Method and apparatus for predicting business information, storage medium and electronic device

Abstract

The application discloses a kind of service information prediction method, device, storage medium and electronic equipment.It relates to the field of financial technology or other related fields, which comprises: obtaining the target information of the to-be-predicted organization, wherein the target information at least includes the attribute information of the to-be-predicted organization, the business volume data of the to-be-predicted organization during disaster and the historical business volume data of the to-be-predicted organization before disaster;The target information of the to-be-predicted organization is subjected to time series prediction processing to obtain the initial survival time, wherein the initial survival time represents the duration of the to-be-predicted organization's business volume affected by historical disasters;The attribute information of the to-be-predicted organization and the initial survival time are subjected to survival analysis processing to obtain the prediction result, wherein the prediction result represents the target duration of the to-be-predicted organization's business volume affected by the current disaster.The application solves the technical problem of low prediction accuracy of the duration of the business volume affected by the existing technology.

Description

Technical Field

[0001] This invention relates to the field of financial technology or other related fields, and more specifically, to a method, apparatus, storage medium, and electronic device for predicting business information. Background Technology

[0002] Currently, there is no effective method to predict the time required for business volume to recover from such a decline. Existing technologies often rely on subjective predictions to estimate the duration of the impact on business volume, lacking reliable evidence and thus resulting in low prediction accuracy.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, storage medium, and electronic device for predicting business information, in order to at least solve the technical problem of low accuracy in predicting the duration of business volume affected by circumstances in the prior art.

[0005] According to one aspect of the present invention, a method for predicting business information is provided, comprising: acquiring target information of an entity to be predicted, wherein the target information includes at least attribute information of the entity to be predicted, business volume data of the entity to be predicted during a disaster, and historical business volume data of the entity to be predicted before the disaster; performing time series prediction processing on the target information of the entity to be predicted to obtain an initial survival duration, wherein the initial survival duration characterizes the target duration of the business volume of the entity to be predicted being affected by historical disasters; and performing survival analysis processing on the attribute information of the entity to be predicted and the initial survival duration to obtain a prediction result, wherein the prediction result characterizes the target duration of the business volume of the entity to be predicted being affected by the current disaster.

[0006] Furthermore, the business information prediction method also includes: before obtaining the target information of the organization to be predicted, obtaining a first target data set of multiple organizations, wherein the first target data set includes at least the attribute information of multiple organizations, the business volume data of multiple organizations during the disaster, and the historical business volume data of multiple organizations before the disaster; converting the format of the first target data set to obtain a converted first target data set; extracting features from the converted first target data set to obtain first feature data; and training a first preset model based on the first feature data to generate a time series prediction model, wherein the first preset model is a time series prediction algorithm model.

[0007] Furthermore, the methods for predicting business information also include: performing time series prediction processing on the target information of the organization to be predicted based on a time series prediction model to obtain the initial survival duration.

[0008] Furthermore, the prediction method for business information also includes: detecting whether there is an initial lifespan corresponding to multiple institutions in the database; and when there is no initial lifespan in the database, obtaining a first target data set of multiple institutions from the database.

[0009] Furthermore, the method for predicting business information also includes: determining historical business volume data based on a first target data set; performing time series decomposition on the historical business volume data to obtain a second target data set, wherein the second target data set represents the time fluctuation data of the historical business volume of multiple institutions before the disaster; and extracting features from the second target data set to obtain first feature data.

[0010] Furthermore, the business information prediction method also includes: performing data processing operations on the second target data set based on a time series prediction model to obtain the initial survival duration; performing a difference calculation operation on the initial survival duration and the actual duration to obtain the target duration, wherein the actual duration represents the actual duration of the business volume of multiple institutions affected by the disaster; when the target duration is greater than a preset threshold, repeatedly performing data processing operations and difference calculation operations until the target duration is less than or equal to the preset threshold, performing data storage operations on the initial survival duration, and storing the initial survival duration in the database.

