CN114626885B - Retail management method and system based on big data - Google Patents
Retail management method and system based on big data Download PDFInfo
- Publication number
- CN114626885B CN114626885B CN202210266308.5A CN202210266308A CN114626885B CN 114626885 B CN114626885 B CN 114626885B CN 202210266308 A CN202210266308 A CN 202210266308A CN 114626885 B CN114626885 B CN 114626885B
- Authority
- CN
- China
- Prior art keywords
- platform
- merchant
- evaluation
- platforms
- data
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The embodiment of the specification provides a retail management method based on big data, which comprises the steps of acquiring evaluation data of a target merchant on a plurality of first platforms based on relevant information of the target merchant; determining whether the evaluation data of the target merchant on at least one of the plurality of first platforms has the risk of controlled evaluation based on the evaluation data on the plurality of first platforms; and if the risk exists, sending prompt information to the target merchant.
Description
Technical Field
The present disclosure relates to the field of retail management, and more particularly, to a retail management method and system.
Background
At present, a user can evaluate the service of an offline store by a plurality of online platforms, and the evaluation generally reflects the real service condition of the offline store. However, there may be a situation of critique control, i.e. the critique is controlled and even goes against the shop.
Therefore, there is a need for a retail management method and system based on big data, which makes the offline store timely detect the occurrence of "controlled evaluation" and reduce the loss.
Disclosure of Invention
One of the embodiments of the present specification provides a retail management method for big data, including: acquiring evaluation data of the target merchant on a plurality of first platforms based on the related information of the target merchant; determining whether the evaluation data of the target merchant on at least one of the plurality of first platforms has the risk of controlled evaluation based on the evaluation data on the plurality of first platforms; and if the risk exists, sending prompt information to the target merchant.
One of the embodiments of the present specification provides a big data based retail management system, including: the acquisition module is used for acquiring evaluation data of the target merchant on a plurality of first platforms based on the relevant information of the target merchant; the analysis module is used for determining whether the evaluation data of the target merchant on at least one of the first platforms has the risk of being controlled and evaluated or not based on the evaluation data on the first platforms; and the reminding module is used for sending prompt information to the target merchant when the controlled evaluation risk exists.
One of the embodiments of the present specification provides a big data based retail management device, which includes a processor for executing a big data based retail management method.
One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes a retail sales management method based on big data.
Drawings
The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:
FIG. 1 is a schematic diagram of an application scenario of a big-data based retail management system according to some embodiments of the present description;
FIG. 2 is an exemplary flow diagram of a big data based retail management method according to some embodiments of the present description;
FIG. 3 is an exemplary flow diagram for determining whether there is a risk of controlled evaluation based on evaluation feature vectors, according to some embodiments of the present description;
FIG. 4 is an exemplary diagram illustrating a determination of whether there is a risk of being assessed based on shift propensity characteristics, according to some embodiments of the present description;
FIG. 5 is an exemplary block diagram of a big data based retail management system, according to some embodiments of the present description.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or stated otherwise, like reference numbers in the figures refer to the same structure or operation.
It should be understood that "system," "device," "unit," and/or "module" as used herein is a method for distinguishing between different components, elements, parts, portions, or assemblies of different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
FIG. 1 is a schematic diagram of an application scenario of a big-data based retail management system according to some embodiments of the present description. As shown in fig. 1, an application scenario 100 of the big data based retail management system according to the embodiment of the present specification may include a server 110, a processor 120, a storage device 130, a user terminal 140, and a network 150.
Big-data based retail management system 100 may determine the risk of whether an evaluation of a target merchant is controlled by implementing the methods and/or processes disclosed herein. The retail management may include different retail modes such as online retail and offline retail. In some embodiments, big-data based retail management system 100 may analyze whether there is a risk of controlling the evaluation of the target merchant based on all of the evaluated big data for the target merchant.
In some embodiments, storage 130 may be included in server 110, user terminal 140, and possibly other system components.
In some embodiments, the processor 120 may be included in the server 110, the user terminal 140, and possibly other system components.
Network 150 may include any suitable network capable of facilitating information and/or data exchange for big-data based retail management system 100. In some embodiments, information and/or data may be exchanged between one or more components of big data based retail management system 100 (e.g., storage device 130, processor 120, user terminal 140) via network 150. In some embodiments, the network 150 may be any one or more of a wired network or a wireless network. In some embodiments, the network 150 may include one or more network access points. For example, the network 150 may include wired or wireless network access points.
FIG. 2 is an exemplary flow diagram of a big-data based retail management method, according to some embodiments of the present description. As shown in fig. 2, the process 200 includes the following steps. In some embodiments, process 200 may be performed by processor 120.
The target merchant may refer to the merchant who is being evaluated for the presence of the controlled risk. The targeted merchants may include online and/or offline merchants, and the like. The online merchants may include targeted merchants on one or more platforms. The offline merchant may include one or more offline stores of the target merchant. Illustratively, one or more online and/or offline merchants engaged in the sale of 3C goods, cell phones, and the like. The related information of the target merchant may refer to information related to the target merchant, for example, merchant type information (e.g., commodity merchant, clothing merchant, 3C commodity merchant, etc.) of the target merchant, commodity information for sale, platform information used for sale, how many offline stores the target merchant includes, locations of different offline stores, and the like.
The first platform refers to a platform which can sell, comment and/or display the goods of the target merchant. In some embodiments, the first platform may include multiple platforms, and the different platforms may include multiple platforms. For example, the first platform may include one or more shopping platforms, review platforms. Through the shopping platform, the target merchant can display and/or sell the goods, the user can browse and/or purchase the goods, and the like, wherein the shopping platform also has an evaluation function. Through the commenting platform, the user can view and/or comment on the commodity.
The evaluation data may refer to data related to the evaluation of the commodity by the user. The user can perform various evaluations on the goods. For example, the evaluation data may include quality of goods, delivery speed, service attitude, and the like. The evaluation data can be represented in a variety of ways (e.g., numerical values, text, etc.). For example, the user may score the product, for example, the evaluation data is a numerical value between 0 and 10, and a higher numerical value indicates that the user evaluates the product more highly; for example, the user may evaluate a product by text, and the evaluation data may include "a product is cheap and affordable", "a product is expensive", "a product is poor in quality", and the like. For another example, the user may evaluate the product by a numerical value and a text, and the evaluation data is "8" and "a product is cheap and affordable", for example.
