WO2019169963A1 - 一种内容推荐方法、装置、电子设备及系统 - Google Patents

一种内容推荐方法、装置、电子设备及系统 Download PDF

Info

Publication number
WO2019169963A1
WO2019169963A1 PCT/CN2019/072761 CN2019072761W WO2019169963A1 WO 2019169963 A1 WO2019169963 A1 WO 2019169963A1 CN 2019072761 W CN2019072761 W CN 2019072761W WO 2019169963 A1 WO2019169963 A1 WO 2019169963A1
Authority
WO
WIPO (PCT)
Prior art keywords
content
type
recommendation
external operation
operation system
Prior art date
Application number
PCT/CN2019/072761
Other languages
English (en)
French (fr)
Inventor
周志超
熊军
周峰
蒋建
黄国进
郑岩
冯健
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Priority to US16/959,643 priority Critical patent/US20210082026A1/en
Publication of WO2019169963A1 publication Critical patent/WO2019169963A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • 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
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions

Definitions

  • the embodiments of the present disclosure relate to the field of network technologies, and in particular, to a content recommendation method, apparatus, electronic device, and system.
  • the recommendation work is mainly performed by the operation platform.
  • the operation platform sets its own internal operation configuration, and on the other hand, it also receives the external operation configuration determined by the merchant; the operation platform integrates the internal operation configuration and the external operation configuration into operational configuration information, and is assigned to the internal operation system for content matching and internal operation.
  • the system sends the matched content to the recommendation system; when the user accesses, the recommendation system recommends the content to the user according to the label determined by the user account or the like from the recommendation system.
  • the external operation configuration of the merchant decision needs to be processed by the operation platform, and the content is matched by the internal operation system, which leads to limitations of the external operation of the merchant.
  • the embodiment of the present specification provides a content recommendation method, device, electronic device and system for solving the problem that the external operation of the merchant in the prior art has limitations.
  • a content recommendation method including:
  • the recommendation system searches for content matching the tag from the content database according to the determined tag;
  • the recommendation system recommends the found content to the user corresponding to the label
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • a content recommendation apparatus including:
  • a finding module searching for content matching the tag from the content database according to the determined tag
  • a recommendation module recommending the found content to a user corresponding to the label
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • a content recommendation apparatus including:
  • the matching module matches the second type of content according to the external operation configuration information uploaded by the merchant;
  • the second type of content is used to determine content in the content database of the recommendation system for the first type of content matched with the internal operation system.
  • a content recommendation system including:
  • a recommendation system searching for content matching the tag from the content database according to the determined tag; and recommending the found content to the user corresponding to the tag;
  • the external operating system matches the second type of content
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:
  • the second type of content is used to determine content in the content database of the recommendation system for the first type of content matched with the internal operation system.
  • a computer readable storage medium storing one or more programs, the one or more programs, when executed by a server including a plurality of applications, causes the The server does the following:
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • a computer readable storage medium storing one or more programs, the one or more programs when executed by a server including a plurality of applications causes the The server does the following:
  • the second type of content is used to determine content in the content database of the recommendation system for the first type of content matched with the internal operation system.
  • the recommendation system searches for content matching the determined tag from the content database, and recommends the content to the corresponding user, and the content is matched according to the first type of content matched by the internal operation system and the external operation system.
  • the second type of content is determined, so that in the content recommendation system, the external operation system and the internal operation system can be configured at the same time to ensure parallel processing of the external operation and the internal operation, and the competition mechanism can improve the conversion rate.
  • the external operation system and the internal operation system can share the recommendation system to ensure the integrity of the content in the recommendation system and the association with external operations and internal operations. Thereby, the operation and maintenance efficiency and resource utilization rate of the content recommendation system are improved as a whole.
  • FIG. 1 is a schematic diagram of a system architecture of a content recommendation scheme according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of steps of a content recommendation method according to an embodiment of the present disclosure
  • FIG. 3 is a second schematic diagram of steps of a content recommendation method according to an embodiment of the present disclosure.
  • FIG. 3b is a third schematic diagram of steps of a content recommendation method according to an embodiment of the present disclosure.
  • FIG. 4a is a schematic diagram of a specific implementation of step 222 of the content recommendation method provided by the embodiment of the present disclosure
  • FIG. 4b is a second schematic diagram of the specific implementation of the step 222 of the content recommendation method provided by the embodiment of the present disclosure.
  • FIG. 5 is a fourth schematic diagram of steps of a content recommendation method according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of a content recommendation apparatus according to an embodiment of the present disclosure.
  • FIG. 7b is a second schematic structural diagram of a content recommendation apparatus according to an embodiment of the present disclosure.
  • the application scenario of the content recommendation scheme is: a system architecture formed by the operation platform and the merchant, which mainly includes: the recommendation system 102, internal operation System 104 and external operations system 106.
  • the external operations system 106 can perform operational content matching, content uploading to the recommendation system 102 in parallel with the internal operations system 104. In this way, the external operation and the internal operation are independent of each other in operation management, but the recommendation system 102 can be shared.
  • the recommendation system 102 can be a server on the operating platform side for implementing content summary to be recommended and finding recommendations. At the same time, at least one content database for storing the content received by the recommendation system 102 is provided in the recommendation system 102.
  • the internal operation system 104 is also a server on the operation platform side, and is configured to match the first type of content according to the operation configuration information set by the management personnel of the operation platform.
  • the internal operation system 104 may specifically include: a content management module 1041, an activity operation module 1042, an application verification management module 1043, a distribution management module 1044, and a human operation management module 1045.
  • other modules that assist the operation platform to perform management operations may be included. . among them:
  • the content management module 1041 is mainly used for managing content related to products that the merchant may promote, for example, product details, product specifications, model displays, and the like. At the same time, you can also manage the type of goods, such as clothing, shoes, bags, underwear accessories and so on.
  • the internal operation system can match the required recommended content from the content management module 1041 according to the received operational configuration information.
  • the activity operation module 1042 is mainly used to manage preferential activities that the operation platform may promote, such as coupons, discount coupons, coupons or other points activities.
  • the write-off management module 1043 is mainly used for the write-off management of the promotion activities promoted by the activity operation module 1042.
  • the traffic distribution management module 1044 is mainly used for traffic distribution management of content. For example, if there are many accesses to the apparel content, then more traffic is allocated for the apparel content.
  • the human process management module 1045 is mainly used for recommendation management of the first type of content matched by the internal operation system and the second type of content matched by the external operation system, for example, management has multiple content recommendation strategies.
  • the external operations system 106 can be a server on the merchant side for matching the second type of content according to the operational configuration information set by the one or more merchants.
  • the external operation system 106 may specifically include: a content management module 1061, an activity operation module 1062, and an application verification management module 1063.
  • the external operation system 13 may further include other modules that assist the merchant and the operation platform to perform management work.
  • each module such as the content management module 1061, the activity operation module 1062, the verification management module 1063, and the like included in the external operation system 106 may be similar to the functions of the corresponding modules included in the internal operation system 104.
  • the content management module 1041 and the content management module 1061 are both for managing product content, such as: product details of the A product, and specification parameters of the B product, and the like.
  • the external operations system is configured with one or more data interfaces that can be used to receive external configuration information uploaded by external merchants.
  • These data interfaces may or may not be distinguished according to the merchant identifier, and this specification does not limit this.
  • FIG. 2 it is a schematic diagram of steps of a content recommendation method provided by an embodiment of the present disclosure.
