CN111767438A - Identity recognition method based on Hash combined integral - Google Patents
Identity recognition method based on Hash combined integral Download PDFInfo
- Publication number
- CN111767438A CN111767438A CN202010550121.9A CN202010550121A CN111767438A CN 111767438 A CN111767438 A CN 111767438A CN 202010550121 A CN202010550121 A CN 202010550121A CN 111767438 A CN111767438 A CN 111767438A
- Authority
- CN
- China
- Prior art keywords
- hamming distance
- hamming
- weighted
- commerce
- value
- 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 16
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 230000008447 perception Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims 3
- 230000006399 behavior Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technical field of e-commerce data software, and discloses an identity identification method based on Hash and integral, which solves the technical problem that the identification of the same client across different service platforms is difficult at present, and comprises the following steps: the method comprises the steps of firstly, respectively obtaining client character information and head portrait image information of two E-commerce platforms; secondly, respectively calculating Hash values of head portrait image information of clients of the two E-commerce platforms; thirdly, calculating the Hamming distance of the Hash values of the head portrait image information of the customers of the two E-commerce platforms; fourthly, carrying out weighted calculation on the hamming distance to obtain a weighted hamming distance; and fifthly, comparing the weighted hamming distance thresholds and comparing the obtained nickname characters of the client. According to the technical scheme, the image similarity of the customers of different service platforms from the E-commerce merchant is analyzed, so that the recognition task across different service platforms is completed. And simultaneously, the characters of various information fields are analyzed, so that the aim of accurate identification is fulfilled.
Description
Technical Field
The invention relates to the technical field of e-commerce data software, in particular to an identity identification method based on Hash and integral combination.
Background
The social development is rapid, the industrial age is advanced to the scientific and technological age, the scientific and technological age is advanced to the information age, the information age has strict requirements on analysis and processing of various data, the social benefits brought by the data are more reasonably applied, and the scientific and technological development is accelerated.
In the society at present, customers of the e-commerce platform need to collect customer information obtained from the e-commerce service platform under different wechat systems, and then follow-up sales operation work is carried out. The customer information gathered by the customers of the e-commerce platform has a great effect on subsequent sales operation work, the supply and demand relationship of the society can be reasonably controlled, and the resource utilization rate is improved.
However, at present, since the identity information of customers on different service platforms is not intercommunicated, a merchant cannot aggregate the information (such as orders) of each platform to the same customer. The reason is that customers of the service platform and the e-commerce platform stand at different angles, the service platform provides own services (such as a mall, an applet and the like), and when a merchant acquires customer information of different service platforms, the same customer cannot be effectively identified. Therefore, the identification of the same customer across different service platforms requires a technique to address.
Disclosure of Invention
Aiming at the technical problem that the identification of the same client across different service platforms is difficult at present in the background technology, the invention aims to analyze the image similarity of the client from different service platforms to help complete the identification task across different service platforms. And simultaneously, the characters of various information fields are analyzed, so that the aim of accurate identification is fulfilled.
In order to achieve the purpose, the invention provides the following technical scheme:
an identity recognition method based on Hash combined integral comprises the following steps:
the method comprises the steps of firstly, respectively obtaining client character information and head portrait image information of two E-commerce platforms;
secondly, calculating an aHash value, a pHash value and a dHash value of the client head portrait image information of the two E-commerce platforms respectively, wherein the aHash is an average Hash algorithm value, the pHash is a perception Hash algorithm value, and the dHash is a difference Hash algorithm value;
thirdly, calculating the Hamming distance aHashHamming of client head portrait image information aHash values of the two E-commerce platforms, calculating the Hamming distance pHashHamming of client head portrait image information pHash values of the two E-commerce platforms, and calculating the Hamming distance dHashHamming of client head portrait image information dHash values of the two E-commerce platforms;
fourthly, carrying out weighted calculation on the Hamming distance to obtain weighted Hamming distance Hamming, wherein Hamming is AHashHamming X + pHashHamming Y + dHamhHamming Z;
fifthly, comparing the weighted Hamming distance with a preset threshold value, simultaneously comparing the nickname characters of the customers of the two E-commerce platforms,
the weighted Hamming distance Hamming is less than the set threshold and the characters are the same, the matching is confirmed,
the weighted Hamming distance Hamming is greater than the set threshold and the characters are the same, confirming the mismatch,
the weighted Hamming distance Hamming is less than the set threshold and the characters are different, the mismatching is confirmed,
and confirming that the weighted Hamming distance Hamming is larger than a set threshold value and the characters are different from each other, and mismatching.
