WO2019042165A1 - 搜索结果优化方法、装置、服务器及可读存储介质 - Google Patents
搜索结果优化方法、装置、服务器及可读存储介质 Download PDFInfo
- Publication number
- WO2019042165A1 WO2019042165A1 PCT/CN2018/101126 CN2018101126W WO2019042165A1 WO 2019042165 A1 WO2019042165 A1 WO 2019042165A1 CN 2018101126 W CN2018101126 W CN 2018101126W WO 2019042165 A1 WO2019042165 A1 WO 2019042165A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- result information
- search result
- search
- click
- preset threshold
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
Definitions
- the present invention relates to the field of computer technologies, and in particular, to a search result optimization method, apparatus, server, and readable storage medium.
- Searching for information using a search engine is a common way for users to browse web pages.
- the traditional search engine composes the search result based on the keyword input by the user at the user terminal, and searches the server for the information corresponding to the keyword, and returns the search result to the corresponding user terminal.
- the search result with weaker relevance to the keyword is returned.
- the search engine can return a product of a strong style class according to the keyword (for example, when the keyword is a music name or a video name, the audio file or the video file is directly returned as a retrieval result), and if the returned search result is weakly correlated, then This makes the occurrence of false triggers more obvious.
- an embodiment of the present invention provides a search result optimization method, apparatus, server, and readable storage medium, which can improve the correlation between returned search results and keywords, and reduce the probability of false triggering.
- an embodiment of the present invention provides a search result optimization method, where the method includes: receiving a search request sent by a user terminal; acquiring a plurality of search result information according to the search request; and querying each search result information correspondingly The effect indicator of the search result information that exceeds the first preset threshold value is returned to the user terminal as new search result information.
- An embodiment of the present invention further provides a search result optimization apparatus, where the apparatus includes: a search request receiving module, a search result information acquiring module, an effect index query module, and a search result information returning module.
- the search request receiving module is configured to receive a search request sent by the user terminal.
- the search result information obtaining module is configured to acquire a plurality of search result information according to the search request.
- the performance indicator query module is used to query the performance indicator corresponding to each search result information.
- the search result information returning module is configured to return the search result information whose effect indicator exceeds the first preset threshold value to the user terminal as new search result information.
- the embodiment of the invention further provides a server, the server comprising a memory and a processor, the memory being coupled to the processor, the memory storing instructions.
- the instruction is executed by the processor, causing the processor to: receive a search request sent by the user terminal; acquire a plurality of search result information according to the search request; and query an effect corresponding to each search result information
- the index result information of the search result exceeding the first preset threshold is returned to the user terminal as new search result information.
- the embodiment of the invention further provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by the processor, implements the search result optimization method described above.
- the search result optimization method, device, server, and readable storage medium acquire a plurality of search result information according to the search request by receiving a search request sent by the user terminal, and query an effect indicator corresponding to each search result information. .
- the search result information whose effect index exceeds the first preset threshold is returned to the user terminal as new search result information.
- the search result optimization method provided by the embodiment of the present invention can accumulate search requests received by different user terminals multiple times, accumulate performance indicators according to search result information fed back by different user terminals, and integrate the obtained effect indicators with the first The preset threshold is compared. If the effect indicator exceeds the first preset threshold, the search result information corresponding to the effect indicator is returned to the user terminal, so that the search result information is continuously optimized, so that the user obtains strong relevance to the search keyword. Search result information.
- FIG. 1 is a schematic diagram of an application environment according to an embodiment of the present invention.
- FIG. 2 is a structural block diagram of a server according to an embodiment of the present invention.
- FIG. 3 is a flowchart of a search result optimization method according to a first embodiment of the present invention
- FIG. 4 is a flowchart of a search result optimization method according to a second embodiment of the present invention.
- FIG. 5 is a structural block diagram of a search result optimization apparatus according to a third embodiment of the present invention.
- FIG. 6 is a structural block diagram of a search result optimization apparatus according to an embodiment of the third embodiment of the present invention.
- a component when referred to as being "fixed” to another component, it can be directly on the other component or the component can be in the middle. When a component is considered to "connect” another component, it can be directly connected to another component or possibly a central component.
- server 10 is in communication with one or more user terminals 20 via network 30 for data communication or interaction.
- a client is installed in the user terminal 20, and the client may be an application, corresponding to the server 10, to provide services for the user (for example, receiving search requirement description information input by the user, and displaying the search to the user. Result information, etc.).
- the server 10 may be a plurality of servers such as a database server, an instant messaging server, a network server, an authentication server, or the like, or may be a server.
- the user terminal 20 may be a personal computer (PC), a tablet computer, a smart phone, an e-book reader, a laptop portable computer, a car-mounted computer, a smart wearable device, or the like.
- the network 30 may be a wireless network or a wired network, for example, the wireless network may be, but not limited to, a Wi-Fi (Wireless Fidelity) network, a 2G/3G/4G network, or the like.
- FIG. 2 shows a block diagram of a structure of a server 10 that can be applied to an embodiment of the present invention.
- server 10 includes a memory 102, a memory controller 104, one or more (only one of which is shown) processor 106, peripheral interface 108, radio frequency module 110, and the like. These components communicate with one another via one or more communication bus/signal lines 116.
- the memory 102 can be used to store software programs and modules, such as the search result optimization method and the program instructions/modules corresponding to the devices in the embodiment of the present invention.
- the processor 106 executes various programs by running software programs and modules stored in the memory 102. Functional applications and data processing, such as search result optimization methods.
- Memory 102 can include high speed random access memory and can also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. Access to the memory 102 by the processor 106 and other possible components can be performed under the control of the memory controller 104.
- non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. Access to the memory 102 by the processor 106 and other possible components can be performed under the control of the memory controller 104.
- Peripheral interface 108 couples various input/input devices to processor 106 and memory 102.
- peripheral interface 108, processor 106, and memory controller 104 can be implemented in a single chip. In other instances, they can be implemented by separate chips.
- the radio frequency module 110 is configured to receive and transmit electromagnetic waves, and realize mutual conversion between electromagnetic waves and electric signals, thereby communicating with a communication network or other devices.
