E-commerce data updating processing method and system based on state difference real-time feedback

Abstract

The invention discloses an e-commerce data updating processing method and system based on state difference real-time feedback, and relates to the technical field of data processing, and the key points of the technical scheme are as follows: obtaining a real-time difference state vector uploaded by a user side; matching from a database to obtain a historical difference state vector of which the similarity with the real-time difference state vector is greater than a set threshold, and reading a historical commodity updating strategy and a feedback evaluation value; and generating a real-time commodity updating strategy in combination with the historical commodity updating strategy, the similarity and the feedback evaluation value, and issuing the real-time commodity updating strategy to the user side. According to the method, the difference between the real-time state vectors generated at the adjacent moments is calculated, the geometric progression coding mode is adopted to code the multi-dimensional behavior data into the lightweight state vectors, the user side uploads coding difference values only having differences to the e-commerce platform, the coding difference values uniquely correspond to the state transition path, the behavior intention can be accurately analyzed by the e-commerce platform, and the user experience is improved. And the data transmission quantity is reduced while the state change condition is reserved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, more particularly, it relates to an e-commerce data updating processing method and system based on state difference real-time feedback. BACKGROUND

[0002] With the rapid development of e-commerce platforms, there are a large number of displayable commodity information in e-commerce platforms, and in order to improve the user experience and operation efficiency, personalized recommendation service has become the main application function of e-commerce platform.

[0003] The existing e-commerce platform generally transmits the user behavior data collected by each user end to the e-commerce platform after local simplified processing, and the e-commerce platform updates the commodity data according to the overall user behavior; some e-commerce platforms directly upload the user behavior data collected by the user end to the e-commerce platform for centralized processing. However, the user end uploads complete user behavior raw data such as click coordinates and stay time, which is easy to cause high network load and response delay, and it is difficult to meet the real-time updating demand. Even if the local simplified processing only retains the core information, a large amount of data exists in the synchronous browsing of a large number of users, which is easy to cause system crash when the user access surges.

[0004] Therefore, how to research and design an e-commerce data updating processing method and system based on state difference real-time feedback which can overcome the above defects is the problem we need to solve urgently at present. SUMMARY

[0005] In order to solve the problems in the prior art, the purpose of the present application is to provide an e-commerce data updating processing method and system based on state difference real-time feedback. The difference between the real-time state vectors generated at adjacent time points is calculated, and the multi-dimensional behavior data is encoded into lightweight state vectors by using the geometric progression encoding method. The user end uploads only the encoding difference value to the e-commerce platform, and the encoding difference value uniquely corresponds to the state transition path, which can be used by the e-commerce platform to accurately analyze the behavior intention. The data transmission amount is reduced while the state change is retained, and the e-commerce data updating efficiency is effectively improved.

[0006] The above technical purpose of the present application is realized by the following technical scheme:

[0007] In a first aspect, an e-commerce data updating processing method based on state difference real-time feedback is provided, comprising the following steps:

[0008] Obtaining the real-time difference state vector uploaded by the user end, the real-time difference state vector being the difference between the real-time state vectors generated by the user end at adjacent time points, and the real-time state vector being a lightweight state vector encoded by the user behavior events captured by the user end in real time;

[0009] matching a historical difference state vector from a database, wherein a similarity between the real-time difference state vector and the historical difference state vector is greater than a set threshold, and reading a historical commodity update strategy and a feedback evaluation value corresponding to the historical difference state vector;

[0010] generating a real-time commodity update strategy in combination with the historical commodity update strategy, the similarity, and the feedback evaluation value, and issuing the real-time commodity update strategy to the user end.

[0011] Further, the generation process of the real-time state vector includes:

[0012] extracting state features of each event type from the user behavior events;

[0013] converting feature values of the state features into encoding values, and encoding different feature values of the same state feature using geometric progression encoding;

[0014] compressing all the encoding values into a fixed-dimensional vector through a feature fusion engine to obtain a real-time state vector.

