Transition index-based information generation method and apparatus, and electronic device

Abstract

The embodiment of the invention discloses an information generation method and device based on a transition index and electronic equipment. A specific embodiment of the method comprises the steps of obtaining a business index information set for a target virtual article; for the service index information, executing the following first processing steps: according to the service index information, performing transition index decomposition on a service index corresponding to the service index information; performing real-time index value updating on the transition index corresponding to each piece of transition index information in the transition index information group; according to the path diagram and the obtained updated transition index information group set, performing real-time restoration on the index value of the business index corresponding to the path diagram; and according to the updated business index information set, generating real-time article information for the target virtual article. According to the embodiment, the problem that index calculation cannot be carried out timely and accurately due to calculation bottleneck is effectively solved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, and electronic device for generating information based on a transition indicator. Background Art

[0002] In the financial industry, how to effectively and accurately manage virtual items (e.g., products with financial asset attributes) and hedging risks depends on various indicators used to quantify risks in financial engineering. For example, these indicators play a vital role in core financial operations such as investment decision-making, position management, hedging risk analysis, financial asset allocation, risk warning, return evaluation, and strategy optimization.

[0003] However, the calculation complexity of these indicators varies, and they may also involve huge data sets for indicator calculation. Especially when the position size is large, the calculation performance will become a bottleneck for the real-time calculation of indicators, making it impossible to calculate indicators in a timely and accurate manner, thus affecting the effective and accurate execution of the above operations.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a method, device, and electronic device for generating information based on a transition indicator to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a method for generating information based on transition indicators, the method comprising: obtaining a set of business indicator information for a target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator for describing the state of the target virtual item; for each business indicator information in the business indicator information set, performing the following first processing step: according to the business indicator information, performing transition indicator decomposition on the business indicator corresponding to the business indicator information to obtain a transition indicator information group, wherein the transition indicator information group comprises: a transition indicator type and transition indicator description information, and the transition indicator type comprises: a first type of transition indicator type and a second type of transition indicator type; performing real-time indicator value update on the transition indicator corresponding to each transition indicator information in the transition indicator information group to generate updated transition indicator information to obtain an updated transition indicator information group; according to a path map and the obtained updated transition indicator information group set, performing real-time restoration on the indicator value of the business indicator corresponding to the path map to obtain an updated business indicator information set, wherein the path map is a two-dimensional map recording at least one analysis path; according to the updated business indicator information set, generating real-time item information for the target virtual item, wherein the real-time item information comprises: item description information and item recommendation information.

[0008] In a second aspect, some embodiments of the present disclosure provide an information generation device based on transition indicators, the device comprising: an acquisition unit, configured to acquire a set of business indicator information for a target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator for describing the state of the target virtual item; an execution unit, configured to execute the following first processing step for each business indicator information in the business indicator information set: performing transition indicator decomposition on the business indicator corresponding to the business indicator information according to the business indicator information to obtain a transition indicator information group, wherein the transition indicator information group comprises: a transition indicator type, and transition indicator description information, and the transition indicator type comprises: a type of transition indicator type and Second type of transition indicator type; updating the transition indicator corresponding to each transition indicator information in the above transition indicator information group in real time to generate updated transition indicator information and obtain an updated transition indicator information group; a real-time restoration unit, configured to restore the indicator value of the business indicator corresponding to the above path map in real time according to the path map and the obtained updated transition indicator information group set, to obtain an updated business indicator information set, wherein the above path map is a two-dimensional graph recording at least one analysis path; a generation unit, configured to generate real-time item information for the above target virtual item according to the above updated business indicator information set, wherein the above real-time item information includes: item description information and item recommendation information.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the information generation method based on transition indicators of some embodiments of the present disclosure, the problem that the calculation of indicators cannot be performed in a timely and accurate manner due to the calculation bottleneck, thereby affecting the effective and accurate execution of the above-mentioned operations, is effectively solved. Specifically, the reason for the above-mentioned problem is that the calculation of indicators is complex and different, and it may also involve a large amount of data sets used to participate in the calculation of indicators. In particular, when the position size is large, the computing performance will become the bottleneck of the real-time calculation of indicators. Based on this, the information generation method based on transition indicators of some embodiments of the present disclosure, first, obtains a business indicator information set for the target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator used to describe the state of the above-mentioned target virtual item. Secondly, for each business indicator information in the above-mentioned business indicator information set, the following first processing step is performed: the first step, according to the above-mentioned business indicator information, the business indicator corresponding to the above-mentioned business indicator information is decomposed into a transition indicator to obtain a transition indicator information group, wherein the transition indicator information group includes: a transition indicator type, a transition indicator description information, and the transition indicator type includes: a first type of transition indicator type and a second type of transition indicator type. In practice, due to the complex calculation logic of business indicators, when any parameter involved in the business indicator changes, the full recalculation of the business indicator will greatly increase the calculation delay. Therefore, the indicator decomposition facilitates the subsequent recalculation of the business indicator for the purpose of reducing the calculation delay. The second step is to update the real-time indicator value of the transition indicator corresponding to each transition indicator information in the above transition indicator information group to generate updated transition indicator information and obtain an updated transition indicator information group. In practice, when the indicator value of the transition indicator changes, it is updated accordingly, and when the indicator value of the transition indicator does not change, it is not updated. In this way, the update of local parameters is realized, so that the subsequent calculation delay can be effectively reduced. Then, according to the path map and the updated transition indicator information group set obtained, the indicator value of the business indicator corresponding to the above path map is restored in real time to obtain an updated business indicator information set, wherein the above path map is a two-dimensional map recording at least one analysis path. In practice, there are many business indicators used to quantify the target virtual items. In different scenarios, the business indicators involved in quantification are different. Therefore, by combining the path map and the updated transition indicator information group set, the business indicators involved in quantification are restored to facilitate the quantification of candidates. Finally, based on the updated business indicator information set, real-time item information for the target virtual items is generated, wherein the real-time item information includes: item description information and item recommendation information. In this way, combined with the real-time updated business indicators, timely and effective description and recommendation of the target virtual items are achieved. In this way, the problem of being unable to calculate indicators in a timely and accurate manner due to computing bottlenecks, which in turn affects the effective and accurate execution of the above operations, is effectively solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flow chart of some embodiments of the method for generating information based on transition indicators according to the present disclosure; Figure 2 It is a tree structure diagram of the indicator relationship tree; Figure 3 It is another tree structure diagram of the indicator relationship tree; Figure 4 is a schematic diagram of the structure of some embodiments of the information generation device based on the transition indicator according to the present disclosure; Figure 5 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0020] refer to Figure 1 , shows a process 100 of some embodiments of the information generation method based on transition indicators according to the present disclosure. The information generation method based on transition indicators includes the following steps: Step 101: Obtain a set of business indicator information for a target virtual item.

