CN117271869A - User search word recommendation method and device and electronic equipment - Google Patents
User search word recommendation method and device and electronic equipment Download PDFInfo
- Publication number
- CN117271869A CN117271869A CN202311562407.9A CN202311562407A CN117271869A CN 117271869 A CN117271869 A CN 117271869A CN 202311562407 A CN202311562407 A CN 202311562407A CN 117271869 A CN117271869 A CN 117271869A
- Authority
- CN
- China
- Prior art keywords
- search
- word
- search word
- commodity
- words
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000011218 segmentation Effects 0.000 claims abstract description 106
- 238000004590 computer program Methods 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000008267 milk Substances 0.000 description 2
- 235000013336 milk Nutrition 0.000 description 2
- 210000004080 milk Anatomy 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 235000013618 yogurt Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3322—Query formulation using system suggestions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Accounting & Taxation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application is applicable to the technical field of search word recommendation, and provides a method and a device for recommending user search words and electronic equipment, wherein the method comprises the following steps: acquiring commodity searching information of a target user, wherein the commodity searching information comprises commodity searching words, a first searching word set is constructed according to the word segmentation of the commodity searching words, any one of the first searching words comprises all the word segmentation of the commodity searching words, a second searching word set is determined according to the first searching word set, the searching words in the second searching word set are determined according to commodities associated with the searching words in the first searching word set, the user searching words are determined according to the first searching word set and the second searching word set, and the user searching words are recommended to the target user. The method and the device can improve the accuracy of the search word recommended to the user.
Description
Technical Field
The application belongs to the technical field of search word recommendation, and particularly relates to a user search word recommendation method, device, electronic equipment and computer readable storage medium.
Background
When a user searches for goods by inputting search words, the search words related to the search words input by the user are recommended to the user in addition to displaying the searched goods to the user so as to facilitate the user to search for the goods. At present, when related search words are recommended to a user, the recommended search words often have a larger gap from the search words input by the user, and the search intention of the user cannot be accurately reflected.
Disclosure of Invention
The embodiment of the application provides a method and a device for recommending search words of a user and electronic equipment, which can improve the accuracy of the search words recommended to the user.
In a first aspect, an embodiment of the present application provides a method for recommending a user search term, including:
acquiring commodity searching information of a target user, wherein the commodity searching information comprises commodity searching words;
constructing a first search word set according to the word segmentation of the commodity search word; any search term in the first search term set comprises all the partial terms of the commodity search term;
determining a second search word set according to the first search word set; the search words in the second search word set are determined according to commodities associated with the search words in the first search word set;
And determining user search words according to the first search word set and the second search word set, and recommending the user search words to the target user.
Optionally, before the first search word set is constructed according to the word segmentation of the commodity search word, the method further includes:
acquiring search click data, wherein the search click data are data generated by different users based on search behaviors of input search words and click behaviors of searched commodities;
constructing a search word library according to the search words in the search click data and commodities clicked by different users based on the search words;
the step of constructing a first search word set according to the word segmentation of the commodity search word comprises the following steps:
and determining the first search word set from the search word library according to the word segmentation of the commodity search word.
Optionally, the constructing a search word library according to the search word in the search click data and the commodity clicked by different users based on the search word includes:
determining search term nodes according to the search terms in the search click data; determining word segmentation nodes according to the word segmentation of the search word in the search click data; determining commodity nodes according to commodities clicked by different users based on the search words;
Determining a first relationship edge; the first relation edge is used for representing the mapping relation between the search word and the word segmentation of the search word;
determining a second relationship edge; the second relation edge is used for representing a mapping relation between the search word and commodities clicked correspondingly by different users based on the search word;
and determining the search word stock according to the search word node, the word segmentation node, the commodity node, the first relation edge and the second relation edge.
Optionally, the determining the first search word set from the search word library according to the word segmentation of the commodity search word includes:
performing word segmentation processing on the commodity search word to obtain a plurality of word segments corresponding to the commodity search word;
matching word segmentation nodes in the search word stock according to the plurality of word segmentation nodes;
determining a first search word node from the search word library by using a first relation edge of the matched word segmentation nodes, wherein the first search word node is associated with all the matched word segmentation nodes;
and constructing the first search word set according to click information of the search words in the first search word node.