[0011] Furthermore, the business information prediction method also includes: before performing survival analysis on the attribute information and initial survival duration of the organization to be predicted to obtain the prediction result, acquiring a third target data set of multiple organizations, wherein the third target data set includes at least the attribute information and initial survival duration of multiple organizations; converting the format of the third target data set to obtain a converted third target data set; extracting features from the converted third target data set to obtain second feature data; and training a second preset model based on the second feature data to obtain a target model, wherein the second preset model is a survival analysis calculation model.

[0012] Furthermore, the prediction method for business information also includes: performing survival analysis on the attribute information and initial survival duration of the organization to be predicted based on the target model to obtain the prediction results.

[0013] According to another aspect of the present invention, a business information prediction apparatus is also provided, comprising: an information acquisition module for acquiring target information of an entity to be predicted, wherein the target information includes at least attribute information of the entity to be predicted, business volume data of the entity to be predicted during a disaster, and historical business volume data of the entity to be predicted before the disaster; a first processing module for performing time series prediction processing on the target information of the entity to be predicted to obtain an initial survival duration, wherein the initial survival duration characterizes the target duration of the business volume of the entity to be predicted being affected by historical disasters; and a second processing module for performing survival analysis processing on the attribute information of the entity to be predicted and the initial survival duration to obtain a prediction result, wherein the prediction result characterizes the target duration of the business volume of the entity to be predicted being affected by the current disaster.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the above-described business information prediction method at runtime.

[0015] According to another aspect of the present invention, an electronic device is also provided, the electronic device including one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are configured to run the programs, wherein the programs are configured to execute the above-described business information prediction method during runtime.

[0016] In this embodiment of the invention, a method is adopted to obtain the prediction result by performing two predictions on the target information of the organization to be predicted. First, the target information of the organization to be predicted is obtained, wherein the target information includes at least the attribute information of the organization to be predicted, the business volume data of the organization to be predicted during the disaster, and the historical business volume data of the organization to be predicted before the disaster. Time series prediction processing is performed on the target information of the organization to be predicted to obtain the initial survival duration, wherein the initial survival duration represents the target duration of the business volume of the organization to be predicted being affected by the historical disaster. Survival analysis processing is performed on the attribute information of the organization to be predicted and the initial survival duration to obtain the prediction result, wherein the prediction result represents the target duration of the business volume of the organization to be predicted being affected by the current disaster.

[0017] In the above process, the first prediction is made based on the target information to determine the duration of the impact of historical disasters on the business volume of the organization to be predicted, thus obtaining the initial survival time. Then, the attribute information of the organization to be predicted and the initial survival time are used for a second prediction. By making two predictions for the network to be predicted, the accuracy of the prediction of the duration of the impact of the situation on the business volume is improved, thereby solving the problem of low prediction accuracy of the duration of the impact of the situation on the business volume.

[0018] Therefore, the solution provided in this application achieves the goal of predicting the duration of business volume affected by circumstances, thereby improving the technical effect of predicting the duration of business volume affected by circumstances, and thus solving the technical problem of low prediction accuracy of business volume affected by circumstances in the prior art. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 This is a schematic diagram of an optional business information prediction method according to an embodiment of the present invention;

[0021] Figure 2 This is a schematic diagram of an optional scenario for predicting the time of impact on network points according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of the data processing module of the network point impact time prediction system according to an optional scenario of an embodiment of the present invention;

[0023] Figure 4 This is a flowchart illustrating an optional business information prediction method according to an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of an optional time series prediction model according to an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of the time processing module of the network point impact time prediction system according to an optional case of the present invention;

[0026] Figure 7 This is a schematic diagram of an optional process for generating a target model according to an embodiment of the present invention;

[0027] Figure 8 A schematic diagram of the survival analysis module of the site impact time prediction system according to an optional scenario of an embodiment of the present invention;

[0028] Figure 9 A schematic diagram of the business logic module of the branch impact time prediction system according to an optional case of an embodiment of the present invention;

[0029] Figure 10 A schematic diagram of an optional business information prediction device according to an embodiment of the present invention;

[0030] Figure 11A schematic diagram of an optional electronic device according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] It should be noted that all relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this invention are information and data authorized by the user or fully authorized by all parties. For example, this system has an interface with the relevant user or organization. Before obtaining relevant information, it needs to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent from the aforementioned user or organization.

