User tag setting method, device and electronic device based on big data

Abstract

The disclosed embodiment discloses a user tag setting method, device and electronic device based on big data, wherein the user tag setting method based on big data includes: dividing users into multiple communities based on the acquired user behavior data, thereby obtaining user communities; extracting the same features of the user communities, and obtaining feature vectors based on the same features; obtaining corresponding tag information based on the feature vectors; and setting tags for users based on the tag information and user communities. By dividing users into multiple communities, extracting the same features of the user communities, and setting tags for the corresponding communities, the user communities are calculated as a whole, avoiding calculations for each user, thereby achieving the purpose of reducing the amount of calculations.

Description

Technical Field

[0001] The present disclosure relates to the field of big data, and in particular to a user tag setting method, device and electronic device based on big data. Background Art

[0002] With the continuous development of the Internet, online lifestyles have gradually penetrated into all aspects of people's lives. People have begun to express their opinions, shop online, and browse on the Internet. These online behaviors are characteristic resources of users, and to a large extent reflect the interests and preferences of users. The interests of users are in a dynamic process. Objective conditions such as the age, marital status, and environment of users, as well as subjective conditions such as the level of education, personality, and personal preferences of users, will affect their interests. This makes the information resources that users generate on the Internet, which are individual representations, not only huge in quantity but also have a certain timeliness.

[0003] However, as the number of users and tags increases, the amount of calculation increases, resulting in more and more computing power required. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a user tag setting method, device and electronic device based on big data, which at least partially solve the problem of large amount of calculation existing in the prior art.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for setting user tags based on big data, including:

[0006] Based on the acquired user behavior data, users are divided into multiple communities to obtain user communities. Users with the same or similar behaviors are grouped together according to their behavior data. User communities are established based on users' interests in tagged resources. The interests in tagged resources are determined by calculating the frequency of user tags. That is, the higher the frequency of users tagging resources with the same tag, the higher the probability that users belong to the same user community.

[0007] Extracting common features of the user community, and obtaining a feature vector based on the common features;

[0008] Obtain corresponding label information based on the feature vector;

[0009] The user is tagged based on the tag information and the user community.

[0010] Optionally, dividing users into multiple communities based on the acquired user behavior data to obtain user communities includes:

[0011] Obtain neighbor relationships, friend relationships, preference relationships, and member relationships based on user behavior data;

[0012] Divide users into communities based on neighbor relationships, friend relationships, preference relationships, and membership relationships;

[0013] The preference relationship is to calculate the frequency of different users using the same tag to mark resources.

[0014] The higher the frequency of the user using the same tag to annotate resources, the higher the user's preference for the tag;

[0015] In the preference relationship judgment, the user preference stability is obtained, and the obtaining of the user preference stability includes calculating the proportion of the frequency of the user using the tag to the frequency of all tags used by the user in a set time. The larger the proportion, the better the user preference stability.

[0016] Optionally, extracting the same features of the user community includes:

[0017] Compare the user's historical feature library with the features of the user community, and extract the user community features based on the comparison results;

[0018] Compare the extraction results and get the same features;

[0019] If the corresponding user community feature is not found in the user history feature library, the user community feature is aggregated and the aggregated result is added to the user history feature library.

[0020] Optionally, the user history feature library is compared with the features of the user community, and user community features are extracted according to the comparison results, including:

[0021] Compare the correlation strength between the features of the user community and the features in the user feature library one by one;

[0022] The association strength is obtained based on the association strength model, which is:

[0023]

[0024] Among them, f is the strength, a and b are weight values, x is the user community feature, k i is the feature in the user feature library, Q(x,k i ) is the positive correlation coefficient between the user community features and the features in the user feature library, H(x,k i ) is the negative correlation coefficient between the user community features and the features in the user feature library, and j is a constant.

[0025] Optionally, the weight value a is based on get.

[0026] Optionally, the weight value b is based on get.

