Grain storage transaction background push information processing method and system based on big data

Abstract

The invention provides a grain storage transaction background push information processing method and system based on big data, and belongs to the technical field of information push, and the method comprises the steps: carrying out the calculation based on a first weight corresponding to the first historical data of a first user, and obtaining a first evaluation value of the first user; performing grade evaluation on the first user based on the first evaluation value to obtain a first grade corresponding to the first user; and pushing information to the first user based on a pushing strategy corresponding to the first level. According to the big data-based grain storage transaction background push information processing method and system provided by the invention, the user experience can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of information push technology, and more specifically, to a method and system for processing information push in the background of grain storage transactions based on big data. Background Art

[0002] In the field of grain storage trading, with the rapid development of information technology, big data applications have become an important means to improve platform operation efficiency and service quality. Traditional information push methods often ignore the personalized needs of users and adopt a "one-size-fits-all" push strategy, resulting in information redundancy and poor user experience. In order to overcome this drawback, the industry has begun to explore push information processing methods based on big data to achieve accurate information delivery and personalized services for users.

[0003] However, existing big data push technologies mostly focus on data collection and preliminary analysis. There are still many shortcomings in how to deeply explore user behavior characteristics, scientifically evaluate user value, and formulate differentiated push strategies, which leads to poor user experience. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for processing grain storage transaction background push information based on big data to improve user experience.

[0005] In a first aspect of the embodiments of the present disclosure, a method for processing information pushed by a grain storage transaction background based on big data is provided, comprising: Calculating based on a first weight corresponding to the first historical data of the first user to obtain a first evaluation value of the first user; Performing a level evaluation on the first user based on the first evaluation value to obtain a first level corresponding to the first user; Information is pushed to the first user based on the push policy corresponding to the first level.

[0006] A second aspect of the disclosed embodiment provides a grain storage transaction backend push information processing system based on big data, including: A user evaluation calculation module, configured to calculate based on a first weight corresponding to first historical data of a first user to obtain a first evaluation value of the first user; A user level determination module, configured to perform a level evaluation on a first user based on the first evaluation value to obtain a first level corresponding to the first user; The information push module is used to push information to the first user based on the push strategy corresponding to the first level.

[0007] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned method for processing information pushed by the background of grain storage transactions based on big data are implemented.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned grain storage transaction background push information processing method based on big data are implemented.

[0009] The beneficial effects of the grain storage transaction backend push information processing method and system based on big data provided by the disclosed embodiment are: the disclosed embodiment realizes accurate quantitative evaluation of user behavior and clearly divides users into different levels by analyzing the first historical data such as transaction records, browsing behaviors, and user feedback, and reasonably configuring the first weight for them. For users of different levels, the disclosed embodiment can intelligently match differentiated push strategies, effectively improve the pertinence and effectiveness of information, reduce the interference of users receiving irrelevant information, and enhance user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a process for processing information pushed by a grain storage transaction background based on big data provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a grain storage transaction backend push information processing system based on big data provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic diagram of a process for processing information pushed by a grain storage transaction background based on big data provided by an embodiment of the present disclosure, the method comprising: S101: Calculate a first weight corresponding to first historical data of a first user to obtain a first evaluation value of the first user.

[0015] In this embodiment, the first historical data refers to various data information related to the user's past behavior and performance on the grain storage trading platform, such as transaction record data, browsing behavior data, user feedback data, etc.

[0016] In this embodiment, a first weight is assigned to the corresponding first data based on the business goal.

[0017] For example, for transaction record data, if the platform needs to increase the total transaction amount in the short term, the weight of the transaction amount can account for a larger proportion, because the transaction record data is directly related to the scale of capital flow. For browsing behavior data, if it is found that users frequently browse information on a certain type of high-value-added grain storage products, the browsing weight of the corresponding products will be increased, guiding subsequent push to focus on such products to meet the potential needs of users. The weight of user feedback data can be set based on factors such as the timeliness and pertinence of feedback. For example, users who provide timely feedback and constructive opinions will have their feedback data weight increased, prompting the platform to optimize its push strategy.

[0018] In this embodiment, the first evaluation value of the first user may be obtained by weighted summation.

