CN117495454A

CN117495454A - User rating method, system, electronic equipment and storage medium

Info

Publication number: CN117495454A
Application number: CN202311376315.1A
Authority: CN
Inventors: 陈鹏; 唐瑞博; 李雄文; 王艳; 孙文文; 潘琳; 高珊; 叶桐; 卓林俐
Original assignee: China Communications Xiamen E Commerce Co ltd
Current assignee: China Communications Xiamen E Commerce Co ltd
Priority date: 2023-10-23
Filing date: 2023-10-23
Publication date: 2024-02-02

Abstract

The invention provides a user rating method, a system, electronic equipment and a storage medium. The method comprises the following steps: acquiring user data of each user in the b2b e-commerce platform; the user data comprises order data; according to a preset abnormal order identification rule, abnormal order data are removed from the user data, and target user data of each user are obtained; the abnormal order data includes: brushing order data, machine-made dummy order data and/or dummy order data; the target level of each user is determined based on the target user data for each user. The obtained order data of each user is filtered, abnormal order data is removed, including the removed order data, the machine fake order data and the false order data, the user level is determined based on the filtered order data, the influence of the abnormal order data on the rating result is reduced, and the accuracy of the rating of the user is improved.

Description

User rating method, system, electronic equipment and storage medium

Technical Field

The present invention relates to the field of user portrait generation, and in particular, to a user rating method, system, electronic device, and storage medium.

Background

With the deep research and application of big data technology, enterprises need to deeply mine potential commercial value, so that the concept of user portraits is generated. The user portrayal can make the service object of the product more focused and focused. Key user information is abstracted from a large amount of user characteristics and user behavior data, and the data is changed into own assets.

b2b (Business-to-Business) electronic commerce platform based on user data, utilizing Business system logic and combining big data related technical means, performing multidimensional analysis on users through a model and an algorithm to realize rating of the users, namely constructing portraits of the users, and assisting the electronic commerce platform to actively know the users so as to promote accurate marketing.

The users in the b2b e-commerce platform are generally classified into suppliers, i.e., users who offer to sell items, and purchasing units, i.e., users who purchase items. In the related art, when a user in the b2b e-commerce platform is rated, the user image is constructed based on a related modeling algorithm, namely, the user rating is usually performed after user data is acquired. However, because the acquired user data comprises more redundant data, the obtained rating result is noisier and lower in accuracy.

Disclosure of Invention

In view of the above, the embodiments of the present invention provide a user rating method, a system, an electronic device, and a storage medium, so as to improve the accuracy of user rating construction.

According to an aspect of the present invention, there is provided a user rating method applied to a b2b e-commerce platform, the method comprising:

acquiring user data of each user in the b2b e-commerce platform; the user data comprises order data;

removing abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of the users; the abnormal order data includes: brushing order data, machine-made dummy order data and/or dummy order data; wherein the machine-made false order data is false order data generated by machine operation

A target level for each of the users is determined based on target user data for each of the users.

In a possible embodiment, the obtaining the user data of each user in the b2b e-commerce platform includes:

acquiring user data of each user from different service systems; the business system comprises: b2b e-commerce platform, contract management platform and household qualification management platform.

In a possible embodiment, in a case where the abnormal order data includes a brush order data, the removing the abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of each user includes:

for each order of each user, determining a brush order evaluation score of the order based on the order quantity corresponding to the order placing IP address of the order, the matching degree of the order placing IP address and the receiving address and the distribution time of the order;

determining that the order is a order in case that the order evaluation score exceeds a preset order score threshold;

and removing the order data from the user data to obtain target user data of the users.

In a possible embodiment, the user data includes request log data; and in the case that the abnormal order data includes machine-made false order data, removing the abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of each user, including:

determining, for each order of each user, a target page access order at the time of generating the order based on the user's request log data;

Under the condition that the target page access sequence of the order is inconsistent with the preset page access sequence, determining that the order is a machine-made false order;

and removing the machine-made false order data from the user data to obtain target user data of the users.

