CN115114506A - Commodity searching method and device, electronic equipment and storage medium - Google Patents
Commodity searching method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115114506A CN115114506A CN202110286778.3A CN202110286778A CN115114506A CN 115114506 A CN115114506 A CN 115114506A CN 202110286778 A CN202110286778 A CN 202110286778A CN 115114506 A CN115114506 A CN 115114506A
- Authority
- CN
- China
- Prior art keywords
- commodity
- obtaining
- candidate
- results
- user
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012163 sequencing technique Methods 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims description 4
- 239000000047 product Substances 0.000 description 46
- 230000006870 function Effects 0.000 description 18
- 239000002537 cosmetic Substances 0.000 description 12
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 11
- 244000265736 Nelumbo pentapetala Species 0.000 description 11
- 238000000605 extraction Methods 0.000 description 11
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000003068 static effect Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 240000005369 Alstonia scholaris Species 0.000 description 2
- 235000013162 Cocos nucifera Nutrition 0.000 description 2
- 244000060011 Cocos nucifera Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000008446 instant noodles Nutrition 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/9538—Presentation of query results
-
- 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]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to a commodity searching method, a commodity searching device, electronic equipment and a storage medium, and belongs to the technical field of internet. The commodity searching method comprises the following steps: acquiring input information of a user, and acquiring intention characteristics of the user according to the input information; obtaining a plurality of commodity obtaining results of a plurality of candidate live commercial tenants according to the intention characteristics of the user; acquiring commodity description information of a plurality of commodity acquisition results; determining correlation scores of a plurality of commodity obtaining results and the input information according to the input information and the commodity description information; the method comprises the steps of obtaining labels of a plurality of candidate live broadcast merchants, and adjusting correlation scores of commodity obtaining results corresponding to the candidate live broadcast merchants according to the labels of the candidate live broadcast merchants; and sorting the plurality of commodity acquisition results according to the adjusted relevance scores. Therefore, the purpose of searching related commodity live broadcast through the input information of the user can be achieved, and meanwhile, the intelligent sequencing and active guidance of the search results are achieved.
Description
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to a method and an apparatus for searching for a commodity, an electronic device, and a storage medium.
Background
Live webcasting is an emerging social networking approach. The anchor uses tools such as a camera to carry out live video on the live broadcast platform. With the continuous popularization of internet live broadcast. Many olfactory keen merchants are beginning to use live broadcast platforms to promote and sell online products, so-called live broadcast delivery.
The live broadcast with goods source point may be a by-product of a live broadcast form, but with the gradual growth of a live broadcast shopping form, more and more professional live broadcast with goods grow on a live broadcast platform, and besides watching the content type of interest of a plurality of audiences, more and more pure live broadcast with goods are searched, so that the live broadcast with goods can be directly watched by purchasing goods in a form similar to television shopping.
Disclosure of Invention
The present disclosure provides a method and an apparatus for searching for commodities, an electronic device, and a storage medium, so as to solve at least the problem that live-broadcast-based e-commerce search is not available in related technologies, achieve the purpose of searching for related commodities live broadcast through user input information, and achieve intelligent sorting and active guidance of search results. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a commodity search method, including:
acquiring input information of a user, and acquiring intention characteristics of the user according to the input information;
obtaining a plurality of commodity obtaining results of a plurality of candidate live commercial tenants according to the intention characteristics of the user;
acquiring commodity description information of the plurality of commodity acquisition results;
determining relevance scores of the plurality of commodity obtaining results and the input information according to the input information and the commodity description information;
obtaining labels of the candidate live broadcast merchants, and adjusting the correlation scores of the commodity obtaining results corresponding to the candidate live broadcast merchants according to the labels of the candidate live broadcast merchants; and
and sorting the plurality of commodity acquisition results according to the adjusted relevance scores.
In a possible implementation manner of the embodiment of the present disclosure, the obtaining the intention characteristic of the user according to the input information includes:
acquiring intention information of the user according to the input information;
if the intention information of the user is a search intention, further extracting search attribute information from the input information, and taking the search attribute information as the intention characteristic.
In a possible implementation manner of the embodiment of the present disclosure, after the further extracting search attribute information from the input information, the method further includes:
and extracting the current node of the commodity category tree from the search attribute information.
In a possible implementation manner of the embodiment of the present disclosure, the obtaining, according to the intention characteristic of the user, a plurality of product obtaining results of a plurality of candidate live merchants includes:
generating and acquiring a keyword according to the intention characteristics;
and obtaining the candidate commodity set according to the obtained keywords to generate a candidate commodity set, wherein the candidate commodity set comprises a plurality of commodity obtaining results, and each commodity obtaining result corresponds to a candidate live merchant.
In a possible implementation manner of the embodiment of the present disclosure, the obtaining according to the obtained keyword to generate an obtained candidate product set includes:
acquiring a commodity acquisition result corresponding to the current node of the commodity category tree, and adding the commodity acquisition result to the acquired candidate commodity set;
and if the quantity of the commodity obtaining results in the obtained candidate commodity set is less than the preset quantity, searching a superior node from the current node along the commodity category tree, and adding the commodity obtaining results corresponding to the superior node to the obtained candidate commodity set.
In a possible implementation manner of the embodiment of the present disclosure, the method for searching for a commodity further includes:
if the number of the commodity obtaining results in the candidate commodity set is still smaller than the preset number, screening and reducing the obtained keywords;
and acquiring again according to the acquired keywords after being screened, and adding the acquired commodity acquisition result into the acquired candidate commodity set.