  • the execution body of the content recommendation method includes at least a recommendation system.
  • the method mainly includes:
  • Step 202 The recommendation system searches for content matching the tag from the content database according to the determined tag.
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • the determined label is determined according to the user identifier analysis when the user logs in or accesses the website operated by the operating platform.
  • the user identifier may include a user account, a mobile phone number, and the like; the specific format of the user identifier may be a string of any combination of numbers, letters, underscores, and the like.
  • the determined label may be one or more, and the embodiment of the present specification does not limit this.
  • the label may be a keyword related to the product recommendation, for example, the user's gender, identity, occupation, location, etc., for example, a label may be: one of women, students, Hong Kong or a combination.
  • the content database stores one or more corresponding relationships, and each of the one or more corresponding relationships is a correspondence between the content and the label; specifically, one content corresponds to one label, or may be one
  • the content corresponds to a plurality of tags, or a plurality of content corresponds to one tag, or a plurality of content corresponds to a plurality of tags.
  • the content in the content database is not only matched by the internal operation system, but the first type of content matched by the internal operation system and the second type of content matched by the external operation system. Determined together. Therefore, the content in the content database is associated with both the internal operating system and the external operating system.
  • the content in the content database may be product information, coupon information, discount event information, and the like.
  • Step 204 The recommendation system recommends the found content to the user corresponding to the label.
  • the recommendation system after the recommendation system finds the content that matches the label, the recommendation system recommends the content to the user corresponding to the label to implement content promotion for the product or the information related to the product.
  • the recommendation system searches for content matching the determined tag from the content database, and recommends the content to the corresponding user, and the content is matched according to the first type of content matched by the internal operation system and the external operation system.
  • the second type of content is determined, so that in the content recommendation system, the external operation system and the internal operation system can be configured at the same time to ensure parallel processing of the external operation and the internal operation, and the competition mechanism can improve the conversion rate.
  • the external operation system and the internal operation system can share the recommendation system to ensure the integrity of the content in the recommendation system and the association with external operations and internal operations. Thereby, the operation and maintenance efficiency and resource utilization rate of the content recommendation system are improved as a whole.
  • the content database in the recommendation system may be preset, as shown in FIG. 3a. Specifically, before step 202, the following operations may be performed in advance:
  • Step 206 The external operation system matches the second type of content according to the external operation configuration information uploaded by the merchant, and sends the content to the recommendation system.
  • the external operating system is a newly added system that is developed for use by merchants by developing corresponding service interfaces. When implemented, the web page can be rendered. Based on the analysis of historical data such as user historical behavior and transaction records, the merchant determines the external operation configuration information that conforms to its own operation mode. Specifically, it can be analyzed manually or automatically, and this specification does not limit this.
  • the external operation configuration information involved herein may be various types of labels obtained from historical data analysis, for example, women, students, and weather; these labels are related to commodities.
  • the external operation configuration information may be a commodity operation plan based on historical data analysis, for example, for a female college student who has a need for access on a rainy or cloudy day.
  • the external operation system matches the second type of content according to the external operation configuration information uploaded by the merchant, and an implementation scheme: matching the corresponding product content from the content management module according to the label uploaded by the merchant, and matching from the activity operation module The corresponding activity content.
  • the label is: female, student, weather; then, you can match the cartoon pattern or other cute umbrellas, raincoats, rain boots from the promotion content; and, match the promotion or match with such labels.
  • Another achievable solution according to the operation plan uploaded by the merchant, respectively matching the corresponding product content from the content management module, and matching the corresponding activity content from the activity operation module.
  • the commodity operation plan is: for female college students who have access demand on rainy or cloudy days; then, keywords can be extracted from the operation plan: women, students, weather, and the corresponding content is matched from the promotion content according to the label processing method.
  • Step 208 The internal operation system matches the first type of content according to the internal operation configuration information uploaded by the operation platform, and sends the content to the recommendation system.
  • the internal operation system may include all the functions of the external operation system, and in addition, as an internal server of the operation platform, there are functions that are not available in the external operation system.
  • the internal operation system can also match the traffic occupation ratio of various types of content according to the traffic distribution policy in the operation configuration information set by the management personnel in the operation platform, so that the subsequent feedback to the recommendation system can be reasonably recommended, thereby rationally regulating resources.
  • the sequence of the step 206 of uploading the second type of content by the external operation system and the step 208 of uploading the first type of content by the internal operation system may not be limited, that is, the steps shown in FIG. 3a may be followed. Executing sequentially; step 208 may be performed first, and then step 206 is performed; or, step 208 and step 206 are performed simultaneously.
  • the order of execution of steps 206 and 208 indicated herein does not affect the core solution of the parallel processing of the external operating system and the internal operating system in the embodiment of the present specification.
  • a human operation management module is further disposed in the internal operation system, and correspondingly, as shown in FIG. 3b, before step 202, the method further includes:
  • Step 220 The internal operation system matches the content recommendation policy according to the internal operation configuration information uploaded by the operation platform, and sends the content recommendation policy to the recommendation system.
  • the internal operation system can also match the internal recommendation policy and send it to the recommendation system to recommend the system recommendation recommendation method or recommendation order.
  • Step 222 The recommendation system processes the received first type content and the second type content according to the content recommendation policy.
  • the steps 220-222 may be processed in parallel with the steps 206 and 208, or may be prioritized, and the specification does not limit this.
  • the content recommendation policy may include an operation and maintenance personnel of the operation platform or various recommendation policies set by the management personnel, and may specifically include: a fusion sub-policy, a sub-policy, and the like.
  • a fusion sub-policy a sub-policy, and the like.
  • the content recommendation strategy includes: a fusion sub-policy.
  • the fusion sub-policy can be a specific fusion mode, for example, a machine prediction fusion model and a manual setting fusion model; the artificial setting fusion model here can be a fusion model calculated by the relevant personnel of the operation platform according to historical data.
  • step 222 includes:
  • the recommendation system combines the received first type of content and the second type of content according to the fusion sub-policy, and stores the merged content in the content database.
  • the fusion sub-policy is a weight ratio according to the received fusion sub-policy
  • the weight of the first type of content is 0.2
  • the weight of the second type of content is 0.8
  • the content after the fusion is 0.2. * The first category of content +0.8* second class content.
  • weighting ratio fusion sub-strategy is only a simple example, and the actual fusion model can set different complexity levels according to the number of contents and the number of merchants.
  • the content recommendation policy further includes: a sorting sub-policy; then, after completing the merging operation in step 222, the method may further include:
  • the recommendation system sorts the content stored in the content database according to the sorting sub-policy.
  • the content recommendation strategy includes: a sorting sub-policy.
  • the sorting sub-policy may be a specific sorting manner, for example, sorting according to the size of the content, sorting according to the degree of relevance of the content and the label, sorting according to the timeliness of the content, etc.; the embodiment of the present specification does not sort the content of the sub-policy. Limited.
  • step 222 includes:
  • the recommendation system sorts the received first type of content and the second type of content according to a sorting sub-policy. Specifically, the recommendation system, according to the received sorting sub-policy, assumes that the sorting sub-policy is sorted according to the relevance of the content and the label, then the recommendation system can follow all the first-type content and all the second-type content received. The degree of relevance to the label is uniformly sorted.
  • the sorted first type content and the second type content may be recommended to the user in the order, or the fusion operation may be further performed, that is, the recommendation system receives the fusion sub-policy while receiving the sort sub-policy, and completes the sorting. After that, the first type of content and the second type of content can be merged according to the fusion sub-policy. After that, the merged content is recommended.