In a possible embodiment, in a case where the abnormal order data includes false order data, the removing the abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of each user includes:

determining, for each order of each user, whether a receiving address of the order is consistent with an actual delivery address of the order;

determining that the order is a false order under the condition that the receiving address of the order is inconsistent with the actual delivery address of the order;

and removing the false order data from the user data to obtain target user data of the users.

In one possible embodiment, the determining the target level of each of the users based on the target user data of each of the users includes:

determining the user data growth rate of each user in a preset time period;

And determining a preset level corresponding to the user data growth rate of each user as a target level of the corresponding user.

In one possible embodiment, the user data growth rate comprises: order amount increase rate, order quantity increase rate, daily activity increase rate;

the determining the preset level corresponding to the user data growth rate of each user includes:

for each user, determining preset rating scores corresponding to various user data growth rates of the user;

for each user, determining a statistical value of each preset rating score corresponding to the user as a target rating score of the user;

and determining a preset level corresponding to the target rating score of each user.

According to another aspect of the present invention, there is provided a user rating system for use with a b2b e-commerce platform, the system comprising:

the acquisition module is used for acquiring user data of each user in the b2b e-commerce platform; the user data comprises order data;

the rejecting module is used for rejecting abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of the users; the abnormal order data includes: brushing order data, machine-made dummy order data and/or dummy order data;

And the determining module is used for determining the target level of each user based on the target user data of each user.

According to another aspect of the present invention, there is provided an electronic apparatus including:

a processor; and

a memory in which a program is stored,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform any of the user rating methods described above.

According to another aspect of the present invention, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform any one of the user rating methods described above.

According to one or more technical schemes provided by the embodiment of the invention, the acquired order data of each user is filtered, abnormal order data is removed, including the order data of a brushed order, the order data of a machine-made false order and the false order data are removed, the level of the user is determined based on the filtered order data, the influence of the abnormal order data on the rating result is reduced, and the accuracy of the rating of the user is improved.

Drawings

Further details, features and advantages of the invention are disclosed in the following description of exemplary embodiments with reference to the following drawings, in which:

FIG. 1 is a schematic flow chart of a user rating method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of a preliminary screening of user data according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a user rating system according to an embodiment of the present invention;

fig. 4 shows a block diagram of an exemplary electronic device that can be used to implement an embodiment of the invention.

Detailed Description

Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the invention is susceptible of embodiment in the drawings, it is to be understood that the invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided to provide a more thorough and complete understanding of the invention. It should be understood that the drawings and embodiments of the invention are for illustration purposes only and are not intended to limit the scope of the present invention.

It should be understood that the various steps recited in the method embodiments of the present invention may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the invention is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those skilled in the art will appreciate that "one or more" is intended to be construed as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of such messages or information.

In order to improve user rating accuracy aiming at a b2b e-commerce platform, the invention provides a user rating method, a user rating system, electronic equipment and a storage medium. The user rating method provided by the invention can be applied to any electronic equipment with a user rating function, wherein the electronic equipment can comprise a computer, a server, a mobile terminal and the like, and the invention is not particularly limited to the above. The user rating method provided by the embodiment of the invention can rate the user in the b2b E-commerce platform. The user may be a purchasing unit or a supplier. The following describes the aspects of the invention with reference to the accompanying drawings:

as shown in fig. 1, fig. 1 is a schematic flow chart of a user rating method according to an embodiment of the present invention, which may include the following steps:

s101, acquiring user data of each user in a b2b e-commerce platform; the user data comprises order data;

s102, removing abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of each user; the abnormal order data includes: brushing order data, machine-made dummy order data and/or dummy order data; wherein the machine-made false order data is false order data generated by machine operation;

S103, determining the target level of each user based on the target user data of each user.

By applying the embodiment of the invention, the obtained order data of each user is filtered, abnormal order data is removed, including the brushed order data, the machine fake order data and the false order data, and then the user level is determined based on the filtered order data, so that the influence of the abnormal order data on the rating result is reduced, and the accuracy of the rating of the user is improved.