In a possible implementation manner of the embodiment of the present disclosure, the sorting the multiple commodity obtaining results according to the adjusted relevance scores includes:
acquiring node levels of nodes where the plurality of commodity acquisition results are located;
and sequencing the plurality of commodity acquisition results according to the node progression and the adjusted relevance scores.
According to a second aspect of the embodiments of the present disclosure, there is provided an article search device including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire input information of a user and acquire intention characteristics of the user according to the input information;
the second acquisition module is configured to acquire a plurality of commodity acquisition results of a plurality of candidate live merchants according to the intention characteristics of the user;
a third acquisition module configured to acquire commodity description information of the plurality of commodity acquisition results;
a determining module configured to determine relevance scores of the plurality of commodity obtaining results and the input information according to the input information and the commodity description information;
the fourth acquisition module is configured to acquire the labels of the multiple candidate live broadcast merchants and adjust the correlation scores of the commodity acquisition results corresponding to the multiple candidate live broadcast merchants according to the labels of the multiple candidate live broadcast merchants; and
a ranking module configured to rank the plurality of commodity acquisition results according to the adjusted relevance scores.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the above-mentioned item search method.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a storage medium, in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the above-described item search method.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
the method comprises the steps of firstly obtaining input information of a user, obtaining intention characteristics of the user according to the input information, obtaining a plurality of commodity obtaining results of a plurality of candidate live merchants according to the intention characteristics of the user, then obtaining commodity description information of the commodity obtaining results, determining relevance scores of the commodity obtaining results and the input information according to the input information and the commodity description information, then obtaining labels of the candidate live merchants, adjusting the relevance scores of the commodity obtaining results corresponding to the candidate live merchants according to the labels of the candidate live merchants, and finally sequencing the commodity obtaining results according to the adjusted relevance scores. Therefore, the method solves the problem that live broadcast-based E-commerce type search is not available in the related technology, can achieve the purpose of searching related commodity live broadcast through input information of a user, and meanwhile achieves intelligent sequencing and active guidance of search results.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a flow chart illustrating a method of item searching according to an exemplary embodiment;
FIG. 2 is a schematic diagram illustrating a live video content understanding flow in accordance with an illustrative embodiment;
FIG. 3 is a schematic diagram illustrating a live audio content understanding flow according to an exemplary embodiment;
FIG. 4 is a block diagram illustrating an article search device according to one exemplary embodiment; and
FIG. 5 is a block diagram of an electronic device shown in accordance with an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the disclosure, as detailed in the appended claims.
A commodity search method, apparatus, electronic device, and storage medium according to embodiments of the present disclosure are described below with reference to the accompanying drawings.
The commodity searching method provided in the embodiment of the present disclosure may be executed by an electronic device, where the electronic device may be a PC (Personal Computer), a mobile phone, a tablet Computer, a palmtop Computer, or the like, and is not limited herein.
In the disclosed embodiment, the electronic device may be provided with a processing component, a storage component and a driving component. Optionally, the driving component and the processing component may be integrated, the storage component may store an operating system, an application program, or other program modules, and the processing component implements the product search method provided by the embodiment of the present disclosure by executing the application program stored in the storage component.
It should be noted that the product search method provided in the embodiment of the present disclosure may be applied to short video APPs (applications) with live broadcast functions, and may also be applied to special live broadcast APPs, which is not limited herein. In addition, the short video APP and the live APP with the live broadcast function can be installed in electronic equipment (for example, a mobile phone, a tablet computer, and the like).
Fig. 1 is a flowchart illustrating an article searching method according to an exemplary embodiment, which may be used in an electronic device, as shown in fig. 1, and includes the following steps.
In step S11, input information of the user is acquired, and the intention characteristic of the user is acquired from the input information.
It should be noted that the input information described in this embodiment may include text information input by a user through speech recognition and input content input by the user into the input method system through an input method, the input method system may convert the input content into word candidates of input characters according to a current input manner of the user, and provide a user with a choice, the user may input the text information through various input means, such as a keyboard, a touch pad, a mouse, and the like, and the user may also select any input manner to input the text information, such as pinyin, wubi, stroke, handwriting, english, and a keypad, and the like, which is not limited herein.
In the embodiment of the disclosure, the intention characteristic may include a commodity search intention, and after acquiring the input information of the user, the electronic device (e.g., a mobile phone) may determine whether the input information of the user includes the commodity search intention, and if the commodity search intention is included, the intention characteristic of the user may be acquired according to the input information. For example, if the input information of the user is "beautiful lotus red lipstick", it can be determined that the input information of the user includes the commodity search intention; if the input information of the user is 'live broadcast of beauty dancing', it can be judged that the input information of the user does not include the commodity search intention.
In one example, the commodity searching method provided by the embodiment of the disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein in a process that a user operates the short video APP with the live broadcast function by using the mobile phone, the short video APP can be operated to call up a search bar, and search information (i.e., input information of the user) is input in the search bar according to a shopping requirement of the user, for example, "american lotus red lipstick" is input, and then a search button is clicked to perform searching. After the user clicks the search button, the mobile phone can firstly judge whether the input information of the user includes the commodity search intention through the short video APP, and if the input information includes the commodity search intention, intention characteristics (such as the beautiful lotus and the lipstick) of the user can be obtained according to the input information.
In step S12, a plurality of product acquisition results of a plurality of candidate live merchants are acquired according to the intention characteristics of the user. The multiple commodity obtaining results of the multiple candidate live broadcast merchants can include short video APPs with live broadcast functions or live broadcast merchants carrying out live broadcast of goods in the live broadcast APPs and information of commodities which are live broadcast.
In an example, the method for searching for a commodity provided by the embodiment of the present disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, where after obtaining an intention feature of a user, the mobile phone may obtain (recall) a plurality of commodity obtaining (recall) results of a plurality of candidate live merchants according to the intention feature of the user.