  • the recommendation system processes the received first type content and the second type content by using the content recommendation policy, the recommendation system recommends the found content to the label correspondingly.
  • the user can be specifically executed as:
  • the recommendation system sequentially searches the found content in the sorting order to the user corresponding to the label.
  • the merchant by setting an external operation system, the merchant is allowed to share the recommendation system directly through the external operation system. Then, when the external operation system matches the second type of content according to the external operation configuration information uploaded by the merchant, the external operation system may be implemented in at least the following two manners.
  • Step 302a The external operation system receives external operation configuration information uploaded by at least one merchant.
  • Step 304a The external operation system performs statistical integration on the external operation configuration information uploaded by the at least one merchant to obtain the business common operation configuration information.
  • the statistical integration method involved can be flexibly designed according to the operation situation, and this specification does not limit this.
  • Step 306a The external operation system matches the second type of content according to the merchant common operation configuration information.
  • Step 302b The external operation system receives the external operation configuration information uploaded by the at least one merchant.
  • Step 304b The external operation system matches the second type of sub-content according to the external operation configuration information uploaded by each of the at least one merchant.
  • Step 306b The external operation system integrates the external operation configuration information uploaded by the at least one merchant to match the second type of sub-content, and obtains the second type of content.
  • the method further includes:
  • Step 224 The recommendation system monitors the user's access status to the recommended content.
  • the recommendation system can monitor the user's access status to the recommended content of the recommendation system, such as browsing time, number of views, whether to purchase recommended products, whether to use recommended coupons, and the like.
  • Step 226 The recommendation system feeds back the access status to the internal operation system and the external operation system.
  • the recommendation system feeds back the access status to the internal operation system and the external operation system, so that the internal operation system can timely adjust the internal operation configuration to meet the user according to the access situation.
  • the external operation system can also adjust the external operation configuration in time to meet the needs of users according to the access situation, thereby improving the content recommendation efficiency.
  • the recommendation system will also feedback the use of coupons and the like to the write-off management module to update the validity of the coupon or to launch a new coupon.
  • the content in the content database of the recommendation system may be periodically updated, and the update scheme is similar to the pre-configuration scheme, and details are not described herein.
  • FIG. 1 is a schematic structural diagram of a content recommendation system according to an embodiment of the present disclosure.
  • the device mainly includes: a recommendation system 102, an internal operation system 104, and an external operation system 106;
  • the recommendation system 102 searches for content matching the tag from the content database according to the determined tag; and recommends the found content to the user corresponding to the tag;
  • the internal operation system 104 matches the first type of content
  • the external operation system 106 matches the second type of content
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • the recommendation system searches for content matching the determined label from the content database, and recommends the content to the corresponding user, and the content is matched according to the first type of content matched by the internal operation system and the external operation system.
  • the second type of content is determined, so that in the content recommendation system, the external operation system and the internal operation system can be simultaneously configured to ensure parallel processing of external operations and internal operations, and the competition mechanism can improve the conversion rate.
  • the external operation system and the internal operation system can share the recommendation system to ensure the integrity of the content in the recommendation system and the association with external operations and internal operations. Thereby, the operation and maintenance efficiency and resource utilization rate of the content recommendation system are improved as a whole.
  • the electronic device includes a processor, optionally including an internal bus, a network interface, and a memory.
  • the memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (Non-Volatile Memory), such as at least one disk memory.
  • RAM high-speed random access memory
  • Non-Volatile Memory non-Volatile Memory
  • the electronic device may also include hardware required for other services.
  • the processor, network interface, and memory can be interconnected by an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an extended industry standard. Extended Industry Standard Architecture (EISA) bus, etc.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one double-headed arrow is shown in Figure 6, but it does not mean that there is only one bus or one type of bus.
  • the program can include program code, the program code including computer operating instructions.
  • the memory can include both memory and non-volatile memory and provides instructions and data to the processor.
  • the processor reads the corresponding computer program from the non-volatile memory into memory and then runs to form a content recommendation device on a logical level.
  • the processor executes the program stored in the memory and is specifically used to perform the method operation performed by the server described above as the execution subject.
  • the method disclosed in the embodiment shown in FIG. 2 to FIG. 5 of the embodiment of the present specification may be applied to a processor or implemented by a processor.
  • the processor may be an integrated circuit chip with signal processing capabilities.
  • each step of the above method may be completed by an integrated logic circuit of hardware in a processor or an instruction in a form of software.
  • the above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or may be a digital signal processor (DSP), dedicated integration.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • other programmable logic device discrete gate or transistor logic device, discrete hardware component.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present specification may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.
  • the electronic device can also perform the functions of the embodiment of FIG. 2 and FIG. 5, and implement the functions of the content recommendation device in the embodiment shown in FIG. 2 to FIG. 5.
  • the embodiments of the present specification are not described herein again.
  • the electronic device in the embodiment of the present specification does not exclude other implementation manners, such as a logic device or a combination of software and hardware, etc., that is, the execution body of the following processing flow is not limited to each logic.
  • the unit can also be hardware or logic.
  • the embodiment of the present specification further provides a computer readable storage medium storing one or more programs, when the one or more programs are executed by a server including a plurality of applications, causing the The server does the following:
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • the embodiment of the present specification further provides a computer readable storage medium storing one or more programs, when the one or more programs are executed by a server including a plurality of applications, causing the The server does the following:
  • the second type of content is used to determine content in the content database of the recommendation system for the first type of content matched with the internal operation system.
  • the computer readable storage medium such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
  • FIG. 7a a schematic structural diagram of a content recommendation apparatus according to an embodiment of the present disclosure, the apparatus mainly includes:
  • the searching module 402a searches for a content matching the tag from the content database according to the determined tag;
  • the recommendation module 404a recommends the found content to the user corresponding to the label
  • the content in the content database is determined according to the first type of content matched by the internal operation system and the second type of content matched by the external operation system.
  • FIG. 6b is a schematic structural diagram of a content recommendation apparatus according to an embodiment of the present disclosure.
  • the apparatus mainly includes:
  • the matching module 402b matches the second type of content according to the external operation configuration information uploaded by the merchant;
  • Sending module 404b sending to the recommendation system
  • the second type of content is used to determine content in the content database of the recommendation system for the first type of content matched with the internal operation system.
  • the recommendation system searches for content matching the determined label from the content database, and recommends the content to the corresponding user, and the content is matched according to the first type of content matched by the internal operation system and the external operation system.
  • the second type of content is determined, so that in the content recommendation system, the external operation system and the internal operation system can be simultaneously configured to ensure parallel processing of external operations and internal operations, and the competition mechanism can improve the conversion rate.
  • the external operation system and the internal operation system can share the recommendation system to ensure the integrity of the content in the recommendation system and the association with external operations and internal operations. Thereby, the operation and maintenance efficiency and resource utilization rate of the content recommendation system are improved as a whole.
  • the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Library & Information Science (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种内容推荐方法、装置、电子设备及系统，包括：推荐系统（102）根据确定的标签，从内容数据库中查找与所述标签匹配的内容，内容数据库中的内容是根据内部运营系统（104）匹配出的第一类内容和外部运营系统（106）匹配出的第二类内容确定的（202）；推荐系统（102）将查找到的所述内容推荐给所述标签对应的用户（204）。

