CN112085561A - Cloud platform e-commerce data processing method and system based on big data - Google Patents
Cloud platform e-commerce data processing method and system based on big data Download PDFInfo
- Publication number
- CN112085561A CN112085561A CN202010864409.3A CN202010864409A CN112085561A CN 112085561 A CN112085561 A CN 112085561A CN 202010864409 A CN202010864409 A CN 202010864409A CN 112085561 A CN112085561 A CN 112085561A
- Authority
- CN
- China
- Prior art keywords
- information
- commodity
- obtaining
- classification
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a cloud platform e-commerce data processing method and system based on big data, which are used for obtaining first picture information of a first commodity; obtaining commodity name information of a first commodity; inputting the first picture information and the commodity name information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the method comprises the steps that first picture information, commodity name information and preset sales volume grade identification information are obtained; obtaining output information of a training model, wherein the output information comprises sales volume grade information; obtaining search keyword information; judging whether the first commodity meets a first preset condition or not; when the first classification information is satisfied, obtaining first classification information; judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition or not; if the first commodity classification information does not meet the requirement, the first commodity is removed from the first classification information, and the technical effect of improving the accuracy of commodity classification is achieved.
Description
Technical Field
The invention relates to the technical field of electronic commerce, in particular to a cloud platform electronic commerce data processing method and system based on big data.
Background
The electronic commerce refers to the commerce activity which takes the information network technology as a means and takes commodity exchange as a center; it can also be understood as transaction activities and related service activities in electronic transaction mode over the internet, intranets and value added networks. The commodity classification means that commodities in a management range are collected into a whole and selected as appropriate to meet all or part of the requirements of production, circulation and consumption activities of the commodities according to a certain management purposeThe basic characteristics of the commodities are used as classification marks and are sequentially summarized into a plurality of sub-aggregates (categories) with smaller ranges and more consistent characteristics, such as large categories, medium categories, small categories and fine categories, and the range is up to the variety and the fine category, so that all the commodities in the range can be clearly distinguished and systematized.At present, in the classification of commodities by merchants, a plurality of classification data have an intersection phenomenon, so that great difficulty is caused to the classification of the commodities.
However, the applicant of the present invention finds that the prior art has at least the following technical problems:
the existing commodity classification system is numerous and complicated, so that the seller has low commodity classification accuracy and low classification speed, and the user experience is poor.
Disclosure of Invention
The embodiment of the invention provides a cloud platform e-commerce data processing method and system based on big data, solves the technical problems that a commodity classification system in the prior art is complicated, so that the seller has low commodity classification accuracy and low classification speed, and the client experience is poor, and achieves the technical effects of correcting error classification of the seller in time, reducing the seller classification burden and improving the commodity classification accuracy.
In view of the foregoing problems, embodiments of the present application are provided to provide a cloud platform e-commerce data processing method and system based on big data.
In a first aspect, the present invention provides a big data based cloud platform e-commerce data processing method, including: obtaining first picture information of a first commodity; obtaining commodity name information of the first commodity; inputting the first picture information and the commodity name information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the first picture information, the commodity name information and preset sales volume grade identification information; obtaining output information of the training model, wherein the output information comprises sales volume grade information of the first commodity; obtaining search keyword information of a consumer, wherein the search keyword information has a first association degree with the first commodity; judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information; when the first preset condition is met, obtaining first classification information of the first commodity; judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition or not; and if not, removing the first commodity from the first classification information.
In a second aspect, the present invention provides a big data based cloud platform e-commerce data processing system, including:
the first obtaining unit is used for obtaining first picture information of a first commodity;
a second obtaining unit configured to obtain commodity name information of the first commodity;
a first training unit, configured to input the first picture information and the commodity name information into a training model, where the training model is obtained through training of multiple sets of training data, and each set of training data in the multiple sets includes: the first picture information, the commodity name information and preset sales volume grade identification information;
a third obtaining unit, configured to obtain output information of the training model, where the output information includes sales level information of the first commodity;
a fourth obtaining unit, configured to obtain search keyword information of a consumer, where the search keyword information has a first degree of association with the first product;
the first judging unit is used for judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information;
a fifth obtaining unit, configured to obtain first classification information of the first commodity when the first preset condition is satisfied;
a second judging unit configured to judge whether a second degree of association between the first classification information and the search keyword information satisfies a second preset condition;
and the first execution unit is used for removing the first commodity from the first classification information if the first commodity does not meet the first classification information.