In some embodiments, the obtaining module 510 may obtain the evaluation data of the target merchant on a plurality of first platforms via a network. For example, the obtaining module 510 may obtain relevant information (such as information of goods sold by the target merchant, platform information used for sale, and the like) of the target merchant from the storage device, and obtain evaluation data of the target merchant on multiple platforms, such as a shopping platform, a review platform, a shopping and/or review platform, and the like, through a network based on the information.
And step 220, determining whether the evaluation data of the target merchant on one or more of the first platforms has the risk of being evaluated under control or not based on the evaluation data on the first platforms. In some embodiments, step 220 may be performed by analysis module 520.
A risk of controlled evaluation may refer to a risk that an evaluation of a target merchant may be controlled. For example, the risk that the user's rating of the target merchant is adjusted, modified, etc. As another example, the target merchant's ratings may be deliberately directed to a certain direction (only good or poor), or disturbed by other means such that a certain type of rating cannot be displayed.
In some embodiments, the analysis module 520 may determine whether the target merchant is at risk of controlled evaluation of the evaluation data on one or more first platforms based on the evaluation data on the plurality of first platforms. For example, when the evaluation data on a certain first platform is greatly different from the evaluation data of other first platforms, the analysis module 520 may determine that the evaluation data on a certain first platform may have a risk of being evaluated under control. Illustratively, the first platforms corresponding to the target merchant a are a shopping platform 1, a shopping platform 2, a commenting platform 3 and a shopping commenting platform 4. The analysis module 520 obtains the multiple evaluation data of the 4 first platforms, performs statistics and analysis on the multiple evaluation data, and determines that the evaluation data of the shopping platform 2 is greatly different from the evaluation data of the other 3 first platforms, and the analysis module 520 may determine that the evaluation data on the shopping platform 2 may have a risk of being evaluated under control.
In some embodiments, the analysis module 520 may determine a plurality of evaluation feature vectors and a reference evaluation feature vector corresponding to the target merchant on the plurality of first platforms, determine a distance between the evaluation feature vectors of the plurality of first platforms and the reference evaluation feature vector, and determine whether the first platform has a risk of being controlled for evaluation according to the distance. For more descriptions of determining whether the first platform has the risk of controlled evaluation through the distances between the evaluation feature vectors of the plurality of first platforms and the reference evaluation feature vector, refer to the description related to fig. 3, and no further description is given here.
In some embodiments, the analysis module 520 may determine a set of merchants on the first platform that match the target merchant (the set of merchants may include one or more reference merchants), determine a baseline shift propensity characteristic for the first platform based on the ratings data of each of the reference merchants in the set of merchants on the first platform and the ratings data of the respective one or more second platforms; determining an offset tendency characteristic of the target merchant on the first platform based on the evaluation data of the target merchant on the first platform and the evaluation data of the target merchant on one or more second platforms; and further determining whether the target merchant is at risk of being assessed on the first platform. For more description on the determination of whether the target merchant has the risk of being assessed on the first platform through the reference offset tendency characteristic and the offset tendency characteristic, reference is made to the related description of fig. 4, and details are not repeated here.
And step 230, if the risk exists, sending a prompt message to the target merchant. In some embodiments, step 230 may be performed by the reminder module 530.
In some embodiments, the reminder may refer to relevant information that alerts the target merchant to the risk of being assessed by the control. The reminder may include the name of the first platform for which the controlled evaluation risk exists, which particular offline store of the target merchant for which the controlled evaluation risk exists, the likelihood of the controlled evaluation risk exists, and the like.
In some embodiments, the reminder module 530 can send the relevant reminder information to the target merchant over a network. The sending mode of the prompt message may include various modes, for example, the prompt message is sent to the target merchant by short message, voice, mail, etc.
In some embodiments of the present description, it is determined whether the evaluation data of the target merchant on the plurality of first platforms has a risk of evaluation control through the evaluation data on the plurality of first platforms, and the target merchant may timely find whether one or more first platforms evaluate himself or herself unfairly, which is helpful for the target merchant to monitor evaluation control, and when evaluation control occurs, the target merchant may timely analyze or process (for example, delete related unfairly comments, etc.), thereby ensuring that the platforms evaluate the target merchant fairly.
Fig. 3 is an exemplary flow diagram illustrating a determination of whether there is a risk of controlled evaluation based on evaluation feature vectors according to some embodiments of the present description. As shown in fig. 3, the process 300 includes the following steps. In some embodiments, process 300 may be performed by processor 120, e.g., by a corresponding module within system 500, such as analysis module 520.
The evaluation feature vector can refer to a vector generated by processing one or more evaluation data on a certain platform and related to a target merchant. The evaluation feature vector may include a plurality of elements, and different elements may reflect different evaluations regarding the target merchant. For example, the different elements may reflect the number of reviews, the number of good reviews, the number of bad reviews, the proportion of good reviews, the proportion of bad reviews, etc. for the target merchant.
In some embodiments, the analysis module 520 may determine, in various ways, a plurality of evaluation feature vectors corresponding to the target merchant on the plurality of first platforms, respectively, based on the evaluation data of the target merchant on the plurality of first platforms. For example, the target merchant corresponds to a plurality of first platforms, and the analysis module 520 may obtain evaluation data on the plurality of first platforms, and determine a plurality of evaluation feature vectors by analyzing the evaluation data on the plurality of first platforms, respectively. Illustratively, the target trader corresponds to 2 first platforms, the analysis module 520 obtains evaluation data on the 2 corresponding first platforms, and by analyzing the evaluation data on the 2 first platforms, it is determined that the number of evaluations of the 1 st first platform is 150, the number of good evaluations is 90, and the number of bad evaluations is 60; the number of evaluations of the 2 nd first platform was 230, the number of good evaluations was 150, and the number of bad evaluations was 80. The evaluation feature vector corresponding to the 1 st first platform may be (150, 90, 60); the evaluation feature vector corresponding to the 2 nd first platform may be (230, 150, 80).
In some embodiments, the appraisal feature vector may be determined by the analysis module 520 based on the appraisal data of the target merchant on a plurality of first platforms. For example, the evaluation feature vector may be (a, b), a may represent a proportion of good evaluation for the target merchant; b may represent a proportion of bad scores for the target merchant. As described in the above example, the target merchant corresponds to 2 first platforms, the evaluation quantity of the 1 st first platform is 150, the good evaluation quantity is 90, and the bad evaluation quantity is 60, and the analysis module 520 may statistically determine that the evaluation feature vector corresponding to the 1 st first platform is (0.6, 0.4), and the good evaluation ratio is 60%; the poor rating is 40%; the evaluation quantity of the 2 nd first platform is 230, the good evaluation quantity is 150, the bad evaluation quantity is 80, and the analysis module 520 can statistically determine that the evaluation feature vector corresponding to the 2 nd first platform is (0.65, 0.35), and the good evaluation proportion is 65%; the bad rating is 35%.
