WO2017071578A1

WO2017071578A1 - Searching method, apparatus and system, and method for determining search result order adjustment basis

Info

Publication number: WO2017071578A1
Application number: PCT/CN2016/103364
Authority: WO
Inventors: 蔡明宸; 王筱钊; 曾洪雷
Original assignee: 广州神马移动信息科技有限公司
Priority date: 2015-10-27
Filing date: 2016-10-26
Publication date: 2017-05-04
Also published as: CN105302903B; CN105302903A

Abstract

Disclosed are a searching method, apparatus and system, and a method for determining a search result order adjustment basis. The searching method comprises: based on a current search word input by a user, obtaining a plurality of current search results by means of searching; acquiring a current operating environment where the user is located when performing an operation on the current search results; and using an order adjustment basis corresponding to the current operating environment to adjust the order of the plurality of current search results. Therefore, by means of the method of the present application, the order of search results can be adjusted according to an operating environment where the user is located, so that under the operation environment, a search result, for which the user's satisfaction degree is high, can be ranked at the front. In this way, a final order of search results can better satisfy the search requirements of a user, and thus the user's search experience can be improved.

Description

Search method, device, system and determination method of search result ordering basis

Technical field

The present application relates to the field of search, and in particular to a search method, an apparatus, a system, and a method for determining the basis of the search result.

Background technique

With the development of the network, more and more network resources are stored on the Internet, and search engines are widely used as an important retrieval tool for network resources.

At present, most search engines mainly sort the search results based on the matching degree of the website with the search keywords, website clicks, website quality, website ranking and other indicators. In addition, the user's operation behavior (such as click, browse, skip, etc.) on the search results reflects the user's demand and satisfaction degree of the search results, and is also an important reference factor for the current mainstream search engine to sort the search results. . Referring to the user's operation behavior on the search results, the search results are sorted, which can reflect the user's search requirements to a certain extent.

On the other hand, when users use search engines in different environments (such as location, network access type, time), the user's search needs will be different. For example, when a user searches for a terminal device such as a mobile phone under WIFI (WIreless-Fidelity), it tends to click on search results that consume more traffic, such as music, video, and APP (Application). Downloads, online games, and more. When users search in a non-WIFI network environment, they tend to click on search results with less traffic consumption, such as encyclopedia, novels, lyrics, and so on.

For example, for the same search term “flowers and bones”, when users search with WIFI, they can predict that they tend to click on the search results of videos containing “flowers and bones”, and when users use 2G, 3G When the network searches, it tends to click on search results that cost less traffic, such as spending thousands of bone novels and spending thousands of bones.

In summary, users have different requirements for search results in different environments. However, the current search engine and the existing sorting method of search results do not take into account the environment in which the user is located when sorting the search results. When users search in different environments, The search results presented by the search engine to the user are uniform and do not meet the individual needs of the user. Therefore, there is a need for a method for sorting search results according to the environment in which the user is located, so as to better satisfy the user's search requirements and improve the user's search experience.

Summary of the invention

A technical problem to be solved by the present application is to provide a search method, device, system and method and device for determining the basis of the search result, which can sort the search results according to the environment in which the user is located, so as to better satisfy the search result. User's search needs.

According to an aspect of the present application, a method for determining a search result ordering basis is disclosed, including: acquiring a search record of a plurality of users over a period of time, the search record comprising: a search term, obtained based on the search term a plurality of search results, operation information performed by the user on each of the search results, and an operation environment in which the user performs an operation on the search result; and calculating, according to the operation information, each search corresponding to the search term in the operating environment The satisfaction score of the results is used as the basis for the search results.

According to another aspect of the present application, a search method is disclosed, including: obtaining a plurality of current search results based on a current search term input by a user; and acquiring a current operating environment in which the user operates the current search result; And aligning the plurality of current search results according to a sequence basis corresponding to the current search term and the current operating environment.

According to still another aspect of the present application, a determining apparatus for determining a basis of a search result is disclosed, comprising: a search record obtaining unit, configured to acquire a search record of a plurality of users over a period of time, the search record comprising: a search term a plurality of search results obtained based on the search term, operation information performed by the user on each of the search results, and an operation environment in which the user performs an operation on the search result; a satisfaction score calculation unit, configured to The operation information calculates a satisfaction score for each search result corresponding to the search term in the operating environment, and uses the search result as a basis for the search result.

According to still another aspect of the present application, a search apparatus is disclosed, including: a current search result obtaining unit, configured to search for a plurality of current search results based on a current search term input by a user; and a current operating environment acquiring unit, configured to acquire a user a current operating environment in which the current search result is operated; a sequencer unit configured to compare the plurality of current search results according to a sequence basis corresponding to the current operating environment and the current search term Perform the sequence.

According to another aspect of the present application, a search system is disclosed, comprising a client and a search server, the client receiving a current search term input by a user and determining a current operating environment; the client to the current search term And the current operating environment is sent to the search server; the client receives a current search result from the search server, and the current search result is arranged in an order according to the current operating environment and the current search term. The corresponding order is adjusted according to the adjustment.

In accordance with still another aspect of the present application, a computing device is disclosed comprising: one or more processors; a memory; and one or more modules, the one or more modules being stored in the memory and configured to Executing by the one or more processors, wherein the one or more modules are configured to: obtain a plurality of current search results based on a current search term input by a user; and acquire an operation when the user operates the current search result a current operating environment in which the plurality of current search results are sequenced according to a scheduling basis corresponding to the current search term and the current operating environment.

According to still another aspect of the present application, a computer readable storage medium having a program on which a determination method for performing the aforementioned search result ordering is recorded is disclosed.

