CN111553765A - E-commerce search sorting method and device and computing equipment - Google Patents
E-commerce search sorting method and device and computing equipment Download PDFInfo
- Publication number
- CN111553765A CN111553765A CN202010344793.4A CN202010344793A CN111553765A CN 111553765 A CN111553765 A CN 111553765A CN 202010344793 A CN202010344793 A CN 202010344793A CN 111553765 A CN111553765 A CN 111553765A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- commodity
- interest
- scoring
- 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
Images
Classifications
-
- 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
-
- 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
- G06F16/90—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
Abstract
The invention relates to an e-commerce search sorting method, an e-commerce search sorting device and computing equipment. The method comprises the following steps: receiving a search keyword of a user; analyzing the search keywords to obtain user interest characteristics and commodity category characteristics; and grading the candidate commodities by using a grading model based on an interest activation method in combination with the user interest characteristics and the category characteristics of the commodities, outputting the grade of each candidate commodity, and selecting and sequencing the candidate commodities according to the grade of the candidate commodities. The candidate commodities are scored by using the scoring model based on the interest activation method, the features related to the current candidate commodities are selected for sorting, interference of irrelevant features on sorting is reduced, searching sorting is more accurate, and the interests of the user can be accurately estimated so as to make accurate recommendation.
Description
Technical Field
The invention relates to the technical field of e-commerce search, in particular to an e-commerce search sorting method, an e-commerce search sorting device and computing equipment.
Background
The original e-commerce search sorting technology can be divided into two types:
the first method is mainly used by part of E-commerce with a relatively primary comparison, is based on reverse arrangement and established based on keywords and full commodity text for retrieval, and is based on contents such as search keywords, titles/descriptions of commodities and the like, and is used for sequencing through correlation calculated by a text similarity algorithm such as BM 25. Such methods do not fully exploit the personalized features of the user, and in particular do not consider various real-time behaviors, such as: after a user clicks/collects/pays attention to a commodity, the relevance obtained by adopting a text similarity algorithm such as BM25 is ranked only according to the contents such as search keywords, titles/descriptions of the commodity and the like, and a model of the method cannot be used for continuously learning in time according to the user behavior so as to perform different rankings on different users.
The second method is to add user portrait on the basis of the first method, the method is used by a part of large-scale e-commerce, the method firstly establishes the user portrait, and uses machine learning models such as logistic regression and the like to sequence click rate modeling after the characteristics, commodities and key words are crossed according to the user portrait. The method considers the influence of all behavior records on the score of the commodity on average, and causes the deviation of the similarity of the commodity due to less commodity score data. And the commodity similarity only depends on the scoring of the commodity by the user, and the inherent characteristics of the commodity are not comprehensively considered. Therefore, the calculated commodity similarity is not accurate, and the sorted commodities cannot accurately reflect the commodities which the user really wants to search.
Disclosure of Invention
In order to overcome the problems in the related technology, the invention provides the E-commerce search sorting method, the E-commerce search sorting device and the E-commerce search sorting computing equipment, which select the features related to the current candidate commodity for sorting, reduce the interference of irrelevant features to sorting, enable the search sorting to be more accurate, and can accurately predict the interest of the user so as to make accurate recommendation.
According to a first aspect of the embodiments of the present invention, there is provided an e-commerce search ranking method, including:
receiving a search keyword of a user;
analyzing the search keywords to obtain user interest characteristics and commodity category characteristics; scoring the candidate commodities by using a scoring model based on an interest activation method in combination with the user interest characteristics and the category characteristics of the commodities, and outputting the score of each candidate commodity;
and selecting and sorting the candidate commodities according to the grade of the candidate commodities.