[0021] In some embodiments, the executing entity (e.g., a computing device) of the information generation method based on the transition indicator can obtain a set of business indicator information for the target virtual item. Among them, the business indicator corresponding to the business indicator information is an indicator used to describe the state of the above-mentioned target virtual item. In practice, the business indicator information may include: indicator type, indicator description information, indicator value, indicator identification. Among them, the indicator description information can be used to describe the indicator calculation logic of the business indicator. The target virtual item may be a product with financial asset attributes. Products with financial asset attributes include but are not limited to: stocks, bonds, futures, funds, options, trust products, etc. For example, the target virtual item may be "Stock A". In addition, the target virtual item may also be a combination of products with different financial asset attributes.

[0022] As an example, the above-mentioned execution entity can capture the business indicators corresponding to the above-mentioned target virtual items from the business indicator library to obtain a business indicator information set. Among them, the business indicator library is a database for storing defined business indicators. The business indicator library can uniformly manage all business indicators through standardized definition, modification and other management methods. In addition, there are a large number of business indicators in the business indicator library, and different business indicators are called at different times. If the indicator values ​​of all business indicators in the business indicator library are updated in combination with transition indicators, a large amount of computing resources will be consumed. In particular, when the number of business indicator calls is extremely low, frequent updates of the indicator values ​​of the business indicators will cause unnecessary use of a large amount of computing resources. Therefore, the present disclosure, from the perspective of the target virtual item, only updates the business indicators related to the target virtual item accordingly, thereby improving the efficiency of computing resource utilization.

[0023] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0024] Step 102: for each piece of business indicator information in the business indicator information set, perform the following first processing step, wherein the first processing step includes: step 1021 and step 1022: Step 1021: According to the business indicator information, the business indicator corresponding to the business indicator information is decomposed into transition indicators to obtain a transition indicator information group.

[0025] In some embodiments, the above-mentioned execution entity can perform transition indicator decomposition on the business indicators corresponding to the business indicator information according to the business indicator information to obtain a transition indicator information group. Among them, the transition indicator information group includes: transition indicator type, transition indicator description information. The transition indicator type includes: a type of transition indicator type and a type of transition indicator type. Among them, the type of transition indicator type represents the business indicators that can be calculated to the corresponding indicator value in a linear manner. The type of transition indicator type represents the business indicators that can be calculated to the corresponding indicator value in a nonlinear manner. The transition indicator description information represents the indicator calculation logic and indicator value of the transition indicator.

[0026] Example 1, business indicator A1 = parameter B1×business indicator A2+parameter B2. At this time, there is a mapping from business indicator A2 to business indicator A1 between business indicator A1 and business indicator A2. Therefore, business indicator A2 can be a transition indicator of a transition indicator type.

[0027] Example 2, taking the Greek sensitivity index (business index) corresponding to option-type virtual products as an example, the sensitivity index is a broad measure of the sensitivity of a system or financial instrument to changes in external environmental factors. Specifically, the Greek sensitivity index is a set of indicators used to measure the corresponding risks and sensitivities of financial derivatives (e.g., option-type virtual items). For example, the "Delta index" represents the sensitivity of the option price to changes in the price of the underlying asset, and specifically, represents the ratio of the option price to changes in the price of the underlying asset. For example, the index value of the "Delta index" of option-type virtual item A is 0.5, which means that if the price of the underlying asset of option-type virtual item A rises by 1 yuan, the price of option-type virtual item A will rise by 0.5 yuan. Therefore, sensitivity indicators are all transition indicators of a type of transition indicator.

