CN113407521B - User behavior tag preference sorting method, device, equipment and storage medium - Google Patents
User behavior tag preference sorting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113407521B CN113407521B CN202110661978.2A CN202110661978A CN113407521B CN 113407521 B CN113407521 B CN 113407521B CN 202110661978 A CN202110661978 A CN 202110661978A CN 113407521 B CN113407521 B CN 113407521B
- Authority
- CN
- China
- Prior art keywords
- behavior
- relevance
- behaviors
- scale
- label
- 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.)
- Active
Links
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
Abstract
According to the user behavior tag preference sorting method, device, equipment and storage medium, user behavior data are collected and are delivered to an analysis database in a cleaning and summarizing mode, behavior tags are obtained by analyzing the user behavior data, numerical values of various behaviors under different behavior tags are counted, and relative weights of various behaviors of the behavior tags are quantified by using an analytic hierarchy process in combination with the behavior tags; calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors; and generating a preference label table according to the sequence of the preference values of the behavior labels, and constructing a clear user behavior label image so as to facilitate the application of the follow-up behavior labels.
Description
Technical Field
The invention relates to the technical field of data platforms, in particular to a user behavior tag preference sorting method, device, equipment and storage medium.
Background
The big data technology is an information processing technology which takes all data resources of any system as objects and discovers the correlation relationship expressed between data from the objects, is widely applied to the aspects of flow optimization, targeted message and advertisement push, user personalized service and improvement and the like of the internet at present, and becomes a powerful background support behind network services.
User portrayal is an important application of big data technology, and the goal is to establish descriptive label attributes aiming at user behaviors in many dimensions, so that real personal features of various aspects of users are outlined by using the behavior label attributes.
In the prior art, user portrait analysis is mostly used for generating a behavior tag of a user, the construction of the tag is not accurate enough, the preference value of the behavior tag of the user cannot be quantized, and the application of the subsequent behavior tag is inconvenient.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide a method, an apparatus, a device, and a storage medium for ordering user behavior tag preferences, which can accurately quantify the preference of a user tag, and facilitate application of a subsequent user behavior tag.
An embodiment of the present invention provides a method for ordering user behavior tag preferences, including:
collecting user behavior data, and delivering the user behavior data into an analysis database in a cleaning and summarizing manner;
behavior tags are obtained by analyzing user behavior data, and numerical values of various behaviors under different behavior tags are counted;
quantifying the relative weight of various behaviors of the behavior tag by using an analytic hierarchy process in combination with the behavior tag;
calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors;
and generating a preference tag table according to the preference value sequence of the behavior tags.
Preferably, the method further comprises:
and repeatedly collecting user behavior data in real time, counting various behaviors of different behavior labels, calculating relative weights of the various behaviors by using an analytic hierarchy process, calculating preference values of the behavior labels, and updating a preference label table in real time.
Preferably, the behavior tag is combined, and the relative weight of each behavior of the behavior tag is quantified by using an analytic hierarchy process, and specifically includes:
for the first label, calibrating every two behaviors of the first label, judging the importance of the first behavior and the second behavior on the first label, and respectively scaling the two behaviors;
establishing a pair comparison matrix of the first behavior, and calculating to obtain the relative weight of the first behavior;
and calibrating and calculating various behaviors respectively to obtain the relative weight of all behaviors of all labels.
Preferably, the determining the importance of the first behavior and the second behavior on the first label and respectively scaling the two behaviors specifically includes:
determining the relevance of the first behavior to the first label compared with the second behavior in the two behaviors, and inquiring a preset relevance degree scale table to obtain the scale of the first behavior;
and taking the reciprocal of the scale of the first behavior to obtain the scale of the second behavior to the first label.
