WO2020077871A1

WO2020077871A1 - Event prediction method and apparatus based on big data, computer device, and storage medium

Info

Publication number: WO2020077871A1
Application number: PCT/CN2018/125082
Authority: WO
Inventors: 黄泽浩; 汤政
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-10-15
Filing date: 2018-12-28
Publication date: 2020-04-23
Also published as: CN109597833A

Abstract

Disclosed in embodiments of the present application are an event prediction method and apparatus based on big data, a computer device, and a storage medium. The method comprises the following steps: obtaining personal information of a user, wherein the personal information comprises working information, family information, and life trajectory information of the user; searching a first target data record matching the working information, the family information and the life trajectory information in a preset national statistical database according to the personal information; and resetting the life trajectory information on the basis of the first target data record to generate prediction event information, and pushing the prediction event information to the user. According to the embodiments of the present application, the personal information of the user is obtained; then a first target data record matching the personal information of the user is searched; the life trajectory information of the user is reset on the basis of the first target data record to generate the prediction event information; the prediction event information is pushed to the user, and a future big probability occurrence event of the user is predicted by means of big data statistics, so that the accuracy and scientificity of the prediction event are improved.

Description

Event prediction method, device, computer equipment and storage medium based on big data

This application requires the priority of the Chinese patent application filed on October 15, 2018 with the Chinese Patent Office, the application number is 201811198445.X, and the invention title is "Big Data-based Event Prediction Method, Device, Computer Equipment, and Storage Medium" The entire contents are incorporated by reference in this application.

Technical field

The embodiments of the present application relate to the technical field of data analysis, and in particular to an event prediction method, device, computer equipment, and storage medium based on big data.

Background technique

Event prediction refers to a method of speculating and budgeting possible future events. However, the inventor found that the existing event prediction methods are unscientific, such as fortune telling. There is no scientific basis for predicting what users will happen or encounter.

Summary of the invention

Embodiments of the present application provide an event prediction method, device, computer equipment, and storage medium based on big data to calculate events with a high probability of occurrence through scientific statistics and big data analysis.

In order to solve the above technical problems, a technical solution adopted by the embodiment created by the present application is to provide an event prediction method based on big data, which includes the following steps: acquiring user's personal information, wherein the personal information includes the user's personal information Work information, family information and life trajectory information; search for a first target data record matching the work information, family information and life trajectory information in a preset national statistics database according to the personal information; use the first The target data record is to generate predicted event information based on resetting the life track information and push it to the user.

To solve the above technical problems, an embodiment of the present application further provides an event prediction device based on big data, including: a first acquisition module for acquiring personal information of a user, wherein the personal information includes the user's work information and family Information and life trajectory information; a first processing module for searching for a first target data record matching the work information, family information and life trajectory information in a preset national statistics database based on the personal information; first The execution module is configured to reset the life track information based on the first target data record to generate predicted event information and push it to the user.

To solve the above technical problems, the embodiments of the present application further provide a computer device, including a memory and a processor, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, The processor executes the following steps of an event prediction method based on big data: acquiring personal information of the user, wherein the personal information includes the user's work information, family information, and life path information; Find the first target data record matching the work information, family information and life trajectory information in the established national statistics database; reset the life trajectory information based on the first target data record to generate predicted event information and Push to the user.

To solve the above technical problems, embodiments of the present application also provide a non-volatile storage medium storing computer-readable instructions, which when executed by one or more processors, cause one or more processes The device executes the following steps of an event prediction method based on big data: acquiring the user ’s personal information, where the personal information includes the user ’s work information, family information, and life trajectory information; according to the personal information in the preset Find the first target data record matching the work information, family information and life track information in the national statistics database; reset the life track information based on the first target data record to generate predicted event information and push to The user.

The embodiment of the present application obtains the user's personal information, including the user's work information, family information and life trajectory information, where the life trajectory information is the information of the user's events in daily life, and then looks up the user's The first target data record that matches personal information, because the first target data record matches the user's work information, family information, and life track information, so that the occurrence of the first target data record is likely to occur On the user, the user ’s life trajectory information can be reset based on the first target data record, thereby generating predicted event information of events that will occur with a high probability in the user ’s future and pushing them to the user, through statistical prediction of big data Users have a high probability of events in the future, improving the accuracy and scientificity of predicting events.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions in the embodiments of the present application, the drawings required in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application For those skilled in the art, without paying any creative work, other drawings can also be obtained based on these drawings.

