A search processing method, apparatus, device, and storage medium

Abstract

The application discloses a search processing method and device, equipment and a storage medium, and relates to the technical field of intelligent search. The specific implementation scheme is as follows: obtaining a query word input by a user; determining at least one candidate key word matched with the query word based on a pre-established index relationship; the index relationship is an index relationship between the segmentation of part of the key words corresponding to each category obtained through clustering according to semantics and the corresponding key words; determining the relevance of each candidate key word and the query word, and screening the candidate key words that meet a set condition; and determining a target key word matched with the query word based on the screened candidate key words. Through the introduction and use of the index relationship between the segmentation of part of the key words of each category after clustering and the corresponding key words, the search time is reduced, the search efficiency is improved, and the recall ability of the search system is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the computer technology field, and in particular, to the intelligent search technology field. BACKGROUND

[0002] When a search engine receives a query word input by a user, it needs to determine a keyword matching the query word according to an index table, and display corresponding information (such as an advertisement corresponding to the keyword) to the user according to the matching result.

[0003] In the prior art, when determining a keyword matching the query word according to the index table, the relevance verification model is used to determine the relevance of the query word and each candidate keyword in the index table respectively, and the keyword matching is performed according to the relevance.

[0004] However, the relevance verification model takes a long time, and can only calculate the relevance between a small number of candidate keywords and the query word each time, which greatly limits the recall ability of the search system. SUMMARY

[0005] The embodiments of the present application provide a search processing method, device and equipment and a storage medium, to reduce the search time, improve the search efficiency, and improve the recall ability of the search system.

[0006] In a first aspect, the embodiments of the present application provide a search processing method, comprising:

[0007] obtaining a query word input by a user;

[0008] determining at least one candidate keyword matching the query word based on a pre-established index relationship, wherein the index relationship is an index relationship between the segmentation of part of the keywords and the corresponding keywords, which is established for part of the keywords corresponding to each category obtained by clustering the keywords according to semantics;

[0009] determining the relevance of each candidate keyword and the query word, and screening the candidate keywords whose relevance satisfies a set condition;

[0010] determining a target keyword matching the query word based on the screened candidate keywords.

[0011] The embodiment of the application obtains a query word input by a user; determines at least one candidate keyword matched with the query word based on an index relationship between a part of keywords and corresponding keywords of each category obtained by clustering the keywords according to sentences and established in advance; determines the relevance of each candidate keyword and the query word, and screens the candidate keywords meeting a set condition; and determines a target keyword matched with the query word based on the screened candidate keywords. The above technical solution establishes the index relationship between the part of keywords and corresponding keywords for the keywords with the same semantics, instead of establishing the index relationship for all keywords, so that the number of candidate keywords matched with the query word based on the index relationship is reduced, and the workload of calculating the relevance between the candidate keywords and the query word is also reduced, thereby reducing the search time and improving the search efficiency, and meanwhile, the recall ability of the search system is improved.

[0012] Optionally, the method for establishing the index relationship comprises:

[0013] clustering the keywords according to semantics;

[0014] selecting a keyword in the current category as a representative keyword;

[0015] performing word segmentation on the representative keyword, and establishing an index relationship between each segmented word obtained by the word segmentation and the corresponding representative keyword.

[0016] In an optional embodiment of the above application, the keywords are clustered according to semantics, a keyword in the current category is selected as a representative keyword after clustering, and word segmentation is performed on the representative keyword, and an index relationship between each segmented word obtained by the word segmentation and the corresponding representative keyword is established, so that the index relationship establishment mechanism is improved, the query word matching operation is laid a foundation, the query word matching time and the calculation amount of the relevance determination are reduced when the query word matching and the relevance determination of the matched candidate keyword and the query word are performed based on the established index relationship, and the search time is reduced and the search efficiency is improved.

[0017] Optionally, after the keyword in the current category is selected as the representative keyword, the method further comprises:

[0018] establishing an index relationship between each representative keyword and the corresponding category;

[0019] Correspondingly, determining a target keyword matched with the query word based on the screened candidate keywords comprises:

[0020] For all or part of the candidate keywords screened, determine the current candidate keyword as the classification corresponding to the representative meta keyword;

[0021] Read each keyword in the determined classification, and read each keyword as a target keyword matched with the query word.

