CN115022098A

CN115022098A - Artificial intelligence safety target range content recommendation method, device and storage medium

Info

Publication number: CN115022098A
Application number: CN202210949803.6A
Authority: CN
Inventors: 不公告发明人
Original assignee: Beijing Real AI Technology Co Ltd
Current assignee: Beijing Real AI Technology Co Ltd
Priority date: 2022-08-09
Filing date: 2022-08-09
Publication date: 2022-09-06
Anticipated expiration: 2042-08-09
Also published as: CN115022098B

Abstract

The embodiment of the application relates to the field of artificial intelligence safety, and provides an artificial intelligence safety shooting range content recommendation method, an artificial intelligence safety shooting range content recommendation device and a storage medium. According to the scheme, when the user logs in the server, the server can determine the first recommended page data based on the user login information and send the first recommended page data to the user side, so that uniform page data is prevented from being recommended to the user side, and the recommended page data can be used for safety attack and defense drilling or basic knowledge learning of the artificial intelligent model.

Description

Artificial intelligence safety shooting range content recommendation method, device and storage medium

Technical Field

The application relates to the technical field of artificial intelligence safety, in particular to an artificial intelligence safety target range content recommendation method, an artificial intelligence safety target range content recommendation device and a storage medium.

Background

The network security shooting range system is an online deployment application which can provide actual attack and defense environments and can provide multifunctional and diversified network security actual combat scenes for users; the user can deepen the understanding of the network safety and improve the network safety protection level through the safety attack and defense drilling target ground environment of different levels. In the research and practice processes of the prior art, the inventor of the embodiment of the application finds that the system building and the safety attack and defense drilling in the conventional network safety shooting range system are all directed at the traditional system codes, so that a uniform user page is pushed to a user, and the conventional network safety shooting range system is not suitable for the safety attack and defense drilling or basic knowledge learning of an artificial intelligence model in an artificial intelligence safety scene.

Disclosure of Invention

The embodiment of the application provides an artificial intelligence safety shooting range content recommendation method, device and storage medium, which can rapidly log in an artificial intelligence safety shooting range platform and carry out AI safety shooting range learning or practice based on first recommendation page data, and the obtained use data can also be used as a data set basis for carrying out page content recommendation when a user logs in the number of the artificial intelligence safety shooting range platforms next time, so that the user can more easily carry out AI safety shooting range learning or practice based on the artificial intelligence safety shooting range platform.

In a first aspect, a method for recommending artificial intelligence safety shooting range content provided in an embodiment of the present application is introduced from a server side perspective, where the method includes:

receiving user login information sent by a user side;

determining first recommended page data according to the received user login information, and sending the first recommended page data to a user side; the first recommendation page data comprises recommendation data of a plurality of artificial intelligence safety targets;

acquiring service end use data corresponding to the first recommended page data; the server side use data comprises server side resource consumption data and server side bandwidth use data;

if the bandwidth use data of the server in the service use data is larger than the bandwidth threshold, determining that the data is in an AI safety shooting range learning mode, and acquiring first use data corresponding to the first recommended page data;

if the server resource consumption data in the server use data are larger than the resource consumption threshold, determining that the target is an AI safe shooting range practice mode, and acquiring second use data corresponding to the first recommended page data;

determining a current tendency matrix according to the first usage data or the second usage data; each row vector in the current tendency degree matrix represents a preference value of a user for a corresponding page tag, the preference value of each page tag is determined based on the access operation of the page tag and the page residence time, and the current tendency degree matrix is used for screening a recommended content set sent to a server side for logging in the user side next time.

In a second aspect, there is provided a function of implementing the artificial intelligence safety shooting range content recommendation method provided corresponding to the first aspect. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions, which may be software and/or hardware.

In one possible design, the apparatus includes:

a transceiver module and a processing module;

the receiving and sending module is used for receiving user login information sent by a user side;

the processing module is used for determining first recommended page data according to the user login information received by the transceiving module and sending the first recommended page data to a user side; the first recommendation page data comprises recommendation data of a plurality of artificial intelligence safety targets; acquiring service end use data corresponding to the first recommended page data; the server side use data comprises server side resource consumption data and server side bandwidth use data; if the bandwidth use data of the server in the service use data is larger than the bandwidth threshold, determining that the data is in an AI safety shooting range learning mode, and acquiring first use data corresponding to the first recommended page data; if the server resource consumption data in the server use data are larger than the resource consumption threshold, determining that the target is an AI safe shooting range practice mode, and acquiring second use data corresponding to the first recommended page data;

the processing module is further used for determining a current tendency matrix according to the first usage data or the second usage data; each row vector in the current tendency degree matrix represents a preference value of a user for a corresponding page tag, the preference value of each page tag is determined based on the access operation of the page tag and the page residence time, and the current tendency degree matrix is used for screening a recommended content set sent to a server side for logging in the user side next time.

Yet another aspect of the embodiments of the present application provides an artificial intelligence security range content recommendation device, which includes at least one connected processor, a memory and a transceiver, wherein the memory is used for storing a computer program, and the processor is used for calling the computer program in the memory to execute the method provided in the first aspect.

A further aspect of embodiments of the present application provides a computer device comprising at least one connected processor, a memory and a transceiver, wherein the memory is used for storing a computer program, and the processor is used for calling the computer program in the memory to execute the method provided in the first aspect.

Yet another aspect of the embodiments of the present application provides a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to perform the method provided in the first aspect.

According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the first aspect described above.

Compared with the prior art, in the scheme provided by the embodiment of the application, on one hand, because the user login information has the characteristic that each user is different, when the user logs in the server of the artificial intelligence safety target range, the server can determine the first recommended page data which is targeted and matched with the user requirements for the user based on the user login information, so that the first recommended page data obtained by each user are different, the specific content of the artificial intelligence safety target range is recommended in a personalized manner, uniform page data can be prevented from being recommended to the user side, and the recommended page data can be used for safety attack and defense drilling or basic knowledge learning of an artificial intelligence model. On the other hand, determining whether the target shooting range learning mode or the target shooting range practicing mode is an AI safety shooting range learning mode or an AI safety shooting range practicing mode based on the service end use data corresponding to the first recommended page data, acquiring corresponding first use data or second use data, and finally determining the current tendency matrix according to the first use data or the second use data.

Drawings

Fig. 1 is a schematic view of an application scenario of an artificial intelligence safety shooting range content recommendation system according to an embodiment of the present application;

FIG. 2a is a schematic flow chart illustrating a method for recommending artificial intelligence safety shooting range content according to an embodiment of the present disclosure;

FIG. 2b is a schematic flow chart illustrating an artificial intelligence safety range content recommendation method according to an embodiment of the present application;

fig. 3a is a schematic diagram of first recommendation page data in the artificial intelligence safety shooting range content recommendation method provided in the embodiment of the present application;

fig. 3b is a schematic diagram of historical recommendation page data in the artificial intelligence safety shooting range content recommendation method provided in the embodiment of the present application;

FIG. 4 is a schematic structural diagram of an artificial intelligence safety range content recommendation device in an embodiment of the present application;

FIG. 5 is a schematic diagram of a server according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a service terminal in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a server in an embodiment of the present application.