According to still another aspect of the present application, a computer readable storage medium having recorded thereon a program for executing the aforementioned search method is disclosed.

The searching method, the device, the system, and the determining method of the search result ordering basis of the present application may generate each search result of the search word in different operating environments based on the operation information of the user on the search result and the operating environment in which the operation is performed. The satisfaction score is used as the basis for the search results of the search words in the operating environment; thus, the order of the search results corresponding to the search words in different operating environments can be obtained; when the user is searching Can be used with users The current operating environment in which the current operating environment corresponds to the current search term is used to sequence the search results, so that the current search results with higher user satisfaction in the current operating environment can be ranked first, thereby enabling the final sorting of the search results. It can meet the user's search needs in this operating environment, which can enhance the user's search experience.

DRAWINGS

The above and other objects, features, and advantages of the present invention will become more apparent from the aspects of the embodiments of the invention. The same parts.

FIG. 1 is a schematic structural diagram of a search system of the present application;

2 is a schematic structural diagram of another search system of the present application;

FIG. 3 is a flow chart showing the steps of a search result ordering determining method according to the present application;

FIG. 4 shows a schematic flow chart of sub-steps S210, S220 which may be included in step S200 shown in FIG. 3;

FIG. 5 is a schematic flowchart of sub-steps S221, S222 which may be included in step S220 shown in FIG. 4;

FIG. 6 shows a schematic flow chart of sub-steps S225, S226, S227 which may be included in step S221 shown in FIG. 5;

Figure 7 is a flow chart showing the steps of a search method of the present application;

FIG. 8 is a structural block diagram of a determining apparatus for a search result ordering basis according to the present application;

9 is a structural block diagram of a determining apparatus for another search result ordering basis of the present application;

FIG. 10 is a block diagram showing the structure of a search device of the present application;

11 is a block diagram showing the structure of a computing device provided in accordance with an application embodiment.

detailed description

Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiment of the present invention has been shown in the drawings, it is understood that Instead, these implementations are provided to The disclosure is more complete and complete, and the scope of the present disclosure can be fully conveyed to those skilled in the art.

The application discloses a search system, which can adjust the order of the search results according to the operating environment in which the user is located, so that the search results with higher user satisfaction in the operating environment can be arranged in the front.

FIG. 1 shows a schematic structural diagram of a search system of the present application.

As shown in FIG. 1, the search system of the present application includes a client 1 and a search server 2. The client 1 can receive the current search term input by the user and determine the current operating environment, and the client 1 sends the current search term and the current operating environment to the search server 2. The client 1 receives the current search result from the search server 2. The order of the current search results received by the client 1 has been adjusted according to the ordering basis corresponding to the current operating environment.

The client 1 can be a client application installed on a terminal such as a mobile phone or a tablet. The search server 2 can determine the order of the current search results according to the current search term and the current operating environment received from the client 1, and send the current search results in the order to the client 1.

The current operating environment may be the network environment in which the user performs operations on the search results (ie, network access types, such as 2G (2-Generation wireless telephone technology), 3G, 4G, WIFI, etc.) ), geographic location (such as at home, on the road, in the unit, at tourist attractions, etc.), time (such as working hours (8:30-17:30), rest time, network idle time (for example, 0:00 to 6: 00 when the Internet is cheaper, when the network is busy (for example, when the Internet is expensive from 6:00 to 24:00), etc.), the default search mode (may be pre-configured on the client 1) Search mode for user selection, such as extreme mode, video mode, no picture mode, etc.).

In general, the current operating environment is consistent with the environment in which the user searches. Therefore, in the case where the requirements are not strict, the environment in which the user searches is also obtained as the current operating environment.

The purpose of adjusting the order of the search results based on the ordering basis is to make the current search results with higher user satisfaction in the current operating environment be ranked first.

When the user's current operating environment is different, the user's search needs are different. Therefore, The order of the search results in different operating environments is also different.

FIG. 2 shows a schematic structural diagram of another search system of the present application.

As shown in FIG. 2, the search system may also optionally include a sequencing basis determining device 3 and a sequencing based storage device 4.

The scheduling basis determining means 3 can acquire search records of a plurality of users over a period of time from a plurality of clients 1 or search servers 2. The search record may include: a search term, a plurality of search results obtained based on the search term, operation information performed by the user on each search result, and an operation environment in which the user performs an operation on the search result.

Based on the operation information, the order-based determining device 3 can calculate the satisfaction scores of the respective search results corresponding to the search words in the operating environment as the basis for the search results. The sequencing basis determining means 3 can store the calculated satisfaction score in the sequence dependent storage means 4. When the user searches using the client 1, the search server 2 can query the satisfaction scores of the current search results from the ordering storage device 4 based on the current search term and the current operating environment, and compare the satisfaction scores according to the satisfaction scores. The order of the current search results is adjusted. The adjusted multiple current search results are then displayed on client 1.

Wherein, when the search server 2 performs the sequence adjustment on the plurality of current search results, the existing sorting result may be adjusted by using a bubble method. Specifically, if the satisfaction scores of two adjacent current search results are reversed and the difference exceeds a certain threshold, the order of the two search results is reversed until the current search result is in accordance with the corresponding satisfaction score. Arrange in order of size. Of course, the ordering method (such as the selection ordering method, the insertion ordering method, and the like) other than the bubbling method is also within the protection scope of the ordering method of the embodiment of the present application.

In addition, the client 1 or the search server 2 may record the current search term, the current search result, the current operating environment, and the user's operation information on the current search result in association in the search record. Thus, on the one hand, the search server 2 can sort the current search results according to the current operating environment recorded in the search record. On the other hand, the scheduling basis determining device 3 can also calculate the satisfaction score in the latest period of time according to the operating environment information and the operation information recorded by the client 1 or the search server 2, as different operating environments in the most recent period of time. The basis of the order.