In step S13, the commodity description information of the plurality of commodity acquisition results is acquired.
In the embodiment of the present disclosure, the article description information may include a brand of the article, a title of the article, a name of the article, a description of the article, a type of the article, sales information of the article, evaluation information of the article, and the like.
In step S14, a relevance score of the plurality of item acquisition results and the input information is determined based on the input information and the item description information.
In an example, the method for searching for a product provided by the embodiment of the present disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, where after a plurality of product obtaining results of a plurality of candidate live broadcast merchants are obtained according to intention characteristics of a user, the mobile phone may analyze the product obtaining results to obtain product description information of the product obtaining results, and then may determine a correlation score between the product obtaining results and input information according to the input information (e.g., a ruby lipstick in maybao) and the product description information (e.g., a product title, a product name, a product description, etc.) by using a preset correlation algorithm. The predetermined correlation algorithm may be calibrated according to actual conditions, for example, the predetermined correlation algorithm may be a conventional correlation determination (calculation) algorithm (for example, the BM25 algorithm).
In step S15, the tags of multiple candidate live broadcast merchants are obtained, and the correlation scores of the product obtaining results corresponding to the multiple candidate live broadcast merchants are adjusted according to the tags of the multiple candidate live broadcast merchants.
It should be noted that the tags described in this embodiment may be dynamic tags, static tags, or feature tags, where the dynamic tags may include a live broadcast room, a live broadcast current content tag is established according to a content understanding tag in the live broadcast room, or a product being explained by a host is converted from a voice to a text description of the product being explained to generate a corresponding tag; the static tags may include tags generated for the title of the article, the segmentation of the description of the article, and keywords, tags generated for the image of the article and the content of the image of the article, tags generated for the category tree information of the article, tags generated by the anchor history live broadcast content, keywords historically searched for the anchor live broadcast (i.e., anchor tags), and the like; the feature tags may include tags generated for statistical features of the current live room (e.g., number of online people, amount of endorsements, total sales orders), tags generated for sales statistical features of the current item.
In step S16, the plurality of item acquisition results are sorted according to the adjusted relevance scores.
In one example, the method for searching for a product provided by the embodiment of the present disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, where after determining that correlation scores between a plurality of product acquisition results and input information are obtained, the mobile phone may obtain tags (for example, dynamic tags, static tags, or feature tags) of a plurality of candidate live broadcast merchants, and adjust the correlation scores of the product acquisition results corresponding to the candidate live broadcast merchants according to the tags of the candidate live broadcast merchants. For example, the user search term (input information of the user) "coconut shoe" may be used to weight a part of the adidas brand results, or the user search term (input information of the user) "american lotus red lipstick" may be used to weight commercial results such as a grand anchor that has been frequently used for direct lipstick broadcasting historically, a direct broadcast that is explaining cosmetics, and the like. Finally, the mobile phone can sort the plurality of commodity acquisition results according to the adjusted relevance scores, for example, the acquisition results defined in a deeper level in the category tree are arranged in front of the acquisition results defined in a shallower level in the category tree forever (for example, user search words: Meibao lotus red lipstick, and the third level: lipstick are arranged in front of the commodities which only have the second level: cosmetics) forever); the commodities limited by the brand words and the attribute words are always ranked in front of the obtained result with relaxed limitation.
In the embodiment of the disclosure, input information of a user is firstly acquired, intention characteristics of the user are acquired according to the input information, then a plurality of commodity acquisition results of a plurality of candidate live merchants are acquired according to the intention characteristics of the user, commodity description information of the commodity acquisition results is acquired, relevance scores of the commodity acquisition results and the input information are determined according to the input information and the commodity description information, labels of the candidate live merchants are acquired, the relevance scores of the commodity acquisition results corresponding to the candidate live merchants are adjusted according to the labels of the candidate live merchants, and finally the commodity acquisition results are sorted according to the adjusted relevance scores. Therefore, the purpose of searching related commodity live broadcast through the input information of the user can be achieved, and meanwhile, the intelligent sequencing and active guidance of the search results are achieved.
In order to clearly illustrate the above embodiment, in one possible implementation manner of the embodiment of the present disclosure, acquiring the intention characteristic of the user according to the input information may include acquiring intention information of the user according to the input information, and if the intention information of the user is a search intention, further extracting search attribute information from the input information, and taking the search attribute information as the intention characteristic.
It should be noted that the search intention described in this embodiment may be a commodity search intention, where the commodity search intention may correspond to node information of each level of the commodity category tree; the search attribute information described in this embodiment may include entity words, brand words, attribute words, and the like corresponding to the search terms.
In an example, the commodity search method provided by the embodiment of the disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein in a process that a user operates the short video APP with the live broadcast function by using the mobile phone, the short video APP can be operated to call up a search bar, search information is input in the search bar according to a shopping requirement of the user, and intention information of the user can be acquired according to the input search information, for example, if the search information of the user is "sepal lotus red lipstick", the intention information can be considered as a commodity search intention, and for example, if the search information of the user is "dancing live broadcast", the intention information can be considered as a viewing intention. If the user's intention information is a search intention (e.g., a commodity search intention), search attribute information may be further extracted from among the input information and used as an intention feature. For example, the search information is: "Meibaoyan red lipstick" is intended to be understood as: with the intention of searching for the item, the search attribute information may include: the entity word: a lipstick; brand words: beautiful lotus; attribute words: red, the intent features may include: lipstick, Meibaoyan, red. Therefore, the intention characteristics of the input information of the user are extracted, the current requirements of the user can be intuitively and accurately captured, the final search result can better meet the current requirements of the user, and detailed search terms (namely the intention characteristics) are provided for subsequent search.
