CN109657145A

CN109657145A - Merchant searching method and device, electronic equipment and computer-readable storage medium

Info

Publication number: CN109657145A
Application number: CN201811565055.1A
Authority: CN
Inventors: 余鹏
Original assignee: Lazas Network Technology Shanghai Co Ltd
Current assignee: Lazas Network Technology Shanghai Co Ltd
Priority date: 2018-12-20
Filing date: 2018-12-20
Publication date: 2019-04-19

Abstract

The embodiment of the invention relates to the technical field of information processing, and discloses a merchant searching method and device, electronic equipment and a computer-readable storage medium. The merchant searching method comprises the following steps: acquiring a search word, and acquiring a word vector corresponding to the search word as a search word vector; acquiring a merchant word vector set of each merchant; determining a commercial tenant related to the search word as a target commercial tenant according to the search word vector and the commercial tenant word vector set; and displaying the target merchant. The merchant searching method and device, the electronic equipment and the computer readable storage medium provided by the embodiment of the invention have the advantage of greatly increasing the number of merchants in the merchant searching result.

Description

Merchant searching method and device, electronic equipment and computer-readable storage medium

Technical Field

The embodiment of the invention relates to the technical field of information processing, in particular to a merchant searching method and device, electronic equipment and a computer-readable storage medium.

Background

With the development of network technology, online shopping is becoming popular, and various online shopping platforms are increasing, so that users can select needed goods from the online shopping platforms. Because the number of merchants and commodities on the online shopping platform is huge, when a user carries out online shopping, the user usually inputs a commodity name or a merchant name which the user needs to buy on the online shopping platform, and the online shopping platform provides the merchant selling the commodity or the merchant input by the user for the user according to the commodity name or the merchant name input by the user.

However, the inventors of the present invention found that: in the existing online shopping platform, when a user inputs a search keyword, the online shopping platform searches a commercial tenant with the same commodity name or store name as the search keyword in the existing database as a search result and provides the search result for the user. Because only commercial tenants with commodity names or store names completely consistent with the search keywords appear in the search results obtained by the method, when the user cannot accurately describe the search requirements or confuse the store names of the commercial tenants, the input search keywords are different from the accurate keywords meeting the user expectations, so that hit results are omitted, and the search requirements of the user cannot be met due to less content available for the user.

Disclosure of Invention

The embodiment of the invention aims to provide a merchant searching method and device, electronic equipment and a computer readable storage medium, so that the number of merchants in a merchant searching result is increased, omission is avoided, and the searching requirement of a user is met.

In order to solve the technical problem, an embodiment of the present invention provides a merchant searching method, including obtaining a search term, and obtaining a term vector corresponding to the search term as a search term vector; acquiring a merchant word vector set of each merchant; determining a commercial tenant related to the search word as a target commercial tenant according to the search word vector and the commercial tenant word vector set; and displaying the target merchant.

The embodiment of the present invention also provides a merchant searching apparatus, including: the merchant word vector set acquisition module is used for acquiring merchant word vector sets of a plurality of merchants; the search word vector acquisition module is used for acquiring search words and acquiring word vectors corresponding to the search words as search word vectors; the target merchant acquisition module is used for determining merchants related to the search terms as target merchants according to the search term vectors and the merchant term vector set; and the display module is used for displaying the target commercial tenant.

An embodiment of the present invention also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement: acquiring a search word, and acquiring a word vector corresponding to the search word as a search word vector; acquiring merchant word vector sets of a plurality of merchants; determining a commercial tenant related to the search word as a target commercial tenant according to the search word vector and the commercial tenant word vector set; and displaying the target merchant.

Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which when executed by a processor implements the merchant searching method described above.

Compared with the prior art, the merchant searching method provided by the embodiment of the invention can acquire the merchant word vector set of each merchant in the platform in advance, acquire the word vector corresponding to the search word as the search word vector after acquiring the search word, determine the merchant related to the search word as the target merchant according to the search word vector and the merchant word vector set, and display the target merchant. Because the target merchants in the embodiment of the invention are merchants related to (but not identical to) the search terms, when the user cannot accurately describe the search requirement of the merchants or confuse the store names of the merchants, and the input search keywords are different from the accurate keywords expected by the user, the target merchants obtained by the embodiment also contain the search results expected by the user, so that the hit results are as omitted as possible, the content available for the user is increased, and the search requirement of the user is fully met.

In addition, optionally, the merchant word vector set of the merchant is obtained by: acquiring a merchant name of a merchant and at least partial sale commodity names of the merchant; and taking a set of merchant name word vectors corresponding to the merchant names and the sales commodity word vectors corresponding to the at least part of the sales commodity names as a merchant word vector set of the merchants. The method comprises the steps of taking a set of merchant name word vectors of merchants and commodity name word vectors of at least part of sold commodities of the merchants as a merchant word vector set corresponding to the merchants, enabling the merchant word vector set to contain characteristics of multiple dimensions of the merchants, and therefore the attributes of the merchants are well represented, and enabling users to search the merchants from the characteristics of multiple different dimensions.

