Customer behavior fingerprint generation method based on a burying point technology

Abstract

The application discloses a customer behavior fingerprint generation method based on a burying point technology, and belongs to the technical field of computers.The method comprises the following steps: acquiring use behavior data of a customer when the customer uses a terminal device; collecting and statistically classifying an APP list of the terminal device used by the customer based on the burying point technology, so as to identify behavior preference data of the customer; acquiring operation flow data of the terminal device used by the customer; and generating a behavior fingerprint of the customer according to the use behavior data, the behavior preference data and the operation flow data of the terminal device used by the customer.The technical scheme of the application solves the problems that in the big data era, the identity information of a customer is easy to be used by others and stolen, the behavior data of the customer is easy to be imitated, and the accuracy, the completeness and the security are low.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method for generating customer behavior fingerprints based on embedding technology. Background Art

[0002] Currently, behavioral tracking is based on tracking behavior technology, which monitors, captures, processes, and sends data for specific user behaviors or events. This means capturing the data generated by events on the front end, reporting the data, understanding the customer's behavioral trajectory and operational data during product use, and improving the user experience. For example, the information entered by the customer in a text box, whether the information was entered or copied by the customer, the time the page was entered, the time spent in a certain scene, etc. Currently, most technologies use "full tracking" technology, which records all customer interactions in detail. The business and product then determine the data dimensions to be applied, eliminating the time consumed by version iterations caused by subsequent demand changes due to poor consideration in the early stages.

[0003] Currently, behavioral data from embedded data points is being maturely applied to enhance product experience and is also finding innovative applications in risk control. However, traditional risk control technology analyzes customer profiles based on business data, People's Bank of China credit data, and third-party data sources. In this era of big data, customer identity information is easily misused and stolen, and customer behavior data is easily imitated. This data alone is less accurate and complete, and therefore less secure. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method for generating customer behavior fingerprints based on point-of-sale technology, aiming to solve the problem that in the big data era, customer identity information is easily misused and stolen, and customer behavior data is easily imitated, resulting in low accuracy and completeness and low security.

[0005] The basic solution provided by the present invention is:

[0006] The customer behavior fingerprint generation method based on tracking technology includes:

[0007] Obtaining usage behavior data of customers when using terminal devices;

[0008] Based on tracking technology, we collect the list of APPs used by customers on their terminal devices and classify and count them to identify their behavioral preference data;

[0009] Obtaining operational process data when customers use terminal devices;

[0010] The customer's behavioral fingerprint is generated based on the customer's usage behavior data, behavioral preference data and operation process data of the terminal device.

[0011] The principle of the basic scheme of the present invention is:

[0012] In this solution, a method for generating customer behavior fingerprints based on tracking technology is applied to risk control fields such as banking, insurance, and securities. Traditional risk control technology relies solely on business data, People's Bank of China credit data, and third-party data sources, resulting in inaccurate customer behavior profiles. To enrich the data dimensions of risk control and make customer profiles more accurate and complete, user behavior data can be collected and combined to construct a user behavior profile. For example, in this era of big data, customer identities are easily misused and stolen, but each customer has a distinct personality, making their behavior data difficult to mimic. Tracking technology can be used to collect customer tracking data, identify their behavior data and terminal device data, and generate a "behavioral fingerprint" for the customer, identifying differences in previous and subsequent behavior and their current needs. Specifically, the method for generating customer behavior fingerprints based on tracking technology includes the following steps: obtaining user behavior data when using a customer's terminal device; using tracking technology to collect and classify a list of apps used by the customer on the terminal device to identify the customer's behavioral preferences; and obtaining operational process data when the customer uses the terminal device. The method generates the customer's behavioral fingerprint based on the user behavior data, behavioral preferences, and operational process data used by the customer on the terminal device.

[0013] This solution solves the problem in the big data era where customer identity information is easily misused and stolen, and customer behavior data is easily imitated, resulting in low accuracy, completeness, and security. Based on the tracking technology, the customer's behavior portrait is enriched and refined, which facilitates the identification of violations, improves the accuracy and security of customer transactions, and thus enhances the customer's process experience in the product.

[0014] Furthermore, the step of generating the customer's behavioral fingerprint based on the customer's usage behavior data, behavior preference data, and operation process data of the terminal device includes:

[0015] When using a terminal device to operate, the customer's current usage data is obtained and compared with the customer's behavioral fingerprint to identify the difference between the customer's previous and subsequent usage data to determine whether the customer's behavior is abnormal.