For clarity of the above embodiment, in a possible implementation manner of the embodiment of the present disclosure, after further extracting the search attribute information from the input information, extracting a current node of the product category tree from the search attribute information may further be included.
In one example, the commodity searching method provided by the embodiment of the disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein after the mobile phone extracts search attribute information from input information, the mobile phone can extract a current node of a commodity category tree from the search attribute information. For example, when the search attribute information includes: the entity word: a lipstick; brand words: beautiful lotus; attribute words: in red, the extracted commodity tree can be first class tree, skin care product/cosmetic/cleaning product; class II, cosmetics; a third category, lipstick, the current node may be: cosmetic product-lipstick, or lipstick, without any limitation herein. Thus, the accuracy of the search can be improved.
In the embodiment of the present disclosure, the extraction of the search attribute information and the extraction of the current node of the commodity category tree may be implemented by an extraction model, where the extraction model may be trained in advance and pre-stored in a storage space of an electronic device (e.g., a mobile phone) to facilitate access to an application, the storage space is not limited to an entity-based storage space, such as a hard disk, and the storage space may also be a storage space (cloud storage space) of a network hard disk connected to the electronic device (e.g., a mobile phone).
The training and the generation of the extraction model can be performed by a related server, the server can be a cloud server or a host of a computer, a communication connection is established between the server and the electronic equipment capable of executing the commodity searching method provided by the public embodiment, and the communication connection can be at least one of a wireless network connection and a wired network connection. The server can send the trained extraction model to the electronic device so that the electronic device can call the extraction model when needed, and therefore computing stress of the electronic device is greatly reduced.
In a possible implementation manner of the embodiment of the present disclosure, the obtaining of the multiple commodity obtaining results of multiple candidate live-broadcast merchants according to the intention characteristics of the user may include generating an obtaining keyword according to the intention characteristics, and obtaining according to the obtaining keyword to generate a candidate commodity set, where the candidate commodity set includes multiple commodity obtaining results, and each commodity obtaining result corresponds to a candidate live-broadcast merchant.
In an example, the commodity searching method provided by the embodiment of the disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein after the mobile phone obtains an intention feature of a user, the mobile phone can generate an obtaining keyword according to all definitions of a solid word, an attribute word, a brand name and the like in the intention feature, wherein the obtaining keyword can correspond to a commodity in the deepest first-level category tree (for example, input information of the user is ' megbaolian red lipstick ', and corresponding category tree information is ' first-level category: skin care product/cosmetic/cleaning product; second-level category: cosmetic; and ' third-level category: lipstick ', all commodities in ' lipstick ' category of the third-level category can be obtained only). Then, the mobile phone performs acquisition according to the acquisition keyword to generate an acquisition candidate commodity set, for example, the plurality of commodity acquisition results may be lipsticks of various brands and color numbers, and corresponding candidate live merchants (i.e., live merchants with live lipstick). Therefore, a user with shopping requirements can find the anchor selling such commodities by inputting information (keywords), and the use experience of the user is improved.
To clearly illustrate the previous embodiment, in a possible implementation manner of the embodiment of the present disclosure, the obtaining according to the obtaining keyword to generate the obtained candidate commodity set may include obtaining a commodity obtaining result corresponding to a current node of the commodity category tree and adding the commodity obtaining result to the obtained candidate commodity set, and if the quantity of the commodity obtaining results in the obtained candidate commodity set is less than a preset quantity, searching for a higher-level node along the commodity category tree from the current node, and adding the commodity obtaining result corresponding to the higher-level node to the obtained candidate commodity set. The preset quantity can be calibrated according to actual conditions.
In one example, the method for searching for a commodity provided by the embodiment of the present disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein after the mobile phone obtains a back key word, the mobile phone can obtain a commodity obtaining result corresponding to a current node (for example, lipstick) of a commodity category tree, and add the commodity obtaining result to an obtained candidate commodity set, and when the number of the commodity obtaining results in the obtained candidate commodity set is smaller than a preset number, the mobile phone can search for an upper node along the commodity category tree from the current node, and add the commodity obtaining result corresponding to the upper node to the obtained candidate commodity set (for example, input information of a user is "mejuan lipstick", and corresponding category tree information is a first-level category: skin care product/cosmetic/cleaning product, a second-level category: cosmetic, a third-level category: lipstick, all commodities in the secondary category 'cosmetics' category are acquired currently) so as to expand the number of commodities in the acquired candidate commodity set.
Further, in another possible implementation manner of the embodiment of the present disclosure, if the number of the commodity obtaining results in the obtained candidate commodity set is still smaller than the preset number, the obtained keywords are filtered, the obtained keywords are obtained again according to the filtered obtained keywords, and the obtained commodity obtaining results are added to the obtained candidate commodity set.
In an example, the commodity searching method provided by the embodiment of the disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein if the number of commodity acquisition results in an acquired candidate commodity set is still smaller than a preset number after a commodity acquisition result corresponding to a superior node is added to the acquired candidate commodity set, the acquired keywords may be filtered (for example, a part of the limitations of attribute words and trademark names are removed), the acquired keywords are acquired again according to the filtered acquired keywords, and the re-acquired commodity acquisition result is added to the acquired candidate commodity set. For example, the restriction of the trade name in the acquisition keyword "scholartree, red and lipstick" is removed, that is, the "scholartree" in the acquisition keyword is removed to keep "red and lipstick", thereby further expanding the number of the commodities in the acquisition candidate commodity set.