Optionally, the determining a second set of search terms according to the first set of search terms includes:
Determining associated commodity nodes according to second relation edges of search words in the first search word set;
determining related commodities according to click information of the commodities in the related commodity nodes;
determining a second search term node by using the associated commodity;
and constructing the second search word set according to the search words corresponding to the second search word nodes.
Optionally, the determining the user search term according to the first search term set and the second search term set includes:
and determining the user search word based on the click information of the search word in the first search word set and the click information of the search word in the second search word set.
Optionally, the determining the user search term based on the click information of the search term in the first search term set and the click information of the search term in the second search term set includes:
determining the similarity degree of the search words in the first search word set and the search words in the second search word set based on the click information of the search words in the first search word set and the click information of the search words in the second search word set;
and selecting the user search word from the second search word set according to the similarity degree and the number of word segmentation nodes associated with the search word in the second search word set.
Illustratively, the determining the search word stock according to the search word node, the word segmentation node, the commodity node, the first relationship edge and the second relationship edge includes:
associating the search term node and the segmentation node by utilizing the first relation edge;
associating the search term node with the commodity node using the second relationship edge;
determining click information of search words in the search word nodes according to the search click data; determining click information of the commodity in the commodity node according to the search click data;
and summarizing all the associated nodes to obtain the search word stock.
In a second aspect, an embodiment of the present application provides a user search term recommendation apparatus, including:
the commodity search word acquisition module is used for acquiring commodity search information of a target user, wherein the commodity search information comprises commodity search words;
the first search word set construction module is used for constructing a first search word set according to the word segmentation of the commodity search word; any search term in the first search term set comprises all the partial terms of the commodity search term;
the second search word set construction module is used for determining a second search word set according to the first search word set; the search words in the second search word set are determined according to commodities associated with the search words in the first search word set;
And the user search word recommending module is used for determining user search words according to the first search word set and the second search word set and recommending the user search words to the target user.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the steps of the user search word recommendation method described in the first aspect are implemented when the processor executes the computer program.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program, where the computer program is executed by a processor to implement the steps of the method for recommending a user search term according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product, which when run on an electronic device, causes the electronic device to perform the user search term recommendation method according to any one of the first aspects above.
Compared with the prior art, the embodiment of the application has the beneficial effects that:
in the embodiment of the application, the second search word set is obtained through the commodity recommended word of the target user, and the user search word is determined according to the first search word set and the second search word set, so that more accurate user search words can be obtained. Specifically, a first search word set is constructed according to the word segmentation of the commodity search word, and any search word in the first search word set comprises all the word segmentation of the commodity search word, which means that the search word in the first search word set can completely reflect the search intention of a target user, and when a second search word set is determined according to the first search word set, because the search word in the second search word set is determined according to the commodity associated with the search word in the first search word set, namely, the search word in the second search word set is determined according to the commodity capable of completely reflecting the search intention of the target user, namely, a second search word set with stronger correlation with the commodity search word of the target user can be obtained through the word segmentation-first search word-commodity association relation, the search word determined according to the first search word set and the second search word set can accurately reflect the search intention of the target user, and therefore the accuracy of the search word recommended to the user is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating a method for recommending user search terms according to an embodiment of the present application;
FIG. 2 is a schematic diagram of different nodes in a search thesaurus according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a user search term recommendation device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
In recommending search terms to a user, similar search terms are typically constructed from search terms entered by the user, including: the method comprises the steps of simply replacing the word segmentation in the search words typed by the user, searching similar word segmentation according to the word segmentation in the search words typed by the user, and recommending the similar word segmentation to the user. However, the manner of substitution by word segmentation may lead to deviations in the search dimension, e.g., the user typing "XX shoes", if "XX trousers" are recommended to the user by word segmentation, the search may deviate from the user's intent; the manner in which similar segmentations are found by the segmentations of the user-entered search term may also deviate from the user's search intent, resulting in a large and inaccurate span of the search term recommended to the user from the user-entered search term, e.g., the user entering "brand a shoes", and by finding similar segmentations, "brand B socks" may be found, which may differ significantly from the user-entered search term.
In order to improve accuracy of search words recommended to users, the application provides a user search word recommendation method based on word segmentation-search word-commodity association.
Fig. 1 shows a flowchart of a user search term recommendation method provided in an embodiment of the present application, which is described in detail below:
S1, acquiring commodity searching information of a target user, wherein the commodity searching information comprises commodity searching words.
