Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 to which the method or apparatus of determining feature dimensions of some embodiments of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include a dimension generation device 101, a front-end interaction device 102, a back-end service device 103, a display device 104, and a database 105. The back-end service device 103 may communicate with the dimension generation device 101, the front-end interaction device 102, the display device 104, and the database 105 through a network. The network may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The dimension generating device 101, the front-end interaction device 102, and the back-end service device 103 may be hardware or software. When hardware, it may be a variety of electronic devices including, but not limited to, smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When it is software, it can be installed in the electronic devices listed above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
The display device 104 may have a display screen and support various display devices for data display, such as a display, a smart phone, and so forth. It is understood that the display device 104 may be integrated with the back-end service device 103 according to actual needs. For example, in the case where the backend service apparatus 103 is a desktop computer, the display apparatus 104 may be a display of the desktop computer.
The database 105 may be a repository for organizing, storing, and managing data, and may be various types of databases. In practice, the service may be deployed on the backend service device 103, or may be deployed on other electronic devices, as an example.
It should be noted that the method for determining feature dimensions provided by the embodiment of the present disclosure may be performed by the backend service device 103. Accordingly, the means for determining the feature dimension may be provided in the back-end service device 103. Further, at least one dimension in some embodiments of the present disclosure may be determined by the dimension generation device 101.
It should be understood that the number of individual devices in fig. 1 is merely illustrative. There may be any number of devices, as desired for implementation.
With continued reference to fig. 2, a flow 200 of some embodiments of a method of determining feature dimensions in accordance with the present disclosure is shown. The method for determining the feature dimension comprises the following steps:
step 201, at least two user groups to be compared and a comparison index are determined.
In some embodiments, an executive (e.g., the backend service device in fig. 1) of the method for determining feature dimensions may determine at least two user groups to be compared and a comparison index in various ways. As an example, the user may input an identification of a group of users to be compared and a comparison index through interaction with the front-end interaction device 102. On the basis, the front-end interaction device 102 may send the identification of the user group to be compared and the comparison index to the execution main body. Optionally, the front-end interaction device 102 may also convert the identifier of the user group to be compared and the comparison index into a request to be sent to the execution main body. So that the executing agent can determine at least two user groups to be compared by identification. The user data corresponding to each user group comprises a plurality of dimensions, including user attribute information and user behavior data. Such as age, gender, location, date of arrival, etc. In practice, the user data specifically includes which dimensions may be predetermined. A contrast indicator may be included in the plurality of dimensions. Wherein the comparison index may be used to compare at least two user groups. In practice, the comparison index may be various indexes such as DAU (daisy Active User, number of Daily Active users), play amount, forwarding amount, and the like, as needed. The user group may include a plurality of users. The users in the user group can be obtained by designation or screening under certain conditions. According to the needs, the appropriate user groups can be obtained through different division conditions. Wherein the division condition may be a defined condition for certain dimensions. For example, the user group a may be a defined condition of the dimension of age, such as a user group of users between 20-50. As another example, the user group B may be a user group composed of users who like makeup.
Step 202, determining difference data of the comparison indexes of at least two user groups in each dimension of at least one dimension of the plurality of dimensions to obtain a difference data set.
In some embodiments, the execution subject may obtain the difference data set by comparing user data corresponding to at least two user groups in each of at least one dimension. It is to be understood that the user data corresponding to the user group may be pre-collected data. In practice, user authorization needs to be obtained before user data is collected in various ways to protect user privacy and data security. At least one dimension may be each dimension of user data, including user attributes or behavior data. For example, the dimension may be age, gender, territory, favorite content, and so forth. Specifically, as an example, divergence or various distance algorithms may be utilized to determine difference data in each of at least one dimension on the contrast indicators corresponding to at least two user groups, respectively. For example, if the comparison index is the daily number, the two user groups to be compared are user groups a and B. The dimensionality is age and region dimensionality. Then, the weibull (Wasserstein) distance of the daily activity number distribution of the user group a and the user group B in the dimension of age may be determined, resulting in the first distance.
Specifically, for any two different distributions u and v, (e.g., daily living number distribution of user group a and user group B in the age dimension), the wecker distance l can be calculated by the following formula1(u,v):
Wherein (mu, v) is represented in
All measures are spatially aggregated and the edge distributions of these measures are u and v, respectively. Where x and y are two distributed random variables, respectively.
Similarly, the wegener distance of the daily activity number distribution of the user group a and the user group B in the dimension of the region may be determined to obtain the second distance. Such that the first distance and the second distance may be included in the difference set. Optionally, before calculating the wegener distance, normalization processing may be performed on the wegener distance, so as to prevent a deviation in distance calculation due to dimensional difference.
In practice, for three or more user groups, the difference data of the comparison index in each dimension of at least one dimension can be calculated pairwise, so as to obtain a difference data set.
Step 203, selecting a preset amount of difference data from the difference data set according to the value of the difference data.
In some embodiments, the execution subject may select a preset number of differences from the difference set according to the value of the difference data. Specifically, as an example, the differences in the difference set may be sorted, so as to select the difference with the pre-set number. Of course, other methods may be used to select the predetermined number of differences. Continuing with the example of the difference set obtained in step 202 comprising the first distance and the second distance, a larger distance may be selected from the first distance and the second distance.
Step 204, determining the dimension corresponding to the selected difference data as the characteristic dimension of at least two user groups.
In some embodiments, the execution subject may determine a dimension corresponding to the selected difference as a feature dimension of at least two user groups. It is also considered that, for the at least two user groups, the influence of the feature dimension on the contrast index is the largest.
In some optional implementations of some embodiments, the method may further include: storing the characteristic dimension; the characteristic dimension is sent to a communicatively connected presentation device (e.g., display device 104 in fig. 1) for presentation of the characteristic dimension. In these implementations, the feature dimensions are stored and exposed to facilitate querying and viewing. Optionally, the characteristic dimension may be stored in association with the user group identifier, thereby facilitating subsequent rapid determination of the characteristic dimension of a certain user group.
In some optional implementations of some embodiments, the method may further include: in response to receiving a user request, determining a user group to which a user corresponding to the user request belongs; and determining recommendation information according to the characteristic dimension of the user group to which the user belongs, and sending the recommendation information to a terminal corresponding to the user. In these implementations, the characteristic dimension of each of the plurality of user groups may be determined by the method described above. On the basis, in response to receiving a user request, a user group to which the user belongs can be determined first, and then the characteristic dimension of the user group is determined. Therefore, the recommendation information can be determined according to the characteristic dimension, and the recommendation information is sent to the terminal corresponding to the user. For example, the feature dimension is a favorite content type, and content of the same type as the favorite content type may be determined as the recommendation information. Therefore, more targeted information pushing is realized.
In some optional implementations of some embodiments, the at least one dimension is determined by: acquiring user data, wherein the user data comprises user attribute information and user behavior information; and removing the initial dimensionality with the correlation degree larger than a preset threshold value in the multiple initial dimensionalities of the user data to obtain multiple candidate dimensionalities. Wherein the initial dimension may be a pre-specified dimension. The degree of correlation of two dimensions can be determined in a number of ways. The degree of correlation may be used to indicate how much one dimension affects another dimension. Two dimensions with large correlation degree, and the change of one dimension necessarily causes the change of the other dimension. In practice, it can be determined by means of manual confirmation which dimensions have a correlation degree greater than a preset threshold value. The dimensionality with the correlation degree larger than the preset threshold value can be screened through a preset condition. On the basis, discretizing the continuity dimension in the candidate dimensions to obtain at least one dimension. The value of the continuity dimension is continuous and can be any value in an interval. For example, the duration of time a user uses an application is a continuity dimension.
The execution subject for generating at least one dimension may be the same as or different from the execution subject of the above method for determining a feature dimension. As an example, at least one dimension may be determined by the dimension generation device 101 in fig. 1. In practice, as an example, the user data may be data received by the execution body from a plurality of terminals (e.g. the front-end interaction device 102).
It should be noted that before the user data is obtained through the terminal, the user authorization needs to be obtained, so as to protect the user privacy and data security. User data acquired in various ways typically includes data of different dimensions. Therefore, the initial dimensionalities with the correlation degree larger than the preset threshold value in the multiple initial dimensionalities of the user data can be removed, multiple candidate dimensionalities are obtained, and influence on subsequent processing is avoided. For multiple candidate dimensions, the continuity dimension can be discretized to obtain at least one dimension. Wherein, as required, the discretization can be carried out by adopting a plurality of modes. For example, discretization can be performed at decile points of population distribution. As another example, information input by a technician may be received for discretization. Through discretization, time complexity can be effectively reduced, the operation amount is reduced, and the processing speed is improved. In addition, the user can observe the classification conveniently.
Some embodiments of the present disclosure provide methods by determining difference data of a comparison index in different dimensions, and taking the selected dimension as a feature dimension. For example, a dimension with large difference data may be selected as the feature dimension. Therefore, the dimensionality with larger influence on the comparison index can be determined, and a basis is provided for achieving more targeted information pushing.
With continued reference to FIG. 3, a flow 300 of further embodiments of a method of determining feature dimensions is illustrated. The process 300 of the method for determining feature dimensions includes the following steps:
step 301, at least two user groups to be compared and a comparison index are determined.
In some embodiments, the specific implementation of step 301 and the technical effect thereof may refer to step 201 in those embodiments corresponding to fig. 2.
In practice, the determination method of the difference data is different due to the difference in the category of the index. Therefore, it is necessary to distinguish the types of the comparison indexes.
Step 302, determining whether the category of the comparison index is the target category.
In some embodiments, the comparison indexes can be divided into different categories according to actual needs. As an example, the comparison index may be classified into a static index and a dynamic index according to whether the comparison index is frequently changed. As still another example, the comparison index may be divided into a proportion-based index and a non-proportion-based index according to a description form of the comparison index. The proportion index may be an index expressed in the form of a proportion. As an example, a female user is 60%. Then, the female user may be a percentage indicator representing the percentage of female users to the total population in the user population. In addition, the occupation ratio index can also be an index such as retention rate, loss rate and the like.
In some embodiments, whether the category of the comparison index is the target category may be determined in different manners according to different dividing manners or criteria. For example, whether a target category is determined may be determined by receiving information input by a technician. For another example, whether the category of the comparison index is the target category may be determined by automatically identifying the target category. For example, whether it is the target category is determined by special character (e.g., character "%") identification. The determination of the target category can be obtained by specification or screening under certain conditions.
Step 303, in response to determining that the category of the comparison index is not the target category, determining a wecker distance of the comparison index of the at least two user groups in each dimension and using the wecker distance as difference data to obtain a difference data set.
In some embodiments, the specific implementation of step 303 may refer to step 202 in the embodiment corresponding to fig. 2, and is not described herein again.
Step 304, in response to determining that the category of the contrast index is the target category, determining a weibull distance and a divergence of the contrast index of the at least two user groups in each of the at least one dimension, and obtaining a distance set and a divergence set.
In some embodiments, for each dimension, the weibull distance and divergence of the contrast index may be computed separately, resulting in a distance set and a divergence set. Wherein JS (Jensen-Shannon) divergence can be calculated by the following formula, as an example:
wherein, P1And P2The distribution of the contrast indexes of different user groups in a certain dimension is respectively represented.
Step 305, a difference data set is obtained based on the distance set and the divergence set.
In some embodiments, as an example, a weighted sum of the Westwars distance and the JS (Jensen-Shannon) divergence for each dimension may be determined and used as the difference. On this basis, the weighted sum of the dimensions can be used as a difference set.
In some optional implementations of some embodiments, before determining difference data of a comparison indicator corresponding to each of at least two user groups in each of at least one dimension, the method further includes: based on the comparison index and the at least one dimension, an alternative dimension is determined. Specifically, the alternative dimensions may be determined by: it is determined whether a comparison indicator is included in at least one dimension. In response to determining the inclusion, the contrast indicator in the at least one dimension is culled. Thereby avoiding the same or similar dimensions from adversely affecting subsequent processing. On this basis, determining difference data of the comparison indexes respectively corresponding to the at least two user groups in each dimension to obtain a difference data set, including: and determining difference data of the comparison indexes respectively corresponding to the at least two user groups in each dimension of the alternative dimensions to obtain a difference data set.
Step 306, selecting a preset amount of difference data from the difference data set according to the value of the difference data.
Step 307, determining the dimension corresponding to the selected difference data as the characteristic dimension of at least two user groups.
In some embodiments, the specific implementation of steps 306-307 and the technical effect thereof can refer to steps 203-204 in those embodiments corresponding to fig. 2.
With further reference to fig. 4, illustrated is one application scenario 400 that is a method of determining feature dimensions in accordance with some embodiments of the present disclosure.
In the application scenario, the at least two user groups to be compared and the comparison index may be obtained by receiving information input by the user. For example, the user may select among a plurality of preset user groups and indexes. The user groups to be compared take the user groups a and B as examples, and the comparison index takes the number of users as an example. On this basis, the execution subject may determine whether the comparison index is of the target category. In the application scenario, whether the number of users is a percentage index or not can be determined. Because the number of the users is not a proportion index, the execution main body can determine the Weibull distance of each dimension of the comparison indexes respectively corresponding to at least two user groups in at least one dimension and use the Weibull distance as difference data to obtain a difference data set. Wherein, at least one dimension takes two dimensions as an example, including age and region. Thus, the execution body can determine the distribution 401 and 402 of the number of users of the user group a and the user group B in the dimension of age. On this basis, the weirs distance of the distributions 401 and 402 can be determined, resulting in a first distance 403. Similarly, the distribution 404 and 405 of the number of users in the dimension of the area of the user group a and the user group B may be determined, and the wegener's distance of the distribution 404 and 405 may be determined, resulting in the second distance 406. Such that the difference data set 407 may include the first distance 403 and the second distance 406. On this basis, a preset number of difference data may be selected from the difference data set 407 according to the value of the difference data. In the present scenario, the larger difference data (first distance 403) may be chosen, resulting in a feature dimension 408 (age). Therefore, the dimensionality with larger influence on the comparison index can be determined, and a basis is provided for achieving more targeted information pushing.
As can be seen from fig. 4, compared with the description of some embodiments corresponding to fig. 2, the difference data set is determined in different ways by determining whether the category of the comparison index is the target category, so that the selected difference data is more accurate, and the finally obtained feature dimension is more accurate.
With further reference to fig. 5, as an implementation of the methods illustrated in the above figures, the present disclosure provides some embodiments of an apparatus for determining feature dimensions, which correspond to those of the method embodiments illustrated in fig. 2, and which may be applied in various electronic devices in particular.
As shown in fig. 5, the apparatus 500 for determining feature dimensions of some embodiments comprises: a first determining unit 501, a second determining unit 502, a selecting unit 503 and a third determining unit 504. Wherein the first determining unit 501 is configured to determine at least two user groups to be compared and a comparison index. The second determining unit 502 is configured to determine difference data of the comparison indicators of the at least two user groups in each of the at least one dimension, resulting in a difference data set. The selecting unit 503 selects a predetermined number of difference data from the difference data set according to the value of the difference data. The third determining unit 504 is configured to determine a dimension corresponding to the selected difference data as a feature dimension of at least two user groups.
In some embodiments, specific implementations of the first determining unit 501, the second determining unit 502, the selecting unit 503, and the third determining unit 504 in the apparatus 500 for determining a feature dimension and technical effects brought by the specific implementations may refer to those embodiments corresponding to fig. 2, and are not described herein again.
In an optional implementation of some embodiments, the second determining unit 502 may be further configured to: determining whether the category of the comparison index is a target category; and in response to determining that the category of the contrast index is not the target category, determining the Weibull distance of the contrast index of the at least two user groups in each dimension and using the Weibull distance as difference data to obtain a difference data set.
In an optional implementation of some embodiments, the second determining unit 502 may be further configured to: in response to determining that the category of the contrast index is the target category, determining a Weibull distance and a divergence of the contrast index corresponding to the at least two user groups in each dimension respectively, obtaining a distance set and a divergence set, and obtaining a difference data set based on the distance set and the divergence set.
In an alternative implementation of some embodiments, the at least one dimension is determined by: acquiring user data, wherein the user data comprises user attribute information and user behavior information; removing initial dimensions of which the correlation degrees are larger than a preset threshold value from a plurality of initial dimensions of user data to obtain a plurality of candidate dimensions; discretizing the continuity dimension in the multiple candidate dimensions to obtain at least one dimension.
In an optional implementation of some embodiments, the apparatus 500 may further include: a storage unit and a presentation unit (not shown in the figures). Wherein the storage unit is configured to store the feature dimensions. The presentation is configured to send the feature dimension to a communicatively connected presentation device for presentation of the feature dimension.
In an optional implementation of some embodiments, the apparatus 500 may further include: a fourth determination unit and a sending unit (not shown in the figure). The fourth determining unit is configured to determine, in response to receiving the user request, a user group to which a user corresponding to the user request belongs. The sending unit is configured to determine recommendation information according to the characteristic dimension of the user group to which the user belongs, and send the recommendation information to a terminal corresponding to the user.
In an optional implementation of some embodiments, the apparatus 500 may further include: and an alternative dimension determination unit. Wherein the alternative dimension determination unit is configured to determine an alternative dimension based on the comparison indicator and the at least one dimension; and the second determination unit is further configured to: and determining difference data of the comparison indexes respectively corresponding to the at least two user groups in each dimension of the alternative dimensions to obtain a difference data set.
In some embodiments, the difference of the contrast indexes in different dimensions is determined, and the dimension with large difference is selected as the feature dimension. Therefore, the dimensionality with larger influence on the comparison index can be determined, and a basis is provided for achieving more targeted information pushing.
Referring now to FIG. 6, a block diagram of an electronic device (e.g., backend service 103 in FIG. 1) 600 suitable for use to implement some embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText transfer protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: determining at least two user groups to be compared and a comparison index; determining difference data of the comparison indexes of at least two user groups in each dimension to obtain a difference data set; selecting a preset amount of difference data from the difference data set according to the numerical value of the difference data; and determining the dimension corresponding to the selected difference data as the characteristic dimension of at least two user groups.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first determining unit, a second determining unit, a selecting unit, and a third determining unit. Where the names of the units do not in some cases constitute a limitation of the unit itself, for example, the first determination unit may also be described as a "unit determining at least two user groups to be compared and a comparison index".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
According to one or more embodiments of the present disclosure, there is provided a method of determining feature dimensions, including: determining at least two user groups to be compared and a comparison index; determining difference data of the comparison indexes of at least two user groups in each dimension to obtain a difference data set; selecting a preset amount of difference data from the difference data set according to the numerical value of the difference data; and determining the dimension corresponding to the selected difference data as the characteristic dimension of at least two user groups.
According to one or more embodiments of the present disclosure, determining difference data of a comparison index of at least two user groups in each dimension of at least one dimension, resulting in a difference data set, includes: determining whether the category of the comparison index is a target category; and in response to determining that the category of the comparison index is not the target category, determining the Weibull distance of the comparison index of the at least two user groups in each dimension, and obtaining the distance as difference data to obtain a difference data set.
According to one or more embodiments of the present disclosure, determining difference data of a comparison index of at least two user groups in each dimension of at least one dimension to obtain a difference data set, further includes: in response to determining that the category of the contrast indicator is the target category, determining a Weibull distance and a divergence of the contrast indicators of the at least two user groups in each of the at least one dimension, resulting in a distance set and a divergence set, and resulting in a difference data set based on the distance set and the divergence set.