It should be noted that the method for expanding and acquiring the number of commodities in the candidate commodity set may be repeatedly executed until the number of commodity acquisition results in the candidate commodity set is greater than or equal to the preset number.
In a possible implementation manner of the embodiment of the present disclosure, the tag may be a dynamic tag, where obtaining tags of multiple candidate live merchants may include: and acquiring current live broadcast content or current explanation content of the candidate live broadcast commercial tenant, and identifying the current live broadcast content or the current explanation content to generate a label.
In one example, referring to fig. 2 and 3, for a live broadcast room, a live broadcast current content tag may be established according to a content understanding tag of a current live broadcast room of a selected live broadcast merchant, such as a yield (1) video understanding tag shown in fig. 2. The live broadcast video stream of the current live broadcast room of the live broadcast merchant is acquired, the live broadcast video stream is input into the convolutional neural network in a frame extraction mode, and the video output through the convolutional neural network understands the label, wherein the label can be hierarchical, for example, as follows: a first stage: "gourmet/digital/article/clothing/game draw full", second level: "fresh/bagged food/keyboard/men's clothing", third level: instant noodles/business suit/king glory.
For the content of the product being explained by the anchor in the live broadcast room (i.e., the currently explained content), the currently explained content is identified to generate a tag, such as output (1), keyword/keyword (tag) shown in fig. 3. The method comprises the steps of obtaining a live broadcast video stream of a current live broadcast room of a live broadcast merchant, inputting the live broadcast video stream into a recurrent neural network in an audio slicing mode, outputting a text through the recurrent neural network, and then performing text word segmentation, syntax analysis, keyword extraction program, named entity identification and the like to generate keywords/keywords (labels).
Therefore, the label can be generated by identifying based on the current live broadcast content or the current explanation content, so that the generated label can better express the current live broadcast room, and the searching accuracy can be improved.
In a possible implementation manner of the embodiment of the present disclosure, the tag may be a static tag, where obtaining tags of multiple candidate live merchants may include extracting commodity description information of the candidate live merchants, and generating the tag according to the commodity description information.
In another possible implementation manner of the embodiment of the present disclosure, the tag may be a static tag, where obtaining tags of multiple candidate live broadcast merchants may include obtaining historical live broadcast content of the candidate live broadcast merchants, and generating the tag according to the historical live broadcast content.
In one example, for a live broadcast room, the commodity description information of candidate live broadcast merchants, such as the commodity title, the participle of the commodity description, keywords, pictures of the commodity, etc., can be extracted, and then word embedding (word vector) deeply learned from the commodity description information is performed to generate related labels, such as the outcome (2) shown in fig. 1. Or generating the label directly according to the category tree information of the commodity. And then establishing an anchor label through anchor historical live broadcast content (namely, historical live broadcast content of candidate live broadcast merchants), keywords of the anchor live broadcast historically searched, and the like. Therefore, the labels can be enriched and diversified, and the searching accuracy is further improved.
In a possible implementation manner of the embodiment of the present disclosure, the tag may be a feature tag, where obtaining tags of multiple candidate live broadcast merchants may include obtaining user statistical features and/or commodity sales statistical features of the candidate live broadcast merchants, and generating the tag according to the user statistical features and/or the commodity sales statistical features.
In one example, for the live broadcast room, statistical characteristics of the current live broadcast room (such as online number of people, amount of like, total sales order amount) and/or sales statistical characteristics of the current goods (such as sales amount, sales evaluation, after sales) can be obtained, and the tags can be generated according to the statistical characteristics of the current live broadcast room and/or the sales statistical characteristics of the current goods. Therefore, the generated label is more consistent with the commodity sales and attention characteristics, and the search result can take the commodity sales and attention characteristics into consideration.
In one possible implementation manner of the embodiment of the disclosure, determining, according to the input information and the commodity description information, a correlation score between the plurality of commodity obtaining results and the intention characteristics of the user may include obtaining the commodity description information of the commodity obtaining results, and determining an initial correlation score according to the input information and the commodity description information of the commodity obtaining results.
Further, in another possible implementation manner of the embodiment of the present disclosure, adjusting the initial relevance score according to the intention characteristics may also be included.
In an example, the method for searching for a product provided by the embodiment of the present disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, where the mobile phone may obtain a plurality of product obtaining results of a plurality of candidate live broadcast merchants according to an intention characteristic of a user, analyze the product obtaining results to obtain product description information of the product obtaining results, and then determine a relevance score of the product obtaining results and input information according to the input information (e.g., a american lotus red lipstick) and the product description information (e.g., a product title, a product name, and the like) by using a preset relevance algorithm, or finely adjust the relevance result by using an intention understanding result (a brand name, an attribute word, category tree information) of the input information and product labeling information (a product category, a keyword calibrated by a vendor) and knowledge in a business field (e.g., a user search word "coconut shoe", the e-commerce domain knowledge will partially weight the adidas brand results), and then adjust the correlation results by using the anchor information, the live content understanding and the commodity explanation content (for example: the user search term (input information) "mebao lotus red lipstick" weights the commercial results such as the live main broadcasting of lipstick and the live broadcasting of cosmetics during explanation in history). Therefore, the obtained relevance score can fully meet the requirements of the user, and the final search result is more reasonable and scientific to display.
In a possible implementation manner of the embodiment of the present disclosure, the sorting of the multiple commodity acquisition results according to the adjusted relevance scores may include acquiring node levels of nodes where the multiple commodity acquisition results are located, and sorting the multiple commodity acquisition results according to the node levels and the adjusted relevance scores.