[0027] In a second aspect, the embodiment of the present disclosure further provides a user tag setting device based on big data, including: a community module, used to divide users into multiple communities based on the acquired user behavior data, thereby obtaining a user community;

[0028] A vector module, used to extract common features of the user community and obtain a feature vector based on the common features;

[0029] A label module is used to obtain corresponding label information based on the feature vector;

[0030] The tag setting module is used to set tags for users based on the tag information and the user community.

[0031] Optionally, the community module is further used to obtain neighbor relationships, friend relationships, preference relationships and member relationships based on user behavior data;

[0032] Users are divided into communities based on neighbor relationships, friend relationships, preference relationships, and membership relationships.

[0033] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0034] at least one processor; and,

[0035] a memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the user tag setting methods based on big data described in the first aspect.

[0037] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute any of the user tag setting methods based on big data described in the first aspect.

[0038] The embodiments of the present disclosure provide a user label setting method, device, electronic device and computer-readable storage medium based on big data, wherein the user label setting method based on big data: by dividing users into multiple communities, and extracting the same features of the user communities, setting labels for the corresponding communities, and performing overall calculations on the user communities, calculations for each user are avoided, thereby achieving the purpose of reducing the amount of calculations.

[0039] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A flowchart of a user tag setting method based on big data provided by an embodiment of the present disclosure;

[0042] Figure 2 A principle block diagram of a user tag setting device based on big data provided by an embodiment of the present disclosure;

[0043] Figure 3 A functional block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0045] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0046] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0047] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0048] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0049] For ease of understanding, Figure 1 As shown, this embodiment discloses a user tag setting method based on big data, including:

[0050] Step S101: users are divided into multiple communities based on the acquired user behavior data, thereby obtaining user communities. Users with the same or similar behaviors are grouped together according to the user behavior data. User communities are established based on the user's interest in the tagged resources. The interest in the tagged resources is determined by calculating the frequency of user tags. That is, the higher the frequency of users tagging resources with the same tag, the higher the probability that the users belong to the same user community.

[0051] That is, users with the same or similar behaviors are grouped together based on their behavioral data, such as dividing the elderly between 50 and 55 years old into a community, or dividing people around 40 years old who like self-driving tours into a community.

[0052] For example, when viewing articles on WeChat official accounts, users can add corresponding tags to their favorite articles. The server normalizes the collected user tags. For example, tags such as cooking and recipes can be normalized to the unified tag of catering. The user's preference is counted by the frequency of user tag use. For example, if a user adds tags to the official account 10 times a day, and the catering tag is used 8 times, the user's frequency of using user tags is 0.8. If another user adds tags 5 times a day and uses the catering tag 4 times, the user's frequency of using user tags is also 0.8. Then the probability that these two users belong to the same user community is 100%.

[0053] Step S102: extracting common features of the user community, and obtaining a feature vector based on the common features;

[0054] That is, the same features can be extracted based on historical user behavior data. For example, in the elderly community aged 50 to 55 in the historical user behavior data, for the elderly who like dancing, dancing is the same feature. Among people around 40 years old who like self-driving tours, the same brand and model of vehicles are the same features, such as RVs.

[0055] The calculation of the feature vector can determine the training data set from the historical data based on the historical user behavior data, and the historical user behavior data includes the historical data that the user has clicked. Based on the training data set, the feature vector of the historical media data is obtained using the vector prediction model. Since the type identifier can reflect the content characteristics of the historical data, the type identifiers included in the training data set are statistically analyzed, and the feature vector of the type identifier is determined based on the feature vector of the historical data corresponding to the type identifier. The feature vector of the type identifier can reflect the content characteristics of the historical data. If the target data for which the feature vector is not calculated is obtained, and the target data is similar to the historical data with the same type identifier, the feature vector of the target data can be calculated based on the feature vector of the type identifier of the target data.

