CN115866280A

CN115866280A - Live webcast user behavior analysis method, device and equipment based on big data

Info

Publication number: CN115866280A
Application number: CN202211227989.0A
Authority: CN
Inventors: 陈赣; 刘丽
Original assignee: Ningbo Richard Cultural Creativity Co ltd
Current assignee: Ningbo Richard Cultural Creativity Co ltd
Priority date: 2023-01-05
Filing date: 2023-01-05
Publication date: 2023-03-28

Abstract

The invention relates to an artificial intelligence technology, and discloses a live webcast user behavior analysis method based on big data, which comprises the following steps: receiving a request for data analysis, and acquiring a data interface according to the request; monitoring the flow of the data interface to obtain the flow data of the data interface; extracting time sequence characteristics and spatial distribution characteristics of the flow data; embedding points on a preset interface of a target network live broadcast platform, and acquiring an interface log of each interface by using the embedded points; and acquiring behavior data of audiences according to the interface log, and generating a user behavior analysis report of the target network live broadcast platform by using the time sequence characteristic, the spatial distribution characteristic and the behavior data. In addition, the invention also relates to a block chain technology, and the data list can be stored in the node of the block chain. The invention also provides a live webcast user behavior analysis device and electronic equipment based on the big data. The invention can improve the efficiency of analyzing the behavior of the live webcast user.

Description

Live webcast user behavior analysis method, device and equipment based on big data

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a live webcast user behavior analysis method, a live webcast user behavior analysis device and live webcast user behavior analysis equipment based on big data.

Background

With the continuous development of mobile communication and internet technology, live webcasting gradually becomes an online entertainment and information propagation mode favored by people in a new media environment, is widely applied to aspects of classroom teaching, real-person shows, electric competition, brand marketing and the like at present, is a novel information communication mode, can enable audiences to see live audio and video in the scene where the anchor is located, and can interact with the anchor in a mode of enjoying or publishing comments, and has the advantages of strong interactivity, high space-time adaptability and the like compared with the traditional information propagation media.

At present, the user behavior data of the live webcast platform is huge, and the classification processing is not performed on the flow data, so that the data is presented without rules, the commonalities and differences among the data are difficult to analyze only by manually identifying the data, and if the commonalities and differences among the data are required to be accurate, a great deal of waste of time and energy is inevitably caused, so that how to improve the user behavior analysis efficiency of live webcast becomes a problem to be solved urgently.

Disclosure of Invention

The invention provides a method, a device and equipment for analyzing network live broadcast user behaviors based on big data, and mainly aims to solve the problem of low efficiency in analyzing the network live broadcast user behaviors.

In order to achieve the above object, the present invention provides a live webcast user behavior analysis method based on big data, which includes:

receiving a request for analyzing data of a target network live broadcast platform, and acquiring a data interface of the target network live broadcast platform according to the request;

monitoring the flow of the data interface to obtain the flow data of the data interface;

extracting time sequence characteristics of the flow data, extracting spatial distribution characteristics of the flow data, and collecting the time sequence characteristics and the spatial distribution characteristics as platform load data of the target network live broadcast platform;

performing point burying on a preset interface of the target network live broadcast platform, and acquiring an interface log of each interface of the target network live broadcast platform by using the point burying;

and acquiring behavior data of audiences of the target network live broadcast platform according to the interface log, and generating a user behavior analysis report of the target network live broadcast platform by using the platform load data and the behavior data.

Optionally, the obtaining a data interface of the target webcast platform according to the request includes:

acquiring an interface protocol corresponding to the request;

converting the input parameter information and the output parameter information in the interface protocol according to a preset description mode to obtain interface information;

and obtaining a data interface of the target network live broadcast platform according to the interface information.