Description

一种内容推荐方法、装置、电子设备及系统
相关申请的交叉引用
本专利申请要求于2018年03月07日提交的、申请号为201810185112.7、发明名称为“一种内容推荐方法、装置、电子设备及系统”的中国专利申请的优先权，该申请的全文以引用的方式并入本文中。
技术领域
本说明书实施例涉及网络技术领域，尤其涉及一种内容推荐方法、装置、电子设备及系统。
背景技术
随着电子商务的快速发展，电子商务中重要信息(例如：商品信息、优惠券信息、折扣信息等)的内容推荐成为运营的关键。
在当前电子商务的运维中，主要由运营平台执行推荐工作。运营平台一方面自己设置内部运营配置，另一方面还接收商家确定的外部运营配置；运营平台将内部运营配置和外部运营配置整合为运营配置信息，并交由内部运营系统进行内容匹配，内部运营系统将匹配出的内容发送给推荐系统；当用户访问时，推荐系统根据由用户账号等确定的标签从推荐系统中匹配合适的内容推荐给用户。
由此，商家决策的外部运营配置需要由运营平台处理，并通过内部运营系统匹配内容，导致商家的外部运营存在局限性。
发明内容
本说明书实施例提供一种内容推荐方法、装置、电子设备及系统，用以解决现有技术中商家的外部运营存在局限性的问题。
为了解决上述技术问题，本说明书实施例采用下述技术方案：
第一方面，提供了一种内容推荐方法，包括：
推荐系统根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
推荐系统将查找到的所述内容推荐给所述标签对应的用户；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
第二方面，提供了一种内容推荐装置，包括：
查找模块，根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
推荐模块，将查找到的所述内容推荐给所述标签对应的用户；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
第三方面，提供了一种内容推荐装置，包括：
匹配模块，根据商家上传的外部运营配置信息匹配出第二类内容；
发送模块，发送给推荐系统；
其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
第四方面，提供了一种内容推荐系统，包括：
推荐系统，根据确定的标签，从内容数据库中查找与所述标签匹配的内容；以及将查找到的所述内容推荐给所述标签对应的用户；
内部运营系统，匹配出第一类内容；
外部运营系统，匹配出第二类内容；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
第五方面，提供了一种电子设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行：
根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
将查找到的所述内容推荐给所述标签对应的用户；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
第六方面，提供了一种电子设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行：
根据商家上传的外部运营配置信息匹配出第二类内容；
将第二类内容发送给推荐系统；
其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
第七方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被包括多个应用程序的服务器执行时，使得所述服务器执行以下操作：
根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
将查找到的所述内容推荐给所述标签对应的用户；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
第八方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被包括多个应用程序的服务器执行时，使得所述服务器执行以下操作：
根据商家上传的外部运营配置信息匹配出第二类内容；
将所述第二类内容发送给推荐系统；
其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
本说明书实施例采用的上述至少一个技术方案能够达到以下有益效果：
通过上述技术方案，由推荐系统从内容数据库中查找与确定的标签相匹配的内容，并推荐给相应用户，而该内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的，从而，使得在内容推荐系统中，可以同时配置外部运营系统和内部运营系统，保证外部运营与内部运营的并行处理，该竞争机制可提升转化率。而且外部运营系统与内部运营系统可以共享推荐系统，保证推荐系统中内容的完整性以及与外部运营、内部运营的关联。由此，从整体上提升内容推荐系统的运维效率以及资源利用率。
附图说明
为了更清楚地说明本说明书实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本说明书实施例中记载的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本说明书实施例提供的内容推荐方案的系统架构示意图；
图2为本说明书实施例提供的内容推荐方法的步骤示意图之一；
图3a为本说明书实施例提供的内容推荐方法的步骤示意图之二；
图3b为本说明书实施例提供的内容推荐方法的步骤示意图之三；
图4a为本说明书实施例提供的内容推荐方法的步骤222的具体执行示意图之一；
图4b为本说明书实施例提供的内容推荐方法的步骤222的具体执行示意图之二；
图5为本说明书实施例提供的内容推荐方法的步骤示意图之四；
图6为本说明书实施例提供的电子设备的结构示意图；
图7a为本说明书实施例提供的内容推荐装置的结构示意图之一；
图7b为本说明书实施例提供的内容推荐装置的结构示意图之二。
具体实施方式
为使本说明书实施例的目的、技术方案和优点更加清楚，下面将结合本说明书具体实施例及相应的附图对本说明书实施例的技术方案进行清楚、完整地描述。显然，所描述的实施例仅是本说明书一部分实施例，而不是全部的实施例。基于本说明书中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本说明书实施例保护的范围。
以下结合附图，详细说明本说明书各实施例提供的技术方案。
实施例一
首先，介绍本说明书实施例中内容推荐方案所适用的系统架构，参照图1所示，该内容推荐方案适用场景为：运营平台与商家所构成的系统架构，主要包括：推荐系统102，内部运营系统104和外部运营系统106。外部运营系统106可以和内部运营系统104并 行执行运营内容匹配、内容上传给推荐系统102的操作。这样，外部运营与内部运营在运营管理上相互独立，但是可以共享推荐系统102。
推荐系统102可以为运营平台侧的服务器，用于实现待推荐的内容汇总以及查找推荐。同时，该推荐系统102内设置有用于存储推荐系统102接收到的内容的至少一个内容数据库。
内部运营系统104同样为运营平台侧的服务器，用于根据运营平台的管理人员设置的运营配置信息匹配出第一类内容。该内部运营系统104可具体包括：内容管理模块1041，活动运营模块1042，核销管理模块1043，分流管理模块1044，人工序管理模块1045；此外，还可以包括其他协助运营平台执行管理工作的模块。其中：
--内容管理模块1041，主要用于管理与商家可能会推广的商品相关的内容，例如，商品详情、商品规格、模特展示等内容。同时，还可以负责管理商品类型，例如，服饰、鞋靴、箱包、内衣配饰等内容。内部运营系统可以根据接收到的运营配置信息从内容管理模块1041中匹配出所需推荐的内容。
--活动运营模块1042，主要用于管理运营平台可能会推广的优惠活动，例如优惠券、打折券、消费券或其他积分活动。
--核销管理模块1043，主要用于对活动运营模块1042推广的优惠活动的核销管理。
--分流管理模块1044，主要用于对内容的流量分配管理，例如，服饰类内容的访问较多，那么，就会为服饰类内容分配较多的访问流量。
--人工序管理模块1045，主要用于对内部运营系统匹配的第一类内容以及外部运营系统匹配的第二类内容的推荐管理，例如，管理有多种内容推荐策略。
外部运营系统106可以为商家侧的服务器，用于根据一个或多个商家设置的运营配置信息匹配出第二类内容。该外部运营系统106可具体包括：内容管理模块1061，活动运营模块1062，核销管理模块1063；此外，该外部运营系统13还可以包括其他协助商家和运营平台执行管理工作的模块。