[0028] Example 3, taking stress test indicators as an example, stress test indicators represent the risk status under different simulation scenarios (for example, macroeconomic shock test scenarios, market risk test scenarios, credit risk test scenarios, liquidity risk test scenarios, etc.). Specifically, take the stress test indicators including: interest rate volatility indicators, exchange rate volatility indicators and stock market crash indicators as examples. Among them, the interest rate volatility indicator represents the impact on the fixed income investment portfolio after a change of K basis points from the current level. Exchange rate volatility represents the exchange rate change of major currencies (for example, RMB, Euro, US dollar, British pound, Swiss franc, etc.) by M%, and evaluates the impact on foreign exchange exposure. The stock market crash indicator represents the loss of the investment portfolio after the simulated stock market index (for example, Hong Kong Hang Seng Index, Nasdaq Index, etc.) changes by F%. Therefore, the above stress test indicators are all transition indicators of a type of transition indicator.

[0029] Example 4, business indicator A1 = F1 ( F2 (Business indicator A2)), at this time, there is a nonlinear mapping from business indicator A2 to business indicator A1 between business indicator A1 and business indicator A2, so, F2 (Business indicator A2) can be a transition indicator of the second type of transition indicator. F1 ()and F2 () all represent the calculation logic. Further analysis shows that the combination of a transition indicator of the first transition indicator type and a transition indicator of the first transition indicator type is still a transition indicator of the first transition indicator type. The combination of a transition indicator of the first transition indicator type and a transition indicator of the second transition indicator type is a transition indicator of the second transition indicator type. The combination of a transition indicator of the second transition indicator type and a transition indicator of the second transition indicator type is still a transition indicator of the first transition indicator type.

[0030] Example 5, taking the risk value indicator as an example, the risk value indicator is a measure of the maximum loss that may occur in a financial asset (a single virtual item) or a financial asset portfolio (multiple virtual items) within a future time window at a certain confidence level. Specifically, the risk value indicator = Percentile ({PnL}). Among them, Percentile () represents a specific quantile value of the loss distribution. Among them, since the risk value indicator has sub-non-additivity, PnL is selected as its effective indicator. Among them, the calculation of PnL can be obtained by the definition of the native indicator, such as by Monte Carlo simulation, to achieve the purpose of simplifying and accelerating the calculation of the risk value indicator. At this time, the risk value indicator can be considered as a transition indicator of the second type of transition indicator.

[0031] Example 6, taking the (counterparty) credit risk exposure indicator as an example, the (counterparty) credit risk exposure indicator is an indicator used to measure the credit risk within a specific time period in the future, specifically referring to the loss that the institution may suffer in the event of a counterparty default. This risk is generated when the counterparty fails to fulfill the payment obligation agreed in the contract. For example, in the event of a default, the non-defaulting party needs to close its position and further seek alternative transactions to maintain its market position. The costs associated with this are defined as risk exposure. In practice, (counterparty) credit risk exposure includes indicators such as Expected exposure EE(t), Potential future exposure PFEa(t), and Expected shortfall. Among them, Expected exposure EE(t) refers to the expected value of the positive part of the expected market value of a transaction portfolio or a single transaction to the counterparty at a certain time point t in the future. In other words, it represents the risk measure of the amount exposed to the counterparty at time point t. Potential future exposure PFEa(t) refers to the maximum potential loss of a transaction portfolio or a single transaction to the counterparty at a certain time point t in the future. In other words, it represents the maximum amount that the trading party needs to pay to the counterparty under unfavorable but reasonable market conditions. Expected shortfall refers to the average expected loss at a given confidence level when the loss exceeds the risk value of the confidence level. Taking Potential future exposure PFEa(t) as an example, the Monte Carlo method can be used to simulate different scenarios and calculate the finishing difference to generate the (counterparty) credit risk exposure. At this point, the (counterparty) credit risk exposure indicator can be considered as a transition indicator of the second type of transition indicator.

[0032] In some optional implementations of some embodiments, the execution subject performs transition indicator decomposition on the business indicator corresponding to the business indicator information according to the business indicator information to obtain a transition indicator information group, including: The first step is to build an indicator relationship tree based on the above business indicator information.

[0033] The indicator relationship tree is a logic tree with the business indicator corresponding to the business indicator information as the root node, which represents the indicator settlement logic of the business indicator corresponding to the business indicator information.

[0034] As an example, the calculation logic of business indicator A corresponding to business indicator information A may be: business indicator A1 = parameter B1×business indicator A2 + parameter B2×business indicator A3 + parameter B3. The corresponding indicator relationship tree can be found in Figure 2Schematic diagram of the tree structure of the indicator relationship tree shown.

