CN111078998B

CN111078998B - Information retrieval method, device, storage medium and server

Info

Publication number: CN111078998B
Application number: CN201911137073.4A
Authority: CN
Inventors: 郭子亮
Original assignee: Oppo Chongqing Intelligent Technology Co Ltd
Current assignee: Oppo Chongqing Intelligent Technology Co Ltd
Priority date: 2019-11-19
Filing date: 2019-11-19
Publication date: 2024-03-12
Anticipated expiration: 2039-11-19
Also published as: CN111078998A

Abstract

The application discloses an information retrieval method, an information retrieval device, a storage medium and a server, wherein the information retrieval method comprises the following steps: receiving a search request sent by a terminal, wherein the search request comprises an entry to be searched and a user portrait; performing retrieval processing based on the to-be-retrieved entry to obtain a retrieval result, wherein the retrieval result comprises multi-entry label information corresponding to the to-be-retrieved entry; sorting the multi-item label information according to the user image to obtain first sorting information; and returning the first ordering information to the terminal, so that the terminal displays the multi-item label information according to the first ordering information. According to the information retrieval scheme provided by the embodiment, the terminal displays the multi-item target information according to the first ordering information, and can display the target information which is more attached to the retrieval intention of the terminal user, so that the terminal user can acquire the required information quickly, and the quality of information retrieval is improved.

Description

Information retrieval method, device, storage medium and server

Technical Field

The application belongs to the technical field of information, and particularly relates to an information retrieval method, an information retrieval device, a storage medium and a server.

Background

With the continuous development of networks, information inquiry based on search websites has become a common search mode for people.

In the related art, the user queries information based on the search website, and the finally obtained search information is not necessarily all information required by the user, for example, the search information carries junk information such as product promotion. Therefore, it takes much time for the user to screen the search information to acquire information required by the user.

Disclosure of Invention

The embodiment of the application provides an information retrieval method, an information retrieval device, a storage medium and a server, which are beneficial to a user to quickly acquire needed information from a plurality of target information.

In a first aspect, an embodiment of the present application provides an information retrieval method, including:

receiving a search request sent by a terminal, wherein the search request comprises an entry to be searched and a user portrait;

performing retrieval processing based on the to-be-retrieved entry to obtain a retrieval result, wherein the retrieval result comprises multi-entry label information corresponding to the to-be-retrieved entry;

sorting the multi-item label information according to the user image to obtain first sorting information;

and returning the first ordering information to the terminal, so that the terminal displays the multi-item label information according to the first ordering information.

In a second aspect, an embodiment of the present application provides an information retrieval apparatus, including:

the receiving module is used for receiving a search request sent by the terminal, wherein the search request comprises an entry to be searched and a user portrait;

the acquisition module is used for carrying out search processing based on the entry to be searched to acquire a search result, wherein the search result comprises multi-entry mark information corresponding to the entry to be searched;

the first ordering module is used for ordering the multi-item label information according to the user image to obtain first ordering information;

and the return module is used for returning the first ordering information to the terminal so that the terminal displays the multi-item label information according to the first ordering information.

In a third aspect, a storage medium provided in an embodiment of the present application has a computer program stored thereon, which when executed on a computer causes the computer to perform an information retrieval method as provided in any embodiment of the present application.

In a fourth aspect, a server provided by an embodiment of the present application includes a processor and a memory, where the memory has a computer program, and the processor is configured to execute an information retrieval method provided by any embodiment of the present application by calling the computer program.

According to the information retrieval scheme provided by the embodiment of the application, as the first ordering information can be formulated for different users, the terminal displays the multi-item target information according to the first ordering information, and can display the target information which is more attached to the retrieval intention of the terminal user in advance, so that the terminal user can acquire the needed information from the multi-item target information quickly.

Drawings

The technical solution of the present application and the advantageous effects thereof will be made apparent from the following detailed description of the specific embodiments of the present application with reference to the accompanying drawings.

Fig. 1 is a schematic diagram of a first scenario of an information retrieval method according to an embodiment of the present application.

Fig. 2 is a schematic flow chart of a first procedure of an information retrieval method according to an embodiment of the present application.

Fig. 3 is a second flow chart of the information retrieval method according to the embodiment of the present application.

Fig. 4 is a second scenario diagram of an information retrieval method according to an embodiment of the present application.

Fig. 5 is a schematic diagram of a third scenario of an information retrieval method according to an embodiment of the present application.

Fig. 6 is a third flow chart of the information retrieval method according to the embodiment of the present application.

Fig. 7 is a schematic structural diagram of an information retrieval device according to an embodiment of the present application.

Fig. 8 is a first structural schematic diagram of a server according to an embodiment of the present application.

Fig. 9 is a second structural schematic diagram of a server provided in an embodiment of the present application.

Detailed Description

The following description is based on the illustrated embodiments of the present application and should not be taken as limiting other embodiments not described in detail herein. The term "module" as used herein may be considered as a software object executing on the computing system. The various modules, engines, and services herein may be viewed as implementation objects on the computing system.

The embodiment of the application provides an information retrieval method, and an execution subject of the information retrieval method can be an information retrieval device provided by the embodiment of the application or a server integrated with the information retrieval device, wherein the information retrieval device can be realized in a hardware or software mode.

The embodiment of the application provides an information retrieval system, which comprises a terminal and a server, wherein the server is used for retrieving according to an entry to be retrieved to obtain multi-entry tag information corresponding to the entry to be retrieved; and ordering the multi-label information, the server also being used for web filtering, i.e. limiting the category of the entry to be retrieved and limiting the category of the multi-label information.

The implementation mode of the server can be an independent server or a server cluster formed by a plurality of servers.