Optionally, the monitoring the traffic of the data interface to obtain the traffic data of the data interface includes:

acquiring flow information of all data interfaces in the target network live broadcast platform;

acquiring an interface ID of each data interface, and classifying the traffic information by using the interface ID to obtain classified traffic;

and screening the classified flow by using a preset flow screening model to obtain flow data of the data interface.

acquiring an input data packet of the data interface, and determining version information corresponding to the input data packet;

determining data IDs of input data of the data interfaces one by one according to the version information, and acquiring output data of the input data according to the data IDs;

and obtaining flow data of a data interface by using the input data and the output data.

Optionally, the extracting the spatial distribution feature of the flow data includes:

dividing the flow data according to a preset geographical partition to obtain a geographical partition flow set;

selecting one geographical partition flow from the geographical partition flow sets as a target geographical partition flow;

obtaining the central flow of the geographical partition flow set;

obtaining the distance between the target geographical partition flow and the central flow by using a spatial weight algorithm as follows:

wherein the content of the first and second substances,

representing a distance of the target geo-partitioned traffic from the central traffic, device for selecting or keeping>

Represents the target geo-partition traffic, <' > or>

Indicates the central flow, is present>

Indicates the fifth->

Based on the geographical division traffic, < > or >>

Representing a total number of said geo-partitioned traffic;

and generating the spatial distribution characteristics of the flow data according to the distance.

Optionally, the embedding the preset interface of the target network live broadcast platform includes:

acquiring a preset embedded point event, and performing code conversion on the embedded point event to obtain an abstract source code corresponding to the embedded point event;

and adding the abstract source code to a key node of a preset interface of the target network live broadcast platform to finish point burying.

Optionally, the obtaining behavior data of the audience of the target webcast platform according to the interface log includes:

screening the interface log according to the service chain identification in the interface log to obtain a target interface log;

dividing the target interface log according to a preset index to obtain a level log;

and analyzing the hierarchical logs in a behavior mode to obtain behavior data of audiences of the target network live broadcast platform.

In order to solve the above problem, the present invention further provides a device for analyzing the user behavior of live webcasting based on big data, where the device includes:

the data interface module is used for receiving a request for analyzing data of a target network live broadcast platform and acquiring a data interface of the target network live broadcast platform according to the request;

the flow data module is used for monitoring the flow of the data interface to obtain the flow data of the data interface;

the platform load module is used for extracting the time sequence characteristics of the flow data, extracting the spatial distribution characteristics of the flow data, and collecting the time sequence characteristics and the spatial distribution characteristics as the platform load data of the target network live broadcast platform;

the interface log module is used for embedding points in a preset interface of the target network live broadcast platform and acquiring an interface log of each interface of the target network live broadcast platform by using the embedded points;

and the analysis report module is used for acquiring behavior data of audiences of the target network live broadcast platform according to the interface log and generating a user behavior analysis report of the target network live broadcast platform by using the platform load data and the behavior data.

In order to solve the above problem, the present invention also provides an electronic device, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the big data based webcast user behavior analysis method described above.

According to the embodiment of the invention, the data interface of the target network live broadcast platform is obtained through the received request, the flow monitoring is carried out on the data interface, the flow data of the data interface is obtained, the accuracy of the flow data is improved, the obtained flow data is ensured to be required, the obtained flow data has real-time performance, the time sequence characteristic and the spatial distribution characteristic of the flow data are extracted, the flow data can be better represented by utilizing the time sequence characteristic and the spatial distribution characteristic, the preset interface of the target network live broadcast platform is subjected to point burying, the interface log of each interface of the target network live broadcast platform is obtained by utilizing the point burying, the comprehensiveness and the effectiveness of the flow data are ensured, the interface logs are subjected to hierarchical classification, the hierarchical logs are obtained, and the retrieval efficiency can be improved. Therefore, the invention provides a method, a device and equipment for analyzing the behavior of the live webcast user based on big data, and can solve the problem of low efficiency of analyzing the behavior of the live webcast user.

