CN105095324A - User classification apparatus, user classification method and electronic device - Google Patents

Abstract

The present invention provides a user classification apparatus, a user classification method and an electronic device. The user classification apparatus is used for classifying users in a predetermined domain and comprises: a content searching unit used for searching a content that contains a keyword of the predetermined domain in a predetermined data source to be used as a predetermined domain content, and taking users who publish the predetermined domain content as to-be-classified users; and a user classification unit used for classifying the to-be-classified users according to an attribute, related to the user, of the predetermined domain content. According to the user classification apparatus, the user classification method and the electronic device, provided by the present invention, at least more precision classification can be performed on the users of the predetermined domain.

Description

User classification device, user classification method and electronic equipment

technical field

The invention relates to the field of information processing, in particular to a user classification device, a user classification method and electronic equipment for classifying users in a predetermined field.

Background technique

With the development of Internet technology, more and more users express their opinions, feelings, etc. on matters of interest to them on Internet platforms (such as blogs, microblogs, etc.). How to classify and manage these users, especially users in specific fields, is a hot spot in current research. At present, the analysis and classification of users who post information are basically based on the relationship formed by the degree of attention among users (also known as fan relationship, that is, when a user expresses continuous attention to the degree of attention of other users, the user can It is called a fan of other users, and it constitutes a fan relationship with the user it follows). However, the limitation of this method is that if there is no fan relationship between users, the analysis cannot be performed, and even if there is fan relationship, since the fan relationship cannot directly express the relationship between each user and a certain field, it cannot realize the analysis of the field. Accurate classification of users. Therefore, there is an urgent need for a user classification device, user classification method, and electronic equipment that can accurately classify users in a certain field.

Contents of the invention

A brief overview of the invention is given below in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to identify key or critical parts of the invention nor to delineate the scope of the invention. Its purpose is merely to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.

In view of the above-mentioned defects in the prior art, one object of the present invention is to provide a user classification device, a user classification method and electronic equipment, so as to at least overcome the existing problems.

According to one aspect of the present disclosure, there is provided a user classification device, which is used to classify users in a predetermined field, and the user classification device includes: a content search unit, which is used to search a predetermined data source for keywords containing the predetermined field The content is the content in the predetermined field, and the users who publish the content in the predetermined field are the users to be classified; and a user classification unit is configured to classify the users to be classified according to the user-related attributes of the content in the predetermined field.

According to another aspect of the present disclosure, there is provided a user classification method for classifying users in a predetermined field, the user classification method includes: searching for content containing keywords of the predetermined field in a predetermined data source as the content of the predetermined field , and use the user who publishes the content in the predetermined field as the user to be classified; and classify the user to be classified according to the user-related attributes of the content in the predetermined field.

According to another aspect of the present disclosure, an electronic device is also provided, the electronic device includes the user classification apparatus as described above.

According to other aspects of the present disclosure, there is also provided a program for causing a computer to function as the user classification device as described above.

According to yet another aspect of the present disclosure, there is also provided a corresponding computer-readable storage medium, where a computer program executable by a computing device is stored on the computer-readable storage medium, and when executed, the computer program can enable the computing device to execute the above user Classification.

The above-mentioned user classification apparatus and method and electronic device according to the embodiments of the present disclosure can obtain at least one of the following benefits: by dividing the predetermined field according to the attributes related to the user of the predetermined field content, more accurate user classification can be realized; Using the entity words in the non-predetermined field to deduplicate the entity words in the predetermined field can realize the expansion of the subject words in the predetermined field.

These and other advantages of the present disclosure will be more apparent through the following detailed description of the preferred embodiments of the present disclosure with reference to the accompanying drawings.

Description of drawings

The present disclosure may be better understood by referring to the following description given in conjunction with the accompanying drawings, wherein the same or similar reference numerals are used throughout to designate the same or similar parts. The accompanying drawings, together with the following detailed description, are incorporated in and form a part of this specification, and serve to further illustrate the preferred embodiments of the present disclosure and explain the principles and advantages of the present disclosure. in:

FIG. 1 is a block diagram schematically showing an example structure of a user classification device according to an embodiment of the present disclosure.

FIG. 2 is a block diagram schematically showing an example structure of the user classification unit in FIG. 1 .

