HK1170040A - A method and device for collecting user action information and transmitting the information - Google Patents

Description

User behavior information collection and information sending method and device

Technical Field

The present application relates to the field of network technologies, and in particular, to a method and an apparatus for collecting user behavior information and sending information.

Background

When the current server pushes information to the client, the interest preference of the user in a short period is determined based on user behavior information stored in a database within a set time length, so that corresponding information can be pushed to the user, wherein the set time length is generally one month.

In the prior art, only short-term (set time length) behavior information of a user is generally stored in a database, so that the storage space of the database can be saved, but based on the short-term behavior information of the user stored in the database, a server can only determine interest and preference of the user within the set time length. When the behavior information of the user in the set time length is not stored in the database, the server cannot determine the interest preference of the user, determines the user as a new user, and pushes information to the user according to the information pushing type corresponding to the new user. In practice, however, the user may have previously accessed the database, e.g., the user is a periodic user, and may periodically access the server. Therefore, in the prior art, although the storage space of the database is saved by only storing the short-term behavior information of the user, the server cannot accurately determine the interest preference of the user due to the small amount of data of the stored user behavior information, and the accuracy of the information pushed to the user is affected. If the span of the set time length in the prior art is increased, although the accuracy of determining the interest preference of the user is improved to a certain extent, and the accuracy of pushing information to the user is improved, the storage space of the database must be expanded due to the increase of the user behavior information amount stored in the database, and the hardware cost is increased.

The problems in the prior art exist mainly because when the time span is large, the historical access data volume of the user is very large, the storage space of the existing database is limited, and the historical access data of the user cannot be stored in the database for a long time, so that the interest preference of the user in a long time cannot be determined, and the accuracy of information pushed to the user is influenced.

Disclosure of Invention

In view of this, embodiments of the present application provide a method and an apparatus for collecting user behavior information and sending information, so as to solve the problem that information pushing is inaccurate due to limited storage space of an existing database.

The user behavior information collection method provided by the embodiment of the application comprises the following steps:

determining the time period for information collection according to the time for information collection last time and the time for information collection at present;

during the time period, the following steps are respectively executed for the users who access the product categories:

determining the access amount of the user in the time period according to the times of the access behaviors of the user interacting with the server aiming at the product category in the time period;

according to the determined access amount and the saved first access amount of the user for the product category, determining a second access amount of the user for the product category;

determining the total frequency of the user accessing the server according to the stored frequency of determining the first access amount and the determined frequency corresponding to the time period;

determining the access interval of the user according to the last time when the user accesses the server for the product category and the current time for information collection;

and determining and saving the long-term preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval.

An information sending method based on the information collecting method provided by the embodiment of the application includes:

determining whether at least one of the long-term preference and the short-term preference of the user is stored or not according to the received information of the user login server, the long-term preference and the short-term preference stored in the database;

and when at least one of the long-term preference and the short-term preference of the user exists, pushing the information of the product category to the user according to the product category corresponding to the at least one of the long-term preference and the short-term preference.

An embodiment of the present application provides a user behavior information collection device, including:

the time period determining module is used for determining the time period for information collection according to the time for information collection last time and the time for information collection at present;

the visit amount determining module is used for respectively executing the following steps for users visiting the product categories in the time period: determining the access amount of the user in the time period according to the times of the access behaviors of the user interacting with the server aiming at the product category in the time period; according to the determined access amount and the saved first access amount of the user for the product category, determining a second access amount of the user for the product category;

the frequency determining module is used for determining the total frequency of the user accessing the server according to the stored frequency of determining the first access amount and the determined frequency corresponding to the time period;

the time interval determining module is used for determining the access interval of the user according to the time when the user last accesses the server aiming at the product category and the current information collection time;

and the preference determining module is used for determining and saving the long-term preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval.

An information sending apparatus based on the information collecting apparatus provided in an embodiment of the present application includes:

the determining module is used for determining whether at least one of the long-term preference and the short-term preference of the user is stored or not according to the received information of the user login server, the long-term preference and the short-term preference stored in the database;

and the pushing module is used for pushing the information of the product category to the user according to the product category corresponding to at least one of the long-term preference and the short-term preference when at least one of the long-term preference and the short-term preference of the user exists.

The embodiment of the application provides a method and a device for collecting user behavior information and sending the information, wherein the information collecting method determines the access amount of a user in a period of time according to the times of the access behavior of the user for interacting with a server in the period of time aiming at a product category, and determines the second access amount of the user aiming at the product category according to the stored first access amount of the user aiming at the product category, and can determine the total frequency of the user accessing the server and the access interval, so that the long-term preference of the user aiming at the product category can be determined. According to the method and the device, the first visit amount of the user aiming at each product category and the visit amount of the user in a period of time are saved, so that the second visit amount of the user, namely the total visit amount of the user can be determined, the long-term preference of the user can be further determined, and the accuracy of the information provided for the user is ensured. In addition, the database does not need to store the historical data of each user one by one, so that the storage pressure of the database is reduced, and the database does not need to provide the required historical data for the server, so that the working efficiency of the database is improved.