[0056] Step S103: Obtain corresponding label information based on the feature vector;

[0057] The extracted parameters are compared with the parameters in the feature library, and the corresponding label information is obtained according to the comparison result. If the comparison result is a self-driving RV, it is marked as a self-driving RV.

[0058] A user interest model is established based on cluster analysis. The feature vector is input into the user interest model, and the corresponding tag information can be calculated. In establishing the user interest model, the candidate tag set of the target user is first obtained. On this basis, the naive Bayes method is applied, and the user's preference for a specific tag is calculated by combining the tag resource matrix and the user tag matrix. After comprehensively considering the influence of each tag, the recommendation degree for the user tag is finally obtained. Using content filtering analysis, the closeness between the feature vector and the tag is first calculated, and then the closeness of the user's feature vector is summed up to obtain the closeness between the user's feature vector and the tag. Then the correlation between each tag is calculated and the related tags are clustered. After summing up, the closeness between the user and the clustered tags is obtained. At the same time, the tag information to be marked is calculated based on each clustered tag, and the tag information recommendation order is obtained by combining the previous closeness.

[0059] Step S104: Setting tags for users based on the tag information and the user community.

[0060] Based on the user communities of self-driving RVs and those around 40 years old, all users of self-driving RVs in the user community of 40 years old who are engaged in self-driving tours are marked with the same label.

[0061] Optionally, dividing users into multiple communities based on the acquired user behavior data to obtain user communities includes:

[0062] Obtain neighbor relationships, friend relationships, preference relationships, and member relationships based on user behavior data;

[0063] Divide users into communities based on neighbor relationships, friend relationships, preference relationships, and membership relationships;

[0064] The preference relationship is to calculate the frequency of different users using the same tag to mark resources.

[0065] The higher the frequency of the user using the same tag to annotate resources, the higher the user's preference for the tag;

[0066] In the preference relationship judgment, the user preference stability is obtained, and the user preference stability is obtained by calculating the proportion of the frequency of the user's use of tags to the frequency of all tags used by the user in the set time. The larger the proportion, the better the user preference stability. The set time is usually one day.

[0067] The stability of user preferences reflects the dynamic changes of user preferences under the influence of time. This embodiment uses the fact that each user preference has a process of forgetting decay and memory strengthening, and uses this to characterize the relationship between the time factor and the tag weight, and further derives stability.

[0068] Optionally, extracting the same features of the user community includes:

[0069] Compare the user's historical feature library with the features of the user community, and extract the user community features based on the comparison results;

[0070] Compare the extraction results and get the same features;

[0071] If the corresponding user community feature is not found in the user history feature library, the user community feature is aggregated and the aggregated result is added to the user history feature library.

[0072] Optionally, the user history feature library is compared with the features of the user community, and user community features are extracted according to the comparison results, including:

[0073] Compare the correlation strength between the features of the user community and the features in the user feature library one by one;

[0074] The association strength is obtained based on the association strength model, which is:

[0075]

[0076] Among them, f is the strength, a and b are weight values, x is the user community feature, k i is the feature in the user feature library, Q(x,k i ) is the positive correlation coefficient between the user community features and the features in the user feature library, H(x,k i ) is the negative correlation coefficient between the user community characteristics and the characteristics in the user feature library, and j is a constant. The positive correlation coefficient and the negative correlation coefficient are calculated based on the correlation of user characteristics. For example, if the user community is RV enthusiasts, then when calculating the user feature library, the RV users are positively correlated with the user community characteristics and their coefficients are positive. Non-RV users, such as users of off-road vehicles, are negatively correlated with the community characteristics and their coefficients are negative. User characteristics can be identified based on user behavior. For example, if a user often searches for RV information in daily searches, he is identified as an RV user, and if he often searches for off-road vehicles, he is an off-road vehicle user. Users can also be distinguished based on the vehicle insurance they purchase.

[0077] Optionally, the weight value a is based on get.

[0078] Optionally, the weight value b is based on Get. The calculated value is a1, The obtained data phase is b1, a=a1 / (a1+b1), b=b1 / (a1+b1).