[0034] Example 1

[0035] According to an embodiment of the present invention, an embodiment of a method for predicting business information is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] Figure 1 This is a schematic diagram of a business information prediction method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0037] Step S101: Obtain the target information of the organization to be predicted, wherein the target information includes at least the attribute information of the organization to be predicted, the business volume data of the organization to be predicted during the disaster, and the historical business volume data of the organization to be predicted before the disaster.

[0038] In step S101, the institution to be predicted can be any of the bank's service outlets. Optionally, the attribute information of the institution to be predicted includes its geographical location, surrounding population density, road conditions, and whether there are large shopping malls or other facilities nearby. Disasters can include natural disasters, situations, etc.; in this embodiment, "situation" is used to refer to a disaster.

[0039] Optionally, target information of the organization to be predicted can be obtained through the system, such as... Figure 2 As shown, this system can be a predictive system for the time impact of situations on network points. The system includes a data preprocessing module, a time processing module, a survival analysis module, and a business logic module. Optionally, such as... Figure 3 As shown, the data preprocessing module includes a data acquisition unit and a format conversion unit. The data acquisition unit is used to acquire the target information of the organization to be predicted, and the format conversion unit is used to convert the acquired data into a data format that can be used for feature engineering. For example, text information is converted into numerical information, such as converting whether to 0 or 1, and classification information (such as road conditions being good, good, medium, or poor) is converted into numerical values ​​such as 1, 2, 3, 5, etc.

[0040] Step S102: Perform time series forecasting processing on the target information of the agency to be predicted to obtain the initial survival duration, where the initial survival duration represents the duration of the continuous target duration of the business volume of the agency to be predicted being affected by historical disasters.

[0041] In step S102, the target information of the organization to be predicted can be processed by the system's time processing module. A time series prediction model is generated by training a preset model, and then time series prediction is performed on the target information of the organization to be predicted based on the time series prediction model to obtain the initial survival duration. For example, Figure 4 As shown, the initial survival time is the position where the distance between curve A and curve B is the smallest at the end of the influence in the figure. Curve A is the predicted survival time curve, and curve B is the actual value curve. When the distance between curve A and curve B is the smallest, the predicted value at this time is determined to be the initial survival time.

[0042] Step S103: Perform survival analysis on the attribute information and initial survival duration of the organization to be predicted to obtain the prediction result, wherein the prediction result represents the target duration of the business volume of the organization to be predicted being affected by the current disaster.

[0043] In step S103, the survival analysis module of the system can perform survival analysis on the attribute information and initial survival duration of the organization to be predicted. A target model is generated by training a preset model. Then, the attribute information and initial survival duration of the organization to be predicted are processed based on the target model to obtain the prediction result.

[0044] Based on the scheme defined in steps S101 to S103 above, it can be understood that in this embodiment of the invention, the method of obtaining the prediction result by performing two predictions on the target information of the organization to be predicted is adopted. First, the target information of the organization to be predicted is obtained, wherein the target information includes at least the attribute information of the organization to be predicted, the business volume data of the organization to be predicted during the disaster, and the historical business volume data of the organization to be predicted before the disaster occurs; the target information of the organization to be predicted is subjected to time series prediction processing to obtain the initial survival duration, wherein the initial survival duration represents the target duration of the business volume of the organization to be predicted being affected by the historical disaster; the attribute information of the organization to be predicted and the initial survival duration are subjected to survival analysis processing to obtain the prediction result, wherein the prediction result represents the target duration of the business volume of the organization to be predicted being affected by the current disaster.