The following is an exemplary description of the above S101-S103:

in the b2b e-commerce platform, the user data and the user identifier are generally stored in a database in a corresponding manner, and the database may be a relational database or a non-relational database, which is not particularly limited in the present invention. As described above, users in b2b e-commerce platforms typically include suppliers and purchasing units. The user data of the purchasing unit may include order data of the purchasing unit, such as order number, order amount, order placing time, type of commodity placed, number of commodity, etc., and may include basic information of the purchasing unit, such as name of the purchasing unit, address of the placing order, etc. The user data of the supplier may then include order data of the sales of the supplier, basic information of the purchaser, etc. The user identifier may be an account number of the user, or may be information that may uniquely identify the user, such as a mobile phone number of the user.

The users in S101 refer to the users who need to be rated, and may be all the users in the b2b e-commerce platform, or may be some of the users in the b2b e-commerce platform, for example, the users may be rated only for purchasing units, or may be rated only for suppliers, or may be randomly extracted to rate, which is not limited in this invention.

In one possible embodiment, after determining the users that need to be rated, user data for the respective users may be obtained from a database based on the user identification.

For the service provider of the b2b e-commerce platform, the enterprise comprises a plurality of service systems, and user data in different aspects are stored in different service systems. For example, the e-commerce platform may store order data to the user as well as basic user information such as business name, shipping address, etc.; the user qualification management platform may store qualification information of the user, including enterprise name, business license information, establishment time and the like; the contract management platform may store contract information for users with businesses. Different service systems are usually mutually independent in a splitting way, so in one possible embodiment, a data center can be built, and the data center can be used for extracting user data from different service systems, for example, the user data of each user are obtained from a contract management platform, a user qualification management platform and an e-commerce platform.

As a possible implementation, each service system may store user data of the same user using the same identity. The data center can acquire user data of the user from each service system based on the user identification. The user data may include order data, basic information, and the like. The order data may include the time of the user's order, the number of orders, the amount of the orders, etc. The basic information may include the name of the user, qualification information, contract information, and the like.

By acquiring the user data stored in different service systems, the comprehensiveness of the acquired user data is improved, and the accuracy of user rating is further improved.

In one possible embodiment, the extraction may be performed according to a preset extraction rule when the user data is acquired. The extraction rule may be set according to actual needs, which is not particularly limited in the present invention. As a possible implementation manner, the extraction rule may include a user attribute, an order attribute, and the like. The user attributes may include the size of the purchasing unit or provider (e.g., the number of employees is greater than 500), the business scope, the contract type, the settlement means and period, etc. The order attributes may include order amount, order frequency, order quantity, order commodity type, and rate of return. The refund rate refers to the ratio of sales money received by the business entity to the total amount of sales income. And acquiring the required data through the extraction rule, so that the subsequent data processing amount is reduced, and the influence of useless data on the user rating is reduced.

In one possible embodiment, a user preliminary rating may also be pre-stored in each business system, which may be set for different business systems. For example, for the user qualification management platform, the user with larger scale and longer establishment time can be set as a high-quality user, that is, the user rating is higher. For the contract management platform, the contract signing time can be set to be longer, and the user with normal operation is a high-quality user. Accordingly, the extraction rules described above may also include different user ratings. By acquiring the user data with higher preliminary rating, the effectiveness of the acquired user data can be improved, and the efficiency of determining high-quality users can be improved.

As a possible implementation manner, the data center may provide a rule configuration page, where options that may be set by related personnel may be included, for example, a user scale, a contract type, and so on. The relevant personnel can set the extraction rule on the page.

In a possible embodiment, after determining the rule, the rule may be further verified, that is, the user extracted based on the rule is verified, and whether the rule is correct or reasonable is determined by determining whether the extracted user meets the expectation.

Since the acquired user data may originate from different service systems, the different service systems may store data in different data standards or different data formats, and at the same time, there may be more duplicate data, invalid data, or erroneous data in the acquired user data.

Thus, in one possible embodiment, the data may be flushed and format converted, the duplicate data, invalid data or error data, etc. filtered, and the data format unified. The data are extracted from different service systems according to the self-defined extraction rules, and the data collected from different service systems are cleaned, so that the reliability and the usability of the data are effectively improved, and a good basis is provided for subsequent data calculation, analysis and application.