Fig. 3 is a block diagram schematically showing another example structure of a user classification device according to an embodiment of the present disclosure.

FIG. 4 is a block diagram schematically showing another example structure of the subject heading determining unit in FIG. 3 .

Fig. 5 is a flowchart schematically illustrating a user classification method according to an embodiment of the present disclosure.

FIG. 6 is a schematic structural diagram showing a possible hardware configuration that can be used to implement a user classification device and a user classification method according to an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present invention will be described below with reference to the accompanying drawings. In the interest of clarity and conciseness, not all features of an actual implementation are described in this specification. It should be understood, however, that in developing any such practical embodiment, many implementation-specific decisions must be made in order to achieve the developer's specific goals, such as meeting those constraints related to the system and business, and those Restrictions may vary from implementation to implementation. Moreover, it should also be understood that development work, while potentially complex and time-consuming, would at least be a routine undertaking for those skilled in the art having the benefit of this disclosure.

Here, it should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only the device structure and/or processing steps closely related to the solution according to the present invention are shown in the drawings, and the Other details not relevant to the present invention are described.

The inventors found that the content published by users can usually reflect the relationship between the user and the predetermined field better than the fan relationship between users. Therefore, the present invention proposes a user classification device for classifying users based on the content published by users. Classification methods and electronic equipment.

FIG. 1 is a block diagram schematically showing an example structure of a user classification device according to an embodiment of the present disclosure.

The user classification device 1 according to the present disclosure is used to classify users in a predetermined field. The predetermined field can be any field such as beauty, automobile, etc., as long as users want to further classify users in this field for easy management. The classified users may be any users who can obtain the information published by them, or may be specific user groups (such as microblog users or blog users, etc.). According to an embodiment of the present disclosure, the user classification device 1 can classify users of microblog users in a predetermined field.

As shown in Figure 1, the user classification device 1 includes: a content search unit 10, which is used to search the content containing the subject words of the predetermined field in the predetermined data source as the content of the predetermined field, and use the user who publishes the content of the predetermined field as the content to be classified users; and a user classification unit 20, configured to classify the users to be classified according to the user-related attributes of the content in the predetermined field.

According to the present disclosure, the content search unit 10 may search for content containing subject words of a predetermined field in a predetermined data source such as a network, a specific database. The predetermined data source may be, for example, a database including microblog information in various portal websites. The subject headings in the predetermined field are words or phrases specific to the predetermined field. According to the embodiments of the present disclosure, subject headings can be specified for the predetermined field, for example, for the automotive field, "gearbox", "brake" and the like can be specified as the subject headings.

By searching a predetermined data source, the content search unit 10 can obtain the content containing the subject words of the predetermined field as the content of the predetermined field, and use the user who released the content of the predetermined field as the user to be classified in the predetermined field for subsequent processing Classify and manage these users in .

According to an embodiment of the present disclosure, when the user classification device 1 is used to classify microblog users, the content search unit 10 may search for microblog content containing subject words in the predetermined field in predetermined data sources as the Predetermined field content, and the microblog users who publish microblogs containing the predetermined field keywords are regarded as users to be classified.

After obtaining the users to be classified in the predetermined field through the content search unit 10, the user classification unit 20 further classifies the users to be classified according to the attributes related to the users in the predetermined field content, so that the users engaged in the predetermined field Users of related jobs can manage their potential customers in a targeted manner according to the classification of users in the predetermined field by the user classification unit 20 .

According to an embodiment of the present disclosure, the user-related attributes of the content in the predetermined field may include a behavior pattern of users to be classified publishing the content in the predetermined field and propagation characteristics of the content in the predetermined field. The behavior pattern of the user to be classified publishing the content in the predetermined field can indicate the degree of interest of the user to be classified in the content of the predetermined field to a certain extent; the propagation characteristics of the content in the predetermined field can indicate the influence of the user to be classified who publishes the content in the predetermined field . Classify users to be classified based on the behavior pattern of users publishing the content in the predetermined field and the propagation characteristics of the content in the predetermined field, which is conducive to targeted management of classified users according to their influence and interest .