In a third aspect, the present invention provides a big data based cloud platform e-commerce data processing system, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
according to the cloud platform e-commerce data processing method and system based on the big data, the first picture information of the first commodity and the commodity name information of the first commodity are input into the training model, so that the sales volume grade information of the first commodity is obtained, the sales volume grade of the commodity is more accurately evaluated, the change data of the sales condition of the commodity can be monitored in real time, whether the classification system of the commodity is correct or not is identified by combining the search keyword information and the first classification information of a consumer, the technical problem that the existing commodity classification system is numerous and complicated, the classification accuracy of a seller to the commodity is low, the classification speed is low, and the user experience is poor is solved, the technical effects that the error classification of the seller is corrected in time, the burden of the seller in classification is reduced, and the accuracy of commodity classification is improved are achieved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Fig. 1 is a schematic flow chart of a cloud platform e-commerce data processing method based on big data according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a method for processing electronic commerce data on a cloud platform based on big data according to an embodiment of the present invention to prevent an inappropriate commodity from affecting user health;
fig. 3 is a schematic flow chart of a cloud platform e-commerce data processing method based on big data according to an embodiment of the present invention, in order to correct errors of merchants in time;
fig. 4 is a schematic flowchart of a big data based cloud platform e-commerce data processing method for helping a consumer perform e-commerce better in an embodiment of the present invention;
FIG. 5 is a schematic flowchart illustrating a training model in a cloud platform e-commerce data processing method based on big data according to an embodiment of the present invention;
fig. 6 is a flow chart illustrating a process of more accurate classification of a commodity in the cloud platform electronic commerce data processing method based on big data according to the embodiment of the present invention;
fig. 7 is a schematic flow chart of a method for processing big data-based cloud platform e-commerce data according to an embodiment of the present invention, in order to give correct inventory guidance to merchants in time;
FIG. 8 is a schematic structural diagram of a big data based cloud platform e-commerce data processing system according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of another exemplary electronic device in an embodiment of the present invention.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a first training unit 13, a third obtaining unit 14, a fourth obtaining unit 15, a first judging unit 16, a fifth obtaining unit 17, a second judging unit 18, a first executing unit 19, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 306.
Detailed Description
The embodiment of the invention provides a cloud platform e-commerce data processing method and system based on big data, which are used for solving the technical problems that the existing commodity classification system is complicated, so that the seller has low commodity classification accuracy and low classification speed, and the client experience is poor, and achieving the technical effects of correcting error classification of the seller in time, reducing the seller classification burden and improving the commodity classification accuracy. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
The electronic commerce refers to the commerce activity which takes the information network technology as a means and takes commodity exchange as a center; it can also be understood as transaction activities and related service activities in electronic transaction mode over the internet, intranets and value added networks. The commodity classification means that, for satisfying all or part of the needs of commodity production, distribution and consumption activities for a certain management purpose, a commodity set total in a management range is gradually summarized into a plurality of sub-aggregates (categories) with smaller ranges and more consistent characteristics by using selected proper commodity basic characteristics as classification marks.At present, in the classification of commodities by merchants, a plurality of classification data have an intersection phenomenon, so that great difficulty is caused to the classification of the commodities.
In order to solve the technical problems, the technical scheme provided by the invention has the following general idea:
the embodiment of the application provides a cloud platform e-commerce data processing method based on big data, which comprises the following steps: obtaining first picture information of a first commodity; obtaining commodity name information of the first commodity; inputting the first picture information and the commodity name information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the first picture information, the commodity name information and preset sales volume grade identification information; obtaining output information of the training model, wherein the output information comprises sales volume grade information of the first commodity; obtaining search keyword information of a consumer, wherein the search keyword information has a first association degree with the first commodity; judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information; when the first preset condition is met, obtaining first classification information of the first commodity; judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition or not; and if not, removing the first commodity from the first classification information.
The embodiment of the application provides a cloud platform electronic commerce data processing method based on big data, which is applied to a data cloud platform of an electronic commerce center, and the data cloud platform is in data association with mobile phone software of a user, such as shopping software, trip software, ordering software and the like. The various data obtained in the embodiment of the invention are automatically matched, associated and processed from the database in the shopping software through a computer communication technology. Furthermore, various data can be efficiently and automatically matched, associated and processed through a computer technology, so that the technical problem to be solved by the invention is solved, and the technical effect of the invention is realized.
After the fundamental principle of the present application is introduced, the technical solutions of the present invention are described in detail with reference to the accompanying drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
Example one
Fig. 1 is a schematic flow chart of a cloud platform e-commerce data processing method based on big data in an embodiment of the present invention. As shown in fig. 1, an embodiment of the present invention provides a method for processing electronic commerce data on a cloud platform based on big data, where the method includes:
step 100: first picture information of a first commodity is obtained.
Specifically, the first commodity is a product sold by a merchant on an e-commerce platform, that is, the merchant can set up an online store on the e-commerce platform, and when a user browses the online store, the user can purchase a commodity required in the online store. The e-commerce platform can be a network trading platform such as Taobao, Wei-Ting, Jingdong and the like. The first picture information is characteristic information of the first commodity, and may include appearance, quality, function, package and the like of the first commodity. For example, when the first product is a red cashmere sweater, the first picture information includes the appearance, color, quality, etc. of the clothes. The mode that further adopts the first picture information to first commodity to carry out the analysis filters out irregular information for the first picture information after handling is more regular, the model study of being convenient for, and then promotes the model and to the accuracy of characteristic portrait information study, promotes data processing speed, so that improve the effect of the accuracy of commodity classification.
Step 200: and obtaining commodity name information of the first commodity.
Specifically, the commodity name information is title information of the first commodity, that is, when the first commodity is offered in the e-commerce platform for sale, the seller needs to name the sold commodity in order to increase the probability that the commodity is searched. That is, the keywords describing the precise goods are combined into a title in a maximized way, so that as many buyers as possible can search. In actual use, the title information of the commodity can also be a piece of link information, so that the title information of the commodity can be copied and then sent to friends of buyers, and the purpose of sharing the commodity is achieved. For example, if the first commodity is a woman's garment, the brand is a korean locker mini-suit, and the title of the garment on treasure can be obtained as korean locker 2020 autumn dressing new style cabinet certified seven-sleeve fashion mini-suit/jacket, so that the buyer can see the garment when searching for words such as "korean locker mini-suit", "korean locker jacket", "korean locker certified product", and the like.