In some embodiments of the present disclosure, evaluation data on a plurality of first platforms are counted, and an evaluation feature vector is determined based on the statistical data, so that differences between the evaluation data on the plurality of first platforms can be determined more intuitively through the evaluation feature vector, thereby facilitating subsequent determination of whether one of the plurality of first platforms has a risk of being controlled and evaluated.
And step 320, determining a reference evaluation feature vector according to the plurality of evaluation feature vectors.
The reference evaluation feature vector may refer to a reference vector used when evaluating the evaluation feature vector. The benchmark evaluation feature vector may include a plurality of elements, and different elements may reflect a comprehensive evaluation of different evaluations regarding the target merchant. For example, the different elements may reflect a composite rating number, a composite goodness number, a composite badness number, a composite goodness ratio, a composite badness ratio, etc. for the target merchant.
In some embodiments, the analysis module 520 may determine a baseline evaluation feature vector from a plurality of evaluation feature vectors.
In some embodiments, the analysis module 520 may fuse a plurality of evaluation feature vectors corresponding to the plurality of first platforms, respectively, to determine a reference evaluation feature vector. In some embodiments, the fusing may include an averaging process, a weighted averaging process, or the like. For example, the analysis module 520 may perform an average, a weighted average, or the like calculation on the plurality of evaluation feature vectors to determine a reference evaluation feature vector. Illustratively, the evaluation feature vector corresponding to the 1 st first platform is (0.6, 0.4); the evaluation feature vector for the 2 nd first platform is (0.65, 0.35). The analysis module 520 determines the reference evaluation feature vector to be (0.625, 0.375) by performing an average calculation on the evaluation feature vectors corresponding to the 2 first platforms. Example 2, the 1 st first platform corresponds to an evaluation feature vector of (0.6, 0.4) and a corresponding weight of 0.7; the evaluation feature vector for the 2 nd first platform is (0.65, 0.35) and the corresponding weight is 0.3. The analysis module 520 determines the reference evaluation feature vector to be (0.615, 0.385) by performing weighted average calculation on the evaluation feature vectors corresponding to the 2 first platforms. In some embodiments, the weights corresponding to the different evaluation feature vectors may be set empirically by the target merchant, or may be set by the processing device according to default values or actual needs of the application scenario 100. For example, the weights corresponding to different evaluation feature vectors may be determined according to the evaluation quantities of different first platforms. When the number of evaluations is larger, the proportion of accidental unfair evaluation is relatively smaller; the smaller the number of evaluations, the larger the proportion of the occasional unfair evaluation. The larger the number of evaluations of a certain first stage is, the larger the weight of the corresponding evaluation feature vector is. Conversely, the smaller the number of evaluations of a certain first platform, the smaller the weight of the corresponding evaluation feature vector.
In some embodiments of the present description, a plurality of evaluation feature vectors corresponding to a plurality of first platforms, respectively, are fused to determine a benchmark evaluation feature vector, so that accuracy of the benchmark evaluation feature vector can be ensured, and it is further facilitated to subsequently determine whether one of the plurality of first platforms has a risk of being controlled and evaluated.
And 330, judging the distance between the evaluation characteristic vector of the first platform and the reference evaluation characteristic vector for each of the first platforms, wherein if the distance is greater than a threshold value, the first platform has a risk of being controlled and evaluated.
In some embodiments, the distance between the evaluation feature vector of the first platform and the reference evaluation feature vector may be represented by a vector distance, which may include a cosine distance, a euclidean distance, a hamming distance, or the like. The vector distance may represent a likelihood that the corresponding first platform is being controlled. For example, the greater the vector distance, the greater the likelihood that the corresponding first platform is being evaluated. When the vector distance is greater than the threshold value, it can be judged that the corresponding first platform has the risk of being controlled and evaluated.
In some embodiments, the analysis module 520 may perform a calculation for each of the plurality of first platforms to determine a distance between the evaluation feature vector for each first platform and a baseline evaluation feature vector. For example, as described in the above example, the analysis module 520 may calculate a distance D1 (e.g., cosine distance, etc.) between the evaluation feature vector (0.6, 0.4) corresponding to the 1 st first platform and the reference evaluation feature vector (0.615, 0.385); the analysis module 520 may calculate a distance D2 (e.g., cosine distance, etc.) between the evaluation feature vector (0.65, 0.35) corresponding to the 2 nd first platform and the reference evaluation feature vector (0.615, 0.385). In some embodiments, if the distance is greater than the threshold, the analysis module 520 may determine that there may be a risk of controlled evaluation of the first platform corresponding to the distance.
In some embodiments of the present disclosure, a plurality of evaluation feature vectors and a reference evaluation feature vector corresponding to each of the first platforms are determined according to evaluation data on the plurality of first platforms, and one or more first platforms having a risk of controlled evaluation among the plurality of first platforms are determined by determining distances between the evaluation feature vectors of the plurality of first platforms and the reference evaluation feature vector and comparing the distances with a threshold. The method is beneficial to improving the accuracy of determining that the first platform has the risk of being controlled and evaluated.
FIG. 4 is an exemplary diagram illustrating a determination of whether there is a risk of being assessed based on shift propensity characteristics, according to some embodiments of the present description. As shown in fig. 4, the process 400 includes the following steps. In some embodiments, flow 400 may be performed by processor 120, e.g., by a corresponding module within system 500, such as analysis module 520.
For a first platform on the plurality of first platforms, a set of merchants on the first platform matching the target merchant is determined, step 410.
The set of merchants may include one or more reference merchants. A reference merchant may refer to a merchant that has some similarity to the target merchant. For example, there may be some similarity between the set of merchants matching the target merchant and the target merchant's items sold, the merchant name, the merchant address, the number of first platforms present, and the like. Illustratively, the set of merchants matching the target merchant and the sales items of the target merchant each include a computer or the name of the merchant includes a 3C product or the address of the merchant is in a certain area, etc.
In some embodiments, the analysis module 520 may determine a set of merchants on each of the plurality of first platforms that match the target merchant in a variety of ways. For example, for first platform 1 and first platform 2, the analysis module may determine a set of merchants matching the target merchant on first platform 1 and a set of merchants matching the target merchant on first platform 2, respectively.
