module 33 is configured to recommend the target entity object acquired by the object acquisition module 32 to the user.
- the information acquiring module 31 when acquiring the potential demand of the user, is specifically configured to: mine the search log in the specified time period of the user to obtain the potential demand of the user.
- the information acquiring module 31 when acquiring the route traveled by the user, is specifically configured to: obtain a route that the user travels daily according to the historical location/navigation data of the user; and/or, according to the current positioning of the user/ Navigate the data to get the route the user is traveling.
- the recommendation module 33 is specifically configured to: mark the target entity object on the positioning/navigation interface to recommend the target entity object to the user.
- the object obtaining module 32 is specifically configured to:
- matching is performed in the description information of the entity object located within the specified range of the route, so as to obtain at least one entity object whose requirement expression words match as the target entity object.
- the recommendation device of this embodiment may be implemented as a client corresponding to each entity object, and is responsible for recommending the entity object to the user.
- the recommending device of the embodiment may also be implemented as a function module in the positioning/navigation application, implementing a combination of positioning/navigation and recommendation to recommend to the user according to the route traveled by the user to meet the user's needs and located near the route traveled by the user. Entity object.
- the recommending device of this embodiment can also be implemented as a functional module in a search engine. The combination of search and recommendation is now available.
- the recommendation device according to the potential demand of the user and the route traveled by the user, recommends the entity object that meets the potential demand of the user and is within the specified range of the route traveled by the user, and performs recommendation based on the potential demand of the user.
- the probability of recommending the entity object of interest to the user is high, and on the other hand, the entity object within the specified range of the route of the route is recommended to the user, so that the user can go to/acquire the recommended entity object, and the information recommendation is targeted and accurate. Higher sex.