[0022] An optional embodiment in the above application, by establishing the index relationship between the representative meta keyword and a classification after clustering each keyword according to semantics in the index relationship construction process, the determination of the target keyword is realized through the index relationship corresponding to the representative meta keyword and the segmentation, and the index relationship corresponding to the representative meta keyword and the classification, the coverage of the target keyword is improved, and the comprehensiveness of the target keyword is ensured.

[0023] Optionally, for part of the candidate keywords screened, determining the current candidate keyword as the classification corresponding to the representative meta keyword comprises:

[0024] Determining a preset number of candidate keywords with the highest relevance to the query word among the screened candidate keywords;

[0025] For each determined candidate keyword, determine the current candidate keyword as the classification corresponding to the representative meta keyword.

[0026] An optional embodiment in the above application, by screening the candidate keywords based on the relevance and the preset number when determining the classification corresponding to the representative meta keyword, and determining the target keyword based on only the candidate keywords with higher relevance, the matching degree between the target keyword and the query word is improved.

[0027] Optionally, selecting one keyword in the current classification as the representative meta keyword comprises:

[0028] Selecting the shortest keyword in the current classification as the representative meta keyword.

[0029] An optional embodiment in the above application, the determination process of the representative meta keyword is refined to select the shortest keyword in the current classification as the representative meta keyword, thereby ensuring the representativeness between the representative meta keyword and other keywords in the current classification, and providing a guarantee for the relevance between the query word and the candidate keyword.

[0030] Optionally, clustering each keyword according to semantics comprises:

[0031] Mining synonymous keyword pairs for each keyword, and determining at least one keyword group based on the mined keyword pairs;

[0032] The semantics of the keywords in each keyword group are all the same.

[0033] In an optional embodiment of the above application, when the keywords are clustered, the synonym keyword pairs are mined, and the keyword groups are determined based on the mined keyword pairs, which improves the keyword clustering mechanism and ensures the comprehensiveness of the classification results through the synonym mining.

[0034] Optionally, after the target keyword matching the query word is determined, the method further includes:

[0035] Based on the target keyword, the information to be put by the information provider who has purchased the target keyword is retrieved;

[0036] The information to be put is pushed to the client of the user for display.

[0037] In an optional embodiment of the above application, after the target keyword is determined, the information to be put by the information provider of the target keyword is determined, and the information to be put is pushed to the user client for display, thereby realizing the function of information pushing based on the user query operation and improving the matching degree and comprehensiveness between the pushed information and the user query word.

[0038] In a second aspect, the embodiments of the present application further provide a search processing device, which includes:

[0039] A query word acquisition module is configured to acquire a query word input by a user.

[0040] A candidate keyword matching module is configured to determine at least one candidate keyword matching the query word based on a pre-established index relationship, wherein the index relationship is an index relationship between the segmentation of part of the keywords and the corresponding keywords, which is established for part of the keywords in the keywords corresponding to each classification obtained after the keywords are clustered according to semantics.

[0041] A candidate keyword screening module is configured to determine the relevance of each candidate keyword to the query word, and screen the candidate keywords whose relevance meets a set condition.

[0042] A target keyword determination module is configured to determine a target keyword matching the query word based on the screened candidate keywords.

[0043] In a third aspect, the embodiments of the present application further provide an electronic device, which includes:

[0044] At least one processor; and

[0045] A memory in communication connection with the at least one processor; wherein

[0046] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the search processing method provided in the embodiment of the first aspect.

[0047] In a fourth aspect, the embodiments of the present application further provide a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to enable the computer to perform the search processing method provided in the embodiment of the first aspect.

[0048] Other effects of the optional manners described above will be explained in the following with reference to specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0049] The accompanying drawings are used to better understand the present application and do not constitute limitations on the present application. Among them:

[0050] Figure 1 is a flowchart of a search processing method in the embodiment one of the present application;

[0051] Figure 2 is a flowchart of a search processing method in the embodiment two of the present application;

[0052] Figure 3 is a flowchart of a search processing method in the embodiment three of the present application;

[0053] Figure 4 is a structural diagram of a search processing device in the embodiment four of the present application;

[0054] Figure 5 is a block diagram of an electronic device used to implement the search processing method of the embodiments of the present application. DETAILED DESCRIPTION

[0055] The exemplary embodiments of the present application are described below with reference to the accompanying drawings, including various details of the embodiments of the present application to help understanding, which should be considered only as exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0056] Embodiment one

[0057] Figure 1 is a flowchart of a search processing method in the embodiment one of the present application, and the embodiment of the present application is applicable to the case where a user searches information through a search engine. The method is executed by a search processing device, which is implemented by software and / or hardware and is specifically configured in an electronic device with certain data operation capability.