Drawings

Fig. 1 is a schematic flowchart of a big data-based webcast user behavior analysis method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of acquiring traffic data according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of acquiring behavior data according to an embodiment of the present invention;

fig. 4 is a functional block diagram of a big data-based webcast user behavior analysis apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device implementing the big data-based live webcast user behavior analysis method according to an embodiment of the present invention.

The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.

The embodiment of the application provides a live webcast user behavior analysis method based on big data. The execution subject of the big data-based webcast user behavior analysis method includes but is not limited to at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the big data-based webcast user behavior analysis method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides 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.

Fig. 1 is a schematic flow chart of a live webcast user behavior analysis method based on big data according to an embodiment of the present invention. In this embodiment, the method for analyzing the user behavior of the webcast based on big data includes:

s1, receiving a request for analyzing data of a target network live broadcast platform, and acquiring a data interface of the target network live broadcast platform according to the request.

In the embodiment of the present invention, the request includes a request line, a message header, and a message body, where the request line is in the first line of the request and includes a request type, a request resource path, a version and a type of a protocol, where when the request type is get, request parameters and values are included in the resource path, and when the request type is post, the request parameters and values are placed in the message body.

In this embodiment of the present invention, the request may use a parser to parse the message header to obtain the user ID in the request, where the parser includes CarakanC/C + +, squirrel fisherc + +, squirrel fisher xtremc + +, and the like.

In detail, the parsing the message header by using a parser to obtain the user ID in the request includes: assigning attributes to the request by using a default reflection construction method to obtain a modifier list of the attributes, wherein the returned modifier is a number, and each number is the code number of the modifier; and converting the Modifier into a character string by using a toString statement of a Modifier class, and acquiring the name of the character string, namely the name of the character string is the user ID.

In detail, the data interface of the target network live broadcast platform is obtained to obtain the flow data by using the data interface.

In this embodiment of the present invention, the acquiring a data interface of the target network live broadcast platform according to the request includes:

acquiring an interface protocol corresponding to the request;

In detail, the converting the parameter entering information and the parameter exiting information in the interface protocol according to a preset description mode to obtain the interface information includes: determining the parameter entering information and parameter exiting information of the interface to be acquired according to the interface protocol; the parameter entering information comprises a merchant identifier, a commodity number and an encrypted signature, and the parameter exiting information comprises an error code, error information and commodity information; for the same parameter, different network platforms have different description modes; and determining the description mode of the access information and the access information corresponding to the network platform from the mapping relation between the network platform and the access information according to the network platform to which the interface to be acquired belongs, and converting the access information and the access information of the network platform according to the preset description mode to obtain the interface information.

In the embodiment of the invention, the reason for acquiring the data interface of the target network live broadcast platform according to the request is that the request has an interface protocol, and when a certain data interface needs to be identified, the interface protocol can be used for carrying out accurate identification.

S2, carrying out flow monitoring on the data interface to obtain flow data of the data interface.

In the embodiment of the present invention, the flow data of the data interface is obtained to be subsequently sorted, which corresponds to an information collection stage in a common project.

In detail, the data interface realizes project separation and reduces the coupling degree between codes, and the data interface prescribes execution matters of a program, namely the data interface prescribes rules to be followed by the program.

In this embodiment of the present invention, as shown in fig. 2, the monitoring traffic of the data interface to obtain traffic data of the data interface includes:

s21, acquiring flow information of all data interfaces in the target network live broadcast platform;

s22, acquiring an interface ID of each data interface, and classifying the flow information by using the interface ID to obtain classified flow;

and S23, screening the classified flow by using a preset flow screening model to obtain flow data of the data interface.

In detail, a traffic monitoring tool can be used for monitoring traffic of The data interface, the obtained interface access log of The data interface can be used for performing visual analysis on The interface access log to obtain traffic data of The data interface, and The traffic monitoring tool comprises Microsoft Network Monitor, um, advanced IP Scanner, capsa Free, the dual and The like; the flow monitoring tool generally tends to capture and send as much events and information as possible during monitoring, and performs work such as trigger condition matching, statistical calculation and the like at the back end of data processing so as to better support change of attention points and backtracking of historical data

In detail, the interface ID is a unique identifier of the data interface, and the interface IDs of different data interfaces have differences, for example: in China, 14 million people are distinguished by identity card numbers.