In summary, the search system of the present application can select the order basis corresponding to the current operating environment and the current search term according to the current operating environment of the user, and search for the user based on the current search term. The order of the current search results is adjusted so that the current search results with higher user satisfaction in the current operating environment can be ranked first. Thus, the final ranked search results can better meet the search needs of the user in the current operating environment.

The ordering basis corresponding to the operating environment and the search term may be obtained by the order-based determining device 3 based on the historical search record of the large-scale user. Specifically, the order-based determining means 3 can acquire search results for a large-scale user for a period of time, operation information of the user on the search results, and an operating environment in which the operation is performed, and then determine different operations based on the data obtained above. The basis for the ordering in the environment.

The following is a detailed description of the method for determining the basis of the sequence in the different operating environments of the present application.

FIG. 3 is a flow chart showing the steps of a search result ordering determination method of the present application.

In step S100, a search record of a plurality of users over a period of time is acquired. The search record may include: a search term, a plurality of search results obtained based on the search term, operation information performed by the user on each search result, and an operating environment in which the user performs an operation on the search result.

The search record in a period of time may be a search record in a short-term time that can reflect the timeliness, or a search record in a long-term time in which a sufficient search record can be obtained.

For example, for a search term, some search results may be more concerned by users in the recent period of time. At this time, obtaining a search record in a short period of time can accurately reflect the user's search demand in a short period of time. For example, in the period after the “Tianjin Port Explosion Accident”, users may be more inclined to search results related to “Tianjin Port Explosion Accident” when searching for “Tianjin”. For example, the latest rescue situation, the latest number of victims, etc., this time is suitable for obtaining the user's search record in a short period of time.

For another example, for the search term "Great Wall", since the Great Wall exists for a long time, the user has a long-term concern for it. At this time, it is appropriate to select the search record of the “Great Wall” in a long period of time, so that the user operation data obtained is richer and more realistically reflects the user's search demand.

The operation information is the user's click on the search result. The operation information mentioned in this article may include, but is not limited to, one of clicks, views, duration, navigation clicks, last clicks, skipped times, or Several.

Among them, the number of navigation clicks refers to the number of times the user clicks on the navigation website when searching based on the search term. For example, when searching for Tencent News, the official website of Tencent News is equivalent to a navigation website.

The operational information can be used to reflect the satisfaction (demand) of the search results in the operating environment in which the user is performing the operation. For example, for a search term in the same operating environment, multiple search results can be obtained based on the search term, and the search result with a large number of clicks reflects to a certain extent that the user has higher satisfaction (demand) in the operating environment. The search results that are skipped more frequently reflect that the user's satisfaction (demand) is lower in the operating environment.

The operating environment can be a network access type, a geographic location, a time, a preset search mode, and the like. For details, please refer to the description of the current operating environment in FIG.

In step S200, based on the operation information, the satisfaction scores of the respective search results corresponding to the search words in the operating environment are calculated as the search result ordering basis.

For each search term, there are many search results. In the actual search, according to the existing arrangement, the search results ranked later are generally not the search results required by the user. Therefore, in order to simplify the calculation process, the satisfaction score of the previous predetermined number of search results among the plurality of search results obtained based on the search term may be calculated as the search result ordering basis. For example, the satisfaction score of the first two pages of the search results of each search term can be calculated. Of course, the first two pages of search results are only a predetermined number of optional embodiments. In fact, the pre-determined number of the embodiment of the present application may be any value. , such as the first three pages of search results, the first four pages of search results, and so on.

The calculated satisfaction score can be stored in the form of a key-value. The key is the search term and the operating environment in which the search is performed, and the value is the satisfaction score of each search result corresponding to the search term in the operating environment.

Based on the operation information, the satisfaction scores of the respective search results corresponding to the search words in the operating environment are calculated. In other words, based on the operational information of a search result, the satisfaction score of the search result is calculated. Among them, the size of the satisfaction score represents the level of satisfaction of the user with the search result. Therefore, it can be foreseen that the user has higher satisfaction with the search results with more clicks and longer stay time, and therefore the satisfaction score is also higher.

In summary, the user's operation information on the search results can reflect the user's satisfaction with the search results. Therefore, based on the operation information of the plurality of search results based on one search term in the same operating environment, the satisfaction scores of the search results corresponding to the search term in the operating environment can be obtained. value.

Specifically, depending on the operational information, there are many ways to calculate the satisfaction score. For example, the satisfaction score can be calculated using the assignment method. The operation information includes a click operation n,

The length of time t and the skip operation n' are taken as an example. The satisfaction score of one click operation can be preset as s ₁ , the satisfaction score of unit stay time is s ₂ , and the satisfaction score of one skip operation is s ₃ . Wherein, s ₁ >0, s ₂ >0, s ₃ <0 (the values of s ₁ , s ₂ , and s ₃ may be preset according to specific conditions). Thus, for a search result, the satisfaction score score=n ₁ ·s ₁ +t ₁ ·s ₂ +n' ₁ ·s ₃ , where n ₁ , t ₁ , n′ ₁ respectively represent the search result Clicks, duration, and number of skips.

Another method for calculating the satisfaction score based on the operation information will be described in detail below with reference to FIG.

4 is a flow chart of sub-steps S210, S220 that may be included in step S200 of FIG.

In step S210, the operation information is normalized to obtain an operation feature value of each search result corresponding to the search word in the operating environment; the operation feature value indicates that the corresponding operation time performed on the search result occupies the same operation The ratio of the number of corresponding operations performed by all search results for the same search term in the environment.