Detailed Description

The terms "first," "second," and the like in the description and in the claims of the embodiments of the application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprise" and "have", and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those explicitly listed, but may include other steps or modules not explicitly listed or inherent to such process, method, article, or apparatus, such that the division into blocks presented in an embodiment of the present application is merely a logical division, and may be implemented in practice in other ways, such that multiple blocks may be combined or integrated into another system, or some features may be omitted, or not implemented, and such that shown or discussed as coupled or directly coupled or communicative with each other may be through interfaces, and such that indirect coupling or communicative coupling between blocks may be electrical or other similar, the embodiments of the present application are not limited. Moreover, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in a plurality of circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

The embodiment of the application provides an artificial intelligence safety shooting range content recommendation method, an artificial intelligence safety shooting range content recommendation device and a storage medium, wherein the method, the device and the storage medium can be used for a server, when the server receives user login information sent by a user, first recommendation page data are determined according to the user login information and are sent to the user, then an AI safety shooting range learning mode or an AI safety shooting range exercise mode is determined based on service end use data corresponding to the first recommendation page data, corresponding first use data or second use data are obtained, and finally a current tendency matrix is determined according to the first use data or the second use data. In the embodiment of the present application, a server (i.e., a server) is taken as an example, and when the embodiment is applied to a server side, reference may be made to the embodiment of the server, which is not described in detail herein.

The scheme of the embodiment of the application can be realized based on an artificial intelligence technology, and particularly relates to the technical field of computer vision in the artificial intelligence technology and the fields of cloud computing, cloud storage, databases and the like in the cloud technology, which are respectively introduced below.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

Computer Vision technology (CV) Computer Vision is a science for researching how to make a machine "see", and further means that a camera and a Computer are used for replacing human eyes to perform machine Vision such as identification, tracking and measurement on a target, and further performing graphic processing, so that the Computer processing becomes an image more suitable for human eyes to observe or transmitted to an instrument to detect. As a scientific discipline, computer vision research-related theories and techniques attempt to build artificial intelligence systems that can capture information from images or multidimensional data. Computer vision technologies generally include image processing, face recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D technologies, virtual reality, augmented reality, synchronous positioning, map construction, and other technologies, and also include common face recognition, fingerprint recognition, and other biometric technologies.

With the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical care, smart customer service, and the like.

The scheme of the embodiment of the application can be realized based on a cloud technology, particularly relates to the technical fields of cloud computing, cloud storage, databases and the like in the cloud technology, and is respectively introduced below.

Cloud technology refers to a hosting technology for unifying serial resources such as hardware, software, network and the like in a wide area network or a local area network to realize calculation, storage, processing and sharing of data. The Cloud technology (Cloud technology) is based on the general names of network technology, information technology, integration technology, management platform technology, application technology and the like applied in a Cloud computing business model, can form a resource pool, can be used as required, and is flexible and convenient. Cloud computing technology will become an important support. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, image-like websites and more portal websites. With the high development and application of the internet industry, each article may have its own identification mark and needs to be transmitted to a background system for logic processing, data in different levels are processed separately, and various industrial data need strong system background support and can only be realized through cloud computing. According to the embodiment of the application, the user login information and the current tendency matrix can be stored through a cloud technology.

A distributed cloud storage system (hereinafter, referred to as a storage system) refers to a storage system that integrates a large number of storage devices (storage devices are also referred to as storage nodes) of different types in a network through application software or application interfaces to cooperatively work by using functions such as cluster application, grid technology, and a distributed storage file system, and provides a data storage function and a service access function to the outside. In the embodiment of the application, information such as network configuration and the like can be stored in the storage system, so that the server can conveniently retrieve the information.

At present, a storage method of a storage system is as follows: logical volumes are created, and when a logical volume is created, physical storage space, which may be the disk composition of a certain storage device or several storage devices, is allocated to each logical volume. The client stores data on a certain logical volume, that is, the data is stored on a file system, the file system divides the data into a plurality of parts, each part is an object, the object not only contains the data but also contains additional information such as data identification (ID, ID entry), the file system writes each object into a physical storage space of the logical volume, and the file system records storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

The process of allocating physical storage space for the logical volume by the storage system specifically includes: physical storage space is divided in advance into stripes according to a group of capacity measures of objects stored in a logical volume (the measures often have a large margin with respect to the capacity of the actual objects to be stored) and Redundant Array of Independent Disks (RAID), and one logical volume can be understood as one stripe, thereby allocating physical storage space to the logical volume.

The Database (Database), which can be regarded as an electronic file cabinet in short, is a place for storing electronic files, and a user can add, query, update, delete, etc. data in the files. A "database" is a collection of data that is stored together in a manner that can be shared by multiple users, has as little redundancy as possible, and is independent of the application.

A Database Management System (DBMS) is a computer software System designed for managing a Database, and generally has basic functions of storage, interception, security assurance, backup, and the like. The database management system may classify the database according to the database model it supports, such as relational, XML (Extensible Markup Language); or classified according to the type of computer supported, e.g., server cluster, mobile phone; regardless of which type of classification is used, some DBMSs can be cross-classified, e.g., supporting multiple Query languages simultaneously.

It should be noted that the service terminal according to the embodiments of the present application may be a device providing voice and/or data connectivity to the service terminal, a handheld device having a wireless connection function, or another processing device connected to a wireless modem. Such as mobile telephones (or "cellular" telephones) and computers with mobile terminals, such as portable, pocket, hand-held, computer-included, or vehicle-mounted mobile devices, that exchange voice and/or data with a radio access network. Examples of such devices include Personal Communication Service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, and Personal Digital Assistants (PDA).

When the service terminal generates the first recommended page data, the service terminal also needs to receive user login information sent by the user terminal. Specifically, the service terminal is used for receiving user login information sent by the user side, determining first recommendation page data according to the user login information and sending the first recommendation page data to the user side.

In some embodiments, the present embodiment can be applied to an artificial intelligence security shooting range content recommendation system 1 as shown in fig. 1, where the artificial intelligence security shooting range content recommendation system 1 includes a server 10 and at least one client 20, and data interaction can be performed between the server 10 and the client 20. When receiving user login information sent by the user terminal 20, the server 10 determines first recommended page data according to the user login information and sends the first recommended page data to the user terminal 20, then determines whether the AI safety shooting range learning mode or the AI safety shooting range practice mode is based on the server usage data corresponding to the first recommended page data, acquires corresponding first usage data or second usage data, and finally determines a current tendency matrix according to the first usage data or the second usage data.

The server related to the present application 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, middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform.

The service terminal according to the embodiment of the present application may include: smart terminals carrying multimedia data processing functions (e.g., video data playing function, music data playing function), such as a smart phone, a tablet pc, a notebook pc, a desktop pc, a smart tv, a smart speaker, a Personal Digital Assistant (PDA), a desktop pc, and a smart watch, but are not limited thereto.