Step 300: inputting the first picture information and the commodity name information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the first picture information, the commodity name information and the preset sales volume grade identification information.
Specifically, the training model is a neural network model in a machine learning model, and the machine learning model can continuously learn through a large amount of data, further continuously correct the model, and finally obtain satisfactory experience to process other data. The machine model is obtained by training a plurality of groups of training data, and the process of training the neural network model by the training data is essentially a process of supervised learning. The training model in the embodiment of the application is obtained by utilizing machine learning training through a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the system comprises first picture information, commodity name information and preset sales volume grade identification information. And the preset sales level identification information is used as supervision data.
Further, in order to enhance the data accuracy, correct the error classification of the seller in time, reduce the burden of the seller in classification, and improve the accuracy of the commodity classification, as shown in fig. 2, step 300 in the embodiment of the present application further includes:
step 310: obtaining evaluation information of the first commodity within preset time;
step 320: acquiring first preset keyword information, second preset keyword information and third preset keyword information;
step 330: screening the evaluation information of the first commodity according to the first preset keyword information, the second preset keyword information and the third preset keyword information to obtain a first evaluation subset, a second evaluation subset and a third evaluation subset;
step 340: obtaining the order quantity of the first commodity within the preset time;
step 350: setting sales volume grade identification information according to the proportion relation between the first evaluation subset, the second evaluation subset and the third evaluation subset and the order volume of the first commodity;
step 360: and inputting the sales level identification information as supervision data into each group of training data, performing supervision learning on the first picture information of the first commodity and the commodity name information of the first commodity, and determining that the output information of the training model reaches a convergence state.
Specifically, the seller classification load is reduced and the commodity classification accuracy is improved in order to accurately judge the sales volume grade of the commodity. First, the evaluation information of the buyer on the first commodity needs to be collected within a preset time, where the preset time is a certain time selected according to actual needs, for example, within three months, within a half year, within a year, and the like, and this embodiment is not limited in particular. The evaluation information is a process of evaluating the use value of the user according to the performance, specification, material, service life, appearance and the like of the specific commodity after the user purchases the first commodity. And then obtaining preset first preset keyword information, second preset keyword information and third preset keyword information. The first preset keyword information is a keyword related to the positive evaluation information, that is, the favorable evaluation information issued by the consumer, such as "like", "satisfied", "will buy", etc., can be determined by the first preset keyword information. The second preset keyword information is a keyword related to the neutral evaluation information, that is, the neutral attitude of the evaluation information issued by the consumer can be determined by the second preset keyword information, for example, "normal", "just" or "return". The third preset keyword information is related to the keywords related to the negative evaluation information, that is, the bad evaluation information issued by the consumer, such as "difficult to use", "dislike", "dissatisfaction", "poor quality", etc., can be determined by the third preset keyword information. And then screening all evaluation information of the first commodity according to the first preset keyword information, the second preset keyword information and the third preset keyword information to obtain a first evaluation subset representing good evaluation, a second evaluation subset representing neutral evaluation and a third evaluation subset representing poor evaluation. Further, the total order quantity of the first commodities in the preset time is obtained, a first proportion of the first evaluation subset to the order quantity, a second proportion of the second evaluation subset to the order quantity and a third proportion of the third evaluation subset to the order quantity can be calculated respectively, and then the sales level identification information is set according to the proportion relation. Specifically, the method comprises the following steps: the sales level identification information is set by selecting the largest of the first, second, and third percentages, and, for example, when the first percentage is the largest, the sales level of the first commodity is high, when the second percentage is the largest, the sales level of the first commodity is normal, and when the third percentage is the largest, the sales level of the first commodity is low.
Further, sales level identification information is used as supervision data and is input into each group of training data, supervision learning is carried out on first picture information of a first commodity and commodity name information of the first commodity, the sales level information is compared with an output result of the training model, when the sales level information is consistent with the output result of the training model, the supervision learning of the group of data is finished, and the supervision learning of the next group of data is carried out; when the output result is inconsistent with the sales volume grade information of the first commodity, the training model carries out self-correction until the output result is consistent with the sales volume grade information of the first commodity, the supervised learning of the group is finished, and the supervised learning of the next group of data is carried out; and (4) through supervised learning of a large amount of data, enabling the output result of the machine learning model to reach a convergence state, and finishing the supervised learning. Through the process of supervising and learning the training model, the sales volume grade identification information of the first commodity output by the training model is more accurate, the burden of seller classification is reduced, and the accuracy of commodity classification is improved.
Step 400: obtaining output information of the training model, wherein the output information comprises sales volume grade information of the first commodity.
Specifically, the sales volume grade information of the first commodity is rated according to the first picture information of the first commodity and the commodity name information of the first commodity. The sales level information of the first commodity can be divided into three aspects: high sales ratings, general sales ratings and low sales ratings. The high sales volume level indicates that the selling condition of the first commodity and the user evaluation condition are in a good state; the sales volume grade generally indicates that the selling condition of the first commodity and the user evaluation condition are in a general level state; the low sales level indicates that the first commodity is sold and the user evaluation condition is in a poor state. The method comprises the steps of inputting a training model according to first picture information of a first commodity and commodity name information of the first commodity to obtain preset sales volume grade identification information, so that the obtained sales volume grade information of the first commodity is accurate, error correction can be timely carried out on error classification of a seller, the burden of the seller in classification is reduced, and the accuracy of commodity classification is improved.