[0058] As shown in a search processing method, comprising: Figure 1

[0059] S101, obtaining a query word input by a user.

[0060] Wherein, the query word can be a noun or a verb input by the user.

[0061] S102, determining at least one candidate keyword matching the query word based on a pre-established index relationship; wherein, the index relationship is an index relationship between the segmentation of part of the keywords corresponding to each classification obtained after clustering the keywords according to semantics and the corresponding keywords.

[0062] Wherein, the index relationship can be an inverted index.

[0063] Wherein, the candidate keyword can be a single word, or a phrase including at least two words.

[0064] Wherein, the index relationship can be pre-stored in the local electronic device, other storage devices associated with the electronic device or the cloud; accordingly, when it is necessary to determine at least one candidate keyword matching the query word based on the index relationship, the index relationship is obtained or queried from the local electronic device, other storage devices associated with the electronic device or the cloud.

[0065] S103, determining the relevance of each candidate keyword and the query word, and screening the candidate keywords whose relevance meets the set conditions.

[0066] Wherein, the relevance of the candidate keyword and the query word can be determined by mutual information (MI, Mutual Information). Of course, the relevance can also be determined by other parameters in the prior art, which will not be described here.

[0067] The relevance between each candidate keyword and the query word is determined respectively, and the candidate keywords are screened according to the size of the relevance and the number of candidate keywords.

[0068] Exemplarily, the relevance of each candidate keyword can be sorted, and the candidate keywords with the highest relevance to the query word can be screened. Wherein, the set number can be set by the technical personnel according to the need or experience value. Of course, the set number can be the number of candidate keywords to be screened, and it can also be the percentage of candidate keywords to be screened, and the number of candidate keywords to be screened is determined according to the pre-set percentage. ​

[0069] S104, determining a target keyword matching the query word based on the screened candidate keyword.

[0070] For example, based on the screened candidate keyword, the target keyword matching the query word can be directly screened as the candidate keyword matching the query word; or alternatively, at least one keyword in the category to which the candidate keyword belongs can be determined as the target keyword according to the category of the candidate keyword in the index relationship; or alternatively, the associated category of the category to which the candidate keyword belongs can be determined, and at least one keyword in the associated category can be determined as the target keyword according to the category of the candidate keyword in the index relationship. The associated category can be a category with similar semantics, similar use or the same upper category. For example, when the determined candidate keyword is "flowerpot", the associated category can be "flower vase", "flower stand" or "flower fertilizer".

[0071] The embodiment of the present application obtains the query word input by the user; determines at least one candidate keyword matching the query word based on the index relationship between the segmented keywords and the corresponding keywords of the keywords in the categories established in advance after clustering the keywords according to the sentences; determines the relevance of each candidate keyword and the query word, and screens the candidate keywords whose relevance meets the set condition; and determines the target keyword matching the query word based on the screened candidate keyword. The above technical solution establishes the index relationship between the segmented keywords and the corresponding keywords of part of the keywords with the same semantics, instead of all keywords, so that the number of candidate keywords matching the query word based on the index relationship is reduced, and the workload of calculating the relevance between the candidate keywords and the query word is also reduced, thereby reducing the search time and improving the search efficiency, and improving the recall ability of the search system.

[0072] On the basis of the technical solutions of the above embodiments, in order to apply the search processing method to the application scenario of information pushing, after determining the target keyword matching the query word, the information to be pushed of the information pushing party that has purchased the target keyword can be retrieved based on the target keyword; and the information to be pushed is pushed to the client of the user for display.

[0073] It can be understood that the search engine usually recommends information according to the content searched by the user to increase the information delivery benefit of the search engine. After determining the target keyword based on the query word input by the user, the information delivery party of each target keyword is determined based on the target keyword, and then the to-be-delivered information corresponding to the current period is determined according to the information delivery party; the determined to-be-delivered information is pushed to the client or the display webpage of the user for information display, so as to realize the information pushing to the user according to the user query word, thereby improving the matching degree of the pushed information and the user demand.