[0015] Further, the event types include a click event, a page browsing event, and a search event;

[0016] The state features of the click event include an embedding vector of a commodity ID, a grid partition encoding of a screen click position, and a click frequency normalization value within a sliding window.

[0017] The state features of the page browsing event include an embedding vector of a page ID, a scroll depth percentage, and a stay duration focus index based on Z-score standardization.

[0018] The state features of the search event include a semantic vector mean of a search word and a binary encoding of a filtering condition.

[0019] Further, the matching of the historical difference state vector from the database includes:

[0020] traversing all ID encoding items in the real-time difference state vector, dividing ID encoding items with an encoding difference value of zero into first encoding items, and dividing ID encoding items with an encoding difference value not equal to zero into second encoding items;

[0021] reading a first encoding difference value of the first encoding items in a last write from a cache list, and writing the first encoding difference value into a corresponding ID encoding item in the real-time difference state vector to obtain an updated real-time difference state vector;

[0022] writing a second encoding difference value corresponding to the second encoding item in the real-time difference state vector into a cache list to update the cache list;

[0023] calculating a similarity between the updated real-time difference state vector and a reference difference state vector, an encoding difference value corresponding to an ID encoding item in the reference difference state vector being updated by a corresponding cache list;

[0024] taking a reference difference state vector corresponding to a similarity greater than a set threshold as the historical difference state vector obtained by matching.

[0025] Further, the similarity is a proportion of the number of encoding items with equal encoding difference values between the real-time difference state vector and the reference difference state vector.

[0026] Further, the similarity is a sum of weight values of encoding items corresponding to equal encoding difference values between the real-time difference state vector and the reference difference state vector.

[0027] If the encoding difference values of the encoding items between the real-time difference state vector and the reference difference state vector are equal, the weight value corresponding to the encoding item is a weight coefficient of the corresponding encoding item.

[0028] If the encoding difference values of the encoding items between the real-time difference state vector and the reference difference state vector are not equal, the weight value corresponding to the encoding item is zero.

[0029] Further, the determination process of the feedback evaluation value is:

[0030] obtaining a next historical difference state vector T+1 of the historical difference state vector T;

[0031] dividing the encoding difference value of each encoding item in the historical difference state vector T+1 by the maximum encoding difference value of the corresponding encoding item, and multiplying the weight coefficient of the corresponding encoding item to obtain an item evaluation value of the corresponding encoding item;

[0032] calculating a sum of all the item evaluation values to obtain a feedback evaluation value of the historical difference state vector T+1.

[0033] Further, the real-time commodity update strategy is generated by combining the historical commodity update strategy, the similarity, and the feedback evaluation value, including:

[0034] if the similarity is greater than or equal to a first threshold value and the feedback evaluation value is greater than or equal to a third threshold value, taking the historical commodity update strategy as the real-time commodity update strategy;

[0035] If the similarity is less than the first threshold value and greater than or equal to a second threshold value, and the feedback evaluation value is greater than or equal to a third threshold value, a local update strategy related to the coding item corresponding to the coding difference value is selected from the historical commodity update strategy, and a real-time commodity update strategy is reconstructed and generated.

[0036] Further, the method further comprises:

[0037] After the user end receives the real-time commodity update strategy, the update strategy of keeping the display interface static is preferentially executed.

[0038] In a second aspect, an e-commerce data update processing system based on state difference real-time feedback is provided, which is used to implement the e-commerce data update processing method based on state difference real-time feedback as any one of the first aspect, and comprises:

[0039] A data acquisition module is configured to acquire a real-time difference state vector uploaded by a user end, wherein the real-time difference state vector is a difference between real-time state vectors generated by the user end at adjacent time points, and the real-time state vector is a lightweight state vector coded by a user behavior event captured by the user end in real time;

[0040] A matching analysis module is configured to match a historical difference state vector with a similarity greater than a set threshold value from the real-time difference state vector from a database, and read a historical commodity update strategy and a feedback evaluation value corresponding to the historical difference state vector;

[0041] A strategy generation module is configured to generate a real-time commodity update strategy by combining the historical commodity update strategy, the similarity and the feedback evaluation value, and to issue the real-time commodity update strategy to the user end.