Drawings

Fig. 1 is a schematic structural diagram of a user information collection system according to an embodiment of the present disclosure;

fig. 2 is a process for collecting user behavior information according to an embodiment of the present disclosure;

fig. 3 is an information sending process based on the above information collecting method according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a user behavior information collecting apparatus according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an information sending apparatus based on the apparatus shown in fig. 4 according to an embodiment of the present application.

Detailed Description

The user information collection method provided by the embodiment of the application can determine the long-term preference of the user, so that the accuracy of the information provided by the server to the user is improved. In addition, the database does not need to store the historical data of each user one by one in the embodiment of the application, so that the storage pressure of the database is reduced, and the database does not need to provide the required historical data of each user for the server, so that the working efficiency of the database is improved.

The following detailed description of embodiments of the invention refers to the accompanying drawings.

Fig. 1 is a schematic structural diagram of a user information collecting system according to an embodiment of the present application, where the system includes: a server, a database, and a client, wherein,

the client sends each access behavior of the user interaction to the server.

When the server receives each access behavior sent by the client and interacted with the user, generating a working log according to the user information, the product category information, the time information of the access behavior and the information of the access behavior, and sending the working log to a database for storage; and when the user behavior information is collected, determining the time period for collecting the information according to the time for collecting the information last time and the time for collecting the information currently.

After the server determines the time period for collecting information, according to the log information stored in the database, because the log information records the time information of the occurrence of the access behavior, each access behavior of the user interacting with the server in the time period can be searched. In a specific implementation process, the database described in the present application may be integrated with the server in one server, or may be a database server that exists separately from the server. The server may be one server or a server cluster formed by a plurality of servers. This is not a limitation of the present application.

Specifically, when the server sends corresponding information to the client where the user is located, in order to ensure accuracy of the sent information, the server needs to push information of product categories with higher preference to the user according to the preference of the user for each product category. In addition, in the embodiment of the present application, in order to reflect the degree of access of a user to information of a certain product category in a long time, the long-term preference of the user to the product category may be used for representing the degree of access.

Fig. 2 is a process for collecting user behavior information according to an embodiment of the present application, where the process includes the following steps:

s201: and determining the time period for collecting the information according to the time for collecting the information last time and the time for collecting the information currently.

The server may collect the user behavior information periodically according to a set information collection period, or may collect the user behavior information when a condition of a certain event is met according to a condition of event triggering, or may collect the user behavior information according to an instruction of an administrator.

S202: during the time period, the following steps are respectively executed for each user accessing each product category: and determining the access amount of the user in the time period according to the times of each access behavior of the user interacting with the server aiming at the category.

Because the database stores the working log which comprises the contents of user information, product category information, time information of the occurrence of the access behavior, information of the access behavior and the like, the server determines the access amount of each user in the time period according to each access behavior of the user interacting with each product category.

S203: and determining a second access amount of the user for the product category according to the determined access amount and the saved first access amount of the user for the product category.

The first access amount may be stored in the server in order to improve the efficiency of determining the long-term preference of the user for the product category by the server, and certainly in order to save the storage space of the server, the first access amount may also be stored in the database server or in other network devices, and when the server calculates the long-term preference of the user for the product category, the server may interact with the database server or other network devices to obtain the first access amount of the user for the product category.

In the embodiment of the application, in order to facilitate the server to determine the long-term preference of each user for each product category, namely the preference degree of the user for a certain product category in a longer time period, the long-term preference of the user for the certain product category can be embodied by the access rate of the user for the certain product category in the longer time period. In the server, a first access amount of each user for each product category, that is, an access amount of each user after information collection is completed last time for each product category, is required. According to the first access amount and the access amount of the user for each product category in the time period, a second access amount of the user after information collection completion is currently performed for each product category can be determined.

In addition, in the present application, after determining the second access amount of the user for a certain product category, since the second access amount is the access amount of the product category until the time when the user currently collects information, the first access amount is updated with the second access amount in order to facilitate the calculation of the long-term preference of the user for the product category next time.

S204: and determining the total frequency of the user accessing the server according to the saved frequency information for determining the first access amount and the determined time period.

In order to facilitate the server to determine the long-term preference of each user for each product category, in the embodiment of the present application, frequency information for determining the first access amount needs to be stored in the server, and generally, the frequency information may be represented by days, and specifically, whether the user accesses the server in one day or not, and how many times the user accesses the server in one day, the day is accumulated into the frequency as one day. The first visit amount is determined by the visit amount of the user to the product category in days between the time of the user interacting with the server for the product category for the first time and the last information collection, wherein the total frequency is the total days between the time of the user interacting with the server for the product category and the current information collection.