According to an embodiment of the present disclosure, the behavior pattern of the user to be classified publishing the content in the predetermined field may include the latest time and frequency of the content in the predetermined field published by the user to be classified; The number of times the domain content is forwarded and/or commented is determined.

According to a preferred embodiment of the present disclosure, whenever a keyword in the predetermined field is mentioned once in the content of the predetermined field, the frequency at which the user to be classified publishes the content of the predetermined field is increased once. Specifically, when a predetermined field content released by a certain user to be classified includes multiple subject words in the predetermined field, the frequency of the predetermined field content published by the user to be classified is recorded as the frequency of the contained subject words The same number of multiple times, for example, when a microblog contains 6 keywords in the automotive field (including the same or different keywords), then the frequency of the user to be classified to publish the content of the automotive field is increased by 6 times .

Those skilled in the art can understand that the later the latest time when the user to be classified publishes the content in the predetermined field, the greater the possibility that the user to be classified is still interested in the content in the predetermined field. If a user to be categorized latest published content in the predetermined field 6 months ago, it indicates that the user was once interested in the predetermined field, but may not be interested now.

Those skilled in the art can also understand that the more times content in a predetermined field of a certain user to be classified is forwarded and/or commented on, the greater the influence of the user to be classified on the predetermined field is.

According to the user-related attributes of the content in the predetermined field such as the behavior pattern of the user to be classified publishing the content in the predetermined field and the propagation characteristics of the content in the predetermined field, the user classification unit 20 can further classify the users in the predetermined field, for example Classified as "Recently interested and influential users", "Recently not interested but influential users", "Recently very interested but not influential users", "Recently not interested and not influential users ", so as to conduct precise analysis and targeted management for each type of user.

FIG. 2 is a block diagram schematically showing an example structure of the user classification unit in FIG. 1 .

As shown in Figure 2, the user classification unit 20 includes: a level determination module 201, which is used to divide the latest time parameter of the user's published content into M levels, divide the frequency parameter of the user's content into N levels, and divide the content propagation characteristic parameters into M levels. Divided into P levels, wherein M, N and P are all integers greater than 1, thereby determining M×N×P user levels; and a user classification module 202, which is used to publish the predetermined field content according to each user to be classified The latest time and frequency of the user and the dissemination characteristics of the content in the predetermined field published by it, the user to be classified is classified into one of the M×N×P user levels.

According to an embodiment of the present disclosure, M, N, and P can all be set to 2. That is, for example, the latest time parameter R of the content published by the user can be divided into two levels (for example, a time threshold can be set, and the latest time parameter can be divided into two levels greater than or equal to the time threshold and less than the time threshold, i.e. long and short ), divide the frequency parameter F of the content published by the user into two levels (for example, the frequency threshold can be set, so that the frequency parameter can be divided into two levels greater than or equal to the frequency threshold and less than the frequency threshold, that is, two levels of high frequency and low frequency), and the content The propagation characteristic parameter I is divided into 2 levels (for example, according to the number of forwarding times and comment times of the predetermined content, determine the influence of the user to be classified who publishes the predetermined content in the predetermined field, and according to the influence, the propagation characteristic parameter is divided into Greater than or equal to the propagation threshold and less than the propagation threshold two levels). Any appropriate method in the prior art can be used to determine the influence of the user to be classified who publishes the predetermined content in the predetermined field based on the number of reposts and comments of the predetermined content. For the sake of simplicity, the specific process of determining the influence is not described here. Let me repeat.

Table 1 shows 8 user levels when the above parameters M, N, P are all set to 2.

Table 1

Although it has been shown above that the level determination module 201 sets the latest time parameter M, the frequency parameter N, and the content propagation characteristic parameter P to 2, thereby dividing them into 2 levels respectively, the present disclosure is not limited thereto, for example, Set M, N, and P to other numerical values (for example, 5). In addition, M, N, and P may also be set to different numerical values respectively.

In addition, the level determination module can also set thresholds for each parameter including the latest time parameter M, the frequency parameter N and the content propagation characteristic parameter P setting threshold parameters, so that the user classification module 202 can classify each user to be classified. For example, when the parameters M, N, and P are equally divided into 2 levels, the threshold for the latest time parameter M can be set to, for example, 3 months, and the threshold for the frequency parameter N can be set to, for example, 5 and so on.