[0074] Embodiment Two

[0075] Figure 2 is a flowchart of a search processing method in Embodiment Two of the present application. The present application optimizes and improves the technical solutions of the above-mentioned embodiments.

[0076] Further, before performing "determining at least one candidate keyword matched with the query word based on the pre-established index relationship", an index relationship establishment operation is added; further, the index relationship establishment operation is refined as "clustering each keyword according to semantics; selecting one keyword in the current classification as a representative meta-keyword for each classification obtained after clustering; performing word segmentation processing on the representative meta-keyword, and establishing an index relationship between each segmented word obtained by word segmentation processing and the corresponding representative meta-keyword", so as to perfect the index relationship establishment mechanism, thereby laying a foundation for the determination of the candidate keyword.

[0077] As shown in a search processing method, comprising: Figure 2

[0078] S201, clustering each keyword according to semantics.

[0079] Exemplarily, the semantic classification of each keyword can be performed through the training and use of a machine learning model, and each keyword is divided into different categories.

[0080] Exemplarily, the synonymous keyword pairs can also be mined for each keyword, and at least one keyword group is determined based on the mined keyword pairs; wherein the semantics of the keywords in each keyword group are all the same, that is, each keyword group corresponds to one classification category.

[0081] It can be understood that, since the synonymous relationship satisfies reflexivity, symmetry and transitivity, when mining the keyword pairs, at least one of the reflexivity, symmetry and transitivity of the keywords can be used to determine the associated keywords corresponding to the keywords, and the keyword groups are constructed according to the keywords and the associated keywords corresponding to the keywords.

[0082] ​For example, when the user is presented with information, the user usually interacts with the message corresponding to keyword A, and also interacts with the message corresponding to keyword B. In this case, keyword A and keyword B are determined to be associated keywords, and a keyword pair can be formed. The interaction behavior can be at least one of browsing, clicking, collecting, ordering, and commenting.

[0083] For another example, when the information corresponding to keyword A can be obtained by rewriting the information corresponding to keyword B, or the information corresponding to keyword A and the information corresponding to keyword B can be generated based on the same information generation template, keyword A and keyword B are determined to be associated keywords, and a keyword pair can be formed.

[0084] For another example, the information corresponding to keyword A and the information corresponding to keyword B are displayed in the same delivery area and / or the delivery area is purchased by the same information delivery party. In this case, keyword A and keyword B are determined to be associated keywords, and a keyword pair can be formed.

[0085] Of course, it can be understood that if keyword A and keyword B are associated keywords, and keyword B and keyword C are associated keywords, keyword A and keyword C can also be determined to be associated keywords.

[0086] S202, for each classification obtained after clustering, selecting a keyword in the current classification as a representative meta-keyword.

[0087] For example, for each classification obtained after clustering, any keyword in the current classification can be randomly selected as a representative meta-keyword. It can be understood that since the keyword can be a short sentence containing multiple words, in order to ensure the matching degree and relevance between the selected keyword and other keywords in the same classification, typically, the shortest keyword in the current classification can be selected as the representative meta-keyword.

[0088] For example, in a classification category, the following keywords are included: “double eyelid surgery cost”, “double eyelid surgery price”, and “eyelid surgery how much money”. In this case, “double eyelid surgery cost” can be selected as the representative meta-keyword.

[0089] S203, performing word segmentation processing on the representative meta-keyword, and establishing an index relationship between each segmented word obtained by the word segmentation processing and the corresponding representative meta-keyword.

[0090] S204, obtaining a query word input by a user.

[0091] S205, determining at least one candidate keyword matched with the query word based on the pre-established index relationship.

[0092] Specifically, at least one representative meta-keyword matched with the query word is determined as a candidate keyword based on the index relationship between the segmented words and the representative meta-keywords.

[0093] It can be understood that, since only one representative meta-keyword is selected from each category according to the clustering result of each keyword in the index relationship establishment process, the data operation amount and the establishment time during the establishment of the index relationship can be greatly reduced, and the index relationship establishment efficiency can be significantly improved.

[0094] Correspondingly, in the subsequent process of determining the candidate keywords matched with the query word using the established index relationship, the data operation amount and the matching time of the candidate keyword matching are also reduced, and thus the candidate keyword determination efficiency can be significantly improved. Meanwhile, since the number of representative meta-keywords in the index relationship is significantly reduced compared with the number of keywords in the index relationship in the prior art, the number of candidate keywords determined during the candidate keyword matching determination is also significantly reduced.