FIG. 1 is a schematic flowchart of an event prediction method based on big data according to an embodiment of the present application;

FIG. 2 is a schematic flowchart of generating predicted event information according to the user ’s historical browsing information according to an embodiment of the present application;

3 is a schematic flowchart of generating predicted event information according to user insurance claims according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a process of setting a person in charge of a material object to obtain insurance compensation information of a user according to an embodiment of the present application;

FIG. 5 is a schematic flowchart of saving predicted event information according to an embodiment of the present application;

FIG. 6 is a schematic flowchart of obtaining personal identity information of a user according to an embodiment of the present application;

7 is a schematic flowchart of establishing an asynchronous thread according to an embodiment of this application;

8 is a schematic diagram of a basic structure of an event prediction device based on big data according to an embodiment of the present application;

9 is a block diagram of a basic structure of a computer device according to an embodiment of the present application.

detailed description

In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application.

Some processes described in the specification and claims of the present application and the above drawings include multiple operations in a specific order, but it should be clearly understood that these operations may not be in the order in which they appear in this document Execution or parallel execution. The sequence numbers of operations such as 101 and 102 are only used to distinguish different operations. The sequence number itself does not represent any execution sequence. In addition, these processes may include more or fewer operations, and these operations may be performed sequentially or in parallel. It should be noted that the descriptions of "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order, nor limit "first" and "second". Are different types.

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the protection scope of the present application.

Example 1

Please refer to FIG. 1 for details. FIG. 1 is a schematic flowchart of an event prediction method based on big data in this embodiment.

As shown in Figure 1, an event prediction method based on big data includes the following steps:

S1100. Acquire personal information of the user, where the personal information includes the user's work information, family information, and life track information;

The user's personal information includes at least: work information, family information and life trajectory information, where work information refers to the job position information the user is engaged in, family information includes the user's family member information and home address information, etc., life trajectory information refers to It is the user ’s life experience information. The life trajectory information includes information about major events that occur in the user ’s life. Among them, whether the event is a major event is determined by the user. When the user feels that an event has a significant impact on himself, such as the graduation ceremony, The first bucket of gold or other events in life can be defined as a major event. Life trajectory events include the education received, renting a house, getting married, having a child, working in a job, and favorite sports. Events in.

During implementation, the user's work information, family information and life track information can be input by the user through the user terminal, and the system obtains the user's personal information sent by the user terminal. Of course, the system can provide a complete set of forms or question and answer questions and send them to the user terminal for the user to fill in, so as to collect the user's recent major events, such as the events that occurred in the last 30 days, 15 days, or within a week.

S1200. Search for a first target data record matching the work information, family information, and life track information in a preset national statistics database according to the personal information;

The national statistics database is a warehouse for storing and managing personal information preset in the system. The national statistics database stores several (for example, 1 million) data records, which correspond to the personal information of a user. The database searches for the first target data record that matches the user's work information, family information, and life track information. The search principle is: the event represented by the personal information corresponding to the first target data record is more representative than the user's personal information. There are many events, so you can predict the user's future events based on the extra events. Among them, the difference between the user ’s personal information and the personal information recorded in the first target data is less than the preset error value (for example, 5%) is considered to match, for example: Zhang San works for the software development engineer under the Ping An Group, Zhang San worked at the Ping'an Building in Futian District, Shenzhen and has been in that position for 5 years. Li Si is also a software development engineer under the Ping An Group. Li Si works at the Ping An Building in Nanshan District, Shenzhen and is already in The position has been in service for 4 years and 10 months, and it is considered that the job information of Zhang San and Li Si match; during implementation, users with the same life track information can also be classified into one category, such as living and living in Shenzhen, Guangdong. The users of the restaurant waiters who learn are classified into one category, and the users of enterprise engineers who live and study in Shenzhen, Guangdong are classified into another category. According to the user's personal information, the user who belongs to the category is found from the national statistics database, and Find the first target data record according to the category to which the user belongs. It should be noted that searching for the first target data record that matches the user's personal information is not limited to the above description and data, and other methods or values may be used according to different application scenarios.