Wherein, the operation feature value corresponds to the operation information. For example, when the operation information is the number of clicks, the operation characteristic value is the click rate. According to FIG. 2, the operation information may include, but is not limited to, one or more of a click number, a browsing count, a stay duration, a navigation click count, a last click count, and a skipped number. Accordingly, the operational feature values may include, but are not limited to, one or more of a click rate, a browsing rate, a long click rate, a navigation click rate, a last click rate, and a skip rate.

In addition, since the operation information can indicate the user's satisfaction with the search result, the operation feature value can also indicate the user's satisfaction with the search result. Specifically, search results with high click-through rate, browsing rate, long click rate, and last click rate have higher user satisfaction.

In step S220, based on the operation feature value, the satisfaction score of each search result corresponding to the search term in the operating environment is calculated.

The calculation of the satisfaction score may be performed by using the assignment method described in step S200 in FIG. 3, or may be performed by other methods. FIG. 5 is another way of calculating the satisfaction score based on the operational feature values, as shown in FIG. 5.

FIG. 5 shows a schematic flow chart of sub-steps S221, S222 which may be included in step S220 shown in FIG.

In step S221, a satisfaction model in different operating environments is established.

The satisfaction model can represent a weighted average of multiple operational feature values, and the corresponding formula is as follows:

Where, Score is the satisfaction score, F _i is the operation feature value, W _i is the weight of the corresponding operation feature value, and n is the number of the operation feature values.

As can be seen from the above equation, the satisfaction model gives the weight (ie, the coefficient) of the operational feature values in different operating environments.

In step S222, based on the operation feature value and the satisfaction model, the satisfaction scores of the respective search results corresponding to the search words in different operating environments are obtained.

According to the weight of the operation feature value and the operation feature value of the search result in the obtained satisfaction model, the satisfaction score of the search result can be calculated.

In summary, the weight (coefficient) of the operational feature values can be obtained by establishing a satisfaction model, and then the weights of the operational feature values and the operational feature values of the large-scale users in different operating environments are obtained according to the obtained different operating environments. The satisfaction scores (ordering basis) of each search result corresponding to the search words in different operating environments can be obtained.

The following is a detailed description of the establishment process of the satisfaction model in conjunction with FIG. 6.

FIG. 6 is a flow chart of sub-steps S225, S226, S227 which may be included in step S221 shown in FIG. 5.

In step S225, for each operating environment, a partial search result is selected from the search results corresponding to the operating environment as a training sample.

That is to say, part of the search record can be selected from the search records of large-scale users as training samples.

At step S226, a sample satisfaction score is assigned to each search result in the training sample.

A sample satisfaction score can be assigned to each search result in the training sample by manual annotation and/or click annotation.

Among them, manual annotation and click annotation are used to indicate the satisfaction of the user's demand for search results. The difference is that manual annotation is based on natural results to assign search results. In other words, manual annotation is based on the text matching degree of search results and search terms, search results. Authoritative, quality, etc. information to give the search results a sample satisfaction score. The click mark is based on the user's operation information on the search result (which can also be the operation feature value) to assign the search result. Therefore, in the actual assignment process, a combination of manual annotation and click annotation can be preferably employed. In this way, the assignment result can be made closer to the user's satisfaction.

In step S227, the satisfaction model in different operating environments is trained based on the training sample and the sample satisfaction score.

For multiple search results in the same operating environment, the operational feature values and sample satisfaction scores of each search result in the sample are known. At this time, the satisfaction model of the linear relationship between the operational feature values and the weights can be trained. (Refer to the expression of the satisfaction model in step S221 in Fig. 4) to obtain the weight of each operation feature value in the satisfaction model. Optionally, the training method of the above-mentioned satisfaction model may include: SVM (Support Vector Machine), LDA (linear discriminant analysis), etc., it can be understood that the specific embodiment of the present application is specific to the satisfaction model. Training methods are not limited.

It should be noted that, in the embodiment of the present application, the search result of the operating environment may change with time, which will result in a change in the training sample and the sample satisfaction score. In this case, the latest training sample will be used. And the sample satisfaction score, the satisfaction model is trained to obtain the latest weight of each operational feature value.

The method of determining the basis of the sequencing in the different operating environments of the present application is described in detail above with reference to FIGS. 3 through 6. It can be seen that the sequencing of the present application is based on a set of satisfaction scores for multiple search results of search terms in different operating environments.

Figure 7 is a flow chart showing the steps of a search method of the present application.

In step S400, a plurality of current search results are searched based on the current search term input by the user.

The current search term input by the user may be received by the client, and then the current search term is sent to the server. The server may search for a plurality of current search results based on the current search term received by the client, and the plurality of current search results obtained by the search may be arranged according to the existing sorting mode.

In step S500, the current operation loop in which the user operates the current search result is obtained. territory. The current operating environment may be a network environment in which the user performs an operation on the search result (ie, network access type, such as 2G, 3G, 4G, WIFI, etc.), geographic location, time, preset search mode (may be a client) A plurality of user-selectable search modes, such as an extreme speed mode, a video mode, a no-image mode, and the like, are provided in advance on the terminal 1.

Among them, the current operating environment in which the user needs to operate the search result can be obtained through the client. In general, the current operating environment is the same as the environment in which users search. Therefore, in the case where the requirements are not strict, the environment in which the user searches is also obtained as the current operating environment.

In step S600, the plurality of current search results are sequenced according to the ordering basis corresponding to the current search term and the current operating environment.

The client can send the obtained current search term and the current operating environment to the server. The server may sequence the plurality of current search results by using a sequence corresponding to the current search term and the current operating environment, and send the adjusted current search result to the client for browsing by the user.