In some embodiments, the analysis module 520 may determine a set of merchants that match the target merchant by the type of items sold by the target merchant. For example, the type of the goods sold by the target merchant is 3C products, and the analysis module 520 may determine a plurality of merchants with the type of the goods sold by the target merchant being 3C products on a certain first platform as a group of merchants matching the target merchant on the first platform.
In some embodiments of the present description, determining a group of merchants matching a target merchant according to a type of a commodity sold by the target merchant may ensure that the type of the commodity sold by the group of merchants is the same as or similar to that of the commodity sold by the target merchant, and thus may accurately determine the group of merchants.
In some embodiments, the analysis module 520 may construct the commodity feature vectors of different merchants based on a plurality of commodity-related information respectively corresponding to a plurality of merchants on each of a plurality of first platforms. And clustering the multiple merchants based on the commodity feature vectors of different merchants to determine multiple clustering centers. Each clustering center represents a certain type of merchants, and the commodity type or/and sales of at least one merchant in the cluster corresponding to the clustering center are similar.
In some embodiments, the analysis module 520 may calculate distances between the commodity feature vector corresponding to the target merchant and the commodity feature vector corresponding to each of the plurality of cluster centers, respectively, and determine a cluster center that best matches the target merchant. Further, the merchant in the cluster corresponding to the best matching cluster center is determined as a group of merchants matching the target merchant on the first platform. The commodity feature vector corresponding to the target merchant may be determined by the analysis module 520 based on the commodity-related information of the target merchant; the commodity feature vector corresponding to the clustering center may be the average value of the commodity feature vectors of all merchants in the cluster corresponding to the clustering center, or the commodity feature vector of the merchant corresponding to the clustering center.
The goods-related information may refer to various information related to the goods, for example, the type of goods, the average price of the goods, the monthly or quarterly sales amount of the goods, the credit rating of the goods, and the like. The type of the commodity can comprise electronic products, electronic accessories, food, clothes or other types of commodities, and the specific situation can be determined according to actual conditions.
The commodity feature vector refers to a vector that can represent the commodity feature. For example, the merchandise feature vector (a, b, c, d), different elements in the merchandise feature vector may represent different features of the merchandise. a may represent a commodity type; b may represent the average price of the goods; c may represent the monthly sales volume of the goods; d may represent the credit rating of the good. In some embodiments, different elements in the merchandise feature vector may be represented by different numerical values. Different numbers represent different characteristics of the article. For example, the element a in the commodity feature vector is represented by 0 to 3, and the numerical values between 0 and 3 can respectively represent the type of the commodity as an electronic product, an electronic accessory, a food, and a garment; the element b in the commodity feature vector can be represented by a numerical value corresponding to the average price of the commodity; the element c in the commodity feature vector can be represented by a numerical value corresponding to the monthly sales volume of the commodity; the element d in the commodity feature vector can be represented by a numerical value corresponding to the credit level of the commodity (such as 1, 2, 3 levels and the like); for example, the goods feature vector (1, 150, 907, 2) may indicate that the type of goods is electronic accessories, the average price of the goods is 150 yuan, the monthly sales volume of the goods is 907 bills, and the credit rating of the goods is 2.
In some embodiments, the cluster center may be obtained by the analysis module 520 clustering a plurality of commodity feature vectors corresponding to a plurality of merchants through a clustering algorithm. For example, clustering algorithms may include K-Means clustering, mean shift clustering, density-based clustering method (DBSCAN), maximum Expectation (EM) clustering with Gaussian Mixture Model (GMM), agglomerative hierarchy clustering, graph Community Detection (Graph Community Detection), and so forth.
In some embodiments, the analysis module 520 may construct the commodity feature vector of the target merchant based on a plurality of commodity-related information corresponding to the target merchant on the first platform. The construction of the commodity feature vector of the target merchant is similar to the construction contents of the commodity feature vectors of a plurality of merchants, and more contents related to the construction of the commodity feature vector of the target merchant refer to the construction of the commodity feature vectors of the plurality of merchants, which are not described again here.
The cluster center that best matches the target merchant may refer to the cluster center that has the smallest vector distance from the target merchant to the target merchant.
In some embodiments, the analysis module 520 may use a cluster center, in which a distance between the commodity feature vector corresponding to the target merchant and the commodity feature vector corresponding to the cluster center meets a preset requirement, as the best matching cluster center. For example, the preset requirement may be that the distance is the smallest, and accordingly, the analysis module 520 may determine the cluster center having the smallest distance from the target merchant vector as the cluster center that best matches the target merchant. For example, for cluster centers 1, 2, 3, and 4, the analyzing module 520 calculates distances between the obtained commodity feature vector corresponding to the target merchant and the merchant feature vectors corresponding to the 4 cluster centers to be distance 1, distance 2, distance 3, and distance 4, respectively, where the distance 3 is to be the smallest distance from the target merchant vector, and the analyzing module 520 may determine the cluster center 3 corresponding to the distance 3 as the cluster center that is the closest match to the target merchant. In some embodiments, the analysis module 520 may determine the plurality of merchants corresponding to the best matching cluster centers as the set of merchants matching the target merchant. For example, as described in the above example, the best matching cluster center 3 corresponds to 10 merchants, and the analysis module 520 may determine the above 10 merchants or a plurality of merchants therein as a group of merchants matching the target merchant.
In some embodiments of the present disclosure, determining a group of merchants matching a target merchant in a clustering manner may enrich types of corresponding commodities for the group of merchants, where multiple reference merchants in the group of merchants have a greater commonality.
In some embodiments, the set of merchants matching the target merchant may refer to a set of merchants that are present on all of the plurality of first platforms, or a set of merchants that are present on all of the plurality of first platforms and that achieve a certain percentage. For example, a group of merchants matching the target merchant on the plurality of first platforms includes 5 reference merchants, all of the 5 reference merchants appearing on the same shopping platform a and shopping platform B, commenting platform C, shopping and/or commenting platform D, and the like. In some embodiments, the set of merchants matching the target merchant may indicate that the percentage of occurrences on the plurality of first platforms is above a preset threshold (i.e., the number of occurrences reaches a certain percentage). For example, the first platform includes 10 first platforms, the preset threshold is 70%, the group of merchants includes 5 reference merchants, and the number of the 5 reference merchants appearing on the 10 first platforms is greater than 7.