Step 500: obtaining search keyword information of a consumer, wherein the search keyword information has a first association degree with the first commodity.
Specifically, the search keyword is keyword information related to the product, which is input by the consumer according to the need when purchasing the product. Therefore, the search keyword information has a certain degree of association with the first product, that is, the search keyword information is information related to the first product. For example, when a user wants to purchase a television, the user can input information related to the television as needed, such as "millet television", "super-definition television", and the like.
Step 600: judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information;
specifically, whether the first commodity meets a first preset condition can be further judged according to the sales volume grade information and the search keyword information of the first commodity, wherein the first preset condition is whether the quantity sold by the preset first commodity according to the search keyword information meets a threshold requirement, namely, under the sales volume grade of the first commodity, part of the sold commodity quantity can be purchased by a user through self search as required, part of the sold commodity quantity can be purchased by the user according to links shared by others, part of the sold commodity quantity can be recommended to the first commodity related to the sold commodity when the user browses the related commodity, and the like. Therefore, at this time, it is necessary to determine whether the first product is sold by the user according to the search keyword, and the ratio of the sold amount to the sales amount level satisfies a certain threshold requirement. For example, when the first product is a sweater, the sold volume is 1000 pieces, and it needs to be determined that the volume sold by the consumer by searching for information related to the sweater, such as "sweater" and "academic style sweater", for example, the volume sold by the consumer by searching for information related to the sweater is 600 pieces, and when the threshold is set to 50%, it indicates that the first product at this time satisfies the first preset condition.
Step 700: when the first preset condition is met, obtaining first classification information of the first commodity;
specifically, when the first commodity meets a first preset condition, classification information of the first commodity is obtained, wherein the first classification information is classification of the first commodity in a merchant store according to a certain rule for facilitating merchant organization and user search in the store. For example, when the shop is a clothing shop, the shop can be classified according to the change of seasons and fashion, the shop can be divided into upper clothes and lower clothes, the upper clothes can be further divided into t-shirts, sweaters, coats and the like, the lower clothes can be further divided into skirts, jeans, casual pants and the like, and the product can be conveniently checked by target consumer groups. There are other specialized industries that may be classified according to performance, such as the electronics industry.
Step 800: judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition or not;
step 900: and if not, removing the first commodity from the first classification information.
Specifically, according to the obtained first classification information, a second association degree between the first classification information and the search keyword information is further obtained, wherein the second association degree is a similarity degree between the first classification information and the search keyword information. And further judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition, wherein the second preset condition is a preset threshold requirement of the second association degree between the first classification information and the search keyword information. And when the second association degree between the first commodity and the second commodity does not meet a second preset condition, the classification information to which the first commodity belongs does not belong to the first classification information, and the first commodity needs to be removed from the first classification information. For example, a search keyword input by a user for a first product in an e-commerce platform is a sweater, the sales volume ratio of the first product in a store sold by the user for searching the sweater reaches the ratio threshold requirement, but the first classification information of the first product in the store is a sweater, and the second association degree between the sweater and the search keyword sweater does not satisfy the second preset condition, that is, the classification information of the first product by the merchant at this time is wrong, and the first product needs to be removed from the first classification information. Whether the classification of the first commodity is correct or not is considered based on the first picture information and the commodity name information, more, the sales volume grade information of the user, the search keyword information of the consumer and the first classification information of the first commodity are comprehensively considered, and then the classification of the first commodity is accurately judged. Therefore, the technical effects of timely judging and correcting the error classification of the seller, reducing the burden of the seller in classification and improving the accuracy of commodity classification are achieved.
Further, in order to detect the picture information in real time and prevent the effect of the inappropriate commodity from affecting the health of the user, as shown in fig. 2, step 100 in the embodiment of the present application further includes:
step 110: judging whether the first picture information meets a third preset condition or not;
step 120: if so, identifying characters in the first picture information, and then obtaining component information of the first commodity;
step 130: obtaining personal label information of a target user;
step 140: judging whether the first commodity meets a fourth preset condition or not according to the component information and the personal label information;
step 140: and if not, sending warning information to the target user when the target user browses the first commodity.
Specifically, after the first picture information is obtained, it is determined whether the first picture information meets a third preset condition, where the third preset condition is whether the first picture information includes related characters, and the characters include chinese and foreign language. When the first commodity contains the text content, the component information of the first commodity is collected after the text in the first picture information is identified, wherein the component information is each component material of the first commodity. Furthermore, personal tag information of a target user is required to be obtained, the target user is a user searching or browsing the first commodity, the personal tag information is portrait information of the target user, and a user information complete picture is abstracted by acquiring personal information of the user, such as social attribute, living habits, consumption information and other data information. For example, when a target user often purchases and browses commodities as mother-infant products on an e-commerce platform, a mom can be used as a label of the user; if the first user frequently purchases and browses commodities as game products on the E-commerce platform, the E-contest fan can be used as a label of the user. And then, whether the first commodity meets the fourth preset condition or not is judged by combining the component information and the personal label information, namely whether the first commodity is suitable for the target user or not is judged. If not, the first commodity is not suitable for the target user, so when the target user browses the first commodity, warning information is sent to the target user. For example, when the first commodity is a piece of polyester clothes, but the user can only wear pure cotton clothes due to the allergic constitution, the clothes are not suitable for the user, and when the user browses the clothes, warning information needs to be sent to the user, so that the effect of preventing the user from purchasing the unsuitable product and influencing the body health is achieved.