As a possible implementation manner, the acquired user data may be stored in the intermediate database, and after the data stored in the intermediate database is cleaned and format-converted, the data is stored in the target database. The intermediate database and the target database may be the same type of database, or may be different types of databases, which is not particularly limited in the present invention. Through the technical scheme, the data which need to be cleaned and converted in format are stored independently, rather than uniformly storing the data and the cleaned and converted data, so that the data cleaning and format conversion efficiency is improved. The data acquisition, cleaning and conversion can be performed at regular time according to actual demands, so that continuous alternation of data in a database is ensured, and accuracy of user rating based on user data is further improved.

Fig. 2 is a schematic flow chart of preliminary screening of data according to an embodiment of the present invention:

fig. 2 shows 3 data sources, namely data source 1, data source 2 and data source 3, which may be different service systems, such as b2b e-commerce platform, contract management platform, user qualification management platform, etc. After extracting user data from each data source according to the preset extraction rules, the extracted user data may be temporarily stored in an intermediate database, where the intermediate database may be mysql, redis, and so on. After the user data stored in the intermediate database is subjected to data format conversion, the data in the same data format is stored in the target database.

In the embodiment of the invention, various abnormal order identification rules can be preset to filter abnormal orders in order data of each user. Such abnormal orders may include brush orders, machine-made false orders, and the like.

The bill is used for providing purchase expense by a seller (provider), impersonating a customer by other people, improving the exposure rate, credit and ranking of the store by a spurious shopping mode, and the like, and the bill can improve the activity, credit and the like of the buyer (purchasing unit). A machine-forged order refers to a user making a request for order data by machine forging. False order data refers to a user placing an order with a false address. For example, the seller places an order in his store by a false address, while the actual recipient is the seller itself. In the following, the user is taken as a purchase unit as an example, and the recognition of the order data of the user, the machine-made false order data, and the false order data are respectively described.

For a swipe order, in one possible embodiment, each time an order placing action of a purchasing unit in the b2b e-commerce platform is detected, the IP (Internet Protocol ) address, device information, and authorization information for the purchasing unit at the time of order placing may be stored. The purchasing unit can be identified by an account number in the b2b e-commerce platform. The device information may include a model number of the device, a system type, a browser type, and the like. The authorization information may include location information, face information, account passwords, and the like. As a specific implementation manner, when the user logs in to the account, a token (an identity authentication token) can be issued for the user, and a validity period is set. If the IP is switched, the login identification is needed again, and authorization authentication is carried out, so that the latest user authorization information can be obtained.

And judging that the order under the IP address or the account is a brush order under the condition that the number of the accounts corresponding to the same IP address exceeds the preset number of the accounts and/or the number of the accounts corresponding to the same IP address exceeds the preset number of the accounts threshold. Therefore, the above-mentioned order data of the brush order may be deleted from the order data of the account number. The preset account number and the preset order number threshold value can be set according to actual needs, for example, the preset account number can be 5, the preset order number can be 100, and the like.

As another possible implementation manner, when it is detected that the number of orders in a certain account exceeds a preset number threshold, and the amount of each order generated by the account and the information such as the receiving address have a large difference, the authorization information of the account can be queried, and if the authorization information is consistent with the previously stored authorization information of the account, the orders are determined to be normal order data; if the authorization information is inconsistent with the previously stored authorization information of the account or no authorization information is queried, the orders are determined to be the order for the refreshing, so that the order data can be deleted from the order data of the account.

In one possible embodiment, the order data may be identified as follows:

and then the order data of the bill is removed from the user data to obtain the target user data of the users.

As described above, the order data may be included in the user data, and specifically may include the order quantity, order amount, commodity quantity, commodity type, and receiving address of the user.

In one possible embodiment, the order number corresponding to the order placement IP address of the order, the matching degree of the order placement IP address and the receiving address, and the order delivery time may be calculated for each order, and the order placement evaluation score may be determined based on the order placement scores.