[0035] As another example, the calculation logic of the business indicator A corresponding to the business indicator information A may be: business indicator A1= F2 ( F1 (Business indicator A2)). The corresponding indicator relationship tree can be found in Figure 3 Another tree structure diagram of the indicator relationship tree shown.

[0036] The second step is to deeply traverse the above indicator relationship tree to obtain at least one indicator relationship path.

[0037] The indicator relationship path is a path with the business indicator corresponding to the above business indicator information as the first node.

[0038] As an example, see further Figure 2 The tree structure diagram of the indicator relationship tree shown in FIG. Figure 2 The indicator relationship tree shown contains only two indicator relationship paths, namely, the first path is: from "business indicator A2" to "business indicator A1". The second path is: from "business indicator A3" to "business indicator A1".

[0039] As yet another example, see Figure 3 Another tree structure diagram of the indicator relationship tree shown in FIG. Figure 3 The indicator relationship tree shown contains only one indicator relationship path, namely: F1 (Business Indicator A2)” points to “Business Indicator A1”.

[0040] In the third step, for each indicator relationship path in the at least one indicator relationship path, the following second processing step is performed: The first sub-step is to remove the first node included in the above indicator relationship path to generate an updated indicator relationship path.

[0041] As an example, Figure 2 The corresponding two updated indicator relationship paths are "business indicator A2" and "business indicator A3".

[0042] As yet another example, Figure 3 The corresponding updated indicator relationship path is " F1 (Business Indicator A2)”.

[0043] The second sub-step is to determine the transition indicator description information included in the transition indicator information corresponding to the first node in the updated indicator relationship path.

[0044] In practice, the above-mentioned execution entity can obtain the indicator calculation logic corresponding to the first node in the updated indicator relationship path as transition indicator description information.

[0045] In the third sub-step, in response to the fact that the indicator types of the business indicators corresponding to the nodes except the first node in the updated indicator relationship path are all first-class transition indicator types, the transition indicator type included in the transition indicator information corresponding to the first node in the updated indicator relationship path is updated to a first-class transition indicator type.

[0046] The fourth sub-step, in response to the existence of two types of transition indicator types in the indicator types of business indicators corresponding to nodes other than the first node in the above-mentioned updated indicator relationship path, updates the transition indicator type included in the transition indicator information corresponding to the first node in the above-mentioned updated indicator relationship path to the second type of transition indicator type.

[0047] Step 1022: update the transition indicator corresponding to each transition indicator information in the transition indicator information group in real time to generate updated transition indicator information and obtain an updated transition indicator information group.

[0048] In some embodiments, the execution subject may perform real-time indicator value updates on the transition indicators corresponding to each transition indicator information in the transition indicator information group to generate updated transition indicator information and obtain an updated transition indicator information group. In practice, the execution subject may perform real-time indicator value updates on the transition indicators corresponding to the transition indicator information to update the indicator value included in the transition indicator description information included in the transition indicator information and obtain updated transition indicator information.

[0049] As an example, for distributed data processing platforms, there is a hardware foundation with a large memory. In order to increase the update speed of the indicator value, the update of the indicator value can be implemented in the large memory corresponding to the distributed system (to avoid the speed bottleneck of data exchange between the memory and the external memory, thereby increasing the update speed). For example, the indicator value is updated by message processing. Specifically, for example, after the indicator value is updated in the memory, an update completion message is generated to notify the update of the indicator value included in the transition indicator description information included in the transition indicator information. For another example, by monitoring the change of the bit position where the indicator value is located in the memory, when there is a change, the indicator value included in the transition indicator description information included in the transition indicator information is updated to obtain the updated transition indicator information.

[0050] In some embodiments, the execution subject updates the transition indicator corresponding to each transition indicator information in the transition indicator information group in real time to generate updated transition indicator information, including: The first step is to create an indicator value update trigger for the transition indicator corresponding to the above transition indicator information.

[0051] The indicator value update trigger is used to monitor the indicator value changes of the business indicators that constitute the transition indicators.

[0052] As an example, take " F1 (Business Indicator A2)" is taken as an example. When the indicator value of "Business Indicator A2" changes, F1 (Business indicator A2)" changes accordingly, thereby triggering the indicator value update trigger.

[0053] In the second step, in response to the indicator value update trigger being triggered, the transition indicator corresponding to the transition indicator information is updated in real time to update the transition indicator description information included in the transition indicator information to obtain updated transition indicator information corresponding to the transition indicator information.

[0054] In practice, the above-mentioned execution entity may update the indicator value included in the transition indicator description information to obtain updated transition indicator information corresponding to the transition indicator information.

[0055] In some optional implementations of some embodiments, after the execution subject updates the real-time indicator value of the transition indicator corresponding to each transition indicator information in the transition indicator information group to generate updated transition indicator information and obtains the updated transition indicator information group, the method further includes: The first step is to obtain the virtual item identifier corresponding to the target virtual item.

[0056] The virtual item identifier may be a unique identifier corresponding to the target virtual item.