Further, in order to correct the error classification of the merchant in time and achieve the effect of improving the accuracy of the commodity classification, as shown in fig. 3, step 900 in the embodiment of the present application further includes:
step 910: obtaining a first category label according to the search keyword information;
step 920: according to the first commodity label information, second classification information is determined from a preset commodity classification list;
step 930: and adjusting the first commodity into the second classification information.
Specifically, a first item label of the first commodity is obtained according to the search keyword information of the consumer, wherein the first item label is the first item label information of the first commodity determined according to the search keyword information. And then according to the first commodity label information, determining second classification information from a preset commodity classification list, and finally adjusting the first commodity from the first classification list to the second classification list. As described above, when the first commodity is a sweater, the search keyword information input by the user is a autumn college wind sweater, the first category label is the college wind sweater, the second category information obtained from the store preset commodity classification list is the sweater, and the sweater is adjusted from the sweater list to the sweater list, so that the error classification of the merchant can be corrected in time, and the effect of improving the accuracy of the commodity classification is achieved.
Further, to further help the consumer to better perform the e-commerce activity and greatly improve the effect of customer satisfaction, as shown in fig. 4, step 930 of the embodiment of the present application further includes:
step 9301: obtaining first purchase information of a target user;
step 9302: obtaining inventory information of the first commodity;
step 9303: judging whether the inventory information meets a fifth preset condition or not according to the first purchase information;
step 9304: if not, obtaining first position information of the target user;
step 9305: obtaining store information within a predetermined distance from the first location information;
step 9306: obtaining first route information according to the store information and the first position information;
step 9307: and sending the first route information to the target user.
Specifically, first purchase information of a target user is obtained, wherein the first purchase information is ordering information of a first commodity of the user on an e-commerce platform, inventory information of the first commodity is further obtained, and whether the inventory information meets a fifth preset condition is judged, wherein the fifth preset condition is judging whether the inventory information can meet ordering information of the target user. If the current position of the target user is not satisfied, it is indicated that the stock of the first commodity cannot satisfy the user requirement by the merchant, and at this time, first position information of the target user needs to be obtained next, wherein the first position information is the current position of the target user and can be a home and a company, and then store information within a certain distance from the current position is obtained according to the current position of the target user, that is, optimal store information is found for the user according to the position of the target user, and the store information is a store which sells the first commodity and of which the stock satisfies the user requirement. And then obtaining the optimal route information of the user for going to the store according to the store information and the first position information, and finally sending the first route information to the target user, so that the user can go to the store according to the route to purchase the first commodity after receiving the first route information. The effects of helping consumers to better perform E-commerce activities and greatly improving the customer satisfaction are further achieved.
Further, in order to achieve the effects of classifying commodities more accurately and improving the classification efficiency, as shown in fig. 6, step 930 in this embodiment of the present application further includes:
step 9308: obtaining the browsing duration of the first commodity;
step 9309: obtaining the sharing amount of the first commodity;
step 9310: obtaining a growth score of the first commodity according to a preset strategy and the browsing duration, the sharing amount and the sales level;
step 9311: and determining the ordering of the first commodity according to the growth score of the first commodity.
Specifically, the browsing duration is the total duration of the first commodity browsed and staying on the first commodity by the user, the sharing amount is the total amount of the first commodity shared by the user through social software such as WeChat, short message, microblog and QQ, and the growth score of the first commodity is obtained according to the browsing duration, the sharing amount and the sales level and according to a preset strategy, wherein the preset strategy is the weight coefficient of the preset browsing duration, the sharing amount and the sales level. Therefore, the growth score of the first commodity can be calculated according to the first weight coefficient, the second weight coefficient and the third weight coefficient which respectively correspond to the browsing duration, the sharing amount and the sales level. The ranking of the first item may then be determined based on the calculated growth score. Further, the commodity classification is more accurate, and therefore the classification efficiency is improved.
Further, in order to achieve the effect of timely giving correct inventory amount guidance to the merchant and improving the user experience, as shown in fig. 7, step 930 in the embodiment of the present application further includes:
step 9312: obtaining a second commodity according to the first commodity, wherein the second commodity information is a new product, and the second commodity and the first commodity have a third degree of association;
step 9313: obtaining a first price for the first item;
step 9314: obtaining a second price for the second item;
step 9315: judging whether the first price and the second price are within a preset threshold value;
step 9316: if so, obtaining the predicted sales grade of the second commodity according to the sales grade information of the first commodity;
step 9317: determining a production capacity of the second commodity based on the forecasted sales level.