Referring to fig. 1, fig. 1 is a schematic diagram of a first scenario of an information retrieval method according to an embodiment of the present application. The information retrieval system comprises a terminal and a server cluster, wherein the server cluster comprises a first server and a second server. The first server is mainly used for searching according to the entry to be searched to obtain multi-entry tag information corresponding to the entry to be searched. The second server mainly sorts the multi-item label information, and the web filters, namely, limits the category of the to-be-searched entry sent to the first server and limits the category of the multi-item label information returned by the first server. The information retrieval means may be integrated in the second server.

In addition, the client in the application is installed in a terminal, and the terminal can be a mobile phone, a tablet computer and other devices.

When the client needs the first server to provide the target information for display, the client sends a search request to the second server through the terminal. The second server receives the search request sent by the terminal, obtains the entry to be searched, the user portrait and the like by analyzing the search request, and sends the entry to be searched to the first server. After receiving the entry to be searched sent by the second server, the first server searches in the information base according to the entry to be searched to obtain a search result, and returns the search result to the second server, wherein the search result comprises multi-entry mark information corresponding to the entry to be searched. And after receiving the search result returned by the first server, the second server sorts the multi-item label information in the search result according to the user image to obtain first sorting information, and returns the first sorting information to the terminal. And after receiving the first ordering information returned by the second server, the terminal displays the multi-item label information on the display interface according to the first ordering information. Therefore, the terminal user can quickly acquire the information needed by the user from the multi-item label information. Hereinafter, for convenience of description, the first server will be referred to as a search server, and the second server will be referred to as a filter server.

Referring to fig. 2, fig. 2 is a schematic flow chart of a first information retrieval method according to an embodiment of the present application, where the information retrieval method may include:

101. and receiving a search request sent by the terminal, wherein the search request comprises an entry to be searched and a user portrait.

For example, when the terminal needs the server to provide the target information for display, the terminal generates a search request and transmits the search request to the server. The server receives a search request sent by the terminal. The search request includes an entry to be searched and a user portrait.

The to-be-searched entry is obtained by expanding a terminal according to a search formula input by a user, and the to-be-searched entry can be one or more. For example, the terminal detects that the retrieval formula input by the user is "sorghum rice", and expands according to the retrieval formula of "sorghum rice" to obtain a plurality of terms to be retrieved such as "science popularization knowledge of sorghum rice", "how big the sorghum rice is, and" commodity recommendation of sorghum rice ". For another example, the terminal detects that the search formulas input by the user are "XX and YY wedding officials", and the terminal expands according to the search formulas "XX and YY wedding officials", so that the obtained entry to be searched is still "XX and YY wedding officials".

The user portrait is an effective tool for outlining users and contacting user requirements and design directions. The terminal can collect the data of the user, label the data, and embody the user image through the label, so as to obtain the user portrait. A user may have one portrayal of one type, and a user may have multiple portraits of a different type, such as a base portrayal containing basic data of age, gender, occupation, academic, etc., a behavioral characteristics portrayal containing behavioral data of applications, trips, etc. The types of data of the tags constituting the portrait are different, which results in different types of the portrait to be obtained.

In some embodiments, each time the collected data reaches a target amount, the terminal generates a user representation from the collected data and clears the statistical amount of the collected data to allow the terminal to re-count the amount of the collected data.

In some embodiments, the terminal obtains a new user portrait according to target data by taking the data collected in each preset time as target data so as to replace the original user portrait, thereby realizing the update of the user portrait. For example, when the terminal collects data a as target data within a predetermined time period (1 month 10 day to 2 month 9 day) and obtains user portrait a based on the target data, the terminal sets user portrait a as the portrait of the terminal user for 2 months 10 day to 3 months 9 day. The data B is collected as target data within a preset time (2 months 10 days to 3 months 9 days) within 3 months 10 days, and the user portrait B is obtained according to the target data, so that the terminal takes the user portrait B as the portrait of the terminal user within 2 months 10 days to 3 months 9 days, and so on.

102. And carrying out retrieval processing based on the entry to be retrieved, and obtaining a retrieval result, wherein the retrieval result comprises multi-entry label information corresponding to the entry to be retrieved.

For example, after receiving the entry to be searched, the server performs search processing according to the entry to be searched to obtain a search result. The search result comprises multi-item label information corresponding to the entry to be searched.

103. And sorting the multi-item label information according to the user image to obtain first sorting information.

For example, after obtaining the search result, the server may sort the multiple pieces of label information in the search result according to the user portrait in the search request, to obtain the first sort information. In the scheme, because the user portrait is an effective tool for outlining the user and contacting the user appeal and the design direction, the multi-item label information is ordered according to the user portrait, and the obtained first ordering information can be formulated for different users.

For example, the end user "Zhang Sano" and the end user "Liqu" are both transmitted to the server including the term to be retrieved "at noon". The server performs retrieval processing according to the term to be retrieved in the noon to obtain a retrieval result. The multi-item label information in the search result is expressed as "target information E1, target information E2, target information E3, target information E4, target information E5". After the server obtains the search result, the 5 items of target information are ordered according to the user pictures of Zhang Sano to obtain first ordering information Y1, and the 5 items of target information are ordered according to the user pictures of Zhun Sano to obtain first ordering information Y2. The first ranking information Y1 obtained by the server is different from the first ranking information Y2 because the user portraits of the different users are not identical, i.e. the user portraits of "Zhang San" are different from the user portraits of "Liqu".

If the user image included in the search request transmitted from the terminal to the server is a plurality of images, the server may sort the multi-item target information by integrating the plurality of images when sorting the multi-item target information based on the user image, or may sort the multi-item target information by selecting one image from the plurality of images.

In addition, the embodiment of the present application is not specifically limited to the specific expression mode of the first ranking information. For example, the first ranking information may be ranked by the title of the target information. For example, the first ranking information may also be represented by adding a sequence number, such as "\2", to the back of each target information. For example, the first ranking information may be represented by the order of placement of the target information.