[0019] The first evaluation value of the first user is obtained by multiplying each type of first historical data by its corresponding first weight and then adding them up. Assuming that the transaction amount weight is 0.4, and the cumulative transaction amount of a user in the past year is 1 million yuan, the score for this item is 40 points; the weight of browsing a key grain storage product information is 0.2, and the user browses 50 times, the score for this item is 10 points, etc. Through such calculations, the comprehensive performance and potential value of the user on the platform can be comprehensively reflected.

[0020] S102: Evaluate the level of the first user based on the first evaluation value to obtain a first level corresponding to the first user.

[0021] In this embodiment, a grading system can be constructed based on business needs and data analysis.

[0022] The first level can be divided into level 1, level 2 and level 3. Level 1 users may be customers who have just come into contact with the platform, have low trading activity and limited understanding of the market; level 2 users may be users with certain trading experience who are beginning to pay attention to product diversity and market trends; level 3 users may be users who trade frequently, have strong funds, and have both deep and broad needs for industry information.

[0023] The calculated first evaluation value of the first user is compared with the set grade classification standard to determine the first grade corresponding to the first user.

[0024] S103: Push information to the first user based on the push policy corresponding to the first level.

[0025] In this embodiment, different first levels correspond to different push strategies. For first-level users, the push content focuses on the popularization and guidance of basic knowledge. For example, push videos explaining the grain storage transaction process, graphic materials introducing common grain storage varieties, notifications of novice discount activities, etc., to help them quickly familiarize themselves with the platform and lower the entry threshold. Second-level users can recommend information combined with market analysis. For example, a comparison of the advantages of popular grain storage products in the season, a dynamic analysis report on regional market supply and demand, exclusive trading package discounts, etc., to help them expand their business. The push content for third-level users may include the progress of new international grain storage technology research and development, bulk grain storage transaction cooperation opportunities, and customized market risk warnings, etc., to meet their needs for in-depth exploration of market value.

[0026] In this embodiment, the information can be accurately sent to the first user according to a predetermined push strategy through the platform's built-in message push system, such as mobile APP push notifications, web page pop-up windows, emails and other channels.

[0027] This embodiment can also track the user's behavior of receiving, opening, reading, interacting with the push information, and provide feedback to the background to further optimize the push strategy and form a closed loop of continuous improvement.

[0028] For example, suppose there is a user named Mr. Zhang on the grain storage trading platform. In the past year, his transaction record data shows that the cumulative transaction amount has reached 800,000 yuan, the transaction frequency is 10 times, and the transaction objects are mostly local small grain traders; browsing behavior data shows that he frequently browses information on high-end grain storage products such as high-quality wheat and organic rice, a total of 60 times, and also reads multiple market analysis reports; user feedback data records that he has promptly reported data errors in the pushed information and proposed suggestions for optimizing the transaction search function.

[0029] If the current platform goal is to increase high value-added grain storage transactions in the short term, the transaction amount weight is set to 0.5, the high-end grain storage product browsing weight is 0.3, and the user feedback timeliness weight is 0.2. After weighted summation, Mr. Zhang's first evaluation value is calculated as: (800,000×0.5)+(60×0.3)+(0.2×10)=40+18+2=60 points.

[0030] According to the level classification, he is a second-level user. After that, the platform pushes the comparison of the advantages of popular grain storage products in the season, the dynamic analysis report of regional market supply and demand, and exclusive trading package discounts through the APP. At the same time, it tracks Mr. Zhang's interactive behavior on the pushed information, and feeds back to the backend for continuous optimization strategy to help him expand his business.

[0031] It can be concluded from the above that this embodiment realizes accurate quantitative evaluation of user behavior and clearly divides users into different levels by analyzing the first historical data such as transaction records, browsing behaviors, and user feedback, and reasonably configuring the first weight for them. For users of different levels, this embodiment can intelligently match differentiated push strategies, effectively improve the pertinence and effectiveness of information, reduce the interference of users receiving irrelevant information, and enhance user experience.