- the disclosed system, apparatus, and method may be implemented in other manners.
- the device embodiments described above are merely illustrative.
- the division of the unit is only a logical function division.
- there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
- each functional unit in various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
- the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
- the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present disclosure. Part of the steps.
- the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
本公开提供一种推荐方法、装置、设备及非易失性计算机存储介质。方法包括：获取用户的潜在需求以及所述用户行进的路线；从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；向所述用户推荐所述目标实体对象。本公开结合用户的潜在需求及用户行进的路线，向用户推荐实体对象，有利于提高信息推荐的针对性和准确性。
Description
本申请要求了申请日为2015年09月14日、申请号为2015105822793、发明名称为“推荐方法及装置”的中国专利申请的优先权。
本公开涉及互联网技术领域，特别涉及一种推荐方法、装置、设备及非易失性计算机存储介质。
随着互联网技术的发展，信息推荐技术日益成熟。信息推荐主要是依赖于互联网向用户推荐商品、店铺、资源等信息，以帮助用户高效率地发掘有价值的信息。
在实际应用中，越来越多的服务提供方意识到信息推荐的优势，于是频频通过互联网向用户推荐各种优惠、促销等信息。现有信息推荐更多的是从服务提供方的角度出发，很少考虑用户的实际情况，例如用户是否有时间或者是否方便去往所推荐的地方，导致信息推荐的针对性和准确性较差。
发明内容
本公开的多个方面提供一种推荐方法、装置、设备及非易失性计算机存储介质，用以提高信息推荐的针对性和准确性。
本公开的一方面，提供一种推荐方法，包括：
获取用户的潜在需求以及所述用户行进的路线；
从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；
向所述用户推荐所述目标实体对象。
作为本公开的进一步改进，所述获取用户的潜在需求，包括：
对所述用户指定时段内的搜索日志进行挖掘，以获取所述用户的潜在需求。
作为本公开的进一步改进，所述获取所述用户行进的路线，包括：
根据所述用户的历史定位/导航数据，获取所述用户日常行进的路线；和/或
根据所述用户当前的定位/导航数据，获取所述用户正在行进的路线。
作为本公开的进一步改进，所述向所述用户推荐所述目标实体对象，包括：
在定位/导航界面上，对所述目标实体对象进行标记，以向所述用户推荐所述目标实体对象。
作为本公开的进一步改进，所述从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象，包括：
根据所述用户的潜在需求，确定需求表达词；
根据所述需求表达词，在位于所述路线指定范围内的实体对象的描述信息中进行匹配，以获取所述需求表达词相匹配的至少一个实体对象作为所述目标实体对象。
本公开的另一方面，提供一种推荐装置，包括：
信息获取模块，用于获取用户的潜在需求以及所述用户行进的路线；
对象获取模块，用于从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；
推荐模块，用于向所述用户推荐所述目标实体对象。
作为本公开的进一步改进，所述信息获取模块具体用于：
对所述用户指定时段内的搜索日志进行挖掘，以获取所述用户的潜在需求。
作为本公开的进一步改进，所述信息获取模块具体用于：
根据所述用户的历史定位/导航数据，获取所述用户日常行进的路线；和/或
根据所述用户当前的定位/导航数据，获取所述用户正在行进的路线。
作为本公开的进一步改进，所述推荐模块具体用于：
在定位/导航界面上，对所述目标实体对象进行标记，以向所述用户推荐所述目标实体对象。
作为本公开的进一步改进，所述对象获取模块具体用于：
根据所述用户的潜在需求，确定需求表达词；
根据所述需求表达词，在位于所述路线指定范围内的实体对象的描述信息中进行匹配，以获取所述需求表达词相匹配的至少一个实体对象作为所述目标实体对象。
本公开的另一方面，提供一种设备，包括：
一个或者多个处理器；
存储器；
一个或者多个程序，所述一个或者多个程序存储在所述存储器中，
当被所述一个或者多个处理器执行时：
获取用户的潜在需求以及所述用户行进的路线；
从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；
向所述用户推荐所述目标实体对象。
本公开的另一方面，提供一种非易失性计算机存储介质，所述非易失性计算机存储介质存储有一个或者多个程序，当所述一个或者多个程序被一个设备执行时，使得所述设备：
获取用户的潜在需求以及所述用户行进的路线；
从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；
向所述用户推荐所述目标实体对象。
在本公开中，根据用户的潜在需求及用户行进的路线，向用户推荐符合用户潜在需求且在用户行进的路线的指定范围内的实体对象，一方面基于用户的潜在需求进行推荐，向用户推荐感兴趣的实体对象的概率较高，另一方面向用户推荐其行进的路线的指定范围内的实体对象，便于用户去往/获取所推荐的实体对象，信息推荐的针对性和准确性较高。
为了更清楚地说明本公开实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开一实施例提供推荐方法的流程示意图；
图2为本公开一实施例提供的推荐目标实体对象的界面示意图；
图3为本公开一实施例提供的推荐装置的结构示意图。
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
图1为本公开一实施例提供的推荐方法的流程示意图。如图1所示，该方法包括：
101、获取用户的潜在需求以及用户行进的路线。
102、从位于上述路线指定范围内的实体对象中，获取符合用户的潜在需求的目标实体对象。
103、向用户推荐目标实体对象。
本实施例提供一种推荐方法，主要原理是：结合用户的潜在需求以及用户行进的路线，向用户推荐位于用户行进的路线的指定范围内的实体对象，以提高信息推荐的针对性和准确性，提高推荐信息带来的转化效益。
具体的，推荐装置获取用户的潜在需求以及用户行进的路线；确定位于用户行进的路线的指定范围内的实体对象，从所确定的实体对象中，获取符合用户的潜在需求的实体对象作为目标实体对象，向用户推荐目
标实体对象。
其中，上述获取用户的潜在需求的方式可以是：推荐装置对用户指定时段内的搜索日志进行挖掘，以获取用户的潜在需求。具体的，推荐装置可以获取用户指定时段内的搜索日志，例如可以通过搜索引擎来获取用户在指定时段内的搜索日志；然后，对用户指定时段内的搜索日志进行挖掘，以获取用户的潜在需求。
可选的，对搜索日志进行挖掘的方法可以是：从搜索日志中，提取用户的搜索词(query)，根据所提取的搜索词的搜索频次和搜索时间等，对搜索词进行排序，根据排序最靠前的N个搜索词，确定用户的潜在需求，N是自然数。
可选的，对搜索日志进行挖掘的方式可以是：从搜索日志中，获取用户点击的页面，根据页面的点击次数和时间，确定用户更为感兴趣的页面，对用户感兴趣的页面的标题和/或正文进行切词处理，根据切词结果确定该用户的潜在需求。
可选的，对搜索日志进行挖掘的方式可以是：从搜索日志中提取用户的搜索词，并获取用户点击的页面，结合用户的搜索词及用户点击的页面，来确定用户的潜在需求。
例如，根据用户的搜索词获知用户近期频繁搜索饭店、美食等，可以确定用户近期可能需要与朋友或家人等聚餐。又例如，除了根据用户的搜索词获知用户频繁搜索饭店、美食之外，根据用户的搜索词及用户感兴趣的页面获知用户频繁搜索商场、查看各大服装品牌的价格及活动等，可以确定用户除了与朋友或家人等聚餐之外，可能还需要购物。
本实施例对上述指定时段的长短不做限定，例如可以是距离当前时
刻一小时、一天、两天、一星期、两星期、一个月甚至更长时间。
在确定用户的潜在需求后，可以考虑向用户进行信息推荐，以满足用户需求。但是，仅仅根据用户的潜在需求向用户推荐信息，其所推荐的信息有可能是用户不便于去往或获取的，信息的针对性和准确性较差，推荐信息的转化率较低。例如，通常用户在工作日上班，用户公司位置在A点，用户的家在B点，如果仅根据用户的需求可能会向用户推荐距离A点和B点相对较远的饭店或商场，推荐信息的针对性及准确性较差，没有考虑用户距离及时间等问题，由于用户没有时间或因距离问题不能去往推荐的饭店或商场，导致推荐信息的转化率较低。现有技术也存在基于用户位置进行信息推荐的方案，但是若用户所在位置没有符合用户需求的对象时，该信息推荐方式将不再适合。
在本实施例中，推荐装置获取用户行进的路线，以用户行进的路线为依据，向用户推荐符合用户的潜在需求的实体对象，不仅可以满足用户需求，而且所推荐的实体对象在用户行进的路线附近，这样用户如果真的有需求则不会受时间或距离等因素的限制，可以顺路去往或获取所推荐的实体对象，有利于提高推荐信息带来的转化效益。
上述路线可以包括：用户日常行进的路线，和/或，用户正在行进的路线。具体的，推荐装置可以根据用户的历史定位/导航数据，获取用户日常行进的路线，例如可以获取次数最多的一条或几条路线作为用户日常行进的路线，例如可以是从家到公司的路线，从家到孩子所在学校的路线等。推荐装置可以根据用户当前的定位/导航数据，获取用户正在行进的路线。其中，用户正在行进的路线可以是用户日常行进的路线，也可以是用户临时行进的路线。
其中，推荐装置可以从各种具有定位/导航功能的应用中，获取用户的历史定位/导航数据或当前的定位/导航数据。例如，推荐装置可以从各种地图应用、导航应用或打车应用等中获取用户的历史定位/导航数据或当前的定位/导航数据，进而确定该用户行进的路线。
在一可选实施方式中，上述从位于用户行进的路线指定范围内的实体对象中，获取符合用户的潜在需求的目标实体对象的实施方式包括：根据用户的潜在需求，确定需求表达词；根据需求表达词，在位于上述路线指定范围内的实体对象的描述信息中进行匹配，以获取需求表达词相匹配度的至少一个实体对象作为目标实体对象。
具体的，推荐装置可以根据用户的潜在需求，确定能够表达该潜在需求的需求表达词。例如用户最近搜索火锅、麻辣火锅较多，则可以确定用户可能要吃火锅，可以将火锅或麻辣火锅作为用户的需求表达词。又例如，用户最近搜索银行、取款机等较多，则可以确定用户可能需要取钱，可以将银行或取款机等作为用户的需求表达词。之后，推荐装置确定位于用户行进的路线的指定范围内的实体对象，所述指定范围内的实体对象可以是到该路线的垂直距离在所述指定范围内的实体对象，所述指定范围可以是50米、100米、200米、500米等。所述实体对象可以是各种商场、电影院、公交车站、地铁站、报刊亭等。之后，获取这些实体对象的描述信息，所述描述信息包括实体对象的名称、位置、优惠活动、评价等。推荐装置将用户的需求表达词在这些实体对象的描述信息中进行匹配，获取与该需求表达词相匹配的至少一个实体对象作为目标实体对象。例如，可以获取与需求表达词的匹配度最高的一个或几个实体对象作为目标实体对象。
基于上述，推荐装置可以在定位/导航界面上，对需要向用户推荐的目标对象实体进行标记，以向用户进行推荐目标实体对象。一种对目标实体对象进行标记的方式如图2所示。在图2中，上地十街可以是用户日常行进的路线或用户正在行进的路线，相应的，“您最近要“取钱”可以去看看”指向的“中国银行”，“您最近要“取钱”可以去看看”指向的“招商银行”以及“您最近要要“吃火锅”可以去看看”指向的“乖乖仔火锅”等即为所述目标实体对象。
如图2所示，推荐给用户的目标实体对象位于用户行进的路线附近且很可能是用户需求的实体对象，推荐信息的针对性和准确性较强，用户可以很方便的去往这些实体对象，有利于提高推荐信息带来的转化效益，在满足用户需求的同时，还达到了对实体对象进行推荐的目的。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本公开并不受所描述的动作顺序的限制，因为依据本公开，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本公开所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
图3为本公开一实施例提供的推荐装置的结构示意图。如图3所示，该装置包括：信息获取模块31、对象获取模块32和推荐模块33。
信息获取模块31，用于获取用户的潜在需求以及用户行进的路线。
对象获取模块32，用于从位于信息获取模块31获取的路线指定范围内的实体对象中，获取符合信息获取模块31获取的用户的潜在需求的目标实体对象。
推荐模块33，用于向用户推荐对象获取模块32获取的目标实体对象。
在一可选实施方式中，信息获取模块31在获取用户的潜在需求时，具体用于：对用户指定时段内的搜索日志进行挖掘，以获取用户的潜在需求。
在一可选实施方式中，信息获取模块31在获取用户行进的路线时，具体用于：根据用户的历史定位/导航数据，获取用户日常行进的路线；和/或，根据用户当前的定位/导航数据，获取用户正在行进的路线。
在一可选实施方式中，推荐模块33具体用于：在定位/导航界面上，对目标实体对象进行标记，以向用户推荐目标实体对象。
在一可选实施方式中，对象获取模块32具体用于：
根据用户的潜在需求，确定需求表达词；
根据需求表达词，在位于路线指定范围内的实体对象的描述信息中进行匹配，以获取需求表达词相匹配的至少一个实体对象作为目标实体对象。
本实施例的推荐装置可作为各实体对象对应的客户端实现，以负责向用户推荐实体对象。或者，本实施例的推荐装置也可以作为定位/导航应用中的功能模块实现，实现定位/导航与推荐的结合，以根据用户行进的路线向用户推荐符合用户需求且位于用户行进的路线附近的实体对象。或者，本实施例的推荐装置还可以作为搜索引擎中的功能模块实现，实
现搜索与推荐的结合。
本实施例提供的推荐装置，根据用户的潜在需求及用户行进的路线，向用户推荐符合用户潜在需求且在用户行进的路线的指定范围内的实体对象，一方面基于用户的潜在需求进行推荐，向用户推荐感兴趣的实体对象的概率较高，另一方面向用户推荐其行进的路线的指定范围内的实体对象，便于用户去往/获取所推荐的实体对象，信息推荐的针对性和准确性较高。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本公开所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本公开各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本公开各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上实施例仅用以说明本公开的技术方案，而非对其限制；尽管参照前述实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本公开各实施例技术方案的精神和范围。
Claims (12)
- 一种推荐方法，其特征在于，包括：获取用户的潜在需求以及所述用户行进的路线；从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；向所述用户推荐所述目标实体对象。
- 根据权利要求1所述的方法，其特征在于，所述获取用户的潜在需求，包括：对所述用户指定时段内的搜索日志进行挖掘，以获取所述用户的潜在需求。
- 根据权利要求1或2所述的方法，其特征在于，所述获取所述用户行进的路线，包括：根据所述用户的历史定位/导航数据，获取所述用户日常行进的路线；和/或根据所述用户当前的定位/导航数据，获取所述用户正在行进的路线。
- 根据权利要求1-3任一项所述的方法，其特征在于，所述向所述用户推荐所述目标实体对象，包括：在定位/导航界面上，对所述目标实体对象进行标记，以向所述用户推荐所述目标实体对象。
- 根据权利要求1-4任一项所述的方法，其特征在于，所述从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象，包括：根据所述用户的潜在需求，确定需求表达词；根据所述需求表达词，在位于所述路线指定范围内的实体对象的描述信息中进行匹配，以获取所述需求表达词相匹配的至少一个实体对象作为所述目标实体对象。
- 一种推荐装置，其特征在于，包括：信息获取模块，用于获取用户的潜在需求以及所述用户行进的路线；对象获取模块，用于从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；推荐模块，用于向所述用户推荐所述目标实体对象。
- 根据权利要求6所述的装置，其特征在于，所述信息获取模块具体用于：对所述用户指定时段内的搜索日志进行挖掘，以获取所述用户的潜在需求。
- 根据权利要求6或7所述的装置，其特征在于，所述信息获取模块具体用于：根据所述用户的历史定位/导航数据，获取所述用户日常行进的路线；和/或根据所述用户当前的定位/导航数据，获取所述用户正在行进的路线。
