CN115511560A

CN115511560A - Time series analysis method and device, electronic equipment and readable storage medium

Info

Publication number: CN115511560A
Application number: CN202211131458.1A
Authority: CN
Inventors: 张少辉
Original assignee: Agricultural Bank of China
Current assignee: Agricultural Bank of China
Priority date: 2022-09-16
Filing date: 2022-09-16
Publication date: 2022-12-23

Abstract

The application provides a time series analysis method, a time series analysis device, electronic equipment and a readable storage medium, and relates to the field of data analysis, wherein the method comprises the following steps: acquiring first commodity recommendation information of a target application in a preset time range, and storing the first commodity recommendation information into a time sequence database; acquiring behavior characteristic data of a target user aiming at the first commodity recommendation information; and performing time-series aggregation analysis in the time-series database based on the first commodity recommendation information and the behavior feature data, and generating second commodity recommendation information according to an analysis result. By the method, targeted recommended commodities in the corresponding time range can be provided for a single user, the actual ordering requirements of the user are met, and the user experience is improved.

Description

Time series analysis method and device, electronic equipment and readable storage medium

Technical Field

The present application relates to the field of data analysis, and in particular, to a time series analysis method and apparatus, an electronic device, and a readable storage medium.

Background

With diversification of banking business, a large number of products are put on the client for selection by a user, and in order to improve user experience, the client can recommend related products to the user by combining big data, for example, recommending the related products to the user in the form of a popular list or a recommendation list.

The current client side recommends products to users in a hot sell list form, the products are mainly obtained through preference analysis of massive users screened from big data or similar users, the single user has no pertinence, and the products recommended by the hot sell list are not in accordance with actual requirements of the users due to the fact that the required products of the users in different time periods are different.

Disclosure of Invention

In order to solve the problems, namely, the problems that products recommended to a user by a client do not have pertinence to a single user and do not meet the actual requirements of the user, the application provides a time sequence analysis method and device, electronic equipment and a readable storage medium.

In order to achieve the above purpose, the present application provides the following technical solutions:

according to an aspect of the present application, there is provided a time series analysis method based on user behavior characteristics, including:

acquiring first commodity recommendation information of a target application in a preset time range, and storing the first commodity recommendation information into a time sequence database;

acquiring behavior characteristic data of a target user aiming at the first commodity recommendation information;

and performing time-series aggregation analysis on the basis of the first commodity recommendation information and the behavior feature data in the time-series database, and generating second commodity recommendation information according to an analysis result.

In an embodiment, the obtaining of the first commodity recommendation information of the target application within a preset time range includes:

the method comprises the steps of obtaining commodity sales amount information of a target application in a preset time range, and obtaining first commodity recommendation information based on the commodity sales amount information.

In one embodiment, the first item recommendation information is a recommendation basis table sorted based on item recommendation indexes, the recommendation basis table including identification information and attribute information of corresponding recommended items, the recommendation indexes being obtained based on inventory turnover rates of the corresponding recommended items.

In one embodiment, the obtaining of the behavior feature data of the target user with respect to the first commodity recommendation information includes:

splitting the first commodity recommendation information into a plurality of standardized product units SPU;

and acquiring the behavior characteristic data of the target user based on the standardized product unit SPU and the behavior data generated by the target user to the SPU.

In one embodiment, the performing a time-series aggregate analysis in the time-series database based on the first commodity recommendation information and the behavior feature data includes:

loading a RedisTimeSeries module in the time series database;

and creating a time series data set based on the first commodity recommendation information and the behavior characteristic data by utilizing a RedisTimeseries module, and carrying out aggregation analysis on the time series data set.

In one embodiment, the performing the aggregate analysis on the set of time series data comprises:

performing aggregation analysis on the time sequence data set based on a preset aggregation type, wherein the preset aggregation type at least comprises one of the following types: averaging, maximum/minimum or summing.

In one embodiment, the behavior feature data is a user behavior data table,

the generating of the second commodity recommendation information according to the analysis result includes:

and re-sequencing the recommendation basis table based on the user behavior data table according to the analysis result to obtain second commodity recommendation information.