In addition, optionally, the acquiring the merchant name of the merchant and the at least partial sale commodity name of the merchant specifically includes: acquiring a merchant name of the merchant; obtaining each sale commodity name of the merchant and a sale commodity word vector corresponding to each sale commodity name; obtaining word vector similarity of each sales commodity word vector and the search word vector; and acquiring at least part of sales commodity names according to the word vector similarity, wherein the minimum value in the word vector similarity corresponding to the at least part of sales commodity names is larger than the maximum value in the word vector similarity corresponding to the sales commodity names which are not acquired. Only the sales commodity names with the parts having larger word vector similarity with the search word vectors are selected, so that the sales commodity names have more reference significance, and the screening precision is improved.

In addition, optionally, the determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant specifically includes: respectively detecting the similarity between the commercial tenant word vector set of each commercial tenant and the search word vector; taking the commercial tenant word vector set with the similarity larger than a first preset threshold value as a target commercial tenant word vector set; and taking the commercial tenant corresponding to the target commercial tenant word vector set as a target commercial tenant.

In addition, optionally, the similarity between the merchant word vector set of the merchant and the search word vector is detected by: acquiring merchant name word vectors and each sales commodity word vector in the merchant word vector set; detecting the similarity between the merchant name word vector and the search word vector as a first vector similarity and the similarity between each sales commodity word vector and the search word vector as a second vector similarity; and acquiring the similarity between the commercial tenant word vector set and the search word vector according to the first vector similarity and the second vector similarity.

In addition, optionally, the obtaining the similarity between the merchant word vector set and the search word vector according to the first vector similarity and the second vector similarity specifically includes: and performing weighted calculation on the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector. And performing weighted calculation on the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector, so that the similarity can more accurately represent the correlation between the search word and the merchant.

In addition, optionally, the weighting calculation of the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector specifically includes: acquiring the similarity ratio of the first vector similarity and the second vector similarity; obtaining weights according to the similarity ratio, wherein the ratio of each weight is the same as the similarity ratio; and performing weighted calculation on the first vector similarity and the second vector similarity according to the weight to obtain the similarity between the commercial tenant word vector set and the search word vector.

In addition, optionally, the obtaining a search term and obtaining a term vector corresponding to the search term as a search term vector specifically include: acquiring a keyword input by a user, and acquiring a word vector corresponding to the keyword as a keyword vector; obtaining at least one expansion word according to the keyword vector, wherein the similarity between the expansion word vector corresponding to the expansion word and the keyword vector is greater than a second preset threshold; and taking the keywords and the expansion words as the search words, and taking a collection of the keyword vectors and the expansion word vectors as the search word vectors.

In addition, optionally, the determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant specifically includes: acquiring a commercial tenant word vector set meeting a first preset condition as a target commercial tenant word vector set according to the search word vector; wherein the first preset condition is that the target merchant word vector set includes at least one of the extension word vector and the keyword vector; and taking the commercial tenant corresponding to the target commercial tenant word vector set as a target commercial tenant.

In addition, optionally, after obtaining at least one expanded word according to the keyword vector, the method further includes: screening expansion words meeting a second preset condition as target expansion words according to the historical click rate of the target commercial tenant obtained by each expansion word; the second preset condition is that the historical click rate is greater than a preset click threshold; the taking the keyword and the expansion word as the search word specifically includes: and taking the target expansion word and the keyword as the search word.

In addition, optionally, the displaying the target merchant specifically includes: after the target commercial tenants are sorted according to preset sorting conditions, the target commercial tenants are displayed in sequence; the preset sorting condition at least comprises one of whether the target merchant purchases the platform advertisement, the sales volume of the target merchant, the high rating of the target merchant and the distance between the target merchant and the user. And sequencing and displaying target merchants according to at least one of whether the target merchants buy the platform advertisement, the sales volume of the target merchants, the goodness of the target merchants and the distance between the target merchants and the user, so that the display positions of the merchants meeting the conditions are higher, and the use experience of the merchants and the user is improved.

Drawings

One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.

Fig. 1 is a program flow chart of a merchant searching method provided in a first embodiment of the present invention;

FIG. 2 is a flowchart of a procedure for obtaining word vectors corresponding to some sold products in the merchant searching method according to the first embodiment of the present invention

Fig. 3 is a flowchart of a procedure for acquiring a word vector corresponding to a merchant name in the merchant searching method according to the first embodiment of the present invention;

fig. 4 is a flowchart of a procedure of a merchant searching method according to a second embodiment of the present invention;

fig. 5 is a flowchart of a procedure of a merchant searching method according to a third embodiment of the present invention;

fig. 6 is a flowchart of a procedure of a merchant searching method according to a fourth embodiment of the present invention;

fig. 7 is a schematic structural diagram of a merchant searching apparatus according to a fifth embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present invention in its various embodiments. However, the technical solution claimed in the present invention can be implemented without these technical details and various changes and modifications based on the following embodiments.