104. And returning the first ordering information to the terminal, so that the terminal displays the multi-item label information according to the first ordering information.

For example, after sorting the multi-item label information according to the user image to obtain the first sorting information, the server may return the first sorting information to the terminal. After receiving the first ordering information returned by the server, the terminal uses the first ordering information as a display sequence and displays the multi-item label information on a display interface.

As can be seen from the above, in the embodiment of the present application, after receiving a search request sent by a terminal, a server may perform search processing based on a term to be searched to obtain a search result, where the search result includes multiple item target information corresponding to the term to be searched, then sort the multiple item target information according to a user image to obtain first sort information, and finally return the first sort information to the terminal, so that the terminal displays the multiple item target information according to the first sort information. In the scheme, the first ordering information returned by the server can be formulated for different users, so that the terminal displays multiple items of target information according to the first ordering information, and can display target information which is more fit with the retrieval intention of the terminal user in advance, thereby being beneficial to the terminal user to quickly acquire the needed information and further improving the quality of information retrieval.

Referring to fig. 3, fig. 3 is a second flow chart of the information retrieval method according to the embodiment of the present application.

201. And receiving a search request sent by the terminal, wherein the search request comprises an entry to be searched and a user portrait.

For example, when the terminal needs to provide the target information for display by the search server, the terminal generates a search request and transmits the search request to the filter server. The filter server receives the search request sent by the terminal. The search request includes an entry to be searched and a user portrait.

In some embodiments, the retrieval request further includes a terminal parameter and a server parameter. The terminal parameter is mainly used for informing the object returned by the filtering server, and the server parameter is mainly used for informing the object sent by the filtering server, so that information retrieval errors caused by object transmission errors can be reduced.

Wherein the server parameters include parameters characterizing the identity of the server, which may be one or more. For example, the parameter characterizing the identity of the server may be the name of the server, etc.

In this solution, the terminal parameters include parameters characterizing the terminal identity, and the parameters characterizing the terminal identity may be one or more. For example, the parameters characterizing the identity of the terminal may be the terminal identity, the client user name, the mobile phone number, the user mailbox, etc. The terminal identity may be represented by an international mobile equipment identity (IMEI, international Mobile Station Equipment Identity) or a mobile equipment identity (MEID, mobile Station Equipment Identifier).

202. And sending the entry to be searched to a search server, and indicating the search server to search according to the entry to be searched.

For example, after receiving a search request sent by a terminal, the filtering server may send an entry to be searched in the search request to the search server, and instruct the search server to search in the information base according to the entry to be searched.

Wherein the search server stores a large amount of information in the information base. The retrieval server can update, add and delete the information in the information base so as to ensure timeliness of the information in the information base. In addition, the embodiments of the present application are not particularly limited as to the source of information in the information repository. For example, information in the information base may originate from a plurality of terminals connected to the search server, and information in the information base may originate from another server connected to the search server, or the like.

In some embodiments, when searching is performed in the information base according to the entry to be searched, the search server may obtain a matching value of the entry to be searched and each piece of information in the information base, take the piece of information with the matching value greater than the first preset threshold value as multi-entry target information corresponding to the entry to be searched, and generate a search result according to the multi-entry target information.

In some embodiments, when searching is performed in the information base according to the to-be-searched term, the search server may obtain a matching value of the to-be-searched term and a tag in the information base, take the tag with the matching value greater than a second preset threshold value as a target tag, take information with the target tag in the information base as multi-item tag information corresponding to the to-be-searched term, and generate a search result according to the multi-item tag information. Wherein, each information in the information base is correspondingly provided with a label. The labels of any two messages may be the same or different.

It will be appreciated that the target information in the information base that matches a term may be a plurality of pieces. For example, the retrieval server obtains the matching value of each piece of information in the information base and the entry to be retrieved of the Kaoliang spirit, and taking the information with the matching value larger than the first preset threshold value as target information of the corresponding 'Kaoliang spirit' to-be-searched entry, obtaining 4-item target information, and marking the target information as target information D1, target information D2, target information D3 and target information D4. Wherein the target information D1 is a sorghum porridge recipe, the target information D2 is a sorghum rice recipe, the target information D3 is a coarse cereal pancake recipe, and the target information D4 is a sorghum steamed corn bread recipe.

In some embodiments, when the search server generates the search result according to the multi-item target information, the search server may combine the multi-item target information in the order of searching to generate the search result. But the solution does not prescribe different orders of combination for different end users. For example, the end user xiao Li and the end user's small sheets are both the words to be searched including the mid-autumn term and are transmitted to the search server through the filter server, and the search server performs search according to the words to be searched in mid-autumn. And sequentially obtaining target information C1, target information C2, target information C3, target information C4 and target information C5 according to the sequence of retrieval. At this time, the search server is the search result transmitted to the end user "xiao Li" or the search result of the end user "sheetlet", and the combination order of the target information in the two search results is the same, and the target information C1, the target information C2, the target information C3, the target information C4, and the target information C5 are all the target information C2.

In some embodiments, the method further includes, before the sending the to-be-retrieved entry to the retrieval server, the steps of:

deleting the to-be-searched entries meeting a fourth preset condition from the plurality of to-be-searched entries;

sending the entry to be searched to a search server, comprising:

and sending at least one to-be-searched entry after deleting the to-be-searched entry meeting the fourth preset condition to a search server.

In the scheme, before the filtering server sends the to-be-searched entry to the searching server, the to-be-searched entry and the preset entry can be matched, if the matching is successful, the to-be-searched entry is judged to meet a fourth preset condition, and if the matching is unsuccessful, the to-be-searched entry is judged to not meet the fourth preset condition. Then deleting the entry to be searched which meets the fourth preset condition, and sending at least one deleted entry to be searched to a search server.