S1300. Reset the life track information based on the first target data record to generate predicted event information and push it to the user.

After finding the first target data record, reset the user's life trajectory information according to the first target data record to generate pre-test volume information and push it to the user. During implementation, the data records matching the user's personal information are found: Multiple, the same feature point can be extracted according to the found multiple data records, and preset event information can be generated according to the same feature point as a parameter. Taking the user Zhang San ’s son born half a month ago as an example, the system finds that the probability that the user will feast (such as a child ’s full moon wine) in the next 15 days is 92%, of which 90% is based on big data According to statistics, for example, by interviewing and collecting 500,000 pairs of parents who will hold a wine banquet when their children are full moon, about 460,000 pairs of parents will indicate that they will put a full moon, and the system will find the probability of occurrence of the event and A preset probability threshold (for example, 85%) is compared. Events that exceed the preset probability threshold are considered to be high probability events. The system automatically resets the high probability event to the user ’s life track information to generate Zhang Sanjiang. The predicted event information of the child's full moon wine will be pushed to Zhang San's user terminal within the next 15 days to serve the purpose of scientifically predicting the future. Of course, due to the different customs and habits in different places, you can select the collected data of the area that matches Zhang San's hometown or place of residence as a reference, thereby improving the accuracy of predicting events.

In one embodiment, the first target data record is a collection of a plurality of other users ’life tracks that are the same as the user ’s life track. The same life track is used to predict the user ’s future events that will occur with a high probability, which can provide prediction events. Accuracy, for example, Zhang San is a mobile phone circuit hardware engineer who has worked for Huawei for ten years. Zhang San wants to predict his job prospects. After the system obtains Zhang San ’s personal information, he finds in the national statistics database with Zhang San ’s personal information matches the first target data record, thus generating the predicted event information that Zhang San will be promoted to department head in the near future and sends it to Zhang San. Specifically, the first target data record is characterized as based on Huawei employees According to information statistics, 89% of employees who worked in Huawei for ten years were promoted to technical supervisors. Therefore, according to the first target data record, the probability of Zhang San being promoted to department head is 89%, and this event is a high probability event, so the first target data record can be used as a parameter to reset Zhang San ’s life trajectory information to generate Zhang San was promoted to the department manager's preset event information and pushed it to the user, thereby predicting the user's high probability of an event in the future.

In this embodiment, the user's personal information is obtained, including the user's work information, family information, and life trajectory information, where the life trajectory information is information about events that occur in the user's daily life, and then looks up the user's personal information in the national statistics database. The first target data record that matches the information, because the first target data record matches the user's work information, family information, and life trajectory information, so that the occurrence of the first target data record is likely to occur in the same On the user, the user's life trajectory information can be reset based on the first target data record, thereby generating predicted event information of events that will occur with high probability in the user's future and pushing them to the user, and predicting the user through big data statistics Events with high probability in the future will improve the accuracy and scientificity of forecasting events.

In an optional embodiment, the user may also be used to predict the user's future high-probability event according to the user's browsing history in the most recent period of time. Please refer to FIG. 2, which is generated according to the user ’s historical browsing information according to an embodiment of the present application. Schematic diagram of the basic process of predicting event information.

As shown in FIG. 2, before the step of resetting the life trajectory information based on the target data record to generate predicted event information and push it to the user, the following steps are also included:

S1210: Obtain historical browsing information of the user within the first preset time period;

The user's historical browsing information refers to the user's history of browsing web pages within the first preset time period, where the first preset time period is preset by the system, such as 7 days, 15 days, 20 days, or 30 days, etc. For example, when a user connects to a network to search for data or browse a page through a preset application APP, the system is associated with the preset application APP, and the system automatically obtains the user's historical browsing information according to the associated application APP.

S1220. Find a second target data record corresponding to the historical browsing information in a preset browsing statistics database and write it into the first target data record.