[0057] In the second step, for each updated transition indicator information in the above updated transition indicator information group, the following third processing step is performed: The first sub-step is to generate a transition indicator feature according to the transition indicator description information included in the updated transition indicator information.

[0058] The above transition indicator features include: a transition indicator identifier and a quantitative feature identifier.

[0059] In practice, the transition indicator identifier is a unique identifier corresponding to the transition indicator. For example, when the transition indicator is a business indicator, the transition indicator identifier may be a business identifier corresponding to the transition indicator. When the transition indicator is a composite indicator composed of business indicators, the transition indicator identifier corresponding to the transition indicator may be reallocated. The quantitative feature identifier may be a feature identifier of a preference feature.

[0060] The second sub-step is to concatenate the virtual item identifier and the transition indicator feature to generate a candidate character string.

[0061] In practice, candidate string = virtual item identifier + transition indicator feature.

[0062] The third sub-step is to perform hashing on the candidate character string to generate a hash character string.

[0063] In practice, the MD5 algorithm can be used to hash the candidate string to generate a hash string. The length of the hash string is 32 bits. For example, the hash string can be "1e46db7ff54e80771611d526cf2c2c19".

[0064] The fourth sub-step is to generate a data storage tree corresponding to the updated transition indicator information based on the hash string and the updated transition indicator information.

[0065] In practice, the data storage tree adopts a B+ tree structure. Specifically, the data storage tree stores the hash string of each transition indicator and the indicator value included in the updated transition indicator information. In particular, the indicator value of the transition indicator is continuously updated over time, showing a time series structure. Therefore, the use of the B+ tree can well support the long-term storage and fast query of time series data.

[0066] The fifth sub-step is to generate a tree index address corresponding to the data storage tree according to the hash string.

[0067] In practice, although the existence of links between leaf nodes of a B+ tree can speed up the query, there is still a certain search delay when the tree structure is complex. Therefore, a Bloom filter can be used based on the hash string to build an index for the data in the data storage tree to further speed up the retrieval. Specifically, the value in the Bloom filter can quickly determine whether the corresponding data is stored in the B+ tree. If it exists, a quick search can be achieved through the pre-linked address.

[0068] Step 103, based on the path map and the obtained updated transition indicator information group set, the indicator values ​​of the business indicators corresponding to the path map are restored in real time to obtain an updated business indicator information set.

[0069] In some embodiments, the execution subject can restore the indicator value of the business indicator corresponding to the path map in real time according to the path map and the updated transition indicator information group set obtained, and obtain the updated business indicator information set. Among them, the path map is a two-dimensional graph that records at least one analysis path. In practice, since there is a calculation logic relationship between the transition indicator and the business indicator, therefore, on the basis of the completion of the update of the transition indicator, the calculation logic of the business indicator can be restored through the calculation logic between the transition indicator and the business indicator, and the indicator value of the business indicator can be updated.

[0070] In some optional implementations of some embodiments, the execution subject restores the indicator value of the business indicator corresponding to the path map in real time according to the path map and the obtained updated transition indicator information group set to obtain the updated business indicator information set, including: The first step is to construct a multidimensional analysis tree for the above target virtual items.

[0071] Among them, the multidimensional analysis tree can be a drill-down structure tree. In practice, a stack structure can be used to construct a multidimensional analysis tree, including: first, define a hierarchical structure, that is, determine the layer structure as a drill-down element, wherein the drill-down elements in the stack structure form a subordinate relationship from the bottom of the stack to the top of the stack. Then, according to the subordinate relationship between the nodes, the corresponding data is assigned to the drill-down elements, such as company information, department information, asset type, account information, etc. Finally, the nodes corresponding to the drill-down elements are connected according to the subordinate relationship to form a tree structure, and a multidimensional analysis tree is obtained.

[0072] The second step is to determine the analysis dimension.

[0073] The analysis dimensions may be two pre-set key dimensions, which are derived from the root node and leaf nodes of the multidimensional analysis tree.

[0074] The third step is to determine at least one analysis path that matches the above analysis dimensions and obtain the above path diagram.

[0075] In practice, the analysis path with the two dimensions included in the analysis dimension as the root node and the end node is determined by deep traversal to obtain the above path diagram. The path diagram is stored in a two-dimensional matrix, with the horizontal axis dimension corresponding to the analysis path and the vertical axis dimension corresponding to the tree nodes included in the analysis path.

[0076] The fourth step is to restore the indicator values ​​of the business indicators corresponding to the above-mentioned path diagram in real time according to the data storage tree corresponding to the above-mentioned path diagram and the updated transition indicator information, so as to obtain the above-mentioned updated business indicator information set.

[0077] In practice, the corresponding indicator value in the data storage tree is located according to the leaf node in the analysis path, and the indicator calculation logic between the business indicator and the transition indicator is combined to restore and update the indicator value of the business indicator to obtain the updated business indicator information.

[0078] Step 104: Generate real-time item information for the target virtual item based on the updated business indicator information set.

[0079] In some embodiments, the execution subject may generate real-time item information for the target virtual item based on the updated business indicator information set. The real-time item information includes: item description information and item recommendation information. The real-time item information table is a dynamically changing item portrait for the target virtual item. The item recommendation information is the reason for recommending the target virtual item.

[0080] In some optional implementations of some embodiments, the execution subject generates real-time item information for the target virtual item according to the updated business indicator information set, including: In the first step, indicator features are extracted for each updated business indicator information in the updated business indicator information set to generate business indicator information features and obtain a business indicator information feature set.

[0081] In practice, since the indicator values ​​included in the updated business indicator information are sequence structure data, a time series model, such as an RNN (Recurrent Neural Network) model, can be used to extract indicator features from each updated business indicator information in the above updated business indicator information set to generate business indicator information features.

[0082] The second step is to determine whether there is any historical item information for the target virtual item.

[0083] In practice, the historical item information may be item information corresponding to the target virtual item in the previous time window. Specifically, by determining whether item information corresponding to the target virtual item information is generated in the previous time window, it is determined whether there is historical item information for the target virtual item.

[0084] The third step is to extract features of the historical item information in response to the existence of the historical item information to generate historical item description information features and historical item recommendation information features.

[0085] In practice, the TextRNN model can be used as the backbone network to extract features from the above historical item information to generate features of historical item description information and historical item recommendation information. Based on the TextRNN model, two sub-recurrent neural network structures are connected to output features of historical item description information and historical item recommendation information respectively.

[0086] The fourth step is to generate the item description information and item recommendation information included in the real-time item information according to the historical item description information characteristics, the historical item recommendation information characteristics and the business indicator information characteristics set.

[0087] In practice, based on the time series model, TextRNN model and sub-cyclic neural network structure, a feature fusion layer is connected to fuse the historical item description information features, the above historical item recommendation information features and the above business indicator information feature set. Then, two predictors are connected after the feature fusion layer, namely the item description information predictor and the item recommendation information predictor. The item description information and item recommendation information included in the real-time item information are output respectively.

[0088] Step 5: In response to the non-existence, obtain reference item information corresponding to the target virtual item.

[0089] The reference item information is historical item information or real-time item information of a virtual item of the same item type as the target virtual item.

[0090] Step 6: Pull the reference item information features corresponding to the above reference item information from the feature cache pool.

[0091] Among them, the feature cache pool is used to store the item information features corresponding to the historically generated item information. By setting the feature cache pool, repeated calculation of features can be avoided. In addition, the item information features stored in the feature cache pool are all set with a cache release timer. When the cache timer is reset, the cache space of the corresponding item information feature is released. When the item information feature is called, the corresponding cache timer is refreshed. To further improve the utilization efficiency of the feature cache pool. In addition, the pool space of the feature cache pool is dynamically scaled. Specifically, by setting the shrinkage coefficient and the basic cache pool size, when the occupancy rate of the feature cache pool is greater than the upper threshold, the shrinkage coefficient and the basic cache pool size are used to control the increase of the feature exchange cache pool, that is, to apply for new cache resources to be allocated to the feature cache pool. When the occupancy rate of the feature cache pool is less than the lower threshold, the shrinkage coefficient and the basic cache pool size are used to control the decrease of the feature exchange cache pool, that is, to release the cache resources of part of the feature cache pool. In this way, the utilization efficiency of the feature cache pool is further improved.

[0092] The seventh step is to generate the item description information and item recommendation information included in the real-time item information according to the reference item information characteristics and the business indicator information feature set.

[0093] In practice, the execution subject can fuse the reference item information features and the business indicator information feature set through the feature fusion layer. Then, two predictors are connected to the feature fusion layer, namely, the item description information predictor and the item recommendation information predictor. The item description information and the item recommendation information included in the real-time item information are outputted respectively.

[0094] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the information generation method based on transition indicators of some embodiments of the present disclosure, the problem that the calculation of indicators cannot be performed in a timely and accurate manner due to the calculation bottleneck, thereby affecting the effective and accurate execution of the above-mentioned operations, is effectively solved. Specifically, the reason for the above-mentioned problem is that the calculation of indicators is complex and different, and it may also involve a large amount of data sets used to participate in the calculation of indicators. In particular, when the position size is large, the computing performance will become the bottleneck of the real-time calculation of indicators. Based on this, the information generation method based on transition indicators of some embodiments of the present disclosure, first, obtains a business indicator information set for the target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator used to describe the state of the above-mentioned target virtual item. Secondly, for each business indicator information in the above-mentioned business indicator information set, the following first processing step is performed: the first step, according to the above-mentioned business indicator information, the business indicator corresponding to the above-mentioned business indicator information is decomposed into a transition indicator to obtain a transition indicator information group, wherein the transition indicator information group includes: a transition indicator type, a transition indicator description information, and the transition indicator type includes: a first type of transition indicator type and a second type of transition indicator type. In practice, due to the complex calculation logic of business indicators, when any parameter involved in the business indicator changes, the full recalculation of the business indicator will greatly increase the calculation delay. Therefore, the indicator decomposition facilitates the subsequent recalculation of the business indicator for the purpose of reducing the calculation delay. The second step is to update the real-time indicator value of the transition indicator corresponding to each transition indicator information in the above transition indicator information group to generate updated transition indicator information and obtain an updated transition indicator information group. In practice, when the indicator value of the transition indicator changes, it is updated accordingly, and when the indicator value of the transition indicator does not change, it is not updated. In this way, the update of local parameters is realized, so that the subsequent calculation delay can be effectively reduced. Then, according to the path map and the updated transition indicator information group set obtained, the indicator value of the business indicator corresponding to the above path map is restored in real time to obtain an updated business indicator information set, wherein the above path map is a two-dimensional map recording at least one analysis path. In practice, there are many business indicators used to quantify the target virtual items. In different scenarios, the business indicators involved in quantification are different. Therefore, by combining the path map and the updated transition indicator information group set, the business indicators involved in quantification are restored to facilitate the quantification of candidates. Finally, based on the updated business indicator information set, real-time item information for the target virtual items is generated, wherein the real-time item information includes: item description information and item recommendation information. In this way, combined with the real-time updated business indicators, timely and effective description and recommendation of the target virtual items are achieved. In this way, the problem of being unable to calculate indicators in a timely and accurate manner due to computing bottlenecks, which in turn affects the effective and accurate execution of the above operations, is effectively solved.

[0095] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an information generation device based on a transition indicator. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the information generation device based on the transition indicator can be specifically applied to various electronic devices.

[0096] like Figure 4 As shown, some embodiments of the information generation device 400 based on transition indicators include: an acquisition unit 401, an execution unit 402, a real-time restoration unit 403 and a generation unit 404. The acquisition unit 401 is configured to acquire a set of business indicator information for a target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator for describing the state of the target virtual item; the execution unit 402 is configured to perform the following first processing step for each business indicator information in the business indicator information set: according to the business indicator information, perform transition indicator decomposition on the business indicator corresponding to the business indicator information to obtain a transition indicator information group, wherein the transition indicator information group includes: a transition indicator type, a transition indicator description information, and the transition indicator type includes: a first type of transition indicator type and a second type of transition indicator type; for the transition indicator information The transition indicators corresponding to each transition indicator information in the group are updated in real time to generate updated transition indicator information and obtain an updated transition indicator information group; the real-time restoration unit 403 is configured to restore the indicator values ​​of the business indicators corresponding to the above path diagram in real time according to the path diagram and the obtained updated transition indicator information group set to obtain an updated business indicator information set, wherein the above path diagram is a two-dimensional diagram that records at least one analysis path; the generation unit 404 is configured to generate real-time item information for the above target virtual item according to the above updated business indicator information set, wherein the above real-time item information includes: item description information and item recommendation information.

[0097] It can be understood that the units recorded in the information generation device 400 based on the transition index are similar to the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the information generation device 400 based on the transition index and the units included therein, and will not be described in detail here.

[0098] Reference below Figure 5 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 500 suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0099] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory 502 or a program loaded from a storage device 508 to a random access memory 503. Various programs and data required for the operation of the electronic device 500 are also stored in the random access memory 503. The processing device 501, the read-only memory 502, and the random access memory 503 are connected to each other via a bus 504. An input / output interface 505 is also connected to the bus 504.

[0100] Typically, the following devices may be connected to the input / output interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 5 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0101] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the read-only memory 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0102] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0103] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0104] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains a business indicator information set for the target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator used to describe the state of the above-mentioned target virtual item; for each business indicator information in the above-mentioned business indicator information set, executes the following first processing step: according to the above-mentioned business indicator information, performs transition indicator decomposition on the business indicator corresponding to the above-mentioned business indicator information to obtain a transition indicator information group, wherein the transition indicator information group includes: transition indicator type, transition indicator description information, and the transition indicator type includes: a type A transition indicator type and a second type of transition indicator type; updating the transition indicator corresponding to each transition indicator information in the above transition indicator information group in real time to generate updated transition indicator information and obtain an updated transition indicator information group; based on the path map and the obtained updated transition indicator information group set, restoring the indicator value of the business indicator corresponding to the above path map in real time to obtain an updated business indicator information set, wherein the above path map is a two-dimensional graph recording at least one analysis path; generating real-time item information for the above target virtual item based on the above updated business indicator information set, wherein the above real-time item information includes: item description information and item recommendation information.

[0105] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be set in a processor, for example, may be described as: a processor includes an acquisition unit, an execution unit, a real-time restoration unit and a generation unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the generation unit may also be described as "generating real-time item information for the above-mentioned target virtual item according to the above-mentioned updated business indicator information set, wherein the above-mentioned real-time item information includes: a unit for item description information and item recommendation information".