[0016] In this solution, when a customer uses a terminal device to perform an operation, the customer's current usage data is obtained and compared with the corresponding generated behavioral fingerprint to compare the differences in the customer's usage data and usage behavior before and after. Based on the comparison results, it is determined whether the customer's behavior is abnormal, thereby improving the security and reliability of the customer's operation.

[0017] Furthermore, the customer's usage behavior data when using the terminal device includes: angular velocity sensor data of the terminal device, screen brightness data of the terminal device, battery temperature data of the terminal device, voice usage data of the terminal device, screen pressure usage data of the terminal device and the horizontal plane angle of the terminal device.

[0018] In this solution, by acquiring various usage behavior data of customers when using terminal devices, the generated customer behavior fingerprint is made more accurate and reliable, which facilitates multi-faceted analysis and judgment of customer behavior in operating terminal devices.

[0019] Furthermore, the step of collecting a list of APPs used by customers on their terminal devices based on tracking technology and performing classification statistics includes:

[0020] Collect the number of apps, app names, basic app information, and app permissions of the terminal devices used by customers, and conduct classified statistics;

[0021] Classify each APP in the APP list into financial APPs, small loan APPs, online loan APPs and illegal software APPs, and count the number of each type of APP.

[0022] In this solution, by collecting the basic information of each APP on the terminal device used by the customer and each APP, and classifying and counting each APP, we can determine the customer's behavioral preferences in using the terminal device, so that the system can perform data comparison every time the customer uses the terminal device.

[0023] Furthermore, after the step of collecting the list of APPs used by the customer on the terminal device based on the tracking technology and classifying and counting them, the following steps are included:

[0024] Based on the classified and statistically analyzed APP data, identify whether the customer is currently engaging in short selling, long selling, or high-risk behavior.

[0025] In this solution, by collecting the basic information of each APP on the terminal device used by the customer and completing the classification statistics of each APP, it is easier to identify the customer's current multiple behaviors and high-risk behaviors, thereby improving the reliability of transactions.

[0026] Furthermore, the step of obtaining the operation process data of the customer using the terminal device includes:

[0027] Obtain customer application and operation behavior data during the operation process;

[0028] Identify whether there are any abnormalities based on the customer's application and operation behavior data.

[0029] In this solution, by obtaining specific operation process data such as application behavior data and operation behavior data when customers use terminal devices, it is easier to judge abnormal situations when customers use terminal devices.

[0030] Furthermore, the customer behavior fingerprint generation method based on the tracking technology also includes:

[0031] Obtain business data, PBOC credit data and third-party data sources when customers use terminal devices.

[0032] Furthermore, the abnormal situations include the terminal editing program automatically filling in information in the terminal, the terminal device being replaced, and batch registration behavior.

[0033] In this solution, the customer is made aware of the relevant abnormal situations by explaining the existing abnormal situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the internal structure of a terminal device according to an embodiment of the present invention;

[0035] Figure 2 This is a flow chart of an embodiment of a method for generating customer behavior fingerprints based on burying point technology of the present invention. DETAILED DESCRIPTION

[0036] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0037] The following is further described in detail through specific implementation methods:

[0038] Reference numerals in the accompanying drawings of the specification include: processor 1001 , communication bus 1002 , user interface 1003 , network interface 1004 , and memory 1005 .

[0039] like Figure 1 As shown, it is a schematic diagram of the internal structure of the terminal device involved in the embodiment of the present invention.

[0040] It should be noted that Figure 1 That is, it is a schematic diagram of the structure of the hardware operating environment of the terminal device. The terminal device in the embodiment of the present invention can be a PC, a portable computer or other terminal device.

[0041] like Figure 1As shown, the terminal device can include a processor 1001, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection communication between the processor 1001, the user interface 1003, the network interface 1004, and the memory 1005. The user interface 1003 can include a display screen (Display), an input unit such as a keyboard (Keyboard), a handwriting board, a stylus, etc. The optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface (such as an RJ45 interface), a wireless interface (such as a WIFI interface). The memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory) such as a disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0042] Those skilled in the art can understand that Figure 1 The terminal device structure in the above description does not constitute a limitation on the terminal device, and can include more or fewer components than the illustration, or combine certain components, or different component arrangements.