According to a second aspect of the embodiments of the present invention, there is provided an electronic commerce search ranking device, including an information receiving module, a data processing module, a commodity scoring module, and a commodity ranking module:
the information receiving module is used for receiving search keywords of a user;
the data processing module is used for analyzing the search keywords to obtain user interest characteristics and commodity category characteristics;
the commodity scoring module is used for scoring the candidate commodities by utilizing a scoring model based on an interest activation method according to the user interest characteristics and the commodity category characteristics and outputting the score of each candidate commodity;
and the commodity ordering module is used for selecting and ordering the candidate commodities according to the grade of the candidate commodities.
According to a third aspect of embodiments of the present invention, there is provided a computing device comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects: the candidate commodities are scored by using the scoring model based on the interest activation method, the features related to the current candidate commodities are selected for sorting, interference of irrelevant features on sorting is reduced, searching sorting is more accurate, and the interests of the user can be accurately estimated so as to make accurate recommendation.
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 invention, as claimed.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
FIG. 1 is a flow diagram illustrating an e-commerce search ranking method in accordance with an exemplary embodiment of the present invention;
FIG. 2 is a flowchart illustrating scoring model generation in an e-commerce search ranking method in accordance with an exemplary embodiment of the present invention;
FIG. 3 is a schematic block diagram illustrating an e-commerce search ranking apparatus in accordance with an exemplary embodiment of the present invention;
FIG. 4 is a schematic block diagram of a scoring model generation module of an e-commerce search ranking apparatus according to an exemplary embodiment of the present invention;
FIG. 5 is a block diagram illustrating a computing device in accordance with an exemplary embodiment of the present invention.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The invention provides an E-commerce search ordering method, device and computing equipment, which select and order the features related to the current candidate commodity, reduce the interference of irrelevant features on ordering, enable the search ordering to be more accurate, and can more accurately predict the interest of a user so as to make accurate recommendation.
Fig. 1 is a flow chart illustrating an e-commerce search ranking method in accordance with an exemplary embodiment of the present invention.
As shown in fig. 1, the method comprises the following steps:
in step 101, a search keyword of a user is received. Here, the user may input a name of a specific commodity in a search box of the e-commerce platform, for example: socks, shoes, ladies' coats, etc.
After step 101 is completed, step 102 may be entered to analyze the search keywords to obtain user interest features and commodity category features. In the step, the keywords are analyzed and processed by word segmentation, semantic analysis and the like to obtain search keywords of the user, so that a user interest characteristic value is obtained, and then a proper commodity category is selected from a commodity category library according to the user interest characteristic to obtain a commodity category characteristic. For example: when a user searches for a skirt recently, the user finds a commodity library of the skirt category in the commodity library. And selecting a proper commodity category from the commodity category library according to the user interest characteristic value to obtain the commodity category characteristic.
After step 102 is completed, step 103 is entered, and candidate commodities are selected from the commodity library according to the commodity category characteristics and the interest characteristics.
After step 101 is completed, step 104 may also be entered to perform user real-time attribute imaging on the user according to the user's search keyword and user information.
After completing step 101, step 105 may also be entered for user offline portrayal of the user based on the user's search keywords, user information, and user history data. The historical data of this step may include user historical search data, historical purchase data, collection data, etc., for example: history searched women's overcoat, purchased women's skirt, and collected information such as socks. The user information includes: contact information, user address and the like.
After the steps 103, 104 and 105 are completed, the method proceeds to step 106, scores are carried out on the candidate commodities by using a scoring model based on an interest activation method in combination with the user interest characteristics, the commodity category characteristics, the user offline portrait data and the user real-time attribute portrait data, and scores of each candidate commodity are output.
Finally, step 107, selecting and sorting the candidate commodities according to the grade of the candidate commodities.
According to the embodiment, whether the interest of the user is activated or not is calculated in real time according to the commodities to be selected, then the commodities are sorted, and finally the commodities are issued according to the sorting result.
It should be noted that, in this embodiment, the execution sequence of step 102, step 104, and step 105 is not limited, and the execution sequence may be changed, performed simultaneously, or may have a sequence.
As seen from the embodiment, the invention firstly receives the search keywords of the user; then analyzing the search keywords to obtain user interest characteristics and commodity category characteristics; scoring the candidate commodities by using a scoring model based on an interest activation method in combination with the user interest characteristics and the category characteristics of the commodities, and outputting the score of each candidate commodity; and selecting and sorting the candidate commodities according to the grade of the candidate commodities. The candidate commodities are scored by using the scoring model based on the interest activation method, the features related to the current candidate commodities are selected for sorting, interference of irrelevant features on sorting is reduced, searching sorting is more accurate, and the interests of the user can be accurately estimated so as to make accurate recommendation.
Fig. 2 is a flowchart illustrating a scoring model generation process in an e-commerce search ranking method according to an exemplary embodiment of the present invention.
As shown in fig. 2, a scoring model based on an interest activation method is generated using user history data and user interests, and the generating step may include:
step 201, collecting historical recommendation data, client historical data and conversion data.
And 202, correlating the historical recommendation data, the client historical data and the conversion data to obtain correlated user behavior data.
Step 203, structuring the associated user behavior data into specific format data.
And step 204, inputting the structured and associated user behavior data, historical portrait data, real-time portrait data and commodity feature table into a scoring model for model training, and generating a scoring model based on an interest activation method.
The scoring model scores the candidate goods in step 103 in the previous embodiment, and assuming that the score (such as click rate score) of the final goods is calculated by a logistic regression model, a traditional logistic regression formula can be used
W iniChange to interest activation function
A score is made, wherein,
here, similar (x)iUSER,xitem) W _ i is a quotient of co-occurrences under the user interest category and the commodity category calculated off-lineThe items are used for evaluating the similarity between the interest categories of the users and the commodity categories. F (x) is the target that the function last predicted, here click-through rate. sigmod is a common sigmod function. I.e. w in the formula is the weight for each feature. x is the characteristics used including user characteristics such as gender, age, merchandise characteristics such as sales and scores, etc. b is a parameter of a model, namely a bias term of logistic regression. Here, the previous weight w of the part of the user features in x is changed to the activation function. By the method, the effect of emphasizing the related behavior history and enabling the unrelated history to be lighter or even neglected can be achieved, and therefore the accuracy of the whole scoring model is improved.
Corresponding to the embodiment of the application function implementation method, the invention also provides an E-commerce search sequencing device and a corresponding embodiment.
Fig. 3 is a schematic block diagram illustrating an e-commerce search ranking apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 3, an electronic commerce search ranking apparatus may include: an information receiving module 301, a data processing module 302, a goods scoring module 306 and a goods sorting module 307.
An information receiving module 301, configured to receive a search keyword of a user. Here, the information receiving module 301 may receive a name of a specific commodity entered by a user in a search box of the e-commerce platform, for example: socks, shoes, ladies' coats, etc.
And the data processing module 302 is configured to analyze the search keyword to obtain user interest features and category features of the product. The data processing module 302 performs analysis processing such as word segmentation and semantic analysis on the keywords to obtain search keywords of the user, and further obtain a user interest feature value, and then selects a proper commodity category from the commodity category library according to the user interest feature to obtain a commodity category feature. For example: when a user searches for a skirt recently, the user finds a commodity library of the skirt category in the commodity library. And selecting a proper commodity category from the commodity category library according to the user interest characteristic value to obtain the commodity category characteristic.
In a preferred real-time mode, the apparatus further comprises: a candidate selection module 303, a real-time rendering module 304, and an offline rendering module 305.
And the candidate commodity selection module 303 is configured to select a candidate commodity from a commodity library according to the commodity category feature and the interest feature.
And the real-time portrait module 304 is used for performing user real-time attribute portrait on the user according to the search keyword and the user information of the user.
And an offline portrayal module 305 for user offline portrayal of the user according to the user's search keywords, user information and user history data. The historical data in the embodiment can include user historical search data, historical purchase data, collection data and the like, for example: history searched women's overcoat, purchased women's skirt, and collected information such as socks. The user information includes: contact information, user address and the like.