[0032] In one embodiment of the present disclosure, calculating based on a first weight corresponding to first historical data of a first user to obtain a first evaluation value of the first user includes: The first historical data of the first user is updated based on a set update cycle to obtain second historical data; Updating a first weight corresponding to the first historical data based on the second historical data to obtain a second weight corresponding to the second historical data; A first evaluation value of the first user is obtained by performing calculation based on the second weight corresponding to the second historical data of the first user.

[0033] In actual business scenarios, user behaviors, preferences, and related situations change dynamically. Setting an update cycle is to ensure that the data used to evaluate users can reflect the user's latest status in a timely manner. For example, for users of a grain storage trading platform, their trading habits may change over time. Originally, they only focused on trading with small local grain traders, but later they may expand to cooperation with large grain companies.

[0034] In this embodiment, the updated first historical data may include transaction record data, browsing behavior data, user feedback data, etc. For example, in terms of transaction record data, the transaction amount, transaction object, and transaction frequency newly generated during the update period will be added to the second historical data; in browsing behavior data, the newly browsed stored grain product information, browsing time, and other changes will be updated and recorded.

[0035] In this embodiment, since the second historical data reflects the new behavior of the user, the first weight previously set based on the first data is no longer applicable to the evaluation of the new data. It is necessary to adjust the weight corresponding to each data according to the new data situation (the second historical data) to obtain the second weight.

[0036] If it is found that the number of users browsing a certain type of emerging grain storage product has increased dramatically during the update cycle, and the platform hopes to promote the transaction of such products, the weight (second weight) corresponding to the browsing behavior data of the product can be increased after the update; if the newly collected user feedback data shows that users are very concerned about transaction security, and the platform wants to focus on solving this problem to improve user satisfaction, the weight (second weight) related to the user feedback data can be increased. By reallocating the weights of each data dimension, the scientificity and effectiveness of the evaluation system can be ensured.

[0037] In this embodiment, a weighted sum may be performed on the second weights corresponding to the second historical data to obtain the first evaluation value of the first user.

[0038] The new first evaluation value is obtained by multiplying and accumulating various types of second historical data with their corresponding second weights. For example, the new transaction record data (such as the transaction amount within the update period, etc.) is multiplied by the updated transaction record data weight (second weight), plus the new browsing behavior data multiplied by its corresponding second weight, plus the new user feedback data multiplied by the corresponding second weight, etc., and finally the first evaluation value that can reflect the comprehensive performance and potential value of the user in the latest stage is obtained.

[0039] For example, suppose a grain storage trading platform sets an update cycle of 3 months. User Xiao Li's transaction record data has changed significantly in the past 3 months. He used to only do sporadic rice transactions with local small grain traders, but in the new cycle, he began to cooperate frequently with large grain companies. The transaction amount soared from an average of 20,000 yuan per month to 100,000 yuan, and the transaction frequency also increased from 2 times a month to 6 times.

[0040] In terms of browsing behavior data, Xiao Li used to occasionally browse information about ordinary rice, but recently he has paid special attention to information about emerging selenium-rich rice products. His browsing time totaled 30 hours, and he also read in depth many related technical analysis reports.

[0041] In terms of user feedback data, he reported that there were security risks in the contract signing process of the platform's transaction process, and put forward detailed suggestions for improvement.

[0042] In view of the fact that the platform currently wants to vigorously promote selenium-rich rice products and improve the transaction security of the platform, the weight of browsing behavior data of selenium-rich rice is increased to 0.4, the weight of user feedback data is increased to 0.3, the weight of transaction amount is set to 0.2, and the weight of transaction frequency is 0.1. The weighted sum is: (100,000×0.2+6×0.1+30×0.4+1×0.3)=14.9 points, which is Xiao Li's latest first evaluation value, accurately reflecting his current comprehensive value to the platform.

[0043] From the above, it can be concluded that the first evaluation value calculated by this embodiment is no longer based on static, outdated data and weights, but takes into account the user's behavior over time and the result of the adjustment of the platform's business direction. It can dynamically present the user's relative importance, value and potential development trend to the platform at different stages, and provide a powerful and up-to-date basis for subsequent more accurate user classification and push strategy formulation operations, which helps the platform better meet user needs, optimize operational strategies, and improve user experience and business benefits.