[0045] It is noteworthy that in the above process, the initial survival time is obtained by first predicting the duration of the impact of historical disasters on the business volume of the organization to be predicted based on the target information. Then, the attribute information of the organization to be predicted and the initial survival time are used for a second prediction. By making two predictions on the network to be predicted, the accuracy of the prediction of the duration of the impact of the situation on the business volume is improved, thereby solving the problem of low prediction accuracy of the duration of the impact of the situation on the business volume.

[0046] Therefore, the solution provided in this application achieves the goal of predicting the duration of business volume affected by circumstances, thereby improving the technical effect of predicting the duration of business volume affected by circumstances, and thus solving the technical problem of low prediction accuracy of business volume affected by circumstances in the prior art.

[0047] In one optional embodiment, before obtaining the target information of the organization to be predicted, the system obtains a first target data set of multiple organizations, wherein the first target data set includes at least the attribute information of multiple organizations, the business volume data of multiple organizations during the disaster, and the historical business volume data of multiple organizations before the disaster; the system performs format conversion on the first target data set to obtain a converted first target data set; the system extracts features from the converted first target data set to obtain first feature data; and the system trains a first preset model based on the first feature data to generate a time series prediction model, wherein the first preset model is a time series prediction algorithm model.

[0048] In this embodiment, the first target data set is a collection of network information for all network points that have been affected by the situation, such as... Figure 5 The diagram shown illustrates the generation of a time series prediction model. First, the system acquires network information from multiple network points. Then, it converts the network information to obtain converted network information. Features are extracted from the converted network information to obtain first feature data. Based on the first feature data, a preset model is trained to obtain the time series prediction model.

[0049] Optionally, the system can... Figure 6 The time processing module shown generates a time series prediction model. This module includes a time series prediction algorithm library, a time series decomposition unit, a feature engineering unit, a control unit, and a survival time calculation unit. In this embodiment, the feature engineering unit extracts features from the converted network information. The extracted first feature data is then input into each algorithm model in the time series prediction algorithm library. The control unit trains each algorithm model to generate a time series prediction model. Different time series prediction algorithms correspond to different time series prediction models.

[0050] Optionally, the time series forecasting algorithm library provides a collection of time series forecasting algorithms. This library primarily selects algorithms that perform forecasting through time series decomposition, including but not limited to the Prophet algorithm.

[0051] Optionally, the control unit determines whether the time series prediction algorithm continues training. The main control methods include accuracy control and round control; training ends when the error falls below a threshold or the number of rounds reaches a set maximum. After the search is complete, the prediction results are saved to the database.

[0052] It should be noted that by training the preset algorithm model with attribute information from multiple institutions, business volume data of multiple institutions during the disaster, and historical business volume data of multiple institutions before the disaster, a time series prediction model was generated. This improved the accuracy of model training and prepared the way for subsequent prediction of survival time based on the time series prediction model.

[0053] Furthermore, the system performs time series prediction processing on the target information of the agency to be predicted based on a time series prediction model to obtain the initial survival duration.

[0054] Optionally, in this embodiment, the system performs time series prediction processing on the target information of the agency to be predicted using a time series prediction model to obtain the initial survival duration.

[0055] Optionally, the initial survival time can be obtained by averaging the outputs of multiple time series prediction models.

[0056] It should be noted that predicting the initial survival time using a time series prediction model improves the accuracy of survival time prediction.

[0057] Furthermore, the system checks whether there is an initial survival duration corresponding to multiple institutions in the database; if there is no initial survival duration in the database, it retrieves the first target data set of multiple institutions from the database.

[0058] Optional, such as Figure 5 The diagram shown illustrates the generation of a time series prediction model. It detects whether there is an initial survival duration corresponding to multiple institutions in the database. If the initial survival duration exists in the database, the processing is skipped. If the initial survival duration does not exist in the database, the first target data set of multiple institutions is obtained from the database.