In some embodiments, the analysis module 520 may further filter the determined set of merchants matching the target merchant by determining whether the set of merchants matching the target merchant are present on all of the first plurality of platforms or are present on all of the plurality of platforms and achieve a certain percentage. For example, the type of the sold goods of the target merchant is 3C products, the target merchant appears on 4 first platforms, and the analysis module 520 may select merchants with the same type of the sold goods as the target merchant on the 4 first platforms, or merchants with the type of the sold goods of the first platform as 3C products, the appearing ratio of which is higher than a preset threshold (that is, the number of occurrences reaches a certain ratio), and determine as a group of merchants matched with the target merchant. For another example, the analysis module 520 may select a merchant that is present on the same first platforms as the target merchant from a plurality of merchants corresponding to the best matching cluster center as a group of merchants matching the target merchant. For another example, the analysis module 520 may select, as a group of merchants matched with the target merchant, merchants corresponding to the most matched cluster centers, where a ratio of the merchants appearing on the same plurality of first platforms as the target merchant is higher than a preset threshold.
In some embodiments of the present disclosure, a group of merchants primarily matched with a target merchant is determined by determining a type or a cluster of goods sold by the target merchant, and a group of merchants matched with the target merchant is determined by determining a condition (e.g., whether the matched merchants appear or appear in proportion) of the matched merchants in the group of merchants on a first platform, so as to further ensure accuracy of determining the group of merchants.
And step 420, determining the benchmark deviation tendency characteristics of the first platform based on the evaluation data of each reference merchant in a group of merchants on the first platform and the evaluation data of each reference merchant on at least one second platform.
The second platform may refer to the platform where the reference merchant is located. The second platform may include a plurality of platforms. In some embodiments, the second platform may be the same as or different from the first platform. For example, the plurality of first platforms may include a critique shopping platform 1, a shopping platform 2, a critique platform 1, and the like. The plurality of second platforms may include a shopping platform 1, a shopping platform 2, a commenting platform 2, a shopping platform 3, and the like. The one or more second platforms corresponding to the reference merchant may be the same or different. For example, the second platform corresponding to the reference merchant 1 is the shopping platform 1; the reference merchant 2 corresponds to a second platform which is a shopping platform 1, a shopping platform 2, an assessment platform 2 and the like; the second platforms corresponding to the reference merchant 3 are a shopping platform 2, a comment platform 1, a shopping platform 3 and the like.
The reference offset propensity feature of the first platform may be indicative of a difference between the merchant's ratings data on the first platform and the merchant's ratings data on the second platform. The reference shift tendency characteristic may be represented by a feature vector.
The analysis module 520 may determine the baseline evaluation feature vector in a variety of ways. In some embodiments, the analysis module 520 may determine the baseline shift propensity feature for the first platform by determining rating data for each reference merchant on the first platform and rating data for the reference merchant on one or more second platforms for a set of merchants matching the target merchant. For example, the analysis module 520 may analyze the evaluation data to determine an evaluation feature vector a corresponding to the evaluation data of the reference merchant on the first platform, one or more evaluation feature vectors B, an evaluation feature vector C corresponding to the evaluation data of the reference merchant on the second platform, and the like, and the analysis module 520 may analyze the evaluation feature vectors to determine a difference between the evaluation feature vector a and the evaluation feature vector B, a difference between the evaluation feature vector a and the evaluation feature vector C, and the like, and determine a reference evaluation feature vector by the difference.
In some embodiments, the analysis module 520 may perform a first fusion of the difference features of the reference merchant between the first platform and each of the one or more second platforms, determine a sub-reference-offset-propensity feature of the reference merchant at the first platform; the analysis module 520 may perform a second fusion on the sub-benchmark deviation tendency characteristics respectively corresponding to one or more reference merchants in the group of merchants to determine the benchmark deviation tendency characteristics of the first platform.
A difference feature refers to a feature that may represent a difference between the user's ratings data for the reference merchant on different platforms, e.g., a difference feature may represent a difference between the reference merchant's ratings data on a first platform and the reference merchant's ratings data on one or more second platforms.
In some embodiments, the analysis module 520 may determine the difference characteristic by processing the evaluation data of the reference merchant on a first platform and the evaluation data of the reference merchant on one or more second platforms.
In some embodiments, the analysis module 520 may determine the difference feature by performing subtraction, determining a ratio, and calculating a variance on the evaluation feature vector corresponding to the evaluation data of the reference merchant on the first platform and the evaluation feature vector corresponding to the evaluation data of the reference merchant on one or more second platforms. For example, the evaluation feature vectors corresponding to the evaluation data of the reference merchant a on the first platform are (a 1, b1, c 1), and the evaluation feature vectors corresponding to the evaluation data of the reference merchant a on the plurality of second platforms are (a 2, b2, c 2), (a 3, b3, c 3), (a 4, b4, c 4), respectively. The difference between the first platform and each of the plurality of second platforms for reference merchant A is characterized by (a 1-a2, b1-b2, c1-c 2), (a 1-a3, b1-b3, c1-c 3), (a 1-a4, b1-b4, c1-c 4), respectively.
The first fusing may refer to processing a plurality of difference features corresponding to the reference merchant. The first fusion may include an averaging process, a weighted averaging process, or the like.
The sub-reference deviation tendency characteristic refers to a sub-reference characteristic which can represent the deviation tendency between evaluation data of a certain reference merchant on a certain first platform and evaluation data on one or more second platforms. The child fiducial shift propensity feature may be represented by a feature vector.
In some embodiments, the analysis module 520 may perform an averaging process or a weighted averaging process on the one or more difference features to determine a sub-reference bias propensity feature of the reference merchant at the first platform. For example, when the first fusion is a weighted average, the weight corresponding to the difference feature between the first platform and each of the plurality of second platforms of the reference merchant a may be determined by the proportion of the plurality of reference merchants on the second platforms that appear on the first platform. For example, the second platform corresponding to the difference features (a 3, b3, c 3) is the second platform 5, the ratio of the plurality of reference merchants appearing in the first platform in the second platform 5 is the largest, and the weight corresponding to the difference features (a 3, b3, c 3) is the largest (e.g. 0.5); the reference merchant appearing in the second platform corresponding to the difference feature (a 2, b2, c 2) appears in the first platform to a lesser degree, and the weight corresponding to the difference feature (a 2, b2, c 2) is centered (e.g., 0.3); the reference merchant appearing in the second platform corresponding to the difference feature (a 4, b4, c 4) appears in the first platform in the smallest proportion, and the weight corresponding to the difference feature (a 4, b4, c 4) is the smallest (e.g. 0.2). The analysis module 520 performs a weighted average process on the plurality of difference features to obtain the sub-standard deviation tendency features of the reference merchant a on the first platform as ((a 1-a 2) × 0.3+ (1-a 3) × 0.5+ (a 1-a 4) × 0.2, (b 1-b 2) × 0.3+ (b 1-b 3) × 0.5+ (b 1-b 4) × 0.2, (c 1-c 2) × 0.3+ (c 1-c 3) ± (c 1-c 4) × 0.2).