The filtering server is provided with preset entries in advance, wherein the preset entries mainly comprise entries of the following preset categories: any one or more of spam, product promotion, platform content, phishing websites. It will be appreciated that the information retrieved by the retrieval server according to the preset vocabulary entry is generally unlikely to be content of interest to the user.

It should be noted that, in this scheme, before sending the entry to be searched to the search server, the entry to be searched satisfying the fourth preset condition is deleted, so that the search result obtained by the search server has less junk content, thereby improving the search quality.

203. And receiving a search result returned by the search server, wherein the search result comprises multi-item label information corresponding to the entry to be searched.

For example, after the search server performs search according to the entry to be searched and returns the search result to the filter server, the filter server receives the search result returned by the search server. The search result comprises multi-item label information corresponding to the entry to be searched.

204. And scoring each piece of target information according to the multiple images to obtain the recommendation score of each piece of target information.

For example, the user portraits in the search request include a plurality of portraits having different types. After receiving the search result returned by the search server, the filter server may score each target information according to the multiple portraits in the search request, to obtain a recommendation score of each target information.

In some embodiments, when scoring each piece of target information according to a plurality of images to obtain a recommendation score of each piece of target information, the filtering server may score each piece of target information according to each image to obtain a plurality of scoring values; and carrying out weighted summation on the multiple scoring values according to the weight corresponding to each image to obtain the recommendation score of each piece of target information.

For example, assuming that the user representation includes 5 representations of different types, respectively denoted as a first representation, a second representation, a third representation, a fourth representation, and a fifth representation, the recommendation score per item of label information can be expressed as:

P＝k ₁ p ₁ +k ₂ p ₂ +k ₃ p ₃ +k ₄ p ₄ +k ₅ p ₅

wherein P represents the recommendation score of each item of target information, P ₁ A first score value, p, representing the first image-based score of each item of label information ₂ A second evaluation indicating that each item of the target information is obtained based on the second imageScore, p ₃ A third score value p representing a third score value obtained based on a third image for each item of label information ₄ A fourth score value p representing a fourth score value obtained based on a fourth image for each item of label information ₅ A fifth score value k representing a fifth score value obtained based on the fifth image for each item of label information ₁ Represents a first weight value, k ₂ Representing a second weight value, k ₃ Represents a first weight value, k ₄ Representing a second weight value, k ₅ Representing a second weight value.

It will be appreciated that k ₁ 、k ₂ 、k ₃ 、k ₄ And k is equal to ₅ The sum of the first weight value, the second weight value, the third weight value, the fourth weight value and the fifth weight value is 1.

In some embodiments, the first image may be a base representation of the user including base data of the user for age, gender, occupation, academic, income, etc. The second image may be a behavioral profile of the user, the behavioral profile including behavioral data of the user, such as an application installed on the terminal by the user, a travel track of the user, and the like. The third image may be a representation of the user's interest, including the most trivial type of content used by the user. The fourth image may be a social representation of the user, the social representation including a friend-making relationship chain of the user. The fifth image may be a mental value representation of the user including payment data for the user on each application. In this scheme, the third image is used as the most important adjustment basis, and the third weight value is set to be the largest of the 5 weight values. For example, the third weight value is set to 50%, and the other weight values are set to 12.5%.

205. And sorting the multi-item label information according to the recommendation score to obtain first sorting information.

For example, after obtaining the recommendation score of each target information, the filtering server may sort the plurality of target information according to the recommendation score of each target information from high to low according to the recommendation score, so as to obtain the first sorting information.

For example, referring to fig. 4, fig. 4 is a second scenario diagram of an information retrieval method according to an embodiment of the present application. Assume that the filtering server receives 6 pieces of target information transmitted from the search server and marks the 6 pieces of target information L1, target information L2, target information L3, target information L4, target information L5, and target information L6 as shown in fig. 4. The filter server obtains recommendation scores of 6 items of mark information according to the user portrait: target information L1 (86 minutes), target information L2 (77 minutes), target information L3 (75 minutes), target information L4 (99 minutes), target information L5 (71 minutes) and target information L6 (80 minutes), and 6 items of target information are ordered according to the height of the recommended score to obtain first ordering information, wherein the first ordering information is: target information L4, target information L1, target information L6, target information L2, target information L3, target information L5, as shown in fig. 4. It should be noted that, the earlier the first ranking of the target information shown in fig. 4, the greater the probability of interest to the user, i.e., the maximum probability of interest to the target information L4, the second probability of interest to the target information L1, and so on.

206. And taking the target information which does not meet the first preset condition as first target information and taking the target information which meets the first preset condition as second target information.

For example, after obtaining the first ordering information, the filtering server may classify a plurality of target information, that is, target information that does not satisfy the first preset condition is regarded as first target information, and target information that satisfies the first preset condition is regarded as second target information.

The meeting of the first preset condition refers to information belonging to a preset category, and the preset category comprises any one or more of junk advertisements, product promotion, platform content and phishing websites. It will be appreciated that information that generally satisfies the first preset condition is unlikely to be content of interest to the user.

In some embodiments, when the target information that does not satisfy the first preset condition is taken as the first target information and the target information that satisfies the first preset condition is taken as the second target information, the filtering server may determine whether each target information belongs to any one of the preset categories, if so, determine that the target information satisfies the first preset condition and take the target information that satisfies the first preset condition as the second target information, and if not, determine that the target information does not satisfy the first preset condition and take the target information that does not satisfy the first preset condition as the first target information.

For example, referring to fig. 5, fig. 5 is a schematic diagram of a third scenario of the information retrieval method according to the embodiment of the present application. The filtering server classifies 6 items of target information, namely, target information meeting a first preset condition is taken as second target information (target information L4, target information L1, target information L2 and target information L5), and target information not meeting the first preset condition is taken as first target information (target information L6 and target information L3).

207. And according to the ordering of the first target information in preference to the ordering of the second target information, adjusting the first ordering information to obtain the second ordering information.