[0059] It should be noted that by checking whether a preset survival time already exists in the database, the repeated generation of the initial survival time is avoided, thereby improving the efficiency of survival time prediction.

[0060] Furthermore, the system determines historical business volume data based on the first target data set; performs time series decomposition on the historical business volume data to obtain the second target data set, wherein the second target data set represents the time fluctuation data of the historical business volume of multiple institutions before the disaster; and extracts features from the second target data set to obtain the first feature data.

[0061] Optional, such as Figure 5 The diagram illustrates the generation of a time series prediction model. After determining historical traffic volume data from a first target data set, the system performs time series decomposition on the historical traffic volume data to obtain a second target data set that reflects the long-term trend of the historical traffic volume data. Then, features are extracted from the second target data set to obtain second feature data. Optionally, the second feature data is the data up to the moment the event occurred.

[0062] It should be noted that historical business volume data includes several components: long-term trend, seasonal variation, cyclical fluctuation, and irregular fluctuation. When a situation occurs, the long-term trend component of the branch business volume time series will show a significant decline. Therefore, we can take the occurrence of the situation as the starting point and the recovery of the long-term trend to normal levels as the ending point to obtain the impact time of the situation. Thus, by performing time series decomposition on historical business volume data to obtain a second target data set for the long-term trend, the accuracy of survival time prediction can be improved.

[0063] Furthermore, the system processes the second target dataset using a time series prediction model to obtain the initial survival duration; then, it calculates the difference between the initial survival duration and the actual duration to obtain the target duration, where the actual duration represents the actual duration of the impact of the disaster on the business volume of multiple institutions; when the target duration exceeds a preset threshold, the data processing and difference calculation operations are repeated until the target duration is less than or equal to the preset threshold, and the initial survival duration is stored in the database.

[0064] Optionally, in this embodiment, after the system performs data processing operations on the second target data set based on the time series prediction model to obtain the initial survival time, the system performs a difference calculation operation on the initial survival time and the actual survival time through the survival time calculation unit to obtain the target survival time. When the target survival time is greater than a preset threshold, the system repeatedly performs data processing operations and difference calculation operations until the target survival time is less than or equal to the preset threshold, and then stores the initial survival time in the database.

[0065] Optionally, if the business volume of the branch to be predicted is small and the target duration is consistently greater than the preset threshold, then the branch to be predicted is considered to be censored data, and the prediction will be stopped.

[0066] It should be noted that the target duration is obtained by calculating the difference between the initial survival time and the actual survival time. The smaller the target duration, the more accurate the predicted initial survival time data can be.

[0067] Furthermore, before performing survival analysis on the attribute information and initial survival duration of the institutions to be predicted to obtain the prediction results, the system acquires a third target dataset of multiple institutions, wherein the third target dataset includes at least the attribute information and initial survival duration of multiple institutions; the system performs format conversion on the third target dataset to obtain a converted third target dataset; the system extracts features from the converted third target dataset to obtain second feature data; and the system trains a second preset model based on the second feature data to obtain a target model, wherein the second preset model is a survival analysis calculation model.

[0068] Optionally, in this embodiment, such as Figure 7 The flowchart shown illustrates the process of generating the target model. The system acquires attribute information and initial survival time of multiple network points, then converts the attribute information into a new format, extracts features based on the converted attribute information and initial survival time to obtain second feature data, and trains a preset model based on the extracted second feature data to obtain the target model.

[0069] Optionally, the target model can be generated through the system's survival analysis module, where, for example... Figure 8The diagram illustrates the survival analysis module of a site impact time prediction system. The survival analysis module includes a data acquisition unit, a survival analysis algorithm library, a data feature construction unit, and a control unit. Optionally, the data acquisition unit acquires attribute information and initial survival duration for multiple sites. The survival analysis algorithm library provides a collection of survival analysis algorithms, including but not limited to the random survival forest algorithm. The data feature construction unit is responsible for constructing feature data for various survival analysis algorithms, including feature filtering and format conversion. Feature filtering removes irrelevant features based on their importance; common filtering methods include the VIMP method and the minimum depth method. Format conversion considers the different data format requirements of different algorithms and requires format conversion according to the specific requirements of each algorithm. The control unit controls the operation of the survival analysis algorithms. Optionally, different survival analysis algorithms correspond to different survival analysis calculation models.