In this embodiment of the present application, the target user refers to a user performing a commodity search through a client, a web page end, or the like. The commodity search words refer to search words typed in by a target user at a client, a webpage end and the like, and the commodity search information refers to search information initiated by the target user through the typed commodity search words, and comprises a search request, commodity search words typed in by the target user and the like.
S2, constructing a first search word set according to the word segmentation of the commodity search word; any of the first set of search terms includes all of the tokens of the merchandise search term.
In the embodiment of the application, in order to enable the search terms in the generalized first search term set to retain the search intention for the target, the first search term set is constructed by the word segmentation of the commodity search terms, and any search term in the first search term set comprises all the word segments of the commodity search terms, which indicates that the search terms in the first search term set cannot be excessively different from the commodity search terms, so that the search terms in the first search term set cannot deviate from the search intention of the user.
In some embodiments, it is assumed that the commodity recommendation is "brand a milk," and the segmentation of the commodity recommendation includes: the first search word set constructed correspondingly comprises 'A brand yoghurt', 'A brand extra-strong milk' and the like, so that the generalized search words in the first search word set still keep approximate search intentions when the user types commodity search words, and deviation of the search intentions of the user is avoided.
S3, determining a second search word set according to the first search word set; and determining the search words in the second search word set according to the commodities associated with the search words in the first search word set.
In the embodiment of the application, in order to obtain more search words reflecting the search intention of the target user, the second search word set is obtained through the commodities associated with the search words in the first search word set, and because the second search word set is the search word set obtained through generalization according to the first search word set, any search word in the first search word set comprises all the division words of the commodity search word, more various search words, namely, the second search word set, can be obtained on the basis of keeping the search intention of the target user.
In some embodiments, assuming that the article 1 is associated with the search word 1, the search word 2, and the search word 3 respectively, after determining that the search word 1 is a search word in the first set of search words, the search word 2 and the search word 3 associated with the article 1 may be used as a search word in the second set of search words, thereby improving diversity of the search words.
And S4, determining user search words according to the first search word set and the second search word set, and recommending the user search words to the target user.
In this embodiment of the present application, the user search term may be determined by a similarity degree between the commodity search term and the search term in the second search term set, for example, calculating a similarity score of the commodity search term and the search term in the second search term set, and selecting a plurality of user search terms according to a descending order of the similarity score. The commodity search word and the second search word set are used for determining the user search word, so that the search word which is more in line with the search intention of the target user can be obtained, and the user search word is recommended to the target user, so that the user search experience can be improved.
In the embodiment of the application, the second search word set is obtained through the commodity recommended word of the target user, and the user search word is determined according to the first search word set and the second search word set, so that more accurate user search words can be obtained. Specifically, a first search word set is constructed according to the word segmentation of the commodity search word, and any search word in the first search word set comprises all the word segmentation of the commodity search word, which means that the search word in the first search word set can completely reflect the search intention of a target user, and when a second search word set is determined according to the first search word set, because the search word in the second search word set is determined according to the commodity associated with the search word in the first search word set, namely, the search word in the second search word set is determined according to the commodity capable of completely reflecting the search intention of the target user, namely, a second search word set with stronger correlation with the commodity search word of the target user can be obtained through the word segmentation-first search word-commodity association relation, the search word determined according to the first search word set and the second search word set can accurately reflect the search intention of the target user, and therefore the accuracy of the search word recommended to the user is improved.
In another optional embodiment of the present application, before the constructing the first search term set according to the word segmentation of the commodity search term, the method further includes:
acquiring search click data, wherein the search click data are data generated by different users based on search behaviors of input search words and click behaviors of searched commodities;
and constructing a search word library according to the search words in the search click data and commodities clicked by different users based on the search words.
In this embodiment of the present application, the above search click data refers to behavior data generated by different users based on a search behavior of an input search term and a click behavior of a product that is clicked, and may be obtained by constructing a buried event, that is, by setting a buried event for the search behavior and the click behavior of the user, the search click data of the user in a period of time is collected through the buried event, which means that the search term in the search click data is a product search term that is actually input by the user in a history time. The search click data includes a search word input by a user, commodity information of a commodity clicked by the user, click information of the search word and the commodity, and the like. The search word library is used for reflecting the corresponding relation between the search words in the search click data and commodities clicked by different users based on the search words.
In some embodiments, the search word library may be a graph database, i.e., the search word and the commodity in the search click data are used as nodes, and the corresponding relationship between different nodes is represented by constructing a relationship edge between the nodes.
