CN115292630A - Data processing method, device and computer readable storage medium - Google Patents
Data processing method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN115292630A CN115292630A CN202211224433.6A CN202211224433A CN115292630A CN 115292630 A CN115292630 A CN 115292630A CN 202211224433 A CN202211224433 A CN 202211224433A CN 115292630 A CN115292630 A CN 115292630A
- Authority
- CN
- China
- Prior art keywords
- target
- item
- record
- browsing
- intention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 34
- 230000006399 behavior Effects 0.000 claims description 145
- 230000006870 function Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 abstract description 13
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data processing method, data processing equipment and a computer readable storage medium, wherein the method comprises the following steps: determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record; and updating the target intention record in the user summary table according to the first intention level and the second intention level. According to the method and the system, the first intention level and the second intention level can be obtained according to the first behavior data obtained in real time, and the target intention record is updated in the user summary table according to the first intention level and the second intention level, so that the intention levels of the user to all items can be accurately obtained while the behavior data of the user is obtained in real time.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a data processing method, a device, and a computer-readable storage medium.
Background
When a user uses various real estate APP software or browses online behaviors of related webpages such as household appliances, whether the user intentionally accesses the online, and the user offline access intention can be analyzed by collecting data of the online behaviors of the user, such as browsing duration, browsing times and the like.
However, due to the large amount of behavior data of the user, the data processing performed after the behavior data is collected is often not accurate enough, so that the accuracy of evaluating the level of the access intention of the user is low.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a data processing method, data processing equipment and a computer readable storage medium, and aims to solve the technical problem that the accuracy of evaluating the access intention level of a user is low after analyzing and calculating user behavior data.
In order to achieve the above object, the present invention provides a data processing method, wherein the data processing method comprises the following steps:
acquiring first behavior data of a user in real time, and acquiring a user summary table and an identity corresponding to the user, wherein the first behavior data comprises behavior browsing duration, behavior browsing times and a first item field;
determining a target intention record in the user summary table according to the identity, determining a first target item record in the target intention record according to the target intention record and the first item field, and determining a second target item record according to the first target item record;
determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record;
and updating the target intention record in the user summary table according to the first intention level and the second intention level.
Further, the step of determining a target intention record in the user summary table according to the identity, determining a first target item record in the target intention record according to the target intention record and the first item field, and determining a second target item record according to the first target item record includes:
if target intention records corresponding to the identity marks exist in the intention records of the user summary table, determining each item record in the target intention records;
and if a target item field matched with the first item field exists in a second item field corresponding to the item record, acquiring a first target item record corresponding to the target item field, and determining each second target item record except the first target item record in the item record.
Further, the step of determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the behavior browsing duration, the behavior browsing frequency, the first target item record and the second target item record includes:
determining the number of the item records, the item browsing duration of the second target item record, the item browsing times of the second target item record, the first target browsing duration of the first target item record, the first target browsing times of the first target item record, and the behavior browsing duration and behavior browsing times of the first behavior data;
determining a mean value of the item browsing durations according to the number, the item browsing duration, the first target browsing duration and the behavior browsing duration, and determining a mean value of the item browsing durations according to the number, the item browsing times, the first target browsing times and the behavior browsing times;
and determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the item browsing duration average value and the item browsing times average value.
Further, the step of determining the mean value of the item browsing durations according to the number, the item browsing durations, the first target browsing durations and the behavior browsing durations, and determining the mean value of the item browsing durations according to the number, the item browsing times, the first target browsing times and the behavior browsing times includes:
adding the first target browsing duration and the behavior browsing duration to obtain a second target browsing duration, and adding the item browsing duration and the second target browsing duration to obtain a total browsing duration;
dividing the total browsing duration by the number to obtain an average value of the item browsing duration;
adding the first target browsing times and the behavior browsing times to obtain second target browsing times, and adding the item browsing times and the second target browsing times to obtain total browsing times;
and dividing the total browsing times and the number to obtain a mean value of the item browsing times.
Further, according to the item browsing time length average value and the item browsing frequency average value, a first intention level corresponding to a first target item record is determined, and a second intention level corresponding to a second target item record comprises the following steps:
determining a first difference value according to the project browsing duration and the mean value of the project browsing duration, and performing square operation on the first difference value to obtain a first operation result; determining a second difference value according to the second target browsing duration and the mean value of the project browsing durations, and performing square operation on the second difference value to obtain a second operation result; determining a time length variance according to each first operation result, each second operation result, the number and the item browsing time length mean value;
determining a third difference value according to the item browsing times and the item browsing time average value, and performing square operation on the third difference value to obtain a third operation result; determining a fourth difference value according to the second target browsing times and the item browsing time average value, and performing square operation on the fourth difference value to obtain a fourth operation result; determining a frequency variance according to each third operation result, the fourth operation result, the number and the item browsing frequency mean value;
determining a first size relation between the first operation result and the duration variance, determining a second size relation between the third operation result and the time variance, and obtaining a second intention level corresponding to each second target item record according to the first size relation, the second size relation and a third intention level in the second target item record;
determining a third size relation between the second operation result and the duration variance, determining a fourth size relation between the fourth operation result and the frequency variance, and obtaining a first intention grade corresponding to the first target item record according to the third size relation, the fourth size relation and a fourth intention grade in the first target item record.
Further, the step of updating the target intent record in the user summary according to the first intent level and the second intent level includes:
and updating a third intention level corresponding to a second target item record into a second intention level, updating a fourth intention level corresponding to a first target item record into a first intention level, and storing the first behavior data into the first target item record so as to update the target intention record in the user summary table.
Further, the step of determining a target intention record in the user summary table according to the identity, and determining a first target item record in the target intention record according to the target intention record and the first item field includes:
if target behavior data matched with the first behavior data exists in the second behavior data, determining a first type of the target behavior data according to a preset classification table;
if the first type is one of preset first target bonus types, determining a second target bonus type matched with the first type in the first target bonus types;
determining a weight function corresponding to a second target bonus type, a first numerical value of the weight function and a parameter numerical value in the weight function according to a preset classification table;
adding a preset value to the parameter value to obtain a target parameter value, and updating the parameter value in the weight function to the target parameter value to obtain a second value;
and determining a second total value according to the second numerical value and the first numerical value, determining a target project grade according to the second total value, and updating the target intention record in the user summary table.
Further, the step of determining a second total value according to the second value and the first value, determining a target project level according to the second total value, and updating the first target project record in the user summary table includes:
carrying out subtraction operation on the second numerical value and the first numerical value to obtain a third numerical value, carrying out addition operation on the third numerical value and the first total numerical value to obtain a second total numerical value, and grading the second total numerical value according to a grading rule to obtain a target item grade;
and updating the first total numerical value of the first target item record into a second total numerical value and updating the item level of the first target item record into a target item level in the user summary table so as to update the target intention degree record.
Furthermore, to achieve the above object, the present invention also provides a data processing apparatus comprising: a memory, a processor and a data processing program stored on the memory and executable on the processor, the data processing program, when executed by the processor, implementing the steps of the data processing method as described above.
Further, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a data processing program which, when executed by a processor, implements the steps of the aforementioned data processing method.
According to the method, first behavior data of a user are obtained in real time, a user summary table and an identity corresponding to the user are obtained, the first behavior data comprise behavior browsing duration, behavior browsing times and a first item field, then a target intention record is determined in the user summary table according to the identity, a first target item record is determined in the target intention record according to the target intention record and the first item field, a second target item record is determined according to the first target item record, then the target intention record is updated in the user summary table according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record, a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record are determined, the first intention level and the second intention level corresponding to the first target item record are obtained according to the first behavior data, the first intention level and the second intention level corresponding to the first intention level are obtained, and the target intention record is updated according to the first intention level and the second intention level of the user summary table, and the user summary data are updated accurately according to the first intention level and the second intention level of the user summary record.
Drawings
Fig. 1 is a schematic structural diagram of a data processing apparatus in a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a data processing method according to a first embodiment of the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a data processing device in a hardware operating environment according to an embodiment of the present invention.
The data processing device in the embodiment of the present invention may be a PC, or may be a mobile terminal device having a display function, such as a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III, motion Picture Experts compression standard Audio Layer 3) player, an MP4 (Moving Picture Experts Group Audio Layer IV, motion Picture Experts compression standard Audio Layer 4) player, a portable computer, or the like.
As shown in fig. 1, the data processing apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory such as a disk memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the data processing device may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. Such as light sensors, motion sensors, and other sensors. In particular, the light sensor may include an ambient light sensor that adjusts the brightness of the display screen based on the ambient light level and a proximity sensor that turns off the display screen and/or backlight when the data processing device is moved to the ear. As one type of motion sensor, the gravitational acceleration sensor can detect the magnitude of acceleration in each direction (generally five axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of data processing equipment (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; of course, the data processing device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a data processing program.
In the terminal shown in fig. 1, the network interface 1004 is used for connecting with a background server and performing data communication with the background server; the user interface 1003 is used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be used to invoke a data processing program stored in the memory 1005.
In this embodiment, the data processing apparatus includes: the system comprises a memory 1005, a processor 1001 and a data processing program which is stored on the memory 1005 and can run on the processor 1001, wherein when the processor 1001 calls the data processing program stored in the memory 1005, the steps of the data processing method in each embodiment are executed.
The invention also provides a data processing method, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method of the invention.
In this embodiment, the data processing method includes the steps of:
step S101, acquiring first behavior data of a user in real time, and acquiring a user summary table and an identity corresponding to the user, wherein the first behavior data comprises behavior browsing duration, behavior browsing times and a first item field;
it should be noted that, the service side performs embedding through the front end of the applet, and reports the behavior of the user embedding to the message middleware rocktmq.