Through the search method of the present application, the current search result with higher user satisfaction in the current operating environment can be ranked first. The method for determining the basis of the sequence can be seen in FIG. 3 to FIG. 6 , and details are not described herein again.

It can be seen from FIG. 7 that the search method proposed by the present application can sort multiple current search results according to the current search term input by the user and the current operating environment in which the user is located, using the ordering basis corresponding to the current search term and the current operating environment. The current search results with higher satisfaction scores can be displayed in front, which can well meet the user's search needs and improve the user's search experience.

Optionally, the scheduling basis corresponding to the current operating environment may be obtained by: querying, according to the current search term and the current operating environment, the current search from the stored content in the form of a key-value The satisfaction score of the word corresponding to the current operating environment.

In addition, based on the search method of the present application, the current operating environment in which the user performs the current search and the operation information performed for each current search result may also be recorded in the user's search log and/or search result operation log. In this way, not only the user's operating environment and operation information are conveniently obtained, but also the arrangement of the plurality of current search results is adjusted according to the obtained current search term and the current operating environment, and the current operating environment and operation information of the record can be used as New search history to keep multiple users' search records updated over time.

The search method of the present application can provide users with different ranked current search results under different current operating environments. Taking the current search term "April April" as an example, the corresponding current search results include: TV dramas, poems, encyclopedias, etc. of the same name; in the WIFI environment, users are more inclined to demand TV dramas, while using traffic Under the circumstances, it is more inclined to demand encyclopedia and poetry. In the WiFi environment, the TV drama, the encyclopedia, and the poetry can be arranged in the order from the front to the back in the WiFi environment. In the traffic environment, the encyclopedia, the poetry, and the TV drama are arranged in the order from front to back, so that it can be better. Meet the needs of users in different operating environments.

The determination method and the search method according to the scheduling basis of the present application are described in detail above with reference to FIGS. 3-7. The configuration of the scheduling basis determining apparatus, the search apparatus, and its related units of the present application will be described below with reference to FIGS. 8-10.

The functions of many of the units of the apparatus described below are the same as those of the corresponding steps described above with reference to Figures 3-7, respectively. In order to avoid repetition, the unit or device structure that the device and the system may have is mainly described herein, and details are not described in detail, and reference may be made to the corresponding description above.

FIG. 8 is a block diagram showing the structure of a determining apparatus for sorting the search results according to the present application.

As shown in FIG. 8, the determining means may include a search record acquisition unit 100 and a satisfaction score calculation unit 200.

The search record obtaining unit 100 is configured to acquire search records of a plurality of users for a period of time, and the search records may include: search words, multiple search results obtained based on the search words, operation information performed by the user on each search result, and user-to-search The operating environment in which the result is performed.

The satisfaction score calculation unit 200 is configured to calculate a satisfaction score of each search result corresponding to the search term in the operating environment based on the operation information, as a basis for the search result.

For a specific function description of the search record obtaining unit 100 and the satisfaction score calculation unit 200, reference may be made to the related descriptions of step S100 and step S200 in FIG.

FIG. 9 is a structural block diagram of a determining apparatus for another search result ordering basis of the present application.

As shown in FIG. 9, the satisfaction score calculation unit 200 may optionally include: an operation feature value The unit 210 and the calculation unit 220 are acquired.

The operation feature value obtaining unit 210 is configured to normalize the operation information to obtain an operation feature value of each search result corresponding to the search word in the operation environment; the operation feature value represents a corresponding operation time of the search result The ratio of the number of corresponding operations performed for all search results corresponding to the same search term in the same operating environment;

The calculating unit 220 is configured to calculate a satisfaction score of each search result corresponding to the search word in the operating environment based on the operation feature value.

For a description of related functions of the operation feature value obtaining unit 210 and the computing unit 220, refer to the related description of steps S210 and S220 in FIG.

As shown in FIG. 9, in an optional embodiment of the present application, the determining apparatus may further include a satisfaction model establishing unit 300.

The satisfaction model training unit 300 is configured to establish a satisfaction model in different operating environments, and the calculating unit 220 is specifically configured to calculate the satisfaction of each search result of the search words in different operating environments based on the operating feature value and the satisfaction model. Score.

The structure of the satisfaction model established by the satisfaction model training unit 300 can be referred to the related description of step S221 in FIG.

As shown in FIG. 9 , in an optional embodiment of the present application, the satisfaction model training unit 300 may further include: a training sample acquiring unit 310, a sample satisfaction score assigning unit 320, and a model training unit 330.

The training sample acquisition unit 310 is configured to select a partial search result as a training sample from the search results corresponding to the operating environment for each operating environment.

The sample satisfaction score assigning unit 320 is configured to assign a sample satisfaction score to each of the search results in the training sample.

The model training unit 330 is configured to train the satisfaction model in different operating environments based on the training samples and the sample satisfaction scores.

A detailed description of the functions of the training sample acquisition unit 310, the sample satisfaction score assignment unit 320, and the model establishment unit 330 can be referred to the description of the relevant steps in FIG.

As shown in FIG. 9, in an optional embodiment of the present application, the determining apparatus may further include: a satisfaction score storage unit 400. Satisfaction score storage unit for key-value The form stores the satisfaction score, wherein the key is a search term and an operating environment in which the search is performed, and the value is a satisfaction score for each search result of the search term in the operating environment.

FIG. 10 is a block diagram showing the structure of a search device of the present application.

As shown in FIG. 10, the search apparatus of the present application may include a current search result acquisition unit 600, a current operating environment acquisition unit 700, and a sequencer unit 800.

The current search result obtaining unit 600 is configured to obtain a plurality of current search results based on the current search word search input by the user.

