CN115456711A - Commodity information pushing method and device based on block chain technology and readable medium - Google Patents

Commodity information pushing method and device based on block chain technology and readable medium Download PDF

Info

Publication number
CN115456711A
CN115456711A CN202211068562.0A CN202211068562A CN115456711A CN 115456711 A CN115456711 A CN 115456711A CN 202211068562 A CN202211068562 A CN 202211068562A CN 115456711 A CN115456711 A CN 115456711A
Authority
CN
China
Prior art keywords
commodity
information
digital
product
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211068562.0A
Other languages
Chinese (zh)
Inventor
奚海峰
曹恒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Border Blockchain Technology Co ltd
Original Assignee
Nanjing Border Blockchain Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Border Blockchain Technology Co ltd filed Critical Nanjing Border Blockchain Technology Co ltd
Priority to CN202211068562.0A priority Critical patent/CN115456711A/en
Publication of CN115456711A publication Critical patent/CN115456711A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0631Item recommendations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • Data Mining & Analysis (AREA)
  • Accounting & Taxation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a commodity information pushing method, a device and a readable medium based on a block chain technology, wherein the method comprises the following steps: acquiring a digital commodity to be sold by a seller and corresponding commodity basic information, and determining the product type of the digital commodity; performing feature extraction on the digital commodities according to product types to obtain a predetermined amount of product feature information; adding a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information; making the digital watermark into an on-chain digital watermark NFT by using a block chain technology; acquiring preference characteristic information of a user, and generating recommendation key information for recommending commodities to the user according to the preference characteristic information; deploying a digital commodity matching intelligent contract on a block chain, and searching a digital watermark NFT on the chain according to recommended key information inside the contract to obtain a digital commodity with matched product characteristic information; and pushing commodity information to the user according to the retrieved digital commodities.

