CN111507786A - Data processing method, device and equipment - Google Patents
Data processing method, device and equipment Download PDFInfo
- Publication number
- CN111507786A CN111507786A CN201910092622.4A CN201910092622A CN111507786A CN 111507786 A CN111507786 A CN 111507786A CN 201910092622 A CN201910092622 A CN 201910092622A CN 111507786 A CN111507786 A CN 111507786A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- category
- determining
- commodity category
- 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.)
- Granted
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]
- G06Q30/0605—Supply or demand aggregation
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a data processing method, a device and equipment, wherein the method comprises the following steps: determining that the first user has funds to flow into the second user according to the fund flow direction data; determining a first commodity category corresponding to a first user and a second commodity category corresponding to a second user; and if the first commodity category and the second commodity category have correlation, determining that a supply-demand relationship exists between the first user and the second user, thereby realizing the mining of the supply-demand relationship between different users.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a data processing method, apparatus, and device.
Background
With the continuous development of the internet, the online shopping mode becomes a shopping mode generally adopted in the life of people. However, this does not mean that the online shopping method has completely replaced the offline shopping method, and at present, the online and offline shopping methods coexist.
An industrial chain for a commodity may go through 4 links, namely, factory, agent, vendor, and consumer, each playing a role in the industrial chain. Different roles can perform various operations on the commodity, and the operations are often submerged in massive data on the line.
In some scenarios, it is important to mine the relationship between different users (e.g., between users in different roles, or between different users in the same role) in the industry chain, i.e., the supply-demand relationship or the stocking relationship. For example, Zhang III has been determined to sell false, and if it is found that it is stocking Li four and Wang five, respectively, and Zhao Liu is also being spammed to Zhang III, then this link will be found to sell false.
Disclosure of Invention
The embodiment of the invention provides a data processing method, a data processing device and data processing equipment, which are used for excavating supply and demand relations among users.
In a first aspect, an embodiment of the present invention provides a data processing method, including:
determining that the first user has funds to flow into the second user according to the fund flow direction data;
determining a first commodity category corresponding to the first user and a second commodity category corresponding to the second user;
and if the first commodity category and the second commodity category have correlation, determining that a supply-demand relationship exists between the first user and the second user.
In a second aspect, an embodiment of the present invention provides a data processing apparatus, including:
the first determining module is used for determining that the funds of the first user flow into the second user according to the fund flow direction data;
the second determining module is used for determining a first commodity category corresponding to the first user and a second commodity category corresponding to the second user;
and the third determining module is used for determining that a supply-demand relationship exists between the first user and the second user if the first commodity category and the second commodity category have correlation.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory stores executable codes, and when the executable codes are executed by the processor, the processor is caused to execute the data processing method in the first aspect.
An embodiment of the present invention provides a non-transitory machine-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform the data processing method in the first aspect.
In addition, an embodiment of the present invention further provides a data processing method, including:
determining that an interactive behavior exists between the first user and the second user according to the interaction record;
determining a first object characteristic corresponding to the first user and a second object characteristic corresponding to the second user, wherein the first object and the second object are both related to the interaction behavior;
and if the first object feature and the second object feature have correlation, determining that a dependency relationship exists between the first user and the second user.
In the embodiment of the present invention, for a certain piece of fund flow direction data, it is assumed that the fund flow direction data is determined according to the fund flow direction of the fund flow direction data, and in order to determine whether a supply-demand relationship exists between a first user and a second user, first, a first commodity category corresponding to the first user, that is, a category to which a commodity sold by the first user belongs, and a second commodity category corresponding to the second user, that is, a category to which a commodity sold by the second user belongs are determined. Secondly, whether the first commodity category and the second commodity category have correlation or not is judged, if yes, the fact that a supply-demand relationship exists between the first user and the second user is determined, namely the fact that the first user feeds goods to the second user exists.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another data processing method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a method for inferring categories of goods sold by a user based on a fund relationship according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a scenario for identifying supply-demand relationship corresponding to the embodiment shown in FIG. 2;
FIG. 5 is a flow chart of another data processing method according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating a scenario of identifying supply and demand relationships according to the embodiment shown in FIG. 5;
fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device corresponding to the data processing apparatus provided in the embodiment shown in fig. 7.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and "a" and "an" generally include at least two, but do not exclude at least one, unless the context clearly dictates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
In addition, the sequence of steps in each method embodiment described below is only an example and is not strictly limited.
The data processing method provided by the embodiment of the invention can be used for judging whether a supply-demand relationship (which can be called an industry chain relationship and a goods-in relationship) exists between two users with fund traffic. The core of the supply and demand relationship judgment is to judge whether the commodity purchased by the buyer (fund flow provider) has correlation with the commodity sold by the buyer. Such as: when a certain user A orders and purchases products of computer products from a user B and sells the computer products, the user A and the user B can be considered to have a stock-in relation.
How to mine the supply-demand relationship between different users is described below with reference to some embodiments as follows.
Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention, where the data processing method may be executed by a device on an e-commerce platform side, such as a server. As shown in fig. 1, the method comprises the steps of:
101. determining that the first user has an influx of funds into the second user based on the fund flow direction data.
In this embodiment, the fund flow direction data refers to data indicating a fund flow direction, and in practical applications, for example, the order data and the transfer data may both indicate the fund flow direction, and therefore, both may be used as the fund flow direction data.
Wherein, for order data: when a user purchases a commodity of a certain merchant in an online shopping mode and finishes payment, order data corresponding to the transaction is generated, wherein the order data comprises relevant information such as a purchaser, a seller, the commodity, money and the like.
For transfer data: a certain merchant may purchase a batch of goods from a certain manufacturer or a certain agent on line, and pay the manufacturer or the agent by an on-line payment means, so that a piece of transfer data is formed, and the transfer data comprises relevant information such as a payer, a payee, transfer time, transfer amount and the like.
Based on this, a server as an execution subject of the embodiment of the present invention may maintain therein a plurality of order data generated by the e-commerce platform side and a plurality of transfer data generated by the payment platform side. The server can analyze order data and transfer data generated in a period of time based on manual triggering or periodically to dig out the supply and demand relationship existing between different users.
Thus, in an alternative, step 101 may be implemented as: and acquiring order data, and determining that the funds of the first user flow into the second user if the buyer and the seller contained in the order data are the first user and the second user respectively.
In another alternative, step 101 may be implemented as: and obtaining transfer data, and if the payer and the payee contained in the transfer data are the first user and the second user respectively, determining that the funds of the first user flow into the second user.
102. And determining a first commodity category corresponding to the first user and a second commodity category corresponding to the second user.
As previously described: at the core of the supply and demand relationship judgment, whether the commodity purchased by the buyer (fund flow provider) is related to the commodity sold by the buyer is judged. Therefore, the determination in step 102 that the first item category corresponding to the first user is actually the category to which the item sold by the first user belongs; determining the category of the second product corresponding to the second user is actually determining the category to which the product sold by the second user belongs, in other words, determining the category to which the product purchased by the first user from the second user belongs.
In the following, a determination method of the first commodity category and the second commodity category is exemplified by taking order data as fund flow data as an example, and a case of transferring data and other determination methods will be exemplified in the following embodiments.
In the case of using the order data as the fund flow data, since the generation of the order data is caused only when the first user purchases a certain commodity from the second user, and the order data includes the purchased commodity information, at this time, it may be determined that the second commodity category corresponding to the second user is the category to which the commodity included in the order data belongs, for example, which category the commodity purchased by the first user belongs to is inquired in an online shop corresponding to the second user.
In addition, if the first user is an online merchant, the first user has an online shop, and at this time, the item category included in the online shop of the first user may be queried as the first item category corresponding to the first user.
103. And if the first commodity category and the second commodity category have correlation, determining that a supply-demand relationship exists between the first user and the second user.
In the embodiment of the present invention, the correlation between the commodity categories may be defined by the following two dimensions: similarity, and relationship between input and output. These two dimensions are in an alternative relationship.
Specifically, if the similarity between the first item category and the second item category is greater than or equal to a set threshold, it is determined that there is a correlation between the first item category and the second item category. Alternatively, if a sell-through relationship exists between the first category of items and the second category of items, a correlation is determined between the first category of items and the second category of items.
The following describes how to determine the similarity and the sale relationship between the first item category and the second item category.
Firstly, the total number of all the commodity categories corresponding to all online shops in the e-commerce platform is generally limited, for example, about several hundred, and the commodity categories are relatively stable and are not updated frequently, so that the similarity of every two commodity categories can be calculated in advance, and when the similarity of the first commodity category and the second commodity category needs to be calculated, only the obtained similarity calculation result needs to be queried.
Alternatively, the similarity between two categories of merchandise may be artificially pre-labeled. Specifically, the commodity category may be set to be a secondary category, structurally represented as a/b, where a represents the primary category and b represents the secondary category. Thus, for example: if the primary category and the secondary category of the two commodity categories are the same, the similarity of the two commodity categories is considered to be F1, if the primary category of the two commodity categories is the same and the secondary category of the two commodity categories is different, the similarity of the two commodity categories is considered to be F2, and if the primary category and the secondary category of the two commodity categories are different, the similarity of the two commodity categories is considered to be F3. It can be understood that F1, F2 and F3 are preset values, F1 is larger than F2, and F2 is far larger than F3, and in addition, a threshold value may be set to a value between F3 and F2, so that if the similarity between two commodity categories is F2 or F1, there is a correlation between the two commodity categories.
Optionally, another method for calculating similarity between commodity categories, word2vec, is also provided herein.