[0042] Compared with the prior art, the present application has the following beneficial effects:

[0043] 1. The e-commerce data update processing method based on state difference real-time feedback provided by the present application calculates the difference between real-time state vectors generated at adjacent time points, and encodes multi-dimensional behavior data into a lightweight state vector by using a geometric progression coding method, so that the user end uploads only a coding difference value with a difference to the e-commerce platform, the coding difference value uniquely corresponds to a state transition path, and the behavior intention can be accurately analyzed by the e-commerce platform, the data transmission amount is reduced while the state change condition is retained, and the e-commerce data update efficiency is effectively improved.

[0044] 2、The application aims at the matching blind area when the coding difference of the ID coding item is zero, and through the design of the cache list dynamic updating process, the ID coding item with zero difference is replaced by the last cache value to restore the historical commodity context, and the ID coding item with non-zero difference is updated in real time, ensuring the continuity of subsequent matching, solving the strategy disconnection problem during continuous operation of the same commodity, and effectively improving the accuracy of similarity matching;

[0045] 3、The application distinguishes key behaviors through weight coefficients, and only accumulates weighted matching items in similarity calculation to avoid secondary noise interference; in addition, the application quantifies strategy effect through feedback evaluation value, dynamically evaluates the effectiveness of historical strategies based on the ratio of the coding difference of the next state vector to the maximum theoretical difference value;

[0046] 4、The application designs a double-threshold decision mechanism, for the matching condition of high similarity and high feedback value, directly reuses the historical strategy; and for the matching condition of medium similarity and high feedback value, extracts a local strategy for reconstruction, which can effectively guarantee the success rate of e-commerce data updating;

[0047] 5、The user end in the application preferentially executes a static interface updating strategy, such as background loading data and pre-rendering, realizes seamless switching of commodity information, and avoids interface flickering to interfere with user operation. BRIEF DESCRIPTION OF DRAWINGS

[0048] The drawings described herein are used to provide further understanding of the embodiments of the application, constitute a part of the application, and do not constitute a limitation on the embodiments of the application. In the drawings:

[0049] Figure 1 is a flowchart in embodiment 1 of the application;

[0050] Figure 2 is a system block diagram in embodiment 2 of the application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical scheme and advantages of the application more clear and obvious, the application is further described in detail below in combination with embodiments and drawings, and the illustrative embodiments of the application and the description thereof are only used to explain the application, and do not constitute a limitation on the application.

[0052] Embodiment 1: An e-commerce data updating processing method based on real-time feedback of state difference, as shown in Figure 1 , including the following steps:

[0053] S1: Obtain the real-time difference state vector uploaded by the user end, the real-time difference state vector is the difference between the real-time state vectors generated by the user end at adjacent time points, and the real-time state vector is a lightweight state vector coded by the user behavior events captured by the user end in real time;

[0054] S2: match the historical difference state vectors from the database with the real-time difference state vector to obtain a historical difference state vector with a similarity greater than a set threshold, and read the historical commodity update strategy and feedback evaluation value corresponding to the historical difference state vector;

[0055] S3: generate a real-time commodity update strategy by combining the historical commodity update strategy, similarity, and feedback evaluation value, and issue the real-time commodity update strategy to the user end.

[0056] In step S1, the generation process of the real-time state vector includes: extracting state features of each event type from user behavior events; converting the feature values of the state features into encoded values, and using geometric progression coding to encode different feature values of the same state feature; compressing all encoded values into a fixed dimension vector through a feature fusion engine to obtain a real-time state vector.

[0057] In some examples, the event types include but are not limited to click events, page browsing events, and search events; wherein the state features of the click events include an embedding vector of a product ID, a grid partition code of a screen click position, and a click frequency normalization value within a sliding window; the state features of the page browsing events include an embedding vector of a page ID, a scroll depth percentage, and a stay time focus index based on Z-score standardization; and the state features of the search events include a semantic vector mean of a search word and a binary code of a filtering condition.