It should be noted that, due to the hierarchical acquisition mechanism, the acquired result defined more deeply in the category tree is always arranged in front of the acquired result defined less deeply in the category tree (for example, the user search word "mebao lotus red lipstick", the product of the third category "lipstick" is always arranged in front of the product of the second category "cosmetics"); the commodities limited by the brand words and the attribute words are always ranked in front of the obtained result with relaxed limitation. In addition, the relevance weight of the commodities related to the live broadcast content and the anchor field can be amplified, so that the commodity results searched by the user can obtain the service of 'explaining', and the search results with high click rate and high order placing rate of the user can be weighted, so that multi-target balance is realized.
In one example, the commodity search method provided by the embodiment of the disclosure is applied to a short video APP with a live broadcast function, and the short video APP is installed in a mobile phone, wherein the mobile phone can obtain the node level of a node where a plurality of commodity acquisition results are located after obtaining the adjusted correlation score, and sequence the plurality of commodity acquisition results according to the node level and the adjusted correlation score, wherein due to the particularity of commodity search based on a live broadcast scene, a plurality of optimization targets are comprehensively considered in a sequencing stage, for example, a result with high correlation is ranked in front as much as possible, a commodity with high commodity score is ranked in front as much as possible, a result with high unit number under a user is ranked in front as much as possible, a result with high duration under the live broadcast user is ranked in front as much as possible (considering the profit of a platform), thereby realizing intelligent sequencing and active guidance of search results, and further, the display of the search result is more in line with the requirements of the user.
In summary, according to the commodity searching method provided by the embodiment of the disclosure, first, input information of a user is obtained, intention characteristics of the user are obtained according to the input information, then, a plurality of commodity obtaining results of a plurality of candidate live merchants are obtained according to the intention characteristics of the user, commodity description information of the commodity obtaining results is obtained, relevance scores of the commodity obtaining results and the input information are determined according to the input information and the commodity description information, then, labels of the candidate live merchants are obtained, the relevance scores of the commodity obtaining results corresponding to the candidate live merchants are adjusted according to the labels of the candidate live merchants, and finally, the commodity obtaining results are sorted according to the adjusted relevance scores. Therefore, the purpose of searching related commodity live broadcast through the input information of the user can be achieved, and meanwhile, the intelligent sequencing and active guidance of the search results are achieved.
Fig. 4 is a block diagram illustrating an article search device according to an exemplary embodiment. Referring to fig. 4, the article search device 40 may include: a first obtaining module 41, a second obtaining module 42, a third obtaining module 43, a determining module 44, a fourth obtaining module 45, and a sorting module 46.
The first obtaining module 41 is configured to obtain input information of a user, and obtain an intention characteristic of the user according to the input information.
The second obtaining module 42 is configured to obtain a plurality of goods obtaining results of a plurality of candidate live merchants according to the intention characteristics of the user.
The third acquisition module 43 is configured to acquire the commodity description information of the plurality of commodity acquisition results.
The determination module 44 is configured to determine the relevance scores of the plurality of product acquisition results and the input information according to the input information and the product description information.
The fourth obtaining module 45 is configured to obtain the tags of the multiple candidate live broadcast merchants, and adjust the correlation scores of the product obtaining results corresponding to the multiple candidate live broadcast merchants according to the tags of the multiple candidate live broadcast merchants.
The ranking module 46 is configured to rank the plurality of item acquisition results according to the adjusted relevance scores.
In a possible implementation manner of the embodiment of the present disclosure, the first obtaining module 41 may include:
an acquisition unit configured to acquire intention information of a user from input information;
a first extraction unit configured to further extract search attribute information from among the input information if the intention information of the user is a search intention, and to take the search attribute information as an intention feature.
In a possible implementation manner of the embodiment of the present disclosure, the first obtaining module 42 may further include:
a second extraction unit configured to extract a current node of the commodity category tree from the search attribute information after the first extraction unit further extracts the search attribute information from the input information.
In a possible implementation manner of the embodiment of the present disclosure, the second obtaining module 42 may include:
a generation unit configured to generate an acquisition keyword according to the intention feature;
the acquisition unit is configured to acquire the candidate commodities according to the acquisition keywords to generate an acquisition candidate commodity set, wherein the acquisition candidate commodity set comprises a plurality of commodity acquisition results, and each commodity acquisition result corresponds to a candidate live merchant.
In a possible implementation manner of the embodiment of the present disclosure, the obtaining unit is specifically configured to:
acquiring a commodity acquisition result corresponding to the current node of the commodity category tree, and adding the commodity acquisition result to the acquired candidate commodity set;
and if the quantity of the commodity obtaining results in the obtained candidate commodity set is less than the preset quantity, searching a superior node from the current node along the commodity category tree, and adding the commodity obtaining results corresponding to the superior node into the obtained candidate commodity set.
In a possible implementation manner of the embodiment of the present disclosure, the obtaining unit is further configured to:
if the number of the commodity obtaining results in the candidate commodity set is still smaller than the preset number, screening and reducing the obtained keywords;
and acquiring again according to the acquired keywords after screening and subtracting, and adding the acquired commodity acquisition result into the acquired candidate commodity set.
In a possible implementation manner of the embodiment of the present disclosure, the tag is a dynamic tag, wherein the fourth obtaining module 45 is specifically configured to:
acquiring current live broadcast content or current explanation content of candidate live broadcast merchants;
the current live content or the current explanation content is identified to generate a tag.
In a possible implementation manner of the embodiment of the present disclosure, the tag is a static tag, wherein the fourth obtaining module 45 is specifically configured to:
extracting commodity description information of candidate live merchants;
and generating a label according to the commodity description information.
In a possible implementation manner of the embodiment of the present disclosure, the tag is a static tag, where the fourth obtaining module 45 is specifically configured to:
acquiring historical live broadcast content of candidate live broadcast merchants;
and generating a label according to the historical live content.
In a possible implementation manner of the embodiment of the present disclosure, the tag is a feature tag, where the fourth obtaining module 45 is specifically configured to:
acquiring user statistical characteristics and/or commodity sales statistical characteristics of candidate live merchants;
and generating the label according to the user statistical characteristics and/or the commodity sales statistical characteristics.
In one possible implementation manner of the embodiment of the present disclosure, the determining module 44 is specifically configured to:
acquiring commodity description information of a commodity acquisition result;
and determining an initial correlation score according to the input information and the commodity description information of the commodity acquisition result.
In one possible implementation manner of the embodiment of the present disclosure, the determining module 44 is further configured to:
the initial relevance score is adjusted according to the intent characteristics.
In one possible implementation manner of the embodiment of the present disclosure, the sorting module 45 is specifically configured to:
acquiring node levels of nodes where a plurality of commodity acquisition results are located;
and sequencing the plurality of commodity acquisition results according to the node progression and the adjusted relevance scores.
In practical use, the article searching device provided by the embodiment of the disclosure may be configured in an electronic device to execute the article searching method. Therefore, with regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
In summary, the commodity searching device provided in the embodiments of the present disclosure first obtains the input information of the user through the first obtaining module, and obtains the intention characteristics of the user according to the input information, and obtains a plurality of commodity obtaining results of a plurality of candidate live merchants according to the intention characteristics of the user through a second obtaining module, then, the third acquisition module acquires the commodity description information of a plurality of commodity acquisition results, the determination module determines the correlation scores of the plurality of commodity acquisition results and the input information according to the input information and the commodity description information, the fourth acquisition module acquires the labels of a plurality of candidate live merchants, and adjusting the relevance scores of the commodity acquisition results corresponding to the candidate live broadcast merchants according to the labels of the candidate live broadcast merchants, and finally sequencing the commodity acquisition results through a sequencing module according to the adjusted relevance scores. Therefore, the purpose of searching related commodity live broadcast through the input information of the user can be achieved, and meanwhile, the intelligent sequencing and active guidance of the search results are achieved.
In order to realize the above embodiment, the present disclosure further provides an electronic device.
The electronic equipment comprises a processor and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the above-mentioned item search method.
In order to implement the above embodiments, the present disclosure also provides a storage medium.
Wherein the instructions in the storage medium, when executed by a processor of the electronic device, enable the electronic device to perform the above-described item search method.
To implement the above embodiments, the present disclosure also provides a computer program product.
Wherein the computer program, when executed by a processor of the electronic device, enables the electronic device to perform the above-described item search method.
FIG. 5 is a block diagram of an electronic device shown in accordance with an example embodiment. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, the electronic device 50 includes a processor 51, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 52 or a program loaded from a Memory 56 into a Random Access Memory (RAM) 53. In the RAM 53, various programs and data necessary for the operation of the electronic apparatus 50 are also stored. The processor 51, the ROM 52, and the RAM 53 are connected to each other via a bus 55. An Input/Output (I/O) interface 55 is also connected to the bus 55.
The following components are connected to the I/O interface 55: a memory 56 including a hard disk and the like; and a communication section 57 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like, the communication section 57 performing communication processing via a Network such as the internet; a drive 58 is also connected to the I/O interface 55 as necessary.
In particular, the processes described above with reference to the flow diagrams may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program embodied on a computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 57. The computer program, when executed by the processor 51, performs the above-described functions defined in the method of the present disclosure.
In an exemplary embodiment, there is also provided a storage medium comprising instructions, such as a memory comprising instructions, executable by the processor 51 of the electronic device 50 to perform the above-described method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method for searching for a commodity, comprising:
acquiring input information of a user, and acquiring intention characteristics of the user according to the input information;
obtaining a plurality of commodity obtaining results of a plurality of candidate live commercial tenants according to the intention characteristics of the user;
acquiring commodity description information of the plurality of commodity acquisition results;
determining relevance scores of the plurality of commodity obtaining results and the input information according to the input information and the commodity description information;
obtaining labels of the candidate live broadcast merchants, and adjusting the correlation scores of the commodity obtaining results corresponding to the candidate live broadcast merchants according to the labels of the candidate live broadcast merchants; and
and sorting the plurality of commodity acquisition results according to the adjusted relevance scores.
2. The item search method according to claim 1, wherein the obtaining of the user's intention characteristic from the input information includes:
acquiring intention information of the user according to the input information;
if the intention information of the user is a search intention, further extracting search attribute information from the input information, and taking the search attribute information as the intention characteristic.
3. The article search method according to claim 2, further comprising, after said further extracting search attribute information from among said input information:
and extracting the current node of the commodity category tree from the search attribute information.
4. The method for searching for commodities according to claim 2 or 3, wherein said obtaining a plurality of commodity obtaining results of a plurality of candidate live merchants according to the intention characteristics of the user comprises:
generating and acquiring a keyword according to the intention characteristics;
and obtaining the candidate commodity set according to the obtained keywords to generate a candidate commodity set, wherein the candidate commodity set comprises a plurality of commodity obtaining results, and each commodity obtaining result corresponds to a candidate live merchant.
5. The item search method according to claim 4, wherein the obtaining according to the obtaining keyword to generate a candidate item set comprises:
acquiring a commodity acquisition result corresponding to the current node of the commodity category tree, and adding the commodity acquisition result to the acquired candidate commodity set;
and if the quantity of the commodity obtaining results in the obtained candidate commodity set is less than the preset quantity, searching a superior node from the current node along the commodity category tree, and adding the commodity obtaining results corresponding to the superior node to the obtained candidate commodity set.
6. The item search method according to claim 5, further comprising:
if the number of the commodity obtaining results in the candidate commodity set is still smaller than the preset number, screening and reducing the obtained keywords;
and acquiring again according to the acquired keywords after being screened, and adding the acquired commodity acquisition result into the acquired candidate commodity set.
7. The item search method according to claim 1, wherein the sorting the plurality of item acquisition results according to the adjusted relevance scores includes:
acquiring node levels of nodes where the plurality of commodity acquisition results are located;
and sequencing the plurality of commodity acquisition results according to the node progression and the adjusted relevance scores.
8. An article search device, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire input information of a user and acquire intention characteristics of the user according to the input information;
the second acquisition module is configured to acquire a plurality of commodity acquisition results of a plurality of candidate live merchants according to the intention characteristics of the user;
a third obtaining module configured to obtain commodity description information of the plurality of commodity obtaining results;
a determining module configured to determine relevance scores of the plurality of commodity obtaining results and the input information according to the input information and the commodity description information;
a fourth obtaining module, configured to obtain the tags of the multiple candidate live broadcast merchants, and adjust the correlation scores of the commodity obtaining results corresponding to the multiple candidate live broadcast merchants according to the tags of the multiple candidate live broadcast merchants; and
a ranking module configured to rank the plurality of commodity acquisition results according to the adjusted relevance scores.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the item search method of any one of claims 1-7.
10. A storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the item search method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110286778.3A CN115114506A (en) | 2021-03-17 | 2021-03-17 | Commodity searching method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110286778.3A CN115114506A (en) | 2021-03-17 | 2021-03-17 | Commodity searching method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115114506A true CN115114506A (en) | 2022-09-27 |
Family
ID=83324318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110286778.3A Pending CN115114506A (en) | 2021-03-17 | 2021-03-17 | Commodity searching method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115114506A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100223157A1 (en) * | 2007-10-15 | 2010-09-02 | Simardip Kalsi | Online virtual knowledge marketplace |
| CN102253936A (en) * | 2010-05-18 | 2011-11-23 | 阿里巴巴集团控股有限公司 | Method for recording access of user to merchandise information, search method and server |
| TW201207646A (en) * | 2010-08-13 | 2012-02-16 | Alibaba Group Holding Ltd | Inquiry method, system and device based on vertical search |
| CN102663627A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Personalized recommendation method |
| CN111970523A (en) * | 2020-08-13 | 2020-11-20 | 北京达佳互联信息技术有限公司 | Information display method, device, terminal, server and storage medium |
-
2021
- 2021-03-17 CN CN202110286778.3A patent/CN115114506A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100223157A1 (en) * | 2007-10-15 | 2010-09-02 | Simardip Kalsi | Online virtual knowledge marketplace |
| CN102253936A (en) * | 2010-05-18 | 2011-11-23 | 阿里巴巴集团控股有限公司 | Method for recording access of user to merchandise information, search method and server |
| TW201207646A (en) * | 2010-08-13 | 2012-02-16 | Alibaba Group Holding Ltd | Inquiry method, system and device based on vertical search |
| CN102663627A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Personalized recommendation method |
| CN111970523A (en) * | 2020-08-13 | 2020-11-20 | 北京达佳互联信息技术有限公司 | Information display method, device, terminal, server and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| Y. WANG 等: "A mobile recommendation system based on logistic regression and gradient boosting decision trees", 《2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS》, 3 November 2016 (2016-11-03), pages 1896 - 1902 * |
| 黄建平: "基于用户参考价格倾向度的协同过滤推荐算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑 》, no. 2016, 15 January 2016 (2016-01-15), pages 138 - 1043 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12039447B2 (en) | Information processing method and terminal, and computer storage medium | |
| US20180053234A1 (en) | Description information generation and presentation systems, methods, and devices | |
| CN109034973B (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation system and computer-readable storage medium | |
| CN110929021B (en) | Text information generation method and text information generation device | |
| CN110427548B (en) | Information pushing method, information pushing device and computer readable storage medium | |
| CN113032676B (en) | Recommendation method and system based on micro-feedback | |
| CN116894711A (en) | Commodity recommendation reason generation method and device and electronic equipment | |
| CN113946754A (en) | User portrait based rights and interests recommendation method, device, equipment and storage medium | |
| CN111767420A (en) | Method and device for generating clothing matching data | |
| CN115907868A (en) | Advertisement delivery analysis method and device | |
| CN111209351A (en) | Object relation prediction method and device, object recommendation method and device, electronic equipment and medium | |
| CN111695041A (en) | Method and device for recommending information | |
| KR102149035B1 (en) | Advertising page creation and management system for performance marketing | |
| CN115860870A (en) | Commodity recommendation method, system and device and readable medium | |
| CN111787042A (en) | Method and device for pushing information | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| US12062060B2 (en) | Method and device for processing user interaction information | |
| CN107688600B (en) | Knowledge point mining method and device | |
| CN112446214A (en) | Method, device and equipment for generating advertisement keywords and storage medium | |
| CN109299378B (en) | Search result display method and device, terminal and storage medium | |
| CN112818082A (en) | Evaluation text pushing method and device | |
| CN115114506A (en) | Commodity searching method and device, electronic equipment and storage medium | |
| CN114330519A (en) | Data determination method and device, electronic equipment and storage medium | |
| CN108205526A (en) | A kind of method and apparatus of determining Technique Using Both Text information | |
| CN111464641B (en) | Message pushing optimization method and device and readable storage medium |
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 |