For example, the time of the user accessing a certain product category of the server for the first time is 2010.3.21, the time of the user performing information currently is 2010.4.21, the time of the last information collection is 2010.3.20, and the time period of the information collection is 2010.3.21-2010.4.21, then for the time of the current information collection, since the user has not accessed the product category before, the stored first access amount of the user for the product category is 0, and the number of times of the user performing the access behavior of interacting with the server for the product in the 2010.3.21-2010.4.21 time period can be obtained from the database, so that the access amount of the user in the time period can be determined, and thus the determined second access amount is the access amount of the user in the time period. Since the user did not interact with the server for the product category before, the frequency of determining the first access amount is 0, and the number of days corresponding to the time period is 31 days, since it is known that the total frequency of accessing the server by the user is 31. And after determining the second access amount and the total frequency of the user for the product category, the server updates the first access amount stored by the server and the frequency of determining the first access amount.

When the user next performs information collection, for example, 2010.5.21, the time is the current time of information collection, the time for collecting information last time is 2010.4.21, the time period for collecting information is 2010.4.22-2010.5.21, depending on the number of access actions the user interacts with the server for the product category during the time period, the access amount of the user in the time period can be determined, the stored first access amount is the access amount of the user to a certain product category of the server for the first time, and the access amount of the user to the product category is determined within the time range of information collection last time, and therefore, according to the saved first visit amount and the determined visit amount of the user in the time period, determining a second visit amount, the second access amount is the access amount of the user to a certain product category of the server for the first time, and the access amount of the user to the product category is within the time range of information collection at present. The saved frequency, i.e. the number of days, determining the first access amount is 31 days, and the time period is 30 days, so the total frequency of the user accessing the server is 61 days. And then, continuing to update the stored first visit amount and the frequency of determining the first visit amount according to the determined second visit amount and the total frequency, and performing subsequent steps, which are not repeated herein.

S205: and determining the access interval of the user according to the time when the user last accesses the server for the product category and the current information collection time.

The access interval may be identified in the present embodiment in terms of days. The visit interval is the difference between the day the user last visited the server for the product category and the day the information collection was performed.

S206: and determining and saving the preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval.

Specifically, determining and saving the preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval, and the method comprises the following steps: determining a product of the second visit amount and the total frequency, and determining the long-term preference of the user for the product category according to the quotient of the product and the visit interval.

In order to determine the long-term preference of each user for each product category in the server, the server needs to save the time of last user behavior information collection in the embodiment of the application. Therefore, when the server currently collects the user behavior information, the time period for collecting the information can be determined according to the current information collection time and the saved last information collection time. For example, when the time of the previous information collection is 2011-1/zero morning and the time of the current information collection is 2011-1/31/zero morning, the time period for the information collection is determined to be 2011-1/1-30 days.

At this time, the server analyzes the working log according to the working log stored in the database, and acquires the working log of which the time when the access behavior occurs is within the time period. Specifically, in this embodiment of the present application, the access behavior includes: search behavior, browse behavior, click behavior, feedback behavior, transaction behavior, and the like.

When the server determines the access amount of each user in the time period, aiming at each user, according to the work log of which the acquired access behavior occurrence time is located in the time period, searching the work log containing the user information, searching the work log containing certain product category information in the work log containing the user information, and searching the times of each access behavior of the user interacting with the server in the work log containing the user information and the certain product category.

For example, the server determines the access amount of the user in the time period according to the number of times of each access behavior of the user a for interacting with the product category B. Firstly, the server searches a working log containing information of a user A and a product category B in the working log of which the acquired access behavior occurrence time is located in the time period, and respectively counts times of interactive search behavior, browsing behavior, clicking behavior, feedback behavior, transaction behavior and the like of the user A in the searched working log, wherein the times are respectively x₁，K，x_nWhere n is the number of classes that the access behavior contains.

After determining the number of times of each access behavior of the user interacting with the server for the product category in the time period, the access amount of the user in the time period needs to be determined, and specifically, when determining the access amount of the user in the time period, the access amount may be determined directly according to the sum of the determined number of times of each access behavior. In addition, different weight values may also be preset for each access behavior, and specifically, for example, the weight value for the user to actively send the access behavior may be considered to be larger, that is, the weight values for the search behavior, the click behavior, and the transaction behavior may be preset to be larger. After different weight values are preset for each access behavior, the number of times of each access behavior of the user interacting with the server for the category in the time period and the weight value corresponding to each access behavior can be determinedThe amount of access in the time period. I.e. according to Y ═ w₁x₁+...+w_nx_nDetermining the visit amount of the user in the time period, wherein Y is the visit amount of the user in the time period, x₁，K，x_nNumber of access actions in n, w₁，...，w_nAnd the weight value corresponding to each access behavior.

After determining the access amount of the user in the time period according to the obtained work log, the server also needs to determine a second access amount of the user for the product category according to the saved first access amount of the user for the product category, that is, a total access amount of the user for the product category until the current information collection time.

After the server determines the second access amount of the user for the product category, it is further required to determine the total frequency of the user accessing the server for the product category according to the stored frequency information for determining the first access amount and the determined time period, that is, the total frequency of information collection is currently performed when the user determines the long-term preference of the user for the product category.