[0058] In some examples, different coding items in a real-time state vector can be encoded using different geometric progressions, such as a coding item using a geometric progression with a first term of 2 and a common ratio of 2, and different state features in a coding item can take values of {2, 4, 8,..., 2 n-1 ,2 n} after encoding; or a coding item using a geometric progression with a first term of 3 and a common ratio of 3, and different state features in a coding item can take values of {3, 9, 27,..., 3 n-1 ,3 n} after encoding.

[0059] In some examples, different coding items in a real-time state vector can also correspond to different intervals in a geometric progression, such as a coding item corresponding to the interval {2, 4, 8,}, and another different coding item corresponding to the interval {16, 32, 64}.

[0060] The real-time difference state vector in the application is the difference between the real-time state vectors generated by the user terminal at adjacent time points, that is, each encoding item in the real-time state vector corresponding to the t+1 time point is subtracted from each encoding item in the real-time state vector corresponding to the t time point. The encoding difference of each encoding item after subtraction can reflect what state feature changes into another state feature. For example, the encoding value of a state feature A is 4, and the encoding value of another state feature B is 16. The encoding difference corresponding to the change from state feature A to state feature B is 12. Whether different encoding items use different geometric progressions or use different intervals of the same geometric progression, the above encoding difference 12 only represents the change from state feature A to state feature B under the condition that the encoding rule is determined. After a large amount of feature information is encoded into a lightweight state vector, the e-commerce platform can still accurately analyze the information uploaded by the user terminal, which can effectively improve the data transmission efficiency and processing efficiency and reduce the network resource consumption.

[0061] In addition, in order to further reduce the data amount of the fixed dimension vector, the encoding items with a zero encoding difference in the fixed dimension vector can also be compressed, such as being deleted. Further compression requires configuring a storage module in the e-commerce platform to store the non-zero encoding items in the previous real-time difference state vector. When reading the complete data, the historical encoding items stored in the storage module can be filled into the real-time difference state vector to realize complete information expansion.

[0062] In step S2, since the state feature is encoded into a lightweight state vector in the application, when the user terminal operates the same product at adjacent time points, the encoding difference of the ID encoding item in the obtained real-time difference state vector is zero. At this time, it is impossible to obtain the product information operated by the user terminal by analyzing the real-time difference state vector. If the similarity calculation is directly performed on the real-time difference state vector, it is easy to match the historical difference state vector of a non-same product, which will increase the probability of product reverse update. Therefore, the application configures a cache list in the e-commerce platform to constrain the matching of the historical difference state vector.

[0063] The matching of the historical difference state vectors with the similarity to the real-time difference state vector greater than the set threshold from the database comprises: traversing all ID coding items in the real-time difference state vector, dividing the ID coding items with a coding difference value of zero into first coding items, and dividing the ID coding items with a coding difference value not equal to zero into second coding items; reading the first coding difference value of the first coding item written in the last time from the cache list, and writing the first coding difference value into the corresponding ID coding item in the real-time difference state vector to obtain an updated real-time difference state vector; writing the second coding difference value corresponding to the second coding item in the real-time difference state vector into the cache list to update the cache list; calculating the similarity between the updated real-time difference state vector and the reference difference state vector, the coding difference value of the ID coding item in the reference difference state vector being updated through the corresponding cache list; and taking the reference difference state vector with the similarity greater than the set threshold as the matching historical difference state vector.

[0064] It should be noted that different state features of the same coding item can be sorted according to the feature approximation degree in the coding process, and then the sorted state features are matched with the geometric progression, for example, the feature values of three state features are 0.7, 0.85 and 0.9 respectively, and the corresponding coding values can be 2, 4 and 8 respectively.

[0065] In some examples, the similarity is the proportion of the number of coding items with equal coding difference values between the real-time difference state vector and the reference difference state vector. For example, a complete real-time difference state vector has a total of 20 coding items, and the number of coding items with equal coding difference values between the real-time difference state vector and the reference difference state vector is 16, and the calculated similarity is 0.8.