A first embodiment of the present invention relates to a merchant search method. The method comprises the steps of obtaining a search word, and obtaining a word vector corresponding to the search word as a search word vector; acquiring a merchant word vector set of each merchant; determining a commercial tenant related to the search word as a target commercial tenant according to the search word vector and the commercial tenant word vector set; and displaying the target merchant. The method comprises the steps of obtaining a commercial tenant related to a search word as a target commercial tenant through a search word vector and a commercial tenant word vector set, wherein the target commercial tenant is the commercial tenant related to the search word and comprises not only commercial tenants which must contain the search word in search results in the prior art, but also commercial tenants which do not contain the search word and are related to the search word, so that when a user cannot accurately describe the search requirement of the commercial tenant or confuse the commercial tenant name of the commercial tenant, and the input search keyword is different from the accurate keyword which meets the user's expectation, the target commercial tenant obtained in the embodiment also contains the search result which is expected by the user, the hit result is as omitted as possible, the content which can be purchased by the user is increased, and the search requirement of the user is fully met. The following describes implementation details of the merchant searching method in this embodiment in detail, and the following is only provided for easy understanding and is not necessary for implementing this embodiment.

The specific process is shown in fig. 1, and comprises the following steps:

step S101: and acquiring the keywords input by the user, and taking the keywords input by the user as search words.

Specifically, in the present embodiment, when the user performs the merchant search, the user inputs a keyword on the platform. In this step, the acquired keywords input by the user are directly used as search words for searching.

Step S102: and acquiring a word vector corresponding to the search word as a search word vector.

Specifically, in this step, after the search word is obtained, a word vector corresponding to the search word is obtained as the search word vector. It can be understood that the method for obtaining the search term vector is the same as the method for obtaining the merchant name term vector in step S101, and is not described herein again.

Step S103: and acquiring a merchant word vector set corresponding to each merchant.

Specifically, in this step, the merchant word vector set is a set of multiple word vectors corresponding to the merchant. In this embodiment, the merchant word vector set includes a merchant name word vector corresponding to a merchant name and a commodity name word vector corresponding to at least a part of a commodity name sold by a merchant.

Further, in this embodiment, the merchant word vector set includes a merchant name word vector corresponding to the merchant name and a product name word vector corresponding to at least a part of the sold product names of the merchants, where the merchant word vector set includes the merchant name word vector corresponding to the merchant name and the product name word vectors corresponding to all the sold product names of the merchants; and the merchant word vector set comprises merchant name word vectors corresponding to the merchant names and commodity name word vectors corresponding to partial sale commodity names of the merchants. The part of the sales commodities are part of sales commodities selected from all sales commodities by a preset method. In the present embodiment, the step of selecting a part of the sales items is shown in fig. 2, and includes the steps of:

step S201: and acquiring each sale commodity name of the merchant and a sale commodity word vector corresponding to each sale commodity name.

Step S202: and obtaining the word vector similarity of each sales commodity word vector and the search word vector.

Step S203: and acquiring partial sales commodity names according to the word vector similarity.

Specifically, in this step, the minimum value of the word vector similarities corresponding to the partial sales commodity name is greater than the maximum value of the word vector similarities corresponding to the sales commodity names that are not acquired. For example, the word vector similarity of each sales commodity word vector and the search word vector may be sorted in descending order, and the top-ranked partial sales commodities may be taken.

It should be understood that the foregoing is only an example of the method for selecting a part of the sales items in the present embodiment, and is not limited thereto, and in other embodiments of the present invention, the part of the sales items may be selected by other methods, such as selecting the same type of items as the search term, selecting items not participating in the promotion activity, and the like.

It is understood that the merchant word vector set including the merchant name word vector and at least a part of the product name word vector is only a specific application example in this embodiment, and in other embodiments of the present invention, the merchant word vector set may further include a person name word vector such as a name of a merchant operator, an address word vector of an address where the merchant is located, and the like, which are not listed herein. In addition, the merchant word vector set may be any one of the aforementioned merchant name word vectors, commodity name word vectors, and person name word vectors, and may be flexibly selected and set according to actual needs.

A word vector, i.e., a vector obtained by mapping a word or phrase from a vocabulary to a real number; the word vector corresponding to each word or phrase is unique and the word or phrase corresponding to each word vector is also unique. The method for obtaining the word vector corresponding to the merchant name will be described below by way of example, and it can be understood that the method for obtaining the commodity name word vector corresponding to the commodity name is the same.

As shown in fig. 3, the method for obtaining the word vector corresponding to the merchant name includes:

step S301: acquiring training corpora and storing the training corpora in a corpus;

specifically, in this step, the internet web pages can be directly captured by obtaining the corpus, the web pages contain all information of the shop, and the captured content of each web page is stored in the corpus as each corpus. Wherein, the linguistic data refers to the language material which actually appears in the practical use of the language; the corpus is usually stored in a corpus, which is a database using an electronic computer as a carrier to carry corpora; the real corpus generally needs to be analyzed and processed to be a useful resource.

Step S302: and performing word segmentation processing on each training corpus in the corpus respectively to obtain an ordered word set corresponding to each training corpus.

Performing word segmentation processing on each training corpus by using a word segmentation tool and a pre-established word segmentation word bank to obtain an ordered word set corresponding to each training corpus; wherein, the ordered word set is a set formed by ordered words; the word segmentation word stock is constructed according to a pre-collected user query log and an input method word stock.

Step S303: and constructing a word list according to the pre-collected user query logs.

Specifically, in this step, the method for constructing the vocabulary includes selecting some words from the corpus, and constructing and generating the vocabulary by using the selected words.