For example, after taking the target information which does not meet the first preset condition as the first target information, such as the target information L6 and the target information L3 in fig. 5, and taking the target information which meets the first preset condition as the second target information, such as the target information L4, the target information L1, the target information L2 and the target information L5 in fig. 5, the filtering server may adjust the first ordering information according to the ordering of the first target information in preference to the ordering of the second target information, so as to obtain the second ordering information. As shown in fig. 5, the first ordering information is prioritized over the ordering of the second target information in order of the ordering of the first target information: target information L4, target information L1, target information L6, target information L2, target information L3, target information L5, and obtaining second ordering information: target information L4, target information L1, target information L2, target information L5, target information L6, target information L3.

For example, assume that the first ranking information is: target information D5, target information D2, target information D1, target information D3 and target information D4, wherein the target information D2 is product promotion and the target information D3 is spam advertisement. Then, the filtering server classifies the 5 pieces of target information to obtain first target information: target information D5, target information D1, and target information D4, and second target information: target information D2 and target information D3. The filtering server adjusts the first ordering information according to the ordering of the first target information in preference to the ordering of the second target information, and the second ordering information is obtained as follows: target information D5, target information D1, target information D4, target information D2, target information D3.

208. And returning the second ordering information to the terminal, so that the terminal displays the multi-item label information according to the second ordering information.

For example, after adjusting the first ordering information to obtain the second ordering information, the filtering server may return the second ordering information to the terminal. And after receiving the second ordering information returned by the filter server, the terminal takes the second ordering information as a display sequence and displays the multi-item label information on a display interface.

It should be noted that, in general, the information that satisfies the first preset condition is unlikely to be content of interest to the user. In a special case, the information meeting the first preset condition may be content of interest to the user, and if the user wants to search for the content, the product is promoted, so deleting the information meeting the first preset condition easily causes that the user cannot acquire the required information. In the scheme, on the premise of not deleting any information, the user is interested in the preceding display and is not interested in the following display, so that the user can be ensured not to miss any useful things, the user experience can be improved, and the information retrieval quality is improved.

Referring to fig. 6, fig. 6 is a third flow chart of the information retrieval method according to the embodiment of the present application.

301. And receiving a search request sent by the terminal, wherein the search request comprises a plurality of to-be-searched entries and user portraits.

For example, when the terminal needs to provide the target information for display by the search server, the terminal generates a search request and transmits the search request to the filter server. The filtering server receives a search request sent by a terminal, wherein the search request comprises a plurality of to-be-searched entries and user portraits.

302. And taking the entry to be searched which does not meet the third preset condition as a first entry, and taking the entry to be searched which meets the third preset condition as a second entry.

For example, after receiving a search request sent by a terminal, the filtering server may classify a plurality of to-be-searched terms, that is, the to-be-searched terms that do not meet the third preset condition are used as first terms, and the to-be-searched terms that meet the third preset condition are used as second terms.

The meeting of the third preset condition refers to the entry to be searched belonging to a preset category, and the preset category comprises any one or more of junk advertisements, product promotion, platform content and phishing websites. It will be appreciated that, in general, information retrieved according to the entry to be retrieved that satisfies the third preset condition is unlikely to be content of interest to the user.

In some embodiments, when an entry that does not satisfy the third preset condition is used as the first entry and an entry that satisfies the third preset condition is used as the second entry, the filtering server may determine whether each entry to be searched belongs to any one of the preset categories, if so, determine that the entry satisfies the third preset condition, and use the entry to be searched that satisfies the third preset condition as the second entry, and if not, determine that the entry to be searched does not satisfy the third preset condition, and use the entry to be searched that does not satisfy the third preset condition as the first entry.

303. And according to the sorting of the first vocabulary entries in preference to the sorting of the second vocabulary entries, sorting the plurality of vocabulary entries to be searched, and obtaining third sorting information.

For example, after taking the to-be-searched entry which does not meet the third preset condition as the first entry and taking the to-be-searched entry which meets the third preset condition as the second entry, the filtering server may obtain third ranking information according to the ranking of the first entry in preference to the ranking of the second entry.

For example, assume that the entry to be retrieved in the retrieval request is: the method comprises the steps of searching an entry E1, an entry E2, an entry E3, an entry E4 and an entry E5, wherein the entry E2 is a product promotion, and the entry E3 is a spam advertisement. Then, the filtering server classifies the 5 terms to be searched to obtain a first term: to-be-retrieved entry E5, to-be-retrieved entry E1, and to-be-retrieved entry E4, and a second entry: the entry to be retrieved E2 and the entry to be retrieved E3. The filtering server adjusts the first ordering information according to the ordering of the first vocabulary entries in preference to the ordering of the second vocabulary entries, and the second ordering information is obtained as follows: the entry to be searched E5, the entry to be searched E1, the entry to be searched E4, the entry to be searched E2 and the entry to be searched E3.

304. And sending the to-be-searched entry and the third ordering information to a search server, and indicating the search server to search according to the to-be-searched entry by taking the third ordering information as a search sequence.

For example, after obtaining the third ranking information, the filtering server sends the entry to be retrieved and the third ranking information to the retrieval server. And after receiving the to-be-searched entry and the third ordering information, the search server uses the third ordering information as a search sequence and searches according to the to-be-searched entry.

305. And receiving a search result returned by the search server, wherein the search result comprises multi-item label information corresponding to the entry to be searched.

For example, after the search server uses the third ordering information as the search order, searches according to the entry to be searched, and returns the search result to the filter server, the filter server receives the search result returned by the search server. The search result comprises multi-item label information corresponding to the entry to be searched.

306. And sorting the multi-item label information according to the user image to obtain first sorting information.

For example, after receiving the search result returned by the search server, the filter server may sort the multi-item label information in the search result according to the user portrait in the search request, to obtain the first sort information. In the scheme, because the user portrait is an effective tool for outlining the user and contacting the user appeal and the design direction, the multi-item label information is ordered according to the user portrait, and the obtained first ordering information can be formulated for different users.