[0066] In some examples, considering that the difference of the ID coding item is more important than the difference of the coding item of the conventional operation, the weight of the product update is greater, for example, the change of the browsed product is more important than the change of the product browsing time, and therefore the weight coefficient can be configured for different coding items according to the importance of the coding item change to the product update, and the similarity is the sum of the weight values of the coding items with equal coding difference values between the real-time difference state vector and the reference difference state vector.

[0067] Specifically, if the coding difference values of the coding items between the real-time difference state vector and the reference difference state vector are equal, the weight value of the corresponding coding item is the weight coefficient of the corresponding coding item; if the coding difference values of the coding items between the real-time difference state vector and the reference difference state vector are not equal, the weight value of the corresponding coding item is zero.

[0068] The application considers that the historical commodity updating strategy may be affected by hot events, seasonal changes, special holidays and other factors during execution, and is prone to cause poor execution effect of the historical commodity updating strategy. Therefore, the application analyzes the execution of the historical commodity updating strategy through the feedback evaluation value. The feedback evaluation value is mainly obtained by comparing and analyzing the relative change degree of the encoding difference between two adjacent historical difference state vectors.

[0069] In some examples, the determination process of the feedback evaluation value is as follows: obtaining a next historical difference state vector T+1 of the historical difference state vector T; dividing the encoding difference of each encoding item in the historical difference state vector T+1 by the maximum encoding difference of the corresponding encoding item, and multiplying the weight coefficient of the corresponding encoding item to obtain the item evaluation value of the corresponding encoding item; and calculating the sum of all item evaluation values to obtain the feedback evaluation value of the historical difference state vector T+1. It should be noted that the maximum encoding difference is the difference between the maximum encoding value and the minimum encoding value in an encoding item.

[0070] In addition, the above-mentioned set threshold value can include a first threshold value and a second threshold value, and the second threshold value is smaller than the first threshold value. The first threshold value is mainly used to filter out as many directly applicable commodity updating strategies as possible, and the second threshold value is mainly used to select multiple second similar commodity updating strategies for combination and reconstruction when there is no directly applicable commodity updating strategy.

[0071] In some examples, the first threshold value and the second threshold value can be dynamically adjusted according to the amount of sample data in the database. The more sample data, the larger the values of the first threshold value and the second threshold value.

[0072] In some examples, since the second threshold value needs to ensure that most user terminals execute commodity updating successfully, when the combination and reconstruction frequency rises to the upper limit condition, the second threshold value and the first threshold value can be adjusted to be smaller. When the combination and reconstruction frequency drops to the lower limit condition, the first threshold value can be appropriately increased, and the second threshold value can remain unchanged or be increased.

[0073] In step S3, the real-time commodity updating strategy is generated in combination with the historical commodity updating strategy, the similarity and the feedback evaluation value, including: if the similarity is greater than or equal to the first threshold value and the feedback evaluation value is greater than or equal to the third threshold value, the historical commodity updating strategy is taken as the real-time commodity updating strategy; if the similarity is less than the first threshold value and greater than or equal to the second threshold value, and the feedback evaluation value is greater than or equal to the third threshold value, a local updating strategy related to the corresponding encoding item with the same encoding difference is selected from the historical commodity updating strategy, and the real-time commodity updating strategy is generated by reconstruction.

[0074] It should be noted that the commodity update strategy described in the application is composed of a plurality of independently executed update instructions, such as the exposure time of a single commodity, adjusting the ranking weight of the search result, pushing the preferential information, replacing the commodity information, and the like.

[0075] The third threshold is generally determined by the overall feedback level in the database, for example, if 70% of the feedback evaluation values are greater than 0.8, 0.8 can be selected as the third threshold.

[0076] In some examples, in order to avoid the visual impact of commodity update on user operation, the user end preferentially executes the update strategy of keeping the display interface static after receiving the real-time commodity update strategy, so that the display interface perceived by the user visually has no obvious difference, and the experience of the user can be enhanced.