After the level determination module 201 has determined the M×N×P user levels, the user classification module 202 is based on the latest time and frequency of each user to be classified publishing the content in the predetermined field and the propagation characteristics of the content in the predetermined field published by the user, The user to be classified is classified into one of the M×N×P user classes. For example, when the parameters M, N, and P are divided into 2 levels, for users to be classified whose latest time is short from the current time, high frequency, and influential, they can be divided into table The first category shown in Table 1, similarly, each user to be classified can be classified into one of the eight types of users shown in Table 1.

Although it is described above that the subject words in the predetermined field are obtained through the user-specified manner, so as to search for content containing the subject words as the content in the predetermined field, the present disclosure is not limited thereto, for example, the subject of the predetermined field can also be determined according to predetermined rules word.

Fig. 3 is a block diagram schematically showing another example structure of a user classification device according to an embodiment of the present disclosure.

As shown in Figure 3, in addition to including the content search unit 10 and the user classification unit 20 similarly to the user classification device 1 of Figure 1, the user classification device 2 also includes: a subject word determination unit 30 for determining the content of the predetermined field A subject word so that the content search unit searches for content containing the subject term as content in a predetermined field.

FIG. 4 is a block diagram schematically showing another example structure of the subject heading determining unit in FIG. 3 .

As shown in Figure 4, the subject word determination unit 30 includes: a first entity word extraction module 301, which is used to extract entity words with a frequency higher than the first threshold in the content issued by a specific user in the predetermined field to form a first entity Word group: The second entity word extraction module 302 is used to extract entity words with a frequency higher than the second threshold from content published by a specific user in a non-predetermined field irrelevant to the predetermined field to form a second entity word group; And the subject word determining module 303, for using the entity words in the second entity word group to carry out deduplication to the entity words in the first entity word group, and the entity words in the first entity word group after deduplication Entity words are used as subject words in the predetermined field.

According to the present disclosure, the specific users in the predetermined field are users whose influence exceeds a third threshold in the predetermined field, and the specific users in the non-predetermined field are users whose influence exceeds a fourth threshold in the non-predetermined field. In the case where it is desired to classify microblog users in a predetermined field, the specific user in the predetermined field may be, for example, a big V user (usually a user whose number of fans is greater than a set threshold, that is, an influential user).

The first entity word extraction module 301 can extract entity words whose frequency is higher than the first threshold in the published content of the predetermined field to form a first entity word group; the second entity word extraction module 302 is used for combining with the Entity words whose frequencies are higher than the second threshold are extracted from all content published by big V users in non-predetermined fields irrelevant to the predetermined field to form a second entity word group.

For example, in the case of desiring to classify microblog users in the field of outdoor sports, the first entity word extraction module 301 can extract the content published by the big V user in the field of outdoor sports according to word frequency. Entity words whose occurrence frequency in the content is higher than the first threshold. For example, the first entity word extraction module 301 may extract entity words whose frequency of occurrence is higher than the first threshold from all content published by a big V user within a predetermined time period (for example, the last week). Similarly, the second entity word extraction module 302 can extract entity words whose occurrence frequency is higher than the second threshold in the content published by the big V user in the field of non-outdoor sports according to word frequency.

According to the present disclosure, the first threshold and the second threshold can be arbitrarily set according to, for example, requirements for obtaining accuracy of users to be classified. In addition, those skilled in the art can also understand that the first threshold and the second threshold can be set to be the same, or can be set to be different.

Usually, the content published by big V users in the predetermined field includes both entity words in the predetermined field and entity words in non-predetermined fields. For example, these big V users will also publish hot entities related to current affairs, sports, finance, etc. word. Based on this, by extracting entity words whose word frequency is higher than the first threshold, and by extracting entity words that are usually not related to the predetermined field from content published by users in non-predetermined fields such as big V users, it is possible to more accurately Obtain subject headings for a predetermined field.

Taking the predetermined field as the field of outdoor sports as an example, the first entity word extraction module 301 can extract entity words from the content published by one of the big V users in the field of outdoor sports, and can obtain the following entity words: house price, runaway, Champions League, self-driving , Jingkai Expressway, cycling, outing, Chelsea, resume, outing. For example, by extracting entity words from content posted by multiple big V users in the field of outdoor sports, the first entity word group including the above entity words can be obtained.