Further, the traffic information may be sorted and classified according to attributes such as usage time, a target IP address, a peak frequency band, and the number of users of the traffic information, and may be recorded and analyzed through an event table, a user attribute table, and a target object table, where each record in the event table describes that a user completes a specific event at a certain time point and a certain place in a certain manner, the user attribute table is a user, each user has a record, and the user attributes include natural attributes such as a platform, a network, a service provider, a mobile phone model, a region, and the like, and unnatural attributes such as a user class, whether the user class is large V, and may be associated with the event table analysis through the user, and the target object table, where the main body is a target object, and the target object is usually a main carrier of a service, such as a short video APP, and the target object is a video, and may be associated with the event table analysis through the target object.

In detail, the determining the presentation form of the classified traffic by using a preset traffic screening model includes: the classified flow comprises attributes such as using time, target IP addresses, peak frequency bands and the number of users, and after the preset flow screening model is used for screening, the flow data only comprises the using time, the target IP addresses and the number of users.

In this embodiment of the present invention, the monitoring traffic of the data interface to obtain traffic data of the data interface includes:

In detail, the data interface refers to an interface between two systems or two components, and may be a connection circuit between two hardware devices, or a common logic boundary between two software devices, the input data packet is an input data set related to the data interface, and the input data set contains version information of the input data packet, and the version information includes but is not limited to: the system version corresponding to the input data packet, the path corresponding to the data packet, and the like, for example: when the project is established, the version information is specified to be 0.0.0, the version information is changed once when the data interface is updated once, and the version information is uniquely determined.

In the embodiment of the present invention, the collecting of the traffic data of the data interface is to further analyze the traffic data to obtain the characteristics of the traffic data, and the traffic monitoring of the data interface can obtain the traffic data, so that the current most real situation can be better reflected, and the real-time performance of the data can be ensured.

And S3, extracting the time sequence characteristics of the flow data, extracting the spatial distribution characteristics of the flow data, and collecting the time sequence characteristics and the spatial distribution characteristics as platform load data of the target network live broadcast platform.

In the embodiment of the present invention, most of the current load research on the target network live broadcast platform focuses on mining time sequence characteristics such as time-of-day effect, time-of-week effect, long-term rule and the like of the live broadcast platform load from time sequence change rules in aspects of system bandwidth, anchor scale, audience number, appreciation amount, comment amount and the like, for example: by collecting live broadcast data of a live broadcast platform in 2016 for 14 days, the audience number and the anchor number show almost consistent change rules in one day, and both decrease from 21 to 8.

Further, the spatial distribution characteristic represents a user distribution of the target webcast platform, such as: the distribution form of the audience number and the watching times of the early network television live broadcast platform among divided geographical blocks is approximate to Zipf distribution; kaytoue et al, by statistically analyzing the distribution of the anchor of a live platform in different time zones, showed that most anchors in the platform are from north america, europe and east asia, consistent with the distribution law that the servers of a live platform are centrally located in north america, europe and asia.

In detail, the traffic data can be better characterized by analyzing the time sequence characteristics and the spatial distribution characteristics of the traffic data, and the method has guiding significance for optimizing resource configuration and providing economic and stable load support for a target network live broadcast platform.

In this embodiment of the present invention, the extracting the time-series characteristic of the flow data includes:

carrying out noise reduction processing on the flow data, and dividing the flow data obtained after the noise reduction processing according to a preset time interval to obtain a plurality of digital signals;

converting the digital signal by using the following signal conversion formula to obtain a frequency domain signal:

wherein the content of the first and second substances,

is the frequency-domain signal, < >>

Is the digital signal, is>

Is a switch variable, < > is>

Is a natural logarithm>

Is an imaginary unit>

Is angular velocity->

Is time->

Is the abscissa on the coordinate axis in the conversion of the digital signal into the frequency-domain signal, and->

Is the ordinate on the coordinate axis when the digital signal is converted into the frequency domain signal;

and generating the time sequence characteristics of the flow data according to the frequency domain signals.

In detail, the denoising process is to delete unnecessary information in the traffic data and perform a dimensionality reduction process on the traffic data.

In detail, in the digital signal coordinate system, the horizontal axis represents time, and the vertical axis represents changes of the digital signal, and the digital signal is represented in the digital signal coordinate system.

In detail, the frequency domain signal coordinate system refers to a coordinate system used for describing frequency characteristics of a frequency domain signal, wherein a horizontal axis of the frequency domain signal coordinate system is frequency, a vertical axis of the frequency domain signal coordinate system is amplitude of the frequency signal, and the frequency domain signal is represented in the frequency domain signal coordinate system.

Further, according to a curve graph of the frequency domain signal in the frequency domain signal coordinate system, an extreme value and a slope of the curve graph are calculated, and the time sequence characteristics of the frequency domain signal are determined.

In an embodiment of the present invention, the extracting spatial distribution characteristics of the flow data includes:

obtaining the central flow of the geographical partition flow set;

obtaining the distance between the target geo-partitioned traffic and the center traffic using a spatial weighting algorithm as follows:

wherein the content of the first and second substances,

Represents the target geo-partition traffic, <' > or>

Represents the central flow rate, < '> or <' > is selected>

Represents a fifth or fifth party>

Based on the geographical division traffic, < > or >>

Representing the geo-partitioned trafficThe total number of (2);

In the embodiment of the invention, the geographical partition can be determined according to the boundary between the countries on the world map, or the geographical partition can be obtained according to the Chinese map, and each province and the direct prefecture city are taken as the geographical partition.

In detail, the step of obtaining the central flow of the flow set of the geographical partition is to convert the flow data in the geographical partition into flow vectors, calculate central vectors of all the flow vectors, and determine the positions of different flow data by using the central vectors and the flow vectors in the geographical partition, so as to form the spatial distribution characteristics of the flow data.

In detail, the digital signal is converted through the signal conversion formula, the processing of the flow data can be accelerated, the spatial distribution characteristics of the flow data are obtained through the spatial weight algorithm, and the algorithm complexity is reduced.

And S4, embedding points on the preset interface of the target network live broadcast platform, and acquiring an interface log of each interface of the target network live broadcast platform by using the embedded points.

In the embodiment of the invention, the event of each interface of the target network live broadcast platform is monitored by using the buried point, the judgment and the capture are carried out when the event needing to be concerned occurs, then the necessary context information is obtained, and finally the information is arranged and sent to the server side.

And further, according to the buried points, the receipts are collected, the application use condition is tracked, and relevant data support is provided for subsequent operation and product optimization.

In detail, in order to improve the efficiency and the usability of the site-burying work, the clumsy acquisition code programming is not used for defining the trigger condition and the subsequent behaviors of behavior acquisition, and the definition and the capture of the key events are completed by back-end configuration or front-end visual selection and the like.

In an embodiment of the present invention, the embedding the preset interface of the target network live broadcast platform includes:

Wherein the abstract source code is an abstract syntax tree, and is represented by a tree of an abstract syntax structure of the source code, and the abstract source code cannot represent every detail appearing in the real syntax, but is only structural and content-related details, such as: grouping brackets are implicit in the tree structure, and syntax structures like the if-condition-then expression can be represented by a single node with three branches.

Further, in an optional embodiment of the present invention, the acquisition of the to-be-added buried point event corresponding to the buried point information may be collected by a client, the code conversion of the buried point event may be implemented by a conversion function, for example, an atoi function, and the adding of the abstract source code is to filter the abstract source code by using a preset node index, so as to add the abstract source code to a key node of the preset interface.

In the embodiment of the invention, the interface log obtained by embedding points ensures the comprehensiveness and the effectiveness of the flow data.

And S5, acquiring behavior data of audiences of the target network live broadcast platform according to the interface log, and generating a user behavior analysis report of the target network live broadcast platform by using the platform load data and the behavior data.

In the embodiment of the invention, the interface log is visually displayed and analyzed to obtain the service chain identifier of the interface log, and the unique log identifier is used for tracing the audience behavior in the target network live broadcast platform to obtain the behavior data of the audience.

In detail, the behavior data includes: selecting a live broadcast room for viewing, switching or exiting the live broadcast room, commenting or enjoying in the live broadcast room, and viewer viewing the live broadcast-induced behavior (e.g., directed by the anchor to purchase goods), such as: if network failure, live broadcast closing, no interest and the like occur in the live broadcast watching process, audiences can reconnect the current live broadcast room, switch to other live broadcasts or directly quit the live broadcast platform.

In detail, the watching law of the audience behaviors of the target live webcast platform is analyzed, various behaviors and the back psychology of the audience are researched, and the method has important decision value for understanding the reason why the audience participates in live webcast, improving user experience and providing more valuable live webcast service for users.

In an embodiment of the present invention, referring to fig. 3, the acquiring, according to the interface log, behavior data of an audience of the target webcast platform includes:

s31, screening the interface log according to the service chain identification in the interface log to obtain a target interface log;

s32, dividing the target interface log according to a preset index to obtain a level log;

and S33, performing behavior pattern analysis on the hierarchical log to obtain behavior data of audiences of the target network live broadcast platform.

In the embodiment of the present invention, the service chain identifier is used to trace back the behavior of the audience; the target interface log is divided according to the preset index, a trained VGG16 model can be used for classifying data with relatively small number of current classifications, and B-CNN (Branch CNN) can also be used for classifying data to be classified with large number.

In detail, the analyzing the behavior pattern of the hierarchical log means to determine a series of behaviors of the audience, such as: the type of live room selected for viewing, the type of live room switched or exited, the behavior of comments or enjoying in the live room, and the behavior of viewers caused by viewing the live room.

In the embodiment of the invention, the interface log data is huge, the target interface log is divided according to the preset index to obtain the hierarchical log, the retrieval efficiency can be improved, the uniqueness of each row of data in the database table can be ensured through the preset data table index, the retrieval speed of the data is greatly accelerated, and the method is also the main reason for creating the index.

According to the embodiment of the invention, the data interface of the target network live broadcast platform is obtained through the received request, the flow monitoring is carried out on the data interface, the flow data of the data interface is obtained, the accuracy of the flow data is improved, the obtained flow data is ensured to be required, the obtained flow data has real-time performance, the time sequence characteristic and the spatial distribution characteristic of the flow data are extracted, the flow data can be better represented by utilizing the time sequence characteristic and the spatial distribution characteristic, the preset interface of the target network live broadcast platform is subjected to point burying, the interface log of each interface of the target network live broadcast platform is obtained by utilizing the point burying, the comprehensiveness and the effectiveness of the flow data are ensured, the interface logs are subjected to hierarchical classification, the hierarchical logs are obtained, and the retrieval efficiency can be improved. Therefore, the invention provides a live webcast user behavior analysis method based on big data, which can solve the problem of low live webcast user behavior analysis efficiency.

Fig. 4 is a functional block diagram of a big data-based live webcast user behavior analysis apparatus according to an embodiment of the present invention.