The second fusion may refer to processing a plurality of sub-reference-offset-propensity features corresponding to a plurality of reference merchants. The second fusion may include an averaging process, or a weighted averaging process, or the like.
The analysis module 520 may perform a second fusion on the sub-benchmark deviation tendency characteristics respectively corresponding to one or more reference merchants in the group of merchants to determine the benchmark deviation tendency characteristics of the first platform. For example, a group of merchants F includes 3 reference merchants, with different reference merchants corresponding to different sub-reference-offset-propensity characteristics. The 3 reference merchants and the corresponding sub-fiducial deviation-propensity features are reference merchant 1 corresponding sub-fiducial deviation-propensity feature 1 (d 1, d2, d3, \8230;), reference merchant 2 corresponding sub-fiducial deviation-propensity feature 2 (e 1, e2, e3, \8230; \8230;), reference merchant 3 corresponding sub-fiducial deviation-propensity feature 3 (f 1, f2, f3, \8230;)/8230;), respectively. The analysis module 520 performs a second fusion on the 3 sub-reference deviation tendency characteristics to determine a reference deviation tendency characteristic of the first platform.
In some embodiments, the analysis module 520 may perform an averaging process or a weighted averaging process on the one or more base reference offset propensity features to determine the reference offset propensity feature for the first platform. For example, when the second fusion is weighted average, the sub-reference deviation tendency characteristics corresponding to different reference merchants correspond to different weights, and the different weights corresponding to the sub-reference deviation tendency characteristics can be determined by the distance between the reference merchant and the cluster center corresponding to a group of merchants corresponding to the reference merchant. The closer the distance, the more weight the child fiducial-shift-prone feature corresponds to. For example, a cluster center corresponding to a group of merchants F is G, and a sub-fiducial-bias-propensity feature 1 (d 1, d2, d3, \8230;) corresponding to a reference merchant 1 is closest to the cluster center G and corresponds to the greatest weight (e.g., 0.6); child fiducial-bias propensity feature 3 (f 1, f2, f3, \8230;) corresponding reference merchant 3 is centered in distance from cluster center G, and corresponding weight is centered (e.g., 0.3); child fiducial-bias propensity feature 2 (e 1, e2, e3, \8230;) corresponds to a reference merchant 2 that is at a minimum distance from cluster center G and a minimum weight (e.g., 0.1). The analysis module 520 performs weighted average processing on the plurality of sub-reference deviation tendency characteristics to obtain the reference deviation tendency characteristics of the first platform as (0.6 + d1+0.3 + e1+0.1 + f1,0.6 + d2+0.3 + e2+0.1 f2,0.6 + d3+0.3 + e3+0.1 + f3, 82303030;).
In some embodiments of the present description, the difference is characterized by determining a difference characteristic for each reference merchant between the first platform and each of the one or more second platforms; performing first fusion on a plurality of difference characteristics corresponding to a reference merchant, and determining a sub-reference deviation tendency characteristic of the reference merchant on a first platform; and performing second fusion on the multiple sub-reference deviation tendency characteristics to determine the reference deviation tendency characteristics of the first platform, so that the accuracy and comprehensiveness of the reference deviation tendency characteristics of the first platform can be better ensured, and the accuracy of subsequently determining the risk of controlled evaluation of the first platform is further improved.
The deviation tendency characteristic of the target merchant on the first platform can represent the difference between the evaluation data of the target merchant on one of the first platforms and the evaluation data of the plurality of first platforms.
In some embodiments, the analysis module 520 may determine the offset propensity characteristic of the target merchant on the first platform in a variety of ways. In some embodiments, the analysis module 520 may analyze the difference between the feature vector of one of the plurality of first platforms and the feature vectors of other first platforms to determine the offset-prone feature of the first platform. For example, the target merchant appears on three first platforms, namely a first platform 1, a first platform 2 and a first platform 3, and the corresponding evaluation feature vectors are an evaluation feature vector M, an evaluation feature vector N and an evaluation feature vector O. Determining the deviation tendency feature of the first platform 1 may first determine a difference feature between the feature evaluation vector M and the evaluation feature vector N, and a difference feature between the feature evaluation vector M and the evaluation feature vector O, where the difference feature may be obtained by making a difference between the vectors. And determining the offset tendency characteristic of the target merchant on the first platform 1 by fusing the difference characteristics. In some embodiments, the difference features may be fused by averaging to obtain the shift-prone feature of a certain first platform.
And step 440, determining the risk of the target merchant being evaluated on the first platform based on the deviation tendency characteristics of the target merchant on the first platform and the benchmark deviation tendency characteristics of the first platform.
In some embodiments, the analysis module 520 may determine the difference between the offset-propensity feature of the first platform and the baseline offset-propensity feature of the first platform by calculating the difference, and determine the risk of the target merchant being assessed on the first platform based on the difference. The difference may refer to a vector distance between the offset-prone feature and the reference offset-prone feature. The analysis module 520 may calculate a distance (e.g., cosine distance, etc.) between the offset-trending feature of the first platform and the baseline offset-trending feature of the first platform, and if the distance is greater than a threshold, the analysis module 520 may determine that the target merchant is likely to be at risk for controlled evaluation at the first platform.
In some embodiments of the present specification, the accuracy of determining the risk that the target merchant is assessed on the first platform may be further ensured by determining the benchmark deviation tendency characteristic of the first platform and the deviation tendency characteristic of the target merchant on the first platform, and further determining the risk that the target merchant is assessed on the first platform.
It should be noted that the above description of the flow is for illustration and description only and does not limit the scope of the application of the present specification. Various modifications and changes to the flow may occur to those skilled in the art, given the benefit of this disclosure. However, such modifications and variations are intended to be within the scope of the present description.
FIG. 5 is an exemplary block diagram of a big data based retail management system, shown in some embodiments herein. In some embodiments, one or more modules in system 500 may be provided in processor 120 in fig. 1. As shown in fig. 5, system 500 may include at least the following modules:
the obtaining module 510 may be configured to obtain rating data of the target merchant on a plurality of first platforms based on the relevant information of the target merchant. For more contents of the relevant information and the evaluation data of the target merchant, refer to fig. 2 and the relevant description thereof, which are not described herein again.