The current operating environment obtaining unit 700 is configured to acquire a current operating environment in which the user operates the current search result.

The sequencer unit 800 is configured to sequence the plurality of current search results according to a sequence basis corresponding to the current search term and the current operating environment.

For a detailed description of the related functions of the current search result obtaining unit 600, the current operating environment acquiring unit 700, and the sequence unit 800, refer to FIG.

In addition, the searching apparatus of the present application may further include the determining device according to the search result ordering manner described in FIG. 8 or FIG. 9, and the determining device may obtain multiple current search words in the current operating environment. The satisfaction score of the current search result, and then the sequence unit 800 may sequence the plurality of current search results according to the size of the satisfaction score corresponding to each current search result.

As shown in FIG. 10, the search device may also optionally include a current operating environment information recording unit 900.

The current operating environment information recording unit 900 may record, in the user's search log and/or the search result operation log, the current operating environment in which the user performs the current search, and the operation information performed for each current search result.

The determination method and apparatus for the search method, apparatus, system, and search result ordering basis according to the present application have been described in detail above with reference to the accompanying drawings.

Furthermore, the method according to the present application can also be embodied as a computer program product comprising a computer readable medium having stored thereon a computer program for performing the functions described above in the method of the present application . Those skilled in the art will also understand The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or combinations of both.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the system and the device described above can refer to the corresponding process in the foregoing method embodiments, and details are not described herein again.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, 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 that illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that 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 function. Or it can be implemented by a combination of dedicated hardware and computer instructions.

The functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, the technical solution of the present application, 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 various embodiments of the present application. 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. .

11 is a structural block diagram of a computing device provided in accordance with an embodiment of the present invention. The computing device can be implemented as various types of computer devices, such as desktops, portable computers, tablets, smart phones, personal data assistants (PDAs), smart wearable devices, or other types of computer devices, but is not limited to any particular form. . The computer may include: a processor 1101, a memory 1102, an input device 1103, a display 1104, a network interface 1105, And bus 1106.

The processor 1101 may be a multi-core processor or may include multiple processors. In some embodiments, processor 1101 can include a general purpose main processor and one or more special coprocessors, such as a graphics processing unit (GPU), a digital signal processor (DSP), and the like. In some embodiments, the processor 1101 can be implemented using custom circuitry, such as an application specific integrated circuit (ASIC) or field programmable gate arrays (FPGA). In some implementations, processor 1101 can be a similar circuit that executes executable instructions stored on itself. In still other implementations, the processor 1101 can execute executable instructions stored on the memory 1102.

Memory 1102 can include various types of storage units, such as system memory, read only memory (ROM), and persistent storage. Among them, the ROM can store static data or instructions required by the processor 1101 or other modules of the computer. The persistent storage device can be a readable and writable storage device. The persistent storage device may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (eg, magnetic or optical disk, flash memory) as the permanent storage device. In other embodiments, the persistent storage device can be a removable storage device (eg, a floppy disk, an optical drive). The system memory can be a readable and writable storage device or a volatile read/write storage device, such as dynamic random access memory. System memory can store instructions and data that some or all of the processors need at runtime. Moreover, memory 1102 can comprise any combination of computer readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read only memory), and magnetic disks and/or optical disks can also be employed. In some implementations, the memory 1102 can include a removable storage device that is readable and/or writable, such as a compact disc (CD), a read-only digital versatile disc (eg, a DVD-ROM, a dual layer DVD-ROM), Read-only Blu-ray discs, ultra-density discs, flash cards (such as SD cards, min SD cards, Micro-SD cards, etc.), magnetic floppy disks, and so on. The computer readable storage medium does not include a carrier wave and an instantaneous electronic signal transmitted by wireless or wire. In some embodiments, the memory 1102 can store one or more software programs that can be executed by the processor 1101 or resource files that need to be called. The resource files can include some third-party libraries, including but not limited to an audio library, a video library, and 2D. Graphics library, 3D graphics library.

The user interface can be input by one or more user input devices 1103, display 1104, and/or One or more other user output devices are provided. Input device 1103 can include means for a user to input signals to a computer that can interpret such signals to include particular user requests or information. In some embodiments, a web address may be input to the user interface through a keyboard to display webpage content corresponding to the input webpage. In some embodiments, input device 1103 can include some or all of a keyboard button, touch screen, mouse or other pointing device, scroll wheel, click wheel, dial, button, switch, keypad, microphone, and the like.

The display 1104 can display computer generated images, and can include various types of image devices such as cathode ray tubes (CRTs), liquid crystal displays (LCDs), light emitting diodes (LEDs) including organic light emitting diodes (OLEDs), projection systems. And other collections of supporting electronic devices (such as DACs, ADCs, signal processors, etc.). In some embodiments, it is also possible to additionally provide other user output devices, or to replace display 1104, such as a signal light, a speaker, a tactile sensor, a printer, and the like.

In some embodiments, the user interface can be provided through a graphical user interface. Certain areas of the display 1104 define some visual graphical elements as interactive objects or control objects that the user selects through the input device 1103. For example, the user can operate the user input device 1103 to move the specified location input URL on the screen, and control the display of the webpage content corresponding to the webpage on the display 1104. In some embodiments, a touch device that can recognize a user gesture can be used as an input device, which may, but need not, be associated with an array on display 1103.

Network interface 1105 provides sound and/or data communication functionality to the computer. In some embodiments, the network interface 1105 can include a radio frequency transceiver to communicate voice and/or data (eg, using cellular telephone technology, such as 3G, 4G or EDGE, WIFI data network technology), GPS receiver modules, and/or other Module. In some embodiments, network interface 1105 can provide an additional wireless network connection or an alternative wireless interface. Network interface 1105 may be a combination of hardware (eg, antennas, modems, codecs, and other analog and/or digital signal processing circuits) and software modules.