After the server determines the second access amount and the total frequency of the user for the product category, the access interval of the user for the product category is determined according to the last time of the user for the product category to access the server and the current information collection time, and then the long-term preference of the user for the product category can be determined and stored. Specifically, Y represents a second access amount of the user for the product category, F is a total frequency, and T is an access interval of the user for the product category, so that the long-term preference P ═ Y × F/T of the user for the product category.

According to the method, the server can determine and store the long-term preference of each user for each product category according to the work logs recorded in the database. Since the number of users accessing the data is very large, the storage space occupied in the server is also very large if the long-term preferences of each user for accessing each product category are kept in the database. In the embodiment of the present invention, in order to reduce the storage space of the server occupied by saving the long-term preference, a user number threshold may be preset for each product category. And when the long-term preference of each user for the product category is determined according to the product category, sequencing the determined long-term preference of each user for the product category, selecting the number of users corresponding to the number threshold with larger long-term preference according to the preset number threshold of the users corresponding to the product category, and storing the long-term preference of each user for the product category.

Or, for each user, according to the determined long-term preference of the user for each product category and a preset threshold value of the number of product categories, selecting the product categories with larger long-term preference and the number corresponding to the threshold value of the number, and storing the long-term preference of the user for each selected product category.

After the server stores the long-term preference of each user for each product category, in order to facilitate the server to determine the long-term preference of each user for each product category in the later period, in this embodiment of the application, the server updates the first visit amount of the user for the product category, which is stored by the server, by using the determined second visit amount of the user for the product category, and updates the stored frequency information which determines the first visit amount by using the total frequency of the user for accessing the server for the product category. In addition, in the embodiment of the application, as long as the first access amount can be acquired, the frequency of the first access amount, the last time when the user accesses the server for the product category and the log of interaction between the user and the server in the information collection time period are determined, the long-term preference of the user for the product category can be determined. Therefore, the access log of the user before the time of information collection last time can be deleted, as long as the log of the interaction between the user and the server in the time period corresponding to the time of information collection last time and the current time of information collection, the first access amount, the frequency of the first access amount and the time information of the last access of the user to the server for the product category are determined, and therefore the storage resource of the server is greatly saved.

For the update of the access interval of the user for the product category, in this embodiment of the application, since the access interval is a difference between the time when the user last accesses the server for the product category and the current information collection time, when the user does not interact with the server for the product category in the time period, the server directly determines the access interval of the user for the product category according to the first access interval of the user for the product category stored by the server and the current information collection time period, and updates the access interval stored in the server for the product category by using the determined time interval.

That is, when the user does not interact with the server for the product category within the time period, the time when the user last accessed the server for the product category is not within the time period, for example, the time period for information collection is from 2011 1 month 1 day to 2011 1 month 30 days, and the user does not interact with the server for a certain product category within the time period, it can be known that the time when the user last accessed the server for the product category is not within the time period and should be within the time period before 2011 1 month 1 day. Therefore, a first access interval of the user for the product category is saved in the server, the first time interval is the time when the user last accesses the server for the product category, and the last time information collection is carried out, so that the access time interval of the user for the access category is the sum of the first access interval and the time period for carrying out information collection within the current information collection time.

When the user interacts with the server aiming at the product in the time period, determining the access time interval of the user according to the last time when the user accesses the server aiming at the product category and the current time for information collection, and updating the access interval of the user aiming at the product category, which is stored in the server, by adopting the determined time interval.

Since the first visit amount, the total frequency, and the visit interval of each user for each product category are stored in the server, therefore, when the server determines the long-term preference of each user for each product category, only the recorded work log information in the time period corresponding to the difference between the current information collection time and the last information collection time is collected, the user's long-term preferences for each product category can be determined, eliminating the need to keep the user's historical data in the database for long periods, therefore, the method for determining the long-term preference of the user for each product category provided by the embodiment of the application effectively saves the memory space of the database, and because the long-term preference of the user for each product category can be determined according to the method provided by the embodiment of the application, the accuracy of the sent information can be ensured when the server sends the information.

In addition, because the short-term preference of the user for each product category is determined according to the behavior information interacted with the server for each product category in the set frequency before the current information collection time of the user, the short-term preference can reflect the access habit of the user in the short term.

When determining the short-term preference of the user for each product category, determining the access amount Y of the user for the product category according to the number of times of each access behavior of the user for interacting with the server for the product category_i. And according to a determined model P (t) K decaying over time t₁+exp((t-K₂)÷K₃) Determining the short-term preference of the user for the product category, wherein t is a negative number corresponding to each day in the set frequency, for example, when t is day 5 in the set frequency, t is-5, and the parameter K is₁，K₂，K₃May be determined according to the particular application. After the determined user visit amount for the product category and the preset decay model, the short-term preference P (0) Y of the user for the product category can be obtained₀+K+P(N)Y_N。

In addition, existing servers, when determining each user's preference for each product category, are typically up to day in granularity of the update time for the data in the database. Therefore, when a user interacts with the server for a certain product category, the server can acquire the work log for recording the interaction process from the database only in the next day after the interaction, so that the existing server cannot generate the current preference of the user for the product category according to the current interaction of the user for the certain product category.

