CN112396433A - Method and system for identifying false commodity comments based on behavior of person to be evaluated - Google Patents
Method and system for identifying false commodity comments based on behavior of person to be evaluated Download PDFInfo
- Publication number
- CN112396433A CN112396433A CN202011368839.2A CN202011368839A CN112396433A CN 112396433 A CN112396433 A CN 112396433A CN 202011368839 A CN202011368839 A CN 202011368839A CN 112396433 A CN112396433 A CN 112396433A
- Authority
- CN
- China
- Prior art keywords
- behavior
- comment
- candidate
- seller
- professional
- 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
- G06Q30/01—Customer relationship services
- G06Q30/012—Providing warranty services
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and a system for identifying false commodity comments based on behavior of a person to be evaluated, wherein the method comprises the following steps: step 1: matching the commenting persons of the commodity comments with the professional commenting person list in the professional commenting person database; step 2: calculating the characteristic value of the candidate, and judging through an occupation candidate behavior characteristic model; and step 3: judging whether the comment is deleted according to a preset comment strategy; and 4, step 4: and judging whether the behavior of the shop of the seller is abnormal or not according to a preset abnormal behavior strategy of the shop of the seller, and if so, sending a correction notice to the seller or closing the shop. The invention can delete the false comments left by the E-commerce seller according to the platform policy requirements, judge whether the E-commerce seller violates the platform rules according to the cooperation condition of the commodities and the professional comment-leaving person, and simultaneously send out the violation correction notice, and even close the on-line shop when the violation correction notice is serious, thereby achieving the purpose of managing the platform commodity comments.
Description
Technical Field
The invention relates to the technical field of E-commerce platform comment governance, in particular to a method and a system for identifying false commodity comments based on behavior of a person who makes comments.
Background
Before shopping online, the consumer browses the description and functions of the goods. It will not be purchased immediately because he is still uncertain whether the descriptions are correct. The comments of other people who purchased the product are sought. These reviews may convince him to eventually purchase the item, or may give up the purchase because of the shortcomings of the item seen in the review. Therefore, the content of the comment has a crucial influence on the transaction conversion rate of the commodity.
Therefore, e-commerce sellers will want to try to improve their positive reviews of their products and reduce their negative reviews. The E-commerce platform is used as a trading intermediate matching party, and false comments of various commodities are reduced as far as possible.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a method and a system for identifying false commodity comments based on behavior of a person who makes a comment, so as to reduce false comments of various commodities.
In order to solve the above technical problem, an embodiment of the present invention provides a method for identifying false product reviews based on behavior of a reviewer, including:
step 1: matching the newly generated commodity comment candidate of the seller shop with the professional comment candidate list in the professional comment candidate database, and entering step 3 if the matching is successful; if the matching fails, entering the step 2;
step 2: calculating the characteristic value of the candidate, judging whether the comment is a normal comment or a comment of the candidate through the behavior characteristic model of the candidate, and if the comment is a comment of the candidate, adding the candidate to a list of the candidate; if the comment is a normal comment, marking the commodity comment as a normal comment;
and step 3: judging whether the comment is deleted according to a preset comment strategy, and if so, entering a step 4;
and 4, step 4: and judging whether the behavior of the shop of the seller is abnormal or not according to a preset abnormal behavior strategy of the shop of the seller, and if so, sending a correction notice to the seller or closing the shop.
Further, step 1 is preceded by:
a database construction step: acquiring information of the professional candidate, extracting a sample of behavior characteristics of the professional candidate, and constructing a database of the professional candidate;
a model construction step: and constructing a behavior feature model of the job retention and evaluation person, and training the behavior feature model of the job retention and evaluation person through a sample in a job retention and evaluation person database by adopting a preset machine learning algorithm.
Further, the preset seller shop abnormal behavior strategy comprises one or more of a ratio of the comments of all the commodities of the shop to the professional reviewer, a ratio of the deleted comments to the reservations of the commodities of the seller shop, and a ratio of the amount of orders of the seller to the number of comments.
Further, step 2 is followed by:
training: and training a behavior characteristic model of the job candidate according to the judged job candidate comment.
Correspondingly, the embodiment of the invention also provides a system for identifying false commodity comments based on behavior of a person who makes comments, which comprises the following steps:
a list matching module: matching the newly generated commodity comment candidate of the seller shop with a professional comment candidate list in a professional comment candidate database;
an extraction and arrangement module: if the list matching module fails to match, extracting and structuring the features of the remaining appraisers, and calculating feature values of the remaining appraisers;
a matching module: judging whether the comment is a normal comment or a comment of the professional candidate through a behavior feature model of the professional candidate according to the feature value of the candidate;
a behavior determination module: and judging whether the comment is deleted according to a preset comment strategy, if so, judging whether the behavior of the seller shop is abnormal according to a preset abnormal behavior strategy library of the seller shop, and if so, sending a correction notice to the seller or closing the shop.