Description

Commodity information pushing method and device based on block chain technology and readable medium
Technical Field
The invention belongs to the technical field of commodity recommendation and block chaining, and particularly relates to a commodity information pushing method and device based on a block chaining technology and a readable medium.
Background
With the rapid growth of Web 3.0, commodities have gradually become less restricted to off-line physical commodity transactions, and more on-line digital commodity transactions have gradually come into the consumer's view.
In one aspect, distinct from physical goods are: since digital goods are easily converted, modified, copied and distributed, various digital watermarks are added to the digital goods by many organizations or platforms to ensure the source and the authenticity reliability of the digital goods during transmission.
On the other hand, similar to the physical commodities are: digital goods also need to attract consumers to purchase through some promotion means like physical goods, for example, many promotion methods for traditional physical goods can be combined with the preference of consumers to recommend related goods in a targeted manner.
For the above reasons, it is expected that a large amount of redundant data will inevitably be generated after a large number of transactions of digital goods are performed on each large platform. Therefore, how to reduce these redundant data as much as possible is a problem to be solved without affecting watermarking and popularization and use of digital goods.
Disclosure of Invention
In order to solve the above problems, the present invention provides a commodity information pushing method based on a block chain technology, and adopts the following technical scheme:
the invention provides a commodity information pushing method based on a block chain technology, which is characterized by comprising the following steps of: acquiring a digital commodity to be sold by a seller and corresponding commodity basic information, and determining the product type of the digital commodity; performing feature extraction on the digital commodities according to product types to obtain a predetermined amount of product feature information; adding a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information; making the digital watermark into an on-chain digital watermark NFT by using a block chain technology; acquiring preference characteristic information of a user, and generating recommendation key information for recommending commodities to the user according to the preference characteristic information; deploying a digital commodity matching intelligent contract on a block chain, and searching a digital watermark NFT on the chain according to recommended key information inside the contract to obtain a digital commodity with matched product characteristic information; and pushing commodity information to the user according to the retrieved digital commodities.
The commodity information pushing method provided by the invention can also have the technical characteristics that the commodity basic information at least comprises seller information of the commodity, when the preference characteristic information indicates that the user purchases the digital commodity of the seller, the digital commodity with the similarity of the product characteristic information of the same seller being larger than the preset similarity is recommended to the user as the recommended commodity according to the seller information of the digital commodity, and the commodity information is pushed to the user according to the recommended commodity.
The commodity information pushing method provided by the invention can also have the technical characteristics that the product characteristic information is a plurality of characteristic keywords for describing the content obtained by identifying the content of the digital commodity, and the similarity of the product characteristic information is greater than the preset similarity degree, so that the matching number of the characteristic keywords is greater than the preset threshold value.
The commodity information pushing method provided by the invention can also have the technical characteristics that the recommendation key information comprises a plurality of recommendation keywords which can be matched with the characteristic keywords.
The commodity information pushing method provided by the invention also has the technical characteristics that the basic information at least comprises introduction information of the digital commodity, and commodity information is recommended to a user according to the retrieved digital commodity, and the method further comprises the following steps: and acquiring the digital watermark NFT on the chain of the retrieved digital commodity, generating commodity information according to the digital watermark NFT, and sending the commodity information to the user.
The commodity information pushing method provided by the invention can also have the technical characteristics that the product type is any one of images, videos and audios.
The commodity information pushing method provided by the invention can also have the technical characteristics that the digital commodities are subjected to characteristic extraction according to product types to obtain the product characteristic information with preset quantity, and the method further comprises the following steps of: and determining a corresponding feature extraction model according to the product type, and performing feature extraction on the digital commodity based on the feature extraction model.
The invention also provides a commodity information pushing device, which is characterized by comprising: the product type determining module is used for acquiring the digital commodity to be sold by the seller and corresponding commodity basic information, and determining the product type of the digital commodity; the characteristic extraction module is used for extracting the characteristics of the digital commodities according to the product types to obtain the characteristic information of products with preset quantity; the watermark adding module is used for adding a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information and generating the digital watermark NFT on the block chain; the recommendation information generation module is used for acquiring preference characteristic information of the user and generating recommendation key information for recommending commodities to the user according to the preference characteristic information; the commodity matching module is used for triggering digital commodity matching intelligent contracts deployed on the block chains according to the recommended key information, and searching the digital watermarks NFT on the chains to obtain digital commodities with matched product characteristic information; and the pushing module is used for pushing the commodity information to the user according to the retrieved digital commodity.
The present invention also provides a computer-readable storage medium characterized in that the computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to carry out the method of any one of claims 1 to 7.
Action and effects of the invention
According to the commodity information pushing method, the commodity information pushing device and the storage medium based on the block chain technology, the digital commodity is subjected to feature extraction, the product feature information and the commodity basic information are included when the digital watermark is generated for the digital commodity, and the digital watermark is created on the block chain to form the digital watermark NFT, so that the digital watermark NFT can play a role in traditional authentication and commodity source authentication on one hand, and can also be beneficial to storing the features of the product and the watermark on the other hand, and the subsequent acquisition is facilitated by the advantages of tamper resistance and source tracing of the block chain. Further, when recommended commodities are pushed to the user according to the preference of the user, matching of the recommendation key information generated based on the user and the feature information in the digital watermark NFT of each commodity can be automatically executed directly through a deployed digital commodity matching intelligent contract on the trigger block chain, and then the digital commodities to be recommended are obtained. In this way, not only the push efficiency of the digital commodity is optimized, but also the redundant data which is easy to generate in the process is optimized.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below.
Fig. 1 is a flowchart of a commodity information pushing method in an embodiment of the present invention;
fig. 2 is a block diagram of a commodity information pushing apparatus in the embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure. It should be apparent that the described embodiments are only a few embodiments, and not all embodiments. All other embodiments that can be derived by one of ordinary skill in the art from one or more embodiments of the disclosure without making any creative effort shall fall within the scope of the disclosure.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification. Rather, they are merely examples of systems and methods consistent with aspects of the present description.
The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification, 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.
< example >
Referring to fig. 1, fig. 1 is a flowchart of a method for pushing commodity information according to an embodiment of the present invention. The commodity information pushing method provided by the invention specifically comprises the following steps S1 to S7.
S1, acquiring digital commodities to be sold by a seller and corresponding commodity basic information, and determining the product types of the digital commodities.
In this embodiment, the basic information of the product may include seller information (for example, seller name, source, etc.) of the digital product, and introduction information (for example, specification parameters, product profile, etc.) of the digital product. The product category of the digital commodity may be any one of image, video, and audio.
And S2, performing feature extraction on the digital commodities according to the product types to obtain product feature information of a preset quantity.
In this embodiment, the product feature information is a plurality of feature keywords for describing the content, which are obtained by identifying the content of the digital commodity. Different product types store different feature extraction models in advance, and feature extraction is performed on the digital commodity through the feature extraction models in step S2.
As an embodiment, when the product type is an image, the feature keyword is one or more of an article name, a color name, and a shape name obtained by image recognition of the digital product to be protected, and the feature extraction model is a pre-trained neural network model for image recognition. For example, if a seller wishes to sell a landscape image of landscape and ink containing mountains and waters, the last recognized keyword may be "mountains, waters, and inks", and if the image also contains characters, the recognized characters may be one of the keywords.
As another implementation, the product type may be audio, the keyword is one or more of an audio name and a style name obtained by identifying a digital product to be protected, and the feature extraction model is an audio identification model used for identifying the tone, and the like of the digital commodity to obtain corresponding product feature information.
And S3, adding a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information.
In this embodiment, since the digital watermark is generated based on the product characteristic information and the commodity basic information in step S3, on one hand, it is ensured that the source and reliability of the digital commodity are determined by the digital watermark, and on the other hand, the digital watermark can be read by using the preset program to obtain the characteristic information of the digital commodity, which is convenient for some third-party software to classify and identify the digital commodity based on the characteristic information.
In practical applications, the digital watermark may be generated in step S3 by using an existing watermark generation method, such as hash operation, which is not limited by this embodiment.
And S4, generating a digital watermark NFT on the chain by using a block chain technology, and storing and transmitting the digital watermark on the chain in the form of the NFT.
And S5, acquiring preference characteristic information of the user, and generating recommendation key information for recommending commodities to the user according to the preference characteristic information.
In this embodiment, the preference feature information may be preference information obtained by analyzing a user figure of a user in advance, such as a historical purchased product, age, gender, and the like. The correspondingly generated recommendation key information comprises a plurality of recommendation keywords which can be matched with the feature keywords. For example, the recommended keyword may be "painting, ink", so that matching with the feature keyword "mountain, water, ink" can be completed.
And S6, deploying a digital commodity matching intelligent contract on the block chain, and searching the digital watermark NFT on the chain according to the recommended key information in the contract to obtain the digital commodity with the matched product characteristic information.
And S7, pushing commodity information to the user according to the searched digital commodity.
In this embodiment, because the digital watermark NFT includes the introduction information of the digital commodity, the introduction information generated in step S7 can be directly pushed to the user according to the digital watermark NFT.
In one embodiment, in addition to the pushing of the commodity information based on the user preference introduced in the above step S7, the commodity information may be pushed to the user by:
and when the preference characteristic information indicates that the user purchases the digital commodity of the seller, recommending the digital commodity with the similarity of the product characteristic information of the same seller larger than the preset similarity as a recommended commodity to the user according to the seller information of the digital commodity, and pushing commodity information to the user according to the recommended commodity.
For example, if the feature keywords of the digital commodities purchased by the user are "a, B, C, D", and the feature keywords of the two types of digital commodities under the same seller are "a, B, C, E" and "D, E, F, G", then 3 feature keyword matches can be obtained for the first type of digital commodity through matching, 1 feature keyword matches can be obtained for the second type of digital commodity, and if the predetermined threshold is 2, the first type of digital commodity can be finally recommended to the user.
Correspondingly, the embodiment also provides a commodity information pushing device corresponding to the commodity information pushing method. As shown in fig. 2, the product information pushing apparatus 10 includes a product type determining module 11, a feature extracting module 12, a watermarking module 13, a recommendation information generating module 14, a product matching module 15, and a pushing module 16.
The product type determining module 11 is configured to obtain a digital commodity to be sold by a seller and corresponding commodity basic information, and determine a product type of the digital commodity;
the feature extraction module 12 performs feature extraction on the digital goods according to the product type to obtain a predetermined amount of product feature information.
The watermark adding module 13 adds a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information, and generates a digital watermark NFT on the block chain.
The recommendation information generation module 14 acquires preference feature information of a user, and generates recommendation key information for recommending a commodity to the user according to the preference feature information.
The commodity matching module 15 implements the retrieval of the recommendation key information on the digital watermark NFT on the chain according to a digital commodity matching intelligent contract deployed on the chain to obtain the digital commodity with the matched product feature information.
The pushing module 16 pushes the commodity information to the user according to the retrieved digital commodity.
The product information pushing device 10 provided in the present embodiment has the same implementation principle and the same technical effects as those of the foregoing method embodiments, and for brevity, reference may be made to the corresponding contents in the foregoing method embodiments for the parts that are not mentioned in the apparatus embodiments.
The present embodiment provides a readable storage medium, which stores a program or instructions, and the program or instructions, when executed by a processor, implement the steps of the merchandise information pushing method as described herein.
Effects and effects of the embodiments
According to the commodity information pushing method, device and storage medium based on the block chain technology provided by the embodiment, as the characteristics of the digital commodity are extracted, the product characteristic information and the commodity basic information are included when the digital watermark is generated for the digital commodity, and the digital watermark is created on the block chain to form the digital watermark NFT, on one hand, the digital watermark NFT can play a role in traditional certification and commodity source certification, on the other hand, the characteristics of the product and the watermark can be stored together, and the subsequent acquisition is facilitated by the advantages of tamper resistance and traceability of the block chain. Further, when recommended commodities are pushed to the user according to the preference of the user, matching of the recommended key information generated based on the user and the feature information in the digital watermark NFT of each commodity can be automatically executed directly through a deployed digital commodity matching intelligent contract on the trigger block chain, and then the digital commodities to be recommended are obtained. In this way, not only the push efficiency of the digital commodity is optimized, but also the redundant data which is easy to generate in the process is optimized.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that: those skilled in the art can still make modifications or changes to the embodiments described in the foregoing embodiments, or make equivalent substitutions for some features, within the scope of the disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (9)

1. The commodity information pushing method based on the block chain technology is characterized by comprising the following steps of:
acquiring a digital commodity to be sold by a seller and corresponding commodity basic information, and determining the product type of the digital commodity;
performing feature extraction on the digital commodities according to the product types to obtain a predetermined amount of product feature information;
adding a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information;
generating a digital watermark NFT on a block chain based on the digital watermark;
acquiring preference characteristic information of a user, and generating recommendation key information for recommending commodities to the user according to the preference characteristic information;
deploying a digital commodity matching intelligent contract on a block chain, and searching the digital watermark NFT inside the contract according to the recommended key information to obtain the digital commodity with the matched product characteristic information;
and pushing commodity information to the user according to the retrieved digital commodities.
2. The commodity information pushing method according to claim 1, characterized in that:
wherein the commodity basic information at least comprises seller information of the commodity,
and when the preference characteristic information shows that the user purchases the digital commodity of the seller, recommending the digital commodity with the similarity of the product characteristic information larger than the preset similarity degree under the same seller to the user as a recommended commodity according to the seller information of the digital commodity, and pushing commodity information to the user according to the recommended commodity.
3. The commodity information push method according to claim 2, characterized in that:
wherein the product characteristic information is a plurality of characteristic keywords for describing the content obtained by identifying the content of the digital commodity,
the similarity of the product feature information is greater than the preset similarity, and the matching number of the feature keywords is greater than the preset threshold.
4. The commodity information pushing method according to claim 3, characterized in that:
and the recommendation key information comprises a plurality of recommendation keywords which can be matched with the feature keywords.
5. The merchandise information pushing method according to claim 1,
the basic information includes at least introduction information of the digital goods,
the recommending commodity information to the user according to the retrieved digital commodity further comprises the following steps:
and acquiring the digital watermark NFT of the retrieved digital commodity, generating commodity information according to the digital watermark NFT, and sending the commodity information to the user.
6. The commodity information pushing method according to claim 1, characterized in that:
wherein, the product type is any one of image, video and audio.
7. The merchandise information pushing method according to claim 6, wherein the extracting the features of the digital merchandise according to the product type to obtain a predetermined amount of product feature information further comprises:
and determining a corresponding feature extraction model according to the product type, and performing feature extraction on the digital commodity based on the feature extraction model.
8. An article information pushing apparatus, characterized by comprising:
the product type determining module is used for acquiring the digital commodity to be sold by the seller and corresponding commodity basic information, and determining the product type of the digital commodity;
the characteristic extraction module is used for extracting the characteristics of the digital commodities according to the product types to obtain the characteristic information of products with preset quantity;
the watermark adding module is used for adding a digital watermark to the digital commodity based on the product characteristic information and the commodity basic information and generating a digital watermark NFT on a block chain by the digital watermark;
the recommendation information generation module is used for acquiring preference characteristic information of a user and generating recommendation key information for recommending commodities to the user according to the preference characteristic information;
the commodity matching module is used for triggering a digital commodity matching intelligent contract deployed on a block chain according to the recommended key information, and searching the digital watermark NFT on the chain to obtain the digital commodity with the matched product characteristic information by the contract interior;
and the pushing module is used for pushing commodity information to the user according to the retrieved digital commodities.
9. A computer-readable storage medium having computer-executable instructions stored thereon which, when invoked and executed by a processor, cause the processor to implement the method of any of claims 1 to 7.
CN202211068562.0A 2022-09-02 2022-09-02 Commodity information pushing method and device based on block chain technology and readable medium Pending CN115456711A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211068562.0A CN115456711A (en) 2022-09-02 2022-09-02 Commodity information pushing method and device based on block chain technology and readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211068562.0A CN115456711A (en) 2022-09-02 2022-09-02 Commodity information pushing method and device based on block chain technology and readable medium