The second entity word extraction module 302 can obtain the following entity words by extracting entity words from the content released by one of the big V users in the field of non-outdoor sports: Kunming, People's Daily, house price, Beijing-Kaikai Expressway, resume, earthquake, Champions League, Beckham, Chelsea, etc. For example, by extracting entity words from content posted by multiple big V users in the field of non-outdoor sports, a second entity word group including, for example, the above entity words can be obtained.

Then, the subject word determination module 303 uses the entity words in the second entity word group related to the non-predetermined field to deduplicate the entity words in the first entity word group related to the predetermined field, and deduplicate the first entity word group after deduplication. The entity words in the entity word group are used as the subject words of the predetermined field.

For example, in the above example, the keyword determination module 303 may obtain "runaway, self-driving, cycling, outing, outing" as the keyword in the field of outdoor sports by removing duplicates.

Then, the content search unit 10 can use the keywords in the predetermined field determined by the keyword determination module to search for content containing the keywords, and obtain users to be classified in the predetermined field, so that the users to be classified can be classified by the user classification unit 20 .

After the users in the predetermined field are classified by the user classification device according to the embodiment of the present invention, corresponding analysis and management can be performed on the users of each classification, so that a more accurate analysis of massive data can be realized, and another A dimension of user attributes for further processing of massive data.

According to an embodiment of the present disclosure, a user classification method is also provided. An exemplary process of the user classification method is described below in conjunction with FIG. 5 .

As shown in FIG. 5 , the processing flow 500 of the user classification method according to the embodiment of the present disclosure starts at S510, and then performs the processing of S520.

In step S520 , search the predetermined data source for the content containing the subject words of the predetermined field as the predetermined field content, and use the users who publish the predetermined field content as to be classified. For example, step S520 may be implemented by executing the processing of the content acquisition unit 10 described with reference to FIGS. 1-4, for example, and its description is omitted here. Then execute S530.

In step S530, the users to be classified are classified according to the user-related attributes of the content in the predetermined field. The user-related attributes of the content in the predetermined field may include, for example, the behavior pattern of the user to be classified publishing the content in the predetermined field and the propagation characteristics of the content in the predetermined field. For example, step S530 may be implemented by executing the processing of the user classification unit 20 described with reference to FIGS. 1-4 , and its description is omitted here. Then execute S540.

The processing flow 500 ends at S540.

According to an embodiment of the present disclosure, before step S530 is performed, a step of determining keywords in the predetermined field may be included, for example, this step may include extracting keywords with a frequency higher than The entity words of the first threshold constitute the first entity word group; the entity words whose frequency is higher than the second threshold are extracted from content published by specific users in non-predetermined fields irrelevant to the predetermined field to form the second entity word group ; and use the entity words in the second entity word group to remove the weight of the entity words in the first entity word group, and use the entity words in the first entity word group after deduplication as the predetermined field Subject headings. The various steps of determining the subject headings in the predetermined field can be implemented by referring to the processing of the first entity word extraction module, the second entity word extraction module and the subject heading determination module described in FIG. 4 , and the detailed description thereof is omitted here.

Compared with the prior art, the user classification device and user classification method according to the present disclosure have at least one of the following advantages: by dividing the predetermined field according to the attributes related to the user in the predetermined field content, more accurate user classification can be realized ;Using the entity words in the non-predetermined field to deduplicate the entity words in the predetermined field can realize the expansion of the subject words in the predetermined field.

In addition, an embodiment of the present disclosure also provides an electronic device configured to include the user classification apparatus 1 as described above. The electronic device may be, for example, any one of the following devices: a mobile phone; a computer; a tablet computer; and a personal digital assistant. Correspondingly, the electronic device can have the beneficial effects and advantages of the above-mentioned user classification device.

Each component unit, subunit, etc. in the user classification device according to the embodiments of the present disclosure (such as the user classification device shown in FIGS. 1-4 ) may be configured by software, firmware, hardware or any combination thereof. In the case of realization by software or firmware, the program constituting the software or firmware can be installed from a storage medium or a network to a machine with a dedicated hardware structure, and when the machine is installed with various programs, it can execute the above-mentioned constituent units and sub-units. Various functions of the unit.