Correspondingly, the constructing a first search word set according to the word segmentation of the commodity search word includes:
and determining the first search word set from the search word library according to the word segmentation of the commodity search word.
In this embodiment of the present application, since the search word library includes a correspondence between a search word and a commodity, the first search word set may be quickly determined from the search word library by word segmentation of the commodity search word.
In an optional embodiment of the present application, the constructing a search word bank according to the search word in the search click data and the commodity clicked by the different users based on the search word includes:
determining search term nodes according to the search terms in the search click data; determining word segmentation nodes according to the word segmentation of the search word in the search click data; determining commodity nodes according to commodities clicked by different users based on the search words;
determining a first relationship edge; the first relation edge is used for representing the mapping relation between the search word and the word segmentation of the search word;
Determining a second relationship edge; the second relation edge is used for representing a mapping relation between the search word and commodities clicked correspondingly by different users based on the search word;
and determining the search word stock according to the search word node, the word segmentation node, the commodity node, the first relation edge and the second relation edge.
In some embodiments, assuming that the search word library is a graph database, performing word segmentation processing on the search words in the search click data, using the word segmentation of the search words in the search click data as word segmentation nodes, using the search words in the search click data as search word nodes, and using commodities clicked by different users based on the search words as commodity nodes; for the search word nodes and the word segmentation nodes, the mapping relation of the search word and the word segmentation of the search word is built through the first relation edge, and for the search word nodes and the commodity nodes, the mapping relation of the search word and the commodity is built through the second relation edge. By constructing the search word library (graph database), the corresponding relation between the word segmentation and the search word and the commodity can be more clearly displayed based on the word segmentation node, the search word node and the commodity node, and meanwhile, the mutual searching capability between the word segmentation and the search word and the commodity can be improved through the first relation edge and the second relation edge, so that the data searching speed is improved.
In some embodiments, the search term in the above search click data may be segmented by an ES segmenter, jieba segmenter, or the like.
In an optional embodiment of the present application, the determining the search word stock according to the search word node, the word segmentation node, the commodity node, the first relationship edge, and the second relationship edge includes:
associating the search term node with the segmentation node by using the first relation edge;
associating the search term node with the commodity node using the second relationship edge;
determining click information of the search word in the search word node according to the search click data; determining click information of the commodity in the commodity node according to the search click data;
and summarizing all the associated nodes to obtain the search word stock.
In an alternative embodiment, referring to fig. 2, a schematic diagram of different nodes in a search word library is shown, wherein a first relation edge is "token" and is used for associating a search word node with a word segmentation node, a second relation edge is "click_stat" and is used for associating the search word node with a commodity node, and as shown in fig. 2, a commodity 1 and a commodity 2 in the search word library are associated by different search words, and different search words are associated with different word segmentation nodes and commodity nodes by the first relation edge "token" and the second relation edge "click_stat". Meanwhile, in order to improve the efficiency of data retrieval in the search word library, click information of the commodity in the commodity node is determined by searching click data, which comprises the following steps: product, total (total number of clicks on a good), click_stat, good_rate (i.e., number of clicks on the good/total number of clicks on the good by the search term); and determining click information of the search term in the search term node by searching the click data, including: keyword total (total number of clicks of a search term), click_stat. Keyword_rate (i.e., number of clicks of the item by the search term/total number of clicks of the search term).
Optionally, the determining the first search word set from the search word library according to the word segmentation of the commodity search word includes:
performing word segmentation processing on the commodity search word to obtain a plurality of word segments corresponding to the commodity search word;
matching word segmentation nodes in the search word stock according to the plurality of word segmentation nodes;
determining a first search word node from the search word library by using a first relation edge of the matched word segmentation node, wherein the first search word node is associated with all matched word segmentation nodes;
and constructing the first search word set according to the click information of the search words in the first search word node.
In the embodiment of the application, the article search word is subjected to word segmentation processing to obtain a plurality of word segments corresponding to the article search word, word segmentation nodes in a search word bank are matched by the plurality of word segments, and a first search word node is determined from the search word bank according to a first relation edge of the matched word segmentation nodes, wherein in order to ensure that the generalized search word (namely, the search word in the first search word set) does not deviate from a user search intention, the first search word node needs to be associated with all the matched word segmentation nodes, namely, the search word in the first search word node comprises all the word segments of the article search word, and meanwhile, in order to reduce the number of the search words, the search word can be selected in a descending order according to click information of the search word in the first search word node to obtain the first search word set.