307. And deleting target information meeting the second preset condition in the multi-item target information.

For example, after the first ordering information is obtained, the filtering server may delete the target information meeting the second preset condition in the multiple-item target information. The meeting of the second preset condition refers to information belonging to a preset category, and the preset category comprises any one or more of junk advertisements, product promotion, platform content and phishing websites. It will be appreciated that information that satisfies the second preset condition is generally unlikely to be content of interest to the user.

In some embodiments, the filtering server may delete the target information satisfying the second preset condition in the multi-item target information, and then sort the multi-item target information according to the user image to obtain the first sorting information.

308. And returning the at least one item of target information after deleting the target information meeting the second preset condition and the first ordering information to the terminal, so that the terminal displays the at least one item of target information after deleting the target information meeting the second preset condition according to the first ordering information.

For example, after deleting the target information meeting the second preset condition in the multiple item target information, the filtering server may return at least one item target information and the first ordering information after deleting the target information meeting the second preset condition to the terminal. After receiving at least one item of target information and first ordering information which are returned by the filter server and are deleted to meet the target information of the second preset condition, the terminal uses the first ordering information as a display sequence, and displays the multi-item of target information which is deleted to meet the target information of the second preset condition on a display interface.

It should be noted that, because some target information related to the first ordering information is deleted, in this solution, the filtering server needs to return not only the first ordering information to the terminal, but also at least one item of target information after deleting the target information meeting the second preset condition to the terminal, so as to instruct the terminal to display only the target information in the at least one item of target information when displaying according to the first ordering information.

For example, assume that at least one item of label information received by the terminal is: the target information Q1, the target information Q2, the target information Q3, the first ordering information received is: target information Q1- (1), target information Q2- (3), target information Q3- (2), and target information Q4- (4). At this time, the terminal only needs to display the target information Q1, the target information Q2 and the target information Q3 when displaying according to the first ordering information, i.e. the target information Q1, the target information Q3 and the target information Q2 are arranged on the display interface from top to bottom to display.

Fig. 7 is a schematic structural diagram of an information retrieval device according to an embodiment of the present application, where the device is configured to execute the information retrieval method according to the foregoing embodiment, and has functional modules and beneficial effects corresponding to the execution method. As shown in fig. 7, the information retrieval apparatus 400 specifically includes: a receiving module 401, an acquiring module 402, a first ordering module 403, and a returning module 404, wherein:

A receiving module 401, configured to receive a search request sent by a terminal, where the search request includes an entry to be searched and a user portrait;

an obtaining module 402, configured to perform a search process based on the entry to be searched, and obtain a search result, where the search result includes multi-entry tag information corresponding to the entry to be searched;

a first sorting module 403, configured to sort the multi-item label information according to the user image, to obtain first sorting information;

and a returning module 404, configured to return the first ordering information to the terminal, so that the terminal displays the multi-item label information according to the first ordering information.

In some embodiments, the user representation comprises a plurality of representations of different types, and the first ordering module 403 is further configured to, when ordering the multi-label information according to the user representation, obtain first ordering information:

scoring each piece of target information according to the multiple portraits to obtain a recommendation score of each piece of target information;

and sorting the multi-item label information according to the recommendation score to obtain first sorting information.

In some embodiments, when scoring each target information according to the multiple portraits, the first ranking module 403 is further configured to:

For each piece of target information, scoring is carried out according to each image respectively, and a plurality of scoring values are obtained;

and carrying out weighted summation on the multiple scoring values according to the weight corresponding to each image to obtain the recommendation score of each piece of target information.

In some embodiments, the information retrieval device 400 further comprises a first classification module and an adjustment module before returning the first ranking information to the terminal;

the first classification module is configured to take target information that does not meet a first preset condition as first target information, and take target information that meets the first preset condition as second target information;

the adjusting module is used for adjusting the first ordering information according to the ordering of the first target information in preference to the ordering of the second target information to obtain second ordering information;

when the first ordering information is returned to the terminal, so that the terminal displays the multi-item label information according to the first ordering information, the returning module 404 is further configured to:

and returning the second ordering information to the terminal, so that the terminal displays the multi-item label information according to the second ordering information.

In some embodiments, the information retrieval apparatus 400 further comprises a first deletion module before returning the first ranking information to the terminal;

the first deleting module is used for deleting target information meeting a second preset condition in the multi-item target information;

and returning at least one item of target information after deleting the target information meeting the second preset condition and the first ordering information to the terminal, so that the terminal displays at least one item of target information after deleting the target information meeting the second preset condition according to the first ordering information.

In some embodiments, when performing the search processing based on the entry to be searched, the obtaining module 402 may further be configured to:

sending the entry to be searched to a search server, and indicating the search server to search according to the entry to be searched;

and receiving a search result returned by the search server.

In some embodiments, the to-be-searched term is plural, and before the to-be-searched term is sent to a search server, the search server is instructed to search according to the to-be-searched term, the information search apparatus 400 further includes a second classification module and a second ranking module;

The second classification module is configured to take, as a first term, a term to be searched that does not satisfy a third preset condition, and take, as a second term, a term to be searched that satisfies the third preset condition;

the second sorting module is used for sorting the plurality of entries to be searched according to the sorting of the first entries in preference to the sorting of the second entries, so as to obtain third sorting information;

when the entry to be searched is sent to a search server and the search server is instructed to search according to the entry to be searched, the sending module is further configured to:

and sending the to-be-searched entry and the third ordering information to a search server, and indicating the search server to search according to the to-be-searched entry by taking the third ordering information as a search sequence.

In some embodiments, the to-be-retrieved entry is plural, and the information retrieval apparatus 400 further includes a second deletion module before the to-be-retrieved entry is sent to the retrieval server;

the second deleting module is used for deleting the to-be-searched entries meeting a fourth preset condition from the plurality of to-be-searched entries;

when the entry to be searched is sent to the search server, the sending module is further configured to:

As can be seen from the foregoing, in the information retrieval device provided in the embodiment of the present application, the receiving module 401 receives a retrieval request sent by a terminal, the retrieval request includes an entry to be retrieved and a user portrait, the obtaining module 402 performs a retrieval process based on the entry to be retrieved, obtains a retrieval result, the retrieval result includes multiple item label information corresponding to the entry to be retrieved, the first ordering module 403 orders the multiple item label information according to the user portrait, so as to obtain first ordering information, and the returning module 404 returns the first ordering information to the terminal, so that the terminal displays the multiple item label information according to the first ordering information. Target information which is more fit with the retrieval intention of the terminal user can be displayed in advance, which is beneficial to the terminal user to quickly acquire the required information, thereby improving the quality of information retrieval.

It should be noted that, the information retrieval device provided in the embodiment of the present application and the information retrieval method in the above embodiment belong to the same concept, and any method provided in the information retrieval method embodiment may be run on the information retrieval device, and detailed implementation processes of the method are shown in the information retrieval method embodiment, which is not repeated herein.

The present embodiments provide a computer-readable storage medium having stored thereon a computer program which, when executed on a computer, causes the computer to perform the steps in the information retrieval method as provided by the embodiments of the present application. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.

Referring to fig. 8, a server 500 includes a processor 501 and a memory 502. The processor 501 is electrically connected to the memory 502.

The processor 501 is a control center of the server 500, connects various parts of the entire server using various interfaces and lines, performs various functions of the server 500 and processes data by running or loading computer programs stored in the memory 502, and calling data stored in the memory 502.

The memory 502 may be used to store software programs and modules, and the processor 501 performs various functional applications and data processing by executing the computer programs and modules stored in the memory 502. The memory 502 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, a computer program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the server, etc.

In addition, memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide access to the memory 502 by the processor 501.

In the embodiment of the present application, the processor 501 in the server 500 loads the instructions corresponding to the processes of one or more computer programs into the memory 502 according to the following steps, and the processor 501 executes the computer programs stored in the memory 502, so as to implement various functions, as follows:

Referring to fig. 9, fig. 9 is a second structural schematic diagram of a server according to an embodiment of the present application, which is different from the server shown in fig. 8 in that the server further includes: display component 603, radio frequency circuitry 604, and power supply 605. The display component 603, the radio frequency circuit 604 and the power supply 605 are electrically connected to the processor 601 respectively.

The display component 603 can be used to display information entered by a user or provided to a user as well as various graphical user interfaces that can be composed of graphics, text, icons, video, and any combination thereof.

The radio frequency circuit 604 may be configured to receive and transmit radio frequency signals to and from a network device or other server via wireless communication to and from the network device or other server via wireless communication.

The power supply 605 may be used to power the various components of the server 600. In some embodiments, the power supply 605 may be logically connected to the processor 601 through a power management system, so as to perform functions of managing charging, discharging, and power consumption management through the power management system.

Although not shown, the server may further include an input unit or the like, which is not described herein.

In the embodiment of the present application, the processor 601 in the server 600 loads instructions corresponding to the processes of one or more computer programs into the memory 602 according to the following steps, and the processor 601 executes the computer programs stored in the memory 602, so as to implement various functions, as follows:

In some embodiments, the user representation comprises a plurality of representations of different types, and the processor 601 may perform, when sorting the multi-label information according to the user representation to obtain first sorting information:

In some embodiments, in scoring each target information based on the plurality of representations, the processor 601 may perform:

In some embodiments, before returning the first ordering information to the terminal, the processor 601 may perform:

taking the target information which does not meet the first preset condition as first target information and taking the target information which meets the first preset condition as second target information;

according to the ordering of the first target information in preference to the ordering of the second target information, the first ordering information is adjusted to obtain second ordering information;

when the first ordering information is returned to the terminal, so that the terminal displays the multi-label information according to the first ordering information, the processor 601 may perform:

Deleting target information meeting a second preset condition in the multi-item target information;

In some embodiments, before receiving the search result returned by the search server, the processor 601 may further perform:

and receiving a search result returned by the search server.

In some embodiments, the term to be searched is a plurality of terms, and the processor 601 may perform, before sending the term to be searched to a search server, instructing the search server to search according to the term to be searched:

taking the to-be-searched entry which does not meet the third preset condition as a first entry and taking the to-be-searched entry which meets the third preset condition as a second entry;

According to the sorting of the first vocabulary entries and the sorting of the second vocabulary entries, sorting the plurality of vocabulary entries to be searched to obtain third sorting information;

when the term to be searched is sent to a search server and the search server is instructed to search according to the term to be searched, the processor 601 may execute:

In some embodiments, the term to be retrieved is a plurality of terms, and the processor 601 may perform:

in sending the entry to be retrieved to the retrieval server, the processor 601 may perform:

As can be seen from the foregoing, after receiving the search request sent by the terminal, the server provided in the embodiment of the present application performs a search process based on the entry to be searched to obtain a search result, where the search result includes multiple entry target information corresponding to the entry to be searched, then sequences the multiple entry target information according to the user image to obtain first sequence information, and finally returns the first sequence information to the terminal, so that the terminal displays the multiple entry target information according to the first sequence information. Target information which is more fit with the retrieval intention of the terminal user can be displayed in advance, which is beneficial to the terminal user to quickly acquire the required information, thereby improving the quality of information retrieval.

The present application also provides a storage medium storing a computer program, which when executed on a computer, causes the computer to perform the information retrieval method of any of the above embodiments, such as: receiving a search request sent by a terminal, wherein the search request comprises an entry to be searched and a user portrait; performing retrieval processing based on the to-be-retrieved entry to obtain a retrieval result, wherein the retrieval result comprises multi-entry label information corresponding to the to-be-retrieved entry; sorting the multi-item label information according to the user image to obtain first sorting information; and returning the first ordering information to the terminal, so that the terminal displays the multi-item label information according to the first ordering information.

In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

It should be noted that, for the information retrieval method according to the embodiment of the present application, it will be understood by those skilled in the art that all or part of the flow of implementing the information retrieval method according to the embodiment of the present application may be implemented by controlling related hardware by a computer program, where the computer program may be stored in a computer readable storage medium, such as a memory of a server, and executed by at least one processor in the server, and the execution may include the flow of the embodiment of the information retrieval method. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.

For the information retrieval device of the embodiment of the present application, each functional module may be integrated in one processing chip, or each module may exist alone physically, or two or more modules may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated module, if implemented as a software functional module and sold or used as a stand-alone product, may also be stored on a computer readable storage medium such as read-only memory, magnetic or optical disk, etc.

The foregoing has described in detail the methods, apparatuses, storage media and servers for information retrieval provided by the embodiments of the present application, and specific examples have been applied to illustrate the principles and embodiments of the present application, where the foregoing description of the embodiments is only for aiding in understanding the methods and core ideas of the present application; meanwhile, those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, and the present description should not be construed as limiting the present application in view of the above.

Claims

1. An information retrieval method, comprising:

receiving a search request sent by a terminal, wherein the search request comprises an entry to be searched and a user portrait, the user portrait is updated according to terminal data collected every preset time, and when the collected data reach the target number, the user portrait is generated according to the collected data to replace the original user portrait so as to update the user portrait; wherein, the user portrait includes: basic portraits, behavioral characteristic portraits of users, interest portraits of users, social portraits of users, and mental value portraits of users;

performing search processing based on the entry to be searched to obtain a search result, wherein the search result comprises multi-entry tag information corresponding to the entry to be searched, and the method comprises the following steps: matching the to-be-searched entry with a preset entry, if the matching is successful, deleting the to-be-searched entry which is successfully matched with the preset entry, and carrying out search processing based on the undeleted to-be-searched entry to obtain a search result, wherein the search result comprises multi-entry mark information corresponding to the to-be-searched entry; wherein the preset vocabulary entry is the vocabulary entry of the category which is not interested by the user;

taking the target information which does not meet the first preset condition as first target information, and taking the target information which meets the first preset condition as second target information, wherein the information which meets the first preset condition refers to content which is not interested by a user;

based on the first ordering information, adjusting the ordering of the first target information to be prior to the ordering of the second target information, so as to obtain second ordering information;

2. The information retrieval method of claim 1, wherein the user representation comprises a plurality of representations of different types, the sorting the multi-item label information according to the user representation to obtain first sorting information, comprising:

3. The information retrieval method according to claim 2, wherein scoring each target information according to the plurality of portraits to obtain a recommendation score for each target information comprises:

4. The information retrieval method as recited in claim 1, wherein the returning the second ranking information to the terminal such that the terminal further includes, before displaying the multi-label information according to the second ranking information:

and returning the second ordering information to the terminal, so that the terminal displays the multi-item label information according to the second ordering information, and the method comprises the following steps:

and returning at least one item of target information after deleting the target information meeting the second preset condition and the second ordering information to the terminal, so that the terminal displays at least one item of target information after deleting the target information meeting the second preset condition according to the second ordering information.

5. The information retrieval method according to any one of claims 1 to 4, wherein the retrieving processing based on the entry to be retrieved, obtaining a retrieval result, includes:

and receiving a search result returned by the search server.

6. The information retrieval method according to claim 5, wherein the plurality of terms to be retrieved are provided, and the sending the terms to be retrieved to a retrieval server indicates the retrieval server to retrieve the terms to be retrieved, and further comprising:

the sending the to-be-searched entry to a search server, and instructing the search server to search according to the to-be-searched entry includes:

7. The information retrieval method according to claim 5, wherein the entry to be retrieved is plural, and before the entry to be retrieved is sent to the retrieval server, further comprising:

the sending the entry to be searched to a search server comprises the following steps:

8. An information retrieval apparatus, comprising:

the receiving module is used for receiving a search request sent by the terminal, wherein the search request comprises an entry to be searched and a user portrait, the user portrait is updated according to terminal data collected every preset time, and when the collected data reach the target number, the user portrait is generated according to the collected data so as to replace the original user portrait, so that the updating of the user portrait is realized; wherein, the user portrait includes: basic portraits, behavioral characteristic portraits of users, interest portraits of users, social portraits of users, and mental value portraits of users;

the acquisition module is used for carrying out search processing based on the entry to be searched to acquire a search result, wherein the search result comprises multi-entry mark information corresponding to the entry to be searched and comprises the following steps: matching the to-be-searched entry with a preset entry, if the matching is successful, deleting the to-be-searched entry which is successfully matched with the preset entry, and carrying out search processing based on the undeleted to-be-searched entry to obtain a search result, wherein the search result comprises multi-entry mark information corresponding to the to-be-searched entry; wherein the preset vocabulary entry is the vocabulary entry of the category which is not interested by the user;

the first classification module is used for taking the target information which does not meet the first preset condition as first target information and taking the target information which meets the first preset condition as second target information, wherein the information which meets the first preset condition refers to the content which is not interested by the user;

the adjusting module is used for adjusting the ordering of the first target information to be prior to the ordering of the second target information based on the first ordering information to obtain second ordering information;

and the return module is used for returning the second ordering information to the terminal so that the terminal displays the multi-item label information according to the second ordering information.

9. A storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the information retrieval method of any of claims 1 to 7.

10. A server comprising a processor, a memory, said memory having a computer program, characterized in that the processor is adapted to perform the information retrieval method according to any of claims 1 to 7 by invoking said computer program.