FIG. 6 is a schematic structural diagram showing a hardware configuration of a possible processing device that can be used to implement the user classification device and method according to the embodiments of the present disclosure.

In FIG. 6 , a central processing unit (CPU) 601 executes various processes according to programs stored in a read only memory (ROM) 602 or loaded from a storage section 608 to a random access memory (RAM) 603 . In the RAM 603 , data required when the CPU 601 executes various processes and the like is also stored as necessary. The CPU 601 , ROM 602 , and RAM 603 are connected to each other via a bus 604 . The input/output interface 605 is also connected to the bus 604 .

The following components are also connected to the input/output interface 605: an input section 606 (including a keyboard, a mouse, etc.), an output section 607 (including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.) , a storage section 608 (including a hard disk, etc.), a communication section 609 (including a network interface card such as a LAN card, a modem, etc.). The communication section 609 performs communication processing via a network such as the Internet. A driver 610 may also be connected to the input/output interface 605 as needed. A removable medium 611 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. can be mounted on the drive 610 as needed, so that a computer program read therefrom can be installed into the storage section 608 as needed.

In the case where the above-described series of processing is realized by software, the program constituting the software can be installed from a network such as the Internet or from a storage medium such as the removable medium 611 .

Those skilled in the art should understand that such a storage medium is not limited to the removable medium 611 shown in FIG. 6 in which the program is stored and distributed separately from the device to provide the program to the user. Examples of the removable medium 611 include magnetic disks (including floppy disks), optical disks (including compact disk read only memory (CD-ROM) and digital versatile disks (DVD)), magneto-optical disks (including MiniDisc (MD) (registered trademark)), and semiconductor memory. Alternatively, the storage medium may be the ROM 602, a hard disk contained in the storage section 608, or the like, in which the programs are stored and distributed to users together with devices containing them.

In addition, the present disclosure also proposes a program product storing machine-readable instruction codes. When the above instruction code is read and executed by a machine, the above user classification method according to the embodiment of the present disclosure can be executed. Accordingly, various storage media such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc. for carrying such program products are also included in the disclosure of the present disclosure.

In the above description of specific embodiments of the present disclosure, features described and/or illustrated for one embodiment can be used in one or more other embodiments in the same or similar manner, and features in other embodiments Combination or replacement of features in other embodiments.

In addition, the methods in the various embodiments of the present disclosure are not limited to being executed in the time sequence described in the specification or shown in the drawings, and may also be executed in other time sequences, in parallel or independently. Therefore, the execution order of the methods described in this specification does not limit the technical scope of the present disclosure.

In addition, obviously, each operation process of the above-mentioned method according to the present disclosure can also be implemented in the form of computer-executable programs stored in various machine-readable storage media.

Moreover, the object of the present disclosure can also be achieved in the following manner: the storage medium storing the above-mentioned executable program code is directly or indirectly provided to a system or device, and the computer or central processing unit (CPU) in the system or device Read and execute the above program code.

At this time, as long as the system or device has the function of executing the program, the embodiment of the present disclosure is not limited to the program, and the program can also be in any form, for example, an object program, a program executed by an interpreter, or a program provided to an operating system. script programs, etc.

The above-mentioned machine-readable storage media include, but are not limited to: various memories and storage units, semiconductor devices, magnetic disk units such as optical, magnetic and magneto-optical disks, and other media suitable for storing information, and the like.

In addition, the client information processing terminal can also implement the embodiments of the present disclosure by connecting to a corresponding website on the Internet, and downloading and installing the computer program code according to the present disclosure into the information processing terminal and then executing the program.

To sum up, in the embodiments according to the present disclosure, the present disclosure provides the following solutions, but not limited thereto:

Scheme 1. A user classification device is used to classify users in a predetermined field, and the user classification device includes:

A content search unit, configured to search for content containing keywords in the predetermined field in a predetermined data source as content in the predetermined field, and use users who publish content in the predetermined field as users to be classified; and

The user classification unit is configured to classify the users to be classified according to the user-related attributes of the content in the predetermined field.