Publications (1)

Publication Number Publication Date
CN115456711A true CN115456711A (en) 2022-12-09

Family

ID=84300569

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211068562.0A Pending CN115456711A (en) 2022-09-02 2022-09-02 Commodity information pushing method and device based on block chain technology and readable medium

Country Status (1)

Country Link
CN (1) CN115456711A (en)

Similar Documents

Publication Publication Date Title
CN103329126B (en) Utilize the search of joint image-audio query
US20190065856A1 (en) Machine learning for identification of candidate video insertion object types
CN106126630B (en) A kind of collection of business object, searching method and device
TWI616834B (en) Network product recommendation method and device
CN110378731A (en) Obtain method, apparatus, server and the storage medium of user&#39;s portrait
US11966436B2 (en) Method and system for determining product similarity in digital domains
Liu et al. Adversarial item promotion: Vulnerabilities at the core of top-n recommenders that use images to address cold start
CN109033105A (en) The method and apparatus for obtaining judgement document&#39;s focus
CN110879974A (en) Video classification method and device
CN111159458A (en) Agricultural product image processing and block chain interactive identification method and system
US20230177089A1 (en) Identifying similar content in a multi-item embedding space
CN111125491A (en) Commodity information searching method and device, storage medium and electronic device
TW202117639A (en) Presenting information on similar objects relative to a target object from a plurality of video frames
CN114297509A (en) User interest vector generation method, product recommendation method, device, equipment and medium
Yousaf et al. Patch-CNN: Deep learning for logo detection and brand recognition
US20240054185A1 (en) Image and video instance association for an e-commerce applications
CN115456711A (en) Commodity information pushing method and device based on block chain technology and readable medium
WO2023185908A1 (en) Article attribute recommendation model training and generation methods and apparatuses, and medium
CN104933140B (en) A kind of Media method based on image
CN114282119B (en) Scientific and technological information resource retrieval method and system based on heterogeneous information network
CN112446743A (en) Block chain-based advertisement recommendation method and terminal
CN115620019A (en) Commodity infringement detection method and device, equipment, medium and product thereof
KR101612997B1 (en) System and method for sharing digital content between NFC terminals using context-based search engine
CN110427513A (en) Picture recommendation method and system
Zhan et al. Cross-domain shoe retrieval using a three-level deep feature representation

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