Further, a professional reviewer database comprising professional reviewer information and behavioral characteristic samples is also included.
Further, training the behavior feature model of the professional raters through samples in the professional rater database by adopting a preset machine learning algorithm.
Further, the system also comprises a characteristic training module for training the behavior characteristic model of the professional candidate according to the comments of the professional candidate determined by the matching module.
Further, the seller abnormal behavior strategy library comprises one or more of a ratio of the comments of all the commodities of the shop to the professional reviewers to the normal buyers, a ratio of the deleted comments to the reserved commodities of the shop of the seller, and a ratio of the number of orders of the seller to the number of the comments.
Further, the system also comprises a management module for managing the performance of the seller according to the behavior of the shop of the seller.
The invention has the beneficial effects that: the invention can delete the false comments left by the E-commerce seller according to the platform policy requirements, judge whether the E-commerce seller violates the platform rules according to the cooperation condition of the commodities and the professional comment-leaving person, and simultaneously send out the violation correction notice, and even close the on-line shop when the violation correction notice is serious, thereby achieving the purpose of managing the platform commodity comments.
Drawings
FIG. 1 is a flow chart of a method of identifying false product reviews based on a rater behavior in accordance with embodiments of the invention.
Fig. 2 is a block diagram of a system for identifying false product reviews based on a rater behavior in accordance with an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other without conflict, and the present invention is further described in detail with reference to the drawings and specific embodiments.
If directional indications (such as up, down, left, right, front, and rear … …) are provided in the embodiment of the present invention, the directional indications are only used to explain the relative position relationship between the components, the movement, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indications are changed accordingly.
In addition, the descriptions related to "first", "second", etc. in the present invention are only used for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature.
Referring to fig. 1, the method for identifying false commodity reviews based on behavior of the reviewer according to the embodiment of the invention comprises steps 1-4.
Step 1: matching the newly generated commodity comment candidate of the seller shop with the professional comment candidate list in the professional comment candidate database, and entering step 3 if the matching is successful; and if the matching fails, entering the step 2. The commodity comments newly generated by the seller shop in the embodiment of the invention comprise comments left after the order is completed and comments directly left on a certain commodity, namely, the comments on the certain commodity do not need to be firstly generated, and the comments can be directly left on the certain commodity but can be marked as the comments which are not actually purchased. The invention can effectively reduce false comments of various commodities.
Step 2: calculating the characteristic value of the candidate, judging whether the comment is a normal comment or a comment of the candidate through the behavior characteristic model of the candidate, and if the comment is a comment of the candidate, adding the candidate to a list of the candidate; and if the comment is a normal comment, marking the commodity comment as a normal comment.
And step 3: and judging whether the comment is deleted according to a preset comment strategy, and if so, entering the step 4.
And 4, step 4: and judging whether the behavior of the shop of the seller is abnormal or not according to a preset abnormal behavior strategy of the shop of the seller, and if so, sending a correction notice to the seller or closing the shop.
As an embodiment, step 1 further includes:
a database construction step: acquiring information of the professional candidate, extracting a sample of behavior characteristics of the professional candidate, and constructing a database of the professional candidate;
a model construction step: and constructing a behavior feature model of the job retention and evaluation person, and training the behavior feature model of the job retention and evaluation person through a sample in a job retention and evaluation person database by adopting a preset machine learning algorithm.
As one embodiment, the preset seller store abnormal behavior strategy comprises one or more of a ratio of the comments of all the commodities of the store to the professional reviewer, a ratio of the deleted comments to the reservations of the commodity history of the seller store, and a ratio of the number of orders of the seller to the number of comments.
As an embodiment, step 2 is followed by:
training: and training a behavior characteristic model of the job candidate according to the judged job candidate comment.
Referring to fig. 2, the system for identifying false commodity comments based on behavior of the person who makes comments includes a list matching module, an extraction and arrangement module, a matching module, and a behavior determination module.
A list matching module: and matching the raters of the newly generated commodity comments of the stores of the sellers with the professional rater lists in the professional rater database. The list matching module reads the professional critic database, and if the critics of the target comments directly hit the database, a subsequent matching process is not needed. The commodity comments newly generated by the seller shop include comments left after the order is completed and comments directly left on a certain commodity.