Specifically, a second commodity related to the first commodity is obtained according to the first commodity, the second commodity is a product to be updated of a store, the second commodity has certain similarity with the first commodity, and the similarity meets a certain similarity threshold requirement. Further, a first price of the first commodity and a second price of the second commodity are obtained, and then whether the difference between the price of the first commodity and the price of the second commodity is within a preset price threshold value or not is judged, that is, when the price difference between the two prices is not large, a predicted sales level of the second commodity can be obtained through prediction according to the sales level information of the first commodity, and then the production of the second commodity can be determined according to the sales of the first commodity. For example, when the first product is a fleece, the second product is a non-fleece and the similarity of the two clothes is high, the price of the first product is 200 yuan, the price of the second product is 170 yuan, if the preset price threshold is set to be 50 yuan, the difference between the two prices is within the price threshold range, so that when the sales level of the first product is high, for example, 5000 items are sold, the sales of the second product can be predicted, and the approximate production of the second product can be predicted, thereby achieving the effect of timely guiding the correct stock quantity of the merchant.
Example two
Based on the same inventive concept as the cloud platform e-commerce data processing method based on big data in the foregoing embodiment, the present invention further provides a cloud platform e-commerce data processing method system based on big data, as shown in fig. 8, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first picture information of a first commodity;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain commodity name information of the first commodity;
a first training unit 13, where the first training unit 13 is configured to input the first picture information and the commodity name information into a training model, where the training model is obtained through training of multiple sets of training data, and each set of training data in the multiple sets includes: the first picture information, the commodity name information and preset sales volume grade identification information;
a third obtaining unit 14, where the third obtaining unit 14 is configured to obtain output information of the training model, where the output information includes sales level information of the first commodity;
a fourth obtaining unit 15, where the fourth obtaining unit 15 is configured to obtain search keyword information of a consumer, where the search keyword information has a first association degree with the first product;
a first judging unit 16, where the first judging unit 16 is configured to judge whether the first commodity meets a first preset condition according to the sales level information of the first commodity and the search keyword information;
a fifth obtaining unit 17, where the fifth obtaining unit 17 is configured to obtain first classification information of the first commodity when the first preset condition is met;
a second judging unit 18, where the second judging unit 18 is configured to judge whether a second degree of association between the first classification information and the search keyword information satisfies a second preset condition;
a first executing unit 19, where the first executing unit 19 is configured to remove the first commodity from the first classification information if the first classification information is not satisfied.
Further, the system further comprises:
a third judging unit, configured to judge whether the first picture information satisfies a third preset condition;
a sixth obtaining unit, configured to, if the first commodity component information is satisfied, obtain component information of the first commodity after recognizing characters in the first picture information;
a seventh obtaining unit configured to obtain personal tag information of a target user;
a fourth judging unit, configured to judge whether the first commodity meets a fourth preset condition according to the component information and the personal tag information;
and the second execution unit is used for sending warning information to the target user when the target user browses the first commodity if the first commodity does not meet the requirement.
Further, the system further comprises:
an eighth obtaining unit, configured to obtain a first category label according to the search keyword information;
the first determining unit is used for determining second classification information from a preset commodity classification list according to the first commodity label information;
a third execution unit, configured to adjust the first commodity into the second classification information.
Further, the system further comprises:
a ninth obtaining unit for obtaining first purchase information of a target user;
a tenth obtaining unit configured to obtain inventory information of the first product;
a fifth judging unit, configured to judge whether the inventory information satisfies a fifth preset condition according to the first purchase information;
an eleventh obtaining unit, configured to obtain first location information of the target user if the first location information does not meet the first location information;
a twelfth obtaining unit configured to obtain store information within a predetermined distance from the first position information;
a thirteenth obtaining unit, configured to obtain first route information according to the store information and the first location information;
a fourth execution unit, configured to send the first route information to the target user.
Further, the feature image information and the vital sign information are input into a training model, wherein the training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets includes:
a fourteenth obtaining unit, configured to obtain evaluation information of the first commodity within a preset time;
a fifteenth obtaining unit, configured to obtain first preset keyword information, second preset keyword information, and third preset keyword information;
a sixteenth obtaining unit, configured to obtain a first evaluation subset, a second evaluation subset, and a third evaluation subset after screening the evaluation information of the first commodity according to the first preset keyword information, the second preset keyword information, and the third preset keyword information;
a seventeenth obtaining unit, configured to obtain the order amount of the first commodity within the preset time;
the first setting unit is used for setting sales volume grade identification information according to the proportion relation among the first evaluation subset, the second evaluation subset and the third evaluation subset and the order volume of the first commodity;
and the second training unit is used for inputting the sales level identification information serving as supervision data into each group of training data, performing supervision learning on the first picture information of the first commodity and the commodity name information of the first commodity, and determining that the output information of the training model reaches a convergence state.
Further, the system further comprises:
an eighteenth obtaining unit, configured to obtain a browsing duration of the first commodity;
a nineteenth obtaining unit, configured to obtain a share amount of the first commodity;
a twentieth obtaining unit, configured to obtain a growth score of the first commodity according to a preset policy, according to the browsing duration, the sharing amount, and the sales level;
a second determining unit, configured to determine a ranking of the first item according to the growth score of the first item.
Further, the system further comprises:
a twenty-first obtaining unit, configured to obtain a second commodity according to the first commodity, where the second commodity information is a new last product, and the second commodity and the first commodity have a third degree of association;
a twenty-second obtaining unit for obtaining a first price of the first item;
a twenty-third obtaining unit for obtaining a second price of the second item;
a sixth judging unit configured to judge whether the first price and the second price are within a preset threshold;
a twenty-fourth obtaining unit, configured to, if the sales volume level information of the first commodity is present, obtain a predicted sales volume level of the second commodity according to the sales volume level information of the first commodity;
a third determining unit for determining the production amount of the second commodity according to the predicted sales level.