In some embodiments, it is assumed that the search word library is a graph database, after obtaining a plurality of word segments of the commodity search word, a first search word node is determined in the graph database according to a first relationship edge "token", and meanwhile, a first search word set may be constructed by selecting search words of the TOP20 in descending order according to keyword.
Optionally, the determining a second search word set according to the first search word set includes:
determining associated commodity nodes according to second relation edges of the search words in the first search word set;
determining related commodities according to click information of the commodities in the related commodity nodes;
determining a second search term node by using the related commodity;
and constructing the second search word set according to the search words corresponding to the second search word nodes.
In an optional embodiment of the present application, assuming that the above search word library is a graph database, commodity nodes associated with search words in the first search word set may be determined according to a second relationship edge "click_stat", and in order to improve diversity of search words, a commodity of TOP300 may be selected as an associated commodity according to a product.
In this embodiment of the present application, the determining, according to the first search word set and the second search word set, a user search word includes:
and determining the user search word based on the click information of the search word in the first search word set and the click information of the search word in the second search word set.
In some embodiments, because the number of the search words in the second search word set is greater, in order to further improve accuracy of recommending the user search word to the target user during actual recommendation, the user search word is further screened by the click information of the search word in the first search word set and the click information of the search word in the second search word set.
In this embodiment of the present application, the determining the user search term based on the click information of the search term in the first search term set and the click information of the search term in the second search term set includes:
determining the similarity degree of the search words in the first search word set and the search words in the second search word set based on the click information of the search words in the first search word set and the click information of the search words in the second search word set;
and selecting the user search word from the second search word set according to the similarity degree and the number of word segmentation nodes associated with the search word in the second search word set.
In some embodiments, the similarity degree of the search words in the first search word set and the search words in the second search word set is determined according to the click information of the search words in the first search word set and the click information of the search words in the second search word set, and as the search words in the first search word set can completely reflect the search intention of the target user, the similarity degree of the search words in the first search word set and the search words in the second search word set is measured according to the actual click behavior of the user, so that the search words are more fit to the actual scene; meanwhile, the more the number of word segmentation nodes associated with the search word in the second search word set is, the higher the fine granularity of the search word in the second search word set is, the more abundant the information is contained, and the search intention of a target user can be better covered, so that the user search word is selected from the second search word set through the similarity degree determined by clicking information and the number of word segmentation nodes associated with the search word in the second search word set, the user search word which has stronger relevance to commodity search words and completely contains the search intention of the user can be obtained, and the accuracy of the search word recommended to the user is improved.
In an optional embodiment of the present application, assuming that the commodity search term is a keyword, the search term in the first search term set is inc_keyword, the search term in the second search term set is sim_keyword, the similarity degree sim_score may be calculated according to the click_stat_rate in the search term library (i.e. the total click times of clicking the commodity by the search term) and the click_stat_rate (i.e. the total click times of clicking the commodity by the search term) of the commodity, for example, by multiplying the click_stat_rate of the search term inc_keyword in the first search term set by the click_stat_rate of the search term sim_keyword in the second search term set, thereby determining the similarity degree of the search term in the second search term set and the search term in the second search term set, and further determining the similarity degree of the search term in the second search term set and the commodity; meanwhile, the word segmentation number, namely the word segmentation node number, of each sim_keyword can be obtained according to the first relation edge 'token', if the word segmentation node number is greater than 1, the priority is 1, and otherwise, the priority is 0. When selecting the user search word, the search word in the second search word set may be first reduced according to the priority, then the search word sim_keyword of the same priority may be selected as the user search word from the second search word set after the reduced order according to the sim_score.
It should be noted that, in order to improve the recommendation efficiency of the user recommended word, the accurate user recommended word may be generated quickly, and the user recommended word may be determined directly according to the commodity searched word and the second search word set, that is, by multiplying the click_state_keyword_rate of the commodity searched word with the click_state_good_rate of the search word sim_keyword in the second search word set, determining the similarity degree of the commodity searched word and the search word in the second search word set, and reducing the order of the search word in the second search word set by the priority determined by the word segmentation number of sim_keyword, and finally selecting the user searched word from the second search word set after the reduced order.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
Corresponding to the user search term recommending method described in the above embodiments, fig. 3 shows a schematic structural diagram of the user search term recommending apparatus provided in the embodiment of the present application, and for convenience of explanation, only the portions relevant to the embodiments of the present application are shown.