The purpose of the word2vec method is to vectorize each word, and change each word into a form of a code vector, and if two words are more similar, the code vectors of the two words are also more similar, that is, an included angle between corresponding vectors is smaller (or a cosine distance is larger). Here, we vectorize each commodity category by using word2vec, which can be specifically realized by the following steps:
respectively obtaining a plurality of commodity categories sold by a plurality of on-line shops;
constructing a co-occurrence relationship pair corresponding to each online shop according to the combination condition of a plurality of commodity categories corresponding to each online shop, wherein one co-occurrence relationship pair consists of two different commodity categories in the plurality of commodity categories;
determining coding vectors corresponding to the multiple commodity categories according to the co-occurrence relation;
and determining the similarity between the two corresponding commodity categories according to the distance between every two coding vectors.
Specifically, the online shop refers to a merchant with an online store opened on the e-commerce platform side, and the interface of the online shop generally includes information on the categories of commodities corresponding to various commodities operated by the corresponding merchant, so that various categories of commodities sold by each online shop, that is, each merchant can be extracted based on the information.
For example, assume that the categories of goods sold by any merchant are as follows: green plant gardening/nutrient soil; green gardening/flower art packing paper; green plants gardening/shovels. Because the merchant sells 3 kinds of commodity categories together, the 3 kinds of commodity categories can be combined pairwise to form 3 co-occurrence relation pairs:
green plant gardening/nutrient soil-green plant gardening/flower art packing paper;
green plant horticulture/nutrient soil-green plant horticulture/shovel;
green plants gardening/flower art packing paper-green plants gardening/shovel.
And constructing the co-occurrence relationship pairs for each online shop, so that the co-occurrence relationship pairs corresponding to all online shops can be used as training samples and provided for word2vec to perform modeling learning, and finally the coding vector of each commodity category is obtained. If the cosine distance between the code vectors corresponding to any two commodity categories is greater than or equal to a certain set threshold (such as 0.7), the two commodity categories can be considered to have correlation.
The following table illustrates the similarity calculation for several commodity categories:
assume that the first commodity category in the above step is: medicinal materials/caulis spatholobi, the second commodity category is: the similarity calculation result is inquired to show that the similarity between the two herbs/loofah sponge is 0.74, which is greater than the set threshold value of 0.7, so that the two herbs/loofah sponge have correlation.
The above describes a way to calculate the similarity between two categories of goods.
How to judge whether the sale entering relationship exists between the two commodity categories is described below, which can be specifically realized by the following steps:
respectively acquiring N commodity categories purchased by each of a plurality of online shops and M commodity categories sold by each of the online shops, wherein M and N are integers greater than or equal to 1;
constructing M x N promotion relation pairs corresponding to each online shop according to the combination condition of N commodity categories and M commodity categories corresponding to each online shop, wherein one promotion relation pair consists of one of the N commodity categories and one of the M commodity categories;
and screening out a target reimbursement relation pair with occurrence times and conditional probability meeting a set threshold.
Specifically, for any one online shop, N commodity categories purchased and M commodity categories sold are counted, and then combined two by two into M × N pairs of advance-sale relations, where × represents the multiplication number. The M commodity categories sold by the shops on a certain line can be obtained by inquiring the corresponding shop interfaces in the e-commerce platform. The N categories of the goods purchased by the on-line shop may be obtained by counting order data of the on-line shop for a period of time and according to the category of the goods to which each of the goods belongs in the order data.
For example, assume that N categories of goods purchased by a store on a line are: horticulture/succulent plants, horticulture/pots, horticulture/nutrient solutions. The M categories of goods sold by the on-line shop are: green/horticultural plants, green/fruit trees. Then the following pairs of pin relationships M × N — 6 can be constructed:
horticulture/succulent plants-green plants/horticulture plants;
horticulture/flowerpot-green plants/horticultural plants;
horticulture/nutrient solution-green plants/horticultural plants;
horticulture/succulent plants-green plants/fruit trees;
horticulture/flowerpots-green plants/fruit trees;
horticulture/nutrient solution-green plants/fruit trees.
And constructing the sales relationship pairs aiming at each online shop, so that the sales relationships corresponding to all online shops are summarized, the occurrence frequency and probability of each sales relationship pair are calculated, and finally the final target sales relationship pair is determined through threshold judgment.
For example, the number of occurrences and the probability for any of the drilling relationship pairs may be determined as follows: assuming that the aggregated results show that there are 100 online shops purchasing the commodity category of horticulture/flowerpot, and on this basis, there are 30 online shops selling the commodity category of green plant/fruit tree, the occurrence frequency of the marketing relationship pair consisting of horticulture/flowerpot-green plant/fruit tree is 30 times, and the probability is 30%. The occurrence frequency threshold and the probability threshold may be set respectively, and if the occurrence frequency of a certain reimbursement relationship pair is higher than the occurrence frequency threshold and the probability is higher than the probability threshold, the reimbursement relationship pair is considered as a target reimbursement relationship pair.
Based on this, for the first commodity category and the second commodity category in the foregoing steps, if the finally obtained target sales relationship pair includes a sales relationship pair composed of the first commodity category and the second commodity category, it is determined that there is a correlation between the first commodity category and the second commodity category.