[0044] In one embodiment of the present disclosure, updating a first weight corresponding to the first historical data based on the second historical data to obtain a second weight corresponding to the second historical data includes: In response to a change rate between the second historical data and the corresponding first historical data being greater than a preset change rate, a first weight corresponding to the first historical data is updated based on a first adjustment step to obtain a second weight.

[0045] In this embodiment, the change rate of the second historical data compared with the first historical data can be continuously monitored and calculated. The change rate reflects the degree of dynamic change in the user's behavior, preference, etc.

[0046] For example, on a grain storage trading platform, a sudden and substantial increase in transaction amounts in transaction record data, a sharp increase in browsing time for specific high-value-added grain storage products in browsing behavior data, or a change in user feedback data from occasional mentions to frequent and in-depth feedback, will all lead to a higher rate of change.

[0047] When the calculated rate of change is greater than the preset rate of change, it indicates that the user's behavior pattern has changed, and the weight needs to be adjusted in time to adapt to this new situation to ensure the accuracy of the evaluation.

[0048] In this embodiment, the first adjustment step is a pre-set adjustment amplitude value, and the first adjustment step determines the speed and magnitude of each weight adjustment. If the rate of change far exceeds the preset value, the first weight corresponding to the corresponding data is updated according to the established first adjustment step. For example, if it is found that a user's browsing volume of organic grain storage products has increased rapidly during the update cycle, far exceeding the preset rate of change, and the platform intends to promote transactions of such products, the first weight related to the browsing of organic grain storage products will be adjusted upward according to the first adjustment step to obtain a new second weight, so that when the user evaluation value is calculated later, the browsing behavior data can play an influence that is more in line with the actual situation of the current user, so that the entire evaluation system can closely follow the user dynamics and always provide accurate and effective evaluation results.

[0049] In this embodiment, the calculation formula of the change rate is:

[0050] in, It is expressed as the change rate of the second historical data and the corresponding first historical data; It is expressed as the sum of the first historical data, which is the cumulative value of the data of the corresponding dimension in the previous period; It is expressed as the sum of the second historical data, which refers to the cumulative value of the dimension data newly acquired during the update cycle, such as the total sum of all transaction amounts during the update cycle; It is expressed as an adjustment coefficient, which is a value pre-set according to the platform's business focus and data importance. The value range can be between 0 and 2 (if the platform values ​​the impact of a certain data dimension on the overall evaluation, the coefficient can be close to 2, otherwise it is close to 0). The adjustment coefficient can flexibly adjust the sensitivity of the change rate to different data, so that more critical data can be more significantly reflected when it changes; It is expressed as a time decay factor. Through the time decay factor, the data changes closer to the current time have a greater weight on the rate of change, which can highlight the importance of recent changes and avoid interference in the current judgment of the rate of change due to data that is too old.

[0051] The time decay factor t can be expressed as:

[0052] in, Represents the current time, Indicates the end time of the previous cycle. Expressed as a set duration. e is a natural constant, and the set duration It is a time constant set by the platform based on business characteristics, such as half a year, one year, etc.

[0053] For example, for the dimension of transaction amount, the total transaction amount in the previous cycle is 1 million yuan (the sum of the first historical data), and the total transaction amount in this update cycle is 1.5 million yuan (the sum of the second historical data). The adjustment coefficient is set to 1.2. Assuming that the time interval between the current time and the end of the previous cycle meets the "time decay factor" calculated to be 0.8, the change rate .

[0054] Compared with conventional calculations, this application takes into account the adjustment of data importance and the influence of time factors, and can more accurately reflect the degree of change of data in line with actual business conditions, providing a more reasonable basis for whether to adjust the weight according to the change rate in the future.

[0055] From the above, it can be concluded that this embodiment, by setting a preset change rate as a trigger condition, can accurately screen out situations where user behavior has changed significantly, avoid frequent adjustments to weights due to small fluctuations, and reduce unnecessary consumption of computing resources. Secondly, updating the weights according to the first adjustment step can ensure that the weight adjustment range is reasonable and orderly, and will not cause weight imbalances due to sudden changes in user data, so that the evaluation system remains stable. This way of dynamically adjusting weights can closely fit the dynamic changes in user behavior, making the evaluation of users more accurate, thereby providing a more reliable basis for subsequent personalized service push, grading and other operations, and effectively improving the platform's operating efficiency and user experience.