The browsing statistics database is preset as a warehouse for storing and managing the user's browsing records. After obtaining the user's historical browsing information, the second target data record is searched in the preset browsing statistics database. (For example, 20 times) go online to find information about car sales, including new car and second-hand car market news, the system will classify Li Si as a pre-purchased car based on Li Si's historical browsing information, and the system will obtain Li Si's history After browsing the information, the second target data record is searched in the browsing statistics database. The information carried by the second target data record is: the probability that a user who browses the car purchase web page information for 7 days to buy a new car is 92%, and the probability of 92% is through Obtained from the statistics of online car purchase records and online browsing records. Specifically, according to the statistics, within 7 days, 300,000 users continued to browse the car purchase webpage for 7 days, of which 275,000 users purchased the vehicle after browsing the web. According to statistics, about 92% of users will continue to browse the web pages about car purchase or vehicle sales When buying a vehicle, the event is a high-probability event. The system generates the predicted event information that Li Si will purchase the vehicle in the near future according to the second target data record and sends it to Li Si. Through big data statistics, the probability of the event is scientifically calculated.

In an alternative embodiment, the user's insurance claims can also be used to predict the user's future event with a high probability. Please refer to FIG. 3, which is a schematic diagram of a basic process for generating predicted event information based on user insurance claims according to an embodiment of the invention. .

As shown in FIG. 3, the step of acquiring the user's personal information, where the personal information includes the user's work information, family information and life track information, includes the following steps:

S1010: Obtain insurance compensation information associated with the user within a second preset time period;

The second preset time period is a time value preset by the system, for example, 30 days, 3 months, or 6 months. In implementation, the values of the first preset time period and the second preset time period can be performed by the user himself Set, the insurance compensation information refers to the information that the user requests for compensation within the second preset time period, including the type of insurance, the amount of compensation, the time of payment and the payment items, where the payment items are the reasons and reasons for the user to request the insurance payment.

In an alternative embodiment, please refer to FIG. 4, which is a schematic diagram of a basic process for obtaining insurance compensation information of a user according to an embodiment of the present application.

As shown in FIG. 4, step S1010 also includes the following steps:

S1011: Acquire the interface information of the preset insurance application program;

Insurance application refers to an APP (Application) issued by an insurance company to facilitate users to make online purchases, inquiries, or apply for compensation. Interface information refers to a method for the insurance application to communicate or exchange data with external programs. The interface information is exposed by the insurance application, and the system can associate with the insurance application based on the interface information.

S1012. Acquire insurance history records associated with the user in the insurance application according to the interface information, where the insurance history records include the insurance compensation information.

After obtaining the interface information of the insurance application, the system associates with the insurance application according to the interface information, for example, the system is associated with the Ping An Life APP under the Ping An Group, thereby obtaining the association with the user within the second preset time period in the Ping An Life APP For insurance history records, it should be noted that the second preset time period is not limited to the above specific values, and the second preset time period may be designed to other values according to different application scenarios.

S1020. Add the insurance compensation information to the user's personal information.

After obtaining the insurance compensation information associated with the user, the insurance compensation information is added to the user's personal information, and the system generates predicted event information based on the personal information added with the insurance compensation information, specifically, Zhang San 2 months ago An example of the Ping An Group ’s auto insurance claims is requested. The reason for Zhang San ’s request for compensation is that Zhang San ’s car suffered an accident during driving and caused damage to the car body, and the damage to Zhang San ’s car reached the level of scrapping. The insurance compensation information looks for the first target data record in the preset Quanming statistical database. According to the first target data record, the probability that Zhang San will buy a new car is 87%. This probability can be used by the Ping An Group to the user The statistics of the insurance compensation return visit data and the data records of the users who bought a new car after buying a new car are statistically obtained. Among them, 600,000 users request insurance compensation for the same reason (the same as the situation of Zhang San ’s vehicle), and these 600,000 users There are approximately 520,000 users who purchase vehicles again within 3 months after receiving insurance compensation, according to the first target data. Joe Smith in the recent (eg within 2 months) the purchase of a new car is a large probability event occurs, the system generates a send event information to predict based on the John Doe big probability event.

Of course, in order to improve the accuracy of forecasting events, you can also make predictions based on Zhang San ’s residential address. For example, Zhang San lives in Shenzhen, and 600,000 users have requested insurance compensation due to the same scrapping reasons as Zhang San ’s vehicle. There are 210,000 Shenzhen users, and 204,000 of the 210,000 Shenzhen users buy vehicles again within 3 months of receiving insurance compensation. Therefore, the probability of Shenzhen users buying cars again after the car is scrapped is 97%, then It can be seen that Zhang San's recent car purchase is a high probability event.