In the embodiment of the application, in order to generate the current preference of a user for each product category, when the user logs in a server, the server generates a working log according to the interactive access behavior of the current user for a certain product category, and before the working log is sent to a database, the server analyzes and acquires the access behavior of the user for the product category recorded in the working day, and acquires the current access data information of the user; determining the current preference of the user for each product category according to the current access data information.

Or, the client where the user is located locally records behavior information of interaction between the user and the server for a certain product category through the client, and records a Cookie file or a Flash file locally. Therefore, when generating the current preference of the user for each category, the server can interact with the client to obtain the Cookie file or Flash file locally recorded by the client where the user is located, record the current access data information of the user, and determine the current preference of the user for each product category according to the obtained current access data information of the user.

In the embodiment of the application, the server can determine the long-term preference, the short-term preference and the current preference of the user for each product category, so that the information can be sent according to the stored preference when the information is sent to the user, and the accuracy of the sent information is ensured.

Fig. 3 is an information sending process based on the above information collecting method according to an embodiment of the present application, where the information sending process includes the following steps:

s301: and receiving information of a user logging in the server.

S302: and determining whether at least one of the long-term preference and the short-term preference of the user is stored or not according to the long-term preference and the short-term preference stored in the database, and performing step S303 when the determination result is yes, or performing step S304 otherwise.

S303: and pushing the information of the product category to the user according to the product category corresponding to at least one of the long-term preference and the short-term preference.

S304: and taking the user as a new user, and sending the product category information corresponding to the new user to the user.

In the embodiment of the application, the long-term preference of the user for each product category is saved in the server. Short term preferences, and current preferences. And after receiving the login information of the user, the server sends the information of the corresponding product category to the user according to the stored preference of each product category corresponding to the user.

When the server stores the long-term preference of the user for each product category, the information of the product category with larger long-term preference can be sent to the user according to the size of the stored long-term preference of the user for each product category. When the server stores the short-term preference of the user for each product category, the information of the product category with larger short-term preference can be sent to the user according to the size of the stored short-term preference of the user for each product category. When the server stores the current preference of the user for each product category, the server can send the information of the product category with larger current preference to the user according to the size of the stored current preference of the user for each product category.

When the server stores the long-term preference, the short-term preference and the current preference of the user for each product category, when information is sent to the user, the information of the product categories with a first quantity can be determined according to each product category corresponding to the long-term preference of the user; determining a second amount of product category information according to each product category corresponding to the short-term preference of the user; determining a third amount of product category information according to each product category corresponding to the current preference of the user; and pushing the information corresponding to the determined first quantity of product categories, the second quantity of product categories and the third quantity of product categories to the user.

According to the long-term preference of the user for each product category, sorting the long-term preference of the user for each product category, selecting a first number N1 of product categories with larger long-term preference, selecting a second number N2 of product categories with larger short-term preference by adopting the same method, selecting a third number N3 of product categories with larger current preference by adopting the same method, and pushing information corresponding to the first number of product categories, the second number of product categories and the third number of product categories to the user.

Or when the server stores the long-term preference, the short-term preference and the current preference of the user for each product category, when information is sent to the user, determining fourth amount of product category information according to the intersection of the product categories corresponding to the long-term preference, the short-term preference and the current preference of the user; determining a fifth amount of product category information according to the intersection of the product categories corresponding to every two preferences in the long-term preference, the short-term preference and the current preference of the user; determining the product category information of the sixth quantity according to each product category corresponding to the long-term preference, the short-term preference or the current preference of the user;

and pushing the information corresponding to the determined fourth quantity of product categories, the determined fifth quantity of product categories and the determined sixth quantity of product categories to the user.

The method comprises the steps of firstly determining which product categories the user aims at, namely long-term preference, short-term preference and current preference exist, selecting the number of the products of the fourth quantity after determining the product categories, then determining which product categories the user aims at, namely two of long-term inquiry rate, short-term preference and current preference exist, selecting the number of the products of the fifth quantity in the product categories, then selecting the product category of the sixth quantity according to the product categories of which only one of the long-term preference, the short-term preference or the current preference exists, and pushing information corresponding to the determined product categories of the fourth quantity, the fifth quantity and the sixth quantity to the user.

Or, when the server stores the long-term preference, the short-term preference and the current preference of the user for each product category, the server may also send information of the corresponding product category to the user according to the activity of the user, that is, judge whether the total frequency of the stored user accessing the server is greater than a set frequency threshold; when the judgment result is yes, recommending information of corresponding product categories to the user according to the short-term preference of the user and the product category information corresponding to the current preference; and if not, recommending the information of the corresponding product category to the user according to the long-term preference and the product category information corresponding to the current preference of the user.