In this embodiment, first behavior data of a user is obtained in real time, and a user summary table and an identity corresponding to the user are obtained, where the first behavior data includes behavior browsing duration, behavior browsing times, and a first item field, where the first item field is manually preset, each first behavior data has a corresponding first item field, and behavior data with the same item field represents belonging to the same item, for example, the item fields may be set to numbers 1, 2, 3, 4, 5, and the like, and certainly, the item fields may also be set to english letters, such as a, b, c, d, e, and the like.
Specifically, the user summary table is obtained by processing behavior data of a user pulled from a message middleware rocktmq, the user summary table creates an intention record corresponding to each user in the user summary table according to behavior data corresponding to a user ID by collecting behavior data of a large number of sample users in advance, the behavior data can pull history data from the message middleware rocktmq, or can use collected sample data as behavior data, and according to an item field of the behavior data, the item field is artificially preset, each behavior data has a corresponding item field, then the behavior data with the same item field is classified into the same item record, and the behavior data including the type of the behavior data, browsing duration and browsing frequency are stored in the intention record, according to the type of each behavior data in each item record and a preset classification table, a total number value of each item record is determined, and the total number value is divided according to a preset division rule to obtain an item level, and finally a preset level is recorded for each item, an initial level of each item record is the same, a specific level of the user summary table includes a total number of the intention records, and the intention records include the total number of the intention records, and the item records include item level.
It should be noted that the classification table may classify the behavior data into three categories, each first bonus type, each second bonus type, and each bonus type. For example, the first bonus type simulates house purchasing, concerned items, browsing item information, scanning behaviors, consultation correlation, browsing item related information, sharing behaviors, browsing item related information, activity correlation and consultation correlation, the second bonus type is other behaviors, the bonus type is suspected to be the same line and suspected to be assisted, and each type can be matched with a weight function. The classification table and the weight function can be obtained by obtaining a first number of visitors and a first total number of visitors of sample data, then dividing the first number of visitors and the first total number of visitors to obtain a first ratio, then obtaining each behavior data in the sample data, dividing the behavior data into types according to a second number of visitors and a second total number of visitors corresponding to each behavior data to obtain a classification table, then dividing the second number of visitors and the second total number of visitors to obtain a second ratio, then dividing the second ratio and the first ratio to obtain a third value, and finally configuring the weight function corresponding to each type according to the size of the third value and the classification table. For example, if the first number of visiting persons and the first total number of persons are 30 persons and 100 persons, respectively, the first ratio is 0.3, the behavior data is classified to obtain a classification table, if the second number of visiting persons and the second total number of persons of the behavior data are 3 persons and 30 persons, respectively, the second ratio is 0.1, the third ratio is one third, and the type of the behavior data is determined according to the classification table. And finally, determining a weight function corresponding to each type in the classification table according to the size of the third numerical value.
Step S102, according to the identity, determining a target intention record in the user summary table, according to the target intention record and the first item field, determining a first target item record in the target intention record, and according to the first target item record, determining a second target item record;
in this embodiment, according to the comparison of the identifiers, whether a target intention record exists in the user summary table may be determined, if the target intention record does not exist, a target intention record corresponding to the user may be directly created in the user summary table, if the target intention record exists, a first target item record may be determined in the target intention record according to the comparison of the first item field, for example, if the identifier is 12, it is queried in the user summary table through the number 12 whether the intention record with the identifier 12 exists, and if the intention record with the identifier 12 exists, the intention record with the identifier 12 is used as the target intention record.
Step S103, determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record;
in this embodiment, a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record may be determined according to the behavior browsing duration, the behavior browsing frequency, the first target item record and the second target item record, where the intention level in the first target item record in the user summary table is the fourth intention level and the intention level in the second target item record is the third intention level.
Step S104, updating the target intention record in the user summary table according to the first intention level and the second intention level.
In this embodiment, the target intention record is updated in the user summary table according to the first intention level and the second intention level, it should be noted that the target intention record includes each item record, and each item record has a corresponding intention level.
Further, in an embodiment, the step S104 includes:
step a, in the user summary table, updating a third intention level corresponding to a second target item record to a second intention level, updating a fourth intention level corresponding to a first target item record to a first intention level, and storing the first behavior data into the first target item record to update the target intention record.
In this embodiment, in the user summary table, first, the intention level of the second target item record is the third intention level, the third intention level is replaced with the second intention level, the intention level of the first target item record is the fourth intention level, the fourth intention level is replaced with the first intention level, and the first behavior data is stored in the first target item record, that is, the update of the target intention record is completed.
According to the data processing method provided by the embodiment, first behavior data of a user are obtained in real time, a user summary table and an identity corresponding to the user are obtained, wherein the first behavior data comprise behavior browsing duration, behavior browsing times and a first item field, then a target intention record is determined in the user summary table according to the identity, a first target item record is determined in the target intention record according to the target intention record and the first item field, a second target item record is determined according to the first target item record, then the target intention record is updated in the user summary table according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record, a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record are determined, and a first intention level and a second intention level corresponding to the first intention level and the second intention level are obtained according to the first behavior browsing duration, the first intention level and the second intention level corresponding to the first target item record, and the user summary table is updated accurately according to the first intention level and the second intention level corresponding to the user summary record.
Based on the first embodiment, a second embodiment of the data processing method of the present invention is proposed, in which step S102 includes:
step S201, if a target intention record corresponding to the identity exists in each intention record of the user summary table, determining each item record in the target intention record;
step S202, if a target item field matched with the first item field exists in a second item field corresponding to the item record, acquiring a first target item record corresponding to the target item field, and determining each second target item record except the first target item record in the item records.
In this embodiment, it is determined whether a target intention record corresponding to the identity exists in each intention record stored in the user summary table, and if the target intention record corresponding to the identity exists, each item record in the target intention record is determined.
Then, whether a target item field matched with the first item field exists in a second item field corresponding to the item record is judged, if so, a first target item record corresponding to the target item field is obtained, wherein the second item field is preset, each item record has a corresponding second item field, and the first item field and the second item field in the first behavior data are the same, i.e., represent the same item, for example, the second item field may be set to a number of 1, 2, 3, 4, 5, etc., and certainly, the item field may also be set to an english letter, such as a, b, c, d, e, etc. Different target item fields correspond to different target item records, which fields may be stored in the behavior data, and finally, respective second target item records other than the first target item record are determined in the item records.
If there is no intention record of the target, a new intention record is created as the intention record of the target, and a corresponding item record is created according to the item field corresponding to the first action data.
In the data processing method provided in this embodiment, if a target intention record corresponding to the identity exists in each intention record of the user summary table, each item record in the target intention record is determined, then, if a target item field matching the first item field exists in a second item field corresponding to the item record, a first target item record corresponding to the target item field is obtained, and each second target item record except the first target item record is determined in the item record, the first target item record can be determined according to the identity and the first item field, and then, the second target intention level is determined more accurately according to the target intention level.
A third embodiment of the data processing method of the present invention is proposed based on the second embodiment, and in this embodiment, step S103 includes:
step 301, determining the number of the item records, the item browsing duration of the second target item record, the item browsing times of the second target item record, the first target browsing duration of the first target item record, the first target browsing times of the first target item record, and the behavior browsing duration and behavior browsing times of the first behavior data;
step 302, determining a mean value of the item browsing durations according to the number, the item browsing durations, the first target browsing duration and the behavior browsing duration, and determining a mean value of the item browsing durations according to the number, the item browsing times, the first target browsing times and the behavior browsing times;
step 303, determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the item browsing duration average and the item browsing frequency average.
In this embodiment, each second target item record except the first target item record is determined in the item record, the number of the item records and the item browsing duration of the second target item record are determined, wherein the item browsing duration is the sum of the browsing durations of each behavior data in the second target item record and the item browsing times of the second target item record, the item browsing times is the sum of the browsing times of each behavior data in the second target item record, the first target browsing duration of the first target item record and the first target browsing times of the first target item record, wherein the first target browsing duration is the sum of the browsing durations of each behavior data in the first target item record, and the first target browsing times is the sum of the browsing times of each behavior data in the first target item record, and the behavior browsing duration and the browsing times of the first behavior data are determined.
And then, determining a mean value of the item browsing duration according to the number, the item browsing duration, the first target browsing duration and the behavior browsing duration, and determining a mean value of the item browsing times according to the number, the item browsing times, the first target browsing times and the behavior browsing times, so that a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record are determined according to the mean value of the item browsing duration and the mean value of the item browsing times.
Further, in an embodiment, step 302 further includes:
step 3021, adding the first target browsing duration and the behavior browsing duration to obtain a second target browsing duration, and adding the item browsing duration and the second target browsing duration to obtain a total browsing duration;
step 3022, dividing the total browsing duration by the number to obtain an average value of the item browsing durations;
step 3023, adding the first target browsing times and the behavior browsing times to obtain second target browsing times, and adding the item browsing times and the second target browsing times to obtain total browsing times;
and step 3024, dividing the total browsing times by the number to obtain an average value of the item browsing times.
In this embodiment, the first target browsing duration and the behavior browsing duration are added to obtain a second target browsing duration, and the item browsing duration and the second target browsing duration are added to obtain a total browsing duration, for example, the first target browsing duration is 10 minutes, the behavior browsing duration is 2 minutes, the second target browsing duration is 12 minutes, the item browsing duration is 360 minutes, the total browsing duration is 372 minutes, and the total browsing duration and the number are divided to obtain an item browsing duration average value, for example, the number is 3, and the item browsing duration average value is 124 minutes.
Finally, the first target browsing frequency and the behavior browsing frequency are added to obtain a second target browsing frequency, the item browsing frequency and the second target browsing frequency are added to obtain a total browsing frequency, then the total browsing frequency and the number are divided to obtain an item browsing frequency mean value, for example, the first target browsing frequency is 10 times, the behavior browsing frequency is 1 time, the second target browsing frequency is 12 times, the item browsing frequency is 360 times, the total browsing frequency is 372 times, then the total browsing frequency and the number are divided to obtain an item browsing frequency mean value, for example, the number is 3, and the item browsing duration mean value is 124 times.
Further, in an embodiment, step 303 further includes:
step 3031, determining a first difference value according to the project browsing time length and the mean value of the project browsing time length, and performing square operation on the first difference value to obtain a first operation result; determining a second difference value according to the second target browsing duration and the mean value of the project browsing durations, and performing square operation on the second difference value to obtain a second operation result; determining a time length variance according to each first operation result, each second operation result, the number and the item browsing time length mean value;
step 3032, determining a third difference value according to the item browsing times and the item browsing time average value, and performing square operation on the third difference value to obtain a third operation result; determining a fourth difference value according to the second target browsing times and the item browsing time average value, and performing square operation on the fourth difference value to obtain a fourth operation result; determining a frequency variance according to each third operation result, the fourth operation result, the number and the item browsing frequency mean value;
step 3033, determining a first magnitude relation between the first operation result and the time variance, determining a second magnitude relation between the third operation result and the time variance, and obtaining a second intention grade corresponding to each second target item record according to the first magnitude relation, the second magnitude relation and a third intention grade in the second target item record;
step 3034, determining a third size relationship between the second operation result and the duration variance, determining a fourth size relationship between the fourth operation result and the time variance, and obtaining a first intention grade corresponding to the first target item record according to the third size relationship, the fourth size relationship and the fourth intention grade in the first target item record.
In this embodiment, the average value of the item browsing duration subtracted from the item browsing duration is subtracted to determine a first difference, the first difference is squared to obtain a first operation result, for example, the average values of the item browsing duration and the item browsing duration are 13 and 11.5, respectively, the first difference is 1.5, the square of the first difference is 2.25, so as to obtain the first operation result, the average value of the item browsing duration subtracted from the second target browsing duration is subtracted to determine a second difference, and the second difference is squared to obtain the second operation result. And finally, substituting each first operation result, each second operation result, the number of the first operation results, and the mean value of the item browsing times into a conventional variance formula to determine the time length variance.
And then subtracting the mean value of the item browsing times from the second target browsing times to determine a fourth difference value, performing square operation on the fourth difference value to obtain a fourth operation result, and determining a time variance according to each third operation result, the fourth operation result, the number and the mean value of the item browsing times.
And determining a first magnitude relation between the first operation result and the duration variance, wherein if the first operation result is 10 and the duration variance is 20, the first magnitude relation is that the first operation result is smaller than the duration variance. A second magnitude relationship between the third operation result and the degree variance is determined, for example, if the third operation result is 20 and the degree variance is 5, the second magnitude relationship is that the third operation result is greater than the degree variance.
Changing a third intention level in the second target item record according to the first magnitude relation and the second magnitude relation to obtain a second intention level, for example, if the first magnitude relation is that the first operation result is greater than the duration variance, and the second magnitude relation is that the third operation result is greater than the frequency variance, the third intention level in the second target item record is raised to obtain the second intention level.
Determining a third size relation between the second operation result and the time variance, determining a fourth size relation between the fourth operation result and the time variance, and changing a fourth intention level in the first target item record according to the third size relation and the fourth size relation to obtain a first intention level, for example, if the third size relation is that the first operation result is greater than the time variance, and if the fourth size relation is that the third operation result is less than the time variance, reducing the third target intention level to obtain the first target intention level.
According to the data processing method provided by the embodiment, the number of the item records, the item browsing duration recorded by the second target item, the item browsing frequency recorded by the second target item, the first target browsing duration recorded by the first target item, the first target browsing frequency recorded by the first target item, and the behavior browsing duration and the behavior browsing frequency of the first behavior data are determined, then, according to the number, the item browsing duration, the first target browsing duration, and the behavior browsing duration, a mean value of the item browsing duration is determined, according to the number, the item browsing frequency, and the first target browsing frequency, a mean value of the item browsing frequency is determined, then, according to the mean value of the item browsing duration and the mean value of the item browsing frequency, a second target intention level is determined, and according to the number of the item records, the item browsing duration recorded by the second target item, the first target browsing duration recorded by the first target item, the first target browsing frequency recorded by the first target item, and the behavior browsing frequency of the first behavior data, a high or low level of each item of a user can be obtained.
A fourth embodiment of the data processing method of the present invention is proposed based on the first embodiment, and in this embodiment, step S102 is followed by:
step 401, if there is target behavior data matched with the first behavior data in the second behavior data, determining a first type of the target behavior data according to a preset classification table;
step 402, if the first type is one of preset first target bonus types, determining a second target bonus type matched with the first type in the first target bonus types;
step 403, determining a weight function corresponding to a second target scoring type, a first value of the weight function, and a parameter value in the weight function according to a preset classification table;
step 404, adding a preset value to the parameter value to obtain a target parameter value, and updating the parameter value in the weight function to the target parameter value to obtain a second value;
step 404, determining a target total value according to the second numerical value and the first numerical value, determining a target project level according to the target total value, and updating the target intention record in the user summary table.
It should be noted that the first target item record includes the respective second behavior data and the first total value.
In this embodiment, first, if there is target behavior data matching the first behavior data in the second behavior data, a first type of the target behavior data is determined according to a preset classification table, where the classification table divides each behavior data of the user into each first bonus type, each second bonus type, and each bonus type.
It should be noted that the bonus type includes a first bonus type and a second bonus type, and the first target bonus type is the second bonus type.
If the first type is one of the preset first bonus types or the first type is one of the preset bonus types, the first target item record is not changed, that is, the number of the first bonus types or the number of the bonus types in the first target item record is not increased, the first target item record is not changed.
If the first type is one of preset first target bonus types, determining a second target bonus type matched with the first type according to the bonus type, specifically, calculating the times of behavior data generation instead of the number of types. For example, if one of the second bonus types is browsing house-buying related legal and legal laws, and the first type is also browsing house-buying related legal and legal laws, the first type is taken as the second target bonus type.
According to the classification table, a weight function corresponding to the second target bonus type can be determined, and a first numerical value corresponding to the weight function is obtained, wherein the first numerical value is a result obtained by the weight function.
And finally, determining a second total value according to the second value and the first value, determining a target item grade according to the second total value, and updating a target intention record in a user summary table.
Further, in an embodiment, step 403 includes:
step 4031, subtract the second numerical value from the first numerical value to obtain a third numerical value, add the third numerical value to the first total numerical value to obtain a second total numerical value, and grade the second total numerical value according to a grading rule to obtain a target item grade;
step 4032, in the user summary table, the first total numerical value of the first target item record is updated to the second total numerical value, and the item level of the first target item record is updated to the target item level, so as to update the target intention record.
In this embodiment, first, the second value and the first value are subtracted to obtain a third value, where the preset value is usually set to 1, and the second value and the first value are subtracted to obtain the third value, for example, the weight function is 40+10 (X-1), X is a parameter value, if X is 20, if the preset value is 1, the target parameter value is 21, and the first value is 230. The parameter value in the weighting function is updated to the target parameter value to obtain a second value, and the second value is subtracted from the first value to obtain a third value, e.g., 40+10 (X-1), where the target parameter value is 21, the second value is 240, and the third value is 240 minus 230 to 10.
Then, the third value and the first total value are added to obtain a second total value, and the second total value is graded according to a grading rule to obtain a target item grade, wherein the first user intention record includes the first total value, and the third value and the first total value are added to obtain the second total value, for example, the first total value is 300, the third value is 10, the second total value is 310, the preset grading rule is manually set, 200 to 300 can be set as a grade B, and 300 to 400 can be set as a grade a, that is, the target item grade is a grade a.
In the data processing method provided in this embodiment, if there is target behavior data matching the first behavior data in the second behavior data, a first type of the target behavior data is determined according to a preset classification table, then, if the first type is one of preset first target bonus types, a second target bonus type matching the first type is determined in the first target bonus type, then, according to the preset classification table, a weight function corresponding to the second target bonus type, a first value of the weight function, and a parameter value in the weight function are determined, then, the parameter value is added to the preset value to obtain a target parameter value, and a parameter value in the weight function is updated to a target parameter value to obtain a second value, and finally, according to the second value and the first value, a second total value is determined, and, according to the second total value, a target item level is determined, and the target collection record is updated in the user collection record table, and the first row is determined as a target behavior data type, so that the target item level is updated to be a target item level.
In addition, an embodiment of the present invention further provides a data processing apparatus, where the data processing apparatus includes: a memory, a processor and a data processing program stored on the memory and executable on the processor, the data processing program, when executed by the processor, implementing the steps of the data processing method as described above.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where a data processing program is stored, and when the data processing program is executed by a processor, the data processing method implements the steps of the data processing method described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A data processing method, characterized in that the data processing method comprises the steps of:
acquiring first behavior data of a user in real time, and acquiring a user summary table and an identity corresponding to the user, wherein the first behavior data comprises behavior browsing duration, behavior browsing times and a first item field;
determining a target intention record in the user summary table according to the identity, determining a first target item record in the target intention record according to the target intention record and the first item field, and determining a second target item record according to the first target item record;
determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record;
and updating the target intention record in the user summary table according to the first intention level and the second intention level.
2. The data processing method of claim 1, wherein the determining a target intent record in the user summary based on the identity, and determining a first target item record in the target intent record based on the target intent record and the first item field, and determining a second target item record based on the first target item record, comprises:
if the target intention record corresponding to the identity exists in each intention record of the user summary table, determining each item record in the target intention record;
and if a target item field matched with the first item field exists in a second item field corresponding to the item record, acquiring a first target item record corresponding to the target item field, and determining each second target item record except the first target item record in the item record.
3. The data processing method according to claim 2, wherein the step of determining a first level of intention corresponding to the first target item record and a second level of intention corresponding to the second target item record according to the behavior browsing duration, the behavior browsing times, the first target item record and the second target item record comprises:
determining the number of the item records, the item browsing duration of the second target item record, the item browsing times of the second target item record, the first target browsing duration of the first target item record, the first target browsing times of the first target item record, and the behavior browsing duration and behavior browsing times of the first behavior data;
determining a mean value of the project browsing durations according to the number, the project browsing durations, the first target browsing durations and the behavior browsing durations, and determining a mean value of the project browsing durations according to the number, the project browsing times, the first target browsing times and the behavior browsing times;
and determining a first intention level corresponding to the first target item record and a second intention level corresponding to the second target item record according to the item browsing duration average value and the item browsing times average value.
4. The data processing method of claim 3, wherein the step of determining the mean value of the item browsing durations according to the number, the item browsing duration, the first target browsing duration and the behavior browsing duration, and determining the mean value of the item browsing durations according to the number, the item browsing times, the first target browsing times and the behavior browsing times comprises:
adding the first target browsing duration and the behavior browsing duration to obtain a second target browsing duration, and adding the item browsing duration and the second target browsing duration to obtain a total browsing duration;
dividing the total browsing duration by the number to obtain a mean value of the item browsing durations;
adding the first target browsing times and the behavior browsing times to obtain second target browsing times, and adding the item browsing times and the second target browsing times to obtain total browsing times;
and dividing the total browsing times by the number to obtain a mean value of the browsing times of the project.
5. The data processing method according to claim 4, wherein the step of determining a first intention level corresponding to a first target item record according to the item browsing duration average and the item browsing times average, and a second intention level corresponding to a second target item record comprises:
determining a first difference value according to the item browsing duration and the item browsing duration mean value, and performing square operation on the first difference value to obtain a first operation result; determining a second difference value according to the second target browsing duration and the mean value of the item browsing durations, and performing square operation on the second difference value to obtain a second operation result; determining a time length variance according to each first operation result, each second operation result, the number and the item browsing time length mean value;
determining a third difference value according to the item browsing times and the item browsing time average value, and performing square operation on the third difference value to obtain a third operation result; determining a fourth difference value according to the second target browsing times and the item browsing time average value, and performing square operation on the fourth difference value to obtain a fourth operation result; determining a frequency variance according to each third operation result, the fourth operation result, the number and the item browsing frequency mean value;
determining a first magnitude relation between the first operation result and the duration variance, determining a second magnitude relation between the third operation result and the frequency variance, and obtaining a second intention grade corresponding to each second target item record according to the first magnitude relation, the second magnitude relation and a third intention grade in the second target item record;
determining a third size relation between the second operation result and the duration variance, determining a fourth size relation between the fourth operation result and the frequency variance, and obtaining a first intention grade corresponding to the first target item record according to the third size relation, the fourth size relation and a fourth intention grade in the first target item record.
6. The data processing method of claim 1, wherein the step of updating the target intent record in the user summary table according to the first intent level and the second intent level comprises:
and updating a third intention level corresponding to a second target item record into a second intention level, updating a fourth intention level corresponding to a first target item record into a first intention level, and storing the first behavior data into the first target item record so as to update the target intention record in the user summary table.
7. The data processing method according to claim 1, wherein the first target item record includes respective second behavior data, a first total value, and wherein determining a target intent record in the user summary table based on the identity and determining a first target item record in the target intent record based on the target intent record and the first item field comprises, after the steps of:
if target behavior data matched with the first behavior data exists in the second behavior data, determining a first type of the target behavior data according to a preset classification table;
if the first type is one of preset first target bonus types, determining a second target bonus type matched with the first type in the first target bonus types;
determining a weight function corresponding to a second target scoring type, a first numerical value of the weight function and a parameter numerical value in the weight function according to a preset classification table;
adding a preset value to the parameter value to obtain a target parameter value, and updating the parameter value in the weight function to the target parameter value to obtain a second value;
and determining a second total value according to the second numerical value and the first numerical value, determining a target project grade according to the second total value, and updating the target intention record in the user summary table.
8. The data processing method of claim 7, wherein the steps of determining a second total value based on the second value and the first value, determining a target item rating based on the second total value, and updating the first target item record in the user summary table comprise:
carrying out subtraction operation on the second numerical value and the first numerical value to obtain a third numerical value, carrying out addition operation on the third numerical value and the first total numerical value to obtain a second total numerical value, and grading the second total numerical value according to a grading rule to obtain a target item grade;
and updating the first total numerical value of the first target item record into a second total numerical value and updating the item level of the first target item record into a target item level in the user summary table so as to update the target intention degree record.