In an alternative embodiment, in order to facilitate the management of the user ’s predicted event information, the generated predicted event information and the user ’s identity information can be saved, please refer to FIG. 5, which is an embodiment of the present application to save the predicted event Schematic diagram of the basic flow of information.

As shown in FIG. 5, after the step of resetting the life trajectory information based on the first target data record to generate predicted event information and pushing it to the user, the following steps are also included:

S1400: Obtain the personal identity information of the user;

Personal identification information is identification identification information used to prove the identity of the user, including but not limited to: name, mobile phone number and ID card number. In implementation, the user can enter the user's personal identification information through the user terminal, the user terminal includes but not It is limited to mobile phones, tablets, notebook computers or other electronic devices that can send and receive information wirelessly, and the system can receive the user's personal identity information sent by the user terminal.

S1500. Save the personal identity information and the predicted event information to a preset user account database.

The user account database is a warehouse for users to store and manage the user's account information preset by the system. After generating the predicted event information, the predicted event information and the user's personal information are merged into the user's predicted information and stored in the user account database, which is convenient for later Find information about predicted events related to users.

In an alternative embodiment, please refer to FIG. 6, which is a schematic diagram of a basic process for obtaining personal identity information of a user according to an embodiment of the present application.

As shown in FIG. 6, the step of acquiring the personal identity information of the user includes the following steps:

S1410: Acquire the face image of the user;

The user's face image can be obtained by taking pictures or videos. In one embodiment, taking the user's face image by taking a video as an example, the user terminal is provided with a camera to shoot the user to obtain the target video and send it to On the server side (system), the system can process the target video through video processing software (such as OpenCV), split the target video into several frames, and extract the picture image from the target video by timing acquisition. For example, a target picture is extracted from the target video at a rate of 0.5 seconds, and then a target picture is randomly selected as the user's face image from the obtained several target pictures; but not limited to this, according to the specific application scenario The speed of image acquisition can be adjusted adaptively. The adjustment principle is that the stronger the processing capacity of the system and the higher the tracking accuracy requirements, the shorter the acquisition time, until it is synchronized with the frequency of image acquisition by the camera equipment; otherwise , The longer the collection interval, but the longest collection interval should not exceed 1s. Of course, it is also possible to directly select a frame as a user's face image from several frames of the target video.

S1420. Input the face image into a preset face recognition model, where the face recognition model is a convolutional neural network model trained to convergence;

In the implementation, LSTM network (Long Short-Term Memory Artificial Neural Network Model, Long Short-Term Memory) is used as the convolutional neural network model. The LSTM network controls the discarding or adding of information through a "gate" to realize the function of forgetting or remembering. A "gate" is a structure that selectively passes information, and is composed of a sigmoid (S-shaped growth curve) function and a dot product operation. The output value of the sigmoid function is in the range of [0, 1], where 0 means completely discarded and 1 means completely passed. The convolutional neural network model trained to convergence has a classifier that can recognize the user's face image. The face recognition model includes the above-mentioned convolutional neural network model. The convolutional neural network model includes N + 1 classifiers , N is a positive integer. Specifically, the user's personal identity information is obtained by inputting the user's face image into a preset face recognition model.

S1430: Acquire the personal identity information of the user output by the face recognition model.

The preset image recognition model recognizes the user's face information based on the user's face image, and synthesizes the face information and the user's name, ID number or mobile phone number and other information into the user's personal identity information, thereby facilitating the user's personal identification information The face information, name, ID card number and mobile phone number are accurately located to the user-predicted event information stored in the user account database.

In an optional embodiment, when storing the predicted event information, the asynchronous thread can be used to store the system when it is idle. Please refer to FIG. 7, which is a basic process of establishing an asynchronous thread according to an embodiment of the present application. schematic diagram.