According to another aspect of the present application, there is provided a time-series analysis apparatus based on user behavior characteristics, including:

the system comprises a first acquisition module, a second acquisition module and a time sequence database, wherein the first acquisition module is used for acquiring first commodity recommendation information of a target application in a preset time range and storing the first commodity recommendation information into the time sequence database

The second acquisition module is used for acquiring behavior characteristic data of the target user aiming at the first commodity recommendation information;

and the analysis recommending module is used for performing time-series aggregation analysis on the basis of the first commodity recommending information and the behavior characteristic data in the time-series database and generating second commodity recommending information according to an analysis result.

According to yet another aspect of the present application, there is provided an electronic device including: a memory and a processor;

the memory stores computer-executable instructions;

the processor executes the computer-executable instructions stored in the memory to cause the electronic device to perform the user behavior feature-based time series analysis method.

According to still another aspect of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored, and the computer-executable instructions are executed by a processor to implement the user behavior feature-based time series analysis method.

It can be understood that the time series analysis method, the time series analysis device, the electronic device and the readable storage medium provided by the embodiment of the application acquire the first commodity recommendation information of the target application within a preset time range, and store the first commodity recommendation information into the time series database; acquiring behavior characteristic data of a target user aiming at the first commodity recommendation information; and performing time-series aggregation analysis on the time-series database based on the first commodity recommendation information and the behavior feature data, and generating second commodity recommendation information according to an analysis result, so that a single user can be provided with a recommended commodity with pertinence in a corresponding time range, the actual ordering requirement of the user is met, and the user experience is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic diagram of one possible scenario provided in an embodiment of the present application;

fig. 2 is a schematic flowchart of a time series analysis method based on user behavior characteristics according to an embodiment of the present application;

FIG. 3 is an exemplary diagram of data relationships of a redis database in an embodiment of the present application;

fig. 4 is a schematic structural diagram of a time series analysis apparatus based on user behavior characteristics according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.

Detailed Description

The statistical analysis identifies "majority of minority" according to pareto's rule, i.e. 20% of the sales of the goods can achieve 80% of the total sales, while the remaining 80% of the sales of the goods can achieve only about 20% of the total sales. 20% present between the percentage of commodity variety and the relative percentage of sales: the regularity of the 80% relationship is called the 20-80 principle. The commodity accounting for 20% of the largest share of the sales is called a best selling commodity, namely the "popular leaderboard" mentioned in the application.

With the development of commodity networking, more and more users tend to order products on the internet, and the hot leaderboard is an almost indispensable element in internet application and can recommend products which may be interested in the users. However, the current popular list is mainly obtained by analyzing the preference of a large number of users or similar users screened according to big data, and has no pertinence to a single user, and because the required products of the users in different time periods are different, the products recommended by the popular list are not in line with the actual requirements of the users. Therefore, the heat market board is a key solution for aggregation and analysis based on the user behavior feature data.

In the related technology, the method for storing the time sequence data of the user by using the Hash and the ordered Set Sorted Set simultaneously is provided, so that the aggregation and analysis of the user behavior data are realized. Although the Hash type can meet the requirement of single-key query of time series data, the Hash type does not support range query of data, the Sorted Set type can support range query according to time, and MULTI and EXEC commands are required to ensure atomicity when the commands are executed, the method is very troublesome, and since the Sorted Set only supports range query and cannot directly perform aggregation calculation, the data in the time range can only be taken back to the client in practical application, and then the aggregation calculation is automatically completed at the client. Although the above scheme can complete the aggregation calculation, a certain potential risk is brought about, that is, a large amount of data is frequently transmitted between the Redis instance and the client, which may compete with other operation commands for network resources, resulting in slowing of other operations.