The embodiment of the application mainly provides the following technical scheme:

when the server receives user login information sent by the user side, determining first recommendation page data according to the user login information and sending the first recommendation page data to the user side, then determining whether the AI safety shooting range learning mode or the AI safety shooting range practice mode is based on service side usage data corresponding to the first recommendation page data, acquiring corresponding first usage data or second usage data, and finally determining a current tendency matrix according to the first usage data or the second usage data. And the obtained current tendency degree matrix is used for screening the recommended content set sent to the server for the next login of the user side.

The technical solution of the present application will be described in detail with reference to several embodiments.

Referring to fig. 2a, a method for recommending artificial intelligence safety shooting range content provided in an embodiment of the present application is described as follows, where the embodiment of the present application includes:

201. the server receives user login information sent by the user side.

In the embodiment of the application, when a user needs to log in a server to enter an artificial intelligence security shooting range platform to perform learning or practicing such as attack and protection of an artificial intelligence algorithm model, user login information such as a login account and a login password needs to be input on the user. After the user terminal obtains the user login information, the user login information is sent to the server terminal to be verified, and after the user login information is verified in the server terminal, the user terminal can successfully enter the artificial intelligence safety shooting range platform provided by the server terminal.

202. And the server determines first recommended page data according to the received user login information and sends the first recommended page data to the user side.

The first recommendation page data comprises recommendation data of a plurality of artificial intelligence safety targets.

In the embodiment of the application, after the user successfully logs in the artificial intelligence safety shooting range platform, the server side can determine the first recommendation page data based on the login information. In the detailed information included in the user login information, the server side can judge whether the user is initially registered and logs in the artificial intelligence safety shooting range platform. If the user is judged not to log in the artificial intelligence safety target range platform for the first time, the server side can generate first recommended page data for historical use data (which can be understood as historical artificial intelligence safety target range use data) in the user login information. If the user logs in the artificial intelligent safety shooting range platform for the first time, the first recommendation page data can be generated by the user login information and the user input information obtained based on the user answering platform push questions. Therefore, no matter whether the user logs in the artificial intelligent safety shooting range platform for the first time or not, first recommended page data are generated in the server based on the user login information, and the first recommended page data are pushed to the user side in time to be displayed.

Mode 1: under the scene of initial login of a user, first recommendation page data are generated based on login information of the user and user input information obtained based on push questions of a user response platform

In some embodiments, the determining, by the server, first recommended page data according to the received user login information includes:

if the accumulated login times corresponding to the user login information are determined to be zero, user interest information data are obtained;

acquiring a pre-stored push question set and sending the pre-stored push question set to a user side;

receiving a reply data set which is sent by the user side and corresponds to the push question set;

determining a first recommended content set according to the user interest information data and the reply data set; wherein the first recommended content set comprises one of AI safe shooting range course data and AI safe shooting range practice data;

and filling the first recommended content data into a preset page container to generate the first recommended page data.

In the embodiment of the application, the server can obtain the login account number, the password and other information of the user for verification and also can obtain the accumulated login times based on the login information of the user, and if the accumulated login times corresponding to the login information of the user is determined to be zero, the server indicates that the user is registered for the first time and logs in the artificial intelligence safety shooting range platform. Since the server does not recommend any content to the user before, in order to more accurately recommend the content of the AI security shooting range after the user logs in at this time, the server needs to obtain the user interest information data entered by the user at the user end, obtain the push question set pre-stored locally by the server, send the push question set to the user end to be answered by the user corresponding to the user end, and then determine the first recommended content set by the reply data set.

For example, the set of push questions includes at least the following push questions:

A1) whether an algorithm basis exists;

A2) whether technical ethics are concerned;

A3) whether the commercial product is heavy;

A4) whether to train the model by oneself;

when the user answers the 4 push questions, one of yes and no is selected for each push question, and the 4 answers obtained after the answer is completed sequentially form a reply data set according to the order of the question numbers. Before the reply data set is obtained, the user also enters user interest information data (such as interest keywords in multiple directions, such as image classification, target detection, human face, voice, text and the like) consisting of a plurality of interest keywords or user interest information data consisting of a whole description text. And extracting a plurality of interest keywords corresponding to the user based on the user interest information data in the server, and then determining a first recommended content set by the server according to the user interest information data and the reply data set. Therefore, the user interest information data and the reply data set which are input by the user can be used as basic input data for the server to quickly determine recommended content.

In some embodiments, the determining a first set of recommended content from the user interest information data and the reply data set includes:

acquiring a first semantic vector corresponding to the user interest information data;

acquiring a second semantic vector corresponding to the reply data set;

connecting the first semantic vector with the second semantic vector to obtain a comprehensive semantic vector;

and acquiring a first recommended content set in a content library based on the comprehensive semantic vector.

In the embodiment of the present application, when determining the first recommended content set according to the user interest information data and the reply data set, the first implementation manner is that the user interest information data is converted into a first semantic vector (essentially, a text or keyword set is converted into a semantic vector), the reply data set is converted into a second semantic vector (wherein, if answer data is yes, the answer data is correspondingly converted into a value 1, if answer data is no, the answer data is correspondingly converted into a value 0, 4 answer data are sequentially connected and then converted into a second semantic vector), then the first semantic vector and the second semantic vector are connected based on a connection function (such as a concat connection function) to obtain a comprehensive semantic vector, and finally, a recommended content set having the maximum vector similarity with the comprehensive semantic vector is obtained in a content library of a server as a first recommended content set. Because the content semantic vector is pre-calculated and set for each recommended content set in the content library of the server, after the comprehensive semantic vector is known, the similarity between the comprehensive semantic vector and the content semantic vector of each recommended content set in the content library can be calculated, and when the comprehensive semantic vector has the maximum vector similarity with the content semantic vector of one recommended content set, the recommended content set is obtained as the first recommended content set.

obtaining interest keywords in the user interest information data to form a first screening condition;

acquiring an initial recommended content set in a content library according to the first screening condition;

forming a second screening condition based on each reply question in the reply data set;

and acquiring a first recommended content set in the initial recommended content set according to the second screening condition.

In the embodiment of the present application, when a first recommended content set is determined according to the user interest information data and the reply data set, a second implementation manner is to first use a plurality of interest keywords extracted from the user interest information data as a first filtering condition (which is essentially a keyword set), and obtain a recommended content set meeting the first filtering condition in a content library of a server as an initial recommended content set. Since each of the initial recommended contents in the initial recommended content set also has a content tag corresponding to each of the reply questions in the reply data set, for example, the initial recommended content a has a tag of "not biased for business", each of the reply questions in the reply data set may constitute a second filtering condition (which is essentially a combination of a positive word or a negative word + a keyword, and if not biased for business ", has a negative word" not "or a keyword" biased for business "), and then a recommended content set satisfying the second filtering condition is acquired as the first recommended content set in the initial recommended content set. Because a plurality of interest keyword labels and at least four combined labels formed by positive words or negative words and the combination of the keywords are preset in each recommended content set in the content library of the server, when the first screening condition is known, the initial recommended content set can be screened out, and then the first recommended content set is screened out by the initial recommended content set based on the second screening condition.

After the first recommended content set is obtained based on the above manner, since the first recommended content set is still relatively dispersed content data, the server needs to concentrate the first recommended content set in a preset page container to generate the first recommended page data, which may specifically refer to fig. 3 a. The total number of the first recommended contents in the first recommended content set can be obtained through statistics, then page sub-containers with the same number are created in the page container based on the total number, and each recommended content in the first recommended content set is correspondingly filled into one page sub-container, so that first recommended page data are obtained. Therefore, based on the user interest information data and the reply data set input by the user, the server can be assisted to quickly determine recommended content and fill the recommended content into the page container to form first recommended page data, and the first recommended page data is pushed to the user side for visual display,

Mode 2: under the condition that a user does not log in for the first time, first recommendation page data are generated based on user login information

In some embodiments, the determining first recommendation page data according to the received user login information includes:

if the accumulated login times corresponding to the user login information are determined to be larger than zero, acquiring historical use data;

determining a historical tendency matrix according to the historical use data; each row vector in the historical tendency degree matrix represents a preference value of a user to a corresponding page tag, and the preference value of each page tag is determined based on the access operation of the page tag and the page residence time;

determining target preference values of which the preference value descending sequence numbers do not exceed a preset sequencing threshold according to the historical tendency degree matrix, and forming a screening page tag set by page tags corresponding to all the target preference values;

determining a first recommended content set according to the screening page tag set; wherein the first recommended content set comprises one of AI safe shooting range course data and AI safe shooting range practice data;

In the embodiment of the application, the server can obtain the login account number, the password and other information of the user for verification and also can obtain the accumulated login times based on the login information of the user, and if the accumulated login times corresponding to the login information of the user is determined to be more than zero, the server indicates that the user does not register for the first time and logs in the artificial intelligence safety shooting range platform, but the user already has the historical login record and the historical use data. At the moment, when the server generates the first recommendation page data, the server does not refer to the user interest information data and the reply data set which are input by the user, but mainly refers to historical use data.

When determining the first recommended content set based on the historical usage data, the historical usage data is first converted into a historical tendency matrix, for example, when a user browses the historical recommended page data, specifically referring to fig. 3b, a page corresponding to the historical recommended page data includes a plurality of page sub-containers, each page sub-container contains corresponding recommended content (that is, each page sub-container corresponds to at least one page tag), and each page sub-container is provided with a buried point to make statistics on the number of clicks of the user on the page sub-container and the page residence time. After the user finishes checking or operating the historical recommended page data, the click times and the page residence time of each page sub-container can be counted by the buried points of each page sub-container, and therefore the click times and the page residence time of each page sub-container are converted into the preference values of each page sub-container based on a preset attention degree conversion strategy.

For example, the attention degree conversion policy is set as a first gear to which the counted click times belong, a second gear to which the page dwell time belongs is counted, and a preference value can be obtained by summing a first gear interval value corresponding to the first gear and a second gear interval value corresponding to the second gear. Wherein, the number of clicks may be more specifically divided into 5 steps, for example, the number of clicks is [0,5 ], which is a first step interval of the number of clicks (corresponding to a first step interval value of 0.1 of the number of clicks), the number of clicks is [5,10 ], which is a second step interval of the number of clicks (corresponding to a second step interval value of 0.2 of the number of clicks), the number of clicks is [10,15 ], which is a third step interval of the number of clicks (corresponding to a third step interval value of 0.3 of the number of clicks), the number of clicks is [15,20 ], which is a fourth step interval of the number of clicks (corresponding to a fourth step interval value of 0.4 of the number of clicks), the number of clicks is [20, + ∞ ], which is a fifth step interval of the number of clicks (corresponding to a first step interval value of the number of clicks, which is 0.5), if the number of clicks of the page sub-container B in the history recommendation page data is actually 8, which is the second step interval of the number of clicks (the first step interval determined by 8), specifically, the second interval value of the number of clicks in the second interval of the number of clicks is 0.2, and the second interval value of the number of clicks 0.2 is used as the first interval value of the number of first steps corresponding to the number of first steps. Of course, the specific implementation is not limited to dividing the number of clicks into 5 steps, and the number of clicks may be divided into steps of other numbers according to actual requirements.

Similarly, the page residence time is divided into 5 steps, for example, if the page residence time is [0,30s ], then the page residence time is the first step interval (corresponding to a page residence time first step interval value of 0.1), if the page residence time is [30s,60s ], then the page residence time is the second step interval (corresponding to a page residence time second step interval value of 0.2), if the page residence time is [60s,90s ], then the page residence time is the third step interval (corresponding to a page residence time third step interval value of 0.3), if the page residence time is [90s,120s ], then the page residence time is the fourth step interval (corresponding to a page residence time fourth step interval value of 0.4), if the page residence time is [120s, + ∞), then the page residence time is the fifth step interval (corresponding to a page residence time first step interval value of 0.5), if the page residence time of the page sub-container B in the history recommended page data is actually 200s, and the page residence time belongs to a fifth gear interval of the page residence time (i.e., a second gear number determined by the page residence time of 200 s), the page residence time is specifically converted into a fifth gear interval value 0.5 of the page residence time of the fifth gear interval of the page residence time, and the fifth gear interval value 0.5 of the page residence time is used as a second gear interval value corresponding to the second gear number. Certainly, the specific implementation is not limited to dividing the page residence time into 5 gear numbers, and the page residence time may be divided into other numerical gear numbers according to the actual requirement.

After the preference value corresponding to each page sub-container in the historical recommended page data is known, a row vector a is used _{user1，itemi} To indicate the preference value of the user1 for the ith page sub-container itemi in the history recommended page data, if the value range of i in itemi is [1, n1 ]]It means that there are n1 page sub-containers in the history recommendation page data, represented by the row vector a _{user1，item1} To a row vector a _{user1，itemn1} And the historical tendency matrixes are sequentially arranged from top to bottom. Moment of tendency due to the historyOnly one non-zero value is taken as a preference value in each row in the array, so that after the preference values determined by the vectors in each row in the historical tendency degree matrix are sorted in a descending order, target preference values which do not exceed a preset sorting threshold (for example, the preset sorting threshold is set to be 5) can be selected, and page tags of the page sub-containers corresponding to the target preference values form a screening page tag set. Therefore, the filtered page tag set of the user is determined based on the historical use data, and can be used as a basis for filling content into an initial page after the user enters the artificial intelligent safety shooting range platform next time, the artificial intelligent safety shooting range platform does not recommend the same page content to all users uniformly, and personalized content recommendation based on the historical tags of the user is achieved.

203. And the server side acquires server side use data corresponding to the first recommended page data.

The server side use data comprises server side resource consumption data and server side bandwidth use data.

In the embodiment of the application, after the user side receives the first recommendation page data, the user side selects the recommendation data of at least one artificial intelligence safety range to carry out local learning or practice. In order to more clearly understand the difference between the learning process of the artificial intelligence safety range-related recommendation data and the practice process of the artificial intelligence safety range-related recommendation data, the learning process and the practice process are respectively described below.

The learning of the recommendation data related to the artificial intelligence safety shooting range refers to the types of contents such as technical means, specific attack codes of the technical means, attack target AI algorithm models for the specific attack codes, specific use instructions of the technical means, teaching videos of the technical means and the like, which are expected by users that artificial intelligence safety shooting range platforms tend to recommend AI safety shooting ranges more. The content of the type is more focused on displaying the relevant basic learning data of the artificial intelligence safety target range to the user, and after the user side receives the first recommendation page data, the user mainly selects the content in the first recommendation page data to view the content. In the learning process, any retraining or reinforcement is not needed for the attack target AI algorithm model, so that the resource consumption of the server is low. And the user side watches or checks the relevant recommended data of the artificial intelligent safety shooting range on line in the learning process, and frequent data transmission is involved in the process, so that the bandwidth is occupied greatly.

The practice of the artificial intelligence safety shooting range related recommended data means that a user expects that an artificial intelligence safety shooting range platform is more prone to recommend an attack target AI algorithm model, then the user operates based on the specialty of the user to compile specific attack codes for the recommended attack target AI algorithm model, and after the specific attack codes are compiled, an attack result, an attack process score, a model attack report and the like of the recommended attack target AI algorithm model are obtained. In the training process, retraining or reinforcing aiming at the attack target AI algorithm model is involved, so that the resource consumption of the server is large. In the training process, the user end completes algorithm reinforcement on the attack target AI algorithm model and sends the reinforced attack target AI algorithm model to the server end for training or reinforcement, and frequent data transmission is not involved in the process, so that the bandwidth occupation is small.

Therefore, after the user specifically views or operates the first recommended page data, the server-side use data is accurately judged how the user specifically operates the first recommended page data, and the accurate operation type can be obtained.

204. And if the server determines that the server bandwidth usage data in the server usage data is larger than the bandwidth threshold, determining that the server bandwidth usage data is in an AI safety shooting range learning mode, and acquiring first usage data corresponding to the first recommended page data.

In the embodiment of the application, if it is determined that the use mode of the user for the artificial intelligence safety shooting range platform is the AI safety shooting range learning mode according to the service use data in the service, it indicates that the service allocates more network bandwidth to perform data interaction with the user side, so as to transmit specific page data corresponding to the first recommended page data in the AI safety shooting range learning mode.

In the AI safety shooting range learning mode, AI safety shooting range course data included in the first recommended page data is stored in each page sub-container in a data link address mode, when a user selects one of the page sub-containers in the first recommended page data and clicks to enter, the server side obtains a data link address corresponding to the page sub-container, obtains original data content according to the data link address, and finally transmits the original data content to the user side. For example, the original data content acquired by the data link address can be a teaching video of an AI safety shooting range, and the server transmits the teaching video of the AI safety shooting range to the user terminal in a streaming media data mode; and the original data content acquired by the data link address can be a teaching text of the AI safety shooting range, and the server transmits the teaching text of the AI safety shooting range to the user terminal in a hypertext transfer protocol mode.

It can be seen that, in the AI safe range learning mode, after the user views or operates the first recommended page data, the page sub-containers can detect data such as specific clicks of the page sub-containers and page residence time based on the embedded points, and then the data such as the specific clicks of the page sub-containers and the page residence time form first usage data of the user for the first recommended page data in the AI safe range learning mode. After the first usage data is acquired, the content viewing or usage preference of the beginner user can be further accurately analyzed to be used as a historical data basis for analyzing the recommended page data again in a follow-up mode. Moreover, under the AI safe shooting range learning mode, the effect of pushing the learning content to the beginner users with lower specialty is fully realized.

205. And if the server determines that the server resource consumption data in the server use data is larger than the resource consumption threshold, determining that the server use data is in the AI safe shooting range practice mode, and acquiring second use data corresponding to the first recommended page data.

In the embodiment of the application, if it is determined that the use mode of the user for the artificial intelligence safety shooting range platform is the AI safety shooting range practice mode according to the service use data in the service end, the service end is indicated to allocate more local resources (such as CPU computing power, memory and the like) for the user end to call, so that the operations of attacking, defending, retraining and the like on the AI algorithm model in the AI safety shooting range practice mode are completed.

In the AI safety shooting range practice mode, the AI safety shooting range practice data included in the first recommended page data stores the original data (such as original codes, model names, etc.) of the AI algorithm model in each page sub-container. For example, the original local code of the target detection model is stored in the page sub-container 1 (the original local code hides part of the model key parameters or the model code relative to the original complete code), the model name of the face recognition model is stored in the page sub-container 2 (only the model name is displayed, the model parameters and the model code of the complete face recognition model need to be supplemented by the user), after the user selects one of the page sub-containers, the original data in the page sub-container needs to be supplemented completely to obtain a complete AI algorithm model, and then the complete AI algorithm model is sent to the server, and after the server receives the complete AI algorithm model, the server calls the local server resource to perform operations such as retraining or reinforcing of the AI algorithm model, so as to achieve the effect of practice in the AI safe target range.

Therefore, in the AI safety shooting range practice mode, the user can analyze the original data of each AI algorithm model and then completely supplement the original data, and the supplemented and completely supplemented AI algorithm model is sent to the server side for verification, so that the effect of examining the user with higher specialty is fully realized. After the second usage data is obtained, the AI algorithm model exercise preference of the professional user can be further accurately analyzed to serve as a historical data basis for subsequent re-analysis of the recommended page data.

206. And the server determines a current tendency matrix according to the first using data or the second using data.

Each row vector in the current tendency degree matrix represents a preference value of a user for a corresponding page tag, the preference value of each page tag is determined based on the access operation of the page tag and the page residence time, and the current tendency degree matrix is used for screening a recommended content set sent to a server side for logging in the user side next time.

In this embodiment of the application, when a user browses first recommended page data, specifically referring to fig. 3a, a page corresponding to the first recommended page data includes a plurality of page sub-containers, each page sub-container contains corresponding recommended content (that is, each page sub-container corresponds to at least one page tag), and each page sub-container is provided with a buried point for making statistics on the number of clicks of the page sub-container and the page residence time of the user. After the user finishes viewing or operating the first recommended page data and obtains the first usage data or the second usage data, the click times and the page residence time of each page sub-container can be counted by the buried points of each page sub-container obtained from the first usage data or the second usage data, and therefore the click times and the page residence time of each page sub-container are converted into preference values of each page sub-container based on the attention degree conversion strategy.

After the preference value corresponding to each page sub-container in the first recommended page data is known, the row vector a is used _{userj，itemk} To express the preference value of the user userj to the kth page sub-container itemk in the first recommended page data, if the value range of k in itemk is [1, n2 ]]It means that there are n2 page sub-containers in the first recommended page data, represented by the row vector a _{userj，item1} To a row vector a _{user1，itemn2} And sequentially arranging the current tendency matrixes from top to bottom.

In some embodiments, as shown in fig. 2a, as a first obtaining manner for obtaining a current tendency matrix to perform recommendation data after a user logs in next time, after determining the current tendency matrix according to the first usage data or the second usage data, the method further includes:

2071. and the server determines the current target preference values of which the preference value descending sequence numbers do not exceed the preset sequencing threshold value based on the current tendency degree matrix, and forms the page tags corresponding to the current target preference values into a current screening page tag set.

In this embodiment of the application, because each row in the current tendency matrix has only one non-zero value as a preference value, after the preference values determined by the vectors in each row in the current tendency matrix are sorted in a descending order, a current target preference value that does not exceed a preset sorting threshold (for example, the preset sorting threshold is set to be 5) is selected, and page tags of a page sub-container corresponding to each current target preference value form a current filtered page tag set. Therefore, the screening page tag set of the user is determined based on the first usage data or the second usage data, the basis that recommended content is filled in a page after the user enters the artificial intelligence safety shooting range platform next time can be used, the artificial intelligence safety shooting range platform does not recommend the same page content to all users in a unified mode, and personalized content recommendation based on historical usage is achieved.

For example, the row vector of the first row in the current tendency matrix represents the preference value of the 1 st page sub-container item1 in the first recommended page data, and the item1 contains the learning content of the attack/defense of the AI algorithm model; the row vector of the second row in the current tendency matrix represents the preference value of the 2 nd page sub-container item2 in the first recommended page data, and the item2 contains the learning content of the AI algorithm model safety problem; the row vector of the third row in the current tendency matrix represents the preference value of the 3 rd page sub-container item3 in the first recommended page data, and learning content of an AI algorithm model white-box/black-box problem is contained in the item 3; the row vector of the fourth row in the current tendency matrix represents a preference value for the 4 th page child container item4 in the first recommended page data, learning contents in item4 containing AI algorithm model components/non-component problems, and the like. The row vector of the first row in the current tendency matrix determines the preference value of the user for the learning content of the attack/defense of the AI algorithm model, the row vector of the second row in the current tendency matrix determines the preference value of the user for the learning content of the safety problem of the AI algorithm model, the row vector of the third row in the current tendency matrix determines the preference value of the user for the learning content of the white box/black box problem of the AI algorithm model, and the row vector of the fourth row in the current tendency matrix determines the preference value of the user for the learning content of the component/non-component problem of the AI algorithm model.

2081. And the server determines a second recommended content set from a content library according to the current screening page tag set.

Wherein the second set of recommended content includes one of AI safety range tutorial data and AI safety range exercise data.

In the embodiment of the application, each piece of recommended content in a content library of a server is provided with a content tag, and when a plurality of page tags included in the current screening page tag set are combined to form a tag screening condition, the tag screening condition is used for retrieving and determining a second recommended content set in the content library, wherein the second recommended content set is the basis for filling the recommended content in the page after the user logs in the artificial intelligent safety shooting range platform next time. Specifically, the second recommended content data is filled into a preset page container to generate second recommended page data. Therefore, the user can obtain the recommended data obtained based on the historical use condition of the user when logging in the artificial intelligent safety target range platform every time, and the unified data pushed by the platform does not need to be received.

In some embodiments, as shown in fig. 2b, as a second obtaining manner for obtaining a current tendency matrix to perform recommendation data after a user logs in next time, after determining the current tendency matrix according to the first usage data or the second usage data, the method further includes:

2072. the server determines a current tendency vector based on the current tendency matrix.

In the embodiment of the application, because each row in the current tendency degree matrix only has one non-zero value as a preference value, the current tendency degree vector with lower dimensionality can be obtained after summing up the vectors of the rows in the current tendency degree matrix, so that the preference value of the user to each page sub-container is represented by the current tendency degree vector. For example, a is the current tendency vector _itemi To indicate the user's preference value for the ith page sub-container itemi in the first recommended page data.

2082. And the server acquires similar tendency vectors from the tendency vector set based on the current tendency vector to form a similar tendency vector set.

And the vector similarity of the similar tendency vector and the current tendency vector exceeds a preset vector similarity threshold.

In the embodiment of the application, the server further stores a tendency vector set formed by the tendency vectors of the users obtained after the other users log in the artificial intelligence security shooting range platform, wherein it needs to be stated that in order to ensure data security, the user tendency vectors (the user tendency vectors form the tendency vector set) obtained after the users belonging to the same organization (for example, belonging to the same company) log in the artificial intelligence security shooting range platform are generally obtained to analyze and obtain the similarity tendency vector of the current tendency vector.

At this time, the server may analyze and obtain a target user tendency vector (i.e., a similar tendency vector) in the tendency vector set, where the vector similarity between the tendency vector set and the current tendency vector exceeds the vector similarity threshold, so as to form a similar tendency vector set. And each target user tendency degree vector corresponds to a specific user, each user has a user tendency degree vector obtained by using an artificial intelligence safety shooting range platform, and after similar users of the users corresponding to the current tendency degree vector are obtained, a second recommended content set can be further determined based on the comprehensive condition that the similar users view and use the page sub-container.

2092. The server determines a second set of recommended content from the content library based on the set of similarity propensity vectors.

In the embodiment of the present application, K target vector values before the vector value sorting can be selected from each similarity vector of the similarity vector set, and the K target vector values before the vector value sorting correspond to preference values of specific contents under page tags in one page sub-container respectively. Therefore, after the page tags of the topks of the similar users are obtained based on the similarity tendency vector set, the page tags of the overall ranking topks after the page tags of the topks of the similar users are integrated can be counted and used as another screening page tag set. A second set of recommended content is then determined from the content repository based on the other set of filter page tags.

Because each recommended content in the content library of the server is provided with a content tag, when a plurality of page tags included in the other screening page tag set are combined into another tag screening condition, the other tag screening condition is used for retrieving and determining a second recommended content set in the content library, and the second recommended content set is the basis for filling the recommended content in the page after the user logs in the artificial intelligent safety target platform next time. Specifically, the second recommended content data is filled into a preset page container to generate second recommended page data. Therefore, the user can log in the artificial intelligent safety target range platform every time to obtain the recommended data obtained based on the historical use condition of the user, and the unified data pushed by the platform does not need to be received.

It can be seen that, according to the scheme, in the scenes such as the artificial intelligence safety shooting range and the like, when the server receives user login information sent by the user, first recommendation page data are determined according to the user login information and sent to the user, then an AI safety shooting range learning mode or an AI safety shooting range exercise mode is determined based on service use data corresponding to the first recommendation page data, corresponding first use data or second use data are obtained, and finally a current tendency matrix is determined according to the first use data or the second use data. The server side can determine the first recommended page data based on the user login information and send the first recommended page data to the user side when the user logs in the server side, so that uniform page data are prevented from being recommended to the user side, and the recommended page data can be used for safety attack and defense drilling or basic knowledge learning of the artificial intelligent model.

Referring to fig. 4, fig. 4 is a schematic structural diagram of an artificial intelligence safety range content recommendation device in the embodiment of the present application. Fig. 4 is a schematic structural diagram of an artificial intelligence safety target range content recommendation device (the server 10 in fig. 1 can also be understood as an artificial intelligence safety target range content recommendation device), which can be applied to scenes such as an artificial intelligence safety target range. The server in the artificial intelligence safety shooting range content recommendation system in the embodiment of the application can implement the steps of the artificial intelligence safety shooting range content recommendation method executed by the server in the embodiment corresponding to the above-mentioned fig. 2a or fig. 2 b. The functions realized by the artificial intelligence safety shooting range content recommendation device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions, which may be software and/or hardware. As shown in fig. 4, the artificial intelligence safety target range content recommendation apparatus specifically includes a transceiver module 11 and a processing module 12, and the transceiver module 11 and the processing module 12 may refer to operations executed in the embodiment corresponding to fig. 2a or fig. 2b for realizing functions, which are not described herein again.

In some embodiments, the artificial intelligence security shooting range content recommendation device (i.e. the server 10) comprises a transceiver module 11 and a processing module 12;

the transceiver module 11 is configured to receive user login information sent by a user side;

the processing module 12 is configured to determine first recommendation page data according to the user login information received by the transceiver module 11, and send the first recommendation page data to a user side; the first recommendation page data comprises recommendation data of a plurality of artificial intelligence safety targets; acquiring service end use data corresponding to the first recommended page data; the server side use data comprises server side resource consumption data and server side bandwidth use data; if the bandwidth use data of the server in the service use data is larger than the bandwidth threshold, determining that the data is in an AI safety shooting range learning mode, and acquiring first use data corresponding to the first recommended page data; if the server resource consumption data in the server use data are larger than the resource consumption threshold, determining that the target is an AI safe shooting range practice mode, and acquiring second use data corresponding to the first recommended page data;

the processing module 12 is further configured to determine a current tendency matrix according to the first usage data or the second usage data; each row vector in the current tendency degree matrix represents a preference value of a user for a corresponding page tag, the preference value of each page tag is determined based on the access operation of the page tag and the page residence time, and the current tendency degree matrix is used for screening a recommended content set sent to a server side for logging in the user side next time.

It can be seen that, according to the scheme, in the scenes such as the artificial intelligence safety shooting range and the like, when the server receives user login information sent by the user, first recommendation page data are determined according to the user login information and sent to the user, then an AI safety shooting range learning mode or an AI safety shooting range exercise mode is determined based on service use data corresponding to the first recommendation page data, corresponding first use data or second use data are obtained, and finally a current tendency matrix is determined according to the first use data or the second use data. The first recommended page data can be determined by the server side based on the user login information and sent to the user side when the user logs in the server side, so that uniform page data are prevented from being recommended to the user side, and the recommended page data can be used for safety attack and defense drilling or basic knowledge learning of the artificial intelligent model.

The artificial intelligence safety shooting range content recommendation device in the embodiment of the present application is described above from the perspective of the modular functional entity, and the artificial intelligence safety shooting range content recommendation device in the embodiment of the present application is described below from the perspective of hardware processing.

It should be noted that in the embodiments of the present application (including the embodiments shown in fig. 4), all entity devices corresponding to the transceiver modules may be transceivers, and all entity devices corresponding to the processing modules may be processors. When one of the devices has the structure shown in fig. 4, the processor, the transceiver and the memory implement the same or similar functions of the transceiver module and the processing module provided in the device embodiment corresponding to the device, and the memory in fig. 5 stores a computer program that needs to be called when the processor executes the artificial intelligence safety range content recommendation method.

When the apparatus shown in fig. 4 has the structure shown in fig. 5, the processor in fig. 5 can implement the same or similar functions of the processing module provided by the apparatus embodiment corresponding to the apparatus, the transceiver in fig. 5 can implement the same or similar functions of the transceiver module provided by the apparatus embodiment corresponding to the apparatus, and the memory in fig. 5 stores a computer program that needs to be called when the processor executes the artificial intelligence safety range content recommendation method. In this application, in the embodiment shown in fig. 4, the entity device corresponding to the transceiver module may be an input/output interface, and the entity device corresponding to the processing module may be a processor.

As shown in fig. 6, for convenience of description, only the parts related to the embodiments of the present application are shown, and details of the specific technology are not disclosed, please refer to the method part of the embodiments of the present application. The terminal device may be any terminal device including a mobile phone, a tablet computer, a Personal Digital Assistant (PDA, for short), a Point of sale terminal (POS, for short), a vehicle-mounted computer, etc., taking the terminal as a mobile phone for example:

fig. 6 is a block diagram illustrating a partial structure of a mobile phone related to a terminal device provided in an embodiment of the present application. Referring to fig. 6, the handset includes: radio Frequency (RF) circuit 610, memory 620, input unit 630, display unit 640, sensor 650, audio circuit 660, wireless fidelity (WiFi) module 670, processor 680, and power supply 690. Those skilled in the art will appreciate that the handset configuration shown in fig. 6 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The following describes each component of the mobile phone in detail with reference to fig. 6:

the RF circuit 610 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then processes the received downlink information to the processor 680; in addition, the data for designing uplink is transmitted to the base station. In general, RF circuit 610 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuitry 610 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), e-mail), Short Message Service (SMS), etc.

The memory 620 may be used to store software programs and modules, and the processor 680 may execute various functional applications and data processing of the mobile phone by operating the software programs and modules stored in the memory 620. The memory 620 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 620 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 630 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the cellular phone. Specifically, the input unit 630 may include a touch panel 631 and other input devices 632. The touch panel 631, also referred to as a touch screen, may collect touch operations of a user (e.g., operations of the user on the touch panel 631 or near the touch panel 631 by using any suitable object or accessory such as a finger or a stylus) thereon or nearby, and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 631 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 680, and can receive and execute commands sent by the processor 680. In addition, the touch panel 631 may be implemented using various types, such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 630 may include other input devices 632 in addition to the touch panel 631. In particular, other input devices 632 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 640 may be used to display information input by the user or information provided to the user and various menus of the mobile phone. The Display unit 640 may include a Display panel 641, and optionally, the Display panel 641 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 631 can cover the display panel 641, and when the touch panel 631 detects a touch operation thereon or nearby, the touch panel is transmitted to the processor 680 to determine the type of the touch event, and then the processor 680 provides a corresponding visual output on the display panel 641 according to the type of the touch event. Although in fig. 6, the touch panel 631 and the display panel 641 are two independent components to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 631 and the display panel 641 may be integrated to implement the input and output functions of the mobile phone.

The handset may also include at least one sensor 650, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that adjusts the brightness of the display panel 641 according to the brightness of ambient light, and a proximity sensor that turns off the display panel 641 and/or the backlight when the mobile phone is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), can detect the magnitude and direction of gravity when the mobile phone is stationary, can be used for applications of recognizing the gesture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and tapping) and the like, and can also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor and the like, which are not described herein again.

Audio circuit 660, speaker 661, and microphone 662 can provide an audio interface between a user and a cell phone. The audio circuit 660 may transmit the electrical signal converted from the received audio data to the speaker 661, and convert the electrical signal into an audio signal through the speaker 661 for output; on the other hand, the microphone 662 converts the collected sound signals into electrical signals, which are received by the audio circuit 660 and converted into audio data, which are processed by the audio data output processor 680 and then transmitted via the RF circuit 610 to, for example, another cellular phone, or output to the memory 620 for further processing.

Wi-Fi belongs to short-distance wireless transmission technology, and a mobile phone can help a user to receive and send emails, browse webpages, access streaming media and the like through a Wi-Fi module 670, and provides wireless broadband internet access for the user. Although fig. 6 shows the W-iFi module 670, it is understood that it does not belong to the essential components of the handset and can be omitted entirely as needed within the scope of not changing the nature of the application.

The processor 680 is a control center of the mobile phone, and connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the mobile phone and processes data by operating or executing software programs and/or modules stored in the memory 620 and calling data stored in the memory 620, thereby performing overall monitoring of the mobile phone. Optionally, processor 680 may include one or more processing units; preferably, the processor 680 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 680.

The phone also includes a power supply 690 (e.g., a battery) for supplying power to the various components, which may be logically coupled to the processor 680 via a power management system, thereby providing management functions such as charging, discharging, and power management via the power management system.

Although not shown, the mobile phone may further include a camera, a bluetooth module, etc., which are not described herein.

In the embodiment of the present application, the processor 680 included in the mobile phone further has a flowchart for controlling the execution of the artificial intelligence security shooting range content recommendation method shown in fig. 2a or fig. 2 b.

Fig. 7 is a schematic structural diagram of a server 720 according to an embodiment of the present disclosure, where the server 720 may have a larger difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 722 (e.g., one or more processors) and a memory 732, and one or more storage media 730 (e.g., one or more mass storage devices) for storing applications 742 or data 744. Memory 732 and storage medium 730 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Further, the central processor 722 may be configured to communicate with the storage medium 730, and execute a series of instruction operations in the storage medium 730 on the server 720.

The Server 720 may also include one or more power supplies 726, one or more wired or wireless network interfaces 750, one or more input-output interfaces 758, and/or one or more operating systems 741, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and so forth.

The steps performed by the server in the above embodiments may be based on the structure of the server 720 shown in fig. 7. The steps of the server shown by fig. 2 in the above-described embodiment may be based on the server structure shown in fig. 7, for example. For example, the central processor 722, by calling instructions in the memory 732, performs the following operations:

receiving user login information sent by a user side through an input/output interface 758;

determining first recommended page data according to the received user login information, and sending the first recommended page data to a user side; the first recommendation page data comprises recommendation data of a plurality of artificial intelligence safety targets; acquiring service end use data corresponding to the first recommended page data; the server side use data comprises server side resource consumption data and server side bandwidth use data; if the bandwidth use data of the server in the service use data is larger than the bandwidth threshold, determining that the data is in an AI safety shooting range learning mode, and acquiring first use data corresponding to the first recommended page data; if the server resource consumption data in the server use data are larger than the resource consumption threshold, determining that the target is an AI safe shooting range practice mode, and acquiring second use data corresponding to the first recommended page data;

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the system, the apparatus, and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. 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 application may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may be stored in a computer-readable storage medium.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, it may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the present application are generated in whole or in part when the computer program is loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a server, a data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

The technical solutions provided by the embodiments of the present application are introduced in detail, and the principles and implementations of the embodiments of the present application are explained by applying specific examples in the embodiments of the present application, and the descriptions of the embodiments are only used to help understanding the method and core ideas of the embodiments of the present application; meanwhile, for a person skilled in the art, according to the idea of the embodiment of the present application, there may be a change in the specific implementation and application scope, and in summary, the content of the present specification should not be construed as a limitation to the embodiment of the present application.

Claims

1. An artificial intelligence safety shooting range content recommendation method is characterized by comprising the following steps:

receiving user login information sent by a user side;

2. The method of claim 1, wherein after determining a current propensity matrix from the first usage data or the second usage data, the method further comprises:

determining current target preference values of which the preference value descending order sequence numbers do not exceed a preset ordering threshold value based on the current tendency degree matrix, and forming page tags corresponding to the current target preference values into a current screening page tag set;

determining a second recommended content set from a content library according to the current screening page tag set; wherein the second set of recommended content includes one of AI safety range tutorial data and AI safety range exercise data.

3. The method of claim 1, wherein after determining a current propensity matrix from the first usage data or the second usage data, the method further comprises:

determining a current tendency vector based on the current tendency matrix;

acquiring similar tendency vectors from the tendency vector set based on the current tendency vector to form a similar tendency vector set; the vector similarity of the similar tendency vector and the current tendency vector exceeds a preset vector similarity threshold, and the tendency vector set is stored by a server and used for representing user tendency vectors corresponding to a plurality of users respectively;

determining a second recommended content set from a content library based on the similarity tendency vector set; wherein the second set of recommended content includes one of AI safety range tutorial data and AI safety range exercise data.

4. The method according to any one of claims 1-3, wherein the determining first recommendation page data according to the received user login information comprises:

5. The method according to any one of claims 1-3, wherein the determining first recommendation page data according to the received user login information comprises:

determining a historical tendency matrix according to the historical use data; each row vector in the historical tendency matrix represents a preference value of a user to a corresponding page tag, and the preference value of each page tag is determined based on the access operation of the page tag and the page residence time;

determining a first recommended content set according to the screening page tag set; wherein the first recommended content set comprises one of AI safety shooting range course data and AI safety shooting range practice data;

6. The method of claim 4, wherein determining a first set of recommended content based on the user interest information data and the reply data set comprises:

acquiring a second semantic vector corresponding to the reply data set;

7. The method of claim 4, wherein determining a first set of recommended content based on the user interest information data and the set of reply data comprises:

8. An artificial intelligence safety target range content recommendation device is characterized by comprising a receiving and sending module and a processing module;

the processing module is used for determining first recommended page data according to the user login information received by the transceiving module and sending the first recommended page data to a user side; the first recommendation page data comprises recommendation data of a plurality of artificial intelligence safety target ranges; acquiring service end use data corresponding to the first recommended page data; the server side use data comprises server side resource consumption data and server side bandwidth use data; if the bandwidth use data of the server in the service use data is larger than the bandwidth threshold, determining that the data is in an AI safety shooting range learning mode, and acquiring first use data corresponding to the first recommended page data; if the server resource consumption data in the server use data are larger than the resource consumption threshold, determining that the target is an AI safe shooting range practice mode, and acquiring second use data corresponding to the first recommended page data;

the processing module is further configured to determine a current tendency matrix according to the first usage data or the second usage data; each row vector in the current tendency degree matrix represents a preference value of a user for a corresponding page tag, the preference value of each page tag is determined based on the access operation of the page tag and the page residence time, and the current tendency degree matrix is used for screening a recommended content set sent to a server side for logging in the user side next time.

9. An artificial intelligence safety shooting range content recommendation device, the device comprising:

at least one processor, memory, and transceiver;

wherein the memory is for storing a computer program and the processor is for calling the computer program stored in the memory to perform the method of any one of claims 1-7.

10. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1-7.