[0056] In one embodiment of the present disclosure, it also includes: The push strategy corresponding to the first level is updated based on the second historical data.

[0057] In this embodiment, the second historical data reflects the user's new behavior performance, preference changes, etc. during the update cycle. For example, on the grain storage trading platform, the user rarely browsed high value-added grain storage products before, but frequently viewed related information in the new stage, or originally only conducted small and scattered transactions, but now the transaction amount has increased significantly and the transaction frequency has also increased, etc. These new data show the change of user status.

[0058] The push strategy corresponding to the first level is formulated based on the old user characteristics. When the second historical data is updated, it means that the user is no longer suitable for the original push content. For example, the first-level user originally received basic knowledge push, but if his trading activity increases rapidly, according to the new second historical data, he is closer to the characteristics of the second-level user.

[0059] Therefore, it is necessary to adjust the push strategy based on the new second historical data. The simple information originally intended for primary users can be updated to more in-depth content combined with market analysis, or the categories of pushed products and the focus of promotional activities can be adjusted, so that the pushed information can better meet the actual needs and status of users at the moment, thereby increasing users' attention and acceptance of pushed content, optimizing user experience, and helping the platform business development.

[0060] In one embodiment of the present disclosure, calculating based on a first weight corresponding to first historical data of a first user to obtain a first evaluation value of the first user includes: Calculate a first evaluation value of the first user based on the first formula; The first formula is:

[0061] in, is represented by the first evaluation value of the first user, Represented as the i-th first historical data, It is represented as the weight corresponding to the first historical data of the ith period, It is expressed as the time adjustment factor corresponding to the i-th first historical data, It is represented as the preference adjustment factor of the i-th first historical data, and n is represented as the number of first historical data.

[0062] In this embodiment, the first historical data It covers data related to the user's past on the platform, such as transaction records, browsing behavior data, user feedback data, etc. It is the basic content source of the evaluation. Different types of data reflect the user's behavioral characteristics and participation in the platform from different angles. It can be set according to the platform's business objectives to measure the relative importance of different first historical data in the overall evaluation. For example, if the platform currently focuses on increasing the transaction volume, the weight corresponding to the transaction record data may be higher, which determines the influence of each data on the final evaluation value.

[0063] can be a time decay coefficient (a pre-set constant), It is the time adjustment factor corresponding to the first historical data of the ith time, and is related to the time from the data generation time to the current time. Its role is to make the data closer to the current time play a more important role in the evaluation, because the recent data tends to better reflect the current status and trend of the user, while the influence of the earlier data will gradually decay over time, so as to avoid the old data from excessively affecting the accuracy of the current evaluation.

[0064] Taking into account the differences in preferences of different users for the behaviors reflected by different types of data, the preference adjustment factor of the first historical data is Values ​​can be assigned based on the user's inclination towards various behaviors. For example, for users who are more interested in browsing information about high value-added grain storage products, the preference adjustment factor of the corresponding browsing behavior data can be set higher, so as to further refine the measurement of the value of user behavior and better fit the characteristics of individual users.

[0065] In this embodiment, by traversing all n first historical data, for each data , and its corresponding weight , Time Adjustment Factor and the preference adjustment factor The first evaluation value of this embodiment takes into account various factors and can accurately reflect the comprehensive performance and potential value of the first user on the platform, thereby providing a scientific and effective quantitative basis for subsequent operations such as grading users and formulating push strategies.

[0066] In one embodiment of the present disclosure, it also includes: Aggregating the first historical data of the first user into a plurality of hierarchical communities based on a dynamic clustering algorithm; In response to the first evaluation value of the first user being in a critical region of two adjacent hierarchical communities, calculating the degree of belonging of the first user to the two adjacent hierarchical communities based on a membership function; Determining a hierarchical community of the first user based on the first user's degree of belonging to two adjacent hierarchical communities; Information is pushed to the first user based on a push strategy corresponding to the hierarchical community of the first user.