Fig. 2 is a flowchart of another data processing method according to an embodiment of the present invention, as shown in fig. 2, the method may include the following steps:
201. and acquiring order data, and determining that the funds of the first user flow into the second user if the buyer and the seller contained in the order data are the first user and the second user respectively.
202. And determining a second commodity category corresponding to the second user as the category to which the commodity contained in the order data belongs.
In this embodiment, in a scenario where the first user purchases a commodity from the second user in an online shopping manner, the second commodity category corresponding to the second user is a commodity category of the commodity purchased by the first user, that is, a category to which the commodity sold by the second user belongs.
203. And if the first user does not have the on-line shop, acquiring a plurality of third users transferring accounts to the first user, wherein the third users respectively have the on-line shop.
204. And if at least part of the commodity categories contained in the online shops of the third users have correlation and the number of the third users meets a set threshold, determining that the first commodity category corresponding to the first user is the at least part of the commodity category.
In this embodiment, in a scenario where a first user purchases a commodity from a second user in an online shopping manner, it is determined that a first commodity category corresponding to the first user is the commodity category sold by the first user. At this time, if the first user has an online shop, that is, a merchant on the e-commerce platform side, the first commodity category corresponding to the first user may be directly determined to be a commodity category included in the online shop of the first user. However, if the first user does not have an online store, for example, the first user may be an offline agent, a scheme for inferring the categories of goods sold by the first user based on the relationship between the funds is provided.
The core idea of the scheme for presuming the commodity category sold by a certain user based on the fund relationship is as follows: if there is a significant commonality in the categories of goods sold by multiple users in the downstream users of a certain user X (i.e., the users who transfer funds to the user) (e.g., there is a high degree of similarity between the categories of goods sold by 4 of 7 downstream users), then the user X is considered to be selling the similar categories of goods.
In particular, records of the first user's funds traffic over a period of time may be aggregated to obtain users who transferred funds to the first user. In fact, the users transferring the money to the first user may include both the merchants with the online store and the merchants without the online store, and the online merchants with the online store are referred to as a plurality of third users. Then, counting to obtain the commodity categories sold by each of the third users, calculating the correlation between the commodity categories sold by different third users, and if a certain number of commodity categories have correlation and the number of the third users meets a set threshold value, determining that the first commodity category corresponding to the first user is the certain number of commodity categories.
This is illustrated in connection with fig. 3: assuming that the first user is user X as illustrated in the figure, it is found that there are four users transferring money to user X according to the records of the fund transaction of user X: user a, user B, user C, and user D. Through the online shop traversal of the four users, the four users are all clothing stores, and the commodity categories operated by the four clothing stores have obvious similarity, then the user X can be considered to have the similar commodity category, and therefore the user X may also be a clothing store, or a clothing agency, a clothing manufacturer.
205. And if the first commodity category and the second commodity category have correlation and the order summarizing information between the first user and the second user meets the set conditions, determining that a supply-demand relationship exists between the first user and the second user.
It should be noted that, when there are a plurality of first commodity categories and a plurality of second commodity categories, it may be calculated whether each combination of the plurality of first commodity categories and the plurality of second commodity categories satisfies the correlation requirement. And if the ratio of the number of the combinations meeting the correlation requirement is larger than a set value, the plurality of first commodity categories and the plurality of second commodity categories are considered to have correlation.
In addition, in the embodiment of the invention, for the determination of whether the supply-demand relationship exists between the two users with the fund relationship, the correlation between the commodity categories sold by the two users respectively is considered, and the order summary information between the two users is also considered, so that the influence of normal consumption behaviors on the judgment result of the supply-demand relationship is avoided. For example, after determining that the first commodity category corresponding to the first user and the second commodity category corresponding to the second user have a correlation, further considering order summary information such as the number of orders between the first user and the second user, the number of traded commodities, the total amount of orders, and the like, and considering that the first user and the second user have a supply-demand relationship only if the order summary information meets a set condition, such as the number of orders is greater than 100, the number of traded commodities is greater than 100, and the total amount of orders is greater than 5000 yuan.
In summary, the present embodiment introduces a process of identifying a supply-demand relationship between users based on order data based on the order data. For a better visual understanding of the process, it is illustrated in connection with fig. 4. As shown in fig. 4, a shoe store a, a fruit store B, a shoe store C, and a general consumer D place an order for the user X to purchase footwear products, and since the footwear products purchased by the shoe store a and the shoe store C are also sold by themselves, there is a high correlation, and thus the relationship between the shoe store a and the shoe store C and the user X is determined as the supply-demand relationship.
Fig. 5 is a flowchart of another data processing method according to an embodiment of the present invention, and as shown in fig. 5, the method may include the following steps:
501. and obtaining transfer data, and if the payer and the payee contained in the transfer data are the first user and the second user respectively, determining that the funds of the first user flow into the second user.
In the embodiment, the identification process of the supply and demand relationship among users is introduced on the basis of the transfer data.
502. And if the first user has an online shop, determining that the first commodity category corresponding to the first user is a commodity category contained in the online shop.
In contrast, if the first user does not have an on-line store, the first category of items corresponding to the first user may be determined in the manner described in the embodiment of fig. 2.
503. And if the second user does not have the on-line shop, acquiring a plurality of fourth users transferring accounts to the second user, wherein the fourth users respectively have the on-line shop.
504. And if at least part of the commodity categories in the commodity categories contained in the online shops of the fourth users have correlation and the number of the fourth users meets a set threshold, determining that the second commodity category corresponding to the second user is the at least part of the commodity category.
505. And if the first commodity category and the second commodity category have correlation and the transfer summary information between the first user and the second user meets the set conditions, determining that a supply-demand relationship exists between the first user and the second user.
In this embodiment, the transfer summary information may be, for example, the total number of transfers, the total amount, and the like between the first user and the second user in a certain period of time.
For parts not described in detail in this embodiment, reference may be made to the related descriptions in the embodiment shown in fig. 2, and details thereof are not repeated.
For a better visual understanding of the supply-demand relationship identification process described in the present embodiment, an example is given in conjunction with fig. 6. As shown in fig. 6, a user a, a user B, a user C, a user D, and a user E respectively have a transfer behavior to a user X, where the user a, the user B, and the user C are clothing stores, the user D is a snack store, and the user E is a consumer. When only the users have transfer behaviors to the user X and do not know the intention of transfer, the corresponding commodity categories of the users can be determined based on the determination method of the commodity categories sold by the users described above, assuming that the clothing categories sold by the user A, the user B and the user C are known, and the user X is also presumed to be sold, however, the transfer summary information of the user A and the user X does not meet the set conditions (for example, the user A transfers the money to the user X only once in a period of time, and the money amount is low), so that the user B and the user C are finally determined to have supply and demand relations with the user X respectively.
Through the above embodiments, in a commodity transaction scenario, it may be determined whether a supply-demand relationship, i.e., a large-amount and long-term stable trading relationship, exists between the first user and the second user in the commodity transaction. In other application scenarios, there may be some other dependency relationship between different users. Therefore, in order to find whether a certain dependency relationship exists between different users in various scenes, the embodiment of the present invention further provides the following general scheme:
determining that an interactive behavior exists between the first user and the second user according to the interaction record;
determining a first object characteristic corresponding to a first user and a second object characteristic corresponding to a second user, wherein the first object and the second object are both related to the interaction behavior;
and if the first object feature and the second object feature have correlation, determining that a dependency relationship exists between the first user and the second user.
The object is related to the interactive behavior, that is, when some interactive behavior exists between different users, a target object for mining whether some dependency relationship exists between the different users is some object.
When the interaction record is the fund flow direction data, the first object and the second object are both commodities, and the index for measuring the characteristics of the commodities adopts a commodity category, the scheme for determining whether the supply-demand relationship on the commodities exists between the first user and the second user in the embodiment is provided.
For another example, in one embodiment, a parking space lease relationship between different users may be mined. At this time, the interaction record may be embodied as a transmission record of a certain shared credential, such as a digital verification code or a two-dimensional code, so that a user entering a certain parking lot may unlock the parking lock through the digital verification code or the two-dimensional code.
Under this scene, user A has the ownership of a certain parking stall, can rent the parking stall to other users and use when it does not use this parking stall. Assuming that an intelligent parking spot lock is deployed on a parking spot, the parking spot lock can be unlocked only by inputting a correct digital verification code or brushing a correct two-dimensional code by a user. For example, if the user B rents the parking space of the user a, the user a can send the digital verification code or the two-dimensional code to the user B through a certain APP, and then the server corresponding to the APP can acquire the interactive information of the digital verification code or the two-dimensional code sent by the user a to the user B.
The user a may transmit the vehicle information and the user information of the user a to the server in advance as a registrant to register. The vehicle information may include information such as a license plate number, a vehicle type, a vehicle color, and the like, and the user information may include a face image of the user.
For a parking space, an image acquisition device can be deployed on a parking space lock at the parking space, and when a vehicle intends to drive into the parking space, the image acquisition device can acquire vehicle information and user information (assumed as a user B) of the current vehicle and send the acquired vehicle information and user information to a server when the parking space lock is unlocked correctly.
Therefore, the server can compare the vehicle information and the user information uploaded by the parking space lock with the user information and the vehicle information of the registered person corresponding to the parking space to determine whether the parking behavior is the parking behavior of the registered person. If the parking behavior is not the parking behavior of the registrant, the service end determines that the user B corresponding to the acquired user information has a lease relationship with the registrant, namely the user A.
In the above example, user a and user B are the first user and the second user, respectively. The first object feature is user information of the user a and vehicle information, and the second object feature is user information of the user B and vehicle information. The correlation between the first object feature and the second object feature is embodied as: if the two object features are not consistent, the two object features are considered to have correlation.