[0077] Embodiment 2: An e-commerce data update processing system based on state difference real-time feedback, which is used to realize the e-commerce data update processing method based on state difference real-time feedback as described in Embodiment 1, as shown in the figure, comprising a data acquisition module, a matching analysis module and a strategy generation module. Figure 2

[0078] The data acquisition module is configured to acquire a real-time difference state vector uploaded by a user end, the real-time difference state vector being a difference between real-time state vectors generated by the user end at adjacent time points, and the real-time state vector being a lightweight state vector encoded by a user behavior event captured by the user end in real time; the matching analysis module is configured to match a historical difference state vector from a database, the historical difference state vector having a similarity greater than a set threshold with the real-time difference state vector, and read a historical commodity update strategy and a feedback evaluation value corresponding to the historical difference state vector; and the strategy generation module is configured to generate a real-time commodity update strategy in combination with the historical commodity update strategy, the similarity and the feedback evaluation value, and to issue the real-time commodity update strategy to the user end.

[0079] It should be noted that the system described above can be an e-commerce platform.

[0080] Working principle: the application calculates the difference between the real-time state vectors generated at adjacent time points, and encodes the multi-dimensional behavior data into a lightweight state vector by using a geometric progression encoding method. The user end uploads only the encoded difference value to the e-commerce platform, the encoded difference value uniquely corresponds to a state transition path, which can be used by the e-commerce platform to accurately analyze the behavior intention, reduce the data transmission amount while retaining the state change, and effectively improve the e-commerce data update efficiency.

[0081] ​Those skilled in the art will appreciate that embodiments of the application can be readily used as software, hardware, or a combination of software and hardware. In one

[0082] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or a combination thereof. Figure 1 means for functionally implementing each of the flowchart blocks or the functions indicated in the blocks of a flowchart.

[0083] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or a combination thereof. Figure 1 means for functionally implementing each of the flowchart blocks or the functions indicated in the blocks of a flowchart.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or a combination thereof. Figure 1 means for functionally implementing each of the flowchart blocks or the functions indicated in the blocks of a flowchart.

[0085] The above detailed description has shown, described, and pointed out the aspects of the application in sufficient detail that others skilled in the art can, by applying the knowledge of those skilled in the art, readily make modifications and / or substitutions for elements of the application as set forth in the concepts of the application and fall within the scope of the application. Accordingly, the patentable scope of the application should be defined only by the following claims.

Claims

1. An e-commerce data updating processing method based on real-time feedback of state difference, characterized in that, The method comprises the following steps: obtaining a real-time difference state vector uploaded by a user terminal, the real-time difference state vector being a difference between real-time state vectors generated by the user terminal at adjacent time points, the real-time state vector being a lightweight state vector encoded by a user behavior event captured by the user terminal in real time; matching a historical difference state vector from a database, the historical difference state vector having a similarity to the real-time difference state vector greater than a set threshold, and reading a historical commodity update strategy and a feedback evaluation value corresponding to the historical difference state vector; generating a real-time commodity update strategy in combination with the historical commodity update strategy, the similarity and the feedback evaluation value, and issuing the real-time commodity update strategy to the user terminal.

2. The method for real-time feedback based on state difference of e-commerce data update processing according to claim 1, characterized in that, The generation process of the real-time state vector comprises: extracting state features of each event type from the user behavior event; converting feature values of the state features into encoding values, different feature values of the same state feature being encoded by using an equal ratio series encoding for encoding processing; compressing all the encoding values into a fixed dimension vector by a feature fusion engine to obtain a real-time state vector. 3.The state difference-based real-time feedback e-commerce data updating processing method of claim 2, wherein, The event types comprise a click event, a page browsing event and a search event; wherein the state features of the click event comprise an embedding vector of a commodity ID, a grid partition encoding of a screen click position and a click frequency normalization value in a sliding window; the state features of the page browsing event comprise an embedding vector of a page ID, a scroll depth percentage and a stay time focus index based on Z-score standardization; the state features of the search event comprise a semantic vector mean of a search word and a binary encoding of a filtering condition.