Further, the determining the association degree of the first behavior in the two behaviors with respect to the first tag as compared with the second behavior, and querying a preset association degree scale table to obtain the scale of the first behavior specifically includes:
inquiring the association degree of the first behavior and the first label, and recording as a first behavior association degree;
inquiring the association degree of the second behavior and the first label, and recording as the association degree of the second behavior;
when the first behavior is the same as the second behavior in relevance degree, the scale of the first behavior is a first threshold value;
when the first behavior association degree is greater than the second behavior association degree and is less than the product of the second behavior association degree and a preset first threshold, the scale of the first behavior is N1;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the first threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset second threshold, the scale of the first behavior is N2;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the second threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset third threshold, the scale of the first behavior is N3;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the third threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset fourth threshold, the scale of the first behavior is N4;
when the first behavior association degree is not less than the product of the second behavior association degree and the fourth threshold, the scale of the first behavior is N5.
Preferably, the calculating the preference value of each behavior tag according to the weight of each behavior under different behavior tags and the numerical value of each behavior includes:
and according to the weights of various behaviors under different behavior labels and the numerical values of the various behaviors, carrying out weighted summation on the numerical values of the various behaviors under different behavior labels to obtain the preference values of the various behavior labels.
According to the user behavior tag preference sorting method provided by the embodiment of the invention, user behavior data are collected and are delivered to an analysis database in a cleaning and summarizing mode, behavior tags are obtained by analyzing the user behavior data, numerical values of various behaviors under different behavior tags are counted, and relative weights of various behaviors of the behavior tags are quantized by using an analytic hierarchy process in combination with the behavior tags; calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors; and generating a preference label table according to the sequence of the preference values of the behavior labels, and constructing a clear user behavior label image so as to facilitate the application of the follow-up behavior labels.
The embodiment of the invention also provides a user behavior tag preference sorting device, which comprises a user data collecting module, a behavior tag module, a level analyzing module, a preference value module and a tag table module:
the user data collection module is used for collecting user behavior data and delivering the user behavior data into the analysis database in a cleaning and summarizing mode;
the behavior tag module is used for obtaining behavior tags by analyzing the user behavior data and counting the numerical values of various behaviors under different behavior tags;
the hierarchical analysis module is used for quantifying the relative weight of each behavior of the behavior label by combining the behavior label and using a hierarchical analysis method;
the preference value module is used for calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and numerical values of various behaviors;
and the tag table module is used for generating a preference tag table according to the sequencing of the preference values of the behavior tags.
As a preferred mode, the apparatus further includes an update module:
the updating module is used for repeatedly collecting user behavior data in real time, counting various behaviors of different behavior labels, calculating relative weight of the various behaviors by using an analytic hierarchy process, calculating preference values of the behavior labels, and updating a preference label table in real time.
As a preferred mode, the hierarchical analysis module is specifically configured to:
for the first label, calibrating every two behaviors of the first label, judging the importance of the first behavior and the second behavior on the first label, and respectively scaling the two behaviors;
establishing a pair comparison matrix of the first behavior, and calculating to obtain the relative weight of the first behavior;
and calibrating and calculating various behaviors respectively to obtain the relative weight of all behaviors of all labels.
As a preferred mode, the determining the importance of the first behavior and the second behavior on the first label and respectively scaling the two behaviors specifically includes:
determining the relevance of the first behavior to the first label compared with the second behavior in the two behaviors, and inquiring a preset relevance degree scale table to obtain the scale of the first behavior;
and taking the reciprocal of the scale of the first behavior to obtain the scale of the second behavior to the first label.
Further, the determining the association degree of the first behavior in the two behaviors with respect to the first tag as compared with the second behavior, and querying a preset association degree scale table to obtain the scale of the first behavior specifically includes:
inquiring the association degree of the first behavior and the first label, and recording as a first behavior association degree;
inquiring the association degree of the second behavior and the first label, and recording as the association degree of the second behavior;
when the first behavior is the same as the second behavior in relevance degree, the scale of the first behavior is a first threshold value;
when the first behavior association degree is greater than the second behavior association degree and is less than the product of the second behavior association degree and a preset first threshold, the scale of the first behavior is N1;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the first threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset second threshold, the scale of the first behavior is N2;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the second threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset third threshold, the scale of the first behavior is N3;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the third threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset fourth threshold, the scale of the first behavior is N4;
when the first behavior association degree is not less than the product of the second behavior association degree and the fourth threshold, the scale of the first behavior is N5.
As a preferred mode, the preference value module is specifically configured to:
and according to the weights of various behaviors under different behavior labels and the numerical values of the various behaviors, carrying out weighted summation on the numerical values of the various behaviors under different behavior labels to obtain the preference values of the various behavior labels.
Another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the processor implements the user behavior tag preference ranking method according to the above embodiment of the present invention.
Another embodiment of the present invention provides a storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, a device where the computer-readable storage medium is located is controlled to execute the method for ordering user behavior tag preferences according to the above-described embodiment of the present invention.
The invention provides a user behavior label preference sorting method, a device, equipment and a storage medium, wherein user behavior data are collected and are delivered to an analysis database in a cleaning and summarizing mode, behavior labels are obtained by analyzing the user behavior data, numerical values of various behaviors under different behavior labels are counted, and relative weights of various behaviors of the behavior labels are quantized by using an analytic hierarchy process in combination with the behavior labels; calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors; and generating a preference tag table according to the preference value sequence of the behavior tags. And a clear user behavior label picture is constructed, so that the application of a subsequent behavior label is facilitated.
Drawings
Fig. 1 is a flowchart illustrating a method for sorting user behavior tag preferences according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a user behavior tag preference sorting apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a user behavior tag preference sorting method, which is shown in fig. 1 and is a flow diagram of the user behavior tag preference sorting method provided by the embodiment of the invention, and the method comprises the following steps of S101-S105:
s101, collecting user behavior data, and delivering the user behavior data into an analysis database in a cleaning and summarizing mode;
s102, obtaining behavior labels by analyzing user behavior data, and counting the numerical values of various behaviors under different behavior labels;
s103, quantifying the relative weight of each behavior of the behavior label by combining the behavior label and using an analytic hierarchy process;
s104, calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors;
and S105, generating a preference tag table according to the preference value sequence of the behavior tags.
When the embodiment is implemented specifically, behavior data of a user is collected through a log system, and is delivered to a data platform in real time, and then the behavior data is delivered to an analysis database in a cleaning and summarizing mode;
analyzing various behaviors of the user under the behavior labels according to different behavior labels through the user behavior data, wherein the behavior labels comprise: major brand, series, price, category. Various behaviors under the behavior tag include: browsing, sharing, collecting, ordering and paying.
Quantifying the relative weight of various behaviors of the behavior tag by using an analytic hierarchy process in combination with the behavior tag;
calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors;
and generating a preference tag table according to the preference value sequence of the behavior tags.
According to the embodiment of the invention, the user behaviors are obtained, the weight of each behavior is calculated through the analytic hierarchy process, and the analytic hierarchy process is used for calculating the relative weight of the behavior under each behavior label, so that the importance degree of each behavior to each label can be objectively and accurately judged, and each behavior label is relatively fairly measured, and thus, a clear user behavior label portrait can be constructed through the calculated preference value of the behavior label.
In another embodiment of the present invention, the method further comprises:
and repeatedly collecting user behavior data in real time, counting various behaviors of different behavior labels, calculating relative weights of the various behaviors by using an analytic hierarchy process, calculating preference values of the behavior labels, and updating a preference label table in real time.
In the specific implementation of this embodiment, after the preference tag table is generated according to the weight ranking of the preference tags, since the data of the user changes every day, the above steps need to be repeated, the user behavior data is repeatedly collected in real time, various behaviors of the user are analyzed, the relative weights of the various behaviors are calculated by using an analytic hierarchy process, the preference values of the behavior tags are obtained by calculation, and the preference tag table is updated in real time;
by means of real-time synchronization of the data, real-time updating of user data can be achieved, timeliness of user behavior data is improved, and timeliness and accuracy of user label construction of user portrait are improved.
In another embodiment provided by the present invention, the quantifying the relative weight of each behavior of the behavior tag by using an analytic hierarchy process in combination with the behavior tag specifically includes:
for the first label, calibrating every two behaviors of the first label, judging the importance of the first behavior and the second behavior on the first label, and respectively scaling the two behaviors;
establishing a pair comparison matrix of the first behavior, and calculating to obtain the relative weight of the first behavior;
and calibrating and calculating various behaviors respectively to obtain the relative weight of all behaviors of all labels.
When the method is implemented specifically, the first label is selected, every two behaviors under the first label are calibrated in a group, all behaviors are not compared together, but behavior data are compared in pairs, so that the difficulty in comparison among behaviors with different properties is reduced, and the calculation accuracy of the weight of each behavior under the behavior label is improved;
it should be noted that if the number of behaviors is singular, there may be behavior data that are compared two by two for many times;
judging the importance of the two behaviors to the first behavior label, and respectively scaling the two behaviors;
establishing a pair-wise comparison positive and negative matrix of the first behavior, and calculating the weight to obtain the weight of the first behavior;
in the specific implementation, in the behavior tag of the main brand, purchasing Ai is obviously important relative to browsing Aj behavior, the score aij of purchasing behavior is 5, and the score aji of browsing behavior is 1/5, and similarly, scales of other behaviors are obtained.
Construction of pairwise comparison matrices from analytic hierarchy processes
The matrix is a positive and a negative matrix. And calculating the characteristic vector W of the judgment matrix A by adopting a sum method.
Assume that M1 ═ 1 ═ 5 ═ 3 ═ 15, M2 ═ 1/5 ═ 1 ═ 1/3 ═ 1/15, M3 ═ 1/3 ═ 1 ═ 3 ═ 1;
the vector is obtained by calculation, and the vector is obtained,
calculating the average value of the vectors to obtain the weight of the first behavior;
similarly, the weights of all behaviors of all behavior tags can be obtained by adopting the method;
the weights of all behaviors under different behavior labels are respectively quantized through an analytic hierarchy process, so that the behavior data of a client user can be objective, the result of user portrait analysis is obtained, and the user portrait is more accurately constructed.
In another embodiment provided by the present invention, the determining the importance of the first behavior and the second behavior on the first label and respectively scaling the two behaviors specifically includes:
determining the relevance of the first behavior to the first label compared with the second behavior in the two behaviors, and inquiring a preset relevance degree scale table to obtain the scale of the first behavior;
and taking the reciprocal of the scale of the first behavior to obtain the scale of the second behavior to the first label.
In the specific implementation of this embodiment, scaling the two behaviors requires comparing the importance degrees of the two behaviors with respect to the first tag, and this specific comparison process may count the necessary connection frequency existing between the two behaviors according to a statistical method, that is, the number of times that a certain behavior and the first tag appear in a certain amount of user behavior data at the same time, and perform normalization processing;
obtaining the association degree of a first behavior intersected with a second behavior to a first label, and inquiring an association degree scale table to obtain the scale of the first behavior;
and taking the reciprocal of the scale of the first behavior to obtain the scale of the second behavior to the first label.
According to the method, the relevance between the behavior labels and the behaviors is obtained, the relevance degree scale table is inquired, the scales of all behaviors under different behavior labels are obtained and are used for calculating the weight of each behavior, the scaling process of each behavior label is more objective, and the preference calculation of the behavior label is more accurate and efficient.
In another embodiment of the present invention, the determining the association degree of the first behavior in the two behaviors with respect to the first tag as compared to the second behavior, and querying a preset association degree scale table to obtain the scale of the first behavior specifically includes:
inquiring the association degree of the first behavior and the first label, and recording as a first behavior association degree;
inquiring the association degree of the second behavior and the first label, and recording as the association degree of the second behavior;
when the first behavior is the same as the second behavior in relevance degree, the scale of the first behavior is a first threshold value;
when the first behavior association degree is greater than the second behavior association degree and is less than the product of the second behavior association degree and a preset first threshold, the scale of the first behavior is N1;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the first threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset second threshold, the scale of the first behavior is N2;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the second threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset third threshold, the scale of the first behavior is N3;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the third threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset fourth threshold, the scale of the first behavior is N4;
when the first behavior association degree is not less than the product of the second behavior association degree and the fourth threshold, the scale of the first behavior is N5.
When the embodiment is implemented specifically, the association degree between the first behavior and the first tag is queried and recorded as a first behavior association degree;
inquiring the association degree of the second behavior and the first label, and recording as the association degree of the second behavior;
when the first behavior is the same as the second behavior in relevance degree, the scale of the first behavior is 1;
when the first behavior association degree is greater than the second behavior association degree and the first behavior association degree is less than twice the second behavior association degree, the scale of the first behavior is 2;
when the first behavior relevance degree is not less than two times of the second behavior relevance degree and the first behavior relevance degree is less than three times of the second behavior relevance degree, the scale of the first behavior is 3;
when the first behavior relevance degree is not less than three times of the second behavior relevance degree and the first behavior relevance degree is less than four times of the second behavior relevance degree, the scale of the first behavior is 4;
when the first behavior association degree is not less than four times of the second behavior association degree and the first behavior association degree is less than five times of the second behavior association degree, the scale of the first behavior is 5;
when the first behavior association degree is not less than five times the second behavior association degree, the scale of the first behavior is 6.
It should be noted that, in this embodiment, values of the first threshold, the second threshold, the third threshold, the fourth threshold, the fifth threshold, N1, N2, N3, N4, and N5 are all a preferred embodiment, and in other embodiments provided by the present invention, the selected value may be another value.
By comparing the first behavior association degree with the second behavior association degree, the scale of the first behavior and the first behavior label is obtained, the scale is used for calculating the weight of each behavior under the first label, the portrait analysis result of the user can be obtained, and the preference label of the user is quantitatively analyzed.
In another embodiment provided by the present invention, the calculating the preference value of each behavior tag according to the weight of each behavior under different behavior tags and the numerical value of each behavior specifically includes:
and according to the weights of various behaviors under different behavior labels and the numerical values of the various behaviors, carrying out weighted summation on the numerical values of the various behaviors under different behavior labels to obtain the preference values of the various behavior labels.
In the specific implementation of this embodiment, the weighted sum of the behavior values under different behavior labels is performed according to the weights of various behaviors under different behavior labels and the values of various behaviors, that is, the preference value of each behavior label is equal to the sum of the product of each behavior value under each behavior label and each behavior weight, and the behavior value is a normalized value of each behavior frequency under each behavior label, so as to obtain the preference values of various behavior labels.
According to the user behavior tag preference sorting method provided by the embodiment of the invention, user behavior data are collected and are delivered to an analysis database in a cleaning and summarizing mode, behavior tags are obtained by analyzing the user behavior data, numerical values of various behaviors under different behavior tags are counted, and relative weights of various behaviors of the behavior tags are quantized by using an analytic hierarchy process in combination with the behavior tags; calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors; and generating a preference label table according to the sequence of the preference values of the behavior labels, and constructing a clear user behavior label image so as to facilitate the application of the follow-up behavior labels.
Another embodiment of the present invention provides a user behavior tag preference sorting apparatus, which includes a user data collection module, a behavior tag module, a hierarchical analysis module, and a tag table module:
the user data collection module is used for collecting user behavior data and delivering the user behavior data into an analysis database in a cleaning and summarizing mode;
the behavior tag module is used for analyzing various behaviors of the user through the user behavior data and generating different behavior tags;
the hierarchical analysis module is used for quantifying the weight of each behavior relative to the behavior tag by combining the behavior tag and using a hierarchical analysis method to obtain a preference value of the behavior tag;
and the label table module is used for generating a preference label table according to the preference value sequence of the behavior labels.
In specific implementation of this embodiment, referring to fig. 2, a schematic structural diagram of a user behavior tag preference sorting apparatus provided in an embodiment of the present invention is shown, where the apparatus includes a user data collection module, a behavior tag module, a hierarchical analysis module, a preference value module, and a tag table module:
the user data collection module is used for collecting user behavior data and delivering the user behavior data into the analysis database in a cleaning and summarizing mode;
the behavior tag module is used for obtaining behavior tags by analyzing the user behavior data and counting the numerical values of various behaviors under different behavior tags;
the hierarchical analysis module is used for quantifying the relative weight of each behavior of the behavior label by combining the behavior label and using a hierarchical analysis method;
the preference value module is used for calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and numerical values of various behaviors;
and the tag table module is used for generating a preference tag table according to the sequencing of the preference values of the behavior tags.