[0070] It should be noted that by generating the target model based on the attribute information of multiple network points and the initial survival time, the accuracy of model generation is improved, which prepares for obtaining prediction results based on the model in the future.

[0071] Furthermore, the system performs survival analysis on the attribute information and initial survival duration of the target model to obtain the prediction results.

[0072] Optionally, in this embodiment, the system predicts the attribute information and initial survival time of the target model to obtain the prediction result.

[0073] Optional, such as Figure 9 The diagram illustrates the business logic modules of the network impact time prediction system. The system's business logic processing modules include a data preprocessing unit, a time processing unit, and a survival analysis unit. The data preprocessing unit interacts with the data acquisition unit and format conversion unit mentioned above, establishing interrelationships. The time processing unit interacts with the time series prediction algorithm library, time series decomposition unit, survival time calculation unit, and control unit mentioned above, establishing interrelationships. The survival analysis unit interacts with the data acquisition unit, survival analysis algorithm library, data feature construction unit, and control unit mentioned above, establishing interrelationships.

[0074] Therefore, this invention provides a system and method for predicting the impact time of situations on network sites based on survival analysis. This method uses time series forecasting to obtain the impact time of situations in historical data, and uses survival analysis algorithms to predict how long a network site will be affected by a newly occurring situation. This provides a reliable means of predicting the impact time of situations, and provides guidance for network sites to estimate the impact of situations and adjust work during situations.

[0075] Example 2

[0076] According to an embodiment of the present invention, an embodiment of a business information prediction device is provided, wherein, Figure 10 A schematic diagram of an optional business information prediction device according to an embodiment of the present invention, such as... Figure 10 As shown, the device includes:

[0077] The information acquisition module 1001 is used to acquire the target information of the organization to be predicted, wherein the target information includes at least the attribute information of the organization to be predicted, the business volume data of the organization to be predicted during the disaster, and the historical business volume data of the organization to be predicted before the disaster. The first processing module 1002 is used to perform time series prediction processing on the target information of the organization to be predicted to obtain the initial survival duration, wherein the initial survival duration represents the target duration of the business volume of the organization to be predicted being affected by historical disasters. The second processing module 1003 is used to perform survival analysis processing on the attribute information and the initial survival duration of the organization to be predicted to obtain the prediction result, wherein the prediction result represents the target duration of the business volume of the organization to be predicted being affected by the current disaster.

[0078] It should be noted that the information acquisition module 1001, the first processing module 1002, and the second processing module 1003 mentioned above correspond to steps S101 to S103 in the above embodiments. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the content disclosed in the above embodiment 1.

[0079] Optionally, the business information prediction device further includes: a first acquisition module, a first conversion module, a first extraction module, and a first generation module. The first acquisition module acquires a first target data set of multiple institutions before acquiring the target information of the institution to be predicted. The first target data set includes at least attribute information of the multiple institutions, business volume data of the multiple institutions during the disaster, and historical business volume data of the multiple institutions before the disaster. The first conversion module converts the format of the first target data set to obtain a converted first target data set. The first extraction module extracts features from the converted first target data set to obtain first feature data. The first generation module trains a first preset model based on the first feature data to generate a time series prediction model, wherein the first preset model is a time series prediction algorithm model.

[0080] Optionally, the business information prediction device also includes: a third processing module, used to perform time series prediction processing on the target information of the organization to be predicted based on a time series prediction model, to obtain the initial survival duration.

[0081] Optionally, the business information prediction device further includes a detection module and a second acquisition module. The detection module is used to detect whether there is an initial survival duration corresponding to multiple institutions in the database; the second acquisition module is used to acquire a first target data set of multiple institutions from the database when there is no initial survival duration in the database.

