WO2022142020A1 - 资讯推送方法、装置、电子设备及计算机可读存储介质 - Google Patents
资讯推送方法、装置、电子设备及计算机可读存储介质 Download PDFInfo
- Publication number
- WO2022142020A1 WO2022142020A1 PCT/CN2021/090700 CN2021090700W WO2022142020A1 WO 2022142020 A1 WO2022142020 A1 WO 2022142020A1 CN 2021090700 W CN2021090700 W CN 2021090700W WO 2022142020 A1 WO2022142020 A1 WO 2022142020A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- user
- data
- browsing
- information data
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000006870 function Effects 0.000 claims description 22
- 238000000605 extraction Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007726 management method Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000013481 data capture Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Definitions
- the present application relates to the technical field of data processing, and in particular, to an information push method, apparatus, electronic device, and computer-readable storage medium.
- the mainstream information push method in the market is to manually filter information, so as to selectively push information to users.
- the inventor realizes that this method relies too much on manual operation, is inefficient, and the filtered information cannot be accurately matched with users, and cannot achieve efficient and personalized information push.
- An information push method comprising:
- a similar user set is obtained according to the information data subset in the information browsing trace data set, and a second information recommendation list is generated according to the information score of the information set to be recommended according to the similar user set, and sent to The user pushes the information in the second information recommendation list.
- An information push device the device includes:
- a user category judgment module configured to obtain a user's information browsing trace data set, and determine whether the user is an active user according to the information browsing trace data set;
- an active user push module configured to classify the information data subsets in the information browsing trace data set if the user is an active user, and calculate the user's preference for different categories of information data in the information data subsets, Select a plurality of information data from the information set to be recommended according to the preference degree, generate a first information recommendation list, and push the information in the first information recommendation list to the user;
- the inactive user push module is used to obtain a similar user set according to the information data subset in the information browsing trace data set if the user is an inactive user, and score the information of the to-be-recommended information set according to the similar user set A second information recommendation list is generated, and the information in the second information recommendation list is pushed to the user.
- An electronic device comprising:
- a processor that executes the instructions stored in the memory to achieve the following steps:
- a similar user set is obtained according to the information data subset in the information browsing trace data set, and a second information recommendation list is generated according to the information score of the information set to be recommended according to the similar user set, and sent to The user pushes the information in the second information recommendation list.
- a computer-readable storage medium comprising a storage data area and a storage program area, the storage data area stores data created, and the storage program area stores a computer program; wherein, the computer program is executed by a processor The following steps are implemented:
- a similar user set is obtained according to the information data subset in the information browsing trace data set, and a second information recommendation list is generated according to the information score of the information set to be recommended according to the similar user set, and sent to The user pushes the information in the second information recommendation list.
- the present application can improve the efficiency of information push and carry out personalized information push.
- FIG. 1 is a schematic flowchart of a method for pushing information provided by an embodiment of the present application
- FIG. 2 is a schematic diagram of a module of an information push device according to an embodiment of the present application
- FIG. 3 is a schematic diagram of the internal structure of an electronic device for implementing an information push method according to an embodiment of the present application
- the execution body of the information push method provided by the embodiment of the present application includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application.
- the information push method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
- the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
- the present application provides an information push method.
- FIG. 1 it is a schematic flowchart of a method for pushing information according to an embodiment of the present application.
- the information push method includes:
- the user's information browsing trace data set includes a browsing information set of the user browsing information data in a browser or similar client for a period of time, wherein the information browsing trace data set includes but is not limited to: browsing information Start time, end time of browsing information, title of browsing information, content of browsing information, rating of browsing information.
- the information browsing trace data set can be obtained by using the data capture method. For example, using a python statement with data scraping function, scrape the information browsing trace data from the background of the website browsed by the user and/or the blockchain used to store the information browsing trace data set, and scrape all the information into
- determining whether the user is an active user according to the information browsing trace data set includes:
- Whether the user is an active user is determined according to the browsing information in the information browsing trace data set, and the browsing information includes but is not limited to one or more of the number of browsing times, the browsing time interval, and the rating of the browsed information.
- a preset number of times threshold such as 10 times
- the user is determined to be an inactive customer; when the number of browsing times is greater than the threshold, the user is determined to be an active user.
- the number of browsing times and the browsing time interval of the user in the statistical information browsing trace data set if the number of browsing times of the user is greater than the preset times threshold (such as 10 times), and the browsing time interval is smaller than the preset interval time or the browsing time interval gradually decreases. If the number of browsing times of the user is less than the preset number of times or the browsing time interval is greater than the preset interval time, the user is determined to be an inactive user.
- the preset times threshold such as 10 times
- the information data subset includes a plurality of information data, wherein the information data includes the content of the information, such as the text content of the information, the title of the information, and the like.
- classifying the information data subsets in the information browsing trace data set can classify the information data subsets from different dimensions. For example, the news data in the news data subset is classified according to the type of the data; or the news data in the news data subset is classified according to the author of the news data.
- feature extraction is performed on the information data subset in the information browsing trace data set, and then the information feature data subset after the feature extraction is classified.
- a convolutional neural network is used to perform feature extraction on a subset of information data in the information browsing trace data set to obtain a subset of information characteristic data.
- the information characteristic data subset includes information characteristic data, and the information characteristic data
- the subsets include: news title, news length, news keywords, news industry distribution, news-related stock distribution, etc.
- the classification of the information data subsets in the information browsing trace data set includes:
- the category of the information data in the information data subset is determined according to the classification result with the largest probability value among the plurality of classification results.
- classification function is:
- ⁇ is a preset system parameter
- X (i) is the ith information data in the information data subset
- e is the natural logarithm
- g( ⁇ X (i) ) is the classification result.
- the classification result includes categories corresponding to each information data in the information data subset, for example, news category, advertisement category, and the like.
- the user's preference for different types of information data is calculated based on the number of times the user browses the information data.
- the present application uses the following preference algorithm to calculate the preference degree:
- n is the total number of times the user browses all information
- m is the number of times the user browses information data of a certain category
- p(o) is the user's preference for this category of information data.
- the information set to be recommended may be a collection of information data that is newly generated and has not been pushed to the user.
- the selecting a plurality of pieces of information data from the information set to be recommended according to the preference degree includes:
- the pushing the information in the first information recommendation list to the user includes:
- the information in the first information recommendation list is pushed to the user at the pushing time.
- the extraction of time series features of the information browsing trace data set includes:
- t u is the time interval for the user to browse the information data.
- the embodiment of the present application after acquiring the time sequence feature, performs mathematical statistics on the time sequence feature to obtain the browsing time preference of the user's browsing information, and then determines the push time according to the browsing time preference. If user L prefers to browse information data in the morning and user J prefers to browse information data in the afternoon, the information in the first information recommendation list is pushed to user L in the morning, and the information in the first information recommendation list is pushed to user J in the afternoon.
- a timer may be used to push information data to the user according to the push time, so as to achieve the purpose of timely personalized push.
- the first information recommendation list is determined, and personalized push can be performed quickly and accurately.
- the set of similar users may include a plurality of similar users, the similar users are users who have browsed the same or similar information data as the users, or the similar users are users who are similar to the user and have browsed the same basic information or similar information data users.
- the obtaining a similar user set according to the information data subset in the information browsing trace data set includes:
- Feature extraction is performed on the information data subset in the information browsing trace data set, and then the similar user set is determined according to the feature extraction result.
- a convolutional neural network is used to perform feature extraction on a subset of information data in the information browsing trace data set to obtain a subset of information characteristic data.
- the information characteristic data subset includes information characteristic data, and the information characteristic data The subset includes: news title, news length, news keywords, news industry distribution, news-related stock distribution, news score, etc.
- a is the inactive user
- b is the similar user in the similar user set
- r a,p is the score of user a on the information data p in the information data subset
- r b,p is the score of user b on the information data p in the information data subset
- P is the information data subset.
- the similar users with the highest similarity to the inactive users are selected from the similar user set, and a preset scoring algorithm is used to calculate the predicted score of the information to be recommended in the information set to be recommended by the similar users, and select The information to be recommended whose predicted score is greater than the preset score threshold in the information set to be recommended is collected into the second information recommendation list.
- the information set to be recommended may be a collection of information data that is newly generated and has not been pushed to the user.
- the scoring algorithm is:
- pred(x,b) is the rating of similar user b to the information to be recommended x in the information set to be recommended
- b is the similar user
- N is the similar user set
- x is the information set to be recommended.
- Information to be recommended, r b, p are the ratings of user b on the information data p in the information data subset, is the mean of user b's score on the news data subset in the news data subset, is a preset score base value
- sim(a, b) is the similarity between the inactive user a and the similar user b in the similar user set.
- the embodiment of the present application realizes the purpose of accurate personalized push by judging whether the user is an active user, and selecting different methods according to the type of the user to generate an information recommendation list and perform information recommendation. efficiency. Therefore, the information push method proposed in the present application can improve the efficiency of information push and carry out personalized information push.
- FIG. 2 it is a schematic diagram of a module of the information push device of the present application.
- the information push apparatus 100 described in this application can be installed in an electronic device.
- the information push device may include a user category determination module 101 , an active user push module 102 and an inactive user push module 103 .
- the modules described in the present invention can also be called units, which refer to a series of computer program segments that can be executed by the electronic device processor and can perform fixed functions, and are stored in the memory of the electronic device.
- each module/unit is as follows:
- the user category judging module 101 is configured to obtain a user's information browsing trace data set, and determine whether the user is an active user according to the information browsing trace data set;
- the active user push module 102 is configured to, if the user is an active user, classify the information data subsets in the information browsing trace data set, and calculate the information data of the different categories in the information data subsets by the user. degree of preference, selecting a plurality of information data from the information set to be recommended according to the degree of preference, generating a first information recommendation list, and pushing the information in the first information recommendation list to the user;
- the inactive user push module 103 is configured to, if the user is an inactive user, obtain a set of similar users according to a subset of information data in the information browsing trace data set, and, according to the set of similar users, provide a set of information to be recommended. generate a second information recommendation list, and push the information in the second information recommendation list to the user.
- each module of the apparatus for extracting and generating text content in the image is as follows:
- the user category judging module 101 is configured to acquire a user's information browsing trace data set, and determine whether the user is an active user according to the information browsing trace data set.
- the user's information browsing trace data set includes a browsing information set of the user browsing information data in a browser or similar client for a period of time, wherein the information browsing trace data set includes but is not limited to: browsing information Start time, end time of browsing information, title of browsing information, content of browsing information, rating of browsing information.
- determining whether the user is an active user according to the information browsing trace data set includes:
- Whether the user is an active user is determined according to the browsing information in the information browsing trace data set, and the browsing information includes but is not limited to one or more of the number of browsing times, the browsing time interval, and the rating of the browsed information.
- a preset number of times threshold such as 10 times
- the user is determined to be an inactive customer; when the number of browsing times is greater than the threshold, the user is determined to be an active user.
- the number of browsing times and the browsing time interval of the user in the statistical information browsing trace data set if the number of browsing times of the user is greater than the preset times threshold (such as 10 times), and the browsing time interval is smaller than the preset interval time or the browsing time interval gradually decreases. If the number of browsing times of the user is less than the preset number of times or the browsing time interval is greater than the preset interval time, the user is determined to be an inactive user.
- the preset times threshold such as 10 times
- the active user push module 102 is configured to, if the user is an active user, classify the information data subsets in the information browsing trace data set, and calculate the information data of the different categories in the information data subsets by the user.
- the preference degree selects a plurality of information data from the information set to be recommended according to the preference degree, generates a first information recommendation list, and pushes the information in the first information recommendation list to the user.
- the information data subset includes a plurality of information data, wherein the information data includes the content of the information, such as the text content of the information, the title of the information, and the like.
- classifying the information data subsets in the information browsing trace data set can classify the information data subsets from different dimensions. For example, the news data in the news data subset is classified according to the type of the data; or the news data in the news data subset is classified according to the author of the news data.
- feature extraction is performed on the information data subset in the information browsing trace data set, and then the information feature data subset after the feature extraction is classified.
- a convolutional neural network is used to perform feature extraction on a subset of information data in the information browsing trace data set to obtain a subset of information characteristic data.
- the information characteristic data subset includes information characteristic data, and the information characteristic data
- the subsets include: news title, news length, news keywords, news industry distribution, news-related stock distribution, etc.
- the active user push module classifies the information data subsets in the information browsing trace data set, including:
- the category of the information data in the information data subset is determined according to the classification result with the largest probability value among the plurality of classification results.
- classification function is:
- ⁇ is a preset system parameter
- X (i) is the ith information data in the information data subset
- e is the natural logarithm
- g( ⁇ X (i) ) is the classification result.
- the classification result includes categories corresponding to each information data in the information data subset, for example, news category, advertisement category, and the like.
- the user's preference for different types of information data is calculated based on the number of times the user browses the information data.
- the present application uses the following preference algorithm to calculate the preference degree:
- n is the total number of times the user browses all information
- m is the number of times the user browses information data of a certain category
- p(o) is the user's preference for this category of information data.
- the information set to be recommended may be a collection of information data that is newly generated and has not been pushed to the user.
- the selecting a plurality of pieces of information data from the information set to be recommended according to the preference degree includes:
- the information in the first information recommendation list that is pushed by the active user push module to the user includes:
- the information in the first information recommendation list is pushed to the user at the pushing time.
- the extraction of time series features of the information browsing trace data set includes:
- t u is the time interval for the user to browse the information data.
- the embodiment of the present application after acquiring the time sequence feature, performs mathematical statistics on the time sequence feature to obtain the browsing time preference of the user's browsing information, and then determines the push time according to the browsing time preference. If user L prefers to browse information data in the morning and user J prefers to browse information data in the afternoon, the information in the first information recommendation list is pushed to user L in the morning, and the information in the first information recommendation list is pushed to user J in the afternoon.
- a timer may be used to push information data to the user according to the push time, so as to achieve the purpose of timely personalized push.
- the first information recommendation list is determined, and personalized push can be performed quickly and accurately.
- the inactive user push module 103 is configured to, if the user is an inactive user, obtain a set of similar users according to a subset of information data in the information browsing trace data set, and, according to the set of similar users, provide a set of information to be recommended. generate a second information recommendation list, and push the information in the second information recommendation list to the user.
- the set of similar users may include a plurality of similar users, the similar users are users who have browsed the same or similar information data as the users, or the similar users are users who are similar to the user and have browsed the same basic information or similar information data users.
- the obtaining a similar user set according to the information data subset in the information browsing trace data set includes:
- Feature extraction is performed on the information data subset in the information browsing trace data set, and then the similar user set is determined according to the feature extraction result.
- the embodiment of the present application uses a convolutional neural network to perform feature extraction on a subset of information data in the information browsing trace data set to obtain a subset of information characteristic data.
- the information characteristic data subset includes information characteristic data, and the information characteristic data
- the subset includes: news title, news length, news keywords, news industry distribution, news-related stock distribution, news score, etc.
- a is the inactive user
- b is the similar user in the similar user set
- r a,p is the score of user a on the information data p in the information data subset
- r b,p is the score of user b on the information data p in the information data subset
- P is the information data subset.
- the similar users with the highest similarity to the inactive users are selected from the similar user set, and a preset scoring algorithm is used to calculate the predicted score of the information to be recommended in the information set to be recommended by the similar users, and select The information to be recommended whose predicted score is greater than the preset score threshold in the information set to be recommended is collected into the second information recommendation list.
- the information set to be recommended may be a collection of information data that is newly generated and has not been pushed to the user.
- the scoring algorithm is:
- pred(x,b) is the rating of similar user b to the information to be recommended x in the information set to be recommended
- b is the similar user
- N is the similar user set
- x is the information set to be recommended.
- Information to be recommended, r b, p are the ratings of user b on the information data p in the information data subset, is the mean of user b's score on the news data subset in the news data subset, is a preset score base value
- sim(a, b) is the similarity between the inactive user a and the similar user b in the similar user set.
- the embodiment of the present application realizes the purpose of accurate personalized push by judging whether the user is an active user, and selecting different methods according to the type of the user to generate an information recommendation list and perform information recommendation. efficiency. Therefore, the information push device proposed in the present application can improve the efficiency of information push and carry out personalized information push.
- FIG. 3 it is a schematic structural diagram of an electronic device implementing the information push method of the present application.
- the electronic device 1 may include a processor 10 , a memory 11 and a bus, and may also include a computer program stored in the memory 11 and executed on the processor 10 , such as an information push program 12 .
- the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc.
- the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 .
- the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash memory card (Flash Card), etc.
- the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
- the memory 11 can not only be used to store application software installed in the electronic device 1 and various types of data, such as the code of the information push program 12, etc., but also can be used to temporarily store data that has been output or will be output.
- the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits.
- Central Processing Unit CPU
- microprocessor digital processing chip
- graphics processor and combination of various control chips, etc.
- the processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing the program or module (for example, executing the program) stored in the memory 11. information push program, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
- the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like.
- PCI peripheral component interconnect
- EISA Extended industry standard architecture
- the bus can be divided into address bus, data bus, control bus and so on.
- the bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.
- FIG. 3 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 3 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the figure. components, or a combination of certain components, or a different arrangement of components.
- the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management
- the device implements functions such as charge management, discharge management, and power consumption management.
- the power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
- the electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
- the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
- a network interface optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
- the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
- the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
- the information push program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, can realize:
- a similar user set is obtained according to the information data subset in the information browsing trace data set, and a second information recommendation list is generated according to the information score of the information set to be recommended according to the similar user set, and sent to The user pushes the information in the second information recommendation list.
- the embodiment of the present application realizes the purpose of accurate personalized push by judging whether the user is an active user, and selecting different methods according to the type of the user to generate an information recommendation list and perform information recommendation. efficiency. Therefore, the efficiency of information push can be improved, and personalized information push can be performed.
- the modules/units integrated in the electronic device 1 may be stored in a computer-readable storage medium.
- the computer-readable storage medium may be volatile or non-volatile, and the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, Mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).
- the computer-usable storage medium may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required by at least one function, and the like; Using the created data, etc., the application program implements the following steps when executed by the processor:
- a similar user set is obtained according to the information data subset in the information browsing trace data set, and a second information recommendation list is generated according to the information score of the information set to be recommended according to the similar user set, and sent to The user pushes the information in the second information recommendation list.
- modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
- each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
- the above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.
- the blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
- Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种资讯推送方法,包括:获取用户的资讯浏览痕迹数据集,判断用户是否为活跃用户;若用户为活跃用户,对资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对资讯数据子集中不同类别的资讯数据的偏好程度,根据偏好程度生成第一资讯推荐列表,向用户推送第一资讯推荐列表中的资讯(S2);若用户为非活跃用户,根据资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据相似用户集对待推荐资讯集的资讯评分生成第二资讯推荐列表,向用户推送第二资讯推荐列表中的资讯(S3)。此外,资讯浏览痕迹数据集还可存储于区块链节点中。通过以上方式可以提高资讯推送的效率,进行个性化的资讯推送。
Description
本申请要求于2020年12月30日提交中国专利局、申请号为CN202011644071.7,发明名称为“资讯推送方法、装置、电子设备及计算机可读存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及数据处理技术领域,尤其涉及一种资讯推送方法、装置、电子设备及计算机可读存储介质。
随着网络的迅速发展,网络中随时都可能产生大量的资讯。在向用户进行资讯推送时,若将海量的资讯都推送至客户端,将消耗较大的网络带宽,占用较大的存储资源,也降低服务器端和客户端的运行效率。如何筛选出符合用户的资讯并推送给用户,成为了越来越重要的需求。
目前市场上主流的资讯推送方法是人工筛选资讯,从而选择性的对用户进行资讯推送。发明人意识到此种方法过于依赖于人工进行,效率低下且筛选出的资讯不能精准的与用户进行匹配,无法达成既高效又个性化的资讯推送。
发明内容
一种资讯推送方法,包括:
获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;
若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
一种资讯推送装置,所述装置包括:
用户类别判断模块,用于获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;
活跃用户推送模块,用于若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
非活跃用户推送模块,用于若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
一种电子设备,所述电子设备包括:
存储器,存储至少一个指令;及
处理器,执行所述存储器中存储的指令以实现如下步骤:
获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;
若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
一种计算机可读存储介质,包括存储数据区和存储程序区,存储数据区存储创建的数据,存储程序区存储有计算机程序;其中,所述计算机程序被处理器执行时实现如下步骤:
获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;
若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
本申请可以提高资讯推送的效率,进行个性化的资讯推送。
图1为本申请一实施例提供的资讯推送方法的流程示意图;
图2为本申请一实施例提供的资讯推送装置的模块示意图;
图3为本申请一实施例提供的实现资讯推送方法的电子设备的内部结构示意图;
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供的资讯推送方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述资讯推送方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
本申请提供一种资讯推送方法。参照图1所示,为本申请一实施例提供的资讯推送方法的流程示意图。在本实施例中,所述资讯推送方法包括:
S1、获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户。
本申请实施例中,所述用户的资讯浏览痕迹数据集包括一段时间内用户在浏览器或类似客户端浏览资讯数据的浏览信息集合,其中,资讯浏览痕迹数据集包括但不限于:浏览资讯的开始时间、浏览资讯的结束时间、浏览资讯的标题、浏览资讯的内容、对所浏览资讯的评分。
具体地,可利用数据抓取方法获取资讯浏览痕迹数据集。例如,利用具有数据抓取功能的python语句,从用户浏览的网站的后台和/或用于存储所述资讯浏览痕迹数据集的区块链中抓取资讯浏览痕迹数据,并将所有抓取到的某一用户的资讯浏览痕迹数据汇集作为 该用户的资讯浏览痕迹数据集,该用户资讯浏览痕迹数据表示为:X
(i)={x
(1),…x
(n)},其中,x表示每次浏览资讯数据的浏览信息子集。
可选的,所述根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户包括:
根据所述资讯浏览痕迹数据集中的浏览信息确定所述用户是否为活跃用户,所述浏览信息包括但不限于浏览次数、浏览时间间隔、对所浏览资讯的评分之中的一项或多项。
例如,统计资讯浏览痕迹数据集中用户对资讯数据的浏览次数,判断在预设时间段内,该浏览次数是否达到预设的次数阈值(如10次),当该浏览次数小于或等于所述次数阈值时,判定该用户为非活跃客户;当该浏览次数大于所述次数阈值时,判定该用户为活跃用户。
又比如,统计资讯浏览痕迹数据集中用户的浏览次数和浏览时间间隔,若用户的浏览次数大于预设的次数阈值(如10次),且浏览时间间隔小于预设间隔时间或浏览时间间隔逐渐减小并趋于稳定,判定用户为活跃用户;若用户的浏览次数小于预设的次数或浏览时间间隔大于预设间隔时间,判定用户为非活跃用户。
S2、若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯。
本实施例中,资讯数据子集包含多个资讯数据,其中,资讯数据包括资讯的内容,如资讯的正文内容,资讯的标题等。
本实施例中,对资讯浏览痕迹数据集中资讯数据子集进行分类可以从不同维度对资讯数据子集进行分类。例如,根据数据的类型对资讯数据子集中资讯数据进行分类;或者根据资讯数据的作者对资讯数据子集中资讯数据进行分类。
具体的,在本实施例中,对资讯浏览痕迹数据集中资讯数据子集进行特征提取,再对特征提取后的资讯特征数据子集进行分类。
较佳地,本申请实施例采用卷积神经网络对资讯浏览痕迹数据集中资讯数据子集进行特征提取,得到资讯特征数据子集,该资讯特征数据子集中包含资讯特征数据,所述资讯特征数据子集包括:资讯标题、资讯长度、资讯关键词、资讯行业分布、资讯相关的股票分布等。
优选的,本申请一可选实施例中,所述对所述资讯浏览痕迹数据集中资讯数据子集进行分类,包括:
利用多个分类函数对所述资讯浏览痕迹数据集中资讯数据子集进行分类,得到多个分类结果;
根据所述多个分类结果中概率值最大的分类结果确定所述资讯数据子集中资讯数据的类别。
进一步地,所述分类函数为:
其中,θ为预设系统参数,X
(i)为所述资讯数据子集中第i个资讯数据,e为自然对数,g(θX
(i))为分类结果。
较佳地,所述分类结果包括资讯数据子集中各资讯数据对应的类别,例如,新闻类,广告类等。
进一步地,本申请一可选实施例中,基于用户对资讯数据的浏览次数,计算用户对不同类别的资讯数据的偏好程度。
详细地,本申请利用如下偏好算法计算所述偏好程度:
p(o)=m/n
其中,n为用户对所有资讯的总浏览次数,m为用户对某一类别的资讯数据的浏览次数,p(o)为用户对该类别的资讯数据的偏好程度。
本实施例中,待推荐资讯集可以为新产生且未向用户进行推送的资讯数据的集合。
所述根据所述偏好程度从待推荐资讯集中选取多个资讯数据包括:
计算待推荐资讯集中资讯数据的类型与所述偏好程度的相似度,选取相似度大于预设相似度的多个资讯数据,生成第一资讯推荐列表。
进一步的,在本申请一可选实施例中,所述向所述用户推送所述第一资讯推荐列表中的资讯,包括:
提取所述资讯浏览痕迹数据集的时序特征;
根据所述时序特征统计所述用户的浏览时间偏好;
根据所述浏览时间偏好确定推送时间;
在所述推送时间向所述用户推送所述第一资讯推荐列表中的资讯。
进一步的,在本申请另一可选实施例中,所述提取资讯浏览痕迹数据集的时序特征,包括:
利用时序特征提取算法提取所述资讯浏览痕迹数据集的时序特征b
u(t):
本实施例中,当获取到时序特征后,本申请实施例对所述时序特征进行数理统计,得到用户浏览资讯的浏览时间偏好,再根据浏览时间偏好确定推送时间。如用户L偏好在早上浏览资讯数据,用户J偏好在午后浏览资讯数据,则在早上向用户L推送第一资讯推荐列表中的资讯,在午后向用户J推送第一资讯推荐列表中的资讯。
优选地,本申请实施例可采用定时器根据推送时间对用户进行资讯数据的推送,达到及时的个性化推送的目的。
本实施例中,通过对用户对不同资讯数据的偏好程序进行计算,从而确定第一资讯推荐列表,能够快速准确的进行个性化推送。
S3、若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。本实施例中,所述相似用户集中可以包含多个相似用户,所述相似用户为与所述用户浏览过相同或相似的资讯数据的用户,或者相似用户为与用户基本信息类似且浏览过相同或相似的资讯数据的用户。
可选的,所述根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集包括:
对资讯浏览痕迹数据集中资讯数据子集进行特征提取,再根据特征提取结果确定相似用户集。
较佳地,本申请实施例采用卷积神经网络对资讯浏览痕迹数据集中资讯数据子集进行特征提取,得到资讯特征数据子集,该资讯特征数据子集中包含资讯特征数据,所述资讯特征数据子集包括:资讯标题、资讯长度、资讯关键词、资讯行业分布、资讯相关的股票分布、资讯评分等。
利用如下相似度算法计算所述非活跃用户和所述相似用户集中相似用户的相似度sim(a,b):
其中,a为所述非活跃用户,b为所述相似用户集中相似用户,
为用户a对资讯数据子集中资讯数据评分的均值,
为用户b对资讯数据子集中资讯数据评分的均值,r
a,p为用 户a对资讯数据子集中资讯数据p的评分,r
b,p为用户b对资讯数据子集中资讯数据p的评分,P为所述资讯数据子集。
优选地,本申请实施例将所述相似用户集中与所述非活跃用户相似度最高的相似用户筛选出来,利用预设评分算法计算所述相似用户对待推荐资讯集中待推荐资讯的预测评分,选择所述待推荐资讯集中预测评分大于预设评分阈值的待推荐资讯,汇集为所述第二资讯推荐列表。
本实施例中,待推荐资讯集可以为新产生且未向用户进行推送的资讯数据的集合。
详细地,所述评分算法为:
其中,pred(x,b)为相似用户b对所述待推荐资讯集中待推荐资讯x的评分,b为所述相似用户,N为所述相似用户集,x为所述待推荐资讯集中的待推荐资讯,r
b,p为用户b对资讯数据子集中资讯数据p的评分,
为用户b对资讯数据子集中资讯数据评分的均值,
为预设的评分基值,sim(a,b)为所述非活跃用户a和所述相似用户集中相似用户b的相似度。
由于非活跃用户的资讯浏览量较少,通过非活跃用户自身的浏览痕迹难以准确地找出所述非活跃用户的浏览偏好,因此难以准确的对其进行资讯推送。本申请一较佳实施例中,通过获取相似用户集,根据相似用户集对待推荐资讯集的资讯评分生成第二资讯推荐列表,并基于第二资讯推荐列表进行推送,实现了精准的个性化推送的目的。
本申请实施例通过判断用户是否为活跃用户,根据用户的类型选取不同方式生成资讯推荐列表并进行资讯推荐,实现准确的个性化推送的目的,同时,推荐时无需人工筛选,提高了资讯推送的效率。因此本申请提出的资讯推送方法,可以提高资讯推送的效率,进行个性化的资讯推送。
如图2所示,是本申请资讯推送装置的模块示意图。
本申请所述资讯推送装置100可以安装于电子设备中。根据实现的功能,所述资讯推送装置可以包括用户类别判断模块101、活跃用户推送模块102和非活跃用户推送模块103。本发所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述用户类别判断模块101,用于获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;
所述活跃用户推送模块102,用于若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
所述非活跃用户推送模块103,用于若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
详细地,所述图像中文本内容提取生成装置各模块的具体实施方式如下:
所述用户类别判断模块101,用于获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户。
本申请实施例中,所述用户的资讯浏览痕迹数据集包括一段时间内用户在浏览器或类似客户端浏览资讯数据的浏览信息集合,其中,资讯浏览痕迹数据集包括但不限于:浏览资讯的开始时间、浏览资讯的结束时间、浏览资讯的标题、浏览资讯的内容、对所浏览资讯的评分。
具体地,所述用户类别判断模块101可使用具有数据抓取功能的python语句,从用户浏览的网站的后台抓取资讯浏览痕迹数据,并将所有抓取到的某一用户的资讯浏览痕迹数据汇集作为该用户的资讯浏览痕迹数据集,该用户资讯浏览痕迹数据表示为:X
(i)={x
(1),…x
(n)},其中,x表示每次浏览资讯数据的浏览信息子集。
可选的,所述根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户包括:
根据所述资讯浏览痕迹数据集中的浏览信息确定所述用户是否为活跃用户,所述浏览信息包括但不限于浏览次数、浏览时间间隔、对所浏览资讯的评分之中的一项或多项。
例如,统计资讯浏览痕迹数据集中用户对资讯数据的浏览次数,判断在预设时间段内,该浏览次数是否达到预设的次数阈值(如10次),当该浏览次数小于或等于所述次数阈值时,判定该用户为非活跃客户;当该浏览次数大于所述次数阈值时,判定该用户为活跃用户。
又比如,统计资讯浏览痕迹数据集中用户的浏览次数和浏览时间间隔,若用户的浏览次数大于预设的次数阈值(如10次),且浏览时间间隔小于预设间隔时间或浏览时间间隔逐渐减小并趋于稳定,判定用户为活跃用户;若用户的浏览次数小于预设的次数或浏览时间间隔大于预设间隔时间,判定用户为非活跃用户。
所述活跃用户推送模块102,用于若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯。
本实施例中,资讯数据子集包含多个资讯数据,其中,资讯数据包括资讯的内容,如资讯的正文内容,资讯的标题等。
本实施例中,对资讯浏览痕迹数据集中资讯数据子集进行分类可以从不同维度对资讯数据子集进行分类。例如,根据数据的类型对资讯数据子集中资讯数据进行分类;或者根据资讯数据的作者对资讯数据子集中资讯数据进行分类。
具体的,在本实施例中,对资讯浏览痕迹数据集中资讯数据子集进行特征提取,再对特征提取后的资讯特征数据子集进行分类。
较佳地,本申请实施例采用卷积神经网络对资讯浏览痕迹数据集中资讯数据子集进行特征提取,得到资讯特征数据子集,该资讯特征数据子集中包含资讯特征数据,所述资讯特征数据子集包括:资讯标题、资讯长度、资讯关键词、资讯行业分布、资讯相关的股票分布等。
优选的,本申请一可选实施例中,所述活跃用户推送模块对所述资讯浏览痕迹数据集中资讯数据子集进行分类,包括:
利用多个分类函数对所述资讯浏览痕迹数据集中资讯数据子集进行分类,得到多个分类结果;
根据所述多个分类结果中概率值最大的分类结果确定所述资讯数据子集中资讯数据的类别。
进一步地,所述分类函数为:
其中,θ为预设系统参数,X
(i)为所述资讯数据子集中第i个资讯数据,e为自然对数,g(θX
(i))为分类结果。
较佳地,所述分类结果包括资讯数据子集中各资讯数据对应的类别,例如,新闻类,广告类等。
进一步地,本申请一可选实施例中,基于用户对资讯数据的浏览次数,计算用户对不同类别的资讯数据的偏好程度。
详细地,本申请利用如下偏好算法计算所述偏好程度:
p(o)=m/n
其中,n为用户对所有资讯的总浏览次数,m为用户对某一类别的资讯数据的浏览次数,p(o)为用户对该类别的资讯数据的偏好程度。
本实施例中,待推荐资讯集可以为新产生且未向用户进行推送的资讯数据的集合。
所述根据所述偏好程度从待推荐资讯集中选取多个资讯数据包括:
计算待推荐资讯集中资讯数据的类型与所述偏好程度的相似度,选取相似度大于预设相似度的多个资讯数据,生成第一资讯推荐列表。
进一步的,在本申请一可选实施例中,所述活跃用户推送模块向所述用户推送所述第一资讯推荐列表中的资讯包括:
提取所述资讯浏览痕迹数据集的时序特征;
根据所述时序特征统计所述用户的浏览时间偏好;
根据所述浏览时间偏好确定推送时间;
在所述推送时间向所述用户推送所述第一资讯推荐列表中的资讯。
进一步的,在本申请另一可选实施例中,所述提取资讯浏览痕迹数据集的时序特征,包括:
利用时序特征提取算法提取所述资讯浏览痕迹数据集的时序特征b
u(t):
本实施例中,当获取到时序特征后,本申请实施例对所述时序特征进行数理统计,得到用户浏览资讯的浏览时间偏好,再根据浏览时间偏好确定推送时间。如用户L偏好在早上浏览资讯数据,用户J偏好在午后浏览资讯数据,则在早上向用户L推送第一资讯推荐列表中的资讯,在午后向用户J推送第一资讯推荐列表中的资讯。
优选地,本申请实施例可采用定时器根据推送时间对用户进行资讯数据的推送,达到及时的个性化推送的目的。
本实施例中,通过对用户对不同资讯数据的偏好程序进行计算,从而确定第一资讯推荐列表,能够快速准确的进行个性化推送。
所述非活跃用户推送模块103,用于若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
本实施例中,所述相似用户集中可以包含多个相似用户,所述相似用户为与所述用户浏览过相同或相似的资讯数据的用户,或者相似用户为与用户基本信息类似且浏览过相同或相似的资讯数据的用户。
可选的,所述根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集包括:
对资讯浏览痕迹数据集中资讯数据子集进行特征提取,再根据特征提取结果确定相似用户集。
较佳地,本申请实施例采用卷积神经网络对资讯浏览痕迹数据集中资讯数据子集进行特征提取,得到资讯特征数据子集,该资讯特征数据子集中包含资讯特征数据,所述资讯特征数据子集包括:资讯标题、资讯长度、资讯关键词、资讯行业分布、资讯相关的股票分布、资讯评分等。
利用如下相似度算法计算所述非活跃用户和所述相似用户集中相似用户的相似度sim(a,b):
其中,a为所述非活跃用户,b为所述相似用户集中相似用户,
为用户a对资讯数据子集中资讯数据评分的均值,
为用户b对资讯数据子集中资讯数据评分的均值,r
a,p为用户a对资讯数据子集中资讯数据p的评分,r
b,p为用户b对资讯数据子集中资讯数据p的评分,P为所述资讯数据子集。
优选地,本申请实施例将所述相似用户集中与所述非活跃用户相似度最高的相似用户筛选出来,利用预设评分算法计算所述相似用户对待推荐资讯集中待推荐资讯的预测评分,选择所述待推荐资讯集中预测评分大于预设评分阈值的待推荐资讯,汇集为所述第二资讯推荐列表。
本实施例中,待推荐资讯集可以为新产生且未向用户进行推送的资讯数据的集合。
详细地,所述评分算法为:
其中,pred(x,b)为相似用户b对所述待推荐资讯集中待推荐资讯x的评分,b为所述相似用户,N为所述相似用户集,x为所述待推荐资讯集中的待推荐资讯,r
b,p为用户b对资讯数据子集中资讯数据p的评分,
为用户b对资讯数据子集中资讯数据评分的均值,
为预设的评分基值,sim(a,b)为所述非活跃用户a和所述相似用户集中相似用户b的相似度。
由于非活跃用户的资讯浏览量较少,通过非活跃用户自身的浏览痕迹难以准确地找出所述非活跃用户的浏览偏好,因此难以准确的对其进行资讯推送。本申请一较佳实施例中,通过获取相似用户集,根据相似用户集对待推荐资讯集的资讯评分生成第二资讯推荐列表,并基于第二资讯推荐列表进行推送,实现了精准的个性化推送的目的。
本申请实施例通过判断用户是否为活跃用户,根据用户的类型选取不同方式生成资讯推荐列表并进行资讯推荐,实现准确的个性化推送的目的,同时,推荐时无需人工筛选,提高了资讯推送的效率。因此本申请提出的资讯推送装置,可以提高资讯推送的效率,进行个性化的资讯推送。
如图3所示,是本申请实现资讯推送方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如资讯推送程序12。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(Smart Media Card,SMC)、安全数字(Secure Digital,SD)卡、闪存卡(Flash Card)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如资讯推送程序12的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(Central Processing unit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(Control Unit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如执行资讯推送程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheral component interconnect,简称PCI)总 线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图3仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图3示出的结构并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的资讯推送程序12是多个指令的组合,在所述处理器10中运行时,可以实现:
获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;
若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
本申请实施例通过判断用户是否为活跃用户,根据用户的类型选取不同方式生成资讯推荐列表并进行资讯推荐,实现准确的个性化推送的目的,同时,推荐时无需人工筛选,提高了资讯推送的效率。因此可以提高资讯推送的效率,进行个性化的资讯推送。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。所述计算机可读存储介质可以是易失性的,也可以是非易失性的,所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)。
进一步地,所述计算机可用存储介质可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序等;存储数据区可存储根据区块链节点的使用所创建的数据等,所述应用程序被处理器执行时实现如下步骤:
获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为 活跃用户;
若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;
若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图表记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。
Claims (20)
- 一种资讯推送方法,其中,所述方法包括:获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
- 如权利要求1所述的资讯推送方法,其中,所述向所述用户推送所述第一资讯推荐列表中的资讯,包括:提取所述资讯浏览痕迹数据集的时序特征;根据所述时序特征统计所述用户的浏览时间偏好;根据所述浏览时间偏好确定推送时间;在所述推送时间向所述用户推送所述第一资讯推荐列表中的资讯。
- 如权利要求1至3中任一项所述的资讯推送方法,其中,所述对所述资讯浏览痕迹数据集中资讯数据子集进行分类,包括:利用多个分类函数对所述资讯浏览痕迹数据集中资讯数据子集进行分类,得到多个分类结果;根据所述多个分类结果中概率值最大的分类结果确定所述资讯数据子集中资讯数据的类别。
- 如权利要求1所述的资讯推送方法,其中,所述根据所述偏好程度从待推荐资讯集中选取多个资讯数据包括:计算待推荐资讯集中资讯数据的类型与所述偏好程度的相似度,选取相似度大于预设相似度的多个资讯数据。
- 如权利要求1所述的资讯推送方法,其中,所述计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度包括利用如下偏好算法计算所述偏好程度:p(o)=m/n其中,n为用户对所有资讯的总浏览次数,m为用户对某一类别的资讯数据的浏览次数,p(o)为用户对该类别的资讯数据的偏好程度。
- 一种资讯推送装置,其中,所述装置包括:用户类别判断模块,用于获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;活跃用户推送模块,用于若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;非活跃用户推送模块,用于若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
- 一种电子设备,其中,所述电子设备包括:至少一个处理器;以及,与所述至少一个处理器通信连接的存储器;其中,所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下步骤:获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
- 如权利要求9所述的电子设备,其中,所述向所述用户推送所述第一资讯推荐列表中的资讯,包括:提取所述资讯浏览痕迹数据集的时序特征;根据所述时序特征统计所述用户的浏览时间偏好;根据所述浏览时间偏好确定推送时间;在所述推送时间向所述用户推送所述第一资讯推荐列表中的资讯。
- 如权利要求9至11中任一项所述的电子设备,其中,所述对所述资讯浏览痕迹数据集中资讯数据子集进行分类,包括:利用多个分类函数对所述资讯浏览痕迹数据集中资讯数据子集进行分类,得到多个分类结果;根据所述多个分类结果中概率值最大的分类结果确定所述资讯数据子集中资讯数据的类别。
- 如权利要求9所述的电子设备,其中,所述根据所述偏好程度从待推荐资讯集中选取多个资讯数据包括:计算待推荐资讯集中资讯数据的类型与所述偏好程度的相似度,选取相似度大于预设相似度的多个资讯数据。
- 如权利要求9所述的电子设备,其中,所述计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度包括利用如下偏好算法计算所述偏好程度:p(o)=m/n其中,n为用户对所有资讯的总浏览次数,m为用户对某一类别的资讯数据的浏览次数,p(o)为用户对该类别的资讯数据的偏好程度。
- 一种计算机可读存储介质,包括存储数据区和存储程序区,存储数据区存储创建的数据,存储程序区存储有计算机程序;其中,所述计算机程序被处理器执行时实现如下步骤:获取用户的资讯浏览痕迹数据集,根据所述资讯浏览痕迹数据集判断所述用户是否为活跃用户;若所述用户为活跃用户,对所述资讯浏览痕迹数据集中资讯数据子集进行分类,计算所述用户对所述资讯数据子集中不同类别的资讯数据的偏好程度,根据所述偏好程度从待推荐资讯集中选取多个资讯数据,生成第一资讯推荐列表,向所述用户推送所述第一资讯推荐列表中的资讯;若所述用户为非活跃用户,根据所述资讯浏览痕迹数据集中资讯数据子集获取相似用户集,根据所述相似用户集对所述待推荐资讯集的资讯评分生成第二资讯推荐列表,向所述用户推送所述第二资讯推荐列表中的资讯。
- 如权利要求16所述的计算机可读存储介质,其中,所述向所述用户推送所述第一资讯推荐列表中的资讯,包括:提取所述资讯浏览痕迹数据集的时序特征;根据所述时序特征统计所述用户的浏览时间偏好;根据所述浏览时间偏好确定推送时间;在所述推送时间向所述用户推送所述第一资讯推荐列表中的资讯。
- 如权利要求16至18中任一项所述的计算机可读存储介质,其中,所述对所述资讯浏览痕迹数据集中资讯数据子集进行分类,包括:利用多个分类函数对所述资讯浏览痕迹数据集中资讯数据子集进行分类,得到多个分类结果;根据所述多个分类结果中概率值最大的分类结果确定所述资讯数据子集中资讯数据的类别。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011644071.7 | 2020-12-30 | ||
CN202011644071.7A CN112733023A (zh) | 2020-12-30 | 2020-12-30 | 资讯推送方法、装置、电子设备及计算机可读存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022142020A1 true WO2022142020A1 (zh) | 2022-07-07 |
Family
ID=75609318
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/090700 WO2022142020A1 (zh) | 2020-12-30 | 2021-04-28 | 资讯推送方法、装置、电子设备及计算机可读存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112733023A (zh) |
WO (1) | WO2022142020A1 (zh) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116150477A (zh) * | 2022-12-06 | 2023-05-23 | 上海贝耳塔信息技术有限公司 | 一种财经资讯个性化推荐方法、装置、设备及介质 |
CN116567068A (zh) * | 2023-07-10 | 2023-08-08 | 深圳比特耐特信息技术股份有限公司 | 一种基于大数据的信息管理方法及系统 |
CN118013129A (zh) * | 2024-03-27 | 2024-05-10 | 广东科技学院 | 基于大数据的财经资讯推送方法、系统、设备及存储介质 |
CN118075347A (zh) * | 2024-04-24 | 2024-05-24 | 杭州高能云科技有限公司 | 资讯数据推送方法、系统与存储介质 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139129B (zh) * | 2021-05-12 | 2024-02-09 | 深圳平安智慧医健科技有限公司 | 虚拟阅读轨迹图生成方法、装置、电子设备及存储介质 |
CN114579916B (zh) * | 2022-05-06 | 2022-07-29 | 深圳格隆汇信息科技有限公司 | 一种基于大数据的信息推荐方法及系统 |
CN115348353B (zh) * | 2022-08-10 | 2024-06-18 | 青岛海信智慧生活科技股份有限公司 | 一种内容推送方法和服务器 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130144871A1 (en) * | 2011-12-02 | 2013-06-06 | Verizon Patent And Licensing Inc. | Dynamic catalog ranking |
CN107066582A (zh) * | 2017-04-14 | 2017-08-18 | 聚好看科技股份有限公司 | 实现虚拟资源推荐的方法及装置 |
CN109977320A (zh) * | 2019-04-08 | 2019-07-05 | 北京网聘咨询有限公司 | 资讯推送方法及系统 |
CN110516147A (zh) * | 2019-07-22 | 2019-11-29 | 平安科技(深圳)有限公司 | 页面数据生成方法、装置、计算机设备及存储介质 |
CN111625713A (zh) * | 2020-04-30 | 2020-09-04 | 平安国际智慧城市科技股份有限公司 | 基于大数据的资源推荐方法、装置、电子设备及介质 |
-
2020
- 2020-12-30 CN CN202011644071.7A patent/CN112733023A/zh active Pending
-
2021
- 2021-04-28 WO PCT/CN2021/090700 patent/WO2022142020A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130144871A1 (en) * | 2011-12-02 | 2013-06-06 | Verizon Patent And Licensing Inc. | Dynamic catalog ranking |
CN107066582A (zh) * | 2017-04-14 | 2017-08-18 | 聚好看科技股份有限公司 | 实现虚拟资源推荐的方法及装置 |
CN109977320A (zh) * | 2019-04-08 | 2019-07-05 | 北京网聘咨询有限公司 | 资讯推送方法及系统 |
CN110516147A (zh) * | 2019-07-22 | 2019-11-29 | 平安科技(深圳)有限公司 | 页面数据生成方法、装置、计算机设备及存储介质 |
CN111625713A (zh) * | 2020-04-30 | 2020-09-04 | 平安国际智慧城市科技股份有限公司 | 基于大数据的资源推荐方法、装置、电子设备及介质 |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116150477A (zh) * | 2022-12-06 | 2023-05-23 | 上海贝耳塔信息技术有限公司 | 一种财经资讯个性化推荐方法、装置、设备及介质 |
CN116567068A (zh) * | 2023-07-10 | 2023-08-08 | 深圳比特耐特信息技术股份有限公司 | 一种基于大数据的信息管理方法及系统 |
CN116567068B (zh) * | 2023-07-10 | 2023-09-15 | 深圳比特耐特信息技术股份有限公司 | 一种基于大数据的信息管理方法及系统 |
CN118013129A (zh) * | 2024-03-27 | 2024-05-10 | 广东科技学院 | 基于大数据的财经资讯推送方法、系统、设备及存储介质 |
CN118075347A (zh) * | 2024-04-24 | 2024-05-24 | 杭州高能云科技有限公司 | 资讯数据推送方法、系统与存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN112733023A (zh) | 2021-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022142020A1 (zh) | 资讯推送方法、装置、电子设备及计算机可读存储介质 | |
WO2022141861A1 (zh) | 情感分类方法、装置、电子设备及存储介质 | |
WO2022121171A1 (zh) | 相似文本匹配方法、装置、电子设备及计算机存储介质 | |
WO2019085335A1 (zh) | 利用新词发现投资标的的方法、装置及存储介质 | |
WO2022160449A1 (zh) | 文本分类方法、装置、电子设备及存储介质 | |
US8990241B2 (en) | System and method for recommending queries related to trending topics based on a received query | |
US10348550B2 (en) | Method and system for processing network media information | |
WO2022116435A1 (zh) | 标题生成方法、装置、电子设备及存储介质 | |
US20140358630A1 (en) | Apparatus and process for conducting social media analytics | |
CN112380859A (zh) | 舆情信息的推荐方法、装置、电子设备及计算机存储介质 | |
WO2022222943A1 (zh) | 科室推荐方法、装置、电子设备及存储介质 | |
WO2022222942A1 (zh) | 问答记录生成方法、装置、电子设备及存储介质 | |
US20150120708A1 (en) | Information aggregation, classification and display method and system | |
CN111523677A (zh) | 实现对机器学习模型的预测结果进行解释的方法及装置 | |
WO2019061664A1 (zh) | 电子装置、基于用户上网数据的产品推荐方法及存储介质 | |
WO2018201666A1 (zh) | 广告生成的方法、计算机可读存储介质及系统 | |
WO2020056979A1 (zh) | 知识库搜索方法、装置及计算机可读存储介质 | |
CN113360768A (zh) | 基于用户画像的产品推荐方法、装置、设备及存储介质 | |
CN114398560B (zh) | 基于web平台的营销界面设置方法、装置、设备及介质 | |
CN112507230A (zh) | 基于浏览器的网页推荐方法、装置、电子设备及存储介质 | |
WO2019062013A1 (zh) | 电子装置、用户分群的方法、系统及计算机可读存储介质 | |
CN113515703A (zh) | 信息推荐方法、装置、电子设备及可读存储介质 | |
CN110442614B (zh) | 元数据的搜索方法及装置、电子设备、存储介质 | |
CN114860667B (zh) | 文件分类方法、装置、电子设备及计算机可读存储介质 | |
WO2022134345A1 (zh) | 文件访问方法、装置、设备及可读存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21912782 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21912782 Country of ref document: EP Kind code of ref document: A1 |