The order score for the number of orders corresponding to the order IP address may be calculated by:

(1) the difference r=xmax-Xmin in the number of IP data from day n to day m is determined. Wherein n and m refer to days from the current time, and can be set arbitrarily according to actual requirements; xmax is the number of IPs from current to m days ago, xmin is the number of IPs from current to n days ago, and R is the range of IP data required to calculate the score of the brush bill for each user. Illustratively, if the IP information is taken in the next week, n may be 0, m may be 7, xmin may be 0, and xmax may be the amount of IP data in 7 days. If the last week of IP data needs to be acquired, n may be 7, m may be 14, xmin is IP data within 7 days, and Xmax is IP data amount within 14 days.

(2) Grouping R according to a preset group. The above groups may be set according to actual conditions, and exemplary, IP addresses may be divided into 3 groups according to south, middle and north China. And the duplication removal can be performed according to the IP address, namely, the corresponding relation between the same IP address and the account number only appears once. And determining the number y of the accounts corresponding to each IP after the duplicate removal.

(3) And determining the order score of the order corresponding to the account number according to y. For example, if y=1, the order corresponding to the account may have a score of 0, if y is greater than or equal to 2 and y <4, the order corresponding to the account may have a score of 10 x (y/10+0.05), if y is greater than or equal to 4 and <10, the order corresponding to the IP address may have a high suspicion rate, and if y is greater than or equal to 10, an excess score of 2 may be added to the total score of 10. Of course, the correspondence between the y range and the score of the bill may be preset, which is not particularly limited in the embodiment of the present invention.

The address assignment unit is configured to analyze the attribution of the IP address, including country, province, city, county, and the like, to which the IP address belongs, according to the IP address when the user places the order. When matching is carried out according to the order receiving address and the IP address, if the country, the province, the city and the county/region are consistent, the order item is scored as 0, the province and the city are consistent but other inconsistent, the order item is scored as 2, the province is consistent but other inconsistent, the order item is scored as 4, the country is consistent, the order item is scored as 7, and if the address is completely inconsistent, the order item is scored as 10.

The order delivery process typically includes order shipping, courier consignment, and receipt of a receipt for a brush score for the delivery time of the order. As a possible implementation, the order score may be calculated according to a time interval of the order delivery time and the check-in time (hereinafter, abbreviated as T1) and a time interval of the delivery time and the check-out time (hereinafter, abbreviated as T2).

For example, the attribute of the commodity of the order is firstly determined, if the commodity belongs to a virtual product, such as video member recharging, website member recharging and the like, the score base of the order is divided into 4 points, if the commodity belongs to a physical commodity, and both T1 and T2 are smaller than 5 minutes, the score of the order is 10 points, T1<1 hour and T2<1 hour, the score of the order is 9 points, T1<1 hour and T2<2 hour, the score of the order is 8 points, T1<1 hour and T2<3 hours, the score of the order is 7 points, T1<1 hour and T2<5 hours, the score of the order is 6 points, T1<1 hour and T2<7 hours, the score of the order is 4 points, T1<1 hour and T2 hours, the score of the order is 3 points, and other points are 0 points, and if the order is 0 points, the order can be reduced within the time interval of T1< 2> and T2 can be rapidly distributed within the interval of the supplier. Of course, the correspondence between the distribution time interval and the score of the bill may be preset.

After determining the three item score, the final score of the order may be determined, where the score of the final score may be the sum of the three item scores, or may be the maximum value, the minimum value, or the like of the three item scores. When the evaluation score exceeds a preset score threshold, the order can be determined to be the data of the brush bill, and therefore the order data can be deleted from the order data of the corresponding account. The preset score threshold may be set according to actual needs, for example, may be 6 score, 10 score, etc.

In one possible embodiment, whether the order is the order-brushing data may be determined according to the following conditions (for convenience of description, the number of orders corresponding to the order-placing IP address, the matching degree of the order-placing IP address and the receiving address, and the delivery time of the order are referred to as a condition one, a condition two, and a condition three, respectively): if the three condition scores are all more than 6 points, the order is a brushing order, if the third condition score is less than 6 points, the first condition score is more than 8 points, and the second condition score is more than 8 points, and the order is also determined to be a brushing order; if the second condition is less than 6 minutes, the first condition is more than 8 minutes, and the third condition is more than 8 minutes, the order is also determined to be a brushing order; if condition one is less than 6 minutes, wherein conditions two and three are both greater than 9 minutes, the order is also determined to be a brush order. If the single condition is 12 minutes, the order is directly judged to be a brush order.