The webcast user behavior analysis device 100 based on big data can be installed in electronic equipment. According to the implemented functions, the big data based webcast user behavior analysis apparatus 100 may include a data interface module 101, a traffic data module 102, a platform load module 103, an interface log module 104, and an analysis report module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the platform load module is used for extracting time sequence characteristics of the flow data, extracting spatial distribution characteristics of the flow data, and collecting the time sequence characteristics and the spatial distribution characteristics as platform load data of the target network live broadcast platform;

Fig. 5 is a schematic structural diagram of an electronic device for implementing a big data-based live webcast user behavior analysis method according to an embodiment of the present invention.

The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a big data based webcast user behavior analysis program, stored in the memory 11 and executable on the processor 10.

In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory 11 (for example, executing a big data-based webcast user behavior analysis program and the like) and calling data stored in the memory 11.

The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used to store not only application software installed in the electronic device and various types of data, such as codes of a big data-based webcast user behavior analysis program, but also temporarily store data that has been output or is to be output.

The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit, such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

Only electronic devices having components are shown, it will be understood by those skilled in the art that the structures shown in the figures do not constitute limitations on the electronic devices, and may include fewer or more components than shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The big data based webcast user behavior analysis program stored in the memory 11 of the electronic device is a combination of a plurality of instructions, and when running in the processor 10, can realize that:

Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.

Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM).

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A big data-based live webcast user behavior analysis method is characterized by comprising the following steps:

s1, receiving a request for analyzing data of a target network live broadcast platform, and acquiring a data interface of the target network live broadcast platform according to the request;

s2, carrying out flow monitoring on the data interface to obtain flow data of the data interface;

s3, extracting time sequence characteristics of the flow data, extracting space distribution characteristics of the flow data, and collecting the time sequence characteristics and the space distribution characteristics as platform load data of the target network live broadcast platform, wherein the extracting of the time sequence characteristics of the flow data comprises the following steps:

s11, carrying out noise reduction on the flow data, and dividing the flow data subjected to noise reduction according to a preset time period to obtain a plurality of digital signals;

s12, converting the digital signal by using the following signal conversion formula to obtain a frequency domain signal:

wherein the content of the first and second substances,

is the frequency-domain signal, < >>

Is the digital signal, is>

Is a switch variable, < > is>

Is a natural logarithm>

Is an imaginary unit, is greater than or equal to>

Is angular velocity->

Is time, is>

s13, generating time sequence characteristics of the flow data according to the frequency domain signals;

s4, embedding points in a preset interface of the target network live broadcast platform, and acquiring an interface log of each interface of the target network live broadcast platform by using the embedded points;

2. The big data-based webcast user behavior analysis method according to claim 1, wherein the obtaining of the data interface of the target webcast platform according to the request includes:

acquiring an interface protocol corresponding to the request;

converting the access information and the access information in the interface protocol according to a preset description mode to obtain interface information;

3. The big data-based webcast user behavior analysis method according to claim 1, wherein the performing traffic monitoring on the data interface to obtain the traffic data of the data interface includes:

4. The big data-based webcast user behavior analysis method according to claim 1, wherein the performing traffic monitoring on the data interface to obtain the traffic data of the data interface includes:

5. The big-data-based webcast user behavior analysis method according to claim 1, wherein the extracting the spatial distribution feature of the traffic data includes:

obtaining the central flow of the geographical partition flow set;

wherein, the first and the second end of the pipe are connected with each other,

Represents the target geo-partition traffic, <' > or>

Indicates the central flow, is present>

Indicates the fifth->

Traffic of the geographical zone，/>

Representing a total number of said geo-partitioned traffic;

6. The big-data-based webcast user behavior analysis method as claimed in claim 1, wherein the embedding of the preset interface of the target webcast platform comprises:

acquiring a preset buried point event, and performing code conversion on the buried point event to obtain an abstract source code corresponding to the buried point event;

7. The big-data-based webcast user behavior analysis method according to any one of claims 1 to 6, wherein the obtaining behavior data of the audience of the target webcast platform according to the interface log comprises:

8. A big data-based live webcast user behavior analysis device, the device comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a big data based webcast user behavior analysis method as claimed in any one of claims 1 to 7.