[0108] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0109] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for generating information based on transition indicators, comprising: Acquire a set of business indicator information for a target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator used to describe the state of the target virtual item; For each piece of business indicator information in the business indicator information set, the following first processing step is performed: According to the business indicator information, the business indicator corresponding to the business indicator information is decomposed into transition indicators to obtain a transition indicator information group, wherein the transition indicator information group includes: a transition indicator type and transition indicator description information, and the transition indicator type includes: a first-class transition indicator type and a second-class transition indicator type; Performing real-time indicator value updates on the transition indicators corresponding to each transition indicator information in the transition indicator information group to generate updated transition indicator information, thereby obtaining an updated transition indicator information group; According to the path map and the obtained updated transition indicator information group set, the indicator value of the business indicator corresponding to the path map is restored in real time to obtain an updated business indicator information set, wherein the path map is a two-dimensional map recording at least one analysis path; According to the updated business indicator information set, real-time item information for the target virtual item is generated, wherein the real-time item information includes: item description information and item recommendation information.

2. The method according to claim 1, wherein: The step of performing transition indicator decomposition on the business indicator corresponding to the business indicator information according to the business indicator information to obtain a transition indicator information group includes: According to the business indicator information, construct an indicator relationship tree, wherein the indicator relationship tree is a logic tree with the business indicator corresponding to the business indicator information as the root node, and characterizing the indicator settlement logic of the business indicator corresponding to the business indicator information; Performing a deep traversal on the indicator relationship tree to obtain at least one indicator relationship path, wherein the indicator relationship path is a path with the business indicator corresponding to the business indicator information as the first node; For each indicator relationship path in the at least one indicator relationship path, the following second processing step is performed: Eliminating the first node included in the indicator relationship path to generate an updated indicator relationship path; Determine transition indicator description information included in transition indicator information corresponding to the first node in the updated indicator relationship path; In response to the indicator types of the business indicators corresponding to the nodes other than the first node in the updated indicator relationship path being all first-class transition indicator types, updating the transition indicator type included in the transition indicator information corresponding to the first node in the updated indicator relationship path to first-class transition indicator type; In response to the existence of two types of transition indicator types in the indicator types of business indicators corresponding to nodes other than the first node in the updated indicator relationship path, the transition indicator type included in the transition indicator information corresponding to the first node in the updated indicator relationship path is updated to the second type of transition indicator type.

3. The method according to claim 2, wherein: The updating of the transition indicator corresponding to each transition indicator information in the transition indicator information group in real time to generate updated transition indicator information includes: Creating an indicator value update trigger for a transition indicator corresponding to the transition indicator information; In response to the indicator value update trigger being triggered, the transition indicator corresponding to the transition indicator information is updated in real time to update the transition indicator description information included in the transition indicator information to obtain updated transition indicator information corresponding to the transition indicator information.

4. The method according to claim 3, wherein: After updating the transition indicator corresponding to each transition indicator information in the transition indicator information group in real time to generate updated transition indicator information and obtaining the updated transition indicator information group, the method further includes: Obtaining a virtual item identifier corresponding to the target virtual item; For each updated transition indicator information in the updated transition indicator information group, the following third processing step is performed: Generate a transition indicator feature according to the transition indicator description information included in the updated transition indicator information, wherein the transition indicator feature includes: a transition indicator identifier and a quantitative feature identifier; Concatenating the virtual item identifier and the transition indicator feature to generate a candidate character string; Performing hashing on the candidate character string to generate a hash character string; Generate a data storage tree corresponding to the updated transition indicator information according to the hash string and the updated transition indicator information; A tree index address corresponding to the data storage tree is generated according to the hash character string.

5. The method according to claim 4, wherein: The step of restoring the indicator value of the business indicator corresponding to the path map in real time according to the path map and the updated transition indicator information group set obtained to obtain the updated business indicator information set includes: Constructing a multidimensional analysis tree for the target virtual item; Determine the dimensions of analysis; Determine at least one analysis path matching the analysis dimension to obtain the path map; According to the data storage tree corresponding to the path map and the updated transition indicator information, the indicator values ​​of the business indicators corresponding to the path map are restored in real time to obtain the updated business indicator information set.

6. An information generation device based on a transition indicator, comprising: An acquisition unit is configured to acquire a set of business indicator information for a target virtual item, wherein the business indicator corresponding to the business indicator information is an indicator for describing a state of the target virtual item; The execution unit is configured to perform the following first processing step for each business indicator information in the business indicator information set: according to the business indicator information, perform transition indicator decomposition on the business indicator corresponding to the business indicator information to obtain a transition indicator information group, wherein the transition indicator information group includes: a transition indicator type and transition indicator description information, and the transition indicator type includes: a first-class transition indicator type and a second-class transition indicator type; perform real-time indicator value update on the transition indicator corresponding to each transition indicator information in the transition indicator information group to generate updated transition indicator information, and obtain an updated transition indicator information group; A real-time restoration unit is configured to restore the indicator value of the business indicator corresponding to the path diagram in real time according to the path diagram and the obtained updated transition indicator information group set to obtain the updated business indicator information set, wherein the path diagram is a two-dimensional diagram recording at least one analysis path; The generating unit is configured to generate real-time item information for the target virtual item according to the updated business indicator information set, wherein the real-time item information includes: item description information and item recommendation information.

7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images