Through the technical scheme, the order form of the bill is judged from three aspects, so that the bill detection rate of the bill is improved, the effectiveness of target user data is further improved, the data redundancy is reduced, and the accuracy of user portrait construction is further improved.

In a possible embodiment, the user data may further include request log data of the user, where the request log data may include a request sent by the user, a time sequence in which the user sends various requests, an IP address when the user sends the request, and device information. The identification of the above-mentioned machine-made false orders can be performed according to the following steps:

and then the machine-made false order data can be removed from the user data to obtain target user data of the users.

In this embodiment, each page in the b2b e-commerce platform may be classified in advance according to a menu, and continuity of page access levels may be set, where the menu is used to identify an entry of a sub-page of the current page. By way of example, pages may be divided into levels 1-5 according to their connection order, and a jump from level 1 to level 3 page may be prohibited. The request of the user can be buried in the process of ordering the user, namely, the request event of the user is captured. For example, a user's request is searched for and the request log is collected by an elastomer search (distributed search and analysis engine at the elastomer Stack core), logstack (which is a platform for application logging, event transmission, processing, management and search), and Kibana (an open source analysis and visualization platform designed for elastomer search, which can be used to search for, view and interact with data stored in the elastomer search index) (ELK), and statistically analyze the request log. When the access sequence of the user to the pages in the generation process of a certain order detected based on the request log of the user is inconsistent with the preset page sequence, the order can be determined to be a machine-made false order, namely false data generated by machine operation.

For example: the first page related page set has no commodity evaluation page, and the access is to jump from the first page to the commodity evaluation page directly, which is regarded as a forging request. For this case, a verification process may be triggered, requiring the user to perform a graphical verification code, thereby intercepting the counterfeit behavior of the robot.

Through the technical scheme, the true active user can be determined, the influence of false data generated by machine operation on the user rating is avoided, and the accuracy of the user rating is improved.

For the false order data, the false order data can be identified according to the following steps:

and determining the order as false order data under the condition that the receiving address of the order is inconsistent with the actual delivery address of the order.

The receiving address of the order, namely the receiving address filled by the user when the user places the order, and the actual delivery address of the order can be obtained according to the final positioning information after the delivery is completed by the hand-held terminal of the courier. If the two addresses can be matched, that is, the difference of the geographic positions of the two addresses is within a preset range, the order is determined to be a normal order, and if the difference of the geographic positions of the two addresses exceeds the preset range, the order is determined to be a false order. The above-mentioned preset range may be set according to actual conditions, for example, may be set to 10m, 100m, or the like. Of course, the order evaluation score may be determined according to the degree of matching of the receiving address with the country, province, city, district/county, street, and district/village of the actual delivery address. Specific evaluation processes can be referred to above, and will not be described here.

According to the technical scheme, abnormal orders in the order data of each user are removed to obtain target user data, and then each user is rated based on the target user data, so that the influence of the abnormal orders on the rating result is eliminated, and the rating accuracy is improved.

And removing abnormal order data in the order data of the purchasing units to obtain target data of each purchasing unit of which the user performs final purchasing unit rating.

In one possible embodiment, the target level for each user may be determined based on target user data for each user by:

determining the user data growth rate of each user in a preset time period;

The preset time period may be set according to actual needs, for example, may be 1 year, half year, 30 days, 15 days, 7 days, etc., which is not particularly limited by the present invention. The user data may include an order amount, an order number, a collaboration range, a daily activity, etc., and the corresponding user data growth rate within the preset time period may include an order amount growth rate, an order number growth rate collaboration range growth rate, and a daily activity growth rate within the preset time period. The daily activity of the user can be determined by the number of times the user uses the e-commerce platform.