And the commodity scoring module 306 is used for scoring the candidate commodities by combining the user interest characteristics, the commodity category characteristics, the user offline portrait data and the user real-time attribute portrait data and utilizing a scoring model based on an interest activation method, and outputting the score of each candidate commodity.
And the commodity sorting module 307 is used for selecting and sorting the candidate commodities according to the grade of the candidate commodities.
In a preferred embodiment, a scoring model generation module 308 is also included for generating a scoring model based on the interest-activated methods using the user history data and the user interests.
Fig. 4 is a schematic block diagram of a scoring model generation module of an e-commerce search ranking apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 4, the scoring model generation module includes: a data acquisition unit 401, a data association unit 402 and a model generation unit 403.
And the data acquisition unit 401 is configured to acquire historical recommendation data, client historical data, and conversion data.
A data association unit 402, configured to associate the historical recommendation data, the client historical data, and the conversion data to obtain associated user behavior data.
And a model generating unit 403, configured to input the associated user behavior data, historical portrait data, real-time portrait data, and commodity feature table into a scoring model for model training, and generate a scoring model based on the interest activation method. The scoring model generated by the scoring model generation module in this embodiment scores candidate commodities, and the score (such as click rate score) of the final commodity is calculated by using the logistic regression model, so that the traditional logistic regression formula can be used
W iniChange to interest activation function
A score is made, wherein,
here, similar (x)iUSER,xitem) W _ i is to evaluate the similarity between the user interest category and the commodity category by calculating commodities co-occurring under the user interest category and the commodity category offline. F (x) is the target that the function last predicted, here click-through rate. sigmod is a common sigmod function. I.e. w in the formula is the weight for each feature. The method comprises the following steps of obtaining a user characteristic (such as gender and age) and a commodity characteristic (such as sales volume, score, the user characteristic is such as gender and age, and the commodity characteristic is such as sales volume and score, and the like).
In a preferred embodiment, the device further comprises a data structuring unit (not shown in the figure) for structuring the associated user behavior data into specific format data.
According to the embodiment, the information receiving module receives the search keywords of the user; then the data processing module analyzes the search keywords to obtain the user interest characteristics and the commodity category characteristics; the commodity scoring module is used for scoring the candidate commodities by combining the user interest characteristics and the commodity category characteristics and utilizing a scoring model based on an interest activation method, and the score of each candidate commodity is output; and the commodity sorting module selects and sorts the candidate commodities according to the grade of the candidate commodities. The candidate commodities are scored by using the scoring model based on the interest activation method, the features related to the current candidate commodities are selected for sorting, interference of irrelevant features on sorting is reduced, searching sorting is more accurate, and the interests of the user can be accurately estimated so as to make accurate recommendation.
Fig. 5 is a schematic structural diagram of a computing device that can be used to implement the above-described e-commerce search ranking method according to an exemplary embodiment of the present invention. The computing device may be, for example, a mobile terminal device or a server device or the like.
As shown in fig. 5, computing device 500 includes memory 510 and processor 520.
The processor 520 may be a multi-core processor or may include a plurality of processors. In some embodiments, processor 520 may include a general-purpose host processor and one or more special coprocessors such as a Graphics Processor (GPU), a Digital Signal Processor (DSP), or the like. In some embodiments, processor 520 may be implemented using custom circuitry, such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA).
The memory 510 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions for the processor 520 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 510 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 510 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a digital versatile disc read only (e.g., DVD-ROM, dual layer DVD-ROM), a Blu-ray disc read only, an ultra-dense disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disk, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
Memory 510 has stored thereon executable code that, when processed by processor 520, causes processor 520 to perform one of the above-described e-commerce search ranking methods.
The above-described method according to the present invention has been described in detail hereinabove with reference to the accompanying drawings.
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 here.
Furthermore, the method according to the invention may also be implemented as a computer program or computer program product comprising computer program code instructions for carrying out the above-mentioned steps defined in the above-mentioned method of the invention.
Alternatively, the invention may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or computing device, server, etc.), causes the processor to perform the steps of the above-described method according to the invention.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. An e-commerce search ranking method, comprising:
receiving a search keyword of a user;
analyzing the search keywords to obtain user interest characteristics and commodity category characteristics;
scoring the candidate commodities by using a scoring model based on an interest activation method in combination with the user interest characteristics and the category characteristics of the commodities, and outputting the score of each candidate commodity;
and selecting and sorting the candidate commodities according to the grade of the candidate commodities.
2. The method of claim 1, further comprising: a scoring model based on an interest-activated approach is generated using the user history data and the user interests.
3. The method of claim 2, wherein generating a scoring model based on an interest-activated approach using user historical data and user interests comprises:
collecting historical recommendation data, client historical data and conversion data;
correlating the historical recommendation data, the client historical data and the conversion data to obtain correlated user behavior data;
and inputting the associated user behavior data, historical portrait data, real-time portrait data and commodity feature table into a scoring model for model training, and generating the scoring model based on the interest activation method.
4. The method of claim 3, further comprising:
structuring the associated user behavior data into specific format data;
inputting the associated user behavior data, historical portrait data, real-time portrait data and commodity feature table into a scoring model for model training, and generating the scoring model based on the interest activation method as follows:
and inputting the structured and associated user behavior data, historical portrait data, real-time portrait data and commodity feature table into a scoring model for model training, and generating a scoring model based on an interest activation method.
5. The method of claim 1, further comprising:
performing user offline portrait on a user according to the search keywords, the user information and the user historical data of the user;
and inputting the user offline portrait data into a scoring model based on an interest activation method for scoring candidate commodities.
6. The method of any of claims 1-5, further comprising:
performing user real-time attribute portrayal on a user according to the search keywords and the user information of the user;
and inputting the real-time attribute image data of the user into a scoring model based on an interest activation method, and scoring the candidate commodities.
7. The utility model provides an electricity merchant searches for sequencing device, includes, information receiving module, data processing module, commodity score module and commodity sequencing module:
the information receiving module is used for receiving search keywords of a user;
the data processing module is used for analyzing the search keywords to obtain user interest characteristics and commodity category characteristics;
the commodity scoring module is used for scoring the candidate commodities by utilizing a scoring model based on an interest activation method according to the user interest characteristics and the commodity category characteristics and outputting the score of each candidate commodity;
and the commodity ordering module is used for selecting and ordering the candidate commodities according to the grade of the candidate commodities.
8. The apparatus of claim 7, further comprising: and the scoring model generating module is used for generating a scoring model based on an interest activation method by using the historical data of the user and the interest of the user.
9. The apparatus of claim 8, wherein the scoring model generation module comprises: the system comprises a data acquisition unit, a data association unit and a model generation unit;
the data acquisition unit is used for acquiring historical recommendation data, client historical data and conversion data;
the data association unit is used for associating the historical recommendation data, the client historical data and the conversion data to obtain associated user behavior data;
and the model generation unit is used for inputting the associated user behavior data, historical portrait data, real-time portrait data and commodity feature table into the scoring model for model training, and generating the scoring model based on the interest activation method.
10. A computing device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010344793.4A CN111553765A (en) | 2020-04-27 | 2020-04-27 | E-commerce search sorting method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010344793.4A CN111553765A (en) | 2020-04-27 | 2020-04-27 | E-commerce search sorting method and device and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111553765A true CN111553765A (en) | 2020-08-18 |
Family
ID=72004108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010344793.4A Pending CN111553765A (en) | 2020-04-27 | 2020-04-27 | E-commerce search sorting method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553765A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258264A (en) * | 2020-09-30 | 2021-01-22 | 中智关爱通（上海）科技股份有限公司 | Welfare commodity selection method and system |
| CN112991004A (en) * | 2021-02-06 | 2021-06-18 | 上海红星美凯龙泛家信息服务有限公司 | Interest classification scoring method and system based on portrait and computer storage medium |
| CN113744015A (en) * | 2020-10-20 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Sorting method, device, equipment and computer storage medium |
| CN113744017A (en) * | 2020-11-13 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | E-commerce search recommendation method and device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102479366A (en) * | 2010-11-25 | 2012-05-30 | 阿里巴巴集团控股有限公司 | Commodity recommending method and system |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106874492A (en) * | 2017-02-23 | 2017-06-20 | 北京京东尚科信息技术有限公司 | Searching method and device |
| CN109189904A (en) * | 2018-08-10 | 2019-01-11 | 上海中彦信息科技股份有限公司 | Individuation search method and system |
-
2020
- 2020-04-27 CN CN202010344793.4A patent/CN111553765A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102479366A (en) * | 2010-11-25 | 2012-05-30 | 阿里巴巴集团控股有限公司 | Commodity recommending method and system |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106874492A (en) * | 2017-02-23 | 2017-06-20 | 北京京东尚科信息技术有限公司 | Searching method and device |
| CN109189904A (en) * | 2018-08-10 | 2019-01-11 | 上海中彦信息科技股份有限公司 | Individuation search method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258264A (en) * | 2020-09-30 | 2021-01-22 | 中智关爱通（上海）科技股份有限公司 | Welfare commodity selection method and system |
| CN113744015A (en) * | 2020-10-20 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Sorting method, device, equipment and computer storage medium |
| CN113744017A (en) * | 2020-11-13 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | E-commerce search recommendation method and device, equipment and storage medium |
| CN112991004A (en) * | 2021-02-06 | 2021-06-18 | 上海红星美凯龙泛家信息服务有限公司 | Interest classification scoring method and system based on portrait and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111553765A (en) | E-commerce search sorting method and device and computing equipment | |
| US8190601B2 (en) | Identifying task groups for organizing search results | |
| CN103329126B (en) | Utilize the search of joint image-audio query | |
| US10664515B2 (en) | Task-focused search by image | |
| US10354308B2 (en) | Distinguishing accessories from products for ranking search results | |
| CN106557480B (en) | Method and device for realizing query rewriting | |
| US20230153870A1 (en) | Unsupervised embeddings disentanglement using a gan for merchant recommendations | |
| TW201520790A (en) | Individualized data search | |
| US20060173753A1 (en) | Method and system for online shopping | |
| CN104951468A (en) | Data searching and processing method and system | |
| US20220414167A1 (en) | Techniques to leverage machine learning for search engine optimization | |
| CA2781326C (en) | System, method and computer program product for parcel assessment | |
| KR20080045659A (en) | Information processing device, method, and program | |
| Yao et al. | An ensemble model for fake online review detection based on data resampling, feature pruning, and parameter optimization | |
| US20100042610A1 (en) | Rank documents based on popularity of key metadata | |
| US11682060B2 (en) | Methods and apparatuses for providing search results using embedding-based retrieval | |
| CN111582984A (en) | Commodity recommendation method and device and computing equipment | |
| US11599927B1 (en) | Artificial intelligence system using deep neural networks for pairwise character-level text analysis and recommendations | |
| US20120117043A1 (en) | Measuring Duplication in Search Results | |
| US20230044152A1 (en) | System and method for multi-modal transformer-based catagorization | |
| CN110851694A (en) | Personalized recommendation system based on user memory network and tree structure depth model | |
| JP7256357B2 (en) | Information processing device, control method, program | |
| CN111553762A (en) | Method, system and terminal equipment for improving search quality | |
| JP5310196B2 (en) | Classification system revision support program, classification system revision support device, and classification system revision support method | |
| Nanopoulos et al. | Know thy neighbor: combining audio features and social tags for effective music similarity |
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 |