- FIG. 2 is merely illustrative, and the server 10 may further include more or less components than those shown in FIG. 2, or have a different configuration than that shown in FIG. 2.
- the components shown in Figure 2 can be implemented in hardware, software, or a combination thereof.
- FIG. 3 is a flowchart of a search result optimization method according to a first embodiment of the present invention. Referring to FIG. 3, this embodiment describes a process flow of a server, where the method includes:
- Step S110 Receive a search request sent by the user terminal.
- the search request refers to a request that the user terminal sends to the server, including the search requirement description information, after the user needs to perform the search, after the user terminal inputs the search requirement description information and confirms.
- Search requirement description information refers to information describing the user's search needs.
- the search requirement description information may be an image, a keyword, or a combination of an image and a keyword.
- Step S120 Acquire a plurality of search result information according to the search request.
- the server obtains search result information related to the search requirement description information, and each search requirement description information may correspond to multiple search result information, and different search result information has different meanings.
- the “Apple” can be understood as a mobile phone brand, can also be understood as a fruit, can also be understood as a song name, etc., so the server can describe according to the search needs.
- the information "Apple” obtained the search result information of Apple mobile phone, fruit apple, and song “Little Apple”.
- Step S130 querying an effect indicator corresponding to each search result information.
- the performance indicator refers to the degree to which each search result information is related to the search requirement description information.
- the performance indicator can be obtained by different users operating the search result information through different user terminals.
- the click amount of the search result information corresponding to the search requirement description information, the click pass rate, and the fitting score of the click model may be determined according to the unit time.
- the click volume refers to the number of times the corresponding search result information was clicked.
- Click-Through-Rate is the click-through rate of the search result information, that is, the actual number of clicks of the search result information divided by the amount of the search result information.
- the click model is a modeling of the user's click behavior.
- the user's behavior is modeled according to the user's historical click information to predict the user's future click behavior and improve relevance.
- the server may collect a search log and a click log in the search process, and the search log includes a search requirement description information and a list of search result information corresponding to the search requirement description information, and the click log includes the search requirement description information and the searched click in the above list. Result information.
- the server may specifically invoke a command line interface of the distributed file system, and push the log information including the search log and the click log to the distributed file system, and the distributed file system acquires the click model according to the log information, and invokes the command line interface. Sending the obtained click model to the server, and the server applies the click model to search.
- the click model may be established according to the division of the geographical area.
- the server may obtain historical click information of the users of the plurality of geographical areas that are divided in advance, and obtain multiple corresponding to the plurality of geographical areas. History click on the information collection. If at least two historical click information sets in the plurality of historical click information sets have higher clicks on one of the plurality of search result information corresponding to the same search demand description information, the at least two historical clicks may be The geographic area corresponding to the information set is used as the area class, and a click model of the area class is generated.
- the click model of the region class continuously accumulates the search demand description information in the region class and the search result information with higher click volume corresponding to the search requirement description information, and when the same search demand description information is received again, the click volume is High search result information gives the corresponding fit score.
- Sichuan and Chongqing can be divided into a regional class.
- the “meat scorpion” has a higher click volume, and the corresponding click in the region class
- the “meat scorpion” is in the upper position of the search result information, and correspondingly, the "meat scorpion” has a higher fitting score.
- the click amount, the click pass rate, and the hit score of the click model may also have respective matching weights, and the click amount, the click pass rate, and the click model fit of a search result information.
- the sum of the scores and the respective matching weights is added to obtain an effect indicator of the search result information.
- the matching weight of the click volume is x%
- the matching weight of the click pass rate is y%
- the matching weight of the hit score of the click model is z%
- the performance indicator click volume*x%+click pass rate*y% + Fitting the score *z%.
- step S140 the search result information whose effect index exceeds the first preset threshold is returned to the user terminal as new search result information.
- the search result information corresponding to the effect indicator may be returned to the user terminal by the server, and if the effect indicator is lower than the first preset threshold, the search result information corresponding to the effect indicator may be If the judgment is made again, the search result information may not be returned to the user terminal.
- the search result optimization method provided by the first embodiment of the present invention obtains a plurality of search result information corresponding to the search requirement description information according to the search requirement description information included in the search request by receiving the search request sent by the user terminal.
- Each search result information corresponds to its effect indicator, and the effect indicator is used to reflect the degree of relevance of the search result information and the search demand description information.
- the server If the performance indicator exceeds the first preset threshold, the server returns the search result information corresponding to the performance indicator to the user terminal, and the first embodiment of the present invention needs to obtain the obtained search result information each time the search operation is performed.
- the effect indicator is compared with the first preset threshold, and the search result information whose effect index is higher than the first preset threshold is returned to the user terminal, which can better improve the correlation between the search result information and the search requirement description information.
- FIG. 4 is a flowchart of a search result optimization method according to a second embodiment of the present invention. Referring to FIG. 4, this embodiment describes a process flow of a server, where the method includes:
- Step S210 Acquire an effect indicator corresponding to each search result information, where the effect indicator is determined in advance according to operation information of the user for each search result information.
- each search result information corresponding to the search requirement description information query has its unique identifier sc_name. Sc_name can be recorded in the click list.
- Each click of the search result information by the user and the browsing duration after the click can be recorded by the server.
- Step S220 receiving a search request sent by the user terminal.
- Step S230 acquiring a plurality of search result information according to the search request.
- Step S240 querying an effect indicator corresponding to each search result information.
- Steps S220 to S240 are the same as steps S110 to S130 in the first embodiment, and are not described herein.
- step S250 whether the performance indicator of the search result information exceeds the first preset threshold, if yes, step S260 is performed; if not, step S270 is performed.
- the performance indicator corresponding to each search result information can be compared with the first preset threshold.
- the performance indicator reflects the correlation between the search result information and the search requirement description information. If the effect indicator exceeds the first preset threshold, the correlation between the search result information corresponding to the effect indicator and the search requirement description information is high, and then the step is performed. S260. If the effect indicator does not exceed the first preset threshold, step S270 is performed.
- Step S260 the search result information is returned to the user terminal as new search result information.
- the server For the search result information that is highly correlated with the search requirement description information, the server returns it as the search result information to the user terminal, so that the user obtains a better search experience.
- step S270 whether the performance indicator of the search result information exceeds the second preset threshold, and if yes, step S280 is performed.
- the second preset threshold is smaller than the first preset threshold.
- the effect indicator is lower than the first preset threshold, may be lower than the first preset threshold, or may be different from the first preset threshold. Therefore, in order to avoid the omission of the search result information, the performance indicator lower than the first preset threshold is compared with the second preset threshold to determine whether the search result information corresponding to the performance indicator lower than the first preset threshold is due to the first A preset threshold is set inappropriately and is omitted.
- step S280 the search result information is recorded as the to-be-determined result information, and the search result information whose performance index exceeds the first preset threshold value and the pending result information are collectively returned to the user terminal as new search result information.
- the effect indicator exceeds the second preset threshold but is lower than the first preset threshold, indicating that the search result information corresponding to the effect indicator may be missed because the first preset threshold is set too high. Therefore, the search result information is recorded as the to-be-determined result information, and the search result information of the pending result information and the effect indicator exceeding the first preset threshold value may be jointly returned to the user terminal by the server, and the operation information of the result information to be determined by the user at the user terminal is performed. To test the result information for testing.
- Step S290 receiving operation information for the to-be-determined result information sent by the user terminal, determining whether the preset time period operation information meets the preset condition, and if yes, executing step S300.
- the preset time period is a fixed time period, which may be one week or one month.
- the specific duration of the preset time period should not be construed as limiting the present invention.
- the operation information of the user to the result information includes the click data of the user to be determined result information and the browsing duration of each pending result information.
- Click data includes click volume, click pass rate, and click model fit score.
- the preset condition may respectively set a corresponding preset value for the click amount, the click pass rate, the click score of the click model, and the browsing duration.
- the preset value of the click amount is a
- the preset value of the click pass rate is b.
- the default value of the fitting score of the click model is c
- the default value of the browsing time is d
- the hit amount of the pending result information is lower than a
- the click pass rate is lower than b
- the hit score of the click model is lower than c
- the preset condition can also set a preset value for one of the click amount, the click pass rate, the click score of the click model, and the browsing duration. If the pending result information is lower than the set preset value, it is determined that the preset time period operation information satisfies the preset condition.
- whether the preset time period operation information satisfies the preset condition may determine whether the operation information about the to-be-determined result information satisfies the preset condition after the preset time period elapses.
- Step S300 reducing an effect indicator of the to-be-determined result information to below a second preset threshold.
- the correlation between the pending result information and the search requirement description information is low, so the corresponding effect indicator is lowered below the second preset threshold.
- step S310 the to-be-determined result information whose performance indicator is lower than the second preset threshold is no longer returned to the user terminal.
- the pending result information whose performance indicator is lower than the second preset threshold may be determined to be less correlated with the search requirement description information, so the server no longer returns the pending result information whose performance indicator is lower than the second preset threshold to the user terminal. .
- the search result optimization method provided by the second embodiment of the present invention can determine the search result information whose performance index is lower than the first preset threshold value, and determine whether the effect indicator is still lower than the second preset threshold. If not, the method will be As the to-be-determined result information, it is determined whether the operation information for the to-be-determined result information satisfies the preset condition, and when satisfied, the effect indicator is lowered below the second preset threshold. The pending result information whose performance indicator is lower than the second preset threshold is no longer returned to the user terminal. Thereby, the occurrence of the partial search result information being missed due to the excessively high setting of the first preset threshold is avoided.
- the embodiment of the present invention further provides a search result optimization device.
- the device 300 includes:
- the search request receiving module 310 is configured to receive a search request sent by the user terminal.
- the search result information obtaining module 320 is configured to obtain a plurality of search result information according to the search request.
- the performance indicator query module 330 is configured to query an effect indicator corresponding to each search result information.
- the search result information returning module 340 is configured to return the search result information whose effect index exceeds the first preset threshold value to the user terminal as new search result information.
- FIG. 6 shows a specific implementation manner of the third embodiment of the present invention.
- the search result optimization apparatus further includes a pending result obtaining module 350, an operation information receiving module 360, a preset condition determining module 370, and an effect.
- the search result information that is lower than the first preset threshold may be used to determine whether the search result information exceeds the second preset threshold. If the value exceeds the first preset threshold, the performance result is lower than the first preset threshold.
- the search result information at the second preset threshold is recorded as the pending result information.
- the search result information returning module may specifically include a returning sub-module (not shown), and the returning sub-module returns the search result information and the pending result information with the effect indicator exceeding the first preset threshold value as new search result information to the user terminal.
- the operation information receiving module 360 receives the operation information for the to-be-determined result information sent by the user terminal, and the operation information of the user to be determined result information includes the click data of the user to be determined result information and the browsing duration for each to-be-determined result information.
- Click data includes click volume, click pass rate, and click model fit score.
- the preset condition determining module 370 determines whether the operation information of the user to be determined result information meets the preset condition within the preset time period, and if yes, reduces the performance index of the pending result information to below the second preset threshold. The pending result information whose performance indicator is lower than the second preset threshold is no longer returned to the user terminal.
- the effect indicator corresponding to each search result information queried by the effect indicator query module 330 is specifically acquired by the effect indicator obtaining module 380.
- the effect indicator is determined in advance according to the operation information of the user for each search result information.
- the matching degree obtaining module 390 obtains and stores each search result information according to the matching weights corresponding to the click amount, the click passing rate, the fitting score of the click model, and the click amount, the click passing rate, and the fitting score of the click model.
- the degree of matching corresponding to the search request which can be used as an effect indicator.
- the present invention also provides a terminal device readable storage medium storing a computer program that, when executed by a processor, implements the method of any of the above embodiments.
- the search result optimization method, apparatus, server, and readable storage medium provided by the embodiments of the present invention can accumulate search requests received through different user terminals multiple times, accumulate performance indicators according to search result information fed back by different user terminals, and Comparing the obtained performance index with the first preset threshold, if the performance index exceeds the first preset threshold, the search result information corresponding to the effect indicator is returned to the user terminal, thereby continuously optimizing the search result information, so that The user obtains search result information that is highly correlated with the search keyword.
- each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the Executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may also occur in a different order than those illustrated in the drawings.
- each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or action. Or it can be implemented by a combination of dedicated hardware and computer instructions.
- each functional module in each embodiment of the present invention may be integrated to form a separate part, or each module may exist separately, or two or more modules may be integrated to form a separate part.
- the functions, if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer readable storage medium.
- the technical solution of the present invention which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
- the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
- 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. .
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明实施例提供一种搜索结果优化方法、装置、服务器及可读存储介质。该方法包括：接收用户终端发送的搜索请求；根据所述搜索请求获取多个搜索结果信息；查询每个搜索结果信息对应的效果指标；将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。本发明实施例提供的方法能够多次累计通过不同的用户终端接收到的搜索请求，根据不同的用户终端反馈回来的搜索结果信息积累效果指标，并且将积累获得的效果指标与第一预设阈值进行比较，若效果指标超过第一预设阈值，则将该效果指标对应的搜索结果信息返回给用户终端，从而不断对搜索结果信息进行优化，使用户获得与搜索关键词相关性强的搜索结果信息。
Description
本发明涉及计算机技术领域，具体而言，涉及一种搜索结果优化方法、装置、服务器及可读存储介质。
随着互联网技术的发展，用户对网页浏览的需求越来越大，使用搜索引擎搜索信息是用户在浏览网页时常见的方式。
传统的搜索引擎根据用户在用户终端输入的关键词，在服务器查找与关键词相应的信息组成检索结果，并将检索结果返回给对应的用户终端。但由于存在误触发的可能，例如对用户查询意图理解有误，或与关键词对应的信息不准确，会返回与关键词相关性较弱的检索结果。
特别是搜索引擎可以根据关键词返回强样式类的产品(例如关键词为音乐名称或视频名称时，直接将音频文件或视频文件作为检索结果返回)，若返回的检索结果相关性较弱，则使得误触发的发生显得更加明显。
发明内容
有鉴于此，本发明实施例提供了一种搜索结果优化方法、装置、服务器及可读存储介质，能够改善返回的检索结果与关键词的相关性，减小误触发发生的概率。
为实现上述目的，本发明实施例提供了一种搜索结果优化方法，所述方法包括：接收用户终端发送的搜索请求；根据所述搜索请求获取多个搜索结果信息；查询每个搜索结果信息对应的效果指标；将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
本发明实施例还提供了一种搜索结果优化装置，所述装置包括：搜索请求接收模块、搜索结果信息获取模块、效果指标查询模块以及搜索结果 信息返回模块。其中，搜索请求接收模块用于接收用户终端发送的搜索请求。搜索结果信息获取模块用于根据所述搜索请求获取多个搜索结果信息。效果指标查询模块用于查询每个搜索结果信息对应的效果指标。搜索结果信息返回模块用于将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
本发明实施例还提供了一种服务器，所述服务器包括存储器和处理器，所述存储器耦接到所述处理器，所述存储器存储指令。当所述指令由所述处理器执行时，使所述处理器执行以下操作：接收用户终端发送的搜索请求；根据所述搜索请求获取多个搜索结果信息；查询每个搜索结果信息对应的效果指标；将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
本发明实施例还提供了一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现上述所述的搜索结果优化方法。
本发明实施例提供的搜索结果优化方法、装置、服务器及可读存储介质的有益效果为：
本发明实施例提供的搜索结果优化方法、装置、服务器及可读存储介质，通过接收用户终端发送的搜索请求，根据搜索请求获取多个搜索结果信息，并且查询每个搜索结果信息对应的效果指标。将效果指标超过第一预设阈值的搜索结果信息作为新的搜索结果信息返回给用户终端。本发明实施例提供的搜索结果优化方法能够多次累计通过不同的用户终端接收到的搜索请求，根据不同的用户终端反馈回来的搜索结果信息积累效果指标，并且将积累获得的效果指标与第一预设阈值进行比较，若效果指标超过第一预设阈值，则将该效果指标对应的搜索结果信息返回给用户终端，从而不断对搜索结果信息进行优化，使用户获得与搜索关键词相关性强的搜索结果信息。
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例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发明的一些实施例，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是本发明实施例的应用环境示意图；
图2示出了本发明实施例提供的服务器的结构框图；
图3示出了本发明第一实施例提供的一种搜索结果优化方法的流程图；
图4示出了本发明第二实施例提供的一种搜索结果优化方法的流程图；
图5示出了本发明第三实施例提供的一种搜索结果优化装置的结构框图；
图6示出了本发明第三实施例的一种具体实施方式提供的搜索结果优化装置的结构框图。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
需要说明的是，当组件被称为“固定于”另一个组件，它可以直接在另一个组件上或者也可以存在居中的组件。当一个组件被认为是“连接”另一个组件，它可以是直接连接到另一个组件或者可能同时存在居中组件。
除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的技术领域的技术人员通常理解的含义相同。本文中在本发明的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本发明。本文所使用的术语“及/或”包括一个或多个相关的所列项目的任意的和所有的组合。