An extraction and arrangement module: and if the list matching module fails to match, extracting and structuring the features of the candidate to be evaluated, and calculating the feature value of the candidate to be evaluated. The extraction and arrangement module is responsible for extracting and structuring the evaluation retention characteristics of the evaluation retention person, and the evaluation retention characteristics comprise but are not limited to: the system comprises a comment processing platform, a comment setting module, a comment ranking module, a comment post-purchase rate module, a comment registration time length module, a comment video module, a comment word module, a comment age module, a comment person classification module, a source address or a website for entering a platform of a comment, and the like.
A matching module: and judging whether the comment is a normal comment or a comment of the professional candidate according to the feature value of the candidate through the behavior feature model of the professional candidate. Various characteristics of the candidate are input into a matching module, and a machine learning algorithm is adopted to match the characteristics by utilizing a pre-trained behavior characteristic model of the professional candidate. Typical machine learning algorithms that can be used are XGBoost, C4.5 decision trees, random deep forest, neural networks, etc. The algorithm output is set to be a 0 or 1 discrete value to directly indicate whether the appraiser is a professional appraiser or not; or a value between 0 and 1, representing the probability that the candidate being the target comment is a professional candidate, which is considered a comment of the professional candidate if it is greater than a preset threshold (e.g., 60%).
A behavior determination module: and judging whether the comment is deleted according to a preset comment strategy, if so, judging whether the behavior of the seller shop is abnormal according to a preset abnormal behavior strategy library of the seller shop, and if so, sending a correction notice to the seller or closing the shop.
And when the comments of the professional commentators are judged, entering a behavior judgment module for further processing. The module judges according to a strategy in a preset seller abnormal behavior strategy library to obtain a conclusion:
1. whether to delete the comment or not;
2. whether the commodity comment in the seller store is manipulated; this is a violation.
3. How serious the violation is, what action is taken with the store of the seller.
4. Typical examples of strategies are: comments on all items of the store leave rates for professional reviewers versus normal buyers, rates for sellers versus reservations for deleted comments of store item histories, seller orders versus number of comments, and so on.
As an embodiment, the system for identifying false commercial comments based on the behavior of the rater further comprises a professional rater database comprising professional rater information and behavioral characteristic samples. In the embodiment of the invention, a perfect professional reviewer database is continuously collected in the operation process, and when a certain buyer is judged as a professional reviewer, the perfect professional reviewer database is added into the database. Professional raters obtained from other external channels or from seller reporting means are also added to the database after platform verification.
As an embodiment, the system for identifying false commodity comments based on behavior of the rater further comprises training a behavior feature model of the professional rater through samples in a database of the professional rater by using a preset machine learning algorithm. The behavior feature model of the job retention evaluation person in the embodiment of the invention needs to adopt a corresponding machine learning algorithm to train a large number of samples in advance, and the larger the number of the samples is, the higher the accuracy rate of the behavior features of the job retention evaluation person is, and generally more than one hundred thousand orders of magnitude are needed. The sample acquisition method comprises the following steps: a buyer of daily abnormal commenting behavior is found; the seller reports an abnormal comment-leaving person; external professional interviewer active social website groups, public numbers, forums, and the like.
As one implementation mode, the system for identifying false commodity comments based on the behavior of the candidate also comprises a feature training module for training a behavior feature model of the professional candidate according to the professional candidate comments determined by the matching module.
As one embodiment, the system for identifying false product comments based on the behavior of the raters further comprises a seller abnormal behavior strategy library, wherein the seller abnormal behavior strategy library comprises one or more of the ratio of the comments of all products of the store to the professional raters to the normal buyers, the ratio of the deleted comments to the reservations of the product history of the store of the seller, and the ratio of the amount of orders of the seller to the number of comments.
As one embodiment, the system for identifying false commodity comments based on the behavior of the raters further comprises a management module for managing the performance of the seller according to the behavior of the shop of the seller. The management module performs various processes on the seller, such as sending a warning message to inform the seller to stop manipulating the behavior of comments, and closing the shop of the seller at the platform in a severe scene or even directly.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A method for identifying false commercial reviews based on behavior of a candidate, comprising:
step 1: matching the newly generated commodity comment candidate of the seller shop with the professional comment candidate list in the professional comment candidate database, and entering step 3 if the matching is successful; if the matching fails, entering the step 2;
step 2: calculating the characteristic value of the candidate, judging whether the comment is a normal comment or a comment of the candidate through the behavior characteristic model of the candidate, and if the comment is a comment of the candidate, adding the candidate to a list of the candidate; if the comment is a normal comment, marking the commodity comment as a normal comment;
and step 3: judging whether the comment is deleted according to a preset comment strategy, and if so, entering a step 4;
and 4, step 4: and judging whether the behavior of the shop of the seller is abnormal or not according to a preset abnormal behavior strategy of the shop of the seller, and if so, sending a correction notice to the seller or closing the shop.
2. The method for identifying false commercial reviews based on rater behavior of claim 1, wherein step 1 is preceded by the further step of:
a database construction step: acquiring information of the professional candidate, extracting a sample of behavior characteristics of the professional candidate, and constructing a database of the professional candidate;
a model construction step: and constructing a behavior feature model of the job retention and evaluation person, and training the behavior feature model of the job retention and evaluation person through a sample in a job retention and evaluation person database by adopting a preset machine learning algorithm.
3. The method for identifying false product reviews based on rater behavior as claimed in claim 2, wherein the preset seller store abnormal behavior strategy comprises one or more of a ratio of reviews of all products of the store to professional raters, a ratio of reviews of seller store product history deleted to reservations, and a ratio of seller orders to reviews.
4. The method for identifying false product reviews based on rater behavior as claimed in claim 2, further comprising, after step 2:
training: and training a behavior characteristic model of the job candidate according to the judged job candidate comment.
5. A system for identifying false commercial reviews based on behavior of a candidate, comprising:
a list matching module: matching the newly generated commodity comment candidate of the seller shop with a professional comment candidate list in a professional comment candidate database;
an extraction and arrangement module: if the list matching module fails to match, extracting and structuring the features of the remaining appraisers, and calculating feature values of the remaining appraisers;
a matching module: judging whether the comment is a normal comment or a comment of the professional candidate through a behavior feature model of the professional candidate according to the feature value of the candidate;
a behavior determination module: and judging whether the comment is deleted according to a preset comment strategy, if so, judging whether the behavior of the seller shop is abnormal according to a preset abnormal behavior strategy library of the seller shop, and if so, sending a correction notice to the seller or closing the shop.
6. The system for identifying false commercial comments based on rater behavior of claim 5, further comprising a professional rater database containing professional rater information and behavioral characteristic samples.
7. The system for identifying false commercial comments based on rater behavior of claim 6, further comprising training a model of professional rater behavior characteristics through samples in a database of professional rater behaviors using a pre-set machine learning algorithm.
8. The system for identifying false commercial comments based on rater behavior of claim 7, further comprising a feature training module for training a model of operational rater behavior features based on the operational rater comments determined by the matching module.
9. The system for identifying false product reviews based on rater behavior as claimed in claim 5, further comprising a seller anomalous behavior policy repository, the seller anomalous behavior policy repository comprising one or more of a ratio of reviews of all products of the store left behind to professional raters to normal buyers, a ratio of reviews of the store product history of the seller deleted to reservations, and a ratio of the number of orders of the seller to the number of reviews.
10. The system for identifying false reviews of merchandise based on rater behavior as recited in claim 5, further comprising a management module that manages seller performance based on seller store behavior.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011368839.2A CN112396433A (en) | 2020-11-30 | 2020-11-30 | Method and system for identifying false commodity comments based on behavior of person to be evaluated |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011368839.2A CN112396433A (en) | 2020-11-30 | 2020-11-30 | Method and system for identifying false commodity comments based on behavior of person to be evaluated |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112396433A true CN112396433A (en) | 2021-02-23 |
Family
ID=74604757
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011368839.2A Pending CN112396433A (en) | 2020-11-30 | 2020-11-30 | Method and system for identifying false commodity comments based on behavior of person to be evaluated |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112396433A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112700265A (en) * | 2021-03-23 | 2021-04-23 | 广州格鲁信息技术有限公司 | Anti-fraud system and method based on big data processing |
CN114245163A (en) * | 2021-12-15 | 2022-03-25 | 四川启睿克科技有限公司 | Method for filtering bullet screen of robot |
CN115983873A (en) * | 2022-12-29 | 2023-04-18 | 珠海蓝度科技有限公司 | Big data based user data analysis management system and method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6144855B1 (en) * | 2016-03-01 | 2017-06-07 | 楽天株式会社 | Recommended device, recommended method, program, and recording medium |
JP2017123185A (en) * | 2017-02-27 | 2017-07-13 | 株式会社ぐるなび | Information processing apparatus, information processing method, and program |
CN109241527A (en) * | 2018-08-24 | 2019-01-18 | 浙江工商大学 | A kind of Chinese commodity falseness comment data collection automatic generation method |
CN109711955A (en) * | 2019-02-18 | 2019-05-03 | 杭州跨境邦信息技术有限公司 | Difference based on current order comments method for early warning, system, blacklist library method for building up |
CN109829733A (en) * | 2019-01-31 | 2019-05-31 | 重庆大学 | A kind of false comment detection system and method based on Shopping Behaviors sequence data |
CN110134770A (en) * | 2019-05-30 | 2019-08-16 | 莆田学院 | A kind of waterborne troops's comment on commodity falseness detection device and method based on capsule network |
CN110288362A (en) * | 2019-07-03 | 2019-09-27 | 北京工业大学 | Brush single prediction technique, device and electronic equipment |
CN111666480A (en) * | 2020-06-10 | 2020-09-15 | 东北电力大学 | False comment identification method based on rolling type collaborative training |
-
2020
- 2020-11-30 CN CN202011368839.2A patent/CN112396433A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6144855B1 (en) * | 2016-03-01 | 2017-06-07 | 楽天株式会社 | Recommended device, recommended method, program, and recording medium |
JP2017123185A (en) * | 2017-02-27 | 2017-07-13 | 株式会社ぐるなび | Information processing apparatus, information processing method, and program |
CN109241527A (en) * | 2018-08-24 | 2019-01-18 | 浙江工商大学 | A kind of Chinese commodity falseness comment data collection automatic generation method |
CN109829733A (en) * | 2019-01-31 | 2019-05-31 | 重庆大学 | A kind of false comment detection system and method based on Shopping Behaviors sequence data |
CN109711955A (en) * | 2019-02-18 | 2019-05-03 | 杭州跨境邦信息技术有限公司 | Difference based on current order comments method for early warning, system, blacklist library method for building up |
CN110134770A (en) * | 2019-05-30 | 2019-08-16 | 莆田学院 | A kind of waterborne troops's comment on commodity falseness detection device and method based on capsule network |
CN110288362A (en) * | 2019-07-03 | 2019-09-27 | 北京工业大学 | Brush single prediction technique, device and electronic equipment |
CN111666480A (en) * | 2020-06-10 | 2020-09-15 | 东北电力大学 | False comment identification method based on rolling type collaborative training |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112700265A (en) * | 2021-03-23 | 2021-04-23 | 广州格鲁信息技术有限公司 | Anti-fraud system and method based on big data processing |
CN114245163A (en) * | 2021-12-15 | 2022-03-25 | 四川启睿克科技有限公司 | Method for filtering bullet screen of robot |
CN115983873A (en) * | 2022-12-29 | 2023-04-18 | 珠海蓝度科技有限公司 | Big data based user data analysis management system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110222272B (en) | Potential customer mining and recommending method | |
CN110009174B (en) | Risk recognition model training method and device and server | |
CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
US20170323358A1 (en) | Evaluating public records of supply transactions | |
CN112396433A (en) | Method and system for identifying false commodity comments based on behavior of person to be evaluated | |
CN108038696B (en) | Method and system for detecting bill swiping based on equipment identification code and social group information | |
CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
US20130317954A1 (en) | Ranking entities based on a count of shipments determined in aggregated public transaction records | |
Wu et al. | User Value Identification Based on Improved RFM Model and K‐Means++ Algorithm for Complex Data Analysis | |
CN105074748A (en) | Profiling auction assets and/or participants to predict auction outcome | |
CN107403345A (en) | Best-selling product Forecasting Methodology and system, storage medium and electric terminal | |
KR101660445B1 (en) | Market survey and analysis system | |
CN113516496B (en) | Advertisement conversion rate estimation model construction method, device, equipment and medium thereof | |
CN112633927B (en) | Combined commodity mining method based on knowledge graph rule embedding | |
CN113362126A (en) | Order data detection method and system applied to online business | |
CN110659926A (en) | Data value evaluation system and method | |
CN111461827A (en) | Product evaluation information pushing method and device | |
CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
JP2021039631A (en) | Information processing method, program, and information processing device | |
CN117236996B (en) | User behavior prediction method and system based on big data analysis | |
KR20190044155A (en) | Method and server for managing a bulletin board for used goods transactions, and computer readable recording medium | |
CN117196758A (en) | Screening method, equipment and medium for commodity before being put on shelf | |
CN110889716A (en) | Method and device for identifying potential registered user | |
Iqbal | Machine learning applications in e-commerce | |
CN115511582A (en) | Artificial intelligence based Commodity recommendation system and method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210223 |