Step S304: and distributing each training corpus stored in the corpus to each node in a distributed word vector learning model.

Specifically, in this step, the ordered word set corresponding to each corpus in the corpus is used as an independent training data, and each corpus in the corpus is randomly allocated to each node in the distributed word vector learning model. For example, assuming that the distributed word vector learning model includes 3 nodes, the current corpus includes about 3 ten thousand corpus, and after word segmentation processing, an ordered word set corresponding to each corpus is obtained; all or part of the corpus is randomly allocated to the 3 nodes for processing, and in fact, the ordered word set corresponding to each corpus is randomly input to each node. Thus, each node can learn by using the ordered word set corresponding to the assigned training corpus as training data.

Step S305: and configuring the distributed word vector learning model to perform periodic word vector training on each word in the word list to obtain a word vector corresponding to each word in the word list.

Specifically, when the distributed word vector learning model starts to work, an initialization configuration operation is executed first, and an initialization word vector is set for a word included in a word list corresponding to each node. In the initial stage of training, the initialized word vectors corresponding to the words included in the word list corresponding to each node are the same. Then, each node starts training words included in the word list on the basis of the initialized word vector to obtain trained word vectors; and then, synchronizing the trained word vectors corresponding to the words in the word list corresponding to the nodes, and performing training in the next period until the training obtains the word vectors corresponding to the words in the word list.

Step S306: and acquiring the name of the merchant, and inquiring word vectors corresponding to the name of the merchant from the word list obtained by training to be used as the name word vectors of the merchant.

It should be understood that the above is only an example of a specific method for obtaining a word vector provided in this embodiment, and is not limiting. In practical applications, any other method for obtaining a word vector corresponding to a word or a phrase may be used in the present embodiment.

It is to be understood that, in the present embodiment, since the search term vector needs to be used in the method of selecting a partial sales commodity, step S103 is placed after steps S101 and 102. It is understood that if other methods without using the search term vector are used to select a part of the sales items, S103 may be disposed after S101 and S102, or disposed between S101 and S102, or performed simultaneously, as long as the performance of the subsequent steps is not affected.

Step S104: and respectively detecting the similarity between the merchant word vector set of each merchant and the search word vector.

Specifically, in this step, a first vector similarity of the search word vector and the merchant name word vector in the merchant word vector set, and a second vector similarity of the search word vector and the commodity name word vector in the merchant word vector set are obtained, respectively.

In this embodiment, the similarity between the merchant word vector set and the search word vector may be obtained through weighted calculation of the first vector similarity and the second vector similarity, that is, the similarity between the merchant word vector set and the search word vector is obtained by performing weighted calculation, such as weighted average, on the first vector similarity and the second vector similarity.

It should be noted that, if there are a plurality of product name word vectors, the number of the second vector similarities is also a plurality, and is the same as the number of the product name word vectors.

For example, let the search term vector be A (X)₁,Y₁) The merchant name word vector in the merchant word vector set is B (X)₂,Y₂) The commodity name word vector is C (X)₃,Y₃)、D(X₄,Y₄)、E(X₅,Y₅) (ii) a The first vector similarity is P₁Second vector similarity includes P₂＝A·C,P₃＝A·D,P₄A · E; let P₁、P₂、P₃、P₄The weights of the weights are 0.5, 0.2, 0.1 and 0.2 respectively; the similarity between the merchant word vector set and the search word vector is: p is 0.5P₁+0.2P₂+0.1P₃+0.2P₄. The above description is only a specific example of the weighting calculation in the present embodiment, and is not limiting. In other embodiments of the present invention, the weight may also be obtained by other methods instead of being preset, for example, the weight is determined by the ratio of the first vector similarity to the second vector similarity, that is, the ratio P of the first vector similarity to the second vector similarity is obtained first₁：P₂：P₃：P₄Making the ratio of the weights equal to the ratio of the first vector similarity to the second vector similarity, i.e. the weights are P₁/(P₁+P₂+P₃+P₄)、P₂/(P₁+P₂+P₃+P₄)、P₃/(P₁+P₂+P₃+P₄)、P₄/(P₁+P₂+P₃+P₄). It can be understood that there are many ways to find the weights in haas, and they are not listed here.

It can be understood that the similarity between the merchant word vector set and the search word vector is calculated by weighting the first vector similarity and the second vector similarity, which is only an example of a specific application in the present embodiment. In other embodiments of the present invention, the similarity between the merchant word vector set and the search word vector may also be obtained by other methods, for example, a maximum value of the first vector similarity and the second vector similarity is used as the similarity between the merchant word vector set and the search word vector, and a minimum value of the first vector similarity and the second vector similarity is used as the similarity between the merchant word vector set and the search word vector, which are not listed one by one here, and may be specifically selected according to actual situations.

Step S105: and acquiring a commercial tenant word vector set with the similarity larger than a first preset threshold value as a target commercial tenant word vector set.

Specifically, the first preset threshold is a preset threshold of similarity, that is, the merchant word vector set with the similarity greater than the first preset threshold is the target merchant word vector set.

In this step, after the similarity between each merchant word vector set and the search word vector is obtained, the similarities are compared with a first preset threshold one by one, and the merchant word vector set with the similarity greater than the first preset threshold is obtained as a target merchant word vector set.