[0067] The traditional classification method based on fixed thresholds is relatively rigid and difficult to adapt to the complex and changeable actual situation of users. In this embodiment, a dynamic clustering algorithm can be used to use multi-dimensional user data related to grain storage transactions, such as transaction amount, transaction frequency, transaction variety, risk tolerance, and attention to market information, to comprehensively and meticulously characterize the behavioral characteristics and comprehensive status of users in grain storage transactions.

[0068] In this embodiment, users can be divided into 5-7 different level communities in real time based on data characteristics through a dynamic clustering algorithm. These communities are not fixed, but can be adjusted with the dynamic changes of user data. For example, as user trading behavior becomes more and more active and risk preferences gradually change, the level community to which they belong may also change accordingly, thereby flexibly and accurately reflecting the user's current real status in the grain storage trading ecosystem. Each level community has a corresponding feature description, such as "aggressive users", "robust users", "new users", etc., which is convenient for intuitively understanding the general situation of users in this level community.

[0069] In practice, the user's first evaluation value is likely to be in the critical area of ​​two adjacent level communities, and it is difficult to simply and clearly determine the level to which it belongs. Therefore, this embodiment constructs a membership function to comprehensively consider multiple factors, not only focusing on the recent transaction amount change rate, transaction frequency increase and decrease, which reflect the change in transaction activity, but also considering transaction stability-related factors, such as the number of transaction defaults in the past six months, the number of transaction interruptions caused by market fluctuations, etc., to measure the degree of fit between the user and the two adjacent level communities when in the critical area from a more comprehensive perspective.

[0070] The degree of belonging of the first user in two adjacent level communities is calculated based on the membership function. For example, the membership of a certain level community is calculated to be 0.6 and the other is 0.4. The membership value represents the closeness of the relationship between the user and the different level communities. When determining the level and formulating relevant push strategies later, weights can be assigned based on these memberships, indicating that the characteristics and strategies of the level community with higher membership are more inclined. This can achieve a smooth transition when dividing the levels, avoid unreasonable and frequent switching of users between adjacent levels due to some minor data fluctuations, and make the level division more in line with the actual situation of users and more reasonable.

[0071] The final level community of the first user is determined based on the calculated degree of belonging of the first user to two adjacent level communities. If the degree of belonging to "aggressive users" is 0.6 and the degree of belonging to "conservative users" is 0.4, it is determined that the user is more suitable to be classified into the level community of "aggressive users", thereby completing relatively accurate user level positioning.

[0072] It can be concluded from the above that this embodiment breaks the limitation of traditional fixed threshold division by aggregating hierarchical communities based on multi-dimensional first historical data through a dynamic clustering algorithm, and can more accurately reflect the real status and hierarchical differences of users in grain storage transactions, so that the hierarchical division fits the dynamic changes of users. Secondly, for users in critical areas, the membership function is used to calculate the degree of belonging, which avoids frequent level jumps caused by rigid division, ensures smooth and reasonable level transition, and enhances the scientificity and stability of level determination. Finally, the implementation of differentiated push strategies based on hierarchical communities greatly improves the matching degree between push information and user needs, enhances user experience, and helps the platform achieve efficient operation and precision marketing.

[0073] In one embodiment of the present disclosure, the degree of belonging of the first user to two adjacent level communities is calculated based on the second formula; The second formula is:

[0074] in, It is represented as the membership degree of the first user to the group A. It is represented as the membership degree of the first user to the group B, It is represented by the normalized value of the first historical data of the ith and They are respectively represented as the ideal characteristic values ​​of hierarchical community A and hierarchical community B in the i-th dimension, It is expressed as the weight of the first historical data of the ith period, Expressed as adjustment coefficient.

[0075] In this embodiment, x represents a user data vector including multiple influencing factors, for example , It can be the standardized value of data in different dimensions, such as the rate of change of transaction amount in the past month, the increase or decrease of transaction frequency, the number of transaction defaults in the past six months, etc. (standardization can use common normalization methods to make its range between 0 and 1, etc.).

[0076] and They are respectively represented as the ideal characteristic values ​​of level community A and level community B in the i-th dimension. The ideal characteristic values ​​can be obtained by statistical analysis of a large amount of user data belonging to the level community in historical data, cluster center calculation, etc., and are also standardized.