The bus 1106 can include various systems, external devices, and chip buses that connect various components within the computer. For example, the bus 1106 connects the processor 1101 and the memory 1102, and may also connect the input device 1103 and the display 1104. Bus 1106 can also cause a computer to interface with the network via network interface 1105. In this case, the computer can act as multiple networked computer devices. portion. Any or all of the components of the computer can be used in concert in embodiments of the present invention.

Some embodiments include electronic components, such as a microprocessor, a memory that stores computer instructions and data in a computer readable storage medium. Many of the features described in the Detailed Description section can be implemented by the method steps of executing computer instructions stored on a computer readable storage medium. When these computer instructions are executed, the computer processing unit performs various functions of the instructions. The embodiment of the program instructions or computer code may be machine code, such as code compiled using a computer, electronic component or microprocessor of the object to be parsed to compile other high-level languages.

It is to be understood that the computer shown in Figure 11 is illustrative. The computer may have other functions not specifically described (eg, mobile call, GPS, power management, one or more cameras, various connection ports or accessories for connecting external devices, etc.). Further, specific functional modules involved in computing devices are described herein, which are described for ease of description and do not imply a specific physical configuration of the functional components. Moreover, these functional modules do not need to be in one-to-one correspondence with physical modules. The module can be configured to perform various operations, such as by programming or setting up appropriate control circuitry, and the module may be reconfigured according to initial settings. Embodiments of the invention may be implemented in a variety of devices, including electronic devices, through the use of a combination of hardware and software.

The embodiment further provides a non-volatile readable storage medium, wherein the storage medium stores one or more programs, and when the one or more programs are applied to the computing device, the The computing device performs the following steps (instructions):

Obtaining a search record of a plurality of users over a period of time, the search record comprising: a search term, a plurality of search results obtained based on the search term, operation information performed by the user on each of the search results, and a user searching for the search The operating environment in which the operation is performed;

Based on the operation information, a satisfaction score of each search result corresponding to the search term in the operating environment is calculated as a basis for the search result.

The embodiment further provides a non-volatile readable storage medium, wherein the storage medium stores one or more programs, and when the one or more programs are applied to the computing device, the computing device can be executed The instructions in the following steps:

Searching for a plurality of current search results based on a current search term input by the user;

Obtaining a current operating environment in which the user operates the current search result;

And aligning the plurality of current search results according to a sequence basis corresponding to the current search term and the current operating environment.

The above is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and should cover Within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims

A method for determining the basis of the search results, including:

Obtaining a search record of a plurality of users over a period of time, the search record comprising: a search term, a plurality of search results obtained based on the search term, operation information performed by the user on each of the search results, and a user searching for the search The operating environment in which the operation is performed;

Based on the operation information, a satisfaction score of each search result corresponding to the search term in the operating environment is calculated as a basis for the search result.
The determining method according to claim 1, wherein the step of calculating a satisfaction score of each search result corresponding to the search term in the operating environment based on the operation information comprises:

Normalizing the operation information to obtain operation feature values of respective search results corresponding to the search words in the operating environment; the operation feature values indicating that the corresponding operations performed on the search results occupy the same operating environment The ratio of the number of corresponding actions performed by all search results for the same search term;

Based on the operational feature value, a satisfaction score for each search result corresponding to the search term in the operating environment is calculated.
The determining method according to claim 2, wherein the calculating the satisfaction score for each search result corresponding to the search term in the operating environment based on the operating feature value comprises:

Establish a satisfaction model in different operating environments;

Based on the operation feature value and the satisfaction model, the satisfaction scores of the respective search results corresponding to the search words in different operating environments are obtained.
The determining method according to claim 3, wherein the satisfaction model is used to represent a weighted average of a plurality of operational feature values.
The determining method according to claim 3, wherein the step of establishing a satisfaction model in different operating environments comprises:

For each operating environment, select a part of the search results from the search results corresponding to the operating environment as a training sample;

Assigning a sample satisfaction score to each of the search results in the training sample;

A satisfaction model in different operating environments is trained based on the training sample and the sample satisfaction score.
The determining method according to claim 5, wherein said step of assigning a sample satisfaction score to each of said search results in said training sample comprises:

A sample satisfaction score is assigned to each of the search results in the training sample using manual annotation and/or click annotation.
The determining method according to claim 2, wherein

The operation information includes at least one of the following: a click count, a browse count, a stay duration, a navigation click count, a last click count, and a skipped number;

The operation characteristic value includes at least one of the following: a click rate, a browsing rate, a long click rate, a navigation click rate, a last click rate, and a skip rate.
The determining method according to claim 1, further comprising:

The satisfaction score is stored in the form of a key-value, wherein the key is a search term and an operating environment in which the search is performed, and the value is a satisfaction score of each search result corresponding to the search term in the operating environment. value.
The determining method according to claim 1, wherein the operating environment comprises at least one of the following:

Network access type, geographic location, time, preset search mode.
The determining method according to claim 1,

Wherein, the period of time includes: a short-term time capable of exhibiting timeliness; or

The period of time includes: long-term time to get enough search records
The determining method according to claim 1, wherein the calculating the satisfaction score of each search result corresponding to the search term in the operating environment based on the operation information comprises:

From the respective search results corresponding to the search words in the operating environment, a predetermined number of search results are selected, and based on the operation information, a satisfaction score of the predetermined predetermined number of search results is calculated.
A search method that includes:

Searching for a plurality of current search results based on a current search term input by the user;