As shown in FIG. 7, the step of saving the personal identity information and the predicted event information in a preset user account database includes the following steps:

S1510: Establish and execute a to-be-executed task by saving the personal identity information and the predicted event information in a preset user account database through a thread;

A thread is a single sequential control flow in an application program. There is a relatively independent and schedulable execution unit in the process, which is the scheduling unit of the program when the system independently schedules and dispatches the basic unit instruction of the CPU. Running multiple threads simultaneously in a single program to complete different tasks is called multithreading. By establishing and executing the to-be-executed task of saving the personal identity information and the predicted event information in a preset user account database, the predicted event information storage operation and other operations of other application programs are asynchronously multi-threaded simultaneously.

S1520: Detect whether there is an operation task with a priority higher than the task to be executed in the task queue after the task to be executed;

S1530. When there is an operation task with a higher priority than the task to be executed in the task queue, execute the operation task with priority until the execution of the operation task is completed and then call back to execute the task to be executed.

Priority execution of other operation tasks with a higher priority than the task to be executed can make the system run smoothly and not stutter. For example, multiple users request predicted event information at the same time, the system first executes the operation task that generates predicted event information before executing The task to be executed reduces the waiting time of the user and improves the user experience.

To solve the above technical problems, embodiments of the present application also provide an event prediction device based on big data.

For details, please refer to FIG. 8, which is a schematic diagram of a basic structure of an event prediction device based on big data in this embodiment.

As shown in FIG. 8, an event prediction device based on big data includes: a first acquisition module 2100, a first processing module 2200, and a first execution module 2300, where the first acquisition module 2100 is used to acquire the user's personal information , Where the personal information includes the user's work information, family information, and life trajectory information; the first processing module is used to search for the work information, family information, and life in a preset national statistics database based on the personal information The first target data record matching the trajectory information; the first execution module is used to reset the life trajectory information based on the first target data record to generate predicted event information and push it to the user.

In some embodiments, the event prediction device based on big data further includes: a second acquisition module and a second execution module, wherein the second acquisition module is used to acquire historical browsing information of the user within a first preset time period; The second execution module is used to search for a second target data record corresponding to the historical browsing information in a preset browsing statistics database and write it into the first target data record.

In some embodiments, the event prediction device based on big data further includes: a third acquisition module and a third execution module, wherein the third acquisition module is used to acquire insurance claims associated with the user within a second preset time period Information; the third execution module is used to add the insurance compensation information to the user's personal information.

In some embodiments, the event prediction device based on big data further includes: a first acquisition submodule and a first execution submodule, wherein the first acquisition submodule is used to acquire preset interface information of the insurance application; the first The execution sub-module is used to obtain the insurance history record associated with the user in the insurance application according to the interface information, wherein the insurance history record includes the insurance compensation information.

In some embodiments, the event prediction device based on big data further includes: a fourth acquisition module and a storage module, wherein the fourth acquisition module is used to acquire the personal identity information of the user; the storage module is used to associate the personal identity The information and the predicted event information are saved in a preset user account database.

In some embodiments, the event prediction apparatus based on big data further includes: a second acquisition submodule, a second execution submodule, and a third acquisition submodule, wherein the second acquisition submodule is used to acquire the user's face Image; the second execution submodule is used to input the face image into a preset face recognition model, wherein the face recognition model is a convolutional neural network model trained to convergence; a third acquisition submodule It is used to obtain the personal identity information of the user output by the face recognition model.

In some embodiments, the event prediction device based on big data further includes: a thread creation sub-module, a detection sub-module, and a third execution sub-module, wherein the thread creation sub-module is used to pass the personal identity information and The predicted event information is saved in a preset task account database to be executed; the detection sub-module is used to detect whether there is an operation task with a priority higher than the task to be executed in the task queue after the task to be executed; The third execution sub-module is used to execute the operation task with priority when the operation task has a higher priority than the task to be executed until the execution of the operation task is completed.

Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

To solve the above technical problems, embodiments of the present application also provide computer equipment. For details, please refer to FIG. 9, which is a block diagram of the basic structure of the computer device of this embodiment.

As shown in FIG. 9, a schematic diagram of the internal structure of the computer device. As shown in FIG. 9, the computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected through a system bus. The non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a sequence of control information. When the computer-readable instructions are executed by the processor, the processor may implement a An event prediction method based on big data. The processor of the computer device is used to provide computing and control capabilities, and support the operation of the entire computer device. The memory of the computer device may store computer readable instructions. When the computer readable instructions are executed by the processor, the processor may cause the processor to execute an event prediction method based on big data. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art can understand that the structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. There are more or fewer components than shown in the figure, or some components are combined, or have different component arrangements.