[0082] Optionally, the business information prediction device further includes: a determination module, a decomposition module, and a second extraction module. The determination module is used to determine historical business volume data based on a first target data set; the decomposition module is used to perform time series decomposition on the historical business volume data to obtain a second target data set, wherein the second target data set represents the time fluctuation data of the historical business volume of multiple institutions before the disaster; the second extraction module is used to extract features from the second target data set to obtain first feature data.

[0083] Optionally, the business information prediction device further includes: a data processing module, a difference calculation module, and an execution module. The data processing module performs data processing operations on the second target dataset based on a time series prediction model to obtain the initial survival duration. The difference calculation module performs difference calculation operations on the initial survival duration and the actual duration to obtain the target duration, where the actual duration represents the actual duration of the impact of the disaster on the business volume of multiple institutions. The execution module repeatedly executes the data processing and difference calculation operations when the target duration exceeds a preset threshold until the target duration is less than or equal to the preset threshold, and then performs data storage operations on the initial survival duration, storing the initial survival duration in the database.

[0084] Optionally, the business information prediction device further includes: a third acquisition module, a second conversion module, a second extraction module, and a second generation module. The third acquisition module is used to acquire a third target data set of multiple institutions before performing survival analysis on the attribute information and initial survival duration of the institutions to be predicted to obtain the prediction result. The third target data set includes at least the attribute information and initial survival duration of multiple institutions. The second conversion module is used to convert the format of the third target data set to obtain a converted third target data set. The second extraction module is used to extract features from the converted third target data set to obtain second feature data. The second generation module is used to train a second preset model based on the second feature data to obtain a target model, wherein the second preset model is a survival analysis calculation model.

[0085] Optionally, the business information prediction device also includes: a fourth processing module, used to perform survival analysis processing on the attribute information and initial survival duration of the organization to be predicted based on the target model, and obtain the prediction results.

[0086] Example 3

[0087] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the above-described business information prediction method at runtime.

[0088] Example 4

[0089] According to another aspect of the present invention, an electronic device is also provided, wherein, Figure 11 This is a schematic diagram of an optional electronic device according to an embodiment of the present invention, such as... Figure 11 As shown, the electronic device includes one or more processors; and a memory for storing one or more programs, which, when executed by one or more processors, enable the one or more processors to run the programs, wherein the programs are configured to execute the aforementioned business information prediction method during runtime.

[0090] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0091] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0095] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0096] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for predicting business information, characterized in that, include: Obtain target information of the organization to be predicted, wherein the target information includes at least the attribute information of the organization to be predicted, the business volume data of the organization to be predicted during the disaster, and the historical business volume data of the organization to be predicted before the disaster. The target information of the institution to be predicted is processed by time series prediction to obtain the initial survival duration, wherein the initial survival duration represents the continuous target duration of the business volume of the institution to be predicted being affected by historical disasters; Survival analysis is performed on the attribute information of the organization to be predicted and the initial survival duration to obtain a prediction result, wherein the prediction result characterizes the target duration of the business volume of the organization to be predicted being affected by the current disaster. Before obtaining the target information of the organization to be predicted, the method further includes: obtaining a first target data set of multiple organizations, wherein the first target data set includes at least the attribute information of the multiple organizations, the business volume data of the multiple organizations during the disaster, and the historical business volume data of the multiple organizations before the disaster; converting the format of the first target data set to obtain a converted first target data set; extracting features from the converted first target data set to obtain first feature data; and training a first preset model based on the first feature data to generate a time series prediction model, wherein the first preset model is a time series prediction algorithm model. The process of extracting features from the transformed first target data set to obtain first feature data includes: determining the historical business volume data based on the first target data set; performing time series decomposition on the historical business volume data to obtain a second target data set with the long-term trend of the historical business volume data, wherein the second target data set represents the time fluctuation data of the historical business volume of the multiple institutions before the disaster; and extracting features from the second target data set to obtain the first feature data.