Obtaining a current operating environment in which the user operates the current search result;

And aligning the plurality of current search results according to a sequence basis corresponding to the current search term and the current operating environment.
The search method according to claim 12, wherein the ordering is based on a satisfaction score of a plurality of current search results corresponding to the current search term in the current operating environment;

The step of using the sequence corresponding to the current operating environment to sequence the plurality of current search results includes:

And sorting the plurality of the current search results according to the size of the satisfaction score corresponding to each of the current search results.
The search method according to claim 12, wherein the ordering basis corresponding to the current operating environment is obtained by the following steps:

And according to the current search term and the current operating environment, the satisfaction score corresponding to the current search term and the current operating environment is queried from the stored content in the form of key-value.
The search method of claim 13, further comprising:

In the user's search log and/or search result operation log, the current operating environment information in which the user performs the current search result is recorded.
A determining device for sorting the search results includes:

a search record obtaining unit, configured to acquire a search record of a plurality of users over a period of time, the search record comprising: a search term, a plurality of search results obtained based on the search term, and an operation performed by the user on each of the search results Information and an operating environment in which the user performs an operation on the search result;

The satisfaction score calculation unit is configured to calculate, according to the operation information, a satisfaction score for each search result corresponding to the search term in the operating environment, as a basis for the search result.
The determining device according to claim 16, wherein the satisfaction score calculation unit comprises:

An operation feature value obtaining unit, configured to normalize the operation information to obtain an operation feature value of each search result corresponding to the search word in the operation environment; the operation feature value represents a pair The ratio of the number of corresponding operations performed by the search result to the total number of operations performed on all search results corresponding to the same search term in the same operating environment;

And a calculating unit, configured to calculate a satisfaction score for each search result corresponding to the search term in the operating environment based on the operation feature value.
The determining device according to claim 17, further comprising:

Satisfaction model training unit for establishing satisfaction models in different operating environments;

Then, the calculating unit is specifically configured to calculate a satisfaction score of each search result corresponding to the search term in different operating environments based on the operation feature value and the satisfaction model.
The determining apparatus according to claim 18, wherein said satisfaction model training unit comprises:

a training sample obtaining unit, configured to select, from each of the search results corresponding to the operating environment, a partial search result as a training sample for each operating environment;

a sample satisfaction score giving unit for assigning a sample satisfaction score to each of the search results in the training sample;

A model training unit is configured to train a satisfaction model in different operating environments based on the training sample and the sample satisfaction score.
The determining device according to claim 16, further comprising:

a satisfaction score storage unit, configured to store the satisfaction score in a form of a key-value, wherein the key is a search term and an operating environment in which the search is performed, and the value is a search term corresponding to the operating environment. Satisfaction score for each search result.
A search device comprising:

a current search result obtaining unit, configured to search for a plurality of current search results based on a current search term input by the user;

a current operating environment acquiring unit, configured to acquire a current operating environment in which the user operates the current search result;

a sequence unit, configured to sequence the plurality of current search results according to a sequence basis corresponding to the current operating environment and the current search term.
The search device according to claim 21, wherein said sequencing is based on said current operation a satisfaction score of a plurality of current search results corresponding to the current search term in the environment;

The sequencer unit is specifically configured to sequence the plurality of the current search results according to the size of the satisfaction score corresponding to each of the current search results.
The search device of claim 21, further comprising:

The current operating environment information recording unit is configured to record, in the user's search log and/or the search result operation log, a current operating environment in which the user performs the current search, and operation information performed for each current search result.
A search system including a client and a search server;

The client receives the current search term input by the user and determines the current operating environment;

The client sends the current search term and the current operating environment to the search server;

The client receives the current search result from the search server, and the order of the current search results has been adjusted according to the order according to the current operating environment and the current search term.
The search system according to claim 24, further comprising: a sequencing basis determining means and a sequencing dependent storage means;

The scheduling according to the determining device acquires, from a plurality of the clients or the search server, search records of a plurality of users for a period of time, the search records include: a search term, and a plurality of search words based on the search words. Search results, operation information performed by the user on each of the search results, and an operating environment in which the user performs an operation on the search results;

The scheduling-based determining device calculates a satisfaction score for each search result corresponding to the search term in the operating environment based on the operation information, as a basis for sorting the search results;

The sequencing stores the satisfaction score according to a storage device;

The search server queries the satisfaction score of the current search result according to the storage device based on the current search term and the current operating environment, and compares the current search result according to the satisfaction score. Adjust the order.
A search system according to claim 25, wherein

The client or the search server correlates the current search in a search record The word, the current search result, the current operating environment, and the user's operational information on the current search result.
A computing device comprising: a memory, and one or more programs, wherein one or more programs are stored in a memory and configured to be executed by one or more processors, the one or more programs included for Instructions for doing the following:

Obtaining a search record of a plurality of users over a period of time, the search record comprising: a search term, a plurality of search results obtained based on the search term, operation information performed by the user on each of the search results, and a user searching for the search The operating environment in which the operation is performed;

Based on the operation information, a satisfaction score of each search result corresponding to the search term in the operating environment is calculated as a basis for the search result.
A computer readable storage medium having recorded thereon a program for performing the method of any one of claims 1 to 11.
A computing device comprising: a memory, and one or more programs, wherein one or more programs are stored in a memory and configured to be executed by one or more processors, the one or more programs included for Instructions for doing the following:

Searching for a plurality of current search results based on a current search term input by the user;

Obtaining a current operating environment in which the user operates the current search result;

And aligning the plurality of current search results according to a sequence basis corresponding to the current search term and the current operating environment.
A computer readable storage medium having recorded thereon a program for performing the method of any one of claims 12 to 15.