[0043] As Figure 1 As shown, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a distributed task processing program. The operating system is a program that manages and controls the hardware and software resources of the sample terminal device, supports the running of the distributed task processing program and other software or programs.

[0044] In Figure 1 As shown in the terminal device, the user interface 1003 is mainly used for data communication with each terminal; the network interface 1004 is mainly used for connecting the background server and communicating data with the background server; and the processor 1001 can be used to call the customer behavior fingerprint generation program based on the embedding point technology in the memory 1005, and perform the following operations as shown in Figure 2

[0045] Step S10, obtaining the use behavior data of the customer using the terminal device;

[0046] Step S20, classifying and counting the APP list of the customer using the terminal device based on the embedding point technology to identify the behavior preference data of the customer;

[0047] Step S30, obtaining the operation flow data of the customer using the terminal device;

[0048] ​Step S40 , generating a behavioral fingerprint of the customer based on the customer's usage behavior data, behavior preference data, and operation process data of the terminal device.

[0049] In this embodiment, a method for generating customer behavior fingerprints based on tracking technology is applied to risk control fields such as banking, insurance, and securities. Traditional risk control technology relies solely on business data, People's Bank of China credit data, and third-party data sources, resulting in inaccurate customer behavior profiles. To enrich the data dimensions of risk control and make customer profiles more accurate and complete, user behavior data can be collected and combined to construct a user behavior profile. In this era of big data, customer identities are easily misused and stolen, but each customer has a distinct personality, making their behavior data difficult to mimic. Tracking technology can be used to collect customer tracking data, identify their behavior data and terminal device data, and generate a "behavioral fingerprint" for the customer, identifying differences in previous and subsequent behavior and their current needs. Specifically, the method for generating customer behavior fingerprints based on tracking technology in this solution includes the steps of: obtaining user behavior data when using a customer's terminal device; collecting a list of apps used by the customer on the terminal device using tracking technology and classifying and statistically analyzing them to identify the customer's behavioral preferences; and obtaining operational process data when the customer uses the terminal device. Thus, the customer's behavioral fingerprint is generated based on the user behavior data, behavioral preferences, and operational process data of the customer using the terminal device. That is, this solution applies the behavioral data collected by the tracking technology to the risk control field, making the customer portrait more accurate and complete. Through the accumulation of collected data, a behavioral fingerprint is constructed for each customer, the behavior is difficult to imitate, and the differences before and after the behavior are identified; it solves the problem that in the big data era, customer identity information is easily misused and stolen, and customer behavior data is easily imitated, resulting in low accuracy and completeness, and low security. Based on the tracking technology, the customer's behavioral portrait is enriched and refined, which facilitates the identification of violations, improves the accuracy and security of customer transactions, and thus improves the customer's process experience in the product.

[0050] It should be noted that the behavior preference data of the terminal device used in the above embodiments can be that there are many sensors on the terminal device, and each customer will generate sensor data when using it. Based on the sensor data, a sensor portrait can be constructed for the customer, such as a gravity sensor, which rotates left and right according to the direction of the screen; a light sensor, which senses the strength of light to change the size of the screen brightness; a temperature sensor, which detects the temperature of the mobile device battery, and if the temperature is abnormal, it will automatically shut down; a sound sensor, which calls a voice assistant, etc.; a pressure sensor, which senses the operating pressure of the mobile device screen, and accurately interacts with the user according to the size of the pressure; for example, each customer uses the mobile phone, the horizontal angle, the finger touch pressure, the altitude, etc. It is difficult for the owner to imitate the sensor data of the owner, so the difference between the before and after behaviors can be easily identified.

[0051] In an embodiment, the number of APPs, APP name, APP basic information, and APP permission of the terminal device used by the customer are collected and classified and counted; each APP in the APP list is classified as a financial APP, a small loan APP, a network lending APP, and a non-compliant software APP, and the number of each type of APP is counted; specifically, the credit preference and high-risk behavior of the customer are identified; for example, through the point embedding technology, the APP list on the current terminal device of the customer can be collected, and most commonly used APPs are classified, and then the customer's APP list can be classified and counted, such as the number of financial APPs, small loan APPs, network lending APPs, and non-compliant software APPs, which can identify the customer's current short selling behavior, multi-head behavior, and high-risk behavior of the device.