2. The method according to claim 1, characterized in that, The target information of the organization to be predicted is subjected to time series prediction processing to obtain the initial survival time, including: The target information of the organization to be predicted is processed by time series prediction based on the time series prediction model to obtain the initial survival duration.

3. The method according to claim 2, characterized in that, Obtain the primary target dataset from multiple institutions, including: Check if the database contains an initial survival duration corresponding to the multiple institutions; If the initial survival duration does not exist in the database, the first target data set of the multiple institutions is obtained from the database.

4. The method according to claim 2, characterized in that, Based on the time series prediction model, the target information of the organization to be predicted is processed by time series prediction to obtain the initial survival duration, including: Based on the time series prediction model, data processing operations are performed on the second target dataset to obtain the initial survival time; The target duration is obtained by performing a difference calculation operation on the initial survival duration and the actual duration, wherein the actual duration represents the actual duration of the impact of the disaster on the business volume of the multiple institutions; When the target duration exceeds a preset threshold, the data processing operation and the difference calculation operation are repeated until the target duration is less than or equal to the preset threshold. Then, the initial survival duration is stored in the database.

5. The method according to claim 1, characterized in that, Before performing survival analysis on the attribute information of the organization to be predicted and the initial survival duration to obtain the prediction result, the method further includes: A third target data set of multiple institutions is obtained, wherein the third target data set includes at least the attribute information of the multiple institutions and the initial survival time of the multiple institutions; The third target data set is format-converted to obtain the converted third target data set; Feature extraction is performed on the transformed third target data set to obtain second feature data; The second preset model is trained based on the second feature data to obtain the target model, wherein the second preset model is a survival analysis calculation model.

6. The method according to claim 5, characterized in that, Survival analysis is performed on the attribute information of the organization to be predicted and the initial survival duration to obtain prediction results, including: Based on the target model, survival analysis is performed on the attribute information of the organization to be predicted and the initial survival time to obtain the prediction result.

7. A business information prediction device, characterized in that, include: The information acquisition module is used to acquire target information of the organization to be predicted, wherein the target information includes at least the attribute information of the organization to be predicted, the business volume data of the organization to be predicted during the disaster, and the historical business volume data of the organization to be predicted before the disaster. The first processing module is used to perform time series prediction processing on the target information of the organization to be predicted to obtain the initial survival duration, wherein the initial survival duration represents the continuous target duration of the business volume of the organization to be predicted being affected by historical disasters. The second processing module is used to perform survival analysis on the attribute information of the organization to be predicted and the initial survival duration to obtain a prediction result, wherein the prediction result characterizes the target duration of the business volume of the organization to be predicted being affected by the current disaster. The business information prediction device further includes: a first acquisition module for acquiring a first target data set of multiple institutions before acquiring the target information of the institution to be predicted, wherein the first target data set includes at least the attribute information of the multiple institutions, the business volume data of the multiple institutions during the disaster, and the historical business volume data of the multiple institutions before the disaster; a first conversion module for converting the format of the first target data set to obtain a converted first target data set; a first extraction module for extracting features from the converted first target data set to obtain first feature data; and a first generation module for training a first preset model based on the first feature data to generate a time series prediction model, wherein the first preset model is a time series prediction algorithm model. The business information prediction device includes: a determination module for determining the historical business volume data based on the first target data set; a decomposition module for performing time series decomposition on the historical business volume data to obtain a second target data set with the long-term trend of the historical business volume data, wherein the second target data set represents the time fluctuation data of the historical business volume of the multiple institutions before the disaster; and a second extraction module for performing feature extraction on the second target data set to obtain the first feature data.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the business information prediction method according to any one of claims 1 to 6 when it is run.

9. An electronic device, characterized in that, The electronic device includes one or more processors; A memory for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to be configured to run the programs, wherein the programs are configured to execute the business information prediction method as described in any one of claims 1 to 6 at runtime.

Images