According to one or more embodiments of the present disclosure, at least one dimension is determined by: acquiring user data, wherein the user data comprises user attribute information and user behavior information; removing initial dimensions of which the correlation degrees are larger than a preset threshold value from a plurality of initial dimensions of user data to obtain a plurality of candidate dimensions; discretizing the continuity dimension in the multiple candidate dimensions to obtain at least one dimension.
In accordance with one or more embodiments of the present disclosure, a method further comprises: storing the characteristic dimension; and sending the characteristic dimension to a display device connected in communication so as to carry out the characteristic dimension.
In accordance with one or more embodiments of the present disclosure, a method further comprises: in response to receiving a user request, determining a user group to which a user corresponding to the user request belongs; and determining recommendation information according to the characteristic dimension of the user group to which the user belongs, and sending the recommendation information to a terminal corresponding to the user.
According to one or more embodiments of the present disclosure, before determining difference data of a comparison indicator of at least two user groups in each dimension of at least one dimension, the method further includes: determining an alternative dimension based on the comparison index and the at least one dimension; and determining difference data of the comparison indexes of the at least two user groups in each dimension to obtain a difference data set, wherein the difference data set comprises: and determining difference data of the comparison indexes respectively corresponding to the at least two user groups in each dimension of the alternative dimensions to obtain a difference data set.
According to one or more embodiments of the present disclosure, there is provided an apparatus for determining feature dimensions, including: a first determination unit configured to determine at least two user groups to be compared and a comparison index; a second determining unit configured to determine difference data of the comparison indexes of the at least two user groups in each dimension to obtain a difference data set; the selecting unit is used for selecting a preset amount of difference data from the difference data set according to the numerical value of the difference data; and the third determining unit is configured to determine the dimension corresponding to the selected difference data as the characteristic dimension of at least two user groups.
According to one or more embodiments of the present disclosure, the second determining unit may be further configured to: determining whether the category of the comparison index is a target category; and in response to determining that the category of the comparison index is not the target category, determining the Weibull distance of the comparison index of the at least two user groups in each dimension, and obtaining the distance as difference data to obtain a difference data set.
According to one or more embodiments of the present disclosure, the second determining unit may be further configured to: in response to determining that the category of the contrast index is the target category, determining a Weibull distance and a divergence of the contrast index corresponding to the at least two user groups in each dimension respectively, obtaining a distance set and a divergence set, and obtaining a difference data set based on the distance set and the divergence set.
According to one or more embodiments of the present disclosure, at least one dimension is determined by: acquiring user data, wherein the user data comprises user attribute information and user behavior information; removing initial dimensions of which the correlation degrees are larger than a preset threshold value from a plurality of initial dimensions of user data to obtain a plurality of candidate dimensions; discretizing the continuity dimension in the multiple candidate dimensions to obtain at least one dimension.
According to one or more embodiments of the present disclosure, an apparatus may further include: a storage unit and a display unit. Wherein the storage unit is configured to store the feature dimensions. A presentation unit configured to send the characteristic dimension to a communicatively connected presentation device for presentation of the characteristic dimension
According to one or more embodiments of the present disclosure, an apparatus may further include: a fourth determination unit and a sending unit (not shown in the figure). The fourth determining unit is configured to determine, in response to receiving the user request, a user group to which a user corresponding to the user request belongs. The sending unit is configured to determine recommendation information according to the characteristic dimension of the user group to which the user belongs, and send the recommendation information to a terminal corresponding to the user.
In an optional implementation of some embodiments, the apparatus may further comprise: and an alternative dimension determination unit. Wherein the alternative dimension determination unit is configured to determine an alternative dimension based on the comparison indicator and the at least one dimension; and the second determination unit is further configured to: and determining difference data of the comparison indexes respectively corresponding to the at least two user groups in each dimension of the alternative dimensions to obtain a difference data set.
According to one or more embodiments of the present disclosure, there is provided an electronic device including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement a method as in any above.
According to one or more embodiments of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the method as any one of the above.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.