By the technical scheme, in order to solve the identification task across different service platforms, the image similarity of the customers of the E-commerce platforms of the different service platforms is analyzed, and meanwhile, other fields are effectively combined for identity authentication, so that the accuracy is improved. Specifically, three Hash algorithms, namely an average Hash algorithm (aHash), a perceptual Hash algorithm (pHash) and a differential Hash algorithm (dHash), are utilized; and calculating a Hash value through three Hash algorithms, and then calculating the Hamming distance of the two numerical values, wherein the smaller the Hamming distance is, the higher the image similarity is. Moreover, the similarity of the character information of the customers of the E-commerce platform is analyzed, the identification accuracy of the same customer is improved, and through the matching of the similarity of the head portrait and the matching of the similarity of the character information, the identification dimension can be increased, and the identification rate is improved. Therefore, the purchasing and behavior conditions of the same customer on different service platforms are accurately judged, and a good foundation is laid for fine operation and service.
The invention is further configured to: the service platform A and the service platform B are used by two e-commerce, and the service platform A and the service platform B are different e-commerce software service platforms or fields.
Through the technical scheme, the conditions of purchase, behavior and the like of different service platforms can be more accurately judged.
The invention is further configured to: when the weighted Hamming distance Hamming is smaller than a set threshold value, obtaining an integral '1';
when the weighted Hamming distance Hamming is larger than a set threshold value, an integral '0' is obtained;
when the character information of the customers of the two E-commerce platforms is the same, the integral '1' is obtained;
when the character information of the customers of the two E-commerce platforms is different, an integral '0' is obtained;
and if the integral is simultaneously provided with the 1, the matching is judged and displayed.
Through the technical scheme, the identification is more convenient.
The invention is further configured to: the character information comprises a network nickname and number characters.
Through the technical scheme, the character information can be one or more of a network nickname and a number character, and can also be other character information.
In conclusion, the invention has the following beneficial effects:
(1) identification of the same merchant across different service platforms;
(2) the recognition accuracy is high;
(3) the dimension of identity recognition can be increased, and the identity recognition rate is improved;
(4) after the recognition task is completed, conditions such as purchasing and behaviors of the same customer on different service platforms are accurately judged, and a good foundation is laid for fine operation and service.
Drawings
FIG. 1 is a schematic flow diagram of image similarity analysis for customers of an e-commerce platform;
FIG. 2 is a schematic flow chart diagram of a specific method for integral identity recognition combined with Hash.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited to these examples.
Example 1
An identity recognition method based on Hash and integral, as shown in FIG. 1 and FIG. 2, includes the following steps:
firstly, using an API provided by a service platform to respectively acquire a network nickname and avatar image information of a client in a Hotan mall and a micro alliance mall;
secondly, calculating an aHash value, a pHash value and a dHash value of the head portrait image information of the client in the Homey mall, and then calculating the aHash value, the pHash value and the dHash value of the head portrait image information of the client in the micro-alliance mall, wherein the aHash is an average Hash algorithm value, the pHash is a perception Hash algorithm value and the dHash is a difference Hash algorithm value;
thirdly, calculating the Hamming distance aHashHamming of the image information aHash value of the client head portrait in the Hotan mall and the micro-union mall, calculating the Hamming distance pHashHamming of the image information pHash value of the client head portrait in the Hotan mall and the micro-union mall, and calculating the Hamming distance dHashHamming of the image information dHash value of the client head portrait in the Hotan mall and the micro-union mall;
fourthly, carrying out weighted calculation on the Hamming distance to obtain weighted Hamming distance Hamming, wherein Hamming is AHashHamming X + pHashHamming Y + dHamhHamming Z;
fifthly, comparing the weighted Hamming distance with a preset threshold value, simultaneously comparing the characters of the network nicknames of the clients in the Hotan mall and the micro alliance mall, confirming the matching when the weighted Hamming distance is smaller than the preset threshold value and the characters are the same; if the weighted Hamming distance Hamming is greater than a set threshold and the characters are the same, confirming that the characters are not matched; confirming that the weighted Hamming distance Hamming is smaller than a set threshold value and the characters are different; and confirming that the weighted Hamming distance Hamming is larger than a set threshold value and the characters are different from each other, and mismatching.