Or, when the server stores the long-term preference, short-term preference and current preference of the user for each product category, the server may also send information of the corresponding product category to the user according to the type of the user, that is, according to the stored type of each user, determine whether the user is a commercial user; when the judgment result is yes, recommending information of corresponding product categories to the user according to the long-term preference and the product category information corresponding to the current preference of the user; and if not, recommending the information of the corresponding product category to the user according to the short-term preference of the user and the product category information corresponding to the current preference.

Fig. 4 is a schematic structural diagram of a user behavior information collecting device according to an embodiment of the present application, where the device includes:

a time period determining module 41, configured to determine a time period for information collection according to a time of information collection last time and a time of information collection currently;

a visit amount determination module 42, configured to perform the following steps for each user visiting each product category during the time period, respectively: determining the access amount of the user in the time period according to the times of each access behavior of the user interacting with the server aiming at the product category in the time period; according to the determined access amount and the saved first access amount of the user for the product category, determining a second access amount of the user for the product category;

a frequency determining module 43, configured to determine, according to the stored frequency for determining the first access amount and the determined frequency corresponding to the time period, a total frequency for the user to access the server;

a time interval determination module 44, configured to determine an access interval of the user according to a time when the user last accessed the server for the product category and a current time for information collection;

and the preference determining module 45 is used for determining and saving the long-term preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval.

The device further comprises:

an updating module 46, configured to update the first access amount with the determined second access amount; and updating the stored frequency information for determining the first access amount by adopting the total frequency.

The preference determining module 45 is specifically configured to determine a product of the second visit amount and the total frequency, and determine the long-term preference of the user for the product category according to a quotient of the product and the visit interval.

The access amount determining module 42 is specifically configured to determine the access amount of the user in the time period according to the number of times of each access behavior of the user interacting with the server for the category in the time period and a weight value corresponding to each access behavior.

The device further comprises:

and a filtering module 47, configured to select, for each user, a number of product categories corresponding to the number threshold with a larger long-term preference according to the determined long-term preference of the user for each product category and a preset number threshold of product categories, and store the long-term preference of the user for each selected product category.

Fig. 5 is a schematic structural diagram of an information sending apparatus based on the apparatus shown in fig. 4 according to an embodiment of the present application, where the apparatus includes:

a determining module 51, configured to determine whether at least one of the long-term preference and the short-term preference of the user is stored according to the received information of the user logging in the server, the long-term preference and the short-term preference stored in the database;

and the pushing module 52 is configured to, when at least one of the long-term preference and the short-term preference of the user exists, push information of the product category to the user according to the product category corresponding to the at least one of the long-term preference and the short-term preference.

The determining module 51 is specifically configured to obtain current access data information of the user according to information of the user logging in the server, a log generated by the server, or a Cookie file or a Flash file stored by a client where the user is located; determining the current preference of the user for each product category according to the current access data information; determining whether at least one of a long-term preference, a short-term preference, and a current preference of the user is stored.

The pushing module 52 is specifically configured to determine, when the long-term preference, the short-term preference, and the current preference of the user exist, a first amount of product category information according to each product category corresponding to the long-term preference of the user; determining a second amount of product category information according to each product category corresponding to the short-term preference of the user; determining a third amount of product category information according to each product category corresponding to the current preference of the user; and pushing the information corresponding to the determined first quantity of product categories, the second quantity of product categories and the third quantity of product categories to the user.

The pushing module 52 is specifically configured to determine, when the long-term preference, the short-term preference, and the current preference of the user exist, a fourth amount of product category information according to an intersection of product categories corresponding to the long-term preference, the short-term preference, and the current preference of the user; determining a fifth amount of product category information according to the intersection of the product categories corresponding to every two preferences in the long-term preference, the short-term preference and the current preference of the user; determining the product category information of the sixth quantity according to each product category corresponding to the long-term preference, the short-term preference or the current preference of the user; and pushing the information corresponding to the determined fourth quantity of product categories, the determined fifth quantity of product categories and the determined sixth quantity of product categories to the user.

The pushing module 52 is specifically configured to, when there are a long-term preference, a short-term preference, and a current preference of the user, determine whether the stored total frequency of the user accessing the server is greater than a set frequency threshold; when the judgment result is yes, recommending information of corresponding product categories to the user according to the short-term preference of the user and the product category information corresponding to the current preference; and if not, recommending the information of the corresponding product category to the user according to the long-term preference and the product category information corresponding to the current preference of the user.

The pushing module 52 is specifically configured to, when there are a long-term preference, a short-term preference, and a current preference of the user, determine whether the user is a business user according to a type of each stored user; when the judgment result is yes, recommending information of corresponding product categories to the user according to the long-term preference and the product category information corresponding to the current preference of the user; and if not, recommending the information of the corresponding product category to the user according to the short-term preference of the user and the product category information corresponding to the current preference.