[0052] It can be understood that multi-head is one of the speculation methods in futures exchanges. Speculators estimate that securities, commodities, etc. have a rising trend, and buy in advance to try to sell after the price rises to obtain the difference in interest. This speculation method is based on buying in advance, and the speculator has a piece of securities or commodities in hand before selling, so it is called "multi-head".

[0053] In an embodiment, the application and operation behavior data of the customer in the operation flow are acquired, and whether there is an abnormal situation is identified according to the application and operation behavior data of the customer. Further, the step of identifying the abnormal behavior can be in the loan application link, the customer needs to click some buttons of the corresponding APP in the terminal device, fill in some basic information of himself, and a large amount of application and operation behavior data will be generated in the process of filling in the information. For example, it is found that the number of clicks of the customer is much smaller than the market data, which indicates that the customer is very familiar with the product; the stay time in the loan application scene, usually the customer needs to fill in some basic information in the loan application process, and the time consumed by most customers should be similar. If a customer fills in the information in milliseconds, which is much smaller than the average level, it is indicated that the information filling may be automatically filled in the terminal by the terminal editing program; in addition, many mobile phones or simulators initiate large-scale registration behavior, through one-key configuration, the angle sensor is 0, the mobile phone power is 100%, the pressure sensor is 0 and other abnormal data, and the abnormal behavior of batch registration or false equipment is identified.

[0054] The above is only an embodiment of the present application, and common knowledge such as specific structures and characteristics in the scheme is not described in detail here. The person skilled in the art knows all the common technical knowledge in the field of the present application before the filing date or the priority date, can know all the prior art in the field, and has the ability to apply conventional experimental means before the date. The person skilled in the art can improve and implement the present scheme under the guidance of the present application, and their own ability, and some typical known structures or known systems should not be an obstacle for the person skilled in the art to implement the present application. It should be pointed out that, for those skilled in the art, without departing from the structure of the present application, a number of modifications and improvements can be made, which should also be considered as the protection scope of the present application, and these will not affect the effect and practicality of the present application. The protection scope claimed in the present application should be subject to the content of its claims, and the specific implementation mode and the like in the specification can be used to explain the content of the claims.

Claims

1. The customer behavior fingerprint generation method based on the embedding technology is characterized by: include: Obtaining usage behavior data of customers when using terminal devices; Based on tracking technology, we collect the list of APPs used by customers on their terminal devices and classify and count them to identify their behavioral preference data; Obtaining operational process data when customers use terminal devices; Generate a behavioral fingerprint of the customer based on the customer's usage behavior data, behavior preference data, and operation process data of the terminal device; The user behavior data when using the terminal device includes: angular velocity sensor data of the terminal device, screen brightness data of the terminal device, battery temperature data of the terminal device, voice usage data of the terminal device, screen pressure usage data of the terminal device, and horizontal angle of the terminal device; The steps for collecting the list of apps used by customers on their terminal devices based on tracking technology and classifying and counting them to identify customer behavior preference data include: Collect the number of apps, app names, basic app information, and app permissions of the terminal devices used by customers, and conduct classified statistics; Categorize the apps in the app list into financial apps, small loan apps, online loan apps, and illegal software apps, and count the number of apps in each category; Based on the classified and statistically analyzed APP data, identify whether the customer currently has multiple or high-risk behaviors; The step of obtaining the operation process data of the client using the terminal device includes: Obtain customer application and operation behavior data during the operation process; Identify whether there are any abnormalities based on the customer's application and operation behavior data.

2. The method for generating customer behavior fingerprints based on embedding technology according to claim 1 is characterized in that: The step of generating the customer's behavior fingerprint based on the customer's usage behavior data, behavior preference data, and operation process data of the terminal device includes: When using a terminal device to operate, the customer's current usage data is obtained and compared with the customer's behavioral fingerprint to identify the difference between the customer's previous and subsequent usage data to determine whether the customer's behavior is abnormal.

3. The method for generating customer behavior fingerprints based on embedding technology according to claim 1 is characterized in that: Also includes: Obtain business data, PBOC credit data and third-party data sources when customers use terminal devices.

4. The method for generating customer behavior fingerprints based on embedding technology according to claim 1 is characterized in that: The abnormal situations include the terminal editing program automatically filling in information on the terminal, the terminal device being replaced and batch registration behavior.

Images