Solution 2. The device for classifying users according to solution 1, wherein the content search unit is configured to search for microblog content containing keywords in the predetermined field in predetermined data sources as the content in the predetermined field.

Solution 3. The device for classifying users according to solution 1 or 2, wherein the user-related attributes of the content in the predetermined field include the behavior pattern of the user to be classified publishing the content in the predetermined field and the content in the predetermined field propagation characteristics.

Solution 4. The user classification device according to solution 3, wherein,

The behavior pattern of the user to be classified publishing the content in the predetermined field includes the latest time and frequency of the content in the predetermined field published by the user to be classified, and

The propagation characteristic of the content in the predetermined field is determined by the number of times the content in the predetermined field is forwarded and/or commented on.

Solution 5. The user classification device according to solution 4, wherein the user classification unit includes:

The level determination module is used to divide the latest time parameter of the content released by the user into M grades, divide the frequency parameter of the content released by the user into N grades, and divide the content propagation characteristic parameters into P grades, wherein M, N and P are all is an integer greater than 1, thereby determining M×N×P user levels; and

The user classification module is used to classify the users to be classified into the M×N×P according to the latest time and frequency of publishing the content in the predetermined field and the propagation characteristics of the content in the predetermined field published by each user to be classified in one of the user levels.

Solution 6. The user classification device according to solution 1 or 2, further comprising: a subject term determining unit, configured to determine a subject term in the predetermined field so that the content search unit searches for content containing the subject term as content in the predetermined field, The subject heading determination unit includes:

The first entity word extraction module is used to extract entity words with a frequency higher than the first threshold from content published by specific users in the predetermined field to form a first entity word group;

The second entity word extraction module is used to extract entity words with a frequency higher than a second threshold from the content published by a specific user in a non-predetermined field irrelevant to the predetermined field to form a second entity word group; and

The subject word determination module is used to use the entity words in the second entity word group to deduplicate the entity words in the first entity word group, and remove the entity words in the first entity word group after deduplication as the subject heading for the intended field.

Solution 7. The user classification device according to solution 6, wherein the specific user in the predetermined field is a user whose influence in the predetermined field exceeds a third threshold, and the specific user in the non-predetermined field is a user whose influence in the non-predetermined field exceeds Users of the fourth threshold.

Scheme 8. A user classification method, which is used to classify users in a predetermined field, and the user classification method includes:

Search for content containing keywords in the predetermined field in the predetermined data source as the content in the predetermined field, and use users who publish the content in the predetermined field as users to be classified; and

The users to be classified are classified according to the user-related attributes of the content in the predetermined field.

Solution 9. The user classification method according to solution 8, wherein the predetermined data source is searched for microblog content containing keywords in the predetermined field as the content in the predetermined field.

Solution 10. The user classification method according to solution 8 or 9, wherein the user-related attributes of the content in the predetermined field include the behavior pattern of the user to be classified to publish the content in the predetermined field and the content in the predetermined field propagation characteristics.

Solution 11. The user classification method according to solution 10, wherein,

The behavior pattern of the user to be classified publishing the content in the predetermined field includes the latest time and frequency of the content in the predetermined field published by the user to be classified, and

The propagation characteristic of the content in the predetermined field is determined by the number of times the content in the predetermined field is forwarded and/or commented on.

Solution 12. The user classification method according to solution 11, wherein classifying the users to be classified includes:

Divide the most recent time parameter of the content published by the user into M grades, divide the frequency parameter of the content published by the user into N grades, and divide the content propagation characteristic parameters into P grades, wherein M, N and P are all integers greater than 1, Thereby determining M×N×P user levels; and

According to the latest time and frequency when each user to be classified publishes the content in the predetermined field and the dissemination characteristics of the content in the predetermined field published by the user, the user to be classified is classified into one of the M×N×P user levels.

Solution 13, according to the user classification method described in solution 8 or 9, further comprising determining the subject words of the predetermined field so that the content search unit searches for content containing the subject words as the content of the predetermined field, wherein determining the subject words of the predetermined field includes :

Extracting entity words with a frequency higher than a first threshold from content published by a specific user in the predetermined field to form a first entity word group;

Extracting entity words with a frequency higher than a second threshold from content published by specific users in a non-predetermined field that is irrelevant to the predetermined field to form a second entity word group; and

Use the entity words in the second entity word group to deduplicate the entity words in the first entity word group, and use the entity words in the first entity word group after deduplication as the subject words in the predetermined field .

Solution 14. The user classification method according to solution 13, wherein the specific user in the predetermined field is a user whose influence in the predetermined field exceeds the third threshold, and the specific user in the non-predetermined field is a user whose influence in the non-predetermined field exceeds Users of the fourth threshold.

Solution 15. An electronic device, comprising the device for classifying users according to any one of solutions 1-7.

Item 16. The electronic device according to item 15, wherein the electronic device is a mobile phone, a computer, a tablet computer, or a personal digital assistant.

Finally, it should also be noted that in this disclosure, relational terms such as first and second are only used to distinguish one entity or operation from another, and do not necessarily require or imply these No such actual relationship or order exists between entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Although the present disclosure has been disclosed above through the description of specific embodiments of the present disclosure, it should be understood that those skilled in the art can design various modifications, improvements or equivalents to the present disclosure within the spirit and scope of the appended claims . These modifications, improvements or equivalents should also be considered to be included in the scope of protection claimed by the present disclosure.

Claims (10)

1. A user classification device is used to classify users in predetermined fields, the user classification device comprising: A content search unit, configured to search for content containing keywords in the predetermined field in a predetermined data source as content in the predetermined field, and use users who publish content in the predetermined field as users to be classified; and The user classification unit is configured to classify the users to be classified according to the user-related attributes of the content in the predetermined field. 2. The user classification device according to claim 1, wherein the content search unit is used to search for microblog content containing keywords in the predetermined field as the content in the predetermined field in a predetermined data source. 3. The user classification device according to claim 1 or 2, wherein the user-related attributes of the content in the predetermined field include the behavior pattern of the user to be classified publishing the content in the predetermined field and the content in the predetermined field propagation characteristics. 4. The user classification device according to claim 3, wherein, The behavior pattern of the user to be classified publishing the content in the predetermined field includes the latest time and frequency of the content in the predetermined field published by the user to be classified, and The dissemination characteristic of the content in the predetermined field is determined by the number of times the content in the predetermined field is forwarded and/or commented on. 5. The user classification device according to claim 4, wherein the user classification unit comprises: The level determination module is used to divide the latest time parameter of the content released by the user into M grades, divide the frequency parameter of the content released by the user into N grades, and divide the content propagation characteristic parameters into P grades, wherein M, N and P are all is an integer greater than 1, thereby determining M×N×P user levels; and The user classification module is used to classify the users to be classified into the M×N×P according to the latest time and frequency of publishing the content in the predetermined field and the propagation characteristics of the content in the predetermined field published by each user to be classified in one of the user levels. 6. The user classification device according to claim 1 or 2, further comprising: a subject term determination unit, used to determine the subject term in the predetermined field so that the content search unit searches for content containing the subject term as the predetermined field content, The subject heading determination unit includes: The first entity word extraction module is used to extract entity words with a frequency higher than the first threshold from content published by specific users in the predetermined field to form a first entity word group; The second entity word extraction module is used to extract entity words with a frequency higher than a second threshold from the content published by a specific user in a non-predetermined field irrelevant to the predetermined field to form a second entity word group; and The subject word determination module is used to use the entity words in the second entity word group to deduplicate the entity words in the first entity word group, and remove the entity words in the first entity word group after deduplication as the subject heading for the intended field. 7. The user classification device according to claim 6, wherein the specific user in the predetermined field is a user whose influence exceeds a third threshold in the predetermined field, and the specific user in the non-predetermined field is a user whose influence exceeds a third threshold in the non-predetermined field. Users of the fourth threshold. 8. A user classification method for classifying users in a predetermined field, the user classification method comprising: Search for content containing keywords in the predetermined field in the predetermined data source as the content in the predetermined field, and use users who publish the content in the predetermined field as users to be classified; and The users to be classified are classified according to the user-related attributes of the content in the predetermined field. 9. An electronic device, comprising the device for classifying users according to any one of claims 1-7. 10. The electronic device according to claim 9, wherein the electronic device is a mobile phone, a computer, a tablet computer, or a personal digital assistant.