Referring to fig. 3, the apparatus may be a user search term recommending apparatus 31, and the user search term recommending apparatus 31 may include a commodity search term acquisition module 311, a first search term set construction module 312, a second search term set construction module 313, and a user search term recommending module 314.
Referring to fig. 3, the user search term recommending apparatus 31 includes:
the commodity search word obtaining module 311 is configured to obtain commodity search information of a target user, where the commodity search information includes a commodity search word;
the first search word set construction module 312 is configured to construct a first search word set according to the word segmentation of the commodity search word; any search term in the first search term set comprises all the partial terms of the commodity search term;
the second search word set construction module 313 is configured to determine a second search word set according to the first search word set; the search words in the second search word set are determined according to commodities associated with the search words in the first search word set;
the user search term recommending module 314 is configured to determine a user search term according to the first search term set and the second search term set, and recommend the user search term to the target user.
In some embodiments, the user search term recommendation device 31 further includes a search term library construction module, where before the search term library construction module is configured to construct the first search term set according to the word segmentation of the commodity search term, the search term library construction module includes:
acquiring search click data, wherein the search click data are data generated by different users based on search behaviors of input search words and click behaviors of searched commodities;
and constructing a search word library according to the search words in the search click data and commodities clicked by different users based on the search words.
Correspondingly, the first search word set construction module 312 constructs a first search word set according to the word segmentation of the commodity search word by the following steps:
and determining the first search word set from the search word library according to the word segmentation of the commodity search word.
In some embodiments, the search word stock construction module constructs a search word stock according to the search word in the search click data and the commodity clicked by different users based on the search word, including:
determining search term nodes according to the search terms in the search click data; determining word segmentation nodes according to the word segmentation of the search word in the search click data; determining commodity nodes according to commodities clicked by different users based on the search words;
Determining a first relationship edge; the first relation edge is used for representing the mapping relation between the search word and the word segmentation of the search word;
determining a second relationship edge; the second relation edge is used for representing a mapping relation between the search word and commodities clicked correspondingly by different users based on the search word;
and determining the search word stock according to the search word node, the word segmentation node, the commodity node, the first relation edge and the second relation edge.
In some embodiments, the search word stock construction module determines the search word stock according to the search word node, the word segmentation node, the commodity node, the first relationship edge, and the second relationship edge by:
associating the search term node and the segmentation node by utilizing the first relation edge;
associating the search term node with the commodity node using the second relationship edge;
determining click information of search words in the search word nodes according to the search click data; determining click information of the commodity in the commodity node according to the search click data;
and summarizing all the associated nodes to obtain the search word stock.
In some embodiments, the first search term set construction module 312 determines the first search term set from the search term library according to the word segmentation of the merchandise search term by:
performing word segmentation processing on the commodity search word to obtain a plurality of word segments corresponding to the commodity search word;
matching word segmentation nodes in the search word stock according to the plurality of word segmentation nodes;
determining a first search word node from the search word library by using a first relation edge of the matched word segmentation nodes, wherein the first search word node is associated with all the matched word segmentation nodes;
and constructing the first search word set according to click information of the search words in the first search word node.
In some embodiments, the second search term set construction module 313 determines the second search term set from the first search term set by:
determining associated commodity nodes according to second relation edges of search words in the first search word set;
determining related commodities according to click information of the commodities in the related commodity nodes;
determining a second search term node by using the associated commodity;
and constructing the second search word set according to the search words corresponding to the second search word nodes.
In some embodiments, the user search term recommendation module 314 determines the user search term from the first set of search terms and the second set of search terms by:
and determining the user search word based on the click information of the search word in the first search word set and the click information of the search word in the second search word set.
In some embodiments, the user search term recommendation module 314 determines the user search term based on the click information of the search term in the first set of search terms and the click information of the search term in the second set of search terms by:
determining the similarity degree of the search words in the first search word set and the search words in the second search word set based on the click information of the search words in the first search word set and the click information of the search words in the second search word set;
and selecting the user search word from the second search word set according to the similarity degree and the number of word segmentation nodes associated with the search word in the second search word set.
It should be noted that, because the content of information interaction and execution process between the devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and details thereof are not repeated herein.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: at least one processor 40 (only one shown in fig. 4), a memory 41, and a computer program 44 stored in the memory 41 and executable on the at least one processor 40. The steps of any of the various method embodiments are performed by the processor 40 when executing the computer program 44.
The electronic device 4 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The electronic device may include, but is not limited to, a processor 40, a memory 41. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not meant to be limiting of the electronic device 4, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input transmitting device, a network access device, a bus, etc.
The processor 40 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may in some embodiments be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 41 may be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used for storing an operating system, application programs, boot loader (BootLoader), data, other programs, etc., such as program codes of the computer program. The memory 41 may also be used for temporarily storing data that has been transmitted or is to be transmitted.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the division of the functional units and modules is illustrated, and in practical application, the functional distribution may be performed by different functional units and modules, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The embodiment of the application also provides a network device, which comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor implementing the steps in any of the various method embodiments when the computer program is executed.
Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements steps in the various method embodiments.
Embodiments of the present application provide a computer program product which, when run on an electronic device, causes the electronic device to perform steps that may be implemented in the various method embodiments described.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. With such understanding, the present application implements all or part of the flow of the method of the embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiments. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a camera device/electronic apparatus, a recording medium, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
In the embodiments, the descriptions of the embodiments are focused on, and the parts of a certain embodiment that are not described or depicted in detail can be referred to for related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A method for recommending a user search term, comprising:
acquiring commodity searching information of a target user, wherein the commodity searching information comprises commodity searching words;
constructing a first search word set according to the word segmentation of the commodity search word; any search term in the first search term set comprises all the partial terms of the commodity search term;
Determining a second search word set according to the first search word set; the search words in the second search word set are determined according to commodities associated with the search words in the first search word set;
and determining user search words according to the first search word set and the second search word set, and recommending the user search words to the target user.
2. The method of claim 1, wherein prior to constructing the first set of search terms from the word segmentation of the merchandise search terms, further comprising:
acquiring search click data, wherein the search click data are data generated by different users based on search behaviors of input search words and click behaviors of searched commodities;
constructing a search word library according to the search words in the search click data and commodities clicked by different users based on the search words;
the step of constructing a first search word set according to the word segmentation of the commodity search word comprises the following steps:
and determining the first search word set from the search word library according to the word segmentation of the commodity search word.
3. The method of claim 2, wherein the constructing a search term library based on the search terms in the search click data and the goods clicked by the different users based on the search terms comprises:
Determining search term nodes according to the search terms in the search click data; determining word segmentation nodes according to the word segmentation of the search word in the search click data; determining commodity nodes according to commodities clicked by different users based on the search words;
determining a first relationship edge; the first relation edge is used for representing the mapping relation between the search word and the word segmentation of the search word;
determining a second relationship edge; the second relation edge is used for representing a mapping relation between the search word and commodities clicked correspondingly by different users based on the search word;
and determining the search word stock according to the search word node, the word segmentation node, the commodity node, the first relation edge and the second relation edge.
4. The method of claim 3, wherein said determining the first set of search terms from the search term library based on the word segmentation of the commodity search term comprises:
performing word segmentation processing on the commodity search word to obtain a plurality of word segments corresponding to the commodity search word;
matching word segmentation nodes in the search word stock according to the plurality of word segmentation nodes;
determining a first search word node from the search word library by using a first relation edge of the matched word segmentation nodes, wherein the first search word node is associated with all the matched word segmentation nodes;
And constructing the first search word set according to click information of the search words in the first search word node.
5. The method of claim 4, wherein the determining a second set of search terms from the first set of search terms comprises:
determining associated commodity nodes according to second relation edges of search words in the first search word set;
determining related commodities according to click information of the commodities in the related commodity nodes;
determining a second search term node by using the associated commodity;
and constructing the second search word set according to the search words corresponding to the second search word nodes.
6. The method of claim 5, wherein the determining the user search term from the first set of search terms and the second set of search terms comprises:
and determining the user search word based on the click information of the search word in the first search word set and the click information of the search word in the second search word set.
7. The method of claim 4-6, wherein the determining the user search term based on the click information of the search term in the first set of search terms and the click information of the search term in the second set of search terms comprises:
Determining the similarity degree of the search words in the first search word set and the search words in the second search word set based on the click information of the search words in the first search word set and the click information of the search words in the second search word set;
and selecting the user search word from the second search word set according to the similarity degree and the number of word segmentation nodes associated with the search word in the second search word set.