In this embodiment, the processor is used to perform specific functions of the first acquisition module 2100, the first processing module 2200, and the first execution module 2300 in FIG. 8. The memory stores program codes and various types of data required to execute the above modules. The network interface is used for data transmission to user terminals or servers. The memory in this embodiment stores the program code and data required to execute all submodules in the event prediction device based on big data, and the server can call the program code and data of the server to execute the functions of all submodules.

The computer obtains the user's personal information, including the user's work information, family information and life trajectory information, where the life trajectory information is the information of the user's events in daily life, and then looks up the user's personal information in the national statistics database. The matching first target data record, because the first target data record matches the user's work information, family information and life track information, so that the occurrence of the first target data record is likely to happen to the user , So the user ’s life trajectory information can be reset based on the first target data record, thereby generating predicted event information of events that will occur with high probability in the user ’s future and pushing them to the user, and predicting the user ’s future through big data statistics Events occur with a high probability, improving the accuracy and scientificity of predicting events.

The present application also provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform any of the foregoing embodiments based on big data The steps of the event prediction method.

A person of ordinary skill in the art may understand that all or part of the processes in the methods of the above embodiments may be completed by instructing relevant hardware through a computer program. The computer program may be stored in a computer-readable storage medium, and the program is being executed At this time, the process of the embodiments of the above methods may be included. The aforementioned storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

It should be understood that although the steps in the flowchart of the drawings are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order limitation for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the order of execution is also It is not necessarily carried out sequentially, but may be executed in turn or alternately with at least a part of other steps or sub-steps or stages of other steps.

The above is only part of the implementation of this application. It should be pointed out that for those of ordinary skill in the art, without departing from the principles of this application, a number of improvements and retouches can also be made. These improvements and retouches also It should be regarded as the scope of protection of this application.

Claims

An event prediction method based on big data includes the following steps:

Obtain the user's personal information, where the personal information includes the user's work information, family information and life track information;

Searching for a first target data record matching the work information, family information and life track information in a preset national statistics database according to the personal information;

Reset the life trajectory information based on the first target data record to generate predicted event information and push it to the user.
The event prediction method based on big data according to claim 1, before the step of resetting the life trajectory information based on the target data record to generate predicted event information and push it to the user, further includes the following step:

Acquiring historical browsing information of the user within the first preset time period;

Find a second target data record corresponding to the historical browsing information in a preset browsing statistics database and write it into the first target data record.
The event prediction method based on big data according to claim 1, wherein the step of acquiring the user's personal information, wherein the personal information includes the user's work information, family information and life trajectory information, including the following steps:

Acquiring insurance compensation information associated with the user within a second preset time period;

Add the insurance compensation information to the user's personal information.
According to the big data-based event prediction method of claim 3, the step of acquiring insurance compensation information associated with the user within a second preset time period includes the following steps:

Obtain the interface information of the preset insurance application;

Acquiring an insurance history record associated with the user in the insurance application according to the interface information, wherein the insurance history record includes the insurance compensation information.
The event prediction method based on big data according to claim 1, after the step of resetting the life track information based on the first target data record to generate predicted event information and pushing it to the user, further comprising The following steps:

Obtain the personal identity information of the user;

Save the personal identity information and the predicted event information to a preset user account database.
According to the event prediction method based on big data of claim 5, the step of acquiring the personal identity information of the user includes the following steps:

Acquiring the face image of the user;

Input the face image into a preset face recognition model, wherein the face recognition model is a convolutional neural network model trained to convergence;

Obtain the personal identity information of the user output by the face recognition model.
According to the big data-based event prediction method of claim 5, the step of saving the personal identity information and the predicted event information in a preset user account database includes the following steps:

Establishing and executing the task to be executed by saving the personal identity information and the predicted event information in a preset user account database through a thread;

Detecting whether there is an operation task with a higher priority than the task to be executed in the task queue after the task to be executed;