9. A data processing apparatus characterized by comprising: memory, a processor and a data processing program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the data processing method of any one of claims 1 to 8.
10. A computer-readable storage medium, on which a data processing program is stored, which when executed by a processor implements the steps of the data processing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211224433.6A CN115292630A (en) | 2022-10-09 | 2022-10-09 | Data processing method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211224433.6A CN115292630A (en) | 2022-10-09 | 2022-10-09 | Data processing method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115292630A true CN115292630A (en) | 2022-11-04 |
Family
ID=83833368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211224433.6A Pending CN115292630A (en) | 2022-10-09 | 2022-10-09 | Data processing method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115292630A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104699693A (en) * | 2013-12-05 | 2015-06-10 | 中国移动通信集团广东有限公司 | Information processing method and device thereof |
| CN106878405A (en) * | 2017-01-25 | 2017-06-20 | 咪咕动漫有限公司 | A kind of method and device for adjusting push project |
| CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
| CN108537373A (en) * | 2018-03-27 | 2018-09-14 | 黄晓鸣 | Travel information recommends method and apparatus |
| CN109685631A (en) * | 2019-01-10 | 2019-04-26 | 博拉网络股份有限公司 | A kind of personalized recommendation method based on big data user behavior analysis |
| CN110852797A (en) * | 2019-10-29 | 2020-02-28 | 深圳市看见网络科技有限公司 | Method, mobile terminal and computer storage medium for helping broker to judge guests efficiently |
| CN111782943A (en) * | 2020-06-24 | 2020-10-16 | 中国平安财产保险股份有限公司 | Information recommendation method, device, equipment and medium based on historical data record |
-
2022
- 2022-10-09 CN CN202211224433.6A patent/CN115292630A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104699693A (en) * | 2013-12-05 | 2015-06-10 | 中国移动通信集团广东有限公司 | Information processing method and device thereof |
| CN106878405A (en) * | 2017-01-25 | 2017-06-20 | 咪咕动漫有限公司 | A kind of method and device for adjusting push project |
| CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
| CN108537373A (en) * | 2018-03-27 | 2018-09-14 | 黄晓鸣 | Travel information recommends method and apparatus |
| CN109685631A (en) * | 2019-01-10 | 2019-04-26 | 博拉网络股份有限公司 | A kind of personalized recommendation method based on big data user behavior analysis |
| CN110852797A (en) * | 2019-10-29 | 2020-02-28 | 深圳市看见网络科技有限公司 | Method, mobile terminal and computer storage medium for helping broker to judge guests efficiently |
| CN111782943A (en) * | 2020-06-24 | 2020-10-16 | 中国平安财产保险股份有限公司 | Information recommendation method, device, equipment and medium based on historical data record |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520444B (en) | Insurance product recommendation method, equipment, device and computer readable storage medium | |
| CN109948077B (en) | User behavior data acquisition method, device, equipment and computer storage medium | |
| CN108763561A (en) | E-book method for pushing, device and computer readable storage medium | |
| CN107958042B (en) | Target topic pushing method and mobile terminal | |
| CN110335139B (en) | Similarity-based evaluation method, device and equipment and readable storage medium | |
| CN108228270A (en) | Start resource loading method and device | |
| CN110264093B (en) | Credit model establishing method, device, equipment and readable storage medium | |
| CN111078556B (en) | Application testing method and device | |
| US20110117537A1 (en) | Usage estimation device | |
| CN110472162B (en) | Evaluation method, system, terminal and readable storage medium | |
| CN102622238A (en) | Method and device for interface layout of mobile devices | |
| CN110825611A (en) | Abnormal program analysis method and device and computer readable storage medium | |
| CN115145801B (en) | A/B test flow distribution method, device, equipment and storage medium | |
| CN111160624A (en) | User intention prediction method, user intention prediction device and terminal equipment | |
| CN110263255A (en) | Acquisition methods, system, server and the storage medium of customer attribute information | |
| CN107918509B (en) | Software shortcut prompt setting method and device and readable storage medium | |
| CN114266601A (en) | Marketing strategy determination method and device, terminal equipment and storage medium | |
| CN105653693A (en) | Individualization recommendation method and apparatus | |
| KR20160006300A (en) | Apparatus And Method For providing advertisement exposure detection | |
| CN114265777B (en) | Application program testing method and device, electronic equipment and storage medium | |
| CN115292630A (en) | Data processing method, device and computer readable storage medium | |
| CN106776634A (en) | A kind of method for network access, device and terminal device | |
| CN106302821B (en) | Data request method and equipment thereof | |
| CN115292555A (en) | Data processing method, device and computer readable storage medium | |
| CN112749235B (en) | Method and device for analyzing classification result and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221104 |
|
| RJ01 | Rejection of invention patent application after publication |