In view of this, embodiments of the present application provide a method and an apparatus for analyzing a time sequence, an electronic device, and a readable storage medium, by acquiring historical and contemporaneous first recommended commodity information of an application, and then storing behavior data of a user on searching, ordering, browsing, collecting, and the like of part or all of the first recommended commodity information in a Redis database, and using a data type and an access interface provided by an extension module RedisTimeSeries module in the Redis database, the data is directly aggregated and calculated according to a time range on a Redis instance, so as to generate second recommended commodity information (a hot list) having user characteristics, so that recommended commodities in a corresponding period are provided for a single user, an actual ordering requirement of the user is satisfied, user experience is improved, and a data analysis process is more efficient, and does not need to occupy too many network resources.

In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar components or components having the same or similar functions throughout. The described embodiments are a subset of the embodiments in the present application and not all embodiments in the present application. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Fig. 1 is a schematic view of a possible scenario provided in the embodiment of the present disclosure, and it should be noted that the time series analysis method of the present disclosure may be applied to the field of financial technology. The time series analysis method can also be used in any other fields, and the application field of the time series analysis method is not limited.

Taking a product recommendation scene of a bank APP as an example, as shown in fig. 1, the product recommendation scene includes a terminal device 110 and a server 120, and the terminal device 110 and the server 120 are connected to each other through a wired or wireless network. Optionally, a bank client APP is installed on the terminal device 110, and is configured to provide the first commodity recommendation information to the server 120, where the first commodity recommendation information is, for example, hot-sell list data in a certain time period, for example, the hot-sell list data may be product data ten times of an order quantity; the server 120 is configured to obtain the data provided by the terminal 110, and generate second commodity recommendation information for the target user according to the data. Optionally, in the process of generating the second commodity recommendation information, the server 120 undertakes a primary computing job, and the terminal device 110 undertakes a secondary computing job; alternatively, server 120 undertakes the secondary computing work and terminal device 110 undertakes the primary computing work; alternatively, the server 120 or the terminal 110 can be capable of undertaking the computing work individually.

The terminal device 110 may include, but is not limited to, a computer, a smart phone, a tablet computer, an e-book reader, a motion Picture experts group audio layer III (MP 3) player, a motion Picture experts group audio layer 4 (MP 4) player, a portable computer, a vehicle-mounted computer, a wearable device, a desktop computer, a set-top box, a smart television, and the like.

The server 120 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Alternatively, the number of the terminals 110 or the servers 120 may be more or less, and the embodiment of the present application is not limited thereto. In some embodiments, the terminal 110 and the server 120 may also serve as nodes in a blockchain system, and synchronize the first commodity recommendation information or the second commodity recommendation information to other nodes in the blockchain, so as to implement wide application of the commodity recommendation data.

The above briefly explains the scene schematic diagram of the present application, and the following takes the server 120 applied in fig. 1 as an example to explain in detail the time series analysis method based on the user behavior feature provided in the embodiment of the present application.

Referring to fig. 2, fig. 2 is a flowchart illustrating a time series analysis method based on user behavior characteristics according to an embodiment of the present application, including steps S201 to S203.

Step S201, obtaining first commodity recommendation information of a target application in a preset time range, and storing the first commodity recommendation information into a time sequence database.

In this embodiment, the first commodity recommendation information may be sales ranking list information, turnover rate ranking list information, or the like. Optionally, the best-selling products can be selected according to historical contemporaneous sales information gathered by the APP system to obtain the first commodity recommendation information, because the best-selling products are displayed in a paginated form, and the hot-selling products on the first page have the greatest influence on the user.

It should be noted that, a person skilled in the art may adaptively set the preset time range in combination with the actual application, in an example, the system first determines the preset time range for data acquisition and then performs the step S201, where the preset time range may be adaptively adjusted in combination with the actual requirement of the target user.

In one embodiment, the step S201 of obtaining the first commodity recommendation information of the target application within the preset time range may include the following steps:

The first commodity recommendation information is a recommendation basis table which is sorted based on a commodity recommendation index, the recommendation basis table comprises identification information and attribute information of corresponding recommended commodities, and the recommendation index is obtained based on an inventory turnover rate of the corresponding recommended commodities.

It can be understood that, in the embodiment, the commodity recommendation index is positively correlated with the sales and/or the survival turnover rate, wherein the recommended commodities are commodities screened according to the sales ranking list.