The analysis module 520 may be configured to determine whether the target merchant is at risk of being assessed in the evaluation data of at least one of the plurality of first platforms based on the evaluation data of the plurality of first platforms. For more details about the evaluation, refer to fig. 3 and 4 and the related description thereof, which are not repeated herein.
In some embodiments, the analysis module 520 may be further configured to determine, based on the evaluation data of the target merchant on the plurality of first platforms, a plurality of evaluation feature vectors respectively corresponding to the target merchant on the plurality of first platforms; determining a reference evaluation feature vector according to the plurality of evaluation feature vectors; and for each of the plurality of first platforms, judging the distance between the evaluation characteristic vector of the first platform and the reference evaluation characteristic vector, and if the distance is greater than a threshold value, judging that the first platform has the risk of being controlled and evaluated. For more contents of determining the controlled evaluation risk according to the evaluation feature vector, refer to fig. 3 and the related description thereof, which are not repeated herein.
In some embodiments, the analysis module 520 may be further configured to, for one of the plurality of first platforms, determine a set of merchants on the first platform that match the target merchant, the set of merchants including at least one reference merchant; determining benchmark deviation tendency characteristics of a first platform based on the evaluation data of each reference merchant in a group of merchants on the first platform and the evaluation data of each reference merchant on at least one second platform; determining an offset tendency characteristic of the target merchant on the first platform based on the evaluation data of the target merchant on the first platform; and determining the risk of the target merchant being controlled and evaluated on the first platform based on the deviation tendency characteristics of the target merchant on the first platform and the reference deviation tendency characteristics of the first platform. For more contents of judging controlled evaluation according to the reference deviation tendency characteristics, refer to fig. 4 and the related description thereof, which are not repeated herein.
In some embodiments, the analysis module 520 may be further configured to, for each reference merchant in the set of merchants, determine a difference characteristic between the reference merchant on each of the first platform and the at least one second platform based on the evaluation data of the reference merchant on the first platform and the evaluation data of the reference merchant on the at least one second platform; performing first fusion on the difference characteristics of the reference merchant between the first platform and each of the at least one second platform, and determining the sub-reference offset tendency characteristics of the reference merchant on the first platform; and performing second fusion on the sub-reference deviation tendency characteristics respectively corresponding to at least one reference merchant in the group of merchants, and determining the reference deviation tendency characteristics of the first platform.
The reminder module 530 may be configured to send a reminder to the target merchant when there is a controlled risk of evaluation. For more contents of the prompt information, refer to fig. 2 and the related description thereof, which are not described herein again.
It should be understood that the system and its modules shown in FIG. 5 may be implemented in a variety of ways. It should be noted that the above description of the system and its modules is for convenience only and should not limit the present disclosure to the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the acquiring module, the analyzing module, and the reminding module disclosed in fig. 5 may be different modules in a system, or may be a module that implements the functions of two or more modules. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means a feature, structure, or characteristic described in connection with at least one embodiment of the specification. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics may be combined as suitable in one or more embodiments of the specification.
Additionally, the order in which elements and sequences are described in this specification, the use of numerical letters, or other designations are not intended to limit the order of the processes and methods described in this specification, unless explicitly stated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the foregoing description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into the specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.
Claims (8)
1. A big-data based retail management method, comprising:
acquiring evaluation data of a target merchant on a plurality of first platforms based on related information of the target merchant;
determining whether the target merchant is at risk of being assessed against at least one of the plurality of first platforms based on the assessment data on the plurality of first platforms, wherein the determining whether the assessment data on at least one of the plurality of platforms is at risk of being assessed against comprises:
determining a plurality of evaluation feature vectors respectively corresponding to the target merchant on the plurality of first platforms based on the evaluation data of the target merchant on the plurality of first platforms;
determining a reference evaluation feature vector according to the plurality of evaluation feature vectors;
for each of the plurality of first platforms, judging the distance between the evaluation feature vector of the first platform and the reference evaluation feature vector, wherein if the distance is greater than a threshold value, the first platform has a risk of being controlled to be evaluated;
and if the risk exists, sending prompt information to the target merchant.
2. The retail management method of claim 1, the determining whether the evaluation data on at least one of the plurality of platforms is at risk for controlled evaluation, comprising:
for one of the plurality of first platforms,
determining a set of merchants on the first platform that match the target merchant, the set of merchants including at least one reference merchant;
determining benchmark deviation tendency characteristics of the first platform based on the evaluation data of each reference merchant in the group of merchants on the first platform and the evaluation data of each reference merchant on at least one second platform;
determining an offset-propensity feature of the target merchant on the first platform based on the evaluation data of the target merchant on the first platform;
determining the risk of the target merchant being assessed on the first platform based on the offset tendency characteristics of the target merchant on the first platform and the benchmark offset tendency characteristics of the first platform.
3. A retail management method according to claim 2, wherein determining a baseline shift propensity profile for the first platform based on the rating data of each reference merchant of the set of merchants on the first platform and the rating data of the respective at least one second platform comprises:
for each reference merchant in the set of merchants,
determining a difference characteristic between the reference merchant on each of the first platform and the at least one second platform based on the reference merchant's ratings data on the first platform and the reference merchant's ratings data on the at least one second platform;
performing a first fusion on the difference features of the reference merchant between the first platform and each of the at least one second platform, and determining a sub-reference offset propensity feature of the reference merchant at the first platform;
and performing second fusion on the sub-benchmark deviation tendency characteristics respectively corresponding to at least one reference merchant in the group of merchants, and determining the benchmark deviation tendency characteristics of the first platform.
4. A big-data based retail management system, comprising:
the acquisition module is used for acquiring evaluation data of a target merchant on a plurality of first platforms based on relevant information of the target merchant;
an analysis module configured to determine whether the target merchant is at risk of controlled evaluation of the evaluation data on at least one of the plurality of first platforms based on the evaluation data on the plurality of first platforms, the analysis module further configured to:
determining a plurality of evaluation feature vectors respectively corresponding to the target merchant on the plurality of first platforms based on the evaluation data of the target merchant on the plurality of first platforms;
determining a reference evaluation feature vector according to the evaluation feature vectors;
for each of the plurality of first platforms, judging the distance between the evaluation feature vector of the first platform and the reference evaluation feature vector, and if the distance is greater than a threshold value, the first platform has a risk of being controlled to be evaluated;
and the reminding module is used for sending prompt information to the target merchant when the controlled evaluation risk exists.