The embodiment of the application provides a method and a device for collecting user behavior information and sending the information, wherein the information collection method determines the access amount of a user in a period of time according to the times of each access behavior of the user interacting with a server in each production category in the period of time, determines the second access amount of the user aiming at the product category according to the stored first access amount of the user aiming at the product category, and can determine the total frequency of the user accessing the server and the access interval, so that the long-term preference of the user aiming at the product category can be determined. According to the method and the device, the first visit amount of the user aiming at each product category and the visit amount of the user in a period of time are saved, so that the second visit amount of the user, namely the total visit amount of the user can be determined, the long-term preference of the user can be further determined, and the accuracy of the information provided for the user is ensured. In addition, the database does not need to store the historical data of each user one by one, so that the storage pressure of the database is reduced, and the database does not need to provide the required historical data for the server, so that the working efficiency of the database is improved.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (22)

1. A method for collecting user behavior information, comprising:

determining the time period for information collection according to the time for information collection last time and the time for information collection at present;

during the time period, the following steps are respectively executed for the users who access the product categories:

determining the access amount of the user in the time period according to the times of the access behaviors of the user interacting with the server aiming at the product category in the time period;

according to the determined access amount and the saved first access amount of the user for the product category, determining a second access amount of the user for the product category;

determining the total frequency of the user accessing the server according to the stored frequency of determining the first access amount and the determined frequency corresponding to the time period;

determining the access interval of the user according to the last time when the user accesses the server for the product category and the current time for information collection;

and determining and saving the long-term preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval.

2. The method of claim 1, wherein the method further comprises:

updating the first visit volume by adopting the determined second visit volume;

and updating the stored frequency information for determining the first access amount by adopting the total frequency.

3. The method of claim 1, wherein determining the user's long term preference for the product category based on the determined second visit amount, total frequency, and visit interval comprises:

determining a product of the second visit amount and the total frequency, and determining the long-term preference of the user for the product category according to the quotient of the product and the visit interval.

4. The method of claim 1, wherein determining the amount of access by the user over the period of time comprises:

and determining the access amount of the user in the time period according to the times of the access behaviors of the user interacting with the server for the category in the time period and the weight values corresponding to the access behaviors.

5. The method of claim 1, wherein the method further comprises:

and selecting a number of product categories corresponding to the number threshold with larger long-term preference according to the determined long-term preference of the user for the product categories and a preset number threshold of the product categories, and storing the long-term preference of the user for each selected product category.

6. An information transmission method based on the collection method of claim 1, characterized in that the method comprises:

determining whether at least one of the long-term preference and the short-term preference of the user is stored or not according to the received information of the user login server, the long-term preference and the short-term preference stored in the database;

and when at least one of the long-term preference and the short-term preference of the user exists, pushing the information of the product category to the user according to the product category corresponding to the at least one of the long-term preference and the short-term preference.

7. The method of claim 6, wherein the determining whether at least one of the long-term preference and the short-term preference of the user is stored comprises:

acquiring current access data information of the user according to the information of the user logging in the server, a log generated by the server, or a Cookie file or a Flash file stored by the client where the user is located;

determining the current preference of the user for the product category according to the current access data information;

determining whether at least one of a long-term preference, a short-term preference, and a current preference of the user is stored.

8. The method of claim 7, wherein pushing information for the product category to the user when there are long-term preferences, short-term preferences, and current preferences of the user comprises:

determining a first amount of product category information according to a product category corresponding to the long-term preference of the user;

determining a second amount of product category information according to the product categories corresponding to the short-term preferences of the user;

determining a third amount of product category information according to the product category corresponding to the current preference of the user;

and pushing the information corresponding to the determined first quantity of product categories, the second quantity of product categories and the third quantity of product categories to the user.

9. The method of claim 7, wherein pushing information for the product category to the user when there are long-term preferences, short-term preferences, and current preferences of the user comprises:

determining a fourth amount of product category information according to the intersection of the product categories corresponding to the long-term preference, the short-term preference and the current preference of the user;

determining a fifth amount of product category information according to the intersection of the product categories corresponding to every two preferences in the long-term preference, the short-term preference and the current preference of the user;

determining the product category information of the sixth quantity according to each product category corresponding to the long-term preference, the short-term preference or the current preference of the user;

and pushing the information corresponding to the determined fourth quantity of product categories, the determined fifth quantity of product categories and the determined sixth quantity of product categories to the user.

10. The method of claim 7, wherein pushing information for the product category to the user when there are long-term preferences, short-term preferences, and current preferences of the user comprises:

judging whether the stored total frequency of the user accessing the server is greater than a set frequency threshold value or not;

when the judgment result is yes, recommending information of corresponding product categories to the user according to the short-term preference of the user and the product category information corresponding to the current preference;

and if not, recommending the information of the corresponding product category to the user according to the long-term preference and the product category information corresponding to the current preference of the user.