Various changes and specific examples of the big-data-based cloud platform e-commerce data processing method in the first embodiment of fig. 1 are also applicable to the big-data-based cloud platform e-commerce data processing system in the present embodiment, and through the foregoing detailed description of the big-data-based cloud platform e-commerce data processing method, those skilled in the art can clearly know the implementation method of the big-data-based cloud platform e-commerce data processing system in the present embodiment, so for the brevity of the description, detailed description is not repeated here.
EXAMPLE III
Based on the same inventive concept as the big data based cloud platform e-commerce data processing method in the foregoing embodiment, the present invention further provides an exemplary electronic device, as shown in fig. 9, including a memory 304, a processor 302, and a computer program stored in the memory 304 and operable on the processor 302, wherein the processor 302, when executing the program, implements the steps of any one of the big data based cloud platform e-commerce data processing methods described above.
Where in fig. 9 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
according to the cloud platform e-commerce data processing method and system based on the big data, provided by the embodiment of the invention, first picture information of a first commodity is obtained; obtaining commodity name information of the first commodity; inputting the first picture information and the commodity name information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the first picture information, the commodity name information and preset sales volume grade identification information; obtaining output information of the training model, wherein the output information comprises sales volume grade information of the first commodity; obtaining search keyword information of a consumer, wherein the search keyword information has a first association degree with the first commodity; judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information; when the first preset condition is met, obtaining first classification information of the first commodity; judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition or not; if the first commodity classification information does not meet the requirement, the first commodity is removed from the first classification information, so that the technical problems that in the prior art, a commodity classification system is numerous and complicated, the seller has low commodity classification accuracy and low classification speed, and the user experience is poor are solved, and the technical effects of correcting error classification of the seller in time, reducing the seller classification burden and improving the commodity classification accuracy are achieved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A cloud platform e-commerce data processing method based on big data is characterized by comprising the following steps:
obtaining first picture information of a first commodity;
obtaining commodity name information of the first commodity;
inputting the first picture information and the commodity name information into a training model, wherein the training model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups comprises: the first picture information, the commodity name information and preset sales volume grade identification information;
obtaining output information of the training model, wherein the output information comprises sales volume grade information of the first commodity;
obtaining search keyword information of a consumer, wherein the search keyword information has a first association degree with the first commodity;
judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information;
when the first preset condition is met, obtaining first classification information of the first commodity;
judging whether a second association degree between the first classification information and the search keyword information meets a second preset condition or not;
and if not, removing the first commodity from the first classification information.
2. The method of claim 1, wherein after obtaining the first picture information for the first article, the method further comprises:
judging whether the first picture information meets a third preset condition or not;
if so, identifying characters in the first picture information, and then obtaining component information of the first commodity;
obtaining personal label information of a target user;
judging whether the first commodity meets a fourth preset condition or not according to the component information and the personal label information;
and if not, sending warning information to the target user when the target user browses the first commodity.
3. The method of claim 1, wherein after removing the first item from the first classification information if not satisfied, the method further comprises:
obtaining a first category label according to the search keyword information;
according to the first commodity label information, second classification information is determined from a preset commodity classification list;
and adjusting the first commodity into the second classification information.
4. The method of claim 3, wherein after adjusting the first item into the second classification information, the method further comprises:
obtaining first purchase information of a target user;
obtaining inventory information of the first commodity;
judging whether the inventory information meets a fifth preset condition or not according to the first purchase information;
if not, obtaining first position information of the target user;
obtaining store information within a predetermined distance from the first location information;
obtaining first route information according to the store information and the first position information;
and sending the first route information to the target user.
5. The method of claim 1, wherein the inputting the first picture information and the brand name information into a training model, wherein the training model is obtained by training a plurality of sets of training data, each of the plurality of sets of training data comprising: the first picture information, the commodity name information and the preset sales volume grade identification information include:
obtaining evaluation information of the first commodity within preset time;
acquiring first preset keyword information, second preset keyword information and third preset keyword information;
screening the evaluation information of the first commodity according to the first preset keyword information, the second preset keyword information and the third preset keyword information to obtain a first evaluation subset, a second evaluation subset and a third evaluation subset;
obtaining the order quantity of the first commodity within the preset time;
setting sales volume grade identification information according to the proportion relation between the first evaluation subset, the second evaluation subset and the third evaluation subset and the order volume of the first commodity;
and inputting the sales level identification information as supervision data into each group of training data, performing supervision learning on the first picture information of the first commodity and the commodity name information of the first commodity, and determining that the output information of the training model reaches a convergence state.
6. The method of claim 3, wherein prior to adjusting the first item into the second classification information, further comprising:
obtaining the browsing duration of the first commodity;
obtaining the sharing amount of the first commodity;
obtaining a growth score of the first commodity according to a preset strategy and the browsing duration, the sharing amount and the sales level;
and determining the ordering of the first commodity according to the growth score of the first commodity.
7. The method of claim 3, wherein after adjusting the first item into the second classification information, the method further comprises:
obtaining a second commodity according to the first commodity, wherein the second commodity information is a new product, and the second commodity and the first commodity have a third degree of association;
obtaining a first price for the first item;
obtaining a second price for the second item;
judging whether the first price and the second price are within a preset threshold value;
if so, obtaining the predicted sales grade of the second commodity according to the sales grade information of the first commodity;
determining a production capacity of the second commodity based on the forecasted sales level.
8. A big data based cloud platform e-commerce data processing system, the system comprising:
the first obtaining unit is used for obtaining first picture information of a first commodity;
a second obtaining unit configured to obtain commodity name information of the first commodity;
a first training unit, configured to input the first picture information and the commodity name information into a training model, where the training model is obtained through training of multiple sets of training data, and each set of training data in the multiple sets includes: the first picture information, the commodity name information and preset sales volume grade identification information;
a third obtaining unit, configured to obtain output information of the training model, where the output information includes sales level information of the first commodity;
a fourth obtaining unit, configured to obtain search keyword information of a consumer, where the search keyword information has a first degree of association with the first product;
the first judging unit is used for judging whether the first commodity meets a first preset condition or not according to the sales volume grade information of the first commodity and the search keyword information;
a fifth obtaining unit, configured to obtain first classification information of the first commodity when the first preset condition is satisfied;
a second judging unit configured to judge whether a second degree of association between the first classification information and the search keyword information satisfies a second preset condition;
and the first execution unit is used for removing the first commodity from the first classification information if the first commodity does not meet the first classification information.
9. A big data based cloud platform e-commerce data processing system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010864409.3A CN112085561A (en) | 2020-08-25 | 2020-08-25 | Cloud platform e-commerce data processing method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010864409.3A CN112085561A (en) | 2020-08-25 | 2020-08-25 | Cloud platform e-commerce data processing method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112085561A true CN112085561A (en) | 2020-12-15 |
Family
ID=73729582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010864409.3A Pending CN112085561A (en) | 2020-08-25 | 2020-08-25 | Cloud platform e-commerce data processing method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085561A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358821A (en) * | 2021-12-27 | 2022-04-15 | 创优数字科技(广东)有限公司 | Commodity detail feature extraction method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596656A (en) * | 2018-04-10 | 2018-09-28 | 王大江 | A kind of method and apparatus of intelligent shopping trolley of the structure based on big data analysis |
| CN108876488A (en) * | 2018-08-30 | 2018-11-23 | 尹庆伟 | A kind of data processing method and device |
| CN110807691A (en) * | 2019-10-31 | 2020-02-18 | 深圳市云积分科技有限公司 | Cross-commodity-class commodity recommendation method and device |
| CN110969512A (en) * | 2019-12-02 | 2020-04-07 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
-
2020
- 2020-08-25 CN CN202010864409.3A patent/CN112085561A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596656A (en) * | 2018-04-10 | 2018-09-28 | 王大江 | A kind of method and apparatus of intelligent shopping trolley of the structure based on big data analysis |
| CN108876488A (en) * | 2018-08-30 | 2018-11-23 | 尹庆伟 | A kind of data processing method and device |
| CN110807691A (en) * | 2019-10-31 | 2020-02-18 | 深圳市云积分科技有限公司 | Cross-commodity-class commodity recommendation method and device |
| CN110969512A (en) * | 2019-12-02 | 2020-04-07 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358821A (en) * | 2021-12-27 | 2022-04-15 | 创优数字科技(广东)有限公司 | Commodity detail feature extraction method and device, computer equipment and storage medium |
| CN114358821B (en) * | 2021-12-27 | 2023-06-30 | 创优数字科技(广东)有限公司 | Commodity detail feature extraction method, commodity detail feature extraction device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8510298B2 (en) | Method for relevancy ranking of products in online shopping | |
| US8762226B2 (en) | Item discovery tools and methods for shopping in an electronic commerce environment | |
| WO2013016503A1 (en) | Providing social product recommendations | |
| CN110969512B (en) | Commodity recommendation method and device based on user purchasing behavior | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| CN110807669B (en) | Cross-platform user information management method and device | |
| US11587028B2 (en) | Computer system for optimizing garment inventory of retailer based on shapes of users | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| CN110880061A (en) | Commodity hand price risk supervision method and system | |
| CN112424812A (en) | Calculating user-specific item-related values on an electronic processing platform | |
| CN112085561A (en) | Cloud platform e-commerce data processing method and system based on big data | |
| Jianjun | Research on collaborative filtering recommendation algorithm based on user behavior characteristics | |
| CN110020918B (en) | Recommendation information generation method and system | |
| CN108074124A (en) | Group purchase reservation system and method | |
| CN110782325B (en) | Member information recommendation method and device | |
| KR102582813B1 (en) | Method and apparatus for providing personalized recommendation service for offline purchase | |
| Saricam et al. | Determination of priorities in apparel purchasing from private sale websites | |
| CN114240545A (en) | Recommendation method, device and equipment for similar commodities and storage medium | |
| CN107341161A (en) | A kind of information query method and device | |
| CN113792220A (en) | Target object recommendation method and device, computer equipment and storage medium | |
| CN111160982A (en) | Merchant joint marketing method and device based on shopping social contact | |
| CN110766478A (en) | Method and device for improving user connectivity | |
| Harale et al. | Small Series Fashion Supplier Selection Using MCDM Methods | |
| CN112819570B (en) | Intelligent commodity collocation recommendation method based on machine learning | |
| US20230237552A1 (en) | Methods and apparatus for recommending substitutions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201215 |