Step S106: and displaying the target commercial tenant corresponding to the target commercial tenant word vector set.

Specifically, in this step, the corresponding merchant is obtained as the target merchant according to the target merchant word vector set, and the target merchant is displayed, so that the target merchant is provided to the user as a merchant search result.

Compared with the prior art, the merchant searching method provided by the first embodiment of the invention represents the correlation between the search word and the merchant through the similarity between the search word vector and the merchant word vector set, and displays the target merchant serving as the search result of the merchant related to the search word. Compared with the prior art that only the merchant name or the merchant name containing the search word is displayed in the search result, the number of merchants in the search result is larger and the user selectivity is higher.

A second embodiment of the present invention relates to a merchant search method. The second embodiment is a parallel arrangement of the first embodiment. The specific steps of the merchant searching method provided by the second embodiment are shown in fig. 4, and include:

step S401: and acquiring keywords typed by a user and keyword vectors corresponding to the keywords, and acquiring at least one expansion word according to the keyword vectors.

Specifically, in this step, a keyword entered by the user is first obtained, and a keyword vector corresponding to the keyword is obtained according to the keyword. It can be understood that the method for obtaining word vectors in this embodiment is the same as the method for obtaining merchant name word vectors in the first embodiment, and is not described herein again. And acquiring at least one expansion word according to the keyword vector, wherein the similarity between the expansion word vector corresponding to the expansion word and the keyword vector is greater than a second preset threshold value. And acquiring all word vectors with the similarity greater than a second preset threshold value with the keyword vectors according to the keyword vectors, and acquiring words corresponding to the word vectors as expansion words.

For example, if the keyword entered by the user is instant noodles, the expanded words may be instant noodles, cup noodles, instant noodles, and doll noodles, which are similar to the words with a large similarity to instant noodles.

Step S402: the keywords and the expansion words are used as search words.

Specifically, in this step, the keyword and the expanded word are used as the search word, and the collection of the keyword vector and the expanded word vector is used as the search word vector.

Step S403: and acquiring a merchant word vector set corresponding to each merchant.

Specifically, since this step is substantially the same as step S103 in the first embodiment, it is intended to obtain a merchant word vector set corresponding to each merchant, and details are not repeated here.

Step S404: and acquiring a commercial tenant word vector set meeting a first preset condition as a target commercial tenant word vector set according to the search word vector.

Specifically, in this step, the search word vector includes a keyword vector and an expansion word vector. The first preset condition is that the target merchant word vector set comprises at least one of an expansion word vector and a keyword vector. Namely, at least one same word vector exists in the merchant name word vector and the commodity name word vector contained in the target merchant word vector set and the expansion word vector and the keyword vector.

Step S405: and displaying the target commercial tenant corresponding to the target commercial tenant word vector set.

Specifically, since this step is substantially the same as step S106 in the first embodiment, the target merchant corresponding to the target merchant word vector set is obtained and displayed, and details are not repeated here.

Compared with the prior art, the merchant searching method provided by the second embodiment of the invention obtains at least one expansion word by keying in a keyword vector of the keyword by the user, searches by taking the keyword and the expansion word as search words, and displays the target merchant of the search result to the user. When the number of merchants in the search result is increased, if no merchant name or trade name of the merchant in the distribution range contains the keyword keyed in by the user, compared with the prior art without the search result, the method and the system for providing the merchant name or trade name of the merchant can provide the relevant merchants to the user, and user experience is improved.

The third embodiment of the present invention relates to a merchant searching method, and is a further improvement of the second embodiment, and is distinguished by: in the second embodiment, the set of the expansion words and the keywords is used as the search word; and in the third embodiment, the set of the filtered expansion words and the keywords is used as the search word. The merchant searching method provided by the third embodiment is shown in fig. 5, and includes:

step S501: and acquiring keywords typed by a user and keyword vectors corresponding to the keywords, and acquiring at least one expansion word according to the keyword vectors.

Specifically, since this step is substantially the same as step S401 in the second embodiment, at least one expanded word is obtained according to the keyword vector, which is not described herein again.

Step S502: and screening the expansion words according to the historical data to obtain target expansion words meeting second preset conditions.

Specifically, in this step, the historical data is the historical click rate of the target merchant obtained by each expansion word. Namely, the historical click rate of the target merchant searched according to each expansion word in the historical data is obtained. The second preset condition is that the historical click rate is greater than a preset click threshold. Namely, the expansion words with the historical click rate larger than the preset click threshold are obtained as the target expansion words. Specifically, in this embodiment, each extension word corresponds to a click number, when a user clicks a certain merchant a, all extension words corresponding to the merchant a are obtained, the click number of all extension words corresponding to the merchant a is added by 1, and the historical click rate corresponding to each extension word is the ratio of the click number corresponding to each extension word to the total click number. It should be understood that the foregoing is only an illustration of the method for obtaining the historical click rate in the present embodiment, and is not a limitation.

Step S503: and taking the keywords and the target expansion words as search words.

Specifically, in this step, the keyword and the target expansion word are used as the search word, and the keyword vector and the target expansion word vector are used as the search word vector.

Step S504: and acquiring a merchant word vector set corresponding to each merchant.

Specifically, since this step is substantially the same as step S403 in the second embodiment, it is intended to obtain merchant word vector sets corresponding to merchants, and details are not repeated here.

Step S505: and acquiring a commercial tenant word vector set meeting a first preset condition as a target commercial tenant word vector set according to the search word vector.

Since this step is substantially the same as step S404 in the second embodiment, the target merchant word vector set meeting the first preset condition is obtained according to the keyword vector, and details are not repeated here.

Step S506: and displaying the target commercial tenant corresponding to the target commercial tenant word vector set.

Specifically, since this step is substantially the same as step S405 in the second embodiment, the target merchant corresponding to the target merchant word vector set is obtained and displayed, and details are not repeated here.

Compared with the prior art, the merchant searching method provided by the third embodiment of the invention screens the expansion words through the historical click rate while keeping the technical effect of the second embodiment to obtain the target expansion words, and performs subsequent searching by taking the target expansion words and the keywords as the search words. And screening the expansion words according to the historical click rate, removing the expansion words with the too low historical click rate, and improving the effectiveness of the expansion words.

A fourth embodiment of the present invention relates to a merchant screening method, as shown in fig. 6, including:

step S601: and acquiring the keywords input by the user, and taking the keywords input by the user as search words.

Step S602: and acquiring a word vector corresponding to the search word as a search word vector.

Step S603: and acquiring a merchant word vector set corresponding to each merchant.

Step S604: and respectively detecting the similarity between the merchant word vector set of each merchant and the search word vector.

Step S605: and acquiring a commercial tenant word vector set with the similarity larger than a first preset threshold value as a target commercial tenant word vector set.

Since steps S601 to S605 in the present embodiment are substantially the same as steps S101 to S105 in the first embodiment, and are intended to obtain the target merchant to be displayed, details thereof are not repeated here.

Step S606: and sequencing the target merchants corresponding to the target merchant word vector set according to a preset sequencing condition and then displaying.

In this step, the preset ordering condition at least includes whether the target merchant purchases the platform advertisement, the sales volume of the target merchant, the rating of the target merchant, and the distance between the target merchant and the user. Specifically, the target merchants who have purchased the platform advertisement are closer to the front in the ranking, the target merchants with large sales are closer to the front in the ranking, the target merchants with large goodness of rating are closer to the front in the ranking, and the target merchants with small distance from the user are closer to the front in the ranking. It is understood that the above are only some specific examples of the ordering conditions, and in practical applications, the ordering conditions may include, but are not limited to, the above conditions, and are not exhaustive herein.

Compared with the prior art, the merchant searching method provided by the fourth embodiment of the invention has the advantages that the technical effect of the first embodiment is kept, the target merchants are sorted and displayed according to the preset sorting condition, excellent merchants are ranked in front, and the use experience of the user is improved.

The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.

A fifth embodiment of the present invention relates to a merchant screening apparatus, as shown in fig. 7, including: a merchant word vector set obtaining module 701, configured to obtain merchant word vector sets of multiple merchants; a search word vector obtaining module 702, configured to obtain a search word and obtain a word vector corresponding to the search word as a search word vector; a target merchant obtaining module 703, configured to determine, according to the search word vector and the merchant word vector set, a merchant related to the search word as a target merchant; a display module 704, configured to display the target merchant.

It should be understood that this embodiment is a system example corresponding to the first embodiment, and may be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment. Thereby, the technical effects of the first embodiment are achieved.

It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.

The sixth embodiment of the present invention relates to an electronic device, and the electronic device of the present embodiment may be a terminal device, such as a mobile phone, a tablet computer, and the like, and may also be a server on a network side.

As shown in fig. 8, the electronic device: includes at least one processor 801; and a memory 802 communicatively coupled to the at least one processor 801; and a communication component 803 communicatively coupled to the scanning device, the communication component 803 receiving and transmitting data under control of the processor 801; wherein the memory 802 stores instructions executable by the at least one processor 801 to implement:

acquiring a merchant word vector set of each merchant; acquiring a search word, and acquiring a word vector corresponding to the search word as a search word vector; determining a commercial tenant related to the search word as a target commercial tenant according to the search word vector and the commercial tenant word vector set; and displaying the target merchant.

The electronic device includes: one or more processors 801 and a memory 802, one processor 801 being illustrated in fig. 8. The processor 801 and the memory 802 may be connected by a bus or other means, and fig. 8 illustrates an example of a connection by a bus. Memory 802, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 801 executes various functional applications and data processing of the device, i.e., implements the merchant search method described above, by running non-volatile software programs, instructions, and modules stored in the memory 802.

The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 802 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 non-volatile solid state storage device. In some embodiments, the memory 802 may optionally include memory located remotely from the processor 801, which may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

One or more modules are stored in the memory 802 that, when executed by the one or more processors 801, perform the order allocation method of any of the method embodiments described above. Thereby providing the technical effects of any of the method embodiments described above.

The product can execute the method provided by the embodiment of the application, has corresponding functional modules and beneficial effects of the execution method, and can refer to the method provided by the embodiment of the application without detailed technical details in the embodiment.

A seventh embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor. Thereby providing the technical effects of any of the method embodiments described above.

That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.

The embodiment of the application discloses A1. a merchant searching method, which comprises the following steps:

acquiring a search word, and acquiring a word vector corresponding to the search word as a search word vector;

acquiring merchant word vector sets of a plurality of merchants;

determining a commercial tenant related to the search word as a target commercial tenant according to the search word vector and the commercial tenant word vector set;

and displaying the target merchant.

A2. According to the merchant searching method described in a1, the merchant word vector set of the merchant is obtained by:

acquiring a merchant name of a merchant and at least partial sale commodity names of the merchant;

and taking a set of merchant name word vectors corresponding to the merchant names and the sales commodity word vectors corresponding to the at least part of the sales commodity names as a merchant word vector set of the merchants.

A3. According to the merchant searching method described in a2, the acquiring the merchant name of the merchant and at least a part of the sales commodity names of the merchant specifically includes:

acquiring a merchant name of the merchant;

obtaining each sale commodity name of the merchant and a sale commodity word vector corresponding to each sale commodity name;

obtaining word vector similarity of each sales commodity word vector and the search word vector;

and acquiring at least part of sales commodity names according to the word vector similarity, wherein the minimum value in the word vector similarity corresponding to the at least part of sales commodity names is larger than the maximum value in the word vector similarity corresponding to the sales commodity names which are not acquired.

A4. According to the merchant searching method described in a1, determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant specifically includes:

respectively detecting the similarity between the commercial tenant word vector set of each commercial tenant and the search word vector;

taking the commercial tenant word vector set with the similarity larger than a first preset threshold value as a target commercial tenant word vector set;

and taking the commercial tenant corresponding to the target commercial tenant word vector set as a target commercial tenant.

A5. According to the merchant searching method described in a4, the similarity between the merchant word vector set of the merchant and the search word vector is detected in the following manner:

acquiring merchant name word vectors and each sales commodity word vector in the merchant word vector set;

detecting the similarity between the merchant name word vector and the search word vector as a first vector similarity and the similarity between each sales commodity word vector and the search word vector as a second vector similarity;

and acquiring the similarity between the commercial tenant word vector set and the search word vector according to the first vector similarity and the second vector similarity.

A6. According to the merchant searching method described in a5, the obtaining the similarity between the merchant word vector set and the search word vector according to the first vector similarity and the second vector similarity specifically includes:

and performing weighted calculation on the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector.

A7. According to the merchant searching method described in a6, the weighting and calculating the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector specifically includes:

acquiring the similarity ratio of the first vector similarity and the second vector similarity;

obtaining weights according to the similarity ratio, wherein the ratio of each weight is the same as the similarity ratio;

and performing weighted calculation on the first vector similarity and the second vector similarity according to the weight to obtain the similarity between the commercial tenant word vector set and the search word vector.

A8. According to the merchant searching method described in a1, the obtaining a search term and obtaining a term vector corresponding to the search term as a search term vector specifically includes:

acquiring a keyword input by a user, and acquiring a word vector corresponding to the keyword as a keyword vector;

obtaining at least one expansion word according to the keyword vector, wherein the similarity between the expansion word vector corresponding to the expansion word and the keyword vector is greater than a second preset threshold;

and taking the keywords and the expansion words as the search words, and taking a collection of the keyword vectors and the expansion word vectors as the search word vectors.

A9. According to the merchant searching method described in A8, determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant specifically includes:

acquiring a commercial tenant word vector set meeting a first preset condition as a target commercial tenant word vector set according to the search word vector;

wherein the first preset condition is that the target merchant word vector set includes at least one of the extension word vector and the keyword vector;

A10. According to the merchant searching method described in a9, after obtaining at least one expansion word according to the keyword vector, the method further includes:

screening expansion words meeting a second preset condition as target expansion words according to the historical click rate of the target commercial tenant obtained by each expansion word;

the second preset condition is that the historical click rate is greater than a preset click threshold;

the taking the keyword and the expansion word as the search word specifically includes: and taking the target expansion word and the keyword as the search word.

A11. The merchant searching method according to any one of a1 to a10, the displaying the target merchant specifically includes:

after the target commercial tenants are sorted according to preset sorting conditions, the target commercial tenants are displayed in sequence;

the preset sorting condition at least comprises one of whether the target merchant purchases the platform advertisement, the sales volume of the target merchant, the high rating of the target merchant and the distance between the target merchant and the user.

B1. A merchant searching apparatus comprising:

the merchant word vector set acquisition module is used for acquiring merchant word vector sets of a plurality of merchants;

the search word vector acquisition module is used for acquiring search words and acquiring word vectors corresponding to the search words as search word vectors;

the target merchant acquisition module is used for determining merchants related to the search terms as target merchants according to the search term vectors and the merchant term vector set;

and the display module is used for displaying the target commercial tenant.

B2. According to the merchant searching apparatus of B1, the merchant word vector set obtaining module specifically includes:

the name acquisition module is used for acquiring a merchant name of a merchant and at least partial sale commodity names of the merchant;

and the calculation module is used for taking a set of merchant name word vectors corresponding to the merchant names and the sales commodity word vectors corresponding to the at least part of the sales commodity names as a merchant word vector set of the merchants.