11. The method of claim 7, wherein pushing information for the product category to the user when there are long-term preferences, short-term preferences, and current preferences of the user comprises:

judging whether the user is a commercial user or not according to the saved type of each user;

when the judgment result is yes, recommending information of corresponding product categories to the user according to the long-term preference and the product category information corresponding to the current preference of the user;

and if not, recommending the information of the corresponding product category to the user according to the short-term preference of the user and the product category information corresponding to the current preference.

12. A user behavior information collecting apparatus, characterized in that the apparatus comprises:

the time period determining module is used for determining the time period for information collection according to the time for information collection last time and the time for information collection at present;

the visit amount determining module is used for respectively executing the following steps for users visiting the product categories in the time period: determining the access amount of the user in the time period according to the times of the user performing interactive access behaviors with the server aiming at the product category in the time period; according to the determined access amount and the saved first access amount of the user for the product category, determining a second access amount of the user for the product category;

the frequency determining module is used for determining the total frequency of the user accessing the server according to the stored frequency of determining the first access amount and the determined frequency corresponding to the time period;

the time interval determining module is used for determining the access interval of the user according to the time when the user last accesses the server aiming at the product category and the current information collection time;

and the preference determining module is used for determining and saving the long-term preference of the user for the product category according to the determined second visit amount, the total frequency and the visit interval.

13. The apparatus of claim 12, wherein the apparatus further comprises:

the updating module is used for updating the first visit volume by adopting the determined second visit volume; and updating the stored frequency information for determining the first access amount by adopting the total frequency.

14. The apparatus of claim 12, wherein the preference determination module is specifically configured to determine a product of the second visit amount and the total frequency, and determine the long term preference of the user for the product category according to a quotient of the product and the visit interval.

15. The apparatus according to claim 12, wherein the access amount determining module is specifically configured to determine the access amount of the user in the time period according to the number of times of access behaviors of the user interacting with the server for the category in the time period and a weight value corresponding to the access behaviors.

16. The apparatus of claim 12, wherein the apparatus further comprises:

and the filtering module is used for selecting the product categories with larger long-term preference according to the determined long-term preference of the user for the product categories and the preset threshold value of the number of the product categories, and storing the long-term preference of the user for the selected product categories.

17. An information transmission apparatus based on the collection apparatus of claim 12, characterized in that the apparatus comprises:

the determining module is used for determining whether at least one of the long-term preference and the short-term preference of the user is stored or not according to the received information of the user login server, the long-term preference and the short-term preference stored in the database;

and the pushing module is used for pushing the information of the product category to the user according to the product category corresponding to at least one of the long-term preference and the short-term preference when at least one of the long-term preference and the short-term preference of the user exists.

18. The apparatus of claim 17, wherein the determining module is specifically configured to obtain current access data information of the user according to information of the user logging in a server, a log generated by the server, or a Cookie file or a Flash file stored by a client where the user is located; determining the current preference of the user for each product category according to the current access data information; determining whether at least one of a long-term preference, a short-term preference, and a current preference of the user is stored.

19. The apparatus of claim 18, wherein the push module is specifically configured to determine a first amount of product category information for each product category corresponding to the user's long-term preference when the user's long-term preference, short-term preference, and current preference are present; determining a second amount of product category information according to each product category corresponding to the short-term preference of the user; determining a third amount of product category information according to each product category corresponding to the current preference of the user; and pushing the information corresponding to the determined first quantity of product categories, the second quantity of product categories and the third quantity of product categories to the user.

20. The apparatus of claim 18, wherein the push module is specifically configured to determine a fourth amount of product category information based on an intersection of product categories corresponding to the long-term preference, the short-term preference, and the current preference of the user when the long-term preference, the short-term preference, and the current preference of the user exist; determining a fifth amount of product category information according to the intersection of the product categories corresponding to every two preferences in the long-term preference, the short-term preference and the current preference of the user; determining the product category information of the sixth quantity according to each product category corresponding to the long-term preference, the short-term preference or the current preference of the user; and pushing the information corresponding to the determined fourth quantity of product categories, the determined fifth quantity of product categories and the determined sixth quantity of product categories to the user.

21. The apparatus of claim 18, wherein the push module is specifically configured to determine whether the saved total frequency of the user accessing the server is greater than a set frequency threshold when the long-term preference, the short-term preference, and the current preference of the user exist; when the judgment result is yes, recommending information of corresponding product categories to the user according to the short-term preference of the user and the product category information corresponding to the current preference; and if not, recommending the information of the corresponding product category to the user according to the long-term preference and the product category information corresponding to the current preference of the user.

22. The apparatus of claim 18, wherein the push module is specifically configured to determine whether the user is a business user based on the saved type of each user when the long-term preference, the short-term preference, and the current preference of the user exist; when the judgment result is yes, recommending information of corresponding product categories to the user according to the long-term preference and the product category information corresponding to the current preference of the user; and if not, recommending the information of the corresponding product category to the user according to the short-term preference of the user and the product category information corresponding to the current preference.