When there is an operation task with a higher priority than the task to be executed in the task queue, the operation task is preferentially executed until the execution of the operation task is completed, and the task to be executed is called back to be executed.
An event prediction device based on big data, including:

The first obtaining module is used to obtain the user's personal information, wherein the personal information includes the user's work information, family information and life track information;

A first processing module, configured to search for a first target data record matching the work information, family information, and life track information in a preset national statistics database according to the personal information;

The first execution module is configured to reset the life track information based on the first target data record to generate predicted event information and push it to the user.
A computer device includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor causes the processor to perform an event prediction based on big data. The following steps of the method:

Obtain the user's personal information, where the personal information includes the user's work information, family information and life track information;

Searching for a first target data record matching the work information, family information and life track information in a preset national statistics database according to the personal information;

Reset the life trajectory information based on the first target data record to generate predicted event information and push it to the user.
The computer device according to claim 9, before the step of resetting the life trajectory information based on the target data record to generate predicted event information and push it to the user, further comprising the following steps:

Acquiring historical browsing information of the user within the first preset time period;

Find a second target data record corresponding to the historical browsing information in a preset browsing statistics database and write it into the first target data record.
The computer device according to claim 9, wherein the step of acquiring the user's personal information, wherein the personal information includes the user's work information, family information, and life path information, including the following steps:

Acquiring insurance compensation information associated with the user within a second preset time period;

Add the insurance compensation information to the user's personal information.
The computer device according to claim 11, the step of acquiring insurance compensation information associated with the user within a second preset time period includes the following steps:

Obtain the interface information of the preset insurance application;

Acquiring an insurance history record associated with the user in the insurance application according to the interface information, wherein the insurance history record includes the insurance compensation information.
The computer device according to claim 9, after the step of resetting the life trajectory information based on the first target data record to generate predicted event information and pushing it to the user, further comprising the following steps:

Obtain the personal identity information of the user;

Save the personal identity information and the predicted event information to a preset user account database.
According to the computer device of claim 13, the step of acquiring the personal identity information of the user includes the following steps:

Acquiring the face image of the user;

Input the face image into a preset face recognition model, wherein the face recognition model is a convolutional neural network model trained to convergence;

Obtain the personal identity information of the user output by the face recognition model.
The computer device according to claim 13, the step of saving the personal identification information and the predicted event information in a preset user account database includes the following steps:

Establishing and executing the task to be executed by saving the personal identity information and the predicted event information in a preset user account database through a thread;

Detecting whether there is an operation task with a higher priority than the task to be executed in the task queue after the task to be executed;

When there is an operation task with a higher priority than the task to be executed in the task queue, the operation task is preferentially executed until the execution of the operation task is completed, and the task to be executed is called back to be executed.
A non-volatile storage medium storing computer-readable instructions, which when executed by one or more processors, causes the one or more processors to perform an event prediction method based on big data The following steps:

Obtain the user's personal information, where the personal information includes the user's work information, family information and life track information;

Searching for a first target data record matching the work information, family information and life track information in a preset national statistics database according to the personal information;

Reset the life trajectory information based on the first target data record to generate predicted event information and push it to the user.
The non-volatile storage medium according to claim 16, before the step of resetting the life trajectory information based on the target data record to generate predicted event information and push it to the user, further comprising the following steps :

Acquiring historical browsing information of the user within the first preset time period;

Find a second target data record corresponding to the historical browsing information in a preset browsing statistics database and write it into the first target data record.
The non-volatile storage medium according to claim 16, wherein the step of acquiring the user's personal information, wherein the personal information includes the user's work information, family information, and life path information, including the following steps:

Acquiring insurance compensation information associated with the user within a second preset time period;

Add the insurance compensation information to the user's personal information.
The non-volatile storage medium according to claim 18, the step of acquiring insurance compensation information associated with the user within a second preset time period includes the following steps:

Obtain the interface information of the preset insurance application;

Acquiring an insurance history record associated with the user in the insurance application according to the interface information, wherein the insurance history record includes the insurance compensation information.
The non-volatile storage medium according to claim 16, after the step of resetting the life trajectory information based on the first target data record to generate predicted event information and pushing it to the user, further comprising the following The steps described:

Obtain the personal identity information of the user;

Save the personal identity information and the predicted event information to a preset user account database.