[0077] The weight of the first historical data It is used to reflect the relative importance of different dimensional factors in determining the degree of attribution. It can be pre-set according to the platform business focus (the value range is between 0 and 1, and all The sum is 1).

[0078] Adjustment coefficient Used to control the sensitivity of the function, The larger the value is, the more sensitive the membership function is to data differences. It can be adjusted according to the actual application scenario and data characteristics. In this embodiment, the value can be greater than 0 (for example, try to optimize the value between 1 and 10).

[0079] In this embodiment, the actual data of the user is compared with the ideal characteristic values ​​of two adjacent level communities in various dimensions, and the weights of various dimensions and adjustment coefficients are comprehensively considered to calculate the level community A ( ) and hierarchical community B ( ). For example, calculate , , it can intuitively reflect the degree of connection between users and communities of different levels, and then be used for subsequent operations such as reasonably determining the level of user communities and formulating push strategies. Compared with the existing technology, it more comprehensively considers factors such as multi-dimensional data, weights, and sensitivity adjustment, and is more in line with the needs of complex actual application scenarios.

[0080] It can be concluded from the above that this embodiment can accurately quantify the degree of close association between users and adjacent level communities A and B by comprehensively considering the first historical data of multi-dimensional standardization, the weights of each dimension, the ideal characteristic values ​​of the level community, and the adjustment coefficient, to provide a reliable basis for the strategy, improve the user experience and satisfaction on the platform, and optimize. This helps to avoid the ambiguity and one-sidedness of traditional classification, making the level determination more scientific and reasonable, thereby accurately pushing information and formulating personalized service platform operation effects in the future.

[0081] Corresponding to the method for processing information pushed by the grain storage transaction background based on big data in the above embodiment, Figure 2 This is a structural block diagram of a grain storage transaction backend push information processing system based on big data provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The grain storage transaction background push information processing system 20 based on big data includes: a user evaluation calculation module 21, a user level determination module 22, and an information push module 23.

[0082] The user evaluation calculation module 21 is used to calculate based on the first weight corresponding to the first historical data of the first user to obtain a first evaluation value of the first user; A user level determination module 22, configured to perform a level evaluation on the first user based on the first evaluation value to obtain a first level corresponding to the first user; The information push module 23 is used to push information to the first user based on the push strategy corresponding to the first level.

[0083] In one embodiment of the present disclosure, the user evaluation calculation module 21 is specifically used for: The first historical data of the first user is updated based on a set update cycle to obtain second historical data; Updating a first weight corresponding to the first historical data based on the second historical data to obtain a second weight corresponding to the second historical data; A first evaluation value of the first user is obtained by performing calculation based on the second weight corresponding to the second historical data of the first user.

[0084] In one embodiment of the present disclosure, the user evaluation calculation module 21 is further used to: Updating a first weight corresponding to the first historical data based on the second historical data to obtain a second weight corresponding to the second historical data includes: In response to a change rate between the second historical data and the corresponding first historical data being greater than a preset change rate, a first weight corresponding to the first historical data is updated based on a first adjustment step to obtain a second weight.

[0085] In one embodiment of the present disclosure, the user evaluation calculation module 21 is further used to: The push strategy corresponding to the first level is updated based on the second historical data.

[0086] In one embodiment of the present disclosure, the user evaluation calculation module 21 is further used to: Calculate a first evaluation value of the first user based on the first formula; The first formula is:

[0087] in, is represented by the first evaluation value of the first user, Represented as the i-th first historical data, It is represented as the weight corresponding to the first historical data of the ith period, It is expressed as the time adjustment factor corresponding to the i-th first historical data, It is represented as the preference adjustment factor of the i-th first historical data, and n is represented as the number of first historical data.

[0088] In one embodiment of the present disclosure, the information push module 23 is specifically used to: Aggregating the first historical data of the first user into a plurality of hierarchical communities based on a dynamic clustering algorithm; In response to the first evaluation value of the first user being in a critical region of two adjacent hierarchical communities, calculating the degree of belonging of the first user to the two adjacent hierarchical communities based on a membership function; Determining a hierarchical community of the first user based on the first user's degree of belonging to two adjacent hierarchical communities; Information is pushed to the first user based on a push strategy corresponding to the hierarchical community of the first user.