- 根据权利要求6-8任一项所述的装置，其特征在于，所述推荐模块具体用于：在定位/导航界面上，对所述目标实体对象进行标记，以向所述用户推荐所述目标实体对象。
- 根据权利要求6-9任一项所述的装置，其特征在于，所述对象获取模块具体用于：根据所述用户的潜在需求，确定需求表达词；根据所述需求表达词，在位于所述路线指定范围内的实体对象的描述信息中进行匹配，以获取所述需求表达词相匹配的至少一个实体对象作为所述目标实体对象。
- 一种设备，包括：一个或者多个处理器；存储器；一个或者多个程序，所述一个或者多个程序存储在所述存储器中，当被所述一个或者多个处理器执行时：获取用户的潜在需求以及所述用户行进的路线；从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；向所述用户推荐所述目标实体对象。
- 一种非易失性计算机存储介质，所述非易失性计算机存储介质存储有一个或者多个程序，当所述一个或者多个程序被一个设备执行时，使得所述设备：获取用户的潜在需求以及所述用户行进的路线；从位于所述路线指定范围内的实体对象中，获取符合所述用户的潜在需求的目标实体对象；向所述用户推荐所述目标实体对象。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510582279.3A CN106528570A (zh) | 2015-09-14 | 2015-09-14 | 推荐方法及装置 |
| CN201510582279.3 | 2015-09-14 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017045256A1 true WO2017045256A1 (zh) | 2017-03-23 |
Family
ID=58288065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/093570 Ceased WO2017045256A1 (zh) | 2015-09-14 | 2015-11-02 | 推荐方法、装置、设备及非易失性计算机存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106528570A (zh) |
| WO (1) | WO2017045256A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064243A (zh) * | 2018-06-19 | 2018-12-21 | 链家网（北京）科技有限公司 | 房源搜索方法 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107566489A (zh) * | 2017-09-01 | 2018-01-09 | 深圳市华腾物联科技有限公司 | 一种信息的智能推荐方法和设备 |
| CN108848463B (zh) * | 2018-06-29 | 2019-09-24 | 百度在线网络技术（北京）有限公司 | 通勤路线确定方法和装置 |
| CN110335077A (zh) * | 2019-07-02 | 2019-10-15 | 上海三菱电梯有限公司 | 商家推荐方法及装置 |
| CN112579906A (zh) * | 2020-12-25 | 2021-03-30 | 深圳市元征科技股份有限公司 | 一种对象推荐方法、装置、设备及存储介质 |
| CN113849741A (zh) * | 2021-09-29 | 2021-12-28 | 北京百度网讯科技有限公司 | 一种内容推荐方法、装置、设备以及存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103345699A (zh) * | 2013-07-10 | 2013-10-09 | 湖南大学 | 一种基于商品森林体系的个性化美食推荐方法 |
| CN103402177A (zh) * | 2013-08-02 | 2013-11-20 | 南京市海聚信息科技有限公司 | 一种WiFi终端信息推送系统及其实现方法 |
| CN103778802A (zh) * | 2014-01-17 | 2014-05-07 | 吴一凡 | 一种基于车位信息共享的停车方案 |
| CN104598602A (zh) * | 2015-01-27 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | 通过计算机实现的基于场景的信息推荐方法及装置 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120010996A1 (en) * | 2010-07-07 | 2012-01-12 | Microsoft Corporation | Recommendations and targeted advertising based upon directions requests activity and data |
| CN102798394A (zh) * | 2011-05-26 | 2012-11-28 | 上海博泰悦臻电子设备制造有限公司 | 路径规划方法及系统 |
| JP5944770B2 (ja) * | 2012-07-17 | 2016-07-05 | 株式会社デンソーアイティーラボラトリ | 行先提案システム、行先提案方法、およびプログラム |
| CN104035947B (zh) * | 2013-09-16 | 2016-04-13 | 腾讯科技（深圳）有限公司 | 兴趣点推荐方法及装置、获取推荐兴趣点的方法及装置 |
| CN103699630B (zh) * | 2013-12-20 | 2017-05-03 | 北京奇虎科技有限公司 | 一种在浏览器中推荐信息的方法与装置 |
-
2015