In one example, 1) the top 20% high sales products are sorted according to a leaderboard of sales. The specific screening method may be screening according to a database key function, wherein the database key function of the first 20% sales commodities is calculated as follows: the top 20% sales = (calcut ('[ sales amount ]', TOPN (counters ('table name')/0.2, 'table name', '[ amount ]'))). 2) Inventory turnover rates are then calculated for the selected products and ranked from high to low to form a leaderboard base table (i.e., a recommendation base table) and written to a redis database with a redisTimeSeries extension module. Wherein, the turnover rate calculation formula is as follows: inventory turnover = sales cost/average inventory.

In one example, according to the results of the two steps 1) and 2), all product IDs and basic attribute information of the popular list are preliminarily inquired and stored in a redis database as a popular list basic table.

Step S202, behavior feature data of the target user aiming at the first commodity recommendation information are obtained.

In this embodiment, the behavior feature data may include: and ordering, collecting or browsing a certain commodity by the user. Specifically, the behavior feature data of the target user can be obtained according to the relationship between the user search, order, browse, and collected commodity and the commodity information of the first commodity.

In the technical scheme of the present application, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the related information such as financial data or user data are all in accordance with the regulations of the relevant laws and regulations, and do not violate the good custom of the public order.

In an embodiment, to improve the efficiency of acquiring the behavior feature data, the present embodiment splits the commodity recommendation information into a plurality of Standardized Product Units (SPUs) and analyzes the user behavior features according to the SPUs. Specifically, the step S202 of acquiring the behavior feature data of the target user for the first product recommendation information may include the following steps:

Specifically, according to attribute information of a commodity searched, ordered, browsed and collected by a user, an SPU corresponding to the attribute information of the commodity is queried from a database, accumulated times of behavior data generated by the SPU and the user on the SPU are summarized, behavior feature data (which may be in a behavior data table form) is generated, and the behavior feature data is stored in a redis database.

It is understood that a standardized product unit is the smallest unit of aggregation of commodity information, and is a set of reusable, easily retrievable standardized information that describes the characteristics of a product. That is, a commodity with the same attribute value and property may be referred to as an SPU.

Further, in order to further improve the efficiency of acquiring the behavior feature data and the efficiency of analyzing the data, the first commodity recommendation information is stored in the redis database in a structure of an SPU, a SKU (Stock Keeping Unit) and an attribute, wherein each commodity data may be classified in advance, and the classification process may adopt the prior art, wherein the structural relationship between the SKU, the SPU and the classification attribute is shown in fig. 3.

Step S203, performing time-series aggregation analysis in the time-series database based on the first commodity recommendation information and the behavior feature data, and generating second commodity recommendation information according to an analysis result.

In one embodiment, the performing a time-series aggregation analysis in the time-series database based on the first product recommendation information and the behavior feature data in step S203 may include:

loading a RedisTimeSeries module in the time series database;

It can be understood that the RedisTimeSeries module does not belong to the built-in functional module of Redis, and in practical application, its source code can be compiled into dynamic link library redistimeries, so separately, and then loaded using loadmodule command, as shown below: so, loadmodule updates.

The specific process of creating the time series data set may be to create a time series data set by using a ts. In the ts.create command, it is also possible to set keys for time series data sets and expiration times (in milliseconds) for data sets, and to set tags for data sets to indicate attributes of the data sets. For example, the following command is executed to create a time series data set with key product, numBrowse, and a data validity period of 600 s. That is, the data in this set is automatically deleted 600s after it is created. Finally, by setting a tag attribute { product _ ID:1} to the set, it indicates that the data belonging to the product ID number 1 is recorded in the data set. For example: CREATE product NumBrowse RETENTION 600000 LABELS product_1;

further, inserting data by using a ts.add command, reading the latest data by using a ts.get command, wherein the data is inserted into the time sequence set by using the ts.add command, the time stamp and the specific numerical value can be included, and reading the latest data in the data set by using the ts.get command. For example, when the following TS.ADD command is executed, a piece of data is inserted into a Numbrowse set, and the browsing amount of a product in 8, 3 and 9 hours in 2020, 5 points is recorded; get command, the latest data just inserted will be read out. ADD product NumBrowse 1596416725; and TS.GET: product is NumBrowse;