It should be noted that, specific functions of the apparatus for sorting user behavior tag preference provided in this embodiment are specifically described in the foregoing embodiments, and are not described herein again.
Fig. 3 is a schematic structural diagram of a terminal device according to an embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program, such as a user behavior tag preference ranking program, stored in the memory and executable on the processor. The processor, when executing the computer program, implements the steps in the above-described embodiments of the user behavior tag preference ranking method, such as steps S101 to S105 shown in fig. 1. Alternatively, the processor implements the functions of the modules/units in the above device embodiments when executing the computer program.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device. For example, the computer program may be divided into a user data collection module, a behavior tag module, a hierarchy analysis module, and a tag table module, and specific functions of each module are not described herein.
The terminal device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a terminal device and does not constitute a limitation of a terminal device, and may include more or less components than those shown, or combine certain components, or different components, for example, the terminal device may also include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal device and connects the various parts of the whole terminal device using various interfaces and lines.
The memory may be used for storing the computer programs and/or modules, and the processor may implement various functions of the terminal device by executing or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein, the terminal device integrated module/unit can be stored in a computer readable storage medium if it is implemented in the form of software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The invention provides a user behavior label preference sorting method, a device, equipment and a storage medium, wherein user behavior data are collected and are delivered to an analysis database in a cleaning and summarizing mode, behavior labels are obtained by analyzing the user behavior data, numerical values of various behaviors under different behavior labels are counted, and relative weights of various behaviors of the behavior labels are quantized by using an analytic hierarchy process in combination with the behavior labels; calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors; and generating a preference label table according to the sequence of the preference values of the behavior labels, and constructing a clear user behavior label image so as to facilitate the application of the follow-up behavior labels.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (7)
1. A user behavior tag preference ranking method is characterized by comprising the following steps:
collecting user behavior data, and delivering the user behavior data into an analysis database in a cleaning and summarizing manner;
behavior tags are obtained by analyzing user behavior data, numerical values of various behaviors under different behavior tags are counted, and the numerical value of each behavior is a normalized numerical value of frequency of each behavior under each behavior tag;
quantifying the relative weight of various behaviors of the behavior tag by using an analytic hierarchy process in combination with the behavior tag;
calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and the numerical values of various behaviors;
generating a preference tag table according to the sequence of the preference values of the behavior tags;
the behavior tag is combined, and an analytic hierarchy process is used for quantifying the relative weight of various behaviors of the behavior tag, and the method specifically comprises the following steps:
for the first label, calibrating every two behaviors of the first label, judging the importance of the first behavior and the second behavior on the first label, and respectively scaling the two behaviors;
establishing a pair comparison matrix of the first behavior, and calculating to obtain the relative weight of the first behavior;
calibrating and calculating various behaviors respectively to obtain the relative weights of all behaviors of all labels;
the determining the importance of the first behavior and the second behavior to the first label, and scaling the two behaviors respectively specifically includes:
determining the relevance of the first behavior to the first label compared with the second behavior in the two behaviors, and inquiring a preset relevance degree scale table to obtain the scale of the first behavior;
taking the reciprocal of the scale of the first behavior to obtain the scale of the second behavior to the first label;
the determining the association degree of the first behavior in the two behaviors with respect to the first tag compared with the second behavior, and querying a preset association degree scale table to obtain the scale of the first behavior specifically includes:
inquiring the association degree of the first behavior and the first label, and recording as a first behavior association degree;
inquiring the association degree of the second behavior and the first label, and recording as the association degree of the second behavior;
when the first behavior is the same as the second behavior in relevance degree, the scale of the first behavior is a first threshold value;
when the first behavior association degree is greater than the second behavior association degree and is less than the product of the second behavior association degree and a preset first threshold, the scale of the first behavior is N1;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the first threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset second threshold, the scale of the first behavior is N2;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the second threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset third threshold, the scale of the first behavior is N3;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the third threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset fourth threshold, the scale of the first behavior is N4;
when the first behavior association degree is not less than the product of the second behavior association degree and the fourth threshold, the scale of the first behavior is N5.