The data processing apparatus of one or more embodiments of the present invention will be described in detail below. Those skilled in the art will appreciate that these data processing devices can each be constructed using commercially available hardware components configured through the steps taught in this scheme.
Fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention, where the data processing apparatus includes a server, and the server may manage or query order data and various transfer data of an e-commerce platform. As shown in fig. 7, the apparatus includes: a first determining module 11, a second determining module 12 and a third determining module 13.
And the first determining module 11 is used for determining that the first user has the fund flow into the second user according to the fund flow data.
A second determining module 12, configured to determine a first commodity category corresponding to the first user and a second commodity category corresponding to the second user.
A third determining module 13, configured to determine that a supply-demand relationship exists between the first user and the second user if there is a correlation between the first commodity category and the second commodity category.
Optionally, the first determining module 11 may be configured to: acquiring order data; and if the buyer and the seller contained in the order data are the first user and the second user respectively, determining that the funds of the first user flow into the second user.
Optionally, the first determining module 11 may be configured to: acquiring transfer data; and if the payer and the payee contained in the transfer data are the first user and the second user respectively, determining that the funds of the first user flow into the second user.
Optionally, the second determining module 12 may be configured to: and determining that the second commodity category corresponding to the second user is the category to which the commodity contained in the order data belongs.
Optionally, the second determining module 12 may be configured to: and if the first user has an on-line shop, determining that the first commodity category corresponding to the first user is a commodity category contained in the on-line shop.
Optionally, the second determining module 12 may be configured to: if the first user does not have an on-line shop, acquiring a plurality of third users transferring accounts to the first user, wherein the third users respectively have the on-line shops;
if at least part of the commodity categories contained in the online shops of the third users have correlation, and the number of the third users meets a set threshold, determining that the first commodity category corresponding to the first user is the at least part of the commodity category.
Optionally, the second user does not have an online shop, and the second determining module 12 may be configured to: obtaining a plurality of fourth users transferring money to the second user, the plurality of fourth users each having an online store; if at least part of the commodity categories contained in the online shops of the fourth users have correlation, and the number of the fourth users meets a set threshold, determining that the second commodity category corresponding to the second user is the at least part of the commodity category.
Optionally, the third determining module 13 may be configured to: and if the first commodity category and the second commodity category have correlation and the order summary information between the first user and the second user meets set conditions, determining that a supply-demand relationship exists between the first user and the second user.
Optionally, the third determining module 13 may be configured to: and if the first commodity category and the second commodity category have correlation and the transfer summary information between the first user and the second user meets set conditions, determining that a supply-demand relationship exists between the first user and the second user.
Optionally, the third determining module 13 may be configured to: and if the similarity between the first commodity category and the second commodity category is larger than or equal to a set threshold value, determining that the first commodity category and the second commodity category have correlation.
Optionally, the third determining module 13 may be configured to: respectively obtaining a plurality of commodity categories sold by a plurality of on-line shops; constructing a co-occurrence relationship pair corresponding to each online shop according to the combination condition of a plurality of commodity categories corresponding to each online shop, wherein one co-occurrence relationship pair consists of two different commodity categories in the plurality of commodity categories; determining the coding vectors corresponding to the plurality of commodity categories according to the co-occurrence relation pairs; determining the similarity between two corresponding commodity categories according to the distance between every two coding vectors; and if the similarity between the first commodity category and the second commodity category is determined to be larger than or equal to a set threshold value through inquiring the obtained similarities, determining that the first commodity category and the second commodity category have correlation.
Optionally, the third determining module 13 may be configured to: and if the sales promotion relation exists between the first commodity category and the second commodity category, determining that the first commodity category and the second commodity category have the correlation.
Optionally, the third determining module 13 may be configured to: respectively acquiring N commodity categories purchased by each of a plurality of online shops and M commodity categories sold by each of the online shops, wherein M and N are integers greater than or equal to 1; constructing M x N promotion relation pairs corresponding to each online shop according to the combination condition of N commodity categories and M commodity categories corresponding to each online shop, wherein one promotion relation pair consists of one of the N commodity categories and one of the M commodity categories; screening out a target sale-in relation pair with occurrence times and conditional probability meeting a set threshold; and if the target sale relationship pair comprises a sale relationship pair consisting of the first commodity category and the second commodity category, determining that the first commodity category and the second commodity category have correlation.
The apparatus shown in fig. 7 can perform the methods in the foregoing embodiments, and details of the portions of this embodiment that are not described in detail can refer to the related descriptions of the foregoing embodiments, which are not described herein again.
In one possible design, the structure of the data processing apparatus shown in fig. 7 may be implemented as an electronic device, such as a server. As shown in fig. 8, the electronic device may include: a processor 21 and a memory 22. Wherein the memory 22 has stored thereon executable code which, when executed by the processor 21, causes at least the processor 21 to perform the steps of:
determining that the first user has funds to flow into the second user according to the fund flow direction data;
determining a first commodity category corresponding to the first user and a second commodity category corresponding to the second user;
and if the first commodity category and the second commodity category have correlation, determining that a supply-demand relationship exists between the first user and the second user.
The structure of the distribution network device may further include a communication interface 23, which is used for communicating with other devices or a communication network.
Additionally, embodiments of the present invention provide a non-transitory machine-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform the steps of the foregoing embodiments.
The above-described apparatus embodiments are merely illustrative, wherein the units described as separate components may or may not be physically separate. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described aspects and portions of the present technology which contribute substantially or in part to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including without limitation disk storage, CD-ROM, optical storage, and the like.
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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable 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 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 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (16)
1. A data processing method, comprising:
determining that the first user has funds to flow into the second user according to the fund flow direction data;
determining a first commodity category corresponding to the first user and a second commodity category corresponding to the second user;
and if the first commodity category and the second commodity category have correlation, determining that a supply-demand relationship exists between the first user and the second user.
2. The method of claim 1, wherein determining that the first user has funds in-flow to the second user based on the funds flow data comprises:
acquiring order data;
and if the buyer and the seller contained in the order data are the first user and the second user respectively, determining that the funds of the first user flow into the second user.
3. The method of claim 1, wherein determining that the first user has funds in-flow to the second user based on the funds flow data comprises:
acquiring transfer data;
and if the payer and the payee contained in the transfer data are the first user and the second user respectively, determining that the funds of the first user flow into the second user.
4. The method of claim 2, wherein the determining the second category of merchandise corresponding to the second user comprises:
and determining that the second commodity category corresponding to the second user is the category to which the commodity contained in the order data belongs.
5. The method of claim 2 or 3, wherein the determining the first category of items corresponding to the first user comprises:
and if the first user has an on-line shop, determining that the first commodity category corresponding to the first user is a commodity category contained in the on-line shop.
6. The method of claim 2 or 3, wherein the determining the first category of items corresponding to the first user comprises:
if the first user does not have an on-line shop, acquiring a plurality of third users transferring accounts to the first user, wherein the third users respectively have the on-line shops;
if at least part of the commodity categories contained in the online shops of the third users have correlation, and the number of the third users meets a set threshold, determining that the first commodity category corresponding to the first user is the at least part of the commodity category.
7. The method of claim 3, wherein the second user does not have an on-line store, and wherein the determining the second category of goods corresponding to the second user comprises:
obtaining a plurality of fourth users transferring money to the second user, the plurality of fourth users each having an online store;
if at least part of the commodity categories contained in the online shops of the fourth users have correlation, and the number of the fourth users meets a set threshold, determining that the second commodity category corresponding to the second user is the at least part of the commodity category.
8. The method of claim 2, wherein determining that a supply-demand relationship exists between the first user and the second user if there is a correlation between the first category of merchandise and the second category of merchandise comprises:
and if the first commodity category and the second commodity category have correlation and the order summary information between the first user and the second user meets set conditions, determining that a supply-demand relationship exists between the first user and the second user.
9. The method of claim 3, wherein determining that a supply-demand relationship exists between the first user and the second user if there is a correlation between the first category of merchandise and the second category of merchandise comprises:
and if the first commodity category and the second commodity category have correlation and the transfer summary information between the first user and the second user meets set conditions, determining that a supply-demand relationship exists between the first user and the second user.
10. The method of claim 1, further comprising:
and if the similarity between the first commodity category and the second commodity category is larger than or equal to a set threshold value, determining that the first commodity category and the second commodity category have correlation.
11. The method of claim 10, further comprising:
respectively obtaining a plurality of commodity categories sold by a plurality of on-line shops;
constructing a co-occurrence relationship pair corresponding to each online shop according to the combination condition of a plurality of commodity categories corresponding to each online shop, wherein one co-occurrence relationship pair consists of two different commodity categories in the plurality of commodity categories;
determining the coding vectors corresponding to the plurality of commodity categories according to the co-occurrence relation pairs;
determining the similarity between two corresponding commodity categories according to the distance between every two coding vectors;
if the similarity between the first commodity category and the second commodity category is greater than or equal to a set threshold, determining that there is a correlation between the first commodity category and the second commodity category, including:
and if the similarity between the first commodity category and the second commodity category is determined to be larger than or equal to a set threshold value through inquiring the obtained similarities, determining that the first commodity category and the second commodity category have correlation.
12. The method of claim 1, further comprising:
and if the sales promotion relation exists between the first commodity category and the second commodity category, determining that the first commodity category and the second commodity category have the correlation.
13. The method of claim 12, further comprising:
respectively acquiring N commodity categories purchased by each of a plurality of online shops and M commodity categories sold by each of the online shops, wherein M and N are integers greater than or equal to 1;
constructing M x N promotion relation pairs corresponding to each online shop according to the combination condition of N commodity categories and M commodity categories corresponding to each online shop, wherein one promotion relation pair consists of one of the N commodity categories and one of the M commodity categories;
screening out a target sale-in relation pair with occurrence times and conditional probability meeting a set threshold;
determining that the first item category and the second item category have a correlation if a marketing relationship exists between the first item category and the second item category, including:
and if the target sale relationship pair comprises a sale relationship pair consisting of the first commodity category and the second commodity category, determining that the first commodity category and the second commodity category have correlation.
14. A data processing apparatus, comprising:
the first determining module is used for determining that the funds of the first user flow into the second user according to the fund flow direction data;
the second determining module is used for determining a first commodity category corresponding to the first user and a second commodity category corresponding to the second user;
and the third determining module is used for determining that a supply-demand relationship exists between the first user and the second user if the first commodity category and the second commodity category have correlation.
15. An electronic device, comprising: a memory, a processor; wherein the memory has stored thereon executable code which, when executed by the processor, causes the processor to carry out the data processing method of any one of claims 1 to 13.
16. A data processing method, comprising:
determining that an interactive behavior exists between the first user and the second user according to the interaction record;
determining a first object characteristic corresponding to the first user and a second object characteristic corresponding to the second user, wherein the first object and the second object are both related to the interaction behavior;
and if the first object feature and the second object feature have correlation, determining that a dependency relationship exists between the first user and the second user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910092622.4A CN111507786B (en) | 2019-01-30 | 2019-01-30 | Data processing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910092622.4A CN111507786B (en) | 2019-01-30 | 2019-01-30 | Data processing method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111507786A true CN111507786A (en) | 2020-08-07 |
| CN111507786B CN111507786B (en) | 2023-05-26 |
Family
ID=71868843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910092622.4A Active CN111507786B (en) | 2019-01-30 | 2019-01-30 | Data processing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507786B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314654A (en) * | 2010-07-08 | 2012-01-11 | 阿里巴巴集团控股有限公司 | Information push method and information push server |
| WO2016105902A1 (en) * | 2014-12-26 | 2016-06-30 | Alibaba Group Holding Limited | Method and apparatus for processing and releasing the information of the business object |
| CN107492000A (en) * | 2016-06-13 | 2017-12-19 | 阿里巴巴集团控股有限公司 | A kind of method and system of data processing |
-
2019
- 2019-01-30 CN CN201910092622.4A patent/CN111507786B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314654A (en) * | 2010-07-08 | 2012-01-11 | 阿里巴巴集团控股有限公司 | Information push method and information push server |
| WO2016105902A1 (en) * | 2014-12-26 | 2016-06-30 | Alibaba Group Holding Limited | Method and apparatus for processing and releasing the information of the business object |
| CN107492000A (en) * | 2016-06-13 | 2017-12-19 | 阿里巴巴集团控股有限公司 | A kind of method and system of data processing |
Non-Patent Citations (1)
| Title |
|---|
| 张耀钢;周力;应瑞瑶;: "以企业为主体的农业技术服务模式的创新及理论探讨" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111507786B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Maihami et al. | Effect of two-echelon trade credit on pricing-inventory policy of non-instantaneous deteriorating products with probabilistic demand and deterioration functions | |
| CN110135876A (en) | The method and device of Method for Sales Forecast | |
| EP3637347B1 (en) | Method and system for processing environmental impact | |
| CN110766428A (en) | Data value evaluation system and method | |
| KR102198960B1 (en) | System and method of optimizing and calculating real-estate tax | |
| CN110533474A (en) | One kind being directed to electric business user credit evaluation system | |
| KR20210000303A (en) | Real-estate tax simulation system | |
| CN112446794A (en) | Supply chain financial credit evaluation system and method based on block chain | |
| CN112396433A (en) | Method and system for identifying false commodity comments based on behavior of person to be evaluated | |
| CN107368962B (en) | Automatic credit investigation method and system for enterprise transaction | |
| KR101947413B1 (en) | Hedging System for Prices of Petroleum Products | |
| KR101575927B1 (en) | Resale system for repeating sale goods and method of the same | |
| CN107180030B (en) | Method and device for generating relational data on network | |
| CN111507786B (en) | Data processing method, device and equipment | |
| Swamy | The digital economy: New business models and key features | |
| US20150170038A1 (en) | Method And System For Generating Item Recommendation | |
| CN114331594A (en) | Commodity recommendation method | |
| CN114493415A (en) | Commodity platform control method, system and readable storage medium | |
| KR20220055185A (en) | pricing method of imported goods using big data | |
| CN110751492A (en) | High-value crowd identification method and device | |
| KR101699472B1 (en) | System for Data Exchange and method therefor | |
| CN116228381B (en) | Money issuing method, money issuing device, computer equipment and readable storage medium | |
| KR102476961B1 (en) | Method for offering credit loans for electronic commerce online seller using ai (artificial intelligence) and system using the same | |
| KR102030592B1 (en) | Method of margin split price setting and price setting server performing the same | |
| US20240020627A1 (en) | Sparse Data Driven Inventory Intelligence for Optimizing Traditional Trade |
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 |