[0095] S206, determining the relevance of each candidate keyword and the query word, and screening the candidate keywords whose relevance meets the set condition.

[0096] It can be understood that, since the number of candidate keywords is significantly reduced, the data operation amount and the determination time during the determination of the relevance of each candidate keyword and the query word are also reduced, and thus the relevance determination efficiency is improved.

[0097] S207, determining the target keyword matched with the query word based on the screened candidate keywords.

[0098] It should be noted that the index relationship establishment operation corresponding to S201-S203 can be executed before S204 or after S204, as long as the execution order is before S205.

[0099] The embodiment of the present application establishes the index relationship between each representative meta keyword and the corresponding classification, thereby laying a foundation for the determination of the candidate keyword. Meanwhile, in the process of establishing the index relationship, one keyword is selected from each classification as a representative meta keyword to establish the index relationship, which greatly reduces the time cost of the index relationship establishment, and meanwhile, when the candidate keyword is matched and the relevance is calculated based on the index relationship, the time cost and the calculation cost can be saved, thereby improving the search efficiency.

[0100] Embodiment three

[0101] Figure 3 is a flowchart of a search processing method in the embodiment three of the present application, and the embodiment of the present application is optimized and improved on the basis of the technical solutions of the above embodiments.

[0102] Further, the operation of "clustering each keyword according to semantics" is followed by the operation of "establishing the index relationship between each representative meta keyword and the corresponding classification"; and correspondingly, the operation of "determining the target keyword matched with the query word based on the screened candidate keyword" is refined into "determining the classification corresponding to the current candidate keyword as a representative meta keyword for all or part of the screened candidate keyword; reading each keyword in the determined classification, and taking the read keyword as the target keyword matched with the query word", so as to improve the coverage and comprehensiveness of the target keyword.

[0103] As shown in a search processing method in the embodiment of the present application, the method comprises the following steps. Figure 3

[0104] S301, clustering each keyword according to semantics.

[0105] S302, for each classification obtained after clustering, selecting one keyword in the current classification as a representative meta keyword.

[0106] S303, performing word segmentation processing on the representative meta keyword, and establishing a first index relationship between each segmented word obtained by the word segmentation processing and the corresponding representative meta keyword.

[0107] S304, establishing a second index relationship between each representative meta keyword and the corresponding classification.

[0108] ​It should be noted that S303 and S304 can be executed in sequence or simultaneously, and the specific execution sequence of the embodiments of the present application is not limited.

[0109] S305, obtaining the query word input by the user.

[0110] S306, determining at least one representative meta-keyword matching the query word as a candidate keyword based on the first index relationship.

[0111] Based on the first index relationship between the pre-established segmentation and the representative meta-keyword, the representative meta-keyword matching the query word is determined, and the matched representative meta-keyword is taken as a candidate keyword.

[0112] S307, determining the relevance of each candidate keyword and the query word, and screening the candidate keywords whose relevance meets the set condition.

[0113] It should be noted that during the relevance calculation process, each candidate keyword will calculate the relevance of each keyword in the category to which the candidate keyword belongs, so calculating the relevance between a candidate keyword and a query word is equivalent to simultaneously calculating the relevance between other keywords in the category to which the candidate keyword belongs and the query word. This significantly reduces the data operation amount of the relevance calculation process, and further improves the recall ability of the search system.

[0114] S308, for all or part of the screened candidate keywords, determining the classification corresponding to the current candidate keyword based on the second index relationship.

[0115] In an optional embodiment of the present application, the second index relationship between the representative meta-keyword and the classification can be used to directly determine the classification corresponding to the screened candidate keywords.

[0116] In order to reduce the data operation amount of the classification determination process and the number of target keywords determined based on the classification result, in another optional embodiment of the present application, only part of the screened candidate keywords can be used to determine the classification corresponding to the representative meta-keyword based on the second index relationship. Among them, the determination of part of the candidate keywords can be performed from the screened candidate keywords by at least one of the following methods: random screening, relevance size of the query word, and length of the candidate keyword.

[0117] Exemplarily, for the screened part of the candidate keywords, determining the classification corresponding to the current candidate keyword as the representative meta keyword based on the second index relationship can be: determining a preset number of candidate keywords with the highest relevance to the query word among the screened candidate keywords; and for the determined candidate keywords, determining the classification corresponding to the current candidate keyword as the representative meta keyword based on the second index relationship.

[0118] S309, reading each keyword in the determined classification, and taking the read each keyword as a target keyword matched with the query word.

[0119] It can be understood that, by the first index relationship between the word segmentation and the representative meta keyword, the determination and screening of the candidate keywords corresponding to the query word can reduce the data operation amount and time consumption of the determination and screening process of the candidate keywords, and further improve the search efficiency; by the second index relationship between the classification and the representative meta keyword, the determination of the target keyword can make the target keyword effectively cover in the category to which the screened candidate keyword belongs, and improve the coverage and comprehensiveness of the target keyword.

[0120] The embodiment of the present application introduces the index relationship between the classification and the representative meta keyword, and determines the classification to which the screened candidate keyword belongs based on the index relationship when determining the target keyword, so as to take each keyword in the determined classification as the target keyword, thereby improving the coverage range and comprehensiveness of the target keyword, and improving the recall ability of the search system.

[0121] Embodiment four

[0122] Figure 4 is a structural diagram of a search processing device in the fourth embodiment of the present application. The embodiment of the present application is applicable to the case that a user searches information through a search engine. The device is implemented by software and / or hardware, and is specifically configured in an electronic device with certain data operation capability.

[0123] As shown in Figure 4 a search processing device 400, comprising: a query word acquisition module 401, a candidate keyword matching module 402, a candidate keyword screening module 403 and a target keyword determination module 404; wherein,

[0124] The query word acquisition module 401 is configured to acquire the query word input by the user.

[0125] The candidate keyword matching module 402 is configured to determine at least one candidate keyword matched with the query word based on a pre-established index relationship, wherein the index relationship is an index relationship between a segmented word of a partial keyword and a corresponding keyword of the partial keyword, which is established for the partial keyword in each category after clustering the keywords according to semantics.

[0126] The candidate keyword screening module 403 is configured to determine a relevance of each candidate keyword to the query word, and screen the candidate keywords that satisfy a set condition in terms of the relevance.

[0127] The target keyword determination module 404 is configured to determine a target keyword matched with the query word based on the screened candidate keywords.

[0128] The embodiment of the present application obtains the query word input by a user through the query word obtaining module, determines at least one candidate keyword matched with the query word based on an index relationship between a segmented word of a partial keyword and a corresponding keyword of the partial keyword, which is established for the partial keyword in each category after clustering the keywords according to semantics through the candidate keyword matching module, determines the relevance of each candidate keyword to the query word through the candidate keyword screening module, screens the candidate keywords that satisfy a set condition in terms of the relevance, and determines a target keyword matched with the query word based on the screened candidate keywords through the target keyword determination module. The above technical solution establishes the index relationship between the segmented word of the partial keyword and the corresponding keyword, instead of establishing the index relationship for all keywords, for the keywords with the same semantics, so that the number of candidate keywords matched with the query word is reduced, the workload of calculating the relevance between the candidate keywords and the query word is reduced, the search time is reduced, the search efficiency is improved, and the recall ability of the search system is improved.

[0129] Further, the apparatus further includes an index relationship establishing module, which includes:

[0130] The clustering unit is configured to cluster the keywords according to semantics.

[0131] The representative meta-keyword selecting unit is configured to select one keyword in the current category as a representative meta-keyword for each category obtained after clustering.

[0132] The first index relationship establishing unit is configured to perform segmentation processing on the representative meta-keyword, and establish an index relationship between each segmented word obtained through the segmentation processing and the corresponding representative meta-keyword.

[0133] Further, the apparatus further includes a second index relationship establishing unit, which is configured to:

[0134] After selecting a keyword in the current category as a representative keyword, an index relationship between each representative keyword and a corresponding category is established;

[0135] Correspondingly, the target keyword determination module 404 includes:

[0136] The category determination unit is configured to determine, for all or part of the candidate keywords filtered out, a category corresponding to the current candidate keyword as a representative keyword.

[0137] The target keyword determination unit is configured to read each keyword in the determined category and take the read keywords as target keywords matched with the query.

[0138] Further, the category determination unit is specifically configured to:

[0139] Determine a preset number of candidate keywords with the highest relevance to the query from the filtered candidate keywords;

[0140] For each determined candidate keyword, determine a category corresponding to the current candidate keyword as a representative keyword.

[0141] Further, the representative keyword selection unit, when selecting a keyword in the current category as a representative keyword, is specifically configured to:

[0142] Select a keyword with the shortest length in the current category as a representative keyword.

[0143] Further, the clustering unit is specifically configured to:

[0144] Mine synonymous keyword pairs for each keyword, and determine at least one keyword group based on the mined keyword pairs.

[0145] Each keyword in each keyword group has the same semantic.

[0146] Further, the device further includes an information pushing module, which is specifically configured to:

[0147] After determining the target keywords matched with the query, retrieve the to-be-launched information of the information launching party that has purchased the target keywords based on the target keywords;

[0148] Push the to-be-launched information to the client of the user for display.

[0149] The above search processing device can execute the search processing method provided by any embodiment of the present application, and has the corresponding functional modules and beneficial effects of executing the search processing method.

[0150] Embodiment five

[0151] According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

[0152] As Figure 5 shown in FIG. 1, it is a block diagram of an electronic device for implementing the search processing method according to the embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown in the FIG. 1, their connections, and their functions, as well as the software implemented by the electronic device, are meant only to be examples and are not intended to limit the present application as described and / or claimed in this document.

[0153] As Figure 5 shown in FIG. 1, the electronic device includes one or more processors 501, a memory 502, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other by different buses, and can be mounted on a common mainboard or otherwise installed as needed. The processor can process instructions executed within the electronic device, including instructions stored in the memory or graphics information stored on the memory to display a GUI on an external input / output device such as a display device coupled to the interface. In other embodiments, multiple processors and / or buses can be used with multiple memories and multiple storage as needed. Also, multiple electronic devices can be connected, each providing part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 In the embodiment, the processor 501 is taken as an example.

[0154] The memory 502 is a non-transitory computer readable storage medium provided by the present application. The memory stores instructions executable by at least one processor, so that the at least one processor executes the search processing method provided by the present application. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to execute the search processing method provided by the present application.

[0155] The memory 502 as a non-transitory computer readable storage medium can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the search processing method in the embodiments of the present application (for example, the search processing method shown in FIG. 2). Figure 4The illustrated search processing apparatus 400 includes a query word obtaining module 401, a candidate keyword matching module 402, a candidate keyword screening module 403, and a target keyword determining module 404. The processor 501 performs various functional applications and data processing of the server by running non-transient software programs, instructions, and modules stored in the memory 502, thereby implementing the search processing method in the above-described method embodiments.

[0156] The memory 502 can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required by a function. The data storage area can store data created by the electronic device implementing the search processing method, and the like. In addition, the memory 502 can include a high-speed random access memory, and can further include a non-transient memory such as at least one magnetic disk storage device, a flash memory device, or other non-transient solid-state memory device. In some embodiments, the memory 502 can optionally include a memory disposed remotely with respect to the processor 501, and these remote memories can be connected to the electronic device implementing the search processing method through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0157] The electronic device implementing the search processing method can further include an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503, and the output device 504 can be connected by a bus or other means, Figure 5 For example, by way of a bus connection.

[0158] The input device 503 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device implementing the search processing method, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, and the like. The output device 504 can include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), and the like. The display device can include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0159] Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0160] These computer programs (also known as programs, software, software applications or code) include machine instructions for the programmable processor, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0161] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0162] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0163] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0164] According to the technical scheme of the embodiment of the present application, the query word input by the user is acquired; based on the index relationship between the partial keyword segmentation and the corresponding keyword of the keywords corresponding to each category obtained after clustering the keywords according to the sentence, which is established in advance, at least one candidate keyword matching the query word is determined; the relevance of each candidate keyword and the query word is determined, and the candidate keyword satisfying the set condition in relevance is screened out; and based on the screened candidate keyword, the target keyword matching the query word is determined. The above technical scheme establishes the index relationship between the partial keyword segmentation and the corresponding keyword of the keywords with the same semantic, instead of establishing the index relationship for all keywords, so that the number of candidate keywords matching the query word is reduced, and the workload of the relevance calculation between the candidate keywords and the query word is also reduced, thereby reducing the search time length, improving the search efficiency, and improving the recall ability of the search system.

[0165] It should be understood that the various forms of flow shown above can be reordered, added to, or deleted from without departing from the scope of the present application. For example, the steps described in the present application can be executed in parallel, in sequence, or in a different order, as long as the desired results of the technical scheme disclosed in the present application can be achieved, which is not limited herein.

[0166] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A search processing method characterized by comprising: The method comprises the following steps: obtaining a query word input by a user; determining at least one candidate keyword matching the query word based on a pre-established index relationship, wherein the index relationship is an index relationship between a segmented word of a part of keywords corresponding to a category obtained after clustering keywords according to semantics and the corresponding keyword, and is established for the part of keywords; determining the relevance of each candidate keyword to the query word, and screening the candidate keywords that meet a set condition; determining a target keyword matching the query word based on the screened candidate keywords; The method for establishing the index relationship comprises the following steps: clustering the keywords according to semantics; selecting one keyword in the current category as a representative meta-keyword; performing segmentation processing on the representative meta-keyword, and establishing an index relationship between each segmented word obtained by the segmentation processing and the corresponding representative meta-keyword; After selecting one keyword in the current category as a representative meta-keyword, the method further comprises the following steps: establishing an index relationship between each representative meta-keyword and the corresponding category; Correspondingly, determining a target keyword matching the query word based on the screened candidate keywords comprises the following steps: determining the category corresponding to the current candidate keyword as a representative meta-keyword for all or part of the screened candidate keywords; reading each keyword in the determined category, and taking the read keywords as target keywords matching the query word; For part of the screened candidate keywords, determining the category corresponding to the current candidate keyword as a representative meta-keyword comprises the following steps: determining a preset number of candidate keywords with the highest relevance to the query word among the screened candidate keywords; determining the category corresponding to the current candidate keyword as a representative meta-keyword for the determined candidate keywords.

2. The method of claim 1, wherein, Selecting one keyword in the current category as a representative meta-keyword comprises the following steps: selecting one keyword with the shortest length in the current category as a representative meta-keyword.

3. The method of claim 2, wherein, Clustering the keywords according to semantics comprises the following steps: mining synonym keyword pairs for the keywords, and determining at least one keyword group based on the mined keyword pairs; The semantics of the keywords in each keyword group are all the same.

4. The method according to any one of claims 1-2, characterized in that, After determining the target keyword matching the query word, the method further comprises the following steps: based on the target keyword, retrieving information to be put by an information putting party that has purchased the target keyword; pushing the information to be put to a client of the user for display.

5. A search processing apparatus characterized by comprising: The method comprises the following steps: a query word obtaining module, configured to obtain a query word input by a user; a candidate keyword matching module, configured to determine at least one candidate keyword matching the query word based on a pre-established index relationship, wherein the index relationship is an index relationship between a segmented word of a part of keywords corresponding to a category obtained after clustering keywords according to semantics and the corresponding keyword, and is established for the part of keywords; The candidate keyword screening module is configured to determine a relevance of each of the candidate keywords to the query word, and screen the candidate keywords whose relevance satisfies a set condition; The target keyword determination module is configured to determine a target keyword matching the query word based on the screened candidate keywords; The index relationship establishing module comprises: The clustering unit is configured to cluster each keyword according to semantics; The representative meta-keyword selection unit is configured to select one keyword in a current category as a representative meta-keyword for each category obtained after clustering; The first index relationship establishing unit is configured to perform word segmentation on the representative meta-keyword, and establish an index relationship between each segmented word obtained through word segmentation and the corresponding representative meta-keyword; The second index relationship establishing unit is configured to establish an index relationship between each representative meta-keyword and the corresponding category after selecting one keyword in the current category as the representative meta-keyword; Correspondingly, the target keyword determination module comprises: The category determination unit is configured to determine, for all or part of the screened candidate keywords, a category corresponding to a current candidate keyword as a representative meta-keyword; The target keyword determination unit is configured to read each keyword in the determined category, and take each read keyword as a target keyword matching the query word; The category determination unit is specifically configured to determine a preset number of candidate keywords with the highest relevance to the query word among the screened candidate keywords, and determine, for each determined candidate keyword, a category corresponding to a current candidate keyword as a representative meta-keyword.

6. An electronic device, comprising: The computer program product comprises: At least one processor; and A memory connected in communication with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the search processing method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the search processing method of any one of claims 1-4.

Images