B3. According to the merchant searching apparatus of B2, the name obtaining module specifically includes:

the merchant name acquisition module is used for acquiring the merchant name of the merchant;

the sales commodity name acquisition module is used for acquiring each sales commodity name of the merchant and a sales commodity word vector corresponding to each sales commodity name, acquiring word vector similarity of each sales commodity word vector and the search word vector, and acquiring at least part of sales commodity names according to the word vector similarity, wherein the minimum value of the word vector similarity corresponding to the at least part of sales commodity names is larger than the maximum value of the word vector similarity corresponding to the sales commodity names which are not acquired.

B4. According to the merchant searching apparatus of B1, the target merchant acquiring module specifically includes:

the similarity detection module is used for respectively detecting the similarity between the commercial tenant word vector set of each commercial tenant and the search word vector;

and the target merchant determining module is used for taking the merchant word vector set with the similarity larger than a first preset threshold value as a target merchant word vector set and taking the merchant corresponding to the target merchant word vector set as a target merchant.

B5. According to the merchant searching apparatus of B4, the similarity detecting module specifically includes:

the merchant word vector set analysis module is used for acquiring merchant name word vectors and each sold commodity word vector in the merchant word vector set;

and the similarity calculation module is used for detecting the similarity between the commercial tenant name word vector and the search word vector as a first vector similarity and the similarity between each sales commodity word vector and the search word vector as a second vector similarity, and acquiring the similarity between the commercial tenant word vector set and the search word vector according to the first vector similarity and the second vector similarity.

B6. The merchant searching apparatus according to B5, wherein the similarity calculating module specifically includes:

and the weighting calculation module is used for weighting and calculating the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector.

B7. According to the merchant searching apparatus of B6, the weighting calculating module is specifically configured to:

B8. According to the merchant searching apparatus of B1, the search term vector acquiring module specifically includes:

the keyword vector acquisition module is used for acquiring keywords input by a user and acquiring word vectors corresponding to the keywords as keyword vectors;

and the expansion word acquisition module is used for acquiring at least one expansion word according to the keyword vector, wherein the similarity between the expansion word vector corresponding to the expansion word and the keyword vector is greater than a second preset threshold, the keyword and the expansion word are used as the search word, and the collection of the keyword vector and the expansion word vector is used as the search word vector.

B9. According to the merchant searching apparatus of B8, the target merchant obtains, specifically, the target merchant is configured to:

B10. The merchant searching apparatus according to B9, wherein the expanded word acquiring module is further configured to:

B11. The merchant searching apparatus according to any one of B1 to B10, wherein the display module is specifically configured to:

C1. An electronic device, comprising:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to implement:

acquiring merchant word vector sets of a plurality of merchants;

and displaying the target merchant.

C2. According to the electronic device of C1, the processor obtains a merchant word vector set for a merchant by:

C3. According to the electronic device of C2, the processor performs the acquiring of the merchant name of the merchant and the at least partial sales commodity name of the merchant, specifically:

acquiring a merchant name of the merchant;

C4. According to the electronic device of C1, the processor executes determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant, specifically:

C5. According to the electronic device of C4, the processor detects the similarity between the merchant word vector set of the merchant and the search word vector, specifically:

C6. According to the electronic device of C5, the processor performs the steps of obtaining the similarity between the merchant word vector set and the search word vector according to the first vector similarity and the second vector similarity, specifically:

C7. According to the electronic device of C6, the processor performs weighted calculation on the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector, specifically:

C8. According to the electronic device of C1, the processor performs obtaining of a search term, and obtains a term vector corresponding to the search term as a search term vector, specifically:

C9. According to the electronic device of C8, the processor executes determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant, specifically:

C10. According to the electronic device of C9, after the processor obtains at least one expanded word according to the keyword vector, the processor further performs:

C11. According to the electronic device of any one of C1-C10, the processor performs displaying the target merchant, specifically:

D1. A computer-readable storage medium storing a computer program which, when executed by a processor, implements the merchant search method of a 1-a 11.

Claims

1. A merchant searching method, comprising:

acquiring merchant word vector sets of a plurality of merchants;

and displaying the target merchant.

2. The merchant searching method according to claim 1, wherein the merchant word vector set of the merchant is obtained by:

3. The merchant searching method according to claim 2, wherein the acquiring of the merchant name of the merchant and the at least partial sale commodity name of the merchant specifically includes:

acquiring a merchant name of the merchant;

4. The merchant searching method according to claim 1, wherein the determining, according to the search term vector and the merchant term vector set, a merchant related to the search term as a target merchant specifically includes:

5. The merchant searching method according to claim 4, wherein the similarity between the merchant word vector set of the merchant and the search word vector is detected by:

6. The merchant searching method according to claim 5, wherein the obtaining the similarity between the merchant word vector set and the search word vector according to the first vector similarity and the second vector similarity specifically includes:

7. The merchant searching method according to claim 6, wherein the weighting and calculating the first vector similarity and the second vector similarity to obtain the similarity between the merchant word vector set and the search word vector specifically includes:

8. A merchant searching apparatus, comprising:

and the display module is used for displaying the target commercial tenant.

9. An electronic device, comprising:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

acquiring merchant word vector sets of a plurality of merchants;

and displaying the target merchant.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the merchant search method of claims 1 to 7.