8. A user search term recommending apparatus, comprising:
the commodity search word acquisition module is used for acquiring commodity search information of a target user, wherein the commodity search information comprises commodity search words;
the first search word set construction module is used for constructing a first search word set according to the word segmentation of the commodity search word; any search term in the first search term set comprises all the partial terms of the commodity search term;
the second search word set construction module is used for determining a second search word set according to the first search word set; the search words in the second search word set are determined according to commodities associated with the search words in the first search word set;
and the user search word recommending module is used for determining user search words according to the first search word set and the second search word set and recommending the user search words to the target user.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311562407.9A CN117271869B (en) | 2023-11-22 | 2023-11-22 | User search word recommendation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311562407.9A CN117271869B (en) | 2023-11-22 | 2023-11-22 | User search word recommendation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117271869A true CN117271869A (en) | 2023-12-22 |
| CN117271869B CN117271869B (en) | 2024-03-29 |
Family
ID=89204922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311562407.9A Active CN117271869B (en) | 2023-11-22 | 2023-11-22 | User search word recommendation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117271869B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577432A (en) * | 2012-07-26 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and system for searching commodity information |
| CN107092608A (en) * | 2016-04-16 | 2017-08-25 | 口碑控股有限公司 | A kind of search of destination object, recommendation method and apparatus |
| CN110020148A (en) * | 2017-11-29 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and the device for information recommendation |
| CN115599768A (en) * | 2022-10-19 | 2023-01-13 | 深圳市灵智数字科技有限公司（Cn） | Association word library construction method, association word recommendation method and device |
| CN116362236A (en) * | 2023-03-30 | 2023-06-30 | 北京沃东天骏信息技术有限公司 | Target word mining method and device and storage medium |
-
2023
- 2023-11-22 CN CN202311562407.9A patent/CN117271869B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577432A (en) * | 2012-07-26 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and system for searching commodity information |
| CN107092608A (en) * | 2016-04-16 | 2017-08-25 | 口碑控股有限公司 | A kind of search of destination object, recommendation method and apparatus |
| CN110020148A (en) * | 2017-11-29 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and the device for information recommendation |
| CN115599768A (en) * | 2022-10-19 | 2023-01-13 | 深圳市灵智数字科技有限公司（Cn） | Association word library construction method, association word recommendation method and device |
| CN116362236A (en) * | 2023-03-30 | 2023-06-30 | 北京沃东天骏信息技术有限公司 | Target word mining method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117271869B (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9858608B2 (en) | Query suggestion for e-commerce sites | |
| US9171088B2 (en) | Mining for product classification structures for internet-based product searching | |
| US9069859B2 (en) | Search query processing | |
| US20200110842A1 (en) | Techniques to process search queries and perform contextual searches | |
| US20140122294A1 (en) | Determining a characteristic group | |
| US20090063461A1 (en) | User query mining for advertising matching | |
| US20240029086A1 (en) | Discovery of new business openings using web content analysis | |
| US9330071B1 (en) | Tag merging | |
| US11500953B2 (en) | Indexing native application data | |
| US20120323932A1 (en) | Iterative set expansion using samples | |
| US11586694B2 (en) | System and method for improved searching across multiple databases | |
| US11120064B2 (en) | Transliteration of data records for improved data matching | |
| CN110827101A (en) | Shop recommendation method and device | |
| CN112328881A (en) | Article recommendation method and device, terminal device and storage medium | |
| CN117271869B (en) | User search word recommendation method and device and electronic equipment | |
| US10922374B1 (en) | Techniques to determine relationships of items in web-based content | |
| CN115599768B (en) | Association word library construction method, association word recommendation method and device | |
| TWI547888B (en) | A method of recording user information and a search method and a server | |
| CN113781180A (en) | Article recommendation method and device, electronic equipment and storage medium | |
| CN117688147B (en) | Commodity information searching method and device and terminal equipment | |
| CN112307298A (en) | Method and device for generating personal brand label | |
| CN115114505B (en) | Online education content distribution system | |
| CN113935316A (en) | Data processing method and device and computer storage medium | |
| CN115587164A (en) | Recommended commodity determining method and device, electronic equipment and storage medium | |
| CN117520610A (en) | Data searching method, device, equipment and storage medium based on graph calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |