CN113962611A - Processing method and system for commodity evaluation - Google Patents
Processing method and system for commodity evaluation Download PDFInfo
- Publication number
- CN113962611A CN113962611A CN202111412318.7A CN202111412318A CN113962611A CN 113962611 A CN113962611 A CN 113962611A CN 202111412318 A CN202111412318 A CN 202111412318A CN 113962611 A CN113962611 A CN 113962611A
- Authority
- CN
- China
- Prior art keywords
- user
- evaluation
- product
- commodity
- abnormal
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 239
- 238000003672 processing method Methods 0.000 title abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 53
- 238000000034 method Methods 0.000 claims description 52
- 230000006399 behavior Effects 0.000 claims description 36
- 230000015654 memory Effects 0.000 claims description 21
- 230000005856 abnormality Effects 0.000 claims description 8
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 2
- 239000000047 product Substances 0.000 description 51
- 238000004891 communication Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005429 filling process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000013065 commercial product Substances 0.000 description 1
- 235000014510 cooky Nutrition 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Computer Security & Cryptography (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本公开公开了一种针对商品评价的处理方法及系统。其中，针对商品评价的处理系统包括：可信度确定单元，适于从针对商品的历史评价中，确定出可信的商品评价；用户权重值确定单元，适于对于可信的商品评价，确定用户权重值，其中用户的权重值与用户拥有商品的时长相关；评分计算单元，适于基于各用户的用户权重值与对应的分值，确定出商品的总分值；并基于各用户的用户权重值与对应的商品评价的数量，确定出商品评价数；以及，基于总分值和商品评价数，确定出商品的评分。
The present disclosure discloses a processing method and system for commodity evaluation. The processing system for commodity evaluation includes: a reliability determination unit, adapted to determine credible commodity evaluations from historical evaluations of commodities; a user weight value determination unit, adapted to determine credible commodity evaluations User weight value, where the weight value of the user is related to the length of time that the user owns the product; the scoring calculation unit is suitable for determining the total score value of the product based on the user weight value of each user and the corresponding score value; The weight value and the corresponding number of product evaluations determine the number of product evaluations; and, based on the total score value and the number of product evaluations, determine the score of the product.
Description
Technical Field
The present disclosure relates to the field of computer network technologies, and in particular, to a processing scheme for commodity evaluation.
Background
On a merchandise sales platform, a public praise of a merchandise is often established through merchandise evaluation published by a user after purchasing the merchandise. The commodity evaluation has become a tool for other users to select commodities and manufacturers to pay attention to their products. Therefore, calculating a score for a product by historical product evaluation is an important function of product evaluation as an index for evaluating the product.
Taking an automobile sales platform as an example, the automobile series public praise scoring algorithm is used for calculating the existing automobile series public praise scoring data published by public praise users, and quantitatively evaluating the automobile series, so that the evaluation, the examination and the management of the automobile series are realized. Finally, the user is helped and guided to make the assessment and shopping of the train by directly showing the scores on the page or ranking and rating the train according to the scores.
The currently common commodity scoring algorithm is to add the scores of each commodity evaluation to calculate the average value, and calculate the average score of the commodity as the final score. For example, the scores of all the product evaluations for a certain train are added to the average value to obtain the score of the train. The algorithm is simple, the difference among commodity evaluations is not considered, and the obtained scores are not comprehensive and accurate enough. In addition, the commodity evaluation has the phenomenon of 'water army' score brushing, so that the credibility of the commodity evaluation can be influenced. The above scheme does not take these situations into account.
Therefore, an effective solution for evaluating commodities is needed to solve the above problems.
Disclosure of Invention
The present disclosure provides a processing method and system for merchandise evaluation in an effort to solve or at least alleviate at least one of the problems identified above.
According to one aspect of the present disclosure, there is provided a method for determining the credibility of a commodity evaluation, wherein the commodity evaluation is an evaluation published by a user for at least one dimension of a commodity purchased by the user, and the commodity evaluation at least comprises characters and images, and the method comprises the following steps: calculating fingerprints of characters in the commodity evaluation, and judging whether all the characters of the commodity evaluation are abnormal or not based on the fingerprints; if all the characters of the commodity evaluation are confirmed to be abnormal, calculating an index value aiming at the commodity evaluation of each dimension, and judging whether part of the characters of the commodity evaluation are abnormal or not based on the index value; if the fact that part of characters of the commodity evaluation are not abnormal is confirmed, calculating a hash value of an image in the commodity evaluation, and judging whether the image of the commodity evaluation is abnormal or not based on the hash value of the image; if the image of the commodity evaluation is confirmed to be abnormal, judging whether the behavior of the user is abnormal at least based on the user account when the user issues the commodity evaluation; and if the user behavior is confirmed to be not abnormal, confirming that the commodity evaluation is credible.
According to another aspect of the present disclosure, there is provided a method of evaluating a commodity based on historical evaluation, comprising the steps of: determining a credible commodity evaluation from historical evaluations aiming at the commodity, wherein the commodity evaluation at least comprises a score; for credible commodity evaluation, determining a user weight value, wherein the user weight value is related to the time length of the commodity owned by the user; determining a total score of the commodity based on the user weight values and corresponding scores of the users; determining the commodity evaluation number based on the user weight value of each user and the corresponding commodity evaluation number; and determining the score of the commodity based on the total score and the commodity score number.
According to still another aspect of the present disclosure, there is provided a processing system for merchandise evaluation, including: a credibility determination unit adapted to determine a credible commodity evaluation from the historical evaluations for the commodity; the user weight value determining unit is suitable for determining a user weight value for credible commodity evaluation, wherein the user weight value is related to the time length of the commodity owned by the user; the score calculating unit is suitable for determining the total score of the commodity based on the user weight value and the corresponding score of each user; determining the commodity evaluation number based on the user weight value of each user and the corresponding commodity evaluation number; and determining the score of the commodity based on the total score and the commodity score number.
According to yet another aspect of the present disclosure, there is provided a computing device comprising: one or more processor memories; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods above.
According to yet another aspect of the disclosure, there is provided a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods described above.
In summary, according to the scheme of the present disclosure, a credible commodity evaluation is determined through analysis of commodity evaluation content and analysis of user behavior. Specifically, when the content of the product evaluation is analyzed, whether or not there is abnormal content (i.e., plagiarism content) is detected from 3 perspectives of all characters, characters of each part, images, and the like in the product evaluation. When the commodity evaluation includes the plagiarism content (whether the whole plagiarism, the partial plagiarism or the image plagiarism), the commodity evaluation is considered to be invalid, i.e., the commodity evaluation is not credible. When the user behavior is analyzed, on one hand, whether the user behavior is abnormal or not is judged by comparing a user equipment identifier generated when the user accesses and a user account generated when the user logs in; on the other hand, whether the user behavior is abnormal or not is judged by comparing the corresponding attribution areas of the user during the behaviors of registration, login, publication and the like. When the user behavior is abnormal, the commodity evaluation correspondingly published by the user is considered to be not credible.
In addition, the influence of the product evaluation number corresponding to each category of the product on the product score is also considered, and the evaluation number is used as a weight to participate in the score calculation of the product.
Drawings
To the accomplishment of the foregoing and related ends, certain illustrative aspects are described herein in connection with the following description and the annexed drawings, which are indicative of various ways in which the principles disclosed herein may be practiced, and all aspects and equivalents thereof are intended to be within the scope of the claimed subject matter. The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description read in conjunction with the accompanying drawings. Throughout this disclosure, like reference numerals generally refer to like parts or elements.
FIG. 1 illustrates a schematic diagram of a processing system 100 for merchandise evaluation according to some embodiments of the present disclosure;
FIG. 2 illustrates a schematic diagram of a computing device 200, according to some embodiments of the present disclosure;
FIG. 3 illustrates a flow diagram of a method 300 of determining the trustworthiness of an evaluation of a good in accordance with some embodiments of the present disclosure; and
FIG. 4 illustrates a flow diagram of a method 400 of evaluating a good based on historical ratings according to some embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
FIG. 1 illustrates a schematic diagram of a processing system 100 for merchandise evaluation according to some embodiments of the present disclosure.
As introduced above, on a merchandise sales platform, a user can evaluate purchased merchandise, with the dimensions of evaluation including the packaging, appearance, performance, cost/performance, etc. of the merchandise. In one embodiment, the merchandise evaluation published by the user at least comprises characters, images and scores, and of course, videos, motion pictures and the like can be provided. The user may also post more than one item rating for one item he or she has purchased. This disclosure is not to be unduly limited thereby.
As shown in fig. 1, a processing system 100 for merchandise evaluation includes: a credibility determination unit 110, a user weight value determination unit 120, and a score calculation unit 130.
The credibility determination unit 110 determines a credible commodity evaluation from the historical evaluations for the commodities. Considering that there may be a situation of water force credit in the commodity evaluation, the credibility determining unit 110 assists to manually check the authenticity of the commodity evaluation content based on a computer artificial intelligence algorithm to select a credible commodity evaluation as an effective commodity evaluation.
In one embodiment, whether the merchandise evaluation is credible is judged from the following aspects:
(1) whether the content of commodity evaluation is abnormal or not;
(2) the user who submits the commodity evaluation whether the abnormal behavior exists;
according to one embodiment, when the content (such as characters and images) of the commodity evaluation has plagiarism, the content of the commodity evaluation is considered to be abnormal. When a user has multiple user accounts at the same time in a period of time, or when a user switches different user accounts on a device, the user is determined to have abnormal behaviors.
Further, if there is no abnormality in the content of the commodity evaluation and no abnormality in the user behavior, the commodity evaluation is determined to be a credible commodity evaluation. A subsequent step of calculating a score may be involved.
For a credible commodity evaluation, the user weight value of the user who issued the commodity evaluation is determined by the user weight value determination unit 120. In one embodiment, the weight value of the user is related to the duration of time the user owns the item.
The score calculating unit 130 is used to calculate the score of the goods. Specifically, the total score of the commodity is determined based on the user weight value of each user and the score in the commodity evaluation corresponding to the user weight value. Meanwhile, the commodity evaluation number is determined based on the user weight value of each user and the corresponding commodity evaluation number. Then, based on the total score and the number of evaluations of the item, the score of the item is determined.
The system 100 may be disposed on a computing device through which the processing of the merchandise's evaluations is accomplished. A detailed description will be given below regarding a specific execution flow of each unit in the system 100.
Fig. 2 is a block diagram of an exemplary computing device 200.
As shown in FIG. 2, in a basic configuration 202, a computing device 200 typically includes a system memory 206 and one or more processors 204. A memory bus 208 may be used for communication between the processor 204 and the system memory 206.
Depending on the desired configuration, the processor 204 may be any type of processing, including but not limited to: a microprocessor (μ P), a microcontroller (μ C), a Digital Signal Processor (DSP), or any combination thereof. The processor 204 may include one or more levels of cache, such as a level one cache 210 and a level two cache 212, a processor core 214, and registers 216. Example processor cores 214 may include Arithmetic Logic Units (ALUs), Floating Point Units (FPUs), digital signal processing cores (DSP cores), or any combination thereof. The example memory controller 218 may be used with the processor 204, or in some implementations the memory controller 218 may be an internal part of the processor 204.
Depending on the desired configuration, system memory 206 may be any type of memory, including but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. The physical memory in the computing device is usually referred to as a volatile memory RAM, and data in the disk needs to be loaded into the physical memory to be read by the processor 204. System memory 206 may include an operating system 220, one or more applications 222, and program data 224. In some implementations, the application 222 can be arranged to execute instructions on the operating system with the program data 224 by the one or more processors 204. Operating system 220 may be, for example, Linux, Windows, or the like, which includes program instructions for handling basic system services and for performing hardware-dependent tasks. The application 222 includes program instructions for implementing various user-desired functions, and the application 222 may be, for example, but not limited to, a browser, instant messenger, a software development tool (e.g., an integrated development environment IDE, a compiler, etc.), and the like. When the application 222 is installed into the computing device 200, a driver module may be added to the operating system 220.
When the computing device 200 is started, the processor 204 reads program instructions of the operating system 220 from the memory 206 and executes them. Applications 222 run on top of operating system 220, utilizing the interface provided by operating system 220 and the underlying hardware to implement various user-desired functions. When the user starts the application 222, the application 222 is loaded into the memory 206, and the processor 204 reads the program instructions of the application 222 from the memory 206 and executes the program instructions.
Computing device 200 also includes storage 232, storage 232 including removable storage 236 and non-removable storage 238, each of removable storage 236 and non-removable storage 238 being connected to storage interface bus 234.
Computing device 200 may also include an interface bus 240 that facilitates communication from various interface devices (e.g., output devices 242, peripheral interfaces 244, and communication devices 246) to the basic configuration 202 via the bus/interface controller 230. The example output device 242 includes a graphics processing unit 248 and an audio processing unit 250. They may be configured to facilitate communication with various external devices, such as a display 253 or speakers, via one or more a/V ports 252. Example peripheral interfaces 244 can include a serial interface controller 254 and a parallel interface controller 256, which can be configured to facilitate communications with external devices such as input devices (e.g., keyboard, mouse, pen, voice input device, touch input device) or other peripherals (e.g., printer, scanner, etc.) via one or more I/O ports 258. An example communication device 246 may include a network controller 260, which may be arranged to facilitate communications with one or more other computing devices 262 over a network communication link via one or more communication ports 264.
A network communication link may be one example of a communication medium. Communication media may typically be embodied by computer readable instructions, data structures, program modules, and may include any information delivery media, such as carrier waves or other transport mechanisms, in a modulated data signal. A "modulated data signal" may be a signal that has one or more of its data set or its changes made in such a manner as to encode information in the signal. By way of non-limiting example, communication media may include wired media such as a wired network or private-wired network, and various wireless media such as acoustic, Radio Frequency (RF), microwave, Infrared (IR), or other wireless media. The term computer readable media as used herein may include both storage media and communication media.
The computing device 200 also includes a storage interface bus 234 coupled to the bus/interface controller 230. The storage interface bus 234 is coupled to the storage device 232, and the storage device 232 is adapted for data storage. The example storage device 232 may include removable storage 236 (e.g., CD, DVD, U-disk, removable hard disk, etc.) and non-removable storage 238 (e.g., hard disk drive, HDD, etc.).
In the computing device 200 according to the present disclosure, the application 222 includes instructions for executing the processing method for merchandise evaluation of the present disclosure. More specifically, instructions are included for performing the method 300 for determining an assessment credibility of a good, and/or the method 400 for assessing a good based on historical assessments. The instructions may instruct the processor 204 to perform the methods of the present disclosure.
For convenience of description, the following describes the process of the computing device 200 performing the above method in conjunction with the system 100 by taking a commercial product as an example.
As previously described, a good rating is a rating published by a user for at least one dimension of the good he or she purchases. According to the embodiment of the disclosure, a user issues commodity evaluations for 8 dimensions of an automobile, specifically: space, power, control, oil consumption, travelling comfort, outward appearance, interior trim, price/performance ratio. And the user gives the evaluation of characters, images and scores for each dimension. Of course, the user may also give a text and/or image rating for each dimension and give a total score rating. The present disclosure is not so limited.
FIG. 3 illustrates a flow diagram of a method 300 of determining the trustworthiness of an item rating in accordance with some embodiments of the present disclosure. As shown in fig. 3, the method 300 begins at step S310.
In step S310, a determination is made based on the entire text of the product evaluation. It can be performed in two steps.
First, in step S312, fingerprints of all characters in the product evaluation are calculated.
According to one embodiment, the words in the merchandise evaluation are hashed to extract the fingerprint of the merchandise evaluation.
Thereafter, in step S314, it is determined whether or not all the character contents of the product evaluation are abnormal based on the fingerprint.
According to one embodiment, the similarity calculation is performed on the extracted fingerprint and the pre-stored article fingerprint respectively to generate a similarity value of the commodity evaluation. If the similarity value is greater than the threshold value, all characters of the commodity evaluation can be determined to be abnormal (namely, the character content is plagiarism). Otherwise, determining that the whole character in the commodity evaluation is not abnormal.
In one embodiment according to the present disclosure, all textual content in the merchandise rating is extracted as one text. And performing SimHash calculation on the text to obtain a SimHash value as a fingerprint of the commodity evaluation. The SimHash value is then stored in the MySql data sheet and in the Faiss (facebook AI Similarity search). The hamming distance (in the information coding, the number of coded different bits on the corresponding bits of two legal codes is called code distance, also called hamming distance) is calculated through the SimHash value of the article stored in the Faiss (namely the pre-stored article fingerprint), and the similarity and the duplication of the text can be judged. The higher the similarity value, the greater the likelihood that the text is considered to be plagiarism.
Alternatively, the pre-stored articles may be text in the merchandise's evaluation from within or outside the sales platform, without limitation.
Considering that in the plagiarism evaluation, the whole plagiarism may not be, but different dimensionality contents are selected from different 8 or several commodity evaluations respectively for plagiarism, and one commodity evaluation is obtained through 'east spelling and western hashing'. For example, "spatial" dimensional content is copied from the commercial offer a, "kinetic" dimensional content is copied from the commercial offer B, "appearance" dimensional content is copied from the commercial offer C, and "fuel consumption" dimensional content is copied from the commercial offer D.
Therefore, if it is confirmed that the entire text of the product evaluation is not abnormal, it is necessary to perform determination based on the text of each dimension in the product evaluation in step S320. The same is performed in two steps.
In step S322, an index value is calculated for each product evaluation of each dimension. Specifically, hash index values of characters in the commodity evaluation of each dimension are calculated.
In step S324, it is determined whether or not a part of the characters evaluated for the product is abnormal based on each index value. Specifically, for the hash index value of each dimension, it is detected whether or not there is a hash index value that coincides with the calculated hash index value of the corresponding dimension from among the pre-stored hash index values. If yes, determining that part of characters evaluated by the commodity are abnormal. Otherwise, the part of characters evaluated by the commodity is determined to be not abnormal.
According to an embodiment of the disclosure, when the commodity evaluation data is stored, a plurality of fields are designed corresponding to each dimension, for example, 8 fields are set corresponding to 8 dimensions of automobile evaluation, so as to respectively store the data of the 8 dimensions. Then, adding a field for each dimension field for storing the Hash index value of the corresponding dimension content. The Hash index can be generated by using the CHECKSUM function in SQL Server, and the disclosure can be generated by using the crc64 function or the crc32 function in MySql database without limitation. And then, commodity evaluations with the same dimensionality content can be quickly found out through the Hash index values, so that the plagiarized commodity evaluation can be accurately identified.
Considering that when the crc64 and the cheksum function generate Hash index values, any character is different, and the generated Hash index results are different, if it is detected that the contents of a dimension are the same, the contents of the dimension can be determined to be plagiarism by 100%. Since it is not possible for the user to write a punctuation mark poorly if he or she writes it by himself. Thus, in some embodiments, the item rating is determined to be anomalous as long as there is a consistent hash index value for any dimension of the hash index value. Of course, for the sake of safety, in other embodiments, the setting condition is also relaxed, and if the hash index values of 2 dimensions and more have the same hash index value, it is considered to be plagiarism, and then it is determined that the commodity evaluation is abnormal.
If it is confirmed that there is no abnormality in part of the characters of the product evaluation, in the subsequent step S330, a determination is made based on the image under product evaluation. It is performed in two steps.
In step S332, a hash value of the image under evaluation of the product is calculated. In one embodiment, the unique hash value of the image may be generated by any of the 3 checking algorithms CRC (32/64), MD5, SHA 1.
In step S334, it is determined whether or not the image evaluated for the product is abnormal based on the hash value of the image.