In one possible implementation, the user data growth rate may be calculated by the following formula

In the formula, n represents the number of months in a preset time period, R _i Representing the user data growth rate, P _i Indicating the i month/day of the preset timeIs provided. As a possible implementation, the growth rate of each item of user data may be calculated according to the above formula.

In calculating the user data growth rate, spurious orders that are counterfeited need to be removed. For example, if the number of orders in a month is 200 orders and a false order is 50 orders, the number of valid orders in a month is 150 orders, i.e. the number of orders in the target user data of a is 150 orders.

In one possible embodiment, the preset level corresponding to the user data growth rate of each user may be determined by:

As described above, a plurality of data are included in the user data, and thus, a corresponding preset rating score thereof may be determined for each user data, respectively. For example, the corresponding preset rating scores may be determined for the order amount increase rate, the order quantity increase rate, the collaboration range increase rate, and the daily activity increase rate.

In a possible embodiment, a correspondence between a growth rate interval and a rating score may be preset, and a range of the growth rate interval and a correspondence between the growth rate interval and the rating score may be set according to actual needs, which is not specifically limited in the embodiment of the present invention. For example, three growth rate intervals may be set, respectively [ p1, p 2), [ p2, p 3), [ p3, p4 ], where p1 may be 10%, p2 may be 20%, p3 may be 50%, and p4 may be 100%. Wherein, the interval [ p1, p 2) corresponds to the rating score S1, the interval [ p2, p 3) corresponds to the rating score S2, and the interval [ p3, p 4) corresponds to the rating score S3. For example, for the user data 1, if the growth rate within the preset period of time falls in the interval [ p2, p 3), the preset rating score corresponding to the user data 1 is S2.

After the rating scores corresponding to various user data of the user are obtained, the statistical value of the rating scores of the various user data can be determined as the target rating score of the user. The statistical value may be an average value, a weighted average value, a maximum value, a minimum value, or the like, which is not particularly limited in the present invention. In the case that the statistical value is a weighted average value, the weights of various user data may be preset according to actual needs.

In one possible embodiment, the target rating score S for the user may be calculated by the following formula:

wherein n is the type of user data, S _i And (5) grading scores corresponding to the ith user data growth rate.

In one possible embodiment, different target rating score ranges may be divided in advance, and the level corresponding to each target rating score range may be set, so that after determining the target rating score of the user, the level corresponding to the target rating score is determined according to the range corresponding to the target rating score.

Illustratively, the purchasing unit may be divided into three ranks A, B, C from top to bottom, with the target score ranges for the three ranks being [ S1, S2), [ S2, S3), [ S3, S4 ], respectively. If the purchase unit a target rating score falls in [ S1, S2), the purchase unit a is rated as A.

In one possible embodiment, the user may also be rated according to the user's underlying information data, behavior data, and tag data. The basic information data may include the enterprise scale, business hours, etc. of the user. The behavioral data may include order data of the user and behavioral data in the b2b e-commerce platform, including browsing, collecting, sharing, and the like. The tag data may be set for different users, such as may be an initial rating of the user.

As a possible implementation manner, a scoring rule may be preset for the basic information data, the behavior data and the tag data of the user, so as to determine a target rating score of the user, and further determine the rating of the user based on the target rating score of the user. For example, a business scale of 500 persons or more corresponding score s1, 100-500 persons corresponding score s2, 50-100 persons corresponding score s3, 50 persons or less corresponding score s4 may be set. Setting the score s5 corresponding to the total times of browsing, collecting, sharing and purchasing by the user more than 50 times and the score s6 below 50 times. The corresponding scores of the initial ratings of the users from high to low are set to be s7, s8, s9 and the like respectively. The present invention is not particularly limited thereto.

In one possible embodiment, the users may also be clustered according to their target rating scores to determine good users. Such as K-means clustering algorithms, DBSCAN algorithms, etc. may be employed.

After the ratings of the users are determined, commodity recommendation, quota setting and the like can be performed for the users according to the grades of the users.