下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
本发明下述各实施例均可应用于如图1所示的环境中。如图1所示，服务器10通过网络30与一个或多个用户终端20进行通信连接，以进行数据通信或交互。在本发明实施例中，用户终端20中安装有客户端，该客户端可以是应用程序，与服务器10相对应，从而为用户提供服务(例 如接收用户输入的搜索需求描述信息，向用户展示搜索结果信息等)。所述服务器10可以是数据库服务器、即时通信服务器、网络服务器、验证服务器等多个服务器，也可以是一个服务器。所述用户终端20可以是个人电脑(personal computer，PC)、平板电脑、智能手机、电子书阅读器、膝上型便携计算机、车载电脑、智能穿戴设备等。所述网络30可以是无线网络或有线网络，例如无线网络可以是，但不限于Wi-Fi(无线保真)网络、2G/3G/4G网络等。
图2示出了一种可应用于本发明实施例中的服务器10的结构框图。如图2所示，服务器10包括存储器102、存储控制器104，一个或多个(图中仅示出一个)处理器106、外设接口108、射频模块110等。这些组件通过一条或多条通讯总线/信号线116相互通讯。
存储器102可用于存储软件程序以及模块，如本发明实施例中的搜索结果优化方法及装置对应的程序指令/模块，处理器106通过运行存储在存储器102内的软件程序以及模块，从而执行各种功能应用以及数据处理，如搜索结果优化方法。
存储器102可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。处理器106以及其他可能的组件对存储器102的访问可在存储控制器104的控制下进行。
外设接口108将各种输入/输入装置耦合至处理器106以及存储器102。在一些实施例中，外设接口108，处理器106以及存储控制器104可以在单个芯片中实现。在其他一些实例中，他们可以分别由独立的芯片实现。
射频模块110用于接收以及发送电磁波，实现电磁波与电信号的相互转换，从而与通讯网络或者其他设备进行通讯。
可以理解，图2所示的结构仅为示意，服务器10还可包括比图2中所示更多或者更少的组件，或者具有与图2所示不同的配置。图2中所示的各组件可以采用硬件、软件或其组合实现。
第一实施例
图3示出了本发明第一实施例提供的一种搜索结果优化方法的流程 图，请参阅图3，本实施例描述的是服务器的处理流程，所述方法包括：
步骤S110，接收用户终端发送的搜索请求。
于本发明实施例中，搜索请求指的是用户需要进行搜索时，在用户终端输入搜索需求描述信息并确认后，用户终端向服务器发送的包含有搜索需求描述信息的请求。搜索需求描述信息是指描述用户搜索需求的信息。在本实施例中，搜索需求描述信息可以是图像、关键字或图像与关键字的组合。
步骤S120，根据所述搜索请求获取多个搜索结果信息。
服务器获取与搜索需求描述信息相关的搜索结果信息，每个搜索需求描述信息均可以对应有多个搜索结果信息，且不同搜索结果信息对应的含义不同。
例如，假设用户的搜索需求描述信息为一关键字，例如“苹果”，该“苹果”可以理解为手机品牌，也可以理解为水果，还可以理解为歌曲名等，因此服务器可以根据搜索需求描述信息“苹果”获取到分别是苹果手机、水果苹果、以及歌曲《小苹果》的搜索结果信息。
步骤S130，查询每个搜索结果信息对应的效果指标。
效果指标指的是每个搜索结果信息与搜索需求描述信息的相关程度。效果指标可以由不同用户通过不同的用户终端对搜索结果信息进行操作来获得。
具体地，可以根据单位时间内，搜索需求描述信息对应的搜索结果信息的点击量、点击通过率以及点击模型的拟合分数确定。点击量指的是相应的搜索结果信息被点击的次数。点击通过率(Click-Through-Rate)是指搜索结果信息的点击到达率，即该搜索结果信息的实际点击次数除以该搜索结果信息的展现量。
点击模型是对用户的点击行为的建模，根据用户的历史点击信息，对用户的行为进行建模，以对用户未来的点击行为进行预测，提高相关性。服务器在搜索过程中可以收集搜索日志和点击日志，搜索日志中包括搜索需求描述信息以及与搜索需求描述信息对应的搜索结果信息的列表，点击日志包括搜索需求描述信息与上述列表中被点击的搜索结果信息。
服务器具体可以调用分布式文件系统的命令行接口，向分布式文件系统推送包含该搜索日志和该点击日志的日志信息，由分布式文件系统根据上述的日志信息获取点击模型，调用该命令行接口，将获取到的点击模型发送给该服务器，由服务器应用该点击模型进行搜索。
由于使用互联网的用户存在地域差异，点击模型可以按照地理区域的划分来建立，具体地，服务器可以获取预先划分的多个地理区域的用户的历史点击信息，得到对应于多个地理区域的多个历史点击信息集合。若多个历史点击信息集合中的至少两个历史点击信息集合对同一搜索需求描述信息对应的多个搜索结果信息中的一个搜索结果信息的点击量较高，则可以将该至少两个历史点击信息集合对应的地理区域作为区域类，并生成该区域类的点击模型。该区域类的点击模型不断积累该区域类内的搜索需求描述信息以及与搜索需求描述信息对应的点击量较高的搜索结果信息，并在再一次接收到同样搜索需求描述信息时，对点击量高的搜索结果信息给出相应的拟合分数。
具体地，可以将四川和重庆划分到一个区域类中，该区域类，当用户的搜索需求描述信息为“粽子”时，“肉粽子”的点击量较高，则在该区域类对应的点击模型中，当接收到搜索请求为“粽子”时，“肉粽子”处于搜索结果信息中靠前的位置，相应的，“肉粽子”的拟合分数较高。
在本发明的一种具体实施方式中，点击量、点击通过率以及点击模型的拟合分数还可以有各自的匹配权重，将一个搜索结果信息的点击量、点击通过率以及点击模型的拟合分数与各自的匹配权重相乘所得的积相加，即可得到该搜索结果信息的效果指标。例如，点击量的匹配权重为x％，点击通过率的匹配权重为y％，点击模型的拟合分数的匹配权重为z％，则效果指标＝点击量*x％+点击通过率*y％+拟合分数*z％。
步骤S140，将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
若效果指标超过了第一预设阈值，则该效果指标对应的搜索结果信息可以被服务器返回给用户终端，若效果指标低于第一预设阈值，则可以对该效果指标对应的搜索结果信息再进行判断，也可以不再将该搜索结果信息返回给用户终端。
本发明第一实施例提供的搜索结果优化方法，通过接收用户终端发送的搜索请求，根据搜索请求中包含的搜索需求描述信息，获得与搜索需求描述信息对应的多个搜索结果信息。每个搜索结果信息均对应有其效果指标，效果指标用来反映搜索结果信息与搜索需求描述信息的相关程度。若效果指标超过第一预设阈值，则服务器将与该效果指标对应的搜索结果信息返回给用户终端，本发明第一实施例在每次执行搜索操作时，都需要将获得的搜索结果信息的效果指标与第一预设阈值对比，并且将效果指标高于第一预设阈值的搜索结果信息才返回给用户终端，能够较好的提高搜索结果信息与搜索需求描述信息的相关程度。
第二实施例
图4示出了本发明第二实施例提供的一种搜索结果优化方法的流程图，请参阅图4，本实施例描述的是服务器的处理流程，所述方法包括：
步骤S210，获取每个搜索结果信息对应的效果指标，所述效果指标预先根据用户针对每个搜索结果信息的操作信息确定。
具体地，用户查询搜索需求描述信息query，与搜索需求描述信息query对应的每个搜索结果信息均有其唯一标识sc_name。sc_name可以被记录在点击列表中。用户对搜索结果信息每次的点击以及点击后的浏览时长均可以被服务器记录。
步骤S220，接收用户终端发送的搜索请求。
步骤S230，根据所述搜索请求获取多个搜索结果信息。
步骤S240，查询每个搜索结果信息对应的效果指标。
步骤S220至步骤S240与第一实施例中的步骤S110至步骤S130对应相同，在此便不做赘述。