[0089] In one embodiment of the present disclosure, the information push module 23 is further used to: Calculate the first user's belonging degree in two adjacent level communities based on the second formula; The second formula is:

[0090] in, It is represented as the membership degree of the first user to the group A. It is represented as the membership degree of the first user to the group B, Represented as the standardized value of the i-th first historical data, and They are respectively represented as the ideal characteristic values ​​of hierarchical community A and hierarchical community B in the i-th dimension, It is expressed as the weight of the first historical data of the ith period, Expressed as adjustment coefficient.

[0091] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0092] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0093] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0094] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0095] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the background push information processing method for grain storage transactions based on big data provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0096] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0097] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0098] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0101] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0102] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0103] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for processing information pushed by the background of grain storage transactions based on big data, characterized in that: include: Calculating based on a first weight corresponding to the first historical data of the first user to obtain a first evaluation value of the first user; Performing a level evaluation on the first user based on the first evaluation value to obtain a first level corresponding to the first user; Information is pushed to the first user based on the push policy corresponding to the first level.

2. The method for processing grain storage transaction background push information based on big data according to claim 1, characterized in that: The calculating based on the first weight corresponding to the first historical data of the first user to obtain the first evaluation value of the first user includes: The first historical data of the first user is updated based on a set update cycle to obtain second historical data; updating a first weight corresponding to the first historical data based on the second historical data to obtain a second weight corresponding to the second historical data; A first evaluation value of the first user is obtained by performing calculation based on the second weight corresponding to the second historical data of the first user.

3. The method for processing information pushed by the background of grain storage transaction based on big data according to claim 2, characterized in that: The updating of the first weight corresponding to the first historical data based on the second historical data to obtain the second weight corresponding to the second historical data includes: In response to a change rate between the second historical data and the corresponding first historical data being greater than a preset change rate, a first weight corresponding to the first historical data is updated based on a first adjustment step to obtain a second weight.

4. The method for processing grain storage transaction background push information based on big data according to claim 2, characterized in that: Also includes: The push strategy corresponding to the first level is updated based on the second historical data.

5. The method for processing grain storage transaction background information push based on big data according to claim 1, characterized in that: The calculating based on the first weight corresponding to the first historical data of the first user to obtain the first evaluation value of the first user includes: Calculate a first evaluation value of the first user based on the first formula; The first formula is: in, is represented by the first evaluation value of the first user, Represented as the i-th first historical data, It is represented as the weight corresponding to the first historical data of the ith period, It is expressed as the time adjustment factor corresponding to the i-th first historical data, It is represented as the preference adjustment factor of the i-th first historical data, and n is represented as the number of first historical data.

6. The method for processing information pushed by the background of grain storage transaction based on big data according to claim 1, characterized in that: Also includes: Aggregating the first historical data of the first user into a plurality of hierarchical communities based on a dynamic clustering algorithm; In response to the first evaluation value of the first user being in a critical region of two adjacent hierarchical communities, calculating the degree of belonging of the first user to the two adjacent hierarchical communities based on a membership function; Determining a hierarchical community of the first user based on the first user's degree of belonging to two adjacent hierarchical communities; Information is pushed to the first user based on a push strategy corresponding to the hierarchical community of the first user.

7. The method for processing information pushed by the background of grain storage transaction based on big data according to claim 6, characterized in that: Calculate the first user's belonging degree in two adjacent level communities based on the second formula; The second formula is: in, It is represented as the membership degree of the first user belonging to the level community A, It is represented as the membership degree of the first user belonging to the level community B, It is represented by the normalized value of the first historical data of the ith and are respectively represented as the ideal characteristic values ​​of hierarchical community A and hierarchical community B in the i-th dimension, It is expressed as the weight of the first historical data of the ith period, Expressed as adjustment coefficient.

8. A grain storage transaction background push information processing system based on big data, characterized in that: include: A user evaluation calculation module, configured to calculate based on a first weight corresponding to first historical data of a first user to obtain a first evaluation value of the first user; A user level determination module, configured to perform a level evaluation on a first user based on the first evaluation value to obtain a first level corresponding to the first user; The information push module is used to push information to the first user based on the push strategy corresponding to the first level.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images