In one possible embodiment, the user data, the user level and the user identification may be stored in a target database, and the related personnel may perform data query and analysis on the user level, the tag, the affiliated unit, the sales contract and other dimensions. The related personnel can also add the user data focused on the front end display area in a simple dragging mode, and the selected data index can be displayed at the front end. The presentation data may be in the form of a table, text card, index card, dashboard, line graph, bar graph, ring graph, radar graph, rectangular tree, scatter graph, funnel graph, and the like.

By applying the embodiment of the invention, multiparty data collection is realized, more data resources are acquired, the data value is efficiently mined by scoring the user, the data value is fully utilized, and the value change is realized. In addition, the user image is generated, each user is intuitively known, on one hand, accurate marketing is facilitated, marketing cost is reduced, on the other hand, new business and products are developed according to user demands, and customized and personalized services are provided, so that income is increased. And the selection of suppliers is realized by fully knowing the users, so that the transaction risk of the users is reduced. And moreover, the process of manually analyzing the data is omitted by automatically acquiring and analyzing the data, the labor cost is reduced, the overall efficiency is improved, the support is provided for decision making through the data, and the risk brought by human decision making errors can be reduced.

Based on the same inventive concept, the present invention also provides a user rating system applied to a b2b e-commerce platform, as shown in fig. 3, the system 300 may include:

the acquiring module 301 is configured to acquire user data of each user in the b2b e-commerce platform; the user data comprises order data;

the rejecting module 302 is configured to reject abnormal order data from the user data according to a preset abnormal order recognition rule, so as to obtain target user data of each user; the abnormal order data includes: brushing order data, machine-made dummy order data and/or dummy order data;

a determining module 303, configured to determine a target level of each user based on target user data of each user.

The exemplary embodiment of the invention also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor for causing the electronic device to perform a method according to an embodiment of the invention when executed by the at least one processor.

The exemplary embodiments of the present invention also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the present invention.

The exemplary embodiments of the invention also provide a computer program product comprising a computer program, wherein the computer program, when being executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the invention.

Referring to fig. 4, a block diagram of an electronic device 400 that may be a server or a client of the present invention will now be described, which is an example of a hardware device that may be applied to aspects of the present invention. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 400 includes a computing unit 401 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In RAM 403, various programs and data required for the operation of device 400 may also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

Various components in electronic device 400 are connected to I/O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 may be any type of device capable of inputting information to the electronic device 400, and the input unit 406 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. The output unit 407 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 404 may include, but is not limited to, magnetic disks, optical disks. The communication unit 409 allows the electronic device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 401 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the respective methods and processes described above. For example, in some embodiments, the user rating method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 400 via the ROM 402 and/or the communication unit 409. In some embodiments, the computing unit 401 may be configured to perform the user rating method by any other suitable means (e.g., by means of firmware)

Program code for carrying out methods of the present invention may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims

1. A user rating method applied to a b2b e-commerce platform, the method comprising:

removing abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of the users; the abnormal order data includes: brushing order data, machine-made dummy order data and/or dummy order data; wherein the machine-made false order data is false order data generated by machine operation;

2. The method of claim 1, wherein the obtaining the user data of each user in the b2b e-commerce platform comprises:

acquiring user data of each user from different service systems; the business system comprises: b2b e-commerce platform, contract management platform and user qualification management platform.

3. The method according to claim 1, wherein, in the case where the abnormal order data includes a brush order data, the removing abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of the users includes:

4. The method of claim 1, wherein the user data comprises request log data; and in the case that the abnormal order data includes machine-made false order data, removing the abnormal order data from the user data according to a preset abnormal order identification rule to obtain target user data of each user, including:

5. The method according to claim 1, wherein, in the case where the abnormal order data includes false order data, the removing abnormal order data from the user data according to a preset abnormal order identification rule, to obtain target user data of the users, includes:

6. The method of claim 1, wherein said determining a target level for each of said users based on target user data for each of said users comprises:

determining the user data growth rate of each user in a preset time period;

7. The method of claim 6, wherein the user data growth rate comprises: order amount increase rate, order quantity increase rate, daily activity increase rate;

8. A user rating system for use with a b2b e-commerce platform, the system comprising:

9. An electronic device, comprising:

a processor; and

a memory in which a program is stored,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any of claims 1-7.

10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.