In order to mark the state when the weighted Hamming distance Hamming is smaller than a set threshold value and mark the state when the character information of the network nickname is the same, when the weighted Hamming distance Hamming is smaller than the set threshold value, an integral '1' is obtained; when the weighted Hamming distance Hamming is set to be larger than a set threshold value, an integral '0' is obtained; when the character information of the clients in the favorable mall and the micro-union mall is the same, the point '1' is also obtained; when the character information of the clients of the favorable shopping mall and the micro-union shopping mall is different, the integral '0' is also obtained; and comprehensively comparing, and judging to be matched when the two have the integral of 1 and displaying.
Example 2
An identity recognition method based on Hash and integral, as shown in FIG. 1 and FIG. 2, includes the following steps:
firstly, respectively acquiring a WeChat nickname and avatar image information of a client in a Hotan mall and a WeChat public platform;
secondly, calculating an aHash value, a pHash value and a dHash value of the head portrait image information of the client in the Homex mall, and then calculating the aHash value, the pHash value and the dHash value of the head portrait image information of the client in the WeChat public platform, wherein the aHash is an average Hash algorithm value, the pHash is a perception Hash algorithm value, and the dHash is a difference Hash algorithm value;
thirdly, calculating the Hamming distance aHashHamming of the image information aHash value of the client head portrait in the Hotan mall and the WeChat public platform, calculating the Hamming distance pHashHamming of the image information pHash value of the client head portrait in the Hotan mall and the WeChat public platform, and calculating the Hamming distance dHashHamming of the image information dHash value of the client head portrait in the Hotan mall and the WeChat public platform;
fourthly, carrying out weighted calculation on the Hamming distance to obtain weighted Hamming distance Hamming, wherein Hamming is AHashHamming X + pHashHamming Y + dHamhHamming Z;
fifthly, comparing the weighted Hamming distance with a preset threshold value, simultaneously comparing characters of the WeChat nickname of the client in the Hopkinson public platform and the Geneva public platform, and confirming matching when the weighted Hamming distance is smaller than the preset threshold value and the characters are the same; if the weighted Hamming distance Hamming is greater than a set threshold and the characters are the same, confirming that the characters are not matched; confirming that the weighted Hamming distance Hamming is smaller than a set threshold value and the characters are different; and confirming that the weighted Hamming distance Hamming is larger than a set threshold value and the characters are different from each other, and mismatching.
In order to mark the state when the weighted Hamming distance Hamming is smaller than a set threshold value and mark the state when the character information of the WeChat nickname is the same, when the weighted Hamming distance Hamming is smaller than the set threshold value, an integral '1' is obtained; when the weighted Hamming distance Hamming is set to be larger than a set threshold value, an integral '0' is obtained; when the character information of the customers with the praise shopping mall and the WeChat public platform is the same, the point '1' is also obtained; when the character information of the customers of the praise shopping mall and the WeChat public platform is different, the integral '0' is also obtained; and comprehensively comparing, and judging to be matched when the two have the integral of 1 and displaying.
The WeChat nickname and the network nickname both belong to character information.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (4)
1. An identity recognition method based on Hash and integral is characterized by comprising the following steps:
the method comprises the steps of firstly, respectively obtaining client character information and head portrait image information of two E-commerce platforms;
secondly, calculating an aHash value, a pHash value and a dHash value of the client head portrait image information of the two E-commerce platforms respectively, wherein the aHash is an average Hash algorithm value, the pHash is a perception Hash algorithm value, and the dHash is a difference Hash algorithm value;
thirdly, calculating the Hamming distance aHashHamming of client head portrait image information aHash values of the two E-commerce platforms, calculating the Hamming distance pHashHamming of client head portrait image information pHash values of the two E-commerce platforms, and calculating the Hamming distance dHashHamming of client head portrait image information dHash values of the two E-commerce platforms;
fourthly, carrying out weighted calculation on the Hamming distance to obtain weighted Hamming distance Hamming, wherein Hamming is AHashHamming X + pHashHamming Y + dHamhHamming Z;
fifthly, comparing the weighted Hamming distance with a preset threshold value, simultaneously comparing the character information of the customers of the two E-commerce platforms,
the weighted Hamming distance Hamming is less than the set threshold and the characters are the same, the matching is confirmed,
the weighted Hamming distance Hamming is greater than the set threshold and the characters are the same, confirming the mismatch,
the weighted Hamming distance Hamming is less than the set threshold and the characters are different, the mismatching is confirmed,
and confirming that the weighted Hamming distance Hamming is larger than a set threshold value and the characters are different from each other, and mismatching.
2. An identity recognition method based on Hash integration according to claim 1, wherein: the E-commerce merchant uses the service platform A and the service platform B, and the service platform A and the service platform B are different E-commerce software service platforms.
3. An identity recognition method based on Hash integration according to claim 1, wherein:
when the weighted Hamming distance Hamming is smaller than a set threshold value, obtaining an integral '1';
when the weighted Hamming distance Hamming is larger than a set threshold value, an integral '0' is obtained;
when the character information of the customers of the two E-commerce platforms is the same, the integral '1' is obtained;
when the character information of the customers of the two E-commerce platforms is different, an integral '0' is obtained;
and if the integral is simultaneously provided with the 1, the matching is judged and displayed.
4. An identity recognition method based on Hash integration according to claim 1, wherein: the character information comprises a network nickname and number characters.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010550121.9A CN111767438A (en) | 2020-06-16 | 2020-06-16 | Identity recognition method based on Hash combined integral |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010550121.9A CN111767438A (en) | 2020-06-16 | 2020-06-16 | Identity recognition method based on Hash combined integral |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111767438A true CN111767438A (en) | 2020-10-13 |
Family
ID=72722732
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010550121.9A Pending CN111767438A (en) | 2020-06-16 | 2020-06-16 | Identity recognition method based on Hash combined integral |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111767438A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139401A (en) * | 2021-06-21 | 2021-07-20 | 南京云联数科科技有限公司 | Method for drug recovery, computing device, drug recovery apparatus and medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104317784A (en) * | 2014-09-30 | 2015-01-28 | 苏州大学 | Cross-platform user identification method and cross-platform user identification system |
CN104778388A (en) * | 2015-05-04 | 2015-07-15 | 苏州大学 | Method and system for identifying same user under two different platforms |
US20180068028A1 (en) * | 2016-09-07 | 2018-03-08 | Conduent Business Services, Llc | Methods and systems for identifying same users across multiple social networks |
CN107832783A (en) * | 2017-10-25 | 2018-03-23 | 平安科技(深圳)有限公司 | Across social platform user matching method, data processing equipment and readable storage medium storing program for executing |
CN107944238A (en) * | 2017-11-15 | 2018-04-20 | 中移在线服务有限公司 | Identity identifying method, server and system |
CN108777806A (en) * | 2018-05-30 | 2018-11-09 | 腾讯科技(深圳)有限公司 | A kind of method for identifying ID, device and storage medium |
CN108897789A (en) * | 2018-06-11 | 2018-11-27 | 西南科技大学 | A kind of cross-platform social network user personal identification method |
CN109255777A (en) * | 2018-07-27 | 2019-01-22 | 昆明理工大学 | A kind of image similarity calculation method of combination wavelet transformation and perceptual hash algorithm |
CN110674337A (en) * | 2019-10-15 | 2020-01-10 | 盛唐威讯数媒科技(北京)有限公司 | Audio-video image-text recognition system |
CN110826605A (en) * | 2019-10-24 | 2020-02-21 | 北京明略软件系统有限公司 | Method and device for identifying user in cross-platform manner |
CN111160130A (en) * | 2019-12-12 | 2020-05-15 | 中国电子科技网络信息安全有限公司 | Multi-dimensional collision recognition method for multi-platform virtual identity account |
-
2020
- 2020-06-16 CN CN202010550121.9A patent/CN111767438A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104317784A (en) * | 2014-09-30 | 2015-01-28 | 苏州大学 | Cross-platform user identification method and cross-platform user identification system |
CN104778388A (en) * | 2015-05-04 | 2015-07-15 | 苏州大学 | Method and system for identifying same user under two different platforms |
US20180068028A1 (en) * | 2016-09-07 | 2018-03-08 | Conduent Business Services, Llc | Methods and systems for identifying same users across multiple social networks |