需要说明的是，外部运营系统106中包括的内容管理模块1061、活动运营模块1062、核销管理模块1063等每个模块的功能可以与内部运营系统104中包括的相应模块的实质功能类似。例如，内容管理模块1041与内容管理模块1061均是用于管理商品内容，比如：A商品的商品详情，B商品的规格参数等与商品相关的类似内容。
应理解，在本说明书实施例中，外部运营系统配置有可以用于接收外部商家上传的外部配置信息的一个或多个数据接口。这些数据接口可以根据商家标识进行区分，也可以不进行区分，本说明书并不对此进行限定。
实施例二
下面即通过实施例二对内容推荐方案进行详细介绍。
参照图2所示，为本说明书实施例提供的内容推荐方法的步骤示意图，该内容推荐方法的执行主体至少包括推荐系统；该方法主要包括：
步骤202：推荐系统根据确定的标签，从内容数据库中查找与所述标签匹配的内容。
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
在本说明书实施例中，所述确定的标签，是在用户登录或访问该运营平台运营的网站时，根据用户标识分析确定的。其中，用户标识可以包括用户账号、手机号等；用户标识具体格式可以为由数字、字母、下划线等任意方式组合的字符串。所述确定的标签，可以为一个或是多个，本说明书实施例并不对此进行限定。而标签具体可以为与商品推荐相关的关键词，例如，可以为用户的性别、身份、职业、地点等，比如，一个标签可以为：女性、学生、香港中之一或是组合。
内容数据库中存储有一个或多个对应关系，这一个或多个对应关系中的每个对应关系，都是内容与标签的对应关系；具体可以是一个内容对应一个标签，或者，也可以是一个内容对应多个标签，或者，多个内容对应一个标签，或者，多个内容对应多个标签。
应理解，在本说明书实施例中，内容数据库中的内容并不是仅由内部运营系统匹配出的，而是由内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容共同确定的。因此，内容数据库中内容既与内部运营系统关联，也与外部运营系统关联。其中，内容数据库中的内容可以为商品信息、优惠券信息、打折活动信息等。
步骤204：推荐系统将查找到的内容推荐给所述标签对应的用户。
在本说明书实施例中，推荐系统在查找到与标签相匹配的内容后，会将该内容推荐给标签对应的用户，以实现对商品或是与商品相关信息的内容推广。
通过上述技术方案，由推荐系统从内容数据库中查找与确定的标签相匹配的内容，并推荐给相应用户，而该内容是根据内部运营系统匹配出的第一类内容和外部运营系统 匹配出的第二类内容确定的，从而，使得在内容推荐系统中，可以同时配置外部运营系统和内部运营系统，保证外部运营与内部运营的并行处理，该竞争机制可提升转化率。而且外部运营系统与内部运营系统可以共享推荐系统，保证推荐系统中内容的完整性以及与外部运营、内部运营的关联。由此，从整体上提升内容推荐系统的运维效率以及资源利用率。
应理解，推荐系统中的内容数据库可以是预先设置的，参照图3a所示，具体可以在步骤202之前，预先执行以下操作：
步骤206：外部运营系统根据商家上传的外部运营配置信息匹配出第二类内容，发送给所述推荐系统。
该外部运营系统是新增加的系统，通过开发相应的服务接口供商家使用。具体实现时，可以服务网页呈现。商家根据自身对用户历史行为、交易记录等历史数据的分析，确定符合自身运营模式的外部运营配置信息。具体可通过人工分析或是自动统计分析，本说明书并不对此进行限定。
应理解，这里所涉及的外部运营配置信息，可以是根据历史数据分析得到的各类标签，例如，女性、学生、天气；这些标签与商品相关。或者，外部运营配置信息可以是根据历史数据分析得到的商品运营方案，例如，针对在雨天或阴天有访问需求的女大学生。
那么，外部运营系统根据商家上传的外部运营配置信息匹配出第二类内容，一种实现方案：根据商家上传的标签，分别从内容管理模块中匹配出相应的商品内容，从活动运营模块中匹配出相应的活动内容。例如，当标签为：女性、学生、天气；那么，可以从推广内容中匹配出卡通图案或其他可爱的雨伞、雨衣、雨靴；以及，从推广活动中匹配出与这类标签相关或是与匹配出的商品内容相关的优惠活动或是优惠券；并作为第二类内容推荐给推荐系统。另一种可实现的方案：根据商家上传的运营方案，分别从内容管理模块中匹配出相应的商品内容，从活动运营模块中匹配出相应的活动内容。当商品运营方案为：针对在雨天或阴天有访问需求的女大学生；那么，可以从运营方案中提取关键词：女性、学生、天气，并按照标签的处理方式从推广内容中匹配出相应的商品内容；以及从推广活动中匹配出相关的优惠活动或是优惠券；并作为第二类内容推荐给推荐系统。
步骤208：内部运营系统根据运营平台上传的内部运营配置信息匹配出第一类内容， 发送给所述推荐系统。
应理解，内部运营系统可以包含外部运营系统所具有的所有功能，此外，作为运营平台的内部服务器，还具备一些外部运营系统不具备的功能。例如，该内部运营系统还可以根据运营平台内管理人员设置的运营配置信息中的分流策略，匹配出各类内容的流量占用比例，以便于后续反馈给推荐系统进行合理推荐，从而合理调控资源。
需要说明的是，本说明书实施例中，外部运营系统上传第二类内容的步骤206与内部运营系统上传第一类内容的步骤208的顺序可以不做限定，即可以按照图3a所示的步骤顺序执行；也可以先执行步骤208，再执行步骤206；或者，步骤208和步骤206同时执行。这里所指出的步骤206和步骤208的执行顺序，并不影响本说明书实施例中外部运营系统和内部运营系统并行处理的核心方案。
此外，在本说明书实施例中，内部运营系统中还设置有人工序管理模块，相应地，参照图3b所示，在步骤202之前，还包括：
步骤220：内部运营系统根据运营平台上传的内部运营配置信息匹配出内容推荐策略，发送给所述推荐系统。
内部运营系统根据内部运营配置信息，还可以匹配出内部推荐策略，并发送给推荐系统，以便于推荐系统决策推荐方式或是推荐顺序。
步骤222：所述推荐系统根据所述内容推荐策略，对接收到的所述第一类内容和所述第二类内容进行处理。
这里，步骤220-步骤222可以与步骤206、步骤208并行处理，或是区分先后顺序，本说明书并不对此进行限定。
应理解，内容推荐策略可以包括运营平台的运维人员或是成为管理人员设置的各种推荐策略，具体可以包括：融合子策略、排序子策略等。下面以这两个子策略为例进行说明。
(1)、内容推荐策略包括：融合子策略。
其中，融合子策略可以为具体的融合方式，例如，机器预测融合模型、人工设置融合模型；这里的人工设置融合模型可以为运营平台的相关人员根据历史数据计算得到的融合模型。
步骤222在具体实现时，包括：
所述推荐系统根据融合子策略，对接收到的所述第一类内容和所述第二类内容进行融合，并将融合后的内容存储在所述内容数据库中。具体地，推荐系统根据接收到的融合子策略，假设该融合子策略为权重配比，第一类内容的权重为0.2，第二类内容的权重为0.8，那么，融合后的内容即为0.2*第一类内容+0.8*第二类内容。
需要说明的是，上述权重配比的融合子策略仅为一个简单的举例，实际的融合模型可根据内容的数量以及商家的数量设置不同的复杂等级。
可选地，在本说明书实施例中，内容推荐策略还包括：排序子策略；那么，在步骤222完成融合操作之后，还可以包括：
所述推荐系统根据所述排序子策略，对存储在所述内容数据库中融合后的内容进行排序。
(2)、内容推荐策略包括：排序子策略。
其中，排序子策略可以为具体的排序方式，例如，根据内容的大小进行排序，根据内容与标签的相关程度进行排序，根据内容的时效进行排序等；本说明书实施例并不对排序子策略的内容进行限定。
步骤222在具体实现时，包括：
所述推荐系统根据排序子策略，对接收到的所述第一类内容和所述第二类内容进行排序。具体地，推荐系统根据接收到的排序子策略，假设该排序子策略是按照内容与标签的相关程度排序，那么，推荐系统可以对接收到的所有第一类内容和所有第二类内容，按照与标签的相关程度，统一进行排序。排序后的第一类内容和第二类内容可以按照该顺序被推荐给用户，或者，可以进一步执行融合操作，即推荐系统在接收到排序子策略的同时还接收到融合子策略，在完成排序后，可对这些第一类内容和第二类内容按照融合子策略进行融合。之后，推荐融合后的内容。
应理解，基于上述方案，当推荐系统采用内容推荐策略对接收到的第一类内容和第二类内容进行处理之后，相应地，推荐系统将查找到的所述内容推荐给所述标签对应的用户时，可具体执行为：
所述推荐系统将查找到的所述内容，按照排序顺序，依次推荐给所述标签对应的用户。
在本说明书实施例中，通过设置外部运营系统，从而赋予了商家能够直接通过 外部运营系统共享推荐系统。那么，该外部运营系统在根据商家上传的外部运营配置信息匹配出第二类内容时，可具体通过至少以下两种方式实现。
参照图4a所示，外部运营系统匹配第二类内容时，具体包括以下步骤：
步骤302a：外部运营系统接收至少一个商家上传的外部运营配置信息。
步骤304a：外部运营系统对所述至少一个商家上传的外部运营配置信息进行统计整合，得到商家共有运营配置信息。
其中，所涉及的统计整合方式，可以按照运营情况灵活设计，本说明书并不对此进行限定。
步骤306a：外部运营系统根据所述商家共有运营配置信息匹配出第二类内容。
参照图4b所示，外部运营系统匹配第二类内容时，具体包括以下步骤：
步骤302b：外部运营系统接收至少一个商家上传的外部运营配置信息。
步骤304b：外部运营系统根据所述至少一个商家中每个商家上传的外部运营配置信息匹配出第二类子内容。
步骤306b：外部运营系统对所述至少一个商家上传的外部运营配置信息匹配出第二类子内容进行整合，得到第二类内容。
应理解，参照图5所示，在推荐系统将查找到的所述内容推荐给所述标签对应的用户之后，还包括：
步骤224：所述推荐系统监测用户对推荐的内容的访问状况。
推荐系统可监测用户对推荐系统推荐的内容的访问状况，例如，浏览时间、浏览次数、是否购买推荐的商品、是否使用推荐的优惠券等。
步骤226：所述推荐系统将所述访问状况反馈给所述内部运营系统和所述外部运营系统。
相应地，为了便于内部运营系统以及外部运营系统能够及时进行资源调配，推荐系统将访问状况反馈给内部运营系统以及外部运营系统，这样，内部运营系统可以根据访问情况及时调整内部运营配置以满足用户的需求，同理，外部运营系统也可以根据访问情况及时调整外部运营配置以满足用户的需求，从而，提升内容推荐效率。
其中，推荐系统还会将优惠券等的使用情况反馈给核销管理模块，以便于对优 惠券的有效性进行更新，或是推出新的优惠券。
应理解，在本说明书实施例中，推荐系统的内容数据库中的内容还可以周期性更新，其更新方案与预配置方案类似，在此不做赘述。
实施例三
参照图1所示，为本说明书实施例提供的内容推荐系统的结构示意图，该装置主要包括：推荐系统102、内部运营系统104以及外部运营系统106；其中，
所述推荐系统102，根据确定的标签，从内容数据库中查找与所述标签匹配的内容；以及将查找到的所述内容推荐给所述标签对应的用户；
所述内部运营系统104，匹配出第一类内容；
所述外部运营系统106，匹配出第二类内容；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
本说明书实施例中，由推荐系统从内容数据库中查找与确定的标签相匹配的内容，并推荐给相应用户，而该内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的，从而，使得在内容推荐系统中，可以同时配置外部运营系统和内部运营系统，保证外部运营与内部运营的并行处理，该竞争机制可提升转化率。而且外部运营系统与内部运营系统可以共享推荐系统，保证推荐系统中内容的完整性以及与外部运营、内部运营的关联。由此，从整体上提升内容推荐系统的运维效率以及资源利用率。
下面参照图6详细介绍本说明书实施例的服务器(其中，服务器可称为电子设备)。请参考图6，在硬件层面，该电子设备包括处理器，可选地还包括内部总线、网络接口、存储器。其中，存储器可能包含内存，例如高速随机存取存储器(Random-Access Memory，RAM)，也可能还包括非易失性存储器(Non-Volatile Memory)，例如至少1个磁盘存储器等。当然，该电子设备还可能包括其他业务所需要的硬件。
处理器、网络接口和存储器可以通过内部总线相互连接，该内部总线可以是工业标准体系结构(Industry Standard Architecture，ISA)总线、外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。所述总线可以分为地址总线、数据总线、控制总 线等。为便于表示，图6中仅用一个双向箭头表示，但并不表示仅有一根总线或一种类型的总线。
存储器，用于存放程序。具体地，程序可以包括程序代码，所述程序代码包括计算机操作指令。存储器可以包括内存和非易失性存储器，并向处理器提供指令和数据。
处理器从非易失性存储器中读取对应的计算机程序到内存中然后运行，在逻辑层面上形成内容推荐装置。处理器，执行存储器所存放的程序，并具体用于执行前文所述服务器作为执行主体时所执行的方法操作。
上述如本说明书实施例图2-图5所示实施例揭示的方法可以应用于处理器中，或者由处理器实现。处理器可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器，包括中央处理器(Central Processing Unit，CPU)、网络处理器(Network Processor，NP)等；还可以是数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field－Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本说明书实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本说明书实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
该电子设备还可执行图2-图5的方法，并实现内容推荐装置在图2-图5所示实施例的功能，本说明书实施例在此不再赘述。
当然，除了软件实现方式之外，本说明书实施例的电子设备并不排除其他实现方式，比如逻辑器件抑或软硬件结合的方式等等，也就是说以下处理流程的执行主体并不限定于各个逻辑单元，也可以是硬件或逻辑器件。
实施例四
本说明书实施例还提供一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被包括多个应用程序的服务器执行时，使得 所述服务器执行以下操作：
根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
将查找到的所述内容推荐给所述标签对应的用户；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
本说明书实施例还提供一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被包括多个应用程序的服务器执行时，使得所述服务器执行以下操作：
根据商家上传的外部运营配置信息匹配出第二类内容；
将所述第二类内容发送给推荐系统；
其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
其中，所述的计算机可读存储介质，如只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等。
实施例五
参照图7a所示，为本说明书实施例提供的内容推荐装置的结构示意图，该装置主要包括：
查找模块402a，根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
推荐模块404a，将查找到的所述内容推荐给所述标签对应的用户；
其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
参照图6b所示，为本说明书实施例提供的内容推荐装置的结构示意图，该装置主要包括：
匹配模块402b，根据商家上传的外部运营配置信息匹配出第二类内容；
发送模块404b，发送给推荐系统；
其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
本说明书实施例中，由推荐系统从内容数据库中查找与确定的标签相匹配的内容，并推荐给相应用户，而该内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的，从而，使得在内容推荐系统中，可以同时配置外部运营系统和内部运营系统，保证外部运营与内部运营的并行处理，该竞争机制可提升转化率。而且外部运营系统与内部运营系统可以共享推荐系统，保证推荐系统中内容的完整性以及与外部运营、内部运营的关联。由此，从整体上提升内容推荐系统的运维效率以及资源利用率。
总之，以上所述仅为本说明书实施例的较佳实施例而已，并非用于限定本说明书实施例的保护范围。凡在本说明书实施例的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本说明书实施例的保护范围之内。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本说明书实施例中的各个实施例均采用递进的方式描述，各个实施例之间相同 相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。

Claims (17)

  1. 一种内容推荐方法，包括：
    推荐系统根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
    推荐系统将查找到的所述内容推荐给所述标签对应的用户；
    其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
  2. 如权利要求1所述的方法，还包括：
    外部运营系统根据商家上传的外部运营配置信息匹配出第二类内容，发送给所述推荐系统；
    内部运营系统根据运营平台上传的内部运营配置信息匹配出第一类内容，发送给所述推荐系统。
  3. 如权利要求2所述的方法，还包括：
    内部运营系统根据运营平台上传的内部运营配置信息匹配出内容推荐策略，发送给所述推荐系统；
    所述推荐系统根据所述内容推荐策略，对接收到的所述第一类内容和所述第二类内容进行处理。
  4. 如权利要求3所述的方法，所述内容推荐策略包括：融合子策略；
    所述推荐系统根据所述内容推荐策略，对接收到的所述第一类内容和所述第二类内容进行处理，包括：
    所述推荐系统根据融合子策略，对接收到的所述第一类内容和所述第二类内容进行融合，并将融合后的内容存储在所述内容数据库中。
  5. 如权利要求3所述的方法，所述内容推荐策略包括：排序子策略；
    所述推荐系统根据所述内容推荐策略，对接收到的所述第一类内容和所述第二类内容进行处理，包括：
    所述推荐系统根据所述排序子策略，对接收到的所述第一类内容和所述第二类内容进行排序。
  6. 如权利要求4所述的方法，所述内容推荐策略包括：排序子策略；
    所述方法还包括：所述推荐系统根据所述排序子策略，对存储在所述内容数据库中融合后的内容进行排序。
  7. 如权利要求6所述的方法，推荐系统将查找到的所述内容推荐给所述标签对应的用户，包括：
    所述推荐系统将查找到的所述内容，按照排序顺序，依次推荐给所述标签对应的用户。
  8. 如权利要求2所述的方法，外部运营系统根据商家上传的外部运营配置信息匹配出第二类内容，包括：
    外部运营系统接收至少一个商家上传的外部运营配置信息；
    外部运营系统对所述至少一个商家上传的外部运营配置信息进行统计整合，得到商家共有运营配置信息；
    外部运营系统根据所述商家共有运营配置信息匹配出第二类内容。
  9. 如权利要求2所述的方法，外部运营系统根据商家上传的外部运营配置信息匹配出第二类内容，包括：
    外部运营系统接收至少一个商家上传的外部运营配置信息；
    外部运营系统根据所述至少一个商家中每个商家上传的外部运营配置信息匹配出第二类子内容；
    外部运营系统对所述至少一个商家上传的外部运营配置信息匹配出第二类子内容进行整合，得到第二类内容。
  10. 如权利要求1所述的方法，在推荐系统将查找到的所述内容推荐给所述标签对应的用户之后，还包括：
    所述推荐系统监测用户对推荐的内容的访问状况；
    所述推荐系统将所述访问状况反馈给所述内部运营系统和所述外部运营系统。
  11. 一种内容推荐装置，包括：
    查找模块，根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
    推荐模块，将查找到的所述内容推荐给所述标签对应的用户；
    其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
  12. 一种内容推荐装置，包括：
    匹配模块，根据商家上传的外部运营配置信息匹配出第二类内容；
    发送模块，将所述第二类内容发送给推荐系统；
    其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
  13. 一种内容推荐系统，包括：
    推荐系统，根据确定的标签，从内容数据库中查找与所述标签匹配的内容；以及将 查找到的所述内容推荐给所述标签对应的用户；
    内部运营系统，匹配出第一类内容；
    外部运营系统，匹配出第二类内容；
    其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
  14. 一种电子设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行：
    根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
    将查找到的所述内容推荐给所述标签对应的用户；
    其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
  15. 一种电子设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行：
    根据商家上传的外部运营配置信息匹配出第二类内容；
    将第二类内容发送给推荐系统；
    其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
  16. 一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被包括多个应用程序的服务器执行时，使得所述服务器执行以下操作：
    根据确定的标签，从内容数据库中查找与所述标签匹配的内容；
    将查找到的所述内容推荐给所述标签对应的用户；
    其中，所述内容数据库中的内容是根据内部运营系统匹配出的第一类内容和外部运营系统匹配出的第二类内容确定的。
  17. 一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被包括多个应用程序的服务器执行时，使得所述服务器执行以下操作：
    根据商家上传的外部运营配置信息匹配出第二类内容；
    将所述第二类内容发送给推荐系统；
    其中，所述第二类内容用于与内部运营系统匹配出的第一类内容确定推荐系统的内容数据库中的内容。
PCT/CN2019/072761 2018-03-07 2019-01-23 一种内容推荐方法、装置、电子设备及系统 WO2019169963A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/959,643 US20210082026A1 (en) 2018-03-07 2019-01-23 Content-recommendation method and apparatus, electronic device, and system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810185112.7A CN108563681B (zh) 2018-03-07 2018-03-07 一种内容推荐方法、装置、电子设备及系统
CN201810185112.7 2018-03-07

Publications (1)

Publication Number Publication Date
WO2019169963A1 true WO2019169963A1 (zh) 2019-09-12

Family

ID=63531436

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/072761 WO2019169963A1 (zh) 2018-03-07 2019-01-23 一种内容推荐方法、装置、电子设备及系统

Country Status (4)

Country Link
US (1) US20210082026A1 (zh)
CN (2) CN112818250B (zh)
TW (1) TW201939395A (zh)
WO (1) WO2019169963A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111858688A (zh) * 2020-07-20 2020-10-30 海尔优家智能科技（北京）有限公司 一种纺织材料以及色卡推荐方法、装置及存储介质
CN112307329A (zh) * 2020-09-30 2021-02-02 北京沃东天骏信息技术有限公司 一种资源推荐方法及装置、设备、存储介质
CN113821728A (zh) * 2021-09-29 2021-12-21 平安银行股份有限公司 内容推荐方法和装置

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818250B (zh) * 2018-03-07 2024-03-08 创新先进技术有限公司 一种内容推荐方法、装置、电子设备及系统
CN109767264A (zh) * 2018-12-20 2019-05-17 深圳壹账通智能科技有限公司 产品数据推送方法、装置、计算机设备和存储介质
CN109493199A (zh) * 2019-01-04 2019-03-19 深圳壹账通智能科技有限公司 产品推荐方法、装置、计算机设备和存储介质
CN113628016A (zh) * 2021-08-27 2021-11-09 重庆世纪禾马科技有限公司 一种商家获客引流方法、系统、计算机设备及存储介质
CN117573945B (zh) * 2024-01-17 2024-05-03 每日互动股份有限公司 一种用户标签的处理方法、装置、设备及介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011098969A1 (en) * 2010-02-11 2011-08-18 Ericsson Television Inc. Ad selection based on promotional coupon redemption
CN106169144A (zh) * 2016-07-12 2016-11-30 乐视控股（北京）有限公司 信息匹配方式确定方法及系统
CN106251168A (zh) * 2016-07-08 2016-12-21 乐视控股（北京）有限公司 信息推送方法及系统
CN107590678A (zh) * 2017-08-07 2018-01-16 北京京东尚科信息技术有限公司 商品推荐方法和系统
CN107767070A (zh) * 2017-11-06 2018-03-06 泰康保险集团股份有限公司 用于信息推广的方法及装置
CN108563681A (zh) * 2018-03-07 2018-09-21 阿里巴巴集团控股有限公司 一种内容推荐方法、装置、电子设备及系统

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8655801B2 (en) * 2005-10-26 2014-02-18 Cortica, Ltd. Computing device, a system and a method for parallel processing of data streams
EP2176730A4 (en) * 2007-08-08 2011-04-20 Baynote Inc METHOD AND APPARATUS FOR CONTENT RECOMMENDATION BASED ON CONTEXT
US20120078937A1 (en) * 2010-09-24 2012-03-29 Rovi Technologies Corporation Media content recommendations based on preferences for different types of media content
US9396492B2 (en) * 2010-10-15 2016-07-19 Opentable, Inc. Computer system and method for analyzing data sets and providing personalized recommendations
US20120209673A1 (en) * 2011-02-14 2012-08-16 Kyung Jin Park System and Method for Merchant's Benefit-focused Electronic Coupon Distribution Business
US20130066972A1 (en) * 2011-09-12 2013-03-14 Cleod9, Inc. Recommendation and Matching Method and Systems
US20150324865A1 (en) * 2012-01-19 2015-11-12 Google Inc. Advertising campaign management
CN102663629A (zh) * 2012-05-03 2012-09-12 黄洪程 一种使用推荐规则的电子商务方法
US11100554B1 (en) * 2014-03-13 2021-08-24 BloomReach Inc. System, method and computer program product for providing thematic landing pages
CN105096151A (zh) * 2014-05-15 2015-11-25 中国移动通信集团公司 信息推荐方法及装置、服务器
JP2016076047A (ja) * 2014-10-04 2016-05-12 ゲヒルン株式会社 商品推薦システム、商品推薦方法、商品推薦システム用プログラム
US10497043B2 (en) * 2015-09-24 2019-12-03 Intel Corporation Online clothing e-commerce systems and methods with machine-learning based sizing recommendation
CN107230098A (zh) * 2016-03-25 2017-10-03 阿里巴巴集团控股有限公司 一种业务对象的分时推荐方法和系统
CN106021562B (zh) * 2016-05-31 2019-05-24 北京京拍档科技有限公司 用于电商平台的基于主题相关的推荐方法
CN106649780B (zh) * 2016-12-28 2020-11-24 北京百度网讯科技有限公司 基于人工智能的信息提供方法及装置
CN106910085B (zh) * 2017-01-06 2020-05-22 哈尔滨学院 一种基于电商平台的产品智能推荐方法及其系统
CN106897369B (zh) * 2017-01-17 2020-10-09 成都视达科信息技术有限公司 一种内容数据推荐方法及系统
CN107146099B (zh) * 2017-04-14 2021-05-25 北京楚科信息技术有限公司 一种营销方法及营销系统
CN107392655B (zh) * 2017-07-03 2020-06-05 携程计算机技术（上海）有限公司 优惠券推送方法、系统、存储介质、电子设备及分流方法
CN107403359A (zh) * 2017-07-20 2017-11-28 义乌洞开网络科技有限公司 一种电商平台商品精准推荐系统及其方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011098969A1 (en) * 2010-02-11 2011-08-18 Ericsson Television Inc. Ad selection based on promotional coupon redemption
CN106251168A (zh) * 2016-07-08 2016-12-21 乐视控股（北京）有限公司 信息推送方法及系统
CN106169144A (zh) * 2016-07-12 2016-11-30 乐视控股（北京）有限公司 信息匹配方式确定方法及系统
CN107590678A (zh) * 2017-08-07 2018-01-16 北京京东尚科信息技术有限公司 商品推荐方法和系统
CN107767070A (zh) * 2017-11-06 2018-03-06 泰康保险集团股份有限公司 用于信息推广的方法及装置
CN108563681A (zh) * 2018-03-07 2018-09-21 阿里巴巴集团控股有限公司 一种内容推荐方法、装置、电子设备及系统

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111858688A (zh) * 2020-07-20 2020-10-30 海尔优家智能科技（北京）有限公司 一种纺织材料以及色卡推荐方法、装置及存储介质
CN111858688B (zh) * 2020-07-20 2024-05-24 海尔优家智能科技（北京）有限公司 一种纺织材料以及色卡推荐方法、装置及存储介质
CN112307329A (zh) * 2020-09-30 2021-02-02 北京沃东天骏信息技术有限公司 一种资源推荐方法及装置、设备、存储介质
CN113821728A (zh) * 2021-09-29 2021-12-21 平安银行股份有限公司 内容推荐方法和装置
CN113821728B (zh) * 2021-09-29 2023-08-25 平安银行股份有限公司 内容推荐方法和装置

Also Published As

Publication number Publication date
US20210082026A1 (en) 2021-03-18
TW201939395A (zh) 2019-10-01
CN112818250B (zh) 2024-03-08
CN108563681B (zh) 2021-02-02
CN112818250A (zh) 2021-05-18
CN108563681A (zh) 2018-09-21

Similar Documents

Publication Publication Date Title
WO2019169963A1 (zh) 一种内容推荐方法、装置、电子设备及系统
US10997258B2 (en) Bot networks
US20190325293A1 (en) Tree enhanced embedding model predictive analysis methods and systems
CN107341173B (zh) 一种信息处理方法及装置
WO2019169978A1 (zh) 资源推荐方法及装置
US20130297382A1 (en) Network transaction platform and processing method thereof
US20230214895A1 (en) Methods and systems for product discovery in user generated content
CN108596695B (zh) 实体推送方法及系统
KR102180267B1 (ko) Ｏ２ｏ 기반 의류산업 내 발주자와 제작자를 연결하는 의류생산 매칭 서비스 제공 시스템
JP2017501480A (ja) ハッシュタグおよびコンテンツ提示
EP2156309A2 (en) A system and device for social shopping on-line
CN112288464A (zh) 商品推荐方法、装置、计算机设备和存储介质
US11455299B1 (en) Providing content in response to user actions
US20190205963A1 (en) Data refining engine for high performance analysis system and method
US20170344643A1 (en) Providing travel or promotion based recommendation associated with social graph
CN112989168B (zh) 一种信息处理方法、装置、设备及介质
CN106445947A (zh) 数据搜索方法和系统
US20230281695A1 (en) Determining and presenting information related to a semantic context of electronic message text or voice data
Zhao et al. Anatomy of a web-scale resale market: a data mining approach
US12111806B2 (en) Method and apparatus for determining associated data linkages
CN112330382A (zh) 物品推荐方法、装置、计算设备和介质
US20230099627A1 (en) Machine learning model for predicting an action
US9754319B2 (en) Source document framework for accounting systems
US10929905B2 (en) Method, system and machine-readable medium for online task exchange
CN110717095B (zh) 服务项目的推送方法及装置

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: 19764088

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: 19764088

Country of ref document: EP

Kind code of ref document: A1