and further, filtering the query data set by tag by adopting a TS.MGET command. When time series data of a plurality of products are stored, data of different products are stored in different sets, and latest data in a part of sets are inquired according to tags through a TS. Create a dataset using ts.create, the set may be set with tag attributes. When the query is needed, the set label attributes can be matched in the query condition, and only the latest data in the matched set is returned in the final query result. For example, assuming that a common 4 sets hold time-series data for 4 products whose ID numbers are 1, 2, 3, 4, product _ ID is set as a tag for each set when creating the data set. Mget command, as well as FILTER setting (this configuration item is used to set the FILTER condition of the set tag), the following ts.mget command may be used to query the data sets of all other products whose product _ id is not equal to 2, and return the latest piece of data in the respective set. MGET FILTER product _ id! And (5) =2.

In one embodiment, the performing the aggregation analysis on the time-series data set in step S203 may include the following steps:

It should be noted that, a person skilled in the art may adaptively set the preset aggregation type in combination with the actual application, and in some embodiments, other aggregation types, such as counting, may be adopted in addition to averaging, maximizing/minimizing, or summing.

Range is further employed to support range queries that require aggregated computation. Range commands are used to specify the time range of the data to be queried, while the type of AGGREGATION calculation to be performed is specified with the AGGREGATION parameter. The aggregation computation types supported by the RedisTimeSeries module are rich, including averaging (avg), max/min, sum (sum), and so on. For example, when the following commands are executed, the data in the period of 8/month/3/9/5/2020 and the data in the period of 8/month/3/9/12/2020 can be averaged for each 180s time window. For example, TS. RANGE product: numBrowse 1596416700 1596417120AGGREGAGATION avg 180000.

The use of the RedisTimeSeries module of this embodiment enables aggregating data according to mean, minimum, maximum, sum, count, range, first and last, so that statistical analysis becomes simple and fast. It can run more than 100000 aggregations per second with a delay of the order of milliseconds and also perform a reverse lookup on the tag within a specific time frame.

In an embodiment, the behavior feature data is a user behavior data table, and the generating of the second product recommendation information according to the analysis result in step S203 may include the following steps:

In one implementation, the ranking of the hot sell list base table is performed according to the user behavior data table to form a final hot sell list. And selecting a commodity record set which is present in the user behavior data table and the hot sell list basic table, sequencing the commodity record set according to the sales and placing the commodity record set on the hot sell list basic table to form a final hot sell list commodity table, and outputting the commodity record set to the front end for displaying when the user refreshes the page each time so as to facilitate the user to check.

In the embodiment of the application, the hot sell list basic table data is used as a reference, the related data is stored in a Redis database, aggregation calculation according to a time range is directly performed on the data on a Redis example through the data type and the access interface provided by the extension module redisTimeSeries, convenience is rapidly provided for data analysis, the hot sell lists are finally sorted again in real time according to user behavior data, and products meeting actual requirements of the users are recommended to the users.

Correspondingly, an embodiment of the present application further provides a time series analysis apparatus based on user behavior characteristics, as shown in fig. 4, including:

a first obtaining module 41 configured to obtain first commodity recommendation information of a target application within a preset time range, and store the first commodity recommendation information in a time sequence database

A second obtaining module 42, configured to obtain behavior feature data of the target user for the first commodity recommendation information;

and the analysis recommending module 43 is configured to perform time-series aggregation analysis on the basis of the first commodity recommendation information and the behavior feature data in the time-series database, and generate second commodity recommendation information according to an analysis result.

In one embodiment, the first obtaining module 41 is specifically configured to obtain the commodity sales amount information of the target application within a preset time range, and obtain the first commodity recommendation information based on the commodity sales amount information.