4. The method for real-time feedback based on state difference of e-commerce data update processing according to claim 1, characterized in that, The matching of the historical difference state vector from the database comprises: traversing all ID encoding items in the real-time difference state vector, dividing ID encoding items with a zero encoding difference value into first encoding items, and dividing ID encoding items with a non-zero encoding difference value into second encoding items; reading a first encoding difference value of the first encoding item from a cache list and writing the first encoding difference value into a corresponding ID encoding item in the real-time difference state vector to obtain an updated real-time difference state vector; writing a second encoding difference value corresponding to the second encoding item in the real-time difference state vector into the cache list to update the cache list; calculating a similarity between the updated real-time difference state vector and a reference difference state vector, the encoding difference value of the ID encoding item in the reference difference state vector being updated by the corresponding cache list; taking the reference difference state vector corresponding to the similarity greater than the set threshold as the matched historical difference state vector.

5. The method for real-time feedback based on state difference of e-commerce data update processing according to claim 1, characterized in that, The similarity is a proportion of the number of encoding items with equal encoding difference values between the real-time difference state vector and the reference difference state vector.

6. The method for real-time feedback based on state difference of e-commerce data update processing according to claim 1, characterized in that, The similarity is a sum of weight values of the encoding items corresponding to the equal encoding difference values between the real-time difference state vector and the reference difference state vector. If the encoding difference value of the encoding item between the real-time difference state vector and the reference difference state vector is equal, the weight value corresponding to the encoding item is the weight coefficient of the corresponding encoding item. If the encoding difference value of the encoding item between the real-time difference state vector and the reference difference state vector is not equal, the weight value corresponding to the encoding item is zero.

7. The method for real-time feedback based on state difference of e-commerce data update processing according to claim 1, characterized in that, The determination process of the feedback evaluation value is as follows: Obtain the next historical difference state vector T+1 of the historical difference state vector T; Divide the encoding difference value of each encoding item in the historical difference state vector T+1 by the maximum encoding difference value of the corresponding encoding item, and multiply by the weight coefficient of the corresponding encoding item to obtain the item evaluation value of the corresponding encoding item. Calculate the sum of all the item evaluation values to obtain the feedback evaluation value of the historical difference state vector T+1. 8.The state difference-based real-time feedback e-commerce data updating processing method of claim 1, wherein, The generation of the real-time commodity update strategy by combining the historical commodity update strategy, the similarity and the feedback evaluation value includes: If the similarity is greater than or equal to the first threshold value, and the feedback evaluation value is greater than or equal to the third threshold value, the historical commodity update strategy is used as the real-time commodity update strategy. If the similarity is less than the first threshold value and greater than or equal to the second threshold value, and the feedback evaluation value is greater than or equal to the third threshold value, a local update strategy related to the encoding item corresponding to the equal encoding difference value is selected from the historical commodity update strategy to reconstruct and generate a real-time commodity update strategy. 9.The state difference-based real-time feedback e-commerce data updating processing method of claim 1, wherein, The method further includes: After receiving the real-time commodity update strategy, the user end preferentially executes an update strategy that keeps the display interface static.

10. An e-commerce data updating processing system based on real-time feedback of state difference, characterized in that, The system is used to implement the e-commerce data update processing method based on real-time feedback of state difference as claimed in any one of claims 1-9, and includes: A data acquisition module is configured to acquire a real-time difference state vector uploaded by a user end, wherein the real-time difference state vector is the difference between real-time state vectors generated by the user end at adjacent time points, and the real-time state vector is a lightweight state vector encoded by a user behavior event captured by the user end in real time; A matching analysis module is configured to match a historical difference state vector with a similarity greater than a set threshold value with the real-time difference state vector from a database, and read a historical commodity update strategy and a feedback evaluation value corresponding to the historical difference state vector; A strategy generation module is configured to generate a real-time commodity update strategy by combining the historical commodity update strategy, the similarity and the feedback evaluation value, and to send the real-time commodity update strategy to the user end.

Images