CN107832783A (en) * | 2017-10-25 | 2018-03-23 | 平安科技(深圳)有限公司 | Across social platform user matching method, data processing equipment and readable storage medium storing program for executing |
CN107944238A (en) * | 2017-11-15 | 2018-04-20 | 中移在线服务有限公司 | Identity identifying method, server and system |
CN108777806A (en) * | 2018-05-30 | 2018-11-09 | 腾讯科技(深圳)有限公司 | A kind of method for identifying ID, device and storage medium |
CN108897789A (en) * | 2018-06-11 | 2018-11-27 | 西南科技大学 | A kind of cross-platform social network user personal identification method |
CN109255777A (en) * | 2018-07-27 | 2019-01-22 | 昆明理工大学 | A kind of image similarity calculation method of combination wavelet transformation and perceptual hash algorithm |
CN110674337A (en) * | 2019-10-15 | 2020-01-10 | 盛唐威讯数媒科技(北京)有限公司 | Audio-video image-text recognition system |
CN110826605A (en) * | 2019-10-24 | 2020-02-21 | 北京明略软件系统有限公司 | Method and device for identifying user in cross-platform manner |
CN111160130A (en) * | 2019-12-12 | 2020-05-15 | 中国电子科技网络信息安全有限公司 | Multi-dimensional collision recognition method for multi-platform virtual identity account |
Non-Patent Citations (2)
Title |
---|
东华果汁哥: "【python 以图搜图】三种图片相似度计算融合算法", HTTPS://BLOG.CSDN.NET/U013421629/ARTICLE/DETAILS/87697794, 19 February 2019 (2019-02-19) * |
吴铮;于洪涛;刘树新;朱宇航;: "基于信息熵的跨社交网络用户身份识别方法", 计算机应用, no. 08, 10 August 2017 (2017-08-10) * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139401A (en) * | 2021-06-21 | 2021-07-20 | 南京云联数科科技有限公司 | Method for drug recovery, computing device, drug recovery apparatus and medium |
CN113139401B (en) * | 2021-06-21 | 2021-09-17 | 南京云联数科科技有限公司 | Method for drug recovery, computing device, drug recovery apparatus and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2483104A1 (en) | Robust and invariant audio pattern matching | |
CN111931212B (en) | E-commerce platform based on block chain technology | |
CN113971751A (en) | Training feature extraction model, and method and device for detecting similar images | |
CN105741132A (en) | Two-dimensional code-based online-to-offline sales data processing system and method | |
CN104616389A (en) | Stamp recognition method and device | |
CN106296277A (en) | A kind of consumption rebating management system | |
CN108595448A (en) | Information-pushing method and device | |
CN111767438A (en) | Identity recognition method based on Hash combined integral | |
CN106604281A (en) | Method and equipment for determining stability of mobile phone number | |
CN111736940A (en) | Business interface display method and device for intelligent counter | |
CN111553241A (en) | Method, device and equipment for rejecting mismatching points of palm print and storage medium | |
CN109710890B (en) | Method and system for identifying false material in real time based on constructed behavior portrait model | |
CN109857499B (en) | Universal method for acquiring cash register software screen amount based on windows system | |
CN110610365A (en) | Method and device for identifying transaction request | |
US20200159907A1 (en) | Automatic extraction of information from obfuscated image regions | |
CN110210939B (en) | Information pushing method and device and computer equipment | |
CN108734514B (en) | User normalization method | |
CN112183417A (en) | Business consultant service capability evaluation system and method | |
CN110705994A (en) | Risk user detection method and device | |
CN113516062B (en) | Customer identification method and system for automobile repair shop | |
CN108280766B (en) | Transaction behavior risk identification method and device | |
CN111340592B (en) | Artificial intelligence block chain electronic commerce system and method based on 5G communication | |
CN114677566A (en) | Deep learning model training method, object recognition method and device | |
CN114418380A (en) | User scoring method based on federal learning, server and storage medium | |
CN111815333A (en) | UnionId-based method for identifying identity of same customer on multiple service platforms |
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 |