- 2015-09-14 CN CN201510582279.3A patent/CN106528570A/zh active Pending
- 2015-11-02 WO PCT/CN2015/093570 patent/WO2017045256A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103345699A (zh) * | 2013-07-10 | 2013-10-09 | 湖南大学 | 一种基于商品森林体系的个性化美食推荐方法 |
| CN103402177A (zh) * | 2013-08-02 | 2013-11-20 | 南京市海聚信息科技有限公司 | 一种WiFi终端信息推送系统及其实现方法 |
| CN103778802A (zh) * | 2014-01-17 | 2014-05-07 | 吴一凡 | 一种基于车位信息共享的停车方案 |
| CN104598602A (zh) * | 2015-01-27 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | 通过计算机实现的基于场景的信息推荐方法及装置 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064243A (zh) * | 2018-06-19 | 2018-12-21 | 链家网（北京）科技有限公司 | 房源搜索方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106528570A (zh) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106209935B (zh) | 一种信息处理方法、终端及服务器 | |
| US8301639B1 (en) | Location based query suggestion | |
| EP2638521B1 (en) | Targeting based on intent or presence | |
| KR101740074B1 (ko) | 사용자 데이터로부터 사용자 특정 위치 시맨틱을 추론하는 방법 | |
| US8949212B1 (en) | Location-based informaton display | |
| US20160148262A1 (en) | Providing Additional Functionality as Advertisements with Search Results | |
| WO2016206196A1 (zh) | 用于获取用户属性信息的方法、装置及服务器 | |
| WO2016150170A1 (zh) | 一种推荐方法、装置、设备及计算机存储介质 | |
| TW201741963A (zh) | 推薦個性化內容的系統和方法 | |
| US10922359B2 (en) | Computerized system and method for extracting entity information from text communications and displaying content based therefrom | |
| WO2012172160A1 (en) | Method and apparatus for resolving geo-identity | |
| US10242114B2 (en) | Point of interest tagging from social feeds | |
| JP2013507695A (ja) | 位置ベースのサービスミドルウェア | |
| CN103443788A (zh) | 用于步行浏览的方法和装置 | |
| JP2015014859A (ja) | Ｐｏｉ情報提供システム、ｐｏｉ情報提供装置、ｐｏｉ情報出力装置、ｐｏｉ情報提供方法、及びプログラム | |
| CN105912556B (zh) | 具有搜索功能的移动装置 | |
| JP2018537760A (ja) | アドレス情報に基づいたアカウントマッピングの方法及び装置 | |
| US9773209B1 (en) | Determining supervised training data including features pertaining to a class/type of physical location and time location was visited | |
| CN105408929A (zh) | 利用反向拍卖的加盟店推荐方法及推荐装置 | |
| CN103123632A (zh) | 搜索中心词确定方法及装置、搜索方法及搜索设备 | |
| WO2015103923A1 (zh) | 进行位置信息搜索的方法和浏览器终端 | |
| CN106528570A (zh) | 推荐方法及装置 | |
| KR101376521B1 (ko) | 역경매를 이용한 가맹점 추천 방법과 장치 | |
| US20170191839A1 (en) | Using activity profiles | |
| US20200120054A1 (en) | Computerized system and method for digital content extraction and propagation in html messages |
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: 15903944 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 15903944 Country of ref document: EP Kind code of ref document: A1 |