5. The retail management system of claim 4, the analysis module further to:
for one of the plurality of first platforms,
determining a set of merchants on the first platform that match the target merchant, the set of merchants including at least one reference merchant;
determining a benchmark deviation tendency characteristic of the first platform based on the evaluation data of each reference merchant in the group of merchants on the first platform and the evaluation data of each reference merchant on at least one second platform;
determining an offset-propensity feature of the target merchant on the first platform based on the ratings data of the target merchant on the first platform;
determining the risk of the target merchant being assessed on the first platform based on the offset tendency characteristics of the target merchant on the first platform and the benchmark offset tendency characteristics of the first platform.
6. The retail management system of claim 5, the analysis module further to:
for each reference merchant in the set of merchants,
determining a difference characteristic between the reference merchant on each of the first platform and the at least one second platform based on the rating data of the reference merchant on the first platform and the rating data of the reference merchant on the at least one second platform;
performing a first fusion on the difference features of the reference merchant between the first platform and each of the at least one second platform, and determining a sub-reference offset propensity feature of the reference merchant at the first platform;
and performing second fusion on the sub-benchmark deviation tendency characteristics respectively corresponding to at least one reference merchant in the group of merchants, and determining the benchmark deviation tendency characteristics of the first platform.
7. A big-data based retail management apparatus comprising a processor for performing the big-data based retail management method of any one of claims 1 to 3.
8. A computer-readable storage medium storing computer instructions, which when read by a computer, cause the computer to perform the big data based retail sales management method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210266308.5A CN114626885B (en) | 2022-03-17 | 2022-03-17 | Retail management method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210266308.5A CN114626885B (en) | 2022-03-17 | 2022-03-17 | Retail management method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114626885A CN114626885A (en) | 2022-06-14 |
| CN114626885B true CN114626885B (en) | 2022-11-15 |
Family
ID=81902778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210266308.5A Active CN114626885B (en) | 2022-03-17 | 2022-03-17 | Retail management method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114626885B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260899A (en) * | 2015-10-27 | 2016-01-20 | 清华大学深圳研究生院 | Electronic business subject credibility evaluation method and system |
| CN111553696A (en) * | 2020-04-23 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Risk prompting method and device and electronic equipment |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8725597B2 (en) * | 2007-04-25 | 2014-05-13 | Google Inc. | Merchant scoring system and transactional database |
| CN103020482A (en) * | 2013-01-05 | 2013-04-03 | 南京邮电大学 | Relation-based spam comment detection method |
| SG10201505793RA (en) * | 2015-07-24 | 2017-02-27 | Mastercard International Inc | Methods and systems for ranking merchants |
| CN105955957B (en) * | 2016-05-05 | 2019-01-25 | 北京邮电大学 | The determination method and device that aspect scores in a kind of businessman's general comment |
| CN106484679B (en) * | 2016-10-20 | 2020-02-11 | 北京邮电大学 | False comment information identification method and device applied to consumption platform |
| CN108874768B (en) * | 2018-05-16 | 2019-04-16 | 山东科技大学 | A kind of e-commerce falseness comment recognition methods based on theme emotion joint probability |
| CN109409671A (en) * | 2018-09-25 | 2019-03-01 | 广州新丝路信息科技有限公司 | A kind of appraisal procedure and device of cross-border electric business enterprise |
| CN110533474A (en) * | 2019-08-30 | 2019-12-03 | 北京智云信国际信用评价有限公司 | One kind being directed to electric business user credit evaluation system |
| CN111428007B (en) * | 2020-06-08 | 2020-09-15 | 北京每日优鲜电子商务有限公司 | Cross-platform based synchronous push feedback method |
| WO2022021400A1 (en) * | 2020-07-31 | 2022-02-03 | 深圳齐心集团股份有限公司 | E-commerce comment identification and marking system |
| CN113393245A (en) * | 2021-06-21 | 2021-09-14 | 浪潮卓数大数据产业发展有限公司 | Early warning method and system for identifying order-swiping shop based on e-commerce operation data |
-
2022
- 2022-03-17 CN CN202210266308.5A patent/CN114626885B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260899A (en) * | 2015-10-27 | 2016-01-20 | 清华大学深圳研究生院 | Electronic business subject credibility evaluation method and system |
| CN111553696A (en) * | 2020-04-23 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Risk prompting method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114626885A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110874778B (en) | Abnormal order detection method and device | |
| US10846775B1 (en) | Identifying item recommendations through recognized navigational patterns | |
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| US10861054B2 (en) | Heuristic customer clustering | |
| JP2019508756A (en) | Method and apparatus for selecting and recommending objects on an electronic delivery platform | |
| CN112396433A (en) | Method and system for identifying false commodity comments based on behavior of person to be evaluated | |
| JP2019032620A (en) | Generation device, method for generation, and generation program | |
| Lestari et al. | The influence of using shopeepay and shopee paylater features on shopee user purchasing decisions during the covid-19 | |
| CN111709813A (en) | Commodity recommendation method based on big data line | |
| US20170364982A1 (en) | Systems and methods for improved apparel fit and apparel distribution | |
| KR20160129588A (en) | on-line trading intermediation system for enhancing transaction reliability | |
| CN114626885B (en) | Retail management method and system based on big data | |
| US20170083973A1 (en) | Assigning business credit scores using peer-to-peer inputs on an open online business social network | |
| CN110634015A (en) | Consumption habit analysis system based on computer software | |
| CN110866220B (en) | Selection recommending system in e-commerce activity process | |
| KR101479379B1 (en) | Method of sharing customer rate of merchandise based on social network | |
| CN115482014B (en) | Method and device for identifying false car source of second-hand car | |
| CN115797020A (en) | Retail recommendation method, system and medium based on data processing of graph database | |
| CN114219547B (en) | Method, device, equipment and storage medium for determining store ordering amount | |
| CN116402569A (en) | Commodity recommendation method, device and system based on knowledge graph and storage medium | |
| US20150170038A1 (en) | Method And System For Generating Item Recommendation | |
| KR20200041714A (en) | System and method for overseas cooperative purchase | |
| CN115187065A (en) | Garment commodity quality analysis system based on electronic commerce platform | |
| US20210342937A1 (en) | System for Providing Scores to Customers Based on Financial Data | |
| KR20190013095A (en) | System and method for trading foreign currency asset |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |