WO2018214869A1 - 业务对象推荐方法、装置、电子设备和存储介质 - Google Patents

业务对象推荐方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2018214869A1
WO2018214869A1 PCT/CN2018/087813 CN2018087813W WO2018214869A1 WO 2018214869 A1 WO2018214869 A1 WO 2018214869A1 CN 2018087813 W CN2018087813 W CN 2018087813W WO 2018214869 A1 WO2018214869 A1 WO 2018214869A1
Authority
WO
WIPO (PCT)
Prior art keywords
business object
attribute information
viewer
audience
business
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/087813
Other languages
English (en)
French (fr)
Inventor
彭彬绪
孔令云
袁平州
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sensetime Technology Development Co Ltd
Original Assignee
Beijing Sensetime Technology Development Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sensetime Technology Development Co Ltd filed Critical Beijing Sensetime Technology Development Co Ltd
Priority to SG11201909846Q priority Critical patent/SG11201909846QA/en
Priority to JP2020505964A priority patent/JP2020517038A/ja
Priority to US16/314,402 priority patent/US20190155864A1/en
Publication of WO2018214869A1 publication Critical patent/WO2018214869A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • G06Q30/0245—Surveys
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products

Definitions

  • the embodiments of the present invention relate to the field of data processing technologies, and in particular, to a service object recommendation method, apparatus, electronic device, and storage medium.
  • the attribute data of users plays an increasingly important role in the field of advertising, and the attribute data of users can guide the investment of advertisements.
  • the user is mainly tagged by the user's historical behavior data, such as a browser cookie, and then the user is classified by the tag to obtain the attribute data of the user.
  • the user's historical behavior data such as a browser cookie
  • the embodiment of the present application provides a method, an apparatus, an electronic device, and a storage medium for recommending a business object.
  • a method for recommending a business object including: acquiring audience attribute information and business object attribute information; determining, according to the audience attribute information and the business object attribute information, whether to display the a business object; the business object is presented when it is determined to present the business object.
  • the determining, according to the audience attribute information and the service object attribute information, whether to display the service object comprising: generating a viewer tag vector according to the audience attribute information; and according to the service object attribute information, Generating a service object tag vector; determining an activation rate of the service object based on the viewer tag vector and the service object tag vector; and determining to display the service object when an activation rate of the service object is greater than a set threshold.
  • generating the viewer tag vector according to the viewer attribute information including: generating a tag value corresponding to each viewer attribute according to the viewer attribute information; generating a viewer tag based on the tag value corresponding to each viewer attribute vector.
  • the generating the service object label vector according to the service object attribute information includes: generating a label value corresponding to each service object attribute according to the service object attribute information; and marking the label corresponding to each service object attribute Value, generate a business object label vector.
  • the determining, according to the audience tag vector and the service object tag vector, the activation rate of the business object including: using a logical regression basis model, based on the audience tag vector and the business object tag vector Determining the activation rate of the business object.
  • the determining, according to the audience tag vector and the service object tag vector, the activation rate of the service object comprising: acquiring a viewer weight value and a service object weight value; and based on the audience weight value and the The service object weight value is respectively weighted by the audience tag vector and the business object tag vector; and the activation rate of the business object is determined based on the weighted processed viewer tag vector and the business object tag vector.
  • the method further includes: performing regularization processing on an activation rate of the business object to obtain an optimal activation rate of the business object.
  • the displaying the business object includes: when determining that the displayed business object is multiple, according to an activation rate of the multiple business objects, the multiple The business objects are sorted; the business objects are displayed in order, in order.
  • the audience attribute information includes at least one of the following: a basic attribute of the viewer, a physical feature, a purchase type, a short-term attribute, a behavior feature, a psychological feature, a live video type, a real-time status feature, and a video business attribute.
  • the audience attribute information further includes: the following anchor attribute information is included, and the focused anchor attribute information includes at least one of the following: the talent type of the focused anchor, the gender ratio of the fan group that has paid attention to the anchor, and the age ratio.
  • the business object attribute information includes at least one of: a domain to which the business object belongs, a brand to which it belongs, an effect attribute, trigger information, a viewer attribute, and an anchor attribute.
  • the business object includes: an effect including the advertisement information.
  • a service object recommendation apparatus including: an obtaining module, configured to acquire audience attribute information and business object attribute information; and a determining module, configured to use the audience attribute information and the Deriving the business object attribute information, determining whether to display the business object; and displaying a module, when the business object is determined to be displayed, displaying the business object.
  • the determining module includes: a viewer tag vector generating submodule, configured to generate a viewer tag vector according to the viewer attribute information; and a service object tag vector generating submodule, configured to use, according to the service object attribute information, Generating a business object tag vector; an enablement rate determining submodule, configured to determine an activation rate of the business object based on the viewer tag vector and the business object tag vector; and a business object determining submodule for using the business object When the enable rate is greater than the set threshold, it is determined to display the business object.
  • the viewer tag vector generation sub-module is configured to generate a tag value corresponding to each viewer attribute according to the viewer attribute information, and generate a viewer tag vector based on the tag value corresponding to each viewer attribute.
  • the service object tag vector generation sub-module is configured to generate a tag value corresponding to each service object attribute according to the service object attribute information, and generate a service object tag based on the tag value corresponding to each service object attribute. vector.
  • the activation rate determining submodule is configured to determine an activation rate of the service object based on the audience tag vector and the service object tag vector by using a logistic regression base model.
  • the activation rate determining submodule is configured to obtain a viewer weight value and a service object weight value, and respectively, the audience label vector and the business object based on the audience weight value and the business object weight value
  • the label vector is weighted, and the activation rate of the business object is determined based on the weighted processed viewer tag vector and the business object tag vector.
  • the device further includes: a regularization processing module, configured to perform regularization processing on an activation rate of the business object, to obtain an optimal activation rate of the business object.
  • a regularization processing module configured to perform regularization processing on an activation rate of the business object, to obtain an optimal activation rate of the business object.
  • the displaying module includes: a sorting submodule, configured to sort the plurality of business objects according to an activation rate of the plurality of business objects when determining that the displayed business objects are multiple; a sub-module for sequentially displaying the business object in order.
  • the audience attribute information includes at least one of the following: a basic attribute of the viewer, a physical feature, a purchase type, a short-term attribute, a behavior feature, a psychological feature, a live video type, a real-time status feature, and a video business attribute.
  • the audience attribute information further includes: the following anchor attribute information is included, and the focused anchor attribute information includes at least one of the following: the talent type of the focused anchor, the gender ratio of the fan group that has paid attention to the anchor, and the age ratio.
  • the business object attribute information includes at least one of: a domain to which the business object belongs, a brand to which it belongs, an effect attribute, trigger information, a viewer attribute, and an anchor attribute.
  • the business object includes: an effect including the advertisement information.
  • an electronic device comprising: a processor, a memory, a communication component, and a communication bus, wherein the processor, the memory, and the communication component are completed by the communication bus Inter-communication; the memory is for storing at least one executable instruction, the executable instruction causing the processor to perform an operation corresponding to the business object recommendation method of the first aspect.
  • a computer readable storage medium having stored thereon a computer program, the program being executed by a processor to implement the steps of the business object recommendation method according to the first aspect .
  • the business object recommendation method in the embodiment of the present application determines whether to display the business object according to the audience attribute information and the business object attribute information by acquiring the audience attribute information and the business object attribute information, and displays the business object when determining to display the business object.
  • the audience attribute information Through the audience attribute information, a business object matching the audience can be determined from the business object library, the business object is more in line with the viewing interest of the viewer, and different business objects can be pushed to different audiences, thereby improving the push business object. Accuracy and flexibility.
  • FIG. 1 is a flow chart of steps of a method for recommending a business object according to an embodiment of the present application
  • FIG. 2 is a flow chart of steps of a method for recommending a business object according to another embodiment of the present application
  • FIG. 3 is a structural block diagram of a service object recommendation apparatus according to an embodiment of the present application.
  • FIG. 4 is a structural block diagram of a service object recommendation apparatus according to another embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • FIG. 1 a flow chart of steps of a method for recommending a business object according to an embodiment of the present application is shown.
  • the background server in the live broadcast scenario is taken as an example, and the method for recommending the service object in the embodiment of the present application is explained.
  • the service object recommendation method in this embodiment can be applied not only to the live broadcast scenario but also to the application.
  • the service object recommendation method in this embodiment may be performed before the video on-demand and the video on-demand process, and the specific application scenario of the service object recommendation method is not limited in this embodiment.
  • the method provided by the embodiment of the present application is applicable not only to the background server but also to the client.
  • Step 102 Obtain audience attribute information and business object attribute information.
  • the first terminal (such as the anchor end) establishes a video communication connection with the second terminal (the fan end, that is, the viewer end) of the live broadcast platform of the live broadcast platform where the video anchor is located.
  • the second terminal the fan end, that is, the viewer end
  • the synchronization and update of the business object can be implemented through the network, wherein the business object library stores a plurality of types of business objects.
  • the background server obtains the current audience attribute information, such as obtaining the viewer's camera permission, collecting the image data of the anchor through the camera, obtaining the audience attribute information through the image data, and obtaining the audience attribute information by means of a questionnaire.
  • Information can be generated in the form of an entry.
  • the tag information of the anchor is established according to the obtained audience attribute information, and the tag information of the anchor is established according to the classification of the attribute information.
  • the tag information may be generated in the form of an entry.
  • Step 104 Determine whether to display the business object according to the audience attribute information and the business object attribute information.
  • the purpose of accurate recommendation is achieved, and the audience attribute information and the business object attribute information are combined to determine whether there is a suitable business object, such as the audience attribute information and the business object attribute.
  • the information is determined whether there is a business object matching the above two parameters in the business object library.
  • Step 106 Display a business object when it is determined to display the business object.
  • a series of related processing may be performed on one or more business objects to be displayed, and the processed business object to be displayed is displayed on the second terminal.
  • the anchor end may display a plurality of service objects to be displayed in a list form on the live broadcast interface of the anchor end. Therefore, based on the list, the part of the service object or all the business objects can be selected and pushed to the audiences in the live broadcast room, and the business objects can be sorted and sent to the audiences in the live broadcast room at the anchor end, thereby realizing Each business object pushed by the anchor is displayed on each viewer.
  • the business object recommendation method of the embodiment determines whether to display the business object according to the audience attribute information and the business object attribute information by acquiring the audience attribute information and the business object attribute information, and displays the business object when determining to display the business object.
  • the audience attribute information Through the audience attribute information, a business object matching the audience can be determined from the business object library, the business object is more in line with the viewing interest of the viewer, and different business objects can be pushed to different audiences, thereby improving the push business object. Accuracy and flexibility.
  • FIG. 2 a flow chart of steps of a method for recommending a business object according to another embodiment of the present application is shown, which may specifically include the following steps:
  • Step 202 Acquire viewer attribute information and business object attribute information.
  • Step 204 Determine, according to the audience attribute information and the business object attribute information, whether to display the business object.
  • this step 204 may include the following sub-steps:
  • Sub-step 2041 generating a viewer tag vector according to the viewer attribute information, and generating a business object tag vector according to the business object attribute information.
  • the tag value corresponding to each viewer attribute may be generated according to the viewer attribute information; and the viewer tag vector is generated based on the tag value corresponding to each viewer attribute.
  • the background server obtains the audience attribute information of the current anchor before the live broadcast or during the live broadcast.
  • the audience attribute information includes at least one of the following: a basic attribute of the viewer, a physical feature, a purchase type, a short-term attribute, a behavior feature, a psychological feature, a live video type, a real-time status feature, and a video commercial attribute; and the audience attribute information includes: Focusing on the anchor attribute information, the attention to the anchor attribute information includes at least one of the following: the gender ratio and age ratio of the fan group that has paid attention to the anchor, and the talent type of the anchor that has been concerned.
  • the tag value corresponding to each viewer attribute is generated according to the viewer attribute information, and the tag value corresponding to each viewer attribute can be seen in Table 1.
  • the tag value corresponding to each viewer attribute may be binarized, that is, “yes” in the tag value corresponding to the audience attribute is represented by “1”. "No” is represented by “0”, and the viewer tag vector is represented by u(n), see Table 2.
  • the tag value corresponding to each business object attribute may be generated according to the business object attribute information; and the business object tag vector is generated based on the tag value corresponding to each business object attribute.
  • the background server, the first terminal, and the second terminal in this embodiment are all provided with a business object library, and the synchronization and update of the business object can be implemented through the network, wherein the business object includes There are special effects of advertising information, such as at least one of the following special effects including advertising information: two-dimensional sticker effects, three-dimensional effects, particle effects.
  • advertising information such as at least one of the following special effects including advertising information: two-dimensional sticker effects, three-dimensional effects, particle effects.
  • an advertisement displayed in the form of a sticker ie, an advertisement sticker
  • an effect for displaying an advertisement such as a 3D advertisement effect.
  • the present invention is not limited thereto, and other forms of business objects are also applicable to the business object recommendation method provided by the embodiment of the present application, such as a text description or introduction of an APP or other application, or a certain form of an object (such as an electronic pet) that interacts with the audience. .
  • the business object attribute information includes at least one of the following: the domain to which the business object belongs, the brand to which it belongs, the effect attribute, the trigger information, the audience attribute, and the anchor attribute, and the tag value corresponding to each business object attribute is generated according to the attribute information of the business object, and the business object attribute corresponds to See Table 3 for the tag values.
  • the label value corresponding to each business object attribute may be binarized, that is, the label value corresponding to the business object attribute is “yes”. 1" means that "No” is represented by "0”, and the business object tag vector is represented by a(n), see Table 4.
  • Sub-step 2042 determining an activation rate of the business object based on the viewer tag vector and the business object tag vector.
  • the activation rate of the business object can be determined based on the audience tag vector and the business object tag vector through the logistic regression base model.
  • x(a, u) is used to represent the eigenvectors of the combination of u(n) and a(n), and then the logistic regression basis model is used to determine the activation rate of the business object, and the following formula can be used. :
  • p is the activation rate of the business object
  • u represents the viewer tag vector
  • a represents the business object tag vector
  • x(a, u) represents the feature vector of the viewer tag vector and the business object tag vector combination
  • ⁇ is the audience attribute information
  • the weighting coefficient of the attribute information of the business object is also a parameter that needs to be optimized by the basic model of the logistic regression;
  • the audience weight value and the business object weight value may be acquired; and the audience label vector and the business object label vector are respectively weighted based on the audience weight value and the business object weight value;
  • the weighted processed viewer tag vector and the business object tag vector determine the activation rate of the business object.
  • ⁇ is a weighting coefficient of each attribute information (including audience attribute information and business object attribute information), the weighting coefficient of u(n) is 0.5, and the weighting coefficient of a(n) is 0.5.
  • the activation rate of the business object when calculating the activation rate of the business object, in order to reduce the error, the activation rate of the business object may be regularized to obtain the optimal activation rate of the business object, which may be calculated by the following formula:
  • C is a constant, which can represent the tolerance rate
  • T represents the number of business objects.
  • Sub-step 2043 when the activation rate of the business object is greater than a set threshold, determining to display the business object.
  • the threshold is set to a, for example, a is 0.6.
  • the service object whose activation rate is greater than 0.6 is determined to be the business object to be displayed, and the threshold a may be set according to The average value of the activation rate of the overall business object is set, which is not specifically limited in this embodiment.
  • Step 206 Display a business object when it is determined to display the business object.
  • the displayed business objects may be one or more.
  • the multiple business objects may be sorted according to the activation rate of the multiple business objects, for example, according to multiple services.
  • the object's enable rate is sorted from high to low to sort multiple business objects, and then display multiple business objects in order.
  • the step of sorting multiple service objects may be completed in the background server, and then the sorted business object to be displayed is pushed to the first terminal; and the determined to be displayed may also be The service object is first pushed to the first terminal, and then the first terminal completes the sorting by the anchor. This is not specifically limited in this embodiment.
  • the business object recommendation method of the embodiment obtains the audience tag vector according to the audience attribute information by acquiring the audience attribute information and the business object attribute information, and generates the business object tag vector according to the business object attribute information, and determines the audience tag vector and the business object tag vector.
  • the service object is enabled, and the business object whose service rate is greater than the set threshold is determined as the business object to be displayed. If there are multiple business objects to be displayed, the multiple to be displayed according to the activation rate of the business object Business objects are sorted and business objects are displayed in sorted order.
  • a business object matching the audience can be determined from the business object library, the business object is more in line with the viewing interest of the viewer, and different business objects can be pushed to different audiences, thereby facilitating the push service. The accuracy and flexibility of the object.
  • the label value corresponding to the audience attribute and the label value corresponding to the business object attribute are binarized, and the workload for generating the audience label vector and the business object label vector is reduced.
  • the audience tag vector and the service object tag vector are respectively weighted according to the audience weight value and the business object weight value, and then the activation rate of the business object is determined based on the weighted processed viewer tag vector and the business object tag vector. It is beneficial to improve the calculation accuracy of the activation rate of the business object, thereby facilitating the more accurate activation rate of the business object.
  • the activation rate of the business object is regularized to obtain an optimal activation rate, which is advantageous for reducing the error of the activation rate of the computing business object.
  • sequence number of each step does not mean the order of execution sequence, and the execution order of each step should be determined by its function and internal logic, instead of The implementation process of the specific embodiments of the embodiments of the present application is not limited.
  • FIG. 3 it is a structural block diagram of a service object recommendation apparatus according to an embodiment of the present application; and may include the following modules: an acquisition module 32, configured to acquire audience attribute information and service object attribute information; Determining whether to display the business object according to the audience attribute information and the business object attribute information; the displaying module 36 is configured to display the business object when determining to display the business object.
  • an acquisition module 32 configured to acquire audience attribute information and service object attribute information
  • the displaying module 36 is configured to display the business object when determining to display the business object.
  • the business object recommendation device of the present embodiment determines whether to display the business object according to the audience attribute information and the business object attribute information by acquiring the audience attribute information and the business object attribute information, and displays the business object when determining to display the business object.
  • the audience attribute information Through the audience attribute information, a business object matching the audience can be determined from the business object library, the business object is more in line with the viewing interest of the viewer, and different business objects can be pushed to different audiences, thereby facilitating the push service. The accuracy and flexibility of the object.
  • FIG. 4 it is a structural block diagram of a service object recommendation apparatus according to another embodiment of the present application, which may include the following modules: an acquisition module 42 for acquiring audience attribute information and service object attribute information; and a determining module 44, The method is configured to determine whether to display a business object according to the audience attribute information and the business object attribute information; and the displaying module 46 is configured to display the business object when determining to display the business object.
  • the determining module 44 includes: a viewer tag vector generating sub-module 441, configured to generate a viewer tag vector according to the viewer attribute information, and a service object tag vector generating sub-module 442, configured to generate a service object tag according to the business object attribute information. a rate-determining sub-module 443, configured to determine an activation rate of the service object based on the audience tag vector and the service object tag vector, and the service object determining sub-module 444, configured to determine when the activation rate of the service object is greater than a set threshold Show business objects.
  • the viewer tag vector generation sub-module 441 is configured to generate a tag value corresponding to each viewer attribute according to the viewer attribute information, and generate a viewer tag vector based on the tag value corresponding to each viewer attribute.
  • the service object tag vector generation sub-module 442 is configured to generate a tag value corresponding to each service object attribute according to the service object attribute information, and generate a service object tag vector based on the tag value corresponding to each service object attribute.
  • the activation rate determining sub-module 443 is configured to determine, by using a logical regression basis model, an activation rate of the business object based on the audience tag vector and the business object tag vector.
  • the activation rate determining sub-module 443 is configured to obtain a viewer weight value and a service object weight value, and perform weighting processing on the audience label vector and the service object label vector respectively based on the audience weight value and the service object weight value, respectively, based on the weighting processing.
  • the audience tag vector and the business object tag vector determine the activation rate of the business object.
  • the business object recommendation device further includes: a regularization processing module 48, configured to perform regularization processing on the activation rate of the business object, to obtain an optimal activation rate of the business object.
  • a regularization processing module 48 configured to perform regularization processing on the activation rate of the business object, to obtain an optimal activation rate of the business object.
  • the display module 46 includes: a sorting sub-module 461, configured to sort a plurality of business objects according to an activation rate of the plurality of business objects when determining that the displayed business objects are multiple; displaying the sub-module 462, The business objects are displayed in order, in order.
  • the audience attribute information includes at least one of the following: a basic attribute of the viewer, a physical feature, a purchase type, a short-term attribute, a behavior feature, a psychological feature, a live video type, a real-time status feature, and a video business attribute.
  • the audience attribute information further includes: the anchor attribute information has been paid attention to, and the focused anchor attribute information includes at least one of the following: the talent type of the anchor that has been paid attention to, the gender ratio of the fan group that has paid attention to the anchor, and the age ratio.
  • the business object attribute information includes at least one of the following: a domain to which the business object belongs, a brand to which it belongs, an effect attribute, a trigger information, a viewer attribute, and an anchor attribute.
  • the business object includes: an effect containing the advertisement information.
  • the embodiment of the present application further provides an electronic device, such as a mobile terminal, a personal computer (PC), a tablet computer, a server, and the like.
  • an electronic device such as a mobile terminal, a personal computer (PC), a tablet computer, a server, and the like.
  • FIG. 5 there is shown a schematic structural diagram of an electronic device 500 suitable for implementing the business object recommendation device of the embodiment of the present application.
  • the electronic device 500 includes one or more processors and communication components.
  • the one or more processors are, for example: one or more central processing units (CPUs) 501, and/or one or more image processing units (GPUs) 513, etc., the processors may be stored in a read only memory ( Various suitable actions and processes are performed by executable instructions in ROM) 502 or executable instructions loaded into random access memory (RAM) 503 from storage portion 508.
  • the communication element includes a communication portion 512 and/or a communication portion (such as a communication interface) 509.
  • the communication part 512 may include, but is not limited to, a network card, which may include, but is not limited to, an IB (Infiniband) network card, the communication part 509 includes a communication interface of a network interface card such as a LAN card, a modem, etc., and the communication part port 509 is via The network of the Internet performs communication processing.
  • a network card which may include, but is not limited to, an IB (Infiniband) network card
  • the communication part 509 includes a communication interface of a network interface card such as a LAN card, a modem, etc.
  • the communication part port 509 is via The network of the Internet performs communication processing.
  • the processor can communicate with the read only memory 502 and/or the random access memory 503 to execute executable instructions, connect to the communication portion 512 via the communication bus 504, and communicate with other target devices via the communication component 512, thereby completing the embodiments of the present application.
  • Providing any operation corresponding to the business object recommendation method for example, acquiring audience attribute information and business object attribute information; determining whether to display the business object according to the audience attribute information and the business object attribute information; The business object is presented when the business object is.
  • RAM 503 various programs and data required for the operation of the device can be stored.
  • the CPU 501 or GPU 513, the ROM 502, and the RAM 503 are connected to each other through a communication bus 504.
  • ROM 502 is an optional module.
  • the RAM 503 stores executable instructions, or writes executable instructions to the ROM 502 at runtime, the executable instructions causing the processor to perform operations corresponding to the above-described communication methods.
  • An input/output (I/O) interface 505 is also coupled to communication bus 504.
  • the communication unit 512 may be integrated or may be provided with a plurality of sub-modules (e.g., a plurality of IB network cards) and on the communication bus link.
  • the following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a storage portion 508 including a hard disk or the like. And a communication interface 509 including a network interface card such as a LAN card, a modem, or the like.
  • Driver 510 is also coupled to I/O interface 505 as needed.
  • a removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 510 as needed so that a computer program read therefrom is installed into the storage portion 508 as needed.
  • FIG. 5 is only an optional implementation manner.
  • the number and type of components in FIG. 5 may be selected, deleted, added, or replaced according to actual needs; Different function component settings may also be implemented in separate settings or integrated settings.
  • the GPU 513 and the CPU 501 may be separately configured or the GPU 513 may be integrated on the CPU 501, and the communication components may be separately configured or integrated on the CPU 501 or the GPU 513. and many more. These alternative embodiments are all within the scope of the present application.
  • the process described above with reference to the flowchart may be implemented as a computer readable storage medium having stored thereon a computer program that, when executed by the processor, implements the steps of the business object recommendation method in the foregoing embodiment.
  • embodiments of the present application include a computer program product comprising a computer program tangibly embodied on a machine readable medium, the computer program comprising program code for executing the method illustrated in the flowchart, the program code comprising the corresponding execution
  • the instructions corresponding to the method steps provided by the embodiment of the present application for example, acquiring audience attribute information and business object attribute information; determining, according to the audience attribute information and the business object attribute information, whether to display the business object;
  • the business object is presented when the business object is described.
  • the computer program can be downloaded and installed from the network via a communication component, and/or installed from the removable media 511.
  • the above-described functions defined in the method of the embodiments of the present application are executed when the computer program is executed by the processor.
  • the methods, apparatus, and apparatus of the present application may be implemented in a number of ways.
  • the method, apparatus, and apparatus of the embodiments of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.
  • the above-described sequence of steps for the method is for illustrative purposes only, and the steps of the method of the embodiments of the present application are not limited to the order specifically described above unless otherwise specifically stated.
  • the present application may also be embodied as a program recorded in a recording medium, the programs including machine readable instructions for implementing a method in accordance with embodiments of the present application.
  • the present application also covers a recording medium storing a program for executing the method according to an embodiment of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本申请实施例提供了一种业务对象推荐方法、装置、电子设备和存储介质，其中，所述方法包括：获取观众属性信息及业务对象属性信息；根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；当确定展示所述业务对象时，展示所述业务对象。通过观众属性信息，可以从业务对象库中确定出与该观众匹配的业务对象，该业务对象更符合该观众的观看兴趣，并且可以给不同的观众推送不同的业务对象，从而提高推送业务对象的准确性及灵活性。

Description

业务对象推荐方法、装置、电子设备和存储介质
本申请要求在2017年5月22日提交中国专利局、申请号为201710364917.3、申请名称为“业务对象推荐方法、装置、电子设备和存储介质”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。
技术领域
本申请实施例涉及数据处理技术领域，尤其涉及一种业务对象推荐方法、装置、电子设备和存储介质。
背景技术
目前互联网中，用户的属性数据在广告领域起到越来越大的作用，用户的属性数据可以指引广告的投入。
现有的用户属性数据的分析方案中，主要是通过用户的历史行为数据，如浏览器cookie对用户进行标签化处理，进而通过标签，实现对用户的归类，得到用户的属性数据。
发明内容
本申请实施例提供一种业务对象推荐方法、装置、电子设备和存储介质。
根据本申请实施例的第一方面，提供了一种业务对象推荐方法，包括：获取观众属性信息及业务对象属性信息；根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；当确定展示所述业务对象时，展示所述业务对象。
可选地，所述根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象，包括：根据所述观众属性信息，生成观众标签向量；根据所述业务对象属性信息，生成业务对象标签向量；基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率；当所述业务对象的启用率大于设定阈值时，确定展示所述业务对象。
可选地，所述根据所述观众属性信息，生成观众标签向量，包括：根据所述观众属性信息，生成各观众属性对应的标签值；基于所述各观众属性对应的标签值，生成观众标签向量。
可选地，所述根据所述业务对象属性信息，生成业务对象标签向量，包括：根据所述业务对象属性信息，生成各业务对象属性对应的标签值；基于所述各业务对象属性对 应的标签值，生成业务对象标签向量。
可选地，所述基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率，包括：通过逻辑回归基础模型，基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率。
可选地，所述通过逻辑回归基础模型，基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率，包括：根据
Figure PCTCN2018087813-appb-000001
确定所述业务对象的启用率；其中，p为所述业务对象的启用率，u表示所述观众标签向量，a表示所述业务对象标签向量，x(a,u)表示所述观众标签向量和所述业务对象标签向量组合后的特征向量，ω为所述观众属性信息和所述业务对象属性信息的加权系数，
Figure PCTCN2018087813-appb-000002
为线性函数，
Figure PCTCN2018087813-appb-000003
的输出经过S型Sigmoid函数σ(z)＝(1+e -z) -1映射到(0,1)区间内，(2h-1)为变换到集合{-1,1}上的点击变量。
可选地，所述基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率，包括：获取观众权重值及业务对象权重值；基于所述观众权重值及所述业务对象权重值，分别对所述观众标签向量及所述业务对象标签向量进行加权处理；基于加权处理后的观众标签向量及业务对象标签向量，确定业务对象的启用率。
可选地，所述方法还包括；对所述业务对象的启用率进行正则化处理，获得所述业务对象的最优启用率。
可选地，所述当确定展示所述业务对象时，展示所述业务对象，包括：当确定展示的业务对象为多个时，按照所述多个业务对象的启用率，对所述多个业务对象进行排序；按照顺序，依次展示所述业务对象。
可选地，所述观众属性信息包括以下至少一个：观众的基本属性、体貌特征、购买类型、短期属性、行为特征、心理特征、关注视频直播类型、实时状态特征和视频商业属性。
可选地，所述观众属性信息还包括：已关注主播属性信息，所述已关注主播属性信息包括以下至少一个：已关注主播的才艺类型、已关注主播的粉丝群体的性别比例和年龄比例。
可选地，所述业务对象属性信息包括以下至少一个：业务对象的所属领域、所属品牌、效果属性、触发信息、观众属性和主播属性。
可选地，所述业务对象包括：包含有广告信息的特效。
根据本申请实施例的第二方面，还提供了一种业务对象推荐装置，包括：获取模块，用于获取观众属性信息及业务对象属性信息；确定模块，用于根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；展示模块，用于当确定展示所述业务对象时，展示所述业务对象。
可选地，所述确定模块，包括：观众标签向量生成子模块，用于根据所述观众属性信息，生成观众标签向量；业务对象标签向量生成子模块，用于根据所述业务对象属性信息，生成业务对象标签向量；启用率确定子模块，用于基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率；业务对象确定子模块，用于当所述业务对象的启用率大于设定阈值时，确定展示所述业务对象。
可选地，所述观众标签向量生成子模块，用于根据所述观众属性信息，生成各观众属性对应的标签值，基于所述各观众属性对应的标签值，生成观众标签向量。
可选地，所述业务对象标签向量生成子模块，用于根据所述业务对象属性信息，生成各业务对象属性对应的标签值，基于所述各业务对象属性对应的标签值，生成业务对象标签向量。
可选地，所述启用率确定子模块，用于通过逻辑回归基础模型，基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率。
可选地，所述启用率确定子模块，用于根据
Figure PCTCN2018087813-appb-000004
确定所述业务对象的启用率；其中，p为所述业务对象的启用率，u表示所述观众标签向量，a表示所述业务对象标签向量，x(a,u)表示所述观众标签向量和所述业务对象标签向量组合后的特征向量，ω为所述观众属性信息和所述业务对象属性信息的加权系数，
Figure PCTCN2018087813-appb-000005
为线性函数，
Figure PCTCN2018087813-appb-000006
的输出经过S型Sigmoid函数σ(z)＝(1+e -z) -1映射到(0,1)区间内，(2h-1)为变换到集合{-1,1}上的点击变量。
可选地，所述启用率确定子模块，用于获取观众权重值及业务对象权重值，基于所述观众权重值及所述业务对象权重值，分别对所述观众标签向量及所述业务对象标签向量进行加权处理，基于加权处理后的观众标签向量及业务对象标签向量，确定业务对象的启用率。
可选地，所述装置还包括：正则化处理模块，用于对所述业务对象的启用率进行正则化处理，获得所述业务对象的最优启用率。
可选地，所述展示模块，包括：排序子模块，用于当确定展示的业务对象为多个时， 按照所述多个业务对象的启用率，对所述多个业务对象进行排序；展示子模块，用于按照顺序，依次展示所述业务对象。
可选地，所述观众属性信息包括以下至少一个：观众的基本属性、体貌特征、购买类型、短期属性、行为特征、心理特征、关注视频直播类型、实时状态特征和视频商业属性。
可选地，所述观众属性信息还包括：已关注主播属性信息，所述已关注主播属性信息包括以下至少一个：已关注主播的才艺类型、已关注主播的粉丝群体的性别比例和年龄比例。
可选地，所述业务对象属性信息包括以下至少一个：业务对象的所属领域、所属品牌、效果属性、触发信息、观众属性和主播属性。
可选地，所述业务对象包括：包含有广告信息的特效。
根据本申请实施例的第三方面，还提供了一种电子设备，包括：处理器、存储器、通信元件和通信总线，所述处理器、所述存储器和所述通信元件通过所述通信总线完成相互间的通信；所述存储器用于存放至少一可执行指令，所述可执行指令使所述处理器执行如第一方面所述的业务对象推荐方法对应的操作。
根据本申请实施例的第四方面，还提供了一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现如第一方面所述的业务对象推荐方法的步骤。
本申请的实施例提供的技术方案可以包括以下有益效果：
本申请实施例的业务对象推荐方法，通过获取观众属性信息及业务对象属性信息，根据观众属性信息和业务对象属性信息确定是否展示业务对象，当确定展示业务对象时，展示业务对象。通过观众属性信息，可以从业务对象库中确定出与该观众匹配的业务对象，该业务对象更符合该观众的观看兴趣，并且可以给不同的观众推送不同的业务对象，从而提高推送业务对象的准确性及灵活性。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本申请。
附图说明
构成说明书的一部分的附图描述了本申请的实施例，并且连同描述一起用于解释本申请的原理。参照附图，根据下面的详细描述，可以更加清楚地理解本申请，其中：
图1是本申请一实施例提供的一种业务对象推荐方法的步骤流程图；
图2是本申请又一实施例提供的一种业务对象推荐方法的步骤流程图；
图3是本申请一实施例提供的一种业务对象推荐装置的结构框图；
图4是本申请又一实施例提供的一种业务对象推荐装置的结构框图；
图5是本申请一实施例提供的一种电子设备的结构示意图。
具体实施例
下面结合附图(若干附图中相同的标号表示相同的元素)和实施例，对本申请实施例的具体实施方式作进一步详细说明。以下实施例用于说明本申请实施例，但不用来限制本申请实施例的范围。
本领域技术人员可以理解，本申请实施例中的“第一”、“第二”等术语仅用于区别不同步骤、设备或模块等，既不代表任何特定技术含义，也不表示它们之间的必然逻辑顺序。
参照图1，示出了本申请一实施例提供的一种业务对象推荐方法的步骤流程图。
本实施例是以直播场景下的后台服务器为例，对本申请实施例的业务对象推荐方法进行解释说明，需要说明的是，本实施例的业务对象推荐方法不仅可以应用于直播场景，还可以应用在其他场景，例如应用在视频点播场景下，可以在视频点播之前、视频点播过程中等时间节点，执行本实施例的业务对象推荐方法，本实施例对业务对象推荐方法的具体应用场景不做限制。在直播场景下，本申请实施例提供的方法不仅适用于后台服务器，同样也适用于客户端，本申请实施例不做限制。
本实施例的业务对象推荐方法具体可以包括如下步骤：
步骤102、获取观众属性信息及业务对象属性信息。
本申请实施例应用于直播场景下，第一终端(如主播端)通过后台服务器与视频主播所在直播平台直播间的第二终端(粉丝端即观众端)建立视频通信连接。在本实施例的后台服务器、第一终端和第二终端，都设置有业务对象库，并且可以通过网络实现业务对象的同步和更新，其中，业务对象库中存储多类业务对象。
后台服务器获取当前观众属性信息，如通过获取观众摄像头的权限，并通过摄像头采集主播的图像数据，再通过图像数据得到观众属性信息，又如通过调查问卷的形式获取观众属性信息。
获取业务对象库中每个业务对象属性信息，如通过条件筛选的方式确定业务对象属性信息；再根据业务对象属性信息的分类，确定业务对象属性对应的业务对象标签信息， 在本实施例中标签信息可以以表项的形式生成。
根据获取到的观众属性信息建立主播的标签信息，如根据属性信息的分类建立主播的标签信息，在本实施例中标签信息可以以表项的形式生成。
步骤104、根据观众属性信息及业务对象属性信息，确定是否展示业务对象。
在本实施例中为确定适合观众属性的业务对象，达到精准推荐的目的，将观众属性信息和业务对象属性信息进行结合，进而确定是否存在适合的业务对象，如将观众属性信息和业务对象属性信息作为参量，确定业务对象库中是否存在与上述两个参量匹配的业务对象。
步骤106、当确定展示业务对象时，展示业务对象。
当后台服务器确定展示业务对象时，可以对待展示的一个或者多个业务对象进行一系列相关处理，并将处理后的待展示业务对象在第二终端上展示。
一种可选的实施方式中，例如在直播场景下，主播端在接收到后台服务器推送的待展示的业务对象后，可以在主播端的直播界面以列表的形式显示多个待展示的业务对象，以使得可以在主播端基于该列表，选择部分业务对象或者全部业务对象推送给直播间内各观众端，还可以在主播端对各业务对象进行排序后推送给直播间内各观众端，从而实现在各观众端上展示主播端推送的各业务对象。
本实施例的业务对象推荐方法，通过获取观众属性信息及业务对象属性信息，根据观众属性信息和业务对象属性信息确定是否展示业务对象，当确定展示业务对象时，展示业务对象。通过观众属性信息，可以从业务对象库中确定出与该观众匹配的业务对象，该业务对象更符合该观众的观看兴趣，并且可以给不同的观众推送不同的业务对象，从而提高推送业务对象的准确性及灵活性。
在上述实施例的基础之上，本实施例重点强调与上述实施例的不同之处，相同之处可以参照上述实施例中的相关说明，在此不再赘述。
参照图2，示出了本申请又一实施例提供的一种业务对象推荐方法的步骤流程图，具体可以包括如下步骤：
步骤202、获取观众属性信息及业务对象属性信息。
步骤204、根据观众属性信息及业务对象属性信息，确定是否展示业务对象。
可选地，本步骤204可以包括如下子步骤：
子步骤2041、根据观众属性信息，生成观众标签向量，根据业务对象属性信息，生成业务对象标签向量。
本子步骤2041中，生成观众标签向量时，可以根据观众属性信息，生成各观众属性对应的标签值；基于各观众属性对应的标签值，生成观众标签向量。
一种可选的实施方式中，主播在进行直播前或直播过程中，后台服务器获取当前主播的观众属性信息。其中，观众属性信息包括以下至少一个：观众的基本属性、体貌特征、购买类型、短期属性、行为特征、心理特征、关注视频直播类型、实时状态特征和视频商业属性；观众属性信息还包括：已关注主播属性信息，已关注主播属性信息包括以下至少一个：已关注主播的粉丝群体的性别比例和年龄比例、已关注主播的才艺类型。根据观众属性信息，生成各观众属性对应的标签值，各观众属性对应的标签值可参见表1。
Figure PCTCN2018087813-appb-000007
表1
在本实施例中，为使生成观众标签向量的处理工作量较小，可以对各观众属性对应的标签值进行二值化处理，即观众属性对应的标签值中“是”用“1”表示，“否”用“0”来表示，观众标签向量用u(n)表示，可参见表2。
Figure PCTCN2018087813-appb-000008
Figure PCTCN2018087813-appb-000009
表2
本子步骤2041中，生成业务对象标签向量时，可以根据业务对象属性信息，生成各业务对象属性对应的标签值；基于各业务对象属性对应的标签值，生成业务对象标签向量。
一种可选的实施方式中，在本实施例的后台服务器、第一终端和第二终端，都设置有业务对象库，并且可以通过网络实现业务对象的同步和更新，其中，业务对象包括包含有广告信息的特效，如包含广告信息的以下至少一种形式的特效：二维贴纸特效、三 维特效、粒子特效。如使用贴纸形式展示的广告(即广告贴纸)；或者，用于展示广告的特效，如3D广告特效。但不限于此，其它形式的业务对象也同样适用本申请实施例提供的业务对象推荐方法，如APP或其它应用的文字说明或介绍，或者一定形式的与观众交互的对象(如电子宠物)等。
业务对象属性信息包括以下至少一个：业务对象的所属领域、所属品牌、效果属性、触发信息、观众属性和主播属性，根据业务对象属性信息，生成各业务对象属性对应的标签值，业务对象属性对应的标签值可参见表3。
Figure PCTCN2018087813-appb-000010
表3
在本实施例中，为使生成业务对象标签向量的处理工作量较小，可以对各业务对象属性对应的标签值进行二值化处理，即业务对象属性对应的标签值中“是”用“1”表示，“否”用“0”来表示，业务对象标签向量用a(n)表示，可参见表4。
Figure PCTCN2018087813-appb-000011
Figure PCTCN2018087813-appb-000012
表4
子步骤2042、基于观众标签向量和业务对象标签向量，确定业务对象的启用率。
本子步骤2042中，可以通过逻辑回归基础模型，基于观众标签向量及业务对象标签向量，确定业务对象的启用率。
一种可选的实施方式中，采用x(a,u)表示u(n)和a(n)组合后的特征向量，进而使用逻辑回归基础模型来确定业务对象的启用率，可采用如下公式：
Figure PCTCN2018087813-appb-000013
其中，p为业务对象的启用率，u表示观众标签向量，a表示业务对象标签向量，x(a,u)表示观众标签向量和业务对象标签向量组合后的特征向量，ω为观众属性信息和业务对象属性信息的加权系数，也是此逻辑回归基础模型需要优化的参数；
Figure PCTCN2018087813-appb-000014
这一线性函数的输出经过S型Sigmoid函数σ(z)＝(1+e -z) -1映射到(0,1)区间内，(2h-1)是为了将{0,1,2,3,……,N}的点击变量变换到集合{-1,1}上，点击变量h属于集合{0,1}，则(2h-1)属于集合{-1,1}，其中，h等于0表示未点击；h等于1表示点击，将集合{0,1}转换为集合{-1,1}，目的在于更好地使用线性函数
Figure PCTCN2018087813-appb-000015
进而准确地确定业务对象的启用率。
本实施例中，为使启用率的计算更加精准，可以获取观众权重值和业务对象权重值；基于观众权重值及业务对象权重值，分别对观众标签向量及业务对象标签向量进行加权处理；基于加权处理后的观众标签向量及业务对象标签向量确定业务对象的启用率。如，ω为各属性信息(包括观众属性信息和业务对象属性信息)的加权系数，u(n)的加权系数为0.5，a(n)的加权系数为0.5。
本实施例中，在计算业务对象的启用率时，为减少误差，可以对业务对象的启用率进行正则化处理，获得业务对象的最优启用率，可采用如下公式计算：
Figure PCTCN2018087813-appb-000016
其中，C为常数，可以表示容忍率，T表示业务对象的数量。
子步骤2043、当业务对象的启用率大于设定阈值时，确定展示业务对象。
本实施例中，设定阈值为a，例如a为0.6，当业务对象的启用率大于设定阈值a时，确定启用率大于0.6的业务对象为待展示的业务对象，设定阈值a可以根据整体业务对象的启用率的平均值进行设定，本实施例对此不作具体限定。
步骤206、当确定展示业务对象时，展示业务对象。
本实施例中，展示的业务对象可以为一个或者多个，当确定展示的业务对象为多个时，可以按照多个业务对象的启用率对多个业务对象进行排序，例如，按照多个业务对象的启用率从高到低对多个业务对象进行排序，进而按照排序依次展示多个业务对象。
此外，在本实施例中，为防止展示的业务对象的数量过多，还可以设定展示的业务对象的数量上限，如设定展示的业务对象的数量不超过20个。
需要说明的是，本实施例中对多个业务对象进行排序的步骤可以先在后台服务器中完成，然后将排序完成的待展示的业务对象向第一终端推送；还可以将确定的待展示的业务对象先推送给第一终端，然后由主播通过第一终端完成排序，对此，本实施例不作具体限定。
本实施例的业务对象推荐方法，通过获取观众属性信息及业务对象属性信息，根据观众属性信息生成观众标签向量，根据业务对象属性信息生成业务对象标签向量，基于观众标签向量和业务对象标签向量确定业务对象的启用率，将业务对象的启用率大于设定阈值的业务对象确定为待展示的业务对象，若存在多个待展示的业务对象，则根据业务对象的启用率对多个待展示的业务对象进行排序，按照排序展示业务对象。通过观众属性信息，可以从业务对象库中确定出与该观众匹配的业务对象，该业务对象更符合该观众的观看兴趣，并且可以给不同的观众推送不同的业务对象，从而有利于提高推送业务对象的准确性及灵活性。
本实施例中，对观众属性对应的标签值和业务对象属性对应的标签值进行二值化处理，减少了生成观众标签向量和业务对象标签向量的工作量。
本实施例中，根据观众权重值和业务对象权重值分别对观众标签向量和业务对象标签向量进行加权处理，再基于加权处理后的观众标签向量及业务对象标签向量确定业务对象的启用率，有利于提高业务对象的启用率的计算精度，从而有利于使得业务对象的启用率更加准确。
本实施例中，对业务对象的启用率进行正则化处理，获得最优启用率，有利于减少计算业务对象的启用率的误差。
本领域技术人员可以理解，在本申请实施例具体实施方式的上述方法中，各步骤的 序号大小并不意味着执行顺序的先后，各步骤的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例具体实施方式的实施过程构成任何限定。
参照图3，示出了本申请一实施例提供的一种业务对象推荐装置的结构框图；可以包括如下模块：获取模块32，用于获取观众属性信息及业务对象属性信息；确定模块34，用于根据观众属性信息及业务对象属性信息，确定是否展示业务对象；展示模块36，用于当确定展示业务对象时，展示业务对象。
本实施例的业务对象推荐装置，通过获取观众属性信息及业务对象属性信息，根据观众属性信息和业务对象属性信息确定是否展示业务对象，当确定展示业务对象时，展示业务对象。通过观众属性信息，可以从业务对象库中确定出与该观众匹配的业务对象，该业务对象更符合该观众的观看兴趣，并且可以给不同的观众推送不同的业务对象，从而有利于提高推送业务对象的准确性及灵活性。
参照图4，示出了本申请又一实施例提供的一种业务对象推荐装置的结构框图，可以包括如下模块：获取模块42，用于获取观众属性信息及业务对象属性信息；确定模块44，用于根据观众属性信息及业务对象属性信息，确定是否展示业务对象；展示模块46，用于当确定展示业务对象时，展示业务对象。
可选地，确定模块44包括：观众标签向量生成子模块441，用于根据观众属性信息，生成观众标签向量；业务对象标签向量生成子模块442，用于根据业务对象属性信息，生成业务对象标签向量；启用率确定子模块443，用于基于观众标签向量及业务对象标签向量，确定业务对象的启用率；业务对象确定子模块444，用于当业务对象的启用率大于设定阈值时，确定展示业务对象。
可选地，观众标签向量生成子模块441，用于根据观众属性信息，生成各观众属性对应的标签值，基于各观众属性对应的标签值，生成观众标签向量。
可选地，业务对象标签向量生成子模块442，用于根据业务对象属性信息，生成各业务对象属性对应的标签值，基于各业务对象属性对应的标签值，生成业务对象标签向量。
可选地，启用率确定子模块443，用于通过逻辑回归基础模型，基于观众标签向量及业务对象标签向量，确定业务对象的启用率。
可选地，启用率确定子模块443，用于根据
Figure PCTCN2018087813-appb-000017
确定业务对象的启用率；其中，p为业务对象的启用率，u表示观众标签向量，a表示业务对象 标签向量，x(a,u)表示观众标签向量和业务对象标签向量组合后的特征向量，ω为观众属性信息和业务对象属性信息的加权系数，
Figure PCTCN2018087813-appb-000018
为线性函数，
Figure PCTCN2018087813-appb-000019
的输出经过S型Sigmoid函数σ(z)＝(1+e -z) -1映射到(0,1)区间内，(2h-1)为变换到集合{-1,1}上的点击变量。
可选地，启用率确定子模块443，用于获取观众权重值及业务对象权重值，基于观众权重值及业务对象权重值，分别对观众标签向量及业务对象标签向量进行加权处理，基于加权处理后的观众标签向量及业务对象标签向量，确定业务对象的启用率。
可选地，业务对象推荐装置还包括；正则化处理模块48，用于对业务对象的启用率进行正则化处理，获得业务对象的最优启用率。
可选地，展示模块46包括：排序子模块461，用于当确定展示的业务对象为多个时，按照多个业务对象的启用率，对多个业务对象进行排序；展示子模块462，用于按照顺序，依次展示业务对象。
可选地，观众属性信息包括以下至少一个：观众的基本属性、体貌特征、购买类型、短期属性、行为特征、心理特征、关注视频直播类型、实时状态特征和视频商业属性。
可选地，观众属性信息还包括：已关注主播属性信息，已关注主播属性信息包括以下至少一个：已关注主播的才艺类型、已关注主播的粉丝群体的性别比例和年龄比例。
可选地，业务对象属性信息包括以下至少一个：业务对象的所属领域、所属品牌、效果属性、触发信息、观众属性和主播属性。
可选地，业务对象包括：包含有广告信息的特效。
本申请实施例还提供了一种电子设备，例如可以是移动终端、个人计算机(PC)、平板电脑、服务器等。下面参考图5，其示出了适于用来实现本申请实施例的业务对象推荐装置的电子设备500的结构示意图：如图5所示，电子设备500包括一个或多个处理器、通信元件等，所述一个或多个处理器例如：一个或多个中央处理单元(CPU)501，和/或一个或多个图像处理器(GPU)513等，处理器可以根据存储在只读存储器(ROM)502中的可执行指令或者从存储部分508加载到随机访问存储器(RAM)503中的可执行指令而执行各种适当的动作和处理。通信元件包括通信部512和/或通信部分(如通信接口)509。其中，通信部512可包括但不限于网卡，所述网卡可包括但不限于IB(Infiniband)网卡，通信部分509包括诸如LAN卡、调制解调器等的网络接口卡的通信接口，通信部分口509经由诸如因特网的网络执行通信处理。
处理器可与只读存储器502和/或随机访问存储器503中通信以执行可执行指令，通 过通信总线504与通信部512相连、并经通信部件512与其他目标设备通信，从而完成本申请实施例提供的任一项业务对象推荐方法对应的操作，例如，获取观众属性信息及业务对象属性信息；根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；当确定展示所述业务对象时，展示所述业务对象。
此外，在RAM503中，还可存储有装置操作所需的各种程序和数据。CPU501或GPU513、ROM502以及RAM503通过通信总线504彼此相连。在有RAM503的情况下，ROM502为可选模块。RAM503存储可执行指令，或在运行时向ROM502中写入可执行指令，可执行指令使处理器执行上述通信方法对应的操作。输入/输出(I/O)接口505也连接至通信总线504。通信部512可以集成设置，也可以设置为具有多个子模块(例如多个IB网卡)，并在通信总线链接上。
以下部件连接至I/O接口505：包括键盘、鼠标等的输入部分506；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分507；包括硬盘等的存储部分508；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信接口509。驱动器510也根据需要连接至I/O接口505。可拆卸介质511，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器510上，以便于从其上读出的计算机程序根据需要被安装入存储部分508。
需要说明的，如图5所示的架构仅为一种可选实现方式，在具体实践过程中，可根据实际需要对上述图5的部件数量和类型进行选择、删减、增加或替换；在不同功能部件设置上，也可采用分离设置或集成设置等实现方式，例如GPU513和CPU501可分离设置或者可将GPU513集成在CPU501上，通信元件可分离设置，也可集成设置在CPU501或GPU513上，等等。这些可替换的实施方式均落入本申请的保护范围。
根据本申请实施例，上文参考流程图描述的过程可以被实现为计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现前述实施例中业务对象推荐方法的步骤。例如，本申请实施例包括一种计算机程序产品，其包括有形地包含在机器可读介质上的计算机程序，计算机程序包含用于执行流程图所示的方法的程序代码，程序代码可包括对应执行本申请实施例提供的方法步骤对应的指令，例如，获取观众属性信息及业务对象属性信息；根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；当确定展示所述业务对象时，展示所述业务对象。在这样的实施例中，该计算机程序可以通过通信元件从网络上被下载和安装，和/或从可拆卸介质511被安装。在该计算机程序被处理器执行时，执行本申请实施例的方法中限定的上述功能。
可能以许多方式来实现本申请的方法和装置、设备。例如，可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本申请实施例的方法和装置、设备。用于方法的步骤的上述顺序仅是为了进行说明，本申请实施例的方法的步骤不限于以上具体描述的顺序，除非以其它方式特别说明。此外，在一些实施例中，还可将本申请实施为记录在记录介质中的程序，这些程序包括用于实现根据本申请实施例的方法的机器可读指令。因而，本申请还覆盖存储用于执行根据本申请实施例的方法的程序的记录介质。
本申请实施例的描述是为了示例和描述起见而给出的，而并不是无遗漏的或者将本申请限于所公开的形式，很多修改和变化对于本领域的普通技术人员而言是显然的。选择和描述实施例是为了更好说明本申请的原理和实际应用，并且使本领域的普通技术人员能够理解本申请从而设计适于特定用途的带有各种修改的各种实施例。

Claims (27)

  1. 一种业务对象推荐方法，其特征在于，包括：
    获取观众属性信息及业务对象属性信息；
    根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；
    当确定展示所述业务对象时，展示所述业务对象。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象，包括：
    根据所述观众属性信息，生成观众标签向量；
    根据所述业务对象属性信息，生成业务对象标签向量；
    基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率；
    当所述业务对象的启用率大于设定阈值时，确定展示所述业务对象。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述观众属性信息，生成观众标签向量，包括：
    根据所述观众属性信息，生成各观众属性对应的标签值；
    基于所述各观众属性对应的标签值，生成观众标签向量。
  4. 根据权利要求2-3任一项所述的方法，其特征在于，所述根据所述业务对象属性信息，生成业务对象标签向量，包括：
    根据所述业务对象属性信息，生成各业务对象属性对应的标签值；
    基于所述各业务对象属性对应的标签值，生成业务对象标签向量。
  5. 根据权利要求2-4任一项所述的方法，其特征在于，所述基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率，包括：
    通过逻辑回归基础模型，基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率。
  6. 根据权利要求2-5任一项所述的方法，其特征在于，所述基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率，包括：
    获取观众权重值及业务对象权重值；
    基于所述观众权重值及所述业务对象权重值，分别对所述观众标签向量及所述业务对象标签向量进行加权处理；
    基于加权处理后的观众标签向量及业务对象标签向量，确定业务对象的启用率。
  7. 根据权利要求6所述的方法，其特征在于，所述方法还包括；
    对所述业务对象的启用率进行正则化处理，获得所述业务对象的最优启用率。
  8. 根据权利要求2-7任一项所述的方法，其特征在于，所述当确定展示所述业务对象时，展示所述业务对象，包括：
    当确定展示的业务对象为多个时，按照所述多个业务对象的启用率，对所述多个业务对象进行排序；
    按照顺序，依次展示所述业务对象。
  9. 根据权利要求1-8任一项所述的方法，其特征在于，所述观众属性信息包括以下至少一个：观众的基本属性、体貌特征、购买类型、短期属性、行为特征、心理特征、关注视频直播类型、实时状态特征和视频商业属性。
  10. 根据权利要求9所述的方法，其特征在于，所述观众属性信息还包括：已关注主播属性信息，所述已关注主播属性信息包括以下至少一个：已关注主播的才艺类型、已关注主播的粉丝群体的性别比例和年龄比例。
  11. 根据权利要求1-10任一项所述的方法，其特征在于，所述业务对象属性信息包括以下至少一个：业务对象的所属领域、所属品牌、效果属性、触发信息、观众属性和主播属性。
  12. 根据权利要求1-11任一项所述的方法，其特征在于，所述业务对象包括：包含有广告信息的特效。
  13. 一种业务对象推荐装置，其特征在于，包括：
    获取模块，用于获取观众属性信息及业务对象属性信息；
    确定模块，用于根据所述观众属性信息及所述业务对象属性信息，确定是否展示所述业务对象；
    展示模块，用于当确定展示所述业务对象时，展示所述业务对象。
  14. 根据权利要求13所述的装置，其特征在于，所述确定模块，包括：
    观众标签向量生成子模块，用于根据所述观众属性信息，生成观众标签向量；
    业务对象标签向量生成子模块，用于根据所述业务对象属性信息，生成业务对象标签向量；
    启用率确定子模块，用于基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率；
    业务对象确定子模块，用于当所述业务对象的启用率大于设定阈值时，确定展示所述业务对象。
  15. 根据权利要求14所述的装置，其特征在于，所述观众标签向量生成子模块，用于根据所述观众属性信息，生成各观众属性对应的标签值，基于所述各观众属性对应的标签值，生成观众标签向量。
  16. 根据权利要求14-15任一项所述的装置，其特征在于，所述业务对象标签向量生成子模块，用于根据所述业务对象属性信息，生成各业务对象属性对应的标签值，基于所述各业务对象属性对应的标签值，生成业务对象标签向量。
  17. 根据权利要求14-16任一项所述的装置，其特征在于，所述启用率确定子模块，用于通过逻辑回归基础模型，基于所述观众标签向量及所述业务对象标签向量，确定所述业务对象的启用率。
  18. 根据权利要求14-17任一项所述的装置，其特征在于，所述启用率确定子模块，用于获取观众权重值及业务对象权重值，基于所述观众权重值及所述业务对象权重值，分别对所述观众标签向量及所述业务对象标签向量进行加权处理，基于加权处理后的观众标签向量及业务对象标签向量，确定业务对象的启用率。
  19. 根据权利要求18所述的装置，其特征在于，所述装置还包括；
    正则化处理模块，用于对所述业务对象的启用率进行正则化处理，获得所述业务对象的最优启用率。
  20. 根据权利要求14-19任一项所述的装置，其特征在于，所述展示模块，包括：
    排序子模块，用于当确定展示的业务对象为多个时，按照所述多个业务对象的启用率，对所述多个业务对象进行排序；
    展示子模块，用于按照顺序，依次展示所述业务对象。
  21. 根据权利要求13-21任一项所述的装置，其特征在于，所述观众属性信息包括以下至少一个：观众的基本属性、体貌特征、购买类型、短期属性、行为特征、心理特征、关注视频直播类型、实时状态特征和视频商业属性。
  22. 根据权利要求21所述的装置，其特征在于，所述观众属性信息还包括：已关注主播属性信息，所述已关注主播属性信息包括以下至少一个：已关注主播的才艺类型、已关注主播的粉丝群体的性别比例和年龄比例。
  23. 根据权利要求13-22任一项所述的装置，其特征在于，所述业务对象属性信息包括以下至少一个：业务对象的所属领域、所属品牌、效果属性、触发信息、观众属性和主播属性。
  24. 根据权利要求13-23任一项所述的装置，其特征在于，所述业务对象包括：包 含有广告信息的特效。
  25. 一种电子设备，其特征在于，包括：处理器、存储器、通信元件和通信总线，所述处理器、所述存储器和所述通信元件通过所述通信总线完成相互间的通信；
    所述存储器用于存放至少一可执行指令，所述可执行指令使所述处理器执行如权利要求1-12任一项所述的业务对象推荐方法对应的操作。
  26. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现权利要求1-12任一项所述的业务对象推荐方法的步骤。
  27. 一种计算机程序，包括计算机指令，当所述计算机指令在设备的处理器中运行时，所述处理器执行用于实现权利要求1-12中任一所述业务对象推荐方法对应的操作。
PCT/CN2018/087813 2017-05-22 2018-05-22 业务对象推荐方法、装置、电子设备和存储介质 Ceased WO2018214869A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
SG11201909846Q SG11201909846QA (en) 2017-05-22 2018-05-22 Method and apparatus for recommending business object, electronic device, and storage medium
JP2020505964A JP2020517038A (ja) 2017-05-22 2018-05-22 ビジネスオブジェクト推薦方法、装置、電子機器および記憶媒体
US16/314,402 US20190155864A1 (en) 2017-05-22 2018-05-22 Method and apparatus for recommending business object, electronic device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710364917.3A CN108090107A (zh) 2017-05-22 2017-05-22 业务对象推荐方法、装置、电子设备和存储介质
CN201710364917.3 2017-05-22

Publications (1)

Publication Number Publication Date
WO2018214869A1 true WO2018214869A1 (zh) 2018-11-29

Family

ID=62170368

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/087813 Ceased WO2018214869A1 (zh) 2017-05-22 2018-05-22 业务对象推荐方法、装置、电子设备和存储介质

Country Status (5)

Country Link
US (1) US20190155864A1 (zh)
JP (1) JP2020517038A (zh)
CN (1) CN108090107A (zh)
SG (1) SG11201909846QA (zh)
WO (1) WO2018214869A1 (zh)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783686A (zh) * 2019-01-21 2019-05-21 广州虎牙信息科技有限公司 行为数据处理方法、装置、终端设备和存储介质
CN110267065B (zh) * 2019-05-29 2021-10-22 深圳市元征科技股份有限公司 直播数据处理方法、装置、服务器及存储介质
CN110769270B (zh) * 2019-11-08 2021-10-26 网易（杭州）网络有限公司 直播互动的方法及装置、电子设备、存储介质
CN111866541B (zh) * 2020-08-06 2022-07-29 广州繁星互娱信息科技有限公司 直播推荐方法、装置、服务器及存储介质
CN112532692B (zh) * 2020-11-09 2024-07-16 北京沃东天骏信息技术有限公司 一种信息推送方法及装置、存储介质
CN112887743B (zh) * 2021-01-19 2023-04-07 北京映客芝士网络科技有限公司 直播平台的信息推送方法、装置、电子设备和存储介质
CN115079878B (zh) 2021-03-15 2024-04-16 北京字节跳动网络技术有限公司 对象展示方法、装置、电子设备和存储介质
CN116758322A (zh) * 2022-03-03 2023-09-15 清华大学 一种数据处理方法、装置、计算机设备及存储介质
CN115795123B (zh) * 2022-10-12 2026-03-13 北京奇艺世纪科技有限公司 确定对象之间相似度的方法、装置、电子设备及存储介质
JP7316598B1 (ja) * 2023-04-24 2023-07-28 １７Ｌｉｖｅ株式会社 サーバ

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1976287A (zh) * 2005-11-30 2007-06-06 阿尔卡特公司 基于ip的电视的个人化节目制作和广告
CN101554048A (zh) * 2006-10-17 2009-10-07 谷歌公司 定向的视频广告
CN103760968A (zh) * 2013-11-29 2014-04-30 理光软件研究所（北京）有限公司 数字标牌显示内容选择方法和装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1156424A2 (en) * 2000-05-17 2001-11-21 Matsushita Electric Industrial Co., Ltd. Information recommendation apparatus and information recommendation system
US8352499B2 (en) * 2003-06-02 2013-01-08 Google Inc. Serving advertisements using user request information and user information
JP2010015441A (ja) * 2008-07-04 2010-01-21 Sony Corp 情報処理装置、コンテンツ情報の検索方法、及び情報処理システム
JP4924565B2 (ja) * 2008-08-01 2012-04-25 沖電気工業株式会社 情報処理システム、及び視聴効果測定方法
US20130085858A1 (en) * 2011-10-04 2013-04-04 Richard Bill Sim Targeting advertisements based on user interactions
JP6226791B2 (ja) * 2014-03-24 2017-11-08 Kddi株式会社 レコメンド装置、レコメンドシステム及びレコメンド方法
JP6226846B2 (ja) * 2014-09-19 2017-11-08 ヤフー株式会社 情報分析装置、情報分析方法および情報分析プログラム
CN105469263A (zh) * 2014-09-24 2016-04-06 阿里巴巴集团控股有限公司 一种商品推荐方法及装置
US10776816B2 (en) * 2015-01-30 2020-09-15 Walmart Apollo, Llc System and method for building a targeted audience for an online advertising campaign
JP2016218578A (ja) * 2015-05-15 2016-12-22 日本電信電話株式会社 画像検索装置、画像検索システム、画像検索方法、及び画像検索プログラム
CN106296257A (zh) * 2015-06-11 2017-01-04 苏宁云商集团股份有限公司 一种基于用户行为分析的固定广告位投放方法及系统
WO2017019643A1 (en) * 2015-07-24 2017-02-02 Videoamp, Inc. Targeting tv advertising slots based on consumer online behavior

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1976287A (zh) * 2005-11-30 2007-06-06 阿尔卡特公司 基于ip的电视的个人化节目制作和广告
CN101554048A (zh) * 2006-10-17 2009-10-07 谷歌公司 定向的视频广告
CN103760968A (zh) * 2013-11-29 2014-04-30 理光软件研究所（北京）有限公司 数字标牌显示内容选择方法和装置

Also Published As

Publication number Publication date
CN108090107A (zh) 2018-05-29
US20190155864A1 (en) 2019-05-23
SG11201909846QA (en) 2019-11-28
JP2020517038A (ja) 2020-06-11

Similar Documents

Publication Publication Date Title
US10776970B2 (en) Method and apparatus for processing video image and computer readable medium
CN112055225B (zh) 直播视频截取、商品信息生成、对象信息生成方法及装置
US10943257B2 (en) Digital media environment for analysis of components of digital content
CN105631702B (zh) 内容创建、部署合作以及随后的销售活动
US20190155864A1 (en) Method and apparatus for recommending business object, electronic device, and storage medium
US10524005B2 (en) Facilitating television based interaction with social networking tools
WO2017186106A1 (zh) 获取用户画像的方法及装置
HK1219332A1 (zh) 识别视频图像中的商品和展示其信息的方法、装置及系统
WO2018033137A1 (zh) 在视频图像中展示业务对象的方法、装置和电子设备
WO2020233432A1 (zh) 一种信息推荐方法及装置
JP2019527395A (ja) コンテンツを効果的に配信するための動的クリエイティブの最適化
WO2018121541A1 (zh) 用户属性提取方法、装置和电子设备
TW201310986A (zh) 虛擬廣告平台
CN108073672A (zh) 业务对象推荐方法、装置和电子设备
CN114080818A (zh) 生成视频
US9818044B2 (en) Content update suggestions
CN108076387A (zh) 业务对象推送方法及装置、电子设备
CN111241385B (zh) 信息处理方法、装置以及计算机系统和介质
WO2025195319A1 (zh) 用于界面交互的方法、装置、设备和存储介质
WO2024104286A1 (zh) 一种视频处理方法、装置、电子设备和存储介质
US8719100B1 (en) Interactive delivery of information through images
US10311497B2 (en) Server, analysis method and computer program product for analyzing recognition information and combination information
CN112308648A (zh) 信息处理方法及装置
CN108074127B (zh) 业务对象的数据分析方法、装置和电子设备
CN119011662B (zh) 对象推送及同款簇的识别方法、介质、设备和程序产品

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: 18805522

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020505964

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 18/03//2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18805522

Country of ref document: EP

Kind code of ref document: A1