步骤S250，搜索结果信息的效果指标是否超过第一预设阈值，若是，执行步骤S260；若否，执行步骤S270。
每个搜索结果信息对应的效果指标均可以与第一预设阈值进行对比。由于效果指标反映搜索结果信息与搜索需求描述信息的相关性，若效果指标超过第一预设阈值，则说明该效果指标对应的搜索结果信息与搜索需求描述信息的相关性较高，则执行步骤S260；若效果指标未超过第一预设阈值，则执行步骤S270。
步骤S260，将搜索结果信息作为新的搜索结果信息返回给所述用户终端。
对于与搜索需求描述信息相关性较高的搜索结果信息，服务器将其作为搜索结果信息返回给用户终端，以使用户获得较好的搜索体验。
步骤S270，搜索结果信息的效果指标是否超过第二预设阈值，若是，执行步骤S280。
第二预设阈值小于第一预设阈值。效果指标低于第一预设阈值，可能低于第一预设阈值较多，也可能与第一预设阈值相差不大。因此，为了避免搜索结果信息的遗漏，将低于第一预设阈值的效果指标与第二预设阈值进行比较，以判断低于第一预设阈值的效果指标对应的搜索结果信息是否因第一预设阈值设置得不合适而被遗漏。
步骤S280，将该搜索结果信息记为待定结果信息，将效果指标超过第一预设阈值的搜索结果信息以及所述待定结果信息，共同作为新的搜索结果信息返回给所述用户终端。
效果指标超过第二预设阈值但低于第一预设阈值，表明该效果指标对应的搜索结果信息可能因第一预设阈值设置得过高而被遗漏。因此，将该搜索结果信息记为待定结果信息，待定结果信息与效果指标超过第一预设阈值的搜索结果信息可以共同被服务器返回给用户终端，通过用户在用户终端对待定结果信息的操作信息来对待定结果信息进行测试。
步骤S290，接收用户终端发送的针对待定结果信息的操作信息，判断预设时间段操作信息是否满足预设条件，若是，执行步骤S300。
预设时间段为一个固定的时间段，可以为一周，也可以为一个月，预设时间段的具体时长不应该理解为是对本发明的限制。
用户对待定结果信息的操作信息包括用户对待定结果信息的点击数据以及关于每个待定结果信息的浏览时长。点击数据包括点击量、点击通过率以及点击模型的拟合分数。
预设条件可以对点击量、点击通过率、点击模型的拟合分数以及浏览时长分别设置相应的预设值，例如，点击量的预设值为a，点击通过率的预设值为b，点击模型的拟合分数的预设值为c，浏览时长的预设值为d，当待定结果信息的点击量低于a，或点击通过率低于b，或点击模型 的拟合分数低于c，或浏览时长低于d时，则可以判定预设时间段操作信息满足预设条件。
预设条件也可以对点击量、点击通过率、点击模型的拟合分数以及浏览时长中的一个设置预设值。若待定结果信息低于设置的预设值时，判定预设时间段操作信息满足预设条件。
由于搜索操作几乎随时都在进行，故待定结果信息的点击数据和浏览时长的数值也在不断变化。因此，预设时间段操作信息是否满足预设条件，可以判断在预设时间段过后，关于待定结果信息的操作信息是否满足预设条件。
步骤S300，降低所述待定结果信息的效果指标至第二预设阈值以下。
若待定结果信息的操作信息满足预设条件，则说明待定结果信息与搜索需求描述信息的相关性较低，因此将其对应的效果指标降低至第二预设阈值以下。
步骤S310，效果指标低于第二预设阈值的待定结果信息不再返回给所述用户终端。
效果指标低于第二预设阈值的待定结果信息可以被判定为与搜索需求描述信息的相关程度较低，因此服务器不再把效果指标低于第二预设阈值的待定结果信息返回给用户终端。
本发明第二实施例提供的搜索结果优化方法能够对效果指标低于第一预设阈值的搜索结果信息再一次进行判断，判断效果指标是否依然低于第二预设阈值，若否，则将其作为待定结果信息，判断针对待定结果信息的操作信息是否满足预设条件，当满足时，再将效果指标降至第二预设阈值之下。效果指标低于第二预设阈值的待定结果信息不再返回给所述用户终端。从而避免了由于第一预设阈值设置的过高导致部分搜索结果信息被遗漏的情况的发生。
第三实施例
本发明实施例还提供了一种搜索结果优化装置，详情请参见图5，该装置300包括：
搜索请求接收模块310，用于接收用户终端发送的搜索请求。搜索结 果信息获取模块320，用于根据所述搜索请求获取多个搜索结果信息。效果指标查询模块330，用于查询每个搜索结果信息对应的效果指标。搜索结果信息返回模块340，用于将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
详情请参见图6，图6示出了本发明第三实施例的一种具体实施方式，搜索结果优化装置还包括待定结果获取模块350、操作信息接收模块360、预设条件判断模块370、效果指标获取模块380以及匹配度获取模块390。
其中，对于效果指标低于第一预设阈值的搜索结果信息，还可以判断其是否超过第二预设阈值，若超过，则待定结果获取模块350将效果指标低于第一预设阈值且高于第二预设阈值的搜索结果信息记为待定结果信息。搜索结果信息返回模块具体可以包括返回子模块(图未示)，返回子模块将效果指标超过第一预设阈值的搜索结果信息以及待定结果信息共同作为新的搜索结果信息返回给用户终端。
操作信息接收模块360接收用户终端发送的针对待定结果信息的操作信息，用户对待定结果信息的操作信息包括用户对待定结果信息的点击数据以及关于每个待定结果信息的浏览时长。点击数据包括点击量、点击通过率以及点击模型的拟合分数。
预设条件判断模块370判断预设时间段内，用户对待定结果信息的操作信息是否满足预设条件，若满足，则将待定结果信息的效果指标降低至第二预设阈值以下。效果指标低于第二预设阈值的待定结果信息不再返回给用户终端。
效果指标查询模块330查询到的每个搜索结果信息对应的效果指标具体由效果指标获取模块380获取。其中，效果指标预先根据用户针对每个搜索结果信息的操作信息确定。具体地，由匹配度获取模块390根据点击量、点击通过率、点击模型的拟合分数以及点击量、点击通过率、点击模型的拟合分数分别对应的匹配权重获得并存储每个搜索结果信息与搜索请求对应的匹配度，该匹配度可作为效果指标。
本发明还提供一种终端设备可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现上述任一实施例的方法。
本发明实施例提供的搜索结果优化方法、装置、服务器及可读存储介质能够多次累计通过不同的用户终端接收到的搜索请求，根据不同的用户终端反馈回来的搜索结果信息积累效果指标，并且将积累获得的效果指标与第一预设阈值进行比较，若效果指标超过第一预设阈值，则将该效果指标对应的搜索结果信息返回给用户终端，从而不断对搜索结果信息进行优化，使用户获得与搜索关键词相关性强的搜索结果信息。
需要说明的是，本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。对于装置类实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
本发明所提供的几个实施例中，应该理解到，所揭露的装置和方法，也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，附图中的流程图和框图显示了根据本发明的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
另外，在本发明各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术 方案的部分可以以软件产品的形式体现出来，该计算机软件产品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)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应所述以权利要求的保护范围为准。
Claims (13)
- 一种搜索结果优化方法，其特征在于，所述方法包括：接收用户终端发送的搜索请求；根据所述搜索请求获取多个搜索结果信息；查询每个搜索结果信息对应的效果指标；将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
- 根据权利要求1所述的方法，其特征在于，所述方法还包括：若某个搜索结果信息对应的效果指标低于所述第一预设阈值且高于第二预设阈值，则将该搜索结果信息记为待定结果信息；相应地，所述将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端，包括：将效果指标超过第一预设阈值的搜索结果信息以及所述待定结果信息，共同作为新的搜索结果信息返回给所述用户终端。
- 根据权利要求2所述的方法，其特征在于，所述方法还包括：接收用户终端发送的针对所述待定结果信息的操作信息；判断预设时间段内操作信息是否满足预设条件，若满足，则降低所述待定结果信息的效果指标至所述第二预设阈值以下。
- 根据权利要求1所述的方法，其特征在于，所述接收用户终端发送的搜索请求之前，还包括：获取每个搜索结果信息对应的效果指标，所述效果指标预先根据用户针对每个搜索结果信息的操作信息确定。
- 根据权利要求4所述的方法，其特征在于，所述操作信息包括点击数据以及浏览时长。
- 根据权利要求5所述的方法，其特征在于，所述点击数据包括点击量、点击通过率、点击模型的拟合分数，所述效果指标的确定，包括：根据点击量、点击通过率、点击模型的拟合分数以及所述点击量、点击通过率、点击模型的拟合分数分别对应的匹配权重，获得并存储每个搜索结果信息与搜索请求对应的匹配度，并将该匹配度作为效果指 标。
- 一种搜索结果优化装置，设置于服务器，其特征在于，所述装置包括：搜索请求接收模块，用于接收用户终端发送的搜索请求；搜索结果信息获取模块，用于根据所述搜索请求获取多个搜索结果信息；效果指标查询模块，用于查询每个搜索结果信息对应的效果指标；搜索结果信息返回模块，用于将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
- 根据权利要求7所述的装置，其特征在于，所述装置还包括：待定结果获取模块，用于若某个搜索结果信息对应的效果指标低于所述第一预设阈值且高于第二预设阈值，将该搜索结果信息记为待定结果信息；所述搜索结果信息返回模块包括：返回子模块，用于将效果指标超过第一预设阈值的搜索结果信息以及所述待定结果信息，共同作为新的搜索结果信息返回给所述用户终端。
- 根据权利要求8所述的装置，其特征在于，所述装置还包括：操作信息接收模块，用于接收用户终端发送的针对所述待定结果信息的操作信息；预设条件判断模块，用于判断预设时间段内操作信息是否满足预设条件，若满足，则降低所述待定结果信息的效果指标至所述第二预设阈值以下。
- 根据权利要求7所述的装置，其特征在于，所述装置还包括：效果指标获取模块，用于获取每个搜索结果信息对应的效果指标，所述效果指标预先根据用户针对每个搜索结果信息的操作信息确定。
- 根据权利要求10所述的装置，其特征在于，所述装置还包括：匹配度获取模块，用于根据点击量、点击通过率、点击模型的拟合分数以及所述点击量、点击通过率、点击模型的拟合分数分别对应的匹配权重，获得并存储每个搜索结果信息与搜索请求对应的匹配度，并将 该匹配度作为效果指标。
- 一种服务器，其特征在于，所述服务器包括存储器和处理器，所述存储器耦接到所述处理器，所述存储器存储指令，当所述指令由所述处理器执行时，使所述处理器执行以下操作：接收用户终端发送的搜索请求；根据所述搜索请求获取多个搜索结果信息；查询每个搜索结果信息对应的效果指标；将效果指标超过第一预设阈值的搜索结果信息，作为新的搜索结果信息返回给所述用户终端。
- 一种计算机可读存储介质，其特征在于，存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-6中任一项所述的方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710751730.9 | 2017-08-28 | ||
| CN201710751730.9A CN109829098A (zh) | 2017-08-28 | 2017-08-28 | 搜索结果优化方法、装置及服务器 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019042165A1 true WO2019042165A1 (zh) | 2019-03-07 |
Family
ID=65524903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/101126 WO2019042165A1 (zh) | 2017-08-28 | 2018-08-17 | 搜索结果优化方法、装置、服务器及可读存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109829098A (zh) |
| WO (1) | WO2019042165A1 (zh) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181755B (zh) * | 2019-07-02 | 2024-05-10 | 腾讯科技（深圳）有限公司 | 一种确定搜索服务中参数阈值的方法及相关设备 |
| CN111797308B (zh) * | 2020-06-16 | 2023-11-28 | 北京达佳互联信息技术有限公司 | 一种资源推荐方法、装置、电子设备及介质 |
| CN111767259A (zh) * | 2020-06-29 | 2020-10-13 | 北京字节跳动网络技术有限公司 | 内容分享的方法、装置、可读介质和电子设备 |
| CN114254179A (zh) * | 2020-09-23 | 2022-03-29 | 北京达佳互联信息技术有限公司 | 搜索请求的处理方法、装置及搜索平台 |
| CN113254671B (zh) * | 2021-06-22 | 2021-09-28 | 平安科技（深圳）有限公司 | 基于query分析的图谱优化方法、装置、设备及介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9002832B1 (en) * | 2012-06-04 | 2015-04-07 | Google Inc. | Classifying sites as low quality sites |
| CN105159938A (zh) * | 2015-08-03 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | 检索方法和装置 |
| CN106294786A (zh) * | 2016-08-12 | 2017-01-04 | 北京创新乐知信息技术有限公司 | 一种代码搜索方法和系统 |
| US20170046435A1 (en) * | 2015-08-10 | 2017-02-16 | Microsoft Corporation | Search engine results system using entity density |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8249885B2 (en) * | 2001-08-08 | 2012-08-21 | Gary Charles Berkowitz | Knowledge-based e-catalog procurement system and method |
| US7386572B2 (en) * | 2004-04-14 | 2008-06-10 | Nancy Kramer | System and method for a modular user controlled search engine |
| CN101520784B (zh) * | 2008-02-29 | 2011-09-28 | 富士通株式会社 | 信息发布系统和信息发布方法 |
| CN101620605A (zh) * | 2008-07-04 | 2010-01-06 | 华为技术有限公司 | 搜索方法、搜索服务器和搜索系统 |
| CN102841904B (zh) * | 2011-06-24 | 2016-05-04 | 阿里巴巴集团控股有限公司 | 一种搜索方法及设备 |
| CN103218719B (zh) * | 2012-01-19 | 2016-12-07 | 阿里巴巴集团控股有限公司 | 一种电子商务网站导航方法及系统 |
| CN103838764B (zh) * | 2012-11-26 | 2019-04-30 | 深圳市世纪光速信息技术有限公司 | 一种搜索结果相关性评测方法及装置 |
| CN103226606B (zh) * | 2013-04-28 | 2016-08-10 | 浙江核新同花顺网络信息股份有限公司 | 查询选取方法及系统 |
| CN105512199B (zh) * | 2015-11-27 | 2020-04-14 | 广州神马移动信息科技有限公司 | 搜索方法、搜索装置以及搜索服务器 |
| CN105975547B (zh) * | 2016-04-29 | 2019-06-25 | 武汉大学 | 基于内容与位置特征的近似web文档检测方法 |
-
2017
- 2017-08-28 CN CN201710751730.9A patent/CN109829098A/zh active Pending
-
2018
- 2018-08-17 WO PCT/CN2018/101126 patent/WO2019042165A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9002832B1 (en) * | 2012-06-04 | 2015-04-07 | Google Inc. | Classifying sites as low quality sites |
| CN105159938A (zh) * | 2015-08-03 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | 检索方法和装置 |
| US20170046435A1 (en) * | 2015-08-10 | 2017-02-16 | Microsoft Corporation | Search engine results system using entity density |
| CN106294786A (zh) * | 2016-08-12 | 2017-01-04 | 北京创新乐知信息技术有限公司 | 一种代码搜索方法和系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829098A (zh) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019042165A1 (zh) | 搜索结果优化方法、装置、服务器及可读存储介质 | |
| US10783206B2 (en) | Method and system for recommending text content, and storage medium | |
| KR100462292B1 (ko) | 중요도 정보를 반영한 검색 결과 리스트 제공 방법 및 그시스템 | |
| US11580168B2 (en) | Method and system for providing context based query suggestions | |
| JP6152226B2 (ja) | キャッシュクエリ要求の生成 | |
| US20190018900A1 (en) | Method and Apparatus for Displaying Search Results | |
| US20150347594A1 (en) | Multi-domain search on a computing device | |
| US20140074527A1 (en) | Schedule generation method and communication terminal for schedule generation method | |
| US10235428B2 (en) | Discovery of news-related content | |
| US9940360B2 (en) | Streaming optimized data processing | |
| US10346496B2 (en) | Information category obtaining method and apparatus | |
| US20180011854A1 (en) | Method and system for ranking content items based on user engagement signals | |
| WO2009031759A1 (en) | Method and system for generating search collection of query | |
| JP2015106347A (ja) | レコメンド装置およびレコメンド方法 | |
| CN104090887A (zh) | 歌曲搜索方法及装置 | |
| US20140250116A1 (en) | Identifying time sensitive ambiguous queries | |
| US20150052126A1 (en) | Method and system for recommending relevant web content to second screen application users | |
| CN116108150A (zh) | 一种智能问答方法、装置、系统及电子设备 | |
| CN107622090B (zh) | 对象的获取方法、装置及系统 | |
| CN110796505B (zh) | 一种业务对象推荐方法以及装置 | |
| KR102046991B1 (ko) | 모바일 단말기용 핫토픽 키워드 관련 문서 제공 시스템, 방법 및 컴퓨터 판독 가능한 기록 매체 | |
| CN109271580B (zh) | 搜索方法、装置、客户端和搜索引擎 | |
| US20170180511A1 (en) | Method, system and apparatus for dynamic detection and propagation of data clusters | |
| CN113157629A (zh) | 数据处理方法、装置、电子设备及存储介质 | |
| CN106156024A (zh) | 一种信息处理方法及服务器 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18851264 Country of ref document: EP Kind code of ref document: A1 |