[0079] like Figure 2As shown, a user tag setting device based on big data includes: a community module, which is used to divide users into multiple communities based on the acquired user behavior data, so as to obtain user communities;

[0080] A vector module, used to extract common features of the user community and obtain a feature vector based on the common features;

[0081] A label module is used to obtain corresponding label information based on the feature vector;

[0082] The tag setting module is used to set tags for users based on the tag information and the user community.

[0083] Optionally, the community module is further used to obtain neighbor relationships, friend relationships, preference relationships and member relationships based on user behavior data;

[0084] Users are divided into communities based on neighbor relationships, friend relationships, preference relationships, and membership relationships.

[0085] Figure 3 is a hardware block diagram of an electronic device according to an embodiment of the present disclosure. Figure 3 As shown, the electronic device according to an embodiment of the present disclosure includes a memory and a processor.

[0086] The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0087] The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the electronic device performs all or part of the steps of setting user tags based on big data in the aforementioned embodiments of the present disclosure.

[0088] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present disclosure.

[0089] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0090] According to the computer-readable storage medium of the embodiment of the present disclosure, non-transitory computer-readable instructions are stored thereon. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the user tag setting method based on big data of the above-mentioned embodiments of the present disclosure are executed.

[0091] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).

[0092] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0093] The terminal device can be implemented in various forms. The terminal device in the present disclosure may include but is not limited to mobile terminal devices such as mobile phones, smart phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), navigation devices, vehicle-mounted terminal devices, vehicle-mounted display terminals, vehicle-mounted electronic rearview mirrors, etc., as well as fixed terminal devices such as digital TVs, desktop computers, etc.

[0094] As an equivalent replacement embodiment, the terminal may also include other components. The terminal may include a power supply unit, a wireless communication unit, an A / V (audio / video) input unit, a user input unit, a sensing unit, an interface unit, a controller, an output unit, and a storage unit, etc. A terminal with various components is shown, but it should be understood that it is not required to implement all the components shown, and more or less components may be implemented alternatively.

[0095] Among them, the wireless communication unit allows radio communication between the terminal and the wireless communication system or network. The A / V input unit is used to receive audio or video signals. The user input unit can generate key input data according to the command input by the user to control various operations of the terminal device. The sensing unit detects the current state of the terminal, the position of the terminal, the presence or absence of the user's touch input to the terminal, the orientation of the terminal, the acceleration or deceleration movement and direction of the terminal, etc., and generates commands or signals for controlling the operation of the terminal. The interface unit is used as an interface through which at least one external device can be connected to the terminal. The output unit is configured to provide output signals in a visual, audio and / or tactile manner. The storage unit can store software programs for processing and control operations performed by the controller, etc., or can temporarily store data that has been output or is to be output. The storage unit may include at least one type of storage medium. Moreover, the terminal can cooperate with a network storage device that performs the storage function of the storage unit through a network connection. The controller generally controls the overall operation of the terminal device. In addition, the controller may include a multimedia module for reproducing or playing back multimedia data. The controller may perform a pattern recognition process to recognize handwriting input or picture drawing input performed on the touch screen as a character or image. The power supply unit receives external power or internal power and provides appropriate power required to operate various elements and components under the control of the controller.

[0096] Various embodiments of the user tag setting method based on big data proposed in the present disclosure can be implemented using a computer-readable medium such as computer software, hardware, or any combination thereof. For hardware implementation, various embodiments of the user tag setting method based on big data proposed in the present disclosure can be implemented by using at least one of a specific application integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, various embodiments of the user tag setting method based on big data proposed in the present disclosure can be implemented in a controller. For software implementation, various embodiments of the user tag setting method based on big data proposed in the present disclosure can be implemented with a separate software module that allows the execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a storage unit and executed by a controller.

[0097] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0098] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0099] In the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0100] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0101] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0102] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0103] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0104] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A user tag setting method based on big data, characterized in that: include: Based on the acquired user behavior data, users are divided into multiple communities to obtain user communities. Users with the same or similar behaviors are grouped together according to their behavior data. User communities are established based on users' interests in tagged resources. The interests in tagged resources are determined by calculating the frequency of user tags. That is, the higher the frequency of users tagging resources with the same tag, the higher the probability that users belong to the same user community. Extracting common features of the user community, and obtaining a feature vector based on the common features; Obtain corresponding label information based on the feature vector; Setting tags for users based on the tag information and the user community; The extracting the same features of the user community includes: comparing the correlation strengths of the features of the user community with the features in the user feature library one by one, and extracting the user community features according to the comparison results; Compare the extraction results and get the same features; The association strength is obtained based on an association strength model, and the association strength model is: Among them, f is the strength, a and b are weight values, x is the user community feature, k i is the feature in the user feature library, Q(x,k i ) is the positive correlation coefficient between the user community features and the features in the user feature library, H(x,k i ) is the negative correlation coefficient between the user community feature and the feature in the user feature library, j is a constant, and the positive correlation coefficient and negative correlation coefficient are calculated based on the user feature correlation; The obtaining corresponding label information based on the feature vector includes: comparing the feature vector with parameters in a feature library, and determining the label according to the comparison result.

2. The user tag setting method based on big data according to claim 1 is characterized in that: The user is divided into multiple communities based on the acquired user behavior data, thereby obtaining user communities, including: Obtain neighbor relationships, friend relationships, preference relationships, and member relationships based on user behavior data; Divide users into communities based on neighbor relationships, friend relationships, preference relationships, and membership relationships; The preference relationship is to calculate the frequency of different users using the same tag to mark resources. The higher the frequency of the user using the same tag to annotate resources, the higher the user's preference for the tag; In the preference relationship judgment, the user preference stability is obtained, and the obtaining of the user preference stability includes calculating the proportion of the frequency of the user using the tag to the frequency of all tags used by the user in a set time. The larger the proportion, the better the user preference stability.

3. The user tag setting method based on big data according to claim 1 is characterized in that: If the corresponding user community feature is not found in the user history feature library, the user community feature is aggregated and the aggregated result is added to the user history feature library.

4. The user tag setting method based on big data according to claim 1 is characterized in that: a=a1 / (a1+b1); 5. The user tag setting method based on big data according to claim 4 is characterized in that: b=b1 / (a1+b1).

6. A user tag setting device based on big data, characterized in that: include: A community module is used to divide users into multiple communities based on the acquired user behavior data, thereby obtaining user communities; A vector module, used to extract common features of the user community and obtain a feature vector based on the common features; A label module is used to obtain corresponding label information based on the feature vector; A tag setting module, used to set tags for users based on the tag information and the user community; The extracting the same features of the user community includes: comparing the correlation strengths of the features of the user community with the features in the user feature library one by one, and extracting the user community features according to the comparison results; Compare the extraction results and get the same features; The association strength is obtained based on an association strength model, and the association strength model is: Among them, f is the strength, a and b are weight values, x is the user community feature, k i is the feature in the user feature library, Q(x,k i ) is the positive correlation coefficient between the user community features and the features in the user feature library, H(x,k i ) is the negative correlation coefficient between the user community feature and the feature in the user feature library, j is a constant, and the positive correlation coefficient and negative correlation coefficient are calculated based on the user feature correlation; The obtaining corresponding label information based on the feature vector includes: comparing the feature vector with parameters in a feature library, and determining the label according to the comparison result.

7. The user tag setting device based on big data according to claim 6 is characterized in that: The community module is also used to obtain neighbor relationships, friend relationships, preference relationships and member relationships based on user behavior data; Users are divided into communities based on neighbor relationships, friend relationships, preference relationships, and membership relationships.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the user tag setting method based on big data as described in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the user tag setting method based on big data as described in any one of claims 1-5.

Images