In one embodiment, the second obtaining module 42 includes:

the splitting unit is used for splitting the first commodity recommendation information into a plurality of standardized product units SPU;

a behavior feature acquisition unit configured to acquire behavior feature data of the target user based on the standardized product unit SPU and the behavior data generated by the target user for the SPU.

In one embodiment, the analysis recommendation module 43 comprises:

a loading unit configured to load a RedisTimeSeries module in the time series database;

and the aggregation analysis unit is arranged for creating a time sequence data set based on the first commodity recommendation information and the behavior characteristic data by utilizing a RedisTimeSeries module, and carrying out aggregation analysis on the time sequence data set.

In an embodiment, the aggregation analysis unit is specifically configured to perform aggregation analysis on the time-series data set based on a preset aggregation type, where the preset aggregation type includes at least one of: averaging, maximum/minimum or summing.

In an embodiment, the behavior feature data is a user behavior data table, and the analysis recommendation module 43 is specifically configured to reorder the recommendation basis table based on the user behavior data table according to an analysis result to obtain the second commodity recommendation information.

It should be noted that, the apparatus provided in the present application can correspondingly implement all the method steps implemented by the server in the foregoing method embodiment, and can achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as those in the method embodiment are not repeated herein.

Correspondingly, an electronic device is further provided in an embodiment of the present application, as shown in fig. 5, including: a memory 51 and a processor 52;

the memory 51 stores computer-executable instructions;

the processor 52 executes the computer-executable instructions stored in the memory 51, so that the electronic device executes the user behavior feature-based time series analysis method.

The embodiment of the present application correspondingly provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the time series analysis method based on the user behavior characteristics.

The embodiment of the present application correspondingly further provides a computer program product, where the computer program product includes computer program code, and when the computer program code runs on a computer, the computer is caused to execute the time series analysis method based on the user behavior feature.

The chip comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor is used for calling and running the computer program from the memory and executing the time series analysis method based on the user behavior characteristics.

It should be noted that, the computer-readable storage medium, the program product, and the chip provided in the present application can correspondingly implement all the method steps implemented by the server in the foregoing method embodiments, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those of the method embodiments in this embodiment are omitted here.

It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).

The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer.

In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.

In the description of the embodiments of the present application, the term "and/or" merely indicates an association relationship describing an associated object, and indicates that three relationships may exist, for example, a and/or B, and may indicate: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" means any one of a variety or any combination of at least two of a variety, for example, including at least one of A, B, and may mean any one or more elements selected from the group consisting of A, B and C communication. Further, the term "plurality" means two or more unless specifically stated otherwise.

In the description of the embodiments of the present application, the terms "first," "second," "third," "fourth," and the like (if any) are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A time series analysis method based on user behavior characteristics is characterized by comprising the following steps:

and performing time-series aggregation analysis in the time-series database based on the first commodity recommendation information and the behavior feature data, and generating second commodity recommendation information according to an analysis result.

2. The method according to claim 1, wherein the obtaining of the first commodity recommendation information of the target application within the preset time range comprises:

3. The method according to claim 1 or 2, wherein the first item recommendation information is a recommendation basis table sorted based on an item recommendation index, the recommendation basis table including identification information and attribute information of the corresponding recommended item, the recommendation index being obtained based on an inventory turnover rate of the corresponding recommended item.

4. The method according to claim 1, wherein the obtaining behavior feature data of the target user for the first commodity recommendation information comprises:

5. The method of claim 1, wherein performing a time-series aggregated analysis in the time-series database based on the first commodity recommendation information and the behavior feature data comprises:

loading a RedisTimeSeries module in the time series database;

6. The method of claim 5, wherein the performing the aggregate analysis on the set of time-series data comprises:

7. The method of claim 3, wherein the behavior feature data is a user behavior data table,

8. A time series analysis device based on user behavior characteristics is characterized by comprising:

9. An electronic device, comprising: a memory and a processor;

the memory stores computer-executable instructions;

the processor executes the computer-executable instructions stored in the memory to cause the electronic device to perform the user behavior feature based time series analysis method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the method for user behavior feature-based time series analysis according to any one of claims 1 to 7 when executed by a processor.