According to one embodiment, a hash value is generated for an image in the evaluation of a good from within or outside the sales platform and stored in a data table as a pre-stored hash value. In this way, for the commodity evaluation newly issued by the user, the hash value of the image in the commodity evaluation is calculated and compared with the prestored hash value, and if the same hash value exists, the image in the commodity evaluation is determined to be abnormal.
According to the embodiment of the disclosure, more than one image may exist in one commodity evaluation, and the hash value may be calculated for each image and compared with the pre-stored hash value. If the same hash value is compared, the image in the commodity evaluation is considered to be abnormal. On the contrary, if the hash values are not the same, it is determined that there is no abnormality in the image under the commodity evaluation.
If it is confirmed that the image of the product evaluation is not abnormal, in the subsequent step S340, it is determined whether the behavior of the user is abnormal based on at least the user account when the user issued the product evaluation.
According to one embodiment, a user device identification is obtained in response to an access operation by a user. When a user issues commodity evaluation, the user needs to log in, a user account of the user is obtained, and the user equipment identification is associated with the user account. And when the user equipment identification corresponds to more than one user account, confirming that the behavior of the user is abnormal. Otherwise, if the user equipment identifier only corresponds to one user account, it is determined that the user behavior is not abnormal.
Wherein the user equipment identity comprises: at least one of a session identification, an International Mobile Equipment Identity (IMEI).
Taking the PC side and the M side as an example, when a user opens a web page of the platform for the first time, the js code of the page asynchronously requests the server interface to generate a unique sessionId (session identifier) for the web page, and the sessionId is stored in a cookie of the browser. The session identity will not change as long as the user is using the same browser of the same device. Generally, a "water force" has a plurality of user accounts, and identity switching and identity hiding are realized by switching different accounts. Then, if the user issues multiple merchandise evaluations by switching the user account, it can be found that the user corresponds to more than one user account by using the sessionId. Usually, the computer and the mobile device are private and cannot be shared by a plurality of people, so that the abnormal behavior of the user can be confirmed, and the evaluation of the commodity is further judged to be unreliable.
In some embodiments, to prevent extreme situations where the user does have a situation such as reselling a used computer, a determination of publication time is added when a different user is determined to publish an item evaluation under sessionId. That is, when the ue identifier corresponds to more than one user account, if the ue identifier corresponds to more than one user account within a predetermined time period (typically 60 days), it is determined that the behavior of the user is abnormal.
Taking APP as an example, IMEI is used to identify mobile communication devices such as each independent mobile phone in a mobile phone network, and is equivalent to an identity card of a mobile phone. The IMEI is unique to each mobile device. Mobile devices (such as cell phones) are also private and cannot be shared with multiple people. Referring to the description about the session identifier, the water force is on the same device, and the user account is switched to issue multiple commodity comments, so that the behavior abnormality of the user can be accurately identified and confirmed, and further the evaluation of the commodity is determined to be unreliable.
According to another embodiment, a first area to which an IP address belongs when a user registers a user account, a second area to which the IP address belongs when the user issues commodity evaluation, and a third area to which the user account belongs are obtained; and judging whether the first area, the second area and the third area are consistent. If the three are consistent, the user behavior is confirmed to be abnormal. Otherwise, if the three are not consistent, the user behavior is determined to be abnormal.
The third area to which the user account belongs can be determined by the attribution of the mobile phone number bound to the user account. Further, the first region, the second region, and the third region may be accurate to province.
Particularly, if the first area, the second area and the third area are not consistent, the user account is determined as a high-risk account, and the behavior of the user is further analyzed. According to one embodiment, user behavior is analyzed from the following aspects: the frequency of recent (e.g., within 30 days) access to the platform and APP, the separation between the time the item rating was published and the time the user account was registered, the length of time it took to fill in the item rating, and the number of stickings during the filling process, etc., are not limited to these. If the access frequency of the user is 0 within 30 days, and/or the number of days between the registration time and the publication time is very small (such as 1-5 days), and/or the duration for filling the commodity evaluation is very short (such as 1 minute), and/or the number of pasting times in the filling process is too large (such as 10 times), the user behavior abnormality can be confirmed.
If it is confirmed that there is no abnormality in the behavior of the user, in the subsequent step S350, it is confirmed that the product evaluation is authentic. And otherwise, if the user behavior is confirmed to be abnormal, confirming that the commodity evaluation is not credible.
It should be noted that the present disclosure does not limit the execution order of the above steps. In other words, based on the description of the present disclosure, when determining whether the product evaluation is authentic, the execution order of step S310, step S320, step S330 and step S340 may be changed arbitrarily, and is not listed here.
Of course, when determining whether the product evaluation is authentic, according to the embodiment of the present disclosure, it may be determined whether the product corresponding to the product evaluation is a product on sale. In some scenarios, the same item may have multiple models, and some of the models may have been sold off. Taking an automobile as an example, the problem of the vehicle type of the stop sale may already be solved in the newly produced vehicle type, and if the vehicle type of the stop sale participates in the calculation, the solution and the improvement of the newly produced vehicle type to the problem cannot be reflected.
According to the method 300 of the present disclosure, a trusted commodity rating is determined through analysis of the contents of the commodity rating and analysis of the user's behavior. Specifically, when the content of the product evaluation is analyzed, whether or not there is abnormal content (i.e., plagiarism content) is detected from 3 perspectives of all characters, characters of each part, images, and the like in the product evaluation. When the commodity evaluation includes the plagiarism content (whether the whole plagiarism, the partial plagiarism or the image plagiarism), the commodity evaluation is considered to be invalid, i.e., the commodity evaluation is not credible. When the user behavior is analyzed, on one hand, whether the user behavior is abnormal or not is judged by comparing a user equipment identifier generated when the user accesses and a user account generated when the user logs in; on the other hand, whether the user behavior is abnormal or not is judged by comparing the corresponding attribution areas of the user during the behaviors of registration, login, publication and the like. When the user behavior is abnormal, the commodity evaluation correspondingly published by the user is considered to be not credible.
FIG. 4 illustrates a flow diagram of a method 400 of evaluating a good based on historical ratings according to some embodiments of the present disclosure. As shown in fig. 4, the method 400 begins at step S410.
In step S410, a credible commodity evaluation is determined from the historical evaluations for commodities.
According to one embodiment, the credibility of the commodity evaluation is judged through processing characters and images in the commodity evaluation and analyzing user behaviors for issuing the commodity evaluation. This may be accomplished by performing the method 300 described previously. And will not be described in detail herein.
According to another embodiment, if the publisher of the merchandise evaluation is an authenticated user, such as an authenticated owner (the authenticated owner can determine by examining and verifying information related to vehicle data, such as vehicle purchase invoice, group photo, driving license, etc.), the merchandise evaluation is deemed to be highly authentic. The present disclosure is not so limited.
Subsequently, in step S420, for the credible commodity evaluation, a user weight value is determined, wherein the user weight value is related to the time period for which the user owns the commodity.
According to one embodiment, the length of time from the time the user purchased the item to the time the user published the item rating for the item is determined as the length of time the user owns the item. Generally, the evaluation of a commodity by a user varies with the length of time the user has the commodity. Therefore, different user weight values are set for different durations of time of owning the goods. Typically, the time at which the user purchased the item is filled in when the user published the item rating.
Taking an automobile as an example, the time for a user to own the automobile is referred to as the automobile congestion time. The applicant finds in research that users within 1 month of a car holding period are generally not familiar with and understand new cars enough, so the credibility of the user group is relatively low, and in addition, the vehicles are still in a break-in period, and parts are easy to fail in the break-in period, such as the faults of the parts, such as jamming, heating, infiltration and the like, and the oil consumption is high, so the user weight value in the period needs to be reduced. In the congestion period of 4-10 months, the user is familiar with the vehicle and the vehicle passes the break-in period, so that the weight value of the user is the highest value of 1. When the vehicle congestion period reaches 25 months or more, the quality guarantee period of a plurality of parts of the vehicle usually passes or the service life of the parts of the vehicle is close to, faults are increased, and users may emotionally score the vehicle low, so that the user credibility in the time period is relatively low, and the user weight value in the time period is reduced.
According to one embodiment of the present disclosure, the user weight values used are shown in the following table.
TABLE 1 user weight values corresponding to different congestion periods
| Congestion period (moon) | Corresponding number of days | User weight value |
| Within 1 month | <30 days after | 0.5 |
| 2-3 months | 31-60 days | 0.8 |
| 4-10 months | 61-300 days | 1 |
| 11-12 months | 301-365 days | 0.9 |
| 13-24 months | 366- | 0.8 |
| 25 months and above | >＝731 | 0.6 |
In subsequent steps S430 to S450, a score of the item is determined based on the credible item evaluation. In one embodiment, the commodity evaluation comprises a point value given to the commodity by the user. If the user gives scores for 8 dimensions of the vehicle, the average score of the 8 dimensions can be calculated as the score of the commodity evaluation. The following steps S430 to S450 may be performed for the score of each dimension, and the score in the dimension is calculated; and taking the average value (or weighted average value) of the scores under all dimensions as the score of the commodity. The present disclosure is not so limited.
In step S430, a total score of the product is determined based on the user weight value and the corresponding score of each user.
The total score S can be represented by the following formula:
in the formula, wiRepresenting the user weight value, s, of the ith useriThe score given by the ith user is shown, and m shows the total number of users corresponding to the credible commodity evaluation aiming at the commodity.
Subsequently, in step S440, the number of product evaluations is determined based on the user weight value of each user and the number of corresponding product evaluations.
That is, according to the embodiment of the present disclosure, when counting the number of product evaluations of a certain product, all the product evaluations are not directly added
The commodity evaluation number N can be represented by the following formula:
in the formula, wiRepresents the user weight value, n, of the ith useriThe number of credible commodity evaluations issued by the ith user for the commodity is usually 1, and m represents the total number of users corresponding to the credible commodity evaluations for the commodity.
Subsequently, in step S450, a score of the item is determined based on the total score and the number of evaluations for the item.
In one embodiment, the total score, S, is divided by the number of evaluations, N, for the item to obtain a score for the item.
To further illustrate the process of calculating a score of the present disclosure, an example of the calculation is given below.
For a certain vehicle type, the scores for the appearance dimensions of 7 credible commodity evaluations are obtained after the processing of step S410. Respectively from 7 users. Table 2 shows the user's car-holding period, the number of evaluation items of the goods, and the corresponding scores.
TABLE 2
| Congestion period (sky) | Number of evaluation items | Score the points |
| 15 | 1 | 5 |
| 32 | 1 | 4 |
| 100 | 1 | 4 |
| 190 | 1 | 3 |
| 400 | 1 | 4 |
| 1500 | 1 | 3 |
| 2000 | 1 | 5 |
According to the method 400 of the present disclosure, the data in table 2 is processed as follows:
TABLE 3
Grading of appearance of the vehicle:
total score:
S＝(5*0.50)+(4*0.80)+(4*1.00)+(3*1.00)+(4*0.80)+(3*0.60)+(5*0.60)＝20.7，
evaluation number of commercial products:
N＝(1*0.50)+(1*0.80)+(1*1.00)+(1*1.00)+(1*0.80)+(1*0.60)+(1*0.60))＝5.3，
the score is 3.906.
If the method of directly taking the mean value is adopted, the score is as follows: (5+4+4+3+4+3+5)/7 ═ 4.0.
According to the method 400, the influence of the commodity evaluation on the time length of the commodity owned by the user is considered, and more specifically, the weight and the influence of the objective conditions of the user in the vehicle break-in period, the quality guarantee period and the like in the vehicle system score are reflected by setting different user weight values for different vehicle holding periods, so that the interference of the influences on the commodity evaluation is well solved.
In some embodiments, if the product includes at least two categories, the ratio of the number of product evaluations corresponding to the product of each category to the total number of product evaluations of the product is counted. Then, based on the commodity evaluation of each category of commodities, calculating the score of each category by executing the steps; and determining the final score of the commodity based on the scores and the proportions of the categories.
Also, taking an automobile as an example, the vehicle system is classified into a plurality of vehicle types, and the commodity evaluation is attributed to a specific vehicle type. At this time, for each vehicle type, the above-described steps S420 to S450 are performed, and the score of each vehicle type is determined. On the basis, the proportion of each vehicle type to all credible commodity evaluation quantities under the vehicle series is calculated according to the commodity evaluation quantities of each vehicle type, and finally the score of the vehicle series is obtained.
For example, there are 2 models below the maiden train, which are fashion type and lead type, respectively, and after the above steps are performed, a score of the fashion type is calculated to be 4.5, and a score of the lead type is calculated to be 5. Meanwhile, the number of credible commodities evaluated against fashion type is counted to be 99, and the number of credible commodities evaluated against lead type is counted to be 1. Then, the fashion type ratio is 99/100-0.99, and the top type ratio is 1/100-0.01.
Taking the proportion of each vehicle type as the weight, and calculating to obtain the score of the Meiteng train as follows:
4.5×0.99+5×0.01＝4.505。
that is, the larger the number of commodity evaluations corresponding to a vehicle type is, the higher the contribution ratio of the commodity evaluations to the final score of the belonging vehicle series is.
According to the method 400 of the present disclosure, the influence of the product evaluation number corresponding to each category of the product on the product score is also considered, and the evaluation is taken as a weight to participate in the product score.
According to the scheme of the disclosure, a series of processes are performed on the commodity evaluation, invalid commodity evaluation (i.e., untrusted commodity evaluation) is deleted, and only authentic commodity evaluation is used to participate in the calculation of the commodity score. In addition, when the grade of the commodity is calculated, factors such as the time length of the commodity owned by the user and different commodity evaluation numbers corresponding to different types of commodities are considered, the influence on the grade of the commodity is obtained, and a more accurate and comprehensive grade of the commodity is obtained so as to help and guide the user to evaluate and select the commodity.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the disclosure, various features of the disclosure are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various disclosed aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the claimed disclosure requires more features than are expressly recited in each claim. Rather, as the following claims reflect, disclosed aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this disclosure.
Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in a device as described in this embodiment or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into multiple sub-modules.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
The present disclosure also discloses:
a7 the method of a1, wherein the step of calculating an index value for each dimension of the product evaluation and determining whether or not a character of the product evaluation is abnormal based on the index value includes: respectively calculating hash index values of characters in commodity evaluation of each dimension; aiming at the hash index value of each dimension, detecting whether a hash index value consistent with the calculated hash index value of the corresponding dimension exists in the prestored hash index values; and if so, determining that the character of the commodity evaluation is abnormal.
B9, the method according to B8, wherein the commodity evaluation further comprises characters and images, and the step of screening out credible commodity evaluation from historical evaluation for commodities comprises: and judging whether the commodity evaluation is credible or not through processing characters and images in the commodity evaluation and analyzing the user behavior which issues the commodity evaluation.
B10, the method of B8 or 9, wherein the step of screening the historical valuations for the good for confidence comprises: by performing the method as described above, a trustworthy merchandise rating is determined.
B11, the method of any one of B8-10, further comprising the steps of: determining a length of time from a time when a user purchases the commodity to a time when a commodity evaluation for the commodity is issued as a time period for which the user owns the commodity; and setting different user weight values for different commodity owned durations.
B12, the method as set forth in B8, further comprising the steps of: if the commodity comprises at least two categories, respectively counting the proportion of the number of commodity evaluations corresponding to the commodities of each category to the total number of commodity evaluations of the commodity; calculating the grade of each category based on the commodity evaluation of the commodity of each category; and determining the grade of the commodity based on the grade and the proportion of each category.
Moreover, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the disclosure and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
Furthermore, some of the described embodiments are described herein as a method or combination of method elements that can be performed by a processor of a computer system or by other means of performing the described functions. A processor having the necessary instructions for carrying out the method or method elements thus forms a means for carrying out the method or method elements. Further, the elements of the apparatus embodiments described herein are examples of the following apparatus: the apparatus is used to implement the functions performed by the elements for the purposes of this disclosure.
As used herein, unless otherwise specified the use of the ordinal adjectives "first", "second", "third", etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.
While the disclosure has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the disclosure as described herein. Moreover, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the disclosed subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present disclosure is intended to be illustrative, but not limiting, of the scope of the disclosure, which is set forth in the following claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111412318.7A CN113962611A (en) | 2021-11-25 | 2021-11-25 | Processing method and system for commodity evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111412318.7A CN113962611A (en) | 2021-11-25 | 2021-11-25 | Processing method and system for commodity evaluation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113962611A true CN113962611A (en) | 2022-01-21 |
Family
ID=79471964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111412318.7A Pending CN113962611A (en) | 2021-11-25 | 2021-11-25 | Processing method and system for commodity evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113962611A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881795A (en) * | 2015-05-16 | 2015-09-02 | 成都数联铭品科技有限公司 | E-commerce false comment judging and recognizing method |
| CN106339375A (en) * | 2015-07-06 | 2017-01-18 | 阿里巴巴集团控股有限公司 | Webpage item evaluate information display method and device |
| CN108550065A (en) * | 2018-04-10 | 2018-09-18 | 百度在线网络技术（北京）有限公司 | comment data processing method, device and equipment |
| CN111160774A (en) * | 2019-12-30 | 2020-05-15 | 深圳大学 | A calculation method and computer equipment for evaluation score |
| CN111612026A (en) * | 2019-02-26 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Method, device and system for obtaining evaluation result of product or class |
-
2021
- 2021-11-25 CN CN202111412318.7A patent/CN113962611A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881795A (en) * | 2015-05-16 | 2015-09-02 | 成都数联铭品科技有限公司 | E-commerce false comment judging and recognizing method |
| CN106339375A (en) * | 2015-07-06 | 2017-01-18 | 阿里巴巴集团控股有限公司 | Webpage item evaluate information display method and device |
| CN108550065A (en) * | 2018-04-10 | 2018-09-18 | 百度在线网络技术（北京）有限公司 | comment data processing method, device and equipment |
| CN111612026A (en) * | 2019-02-26 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Method, device and system for obtaining evaluation result of product or class |
| CN111160774A (en) * | 2019-12-30 | 2020-05-15 | 深圳大学 | A calculation method and computer equipment for evaluation score |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109118214B (en) | Method and device for operating intelligent contract | |
| KR102351947B1 (en) | Automated Techniques for Image Verification | |
| CN112507936B (en) | Image information auditing method and device, electronic equipment and readable storage medium | |
| US20140351109A1 (en) | Method and apparatus for automatically identifying a fraudulent order | |
| US20130325701A1 (en) | E-currency validation and authorization services platform | |
| US20150161529A1 (en) | Identifying Related Events for Event Ticket Network Systems | |
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| TWI534735B (en) | Information identification methods and equipment | |
| AU2018267630A1 (en) | Intelligent chargeback processing platform | |
| CN104965844A (en) | Information processing method and apparatus | |
| AU2013246140B2 (en) | Discovering spam merchants using product feed similarity | |
| EP3987740B1 (en) | Systems and methods for authenticating an electronic transaction | |
| CN112529575B (en) | Risk early warning method, equipment, storage medium and device | |
| CN104718547A (en) | Customer data analysis system | |
| CN110619530A (en) | Agricultural product tracing method, electronic equipment and computer readable storage medium | |
| CN113763057A (en) | User identity portrait data processing method and device | |
| CN108648038A (en) | A kind of credit propagation and maliciously evaluation recognition methods excavated based on subgraph | |
| CN113743522A (en) | Detection method and device for illegal behavior and electronic equipment | |
| CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
| CN108734366B (en) | User identification method and system, nonvolatile storage medium and computer system | |
| CN103955833A (en) | Navy identity verification method based on bogus transaction and social relation matrix analysis | |
| CN111476668B (en) | Identification method and device of credible relationship, storage medium and computer equipment | |
| CN111047146B (en) | Risk identification method, device and equipment for enterprise users | |
| CN116894124B (en) | Policy generation method, device, equipment and medium | |
| CN113962611A (en) | Processing method and system for commodity evaluation |
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 |