2. The method of user behavior tag preference ranking of claim 1, the method further comprising:
and repeatedly collecting user behavior data in real time, counting various behaviors of different behavior labels, calculating relative weights of the various behaviors by using an analytic hierarchy process, calculating preference values of the behavior labels, and updating a preference label table in real time.
3. The method according to claim 1, wherein the calculating preference values of various behavior tags according to weights of various behaviors under different behavior tags and numerical values of various behaviors specifically comprises:
and according to the weights of various behaviors under different behavior labels and the numerical values of the various behaviors, carrying out weighted summation on the numerical values of the various behaviors under different behavior labels to obtain the preference values of the various behavior labels.
4. A user behavior tag preference sorting device is characterized by comprising a user data collecting module, a behavior tag module, a hierarchy analyzing module, a preference value module and a tag table module:
the user data collection module is used for collecting user behavior data and delivering the user behavior data into the analysis database in a cleaning and summarizing mode;
the behavior tag module is used for obtaining behavior tags by analyzing user behavior data, counting the numerical values of various behaviors under different behavior tags, wherein the numerical value of each behavior is the normalized numerical value of the frequency of each behavior under each behavior tag;
the hierarchical analysis module is used for quantifying the relative weight of each behavior of the behavior label by combining the behavior label and using a hierarchical analysis method;
the preference value module is used for calculating preference values of various behavior labels according to the weights of various behaviors under different behavior labels and numerical values of various behaviors;
the tag table module is used for generating a preference tag table according to the sorting of preference values of the behavior tags;
the hierarchical analysis module is specifically configured to:
for the first label, calibrating every two behaviors of the first label, judging the importance of the first behavior and the second behavior on the first label, and respectively scaling the two behaviors;
establishing a pair comparison matrix of the first behavior, and calculating to obtain the relative weight of the first behavior;
calibrating and calculating various behaviors respectively to obtain the relative weights of all behaviors of all labels;
the determining the importance of the first behavior and the second behavior to the first label, and scaling the two behaviors respectively specifically includes:
determining the relevance of the first behavior to the first label compared with the second behavior in the two behaviors, and inquiring a preset relevance degree scale table to obtain the scale of the first behavior;
taking the reciprocal of the scale of the first behavior to obtain the scale of the second behavior to the first label;
further, the determining the association degree of the first behavior in the two behaviors with respect to the first tag as compared with the second behavior, and querying a preset association degree scale table to obtain the scale of the first behavior specifically includes:
inquiring the association degree of the first behavior and the first label, and recording as a first behavior association degree;
inquiring the association degree of the second behavior and the first label, and recording as the association degree of the second behavior;
when the first behavior is the same as the second behavior in relevance degree, the scale of the first behavior is a first threshold value;
when the first behavior association degree is greater than the second behavior association degree and is less than the product of the second behavior association degree and a preset first threshold, the scale of the first behavior is N1;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the first threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset second threshold, the scale of the first behavior is N2;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the second threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset third threshold, the scale of the first behavior is N3;
when the first behavior relevance is not smaller than the product of the second behavior relevance and the third threshold, and the first behavior relevance is smaller than the product of the second behavior relevance and a preset fourth threshold, the scale of the first behavior is N4;
when the first behavior association degree is not less than the product of the second behavior association degree and the fourth threshold, the scale of the first behavior is N5.
5. The apparatus of claim 4, wherein the apparatus further comprises an update module to:
the updating module is used for repeatedly collecting user behavior data in real time, counting various behaviors of different behavior labels, calculating relative weight of the various behaviors by using an analytic hierarchy process, calculating preference values of the behavior labels, and updating a preference label table in real time.
6. A terminal device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the user behavior tag preference ranking method of any of claims 1 to 3 when executing the computer program.
7. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method of ranking user behavior tag preferences according to any of claims 1 to 3.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565822 | 2021-05-24 | ||
| CN2021105658224 | 2021-05-24 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113407521A CN113407521A (en) | 2021-09-17 |
| CN113407521B true CN113407521B (en) | 2022-02-08 |
Family
ID=77683853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110661978.2A Active CN113407521B (en) | 2021-05-24 | 2021-06-15 | User behavior tag preference sorting method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113407521B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391680A (en) * | 2017-07-24 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Content recommendation method, device and equipment |
| CN109446401A (en) * | 2017-08-29 | 2019-03-08 | 合肥美的智能科技有限公司 | User's preferred diet portrait construction method, device and machine readable storage medium |
| CN109657138A (en) * | 2018-12-10 | 2019-04-19 | 深圳墨世科技有限公司 | A kind of video recommendation method, device, electronic equipment and storage medium |
| CN109992982A (en) * | 2019-04-11 | 2019-07-09 | 北京信息科技大学 | Big data access authorization methods, device and big data platform |
-
2021
- 2021-06-15 CN CN202110661978.2A patent/CN113407521B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391680A (en) * | 2017-07-24 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Content recommendation method, device and equipment |
| CN109446401A (en) * | 2017-08-29 | 2019-03-08 | 合肥美的智能科技有限公司 | User's preferred diet portrait construction method, device and machine readable storage medium |
| CN109657138A (en) * | 2018-12-10 | 2019-04-19 | 深圳墨世科技有限公司 | A kind of video recommendation method, device, electronic equipment and storage medium |
| CN109992982A (en) * | 2019-04-11 | 2019-07-09 | 北京信息科技大学 | Big data access authorization methods, device and big data platform |
Non-Patent Citations (2)
| Title |
|---|
| 基于层次分析的个性化推荐算法;郭晓慧;《长春工业大学学报》;20161215(第06期);第1-6页 * |
| 舰艇对来袭反舰导弹威胁评估算法;尹高扬等;《兵工自动化》;20111221(第12期);第1-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113407521A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3893154A1 (en) | Recommendation model training method and related apparatus | |
| TWI718422B (en) | Method, device and equipment for fusing model prediction values | |
| CN111125574B (en) | Method and device for generating information | |
| CN110162359B (en) | Method, device and system for pushing novice guiding information | |
| CN109509010B (en) | Multimedia information processing method, terminal and storage medium | |
| CN109558384B (en) | Log classification method, device, electronic equipment and storage medium | |
| CN113688310B (en) | Content recommendation method, device, equipment and storage medium | |
| CN111861605A (en) | Business object recommendation method | |
| CN111626767A (en) | Resource data distribution method, device and equipment | |
| CN111538909A (en) | Information recommendation method and device | |
| CN113407521B (en) | User behavior tag preference sorting method, device, equipment and storage medium | |
| CN109344327B (en) | Method and apparatus for generating information | |
| CN109976710B (en) | Data processing method and equipment | |
| CN115905472A (en) | Business opportunity service processing method, business opportunity service processing device, business opportunity service processing server and computer readable storage medium | |
| CN107357847B (en) | Data processing method and device | |
| CN110827101A (en) | Shop recommendation method and device | |
| CN110866605A (en) | Data model training method and device, electronic equipment and readable medium | |
| CN111144098B (en) | Recall method and device for extended question | |
| CN114549125A (en) | Item recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN110688582B (en) | Application recommendation method, application recommendation device and terminal equipment | |
| CN109472454B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN109947830B (en) | Method and apparatus for outputting information | |
| CN110825898A (en) | Nail art recommendation method and device, electronic equipment and storage medium | |
| CN110738538A (en) | Method and device for identifying similar articles | |
| CN111008343B (en) | Content recommendation method, device, platform and storage medium based on region |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder |
Address after: 511430 No. 16, Panyu Avenue North, Nancun Town, Panyu District, Guangzhou, Guangdong Patentee after: WBIAO TECHNOLOGY CO.,LTD. Address before: 511430 No. 1, No. 60, North Panyu Avenue, Dashi street, Panyu District, Guangzhou City, Guangdong Province Patentee before: WBIAO TECHNOLOGY CO.,LTD. |
|
| CP02 | Change in the address of a patent holder | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A user behavior label preference sorting method, device, device and storage medium Effective date of registration: 20220527 Granted publication date: 20220208 Pledgee: Bank of China Limited Guangzhou Development Zone Branch Pledgor: WBIAO TECHNOLOGY CO.,LTD. Registration number: Y2022980006545 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |