WO2023077944A1 - Method and apparatus for outputting information, device, and storage medium - Google Patents

Method and apparatus for outputting information, device, and storage medium Download PDF

Info

Publication number
WO2023077944A1
WO2023077944A1 PCT/CN2022/117037 CN2022117037W WO2023077944A1 WO 2023077944 A1 WO2023077944 A1 WO 2023077944A1 CN 2022117037 W CN2022117037 W CN 2022117037W WO 2023077944 A1 WO2023077944 A1 WO 2023077944A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
determining
input information
commodity
input
Prior art date
Application number
PCT/CN2022/117037
Other languages
French (fr)
Chinese (zh)
Inventor
刘雅琪
李志平
Original Assignee
北京沃东天骏信息技术有限公司
北京京东世纪贸易有限公司
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 北京沃东天骏信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京沃东天骏信息技术有限公司
Publication of WO2023077944A1 publication Critical patent/WO2023077944A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462Approximate or statistical queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3344Query execution using natural language analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0631Item recommendations

Definitions

  • the present disclosure relates to the field of computer technology, specifically to the field of big data technology, and in particular to a method, device, device, and storage medium for outputting information.
  • the present disclosure provides a method, device, device and storage medium for outputting information.
  • Some embodiments of the present application provide a method for outputting information, including: acquiring user input information; determining the type of the input information; determining associated information of the input information according to the type; determining commodity information matching the associated information; Output product information.
  • Some embodiments of the present application provide an apparatus for outputting information, including: an information acquisition unit configured to acquire user input information; a type determination unit configured to determine the type of input information; an associated information determination unit, It is configured to determine associated information of the input information according to the type; the item information determining unit is configured to determine item information matching the associated information; the information output unit is configured to output item information.
  • Some embodiments of the present application provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by Executed by at least one processor, so that at least one processor can execute the method as described in the first aspect.
  • Some embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to make a computer execute the method as described in the first aspect.
  • Some embodiments of the present application provide a computer program product, including a computer program.
  • the above computer program implements the method as described in the first aspect when executed by a processor.
  • FIG. 1 is an exemplary system architecture diagram to which an embodiment of the present disclosure can be applied;
  • FIG. 2 is a flowchart of one embodiment of a method for outputting information according to the present disclosure
  • FIG. 3 is a flowchart of another embodiment of a method for outputting information according to the present disclosure
  • Fig. 4 is a schematic diagram of an application scenario of a method for outputting information according to the present disclosure
  • Fig. 5 is a schematic structural diagram of an embodiment of an apparatus for outputting information according to the present disclosure
  • FIG. 6 is a block diagram of an electronic device for implementing a method for outputting information of an embodiment of the present disclosure.
  • FIG. 1 shows an exemplary system architecture 100 to which embodiments of the method for outputting information or the apparatus for outputting information of the present disclosure can be applied.
  • a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 .
  • the network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 .
  • Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.
  • terminal devices 101 , 102 , 103 Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like.
  • Various communication client applications such as retrieval applications, can be installed on the terminal devices 101, 102, and 103.
  • the terminal devices 101, 102, and 103 may be hardware or software.
  • the terminal devices 101, 102, and 103 can be various electronic devices, including but not limited to smart phones, tablet computers, e-book readers, vehicle-mounted computers, laptop computers, desktop computers, and the like.
  • the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as a plurality of software or software modules (for example, to provide distributed services), or as a single software or software module. No specific limitation is made here.
  • the server 105 may be a server that provides various services, such as a background server that provides support for information displayed on the terminal devices 101 , 102 , 103 .
  • the background server can obtain matching product information according to the information input by the user through the terminal devices 101 , 102 , 103 , and feed back the product information to the terminal devices 101 , 102 , 103 .
  • the server 105 may be hardware or software.
  • the server 105 can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.
  • the method for outputting information provided by the embodiments of the present disclosure is generally executed by the server 105 . Accordingly, means for outputting information is generally provided in the server 105 .
  • terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.
  • a flow 200 of an embodiment of a method for outputting information according to the present disclosure includes the following steps:
  • Step 201 acquire user input information.
  • the subject of execution of the method for outputting information may acquire the user's input information in various ways.
  • the execution subject may interact with the terminal device used by the user to receive input information from the user.
  • the above input information may include text, pictures and links, and may also include SKU (stock keeping unit, stock keeping unit).
  • the execution subject acquires user input information through an input interface.
  • the execution subject provides and presents an input box to the user, and the information input by the user through the input box is obtained by the execution subject.
  • the input box can receive input of text, pictures, links, SKU and other information.
  • Step 202 determine the type of input information.
  • the execution subject After the execution subject receives the input information, it can analyze the input information and determine the type of the input information.
  • the above types may include but not limited to: text, picture, link, SKU, etc.
  • the execution body analyzes the format of the above-mentioned input information, and if it detects that the input information is a file in a picture format, it can determine that the type of the input information is a picture. If it is detected that the input information includes a web address or a file address, it can be determined that the type of the input information is a link.
  • the execution subject may input the above-mentioned input information into the pre-trained convolutional neural network to identify the type of the input information.
  • Step 203 determine the associated information of the input information.
  • the execution subject may determine the related information of the input information according to the above type. For example, if the type of input information is a picture, the vector or feature map of the picture may be used as the associated information, or the attribute information of the object included in the picture may be used as the associated information. For example, if the object included in the picture is a bag, the execution subject may use the shape of the bag (saddle bag, bucket bag, cloud bag, etc.), the color of the bag, etc. as associated information. If the type of the input information is a link, a title, a keyword, or a picture in a web page corresponding to the link may be used as associated information.
  • Step 204 determining commodity information matching the type association information.
  • the executive body After the executive body determines the related information of the input information, it can further determine the product information that matches the above related information. Specifically, the execution subject can search according to the associated information, and obtain matching commodity information according to the search results. For example, the executive body may use different items in the associated information as search terms to perform commodity search. The product most relevant to each search term is used as the matching product information.
  • the execution subject can search and match in the pre-stored vector set according to the associated information, or use the Elasticsearch search engine to search in the pre-stored Elasticsearch index, so as to obtain the matching product information.
  • Step 204 outputting the above commodity information.
  • the execution subject After the execution subject determines the matching product information, it can output the above product information for the user to view.
  • the execution subject may display pictures of matching commodities on the terminal for users to view.
  • the user may refer to an operator who is used to arrange commodities participating in promotional activities.
  • a user can also be a shopper, retrieving suitable items.
  • the method for outputting information provided by the above-mentioned embodiments of the present disclosure can determine matching commodity information according to user input information, and improve commodity retrieval efficiency.
  • FIG. 3 shows a flow 300 of another embodiment of the method for outputting information according to the present disclosure.
  • the method of this embodiment may include the following steps:
  • Step 301 acquiring user input information.
  • the above input information is not limited to "recognition” (retention), but also supports “filtering” (elimination).
  • the identification attribute is “applicable people/women”, but filter out "applicable age: under 10 years old”. It should be noted that if the input information includes filter information, the execution subject may first filter unsuitable product information, and then sort the rest of the product information.
  • Step 302 determine the type of input information.
  • Step 3031 in response to determining that the type of the input information is a picture, determine a target vector of the picture; and determine related information of the input information according to the target vector.
  • the execution subject may first determine the target vector of the picture. Specifically, the execution subject can determine the target vector of the picture through various feature extraction algorithms. For example, a picture can be fed into the feature extraction network to obtain the target vector of the picture. Then, the execution subject may expand the above vectors, for example, determine similar vectors, and use the target vector and similar vectors as associated information.
  • Step 3041 according to the associated information and the pre-stored vector set, determine a vector similar to the target vector; use the product information corresponding to the determined vector as the matched product information.
  • the execution subject may compare the above-mentioned associated information with each vector in the pre-stored vector set, and determine a vector similar to each vector in the associated information.
  • each vector in the above vector set is in one-to-one correspondence with each main image of commodity information. That is, different vectors in the vector set correspond to different commodity information.
  • the execution subject may use the commodity information corresponding to the determined vector as the commodity information matching the input information.
  • the pre-stored vector set is a pre-generated offline vector set.
  • the execution subject pre-constructs a graph embedding algorithm model, and through this graph embedding algorithm model, the main graph of stock commodities on the e-commerce platform can be embedded into a finite-dimensional vector space, and stored as a vector library (that is, a vector collection ).
  • Step 3032 in response to determining that the type of the input information is text, perform association on the text, and determine association information; in response to receiving filtering information for the association information, determine associated information according to the filtering information.
  • the execution subject may first determine the associated information of the text. Specifically, the execution subject may use synonyms of the above-mentioned words or words with similar shapes as related information. Or, if the text represents a certain category, the executive body can also use a similar category of the category as associated information, or use a lower-level category of the category as associated information. Or, after receiving the text, the execution subject can make associations and determine association information. Specifically, the execution subject may use synonyms and similar words of the text as association information. Alternatively, the execution subject may also determine the text after or before the text according to the historical input information of the user, and use the above text as association information. Or, if the words represent categories or industrial attributes, the executive body can also use the parallel categories of the above categories as association information.
  • the execution subject may output the above association information.
  • the associative related descriptors or related words are presented to the user in a checkable manner.
  • the user can give feedback on the above association information, that is, further input, or check or delete the output association information, and the like.
  • the above association information may be displayed in the form of multiple words, and each word is associated with a check box. If the user clicks a check box, it means that the corresponding word in the association information is selected.
  • the executive body can use the words checked by the user as new input information, and then make further associations based on the new input information until the user enters text or clicks the end button to end the association.
  • the execution subject can determine the final matching commodity information according to the user's feedback information and the above association information.
  • the execution subject can determine the related information through the following steps: segment the text into words, and determine the vector of each word obtained; according to the vector of each word, determine the synonyms of each word as association information .
  • the execution subject may perform word segmentation on the text to obtain at least one word. Then determine the vector for each word. Specifically, the execution subject can use algorithms such as Word2vec to determine the vector of each word. Then, according to the vector of each word, the execution subject can find words with similar semantics to each word as synonyms, and use the above synonyms as association information.
  • the executive body may determine associated information through the following steps: determine the category tree corresponding to the text; and determine the subcategory of the text as association information according to the category tree.
  • the execution subject may also determine the category tree corresponding to the text.
  • the category tree may include multi-level categories, and an upper-level category may correspond to multiple lower-level categories.
  • the executive body can compare the above-mentioned text with the categories at all levels in the category tree, and if the two are the same or similar, it can be determined that the lower-level category of the above-mentioned category is association information.
  • the executive body may determine association information through the following steps: determine associated information of historical input information according to historical input information and historical click information and historical exposure information corresponding to the historical input information.
  • the associated information of the input information is determined according to the associated information of the historical input information of the same type as the input information.
  • the executive body can also obtain historical input information and historical click information and historical exposure information generated by a large number of users for each historical input information, and determine association information accordingly.
  • the historical click information may include the number of clicks on each product information by a large number of users under specific historical input information.
  • the historical exposure information may include the number of times that a large number of users have browsed each product information under specific historical input information.
  • the execution subject may analyze the historical click information of the historical input information, and use the item information with the most clicks in the historical click information as the item information most relevant to the historical input information. Then the execution subject can use the title words, keywords, or industrial attributes in the above-mentioned most relevant commodity information as the related information of the historical input information.
  • the execution subject can also analyze the historical exposure information of the historical input information, and use the title words, keywords, or industrial attributes in the product information with the most exposure times as the associated information of the historical input information. Then, the execution subject can use the associated information of the historical input information to determine the associated information of the input information of the same type as the historical input information. In this implementation, all input will eventually be saved in digital form. In a relatively long time window, the product selection strategy of the event scene can be reused, and can also be shared among different operators, so that a knowledge system related to the event scene can be formed.
  • Step 3042 determine the matching degree of each commodity information in the preset commodity information set and the associated information; according to the matching degree, determine the matching commodity information.
  • the input information may include industrial attributes, title words, keywords, seed commodities, pictures and so on.
  • the above items of information can be regarded as rules, and the execution subject can record the number of times each product hits the rule and the correlation score between the product and the keyword. If a product S hits the industrial attribute a time, the title word b times, the keyword c times, is an extended product of the seed product, and is a similar item returned by the product image, it hits the rule (a+b+c+1+1) times .
  • the number of times a product hits a rule can be understood as a matching degree.
  • Sort by the number of times the product hits the rule, and the products with the same number of times are sorted by the highest correlation score of the keyword or picture (for example, when a product hits "printed dress", the correlation score is 0.75, and when it hits "fishtail skirt", the correlation score is 0.75; 0.92, and 0.81 is the correlation score of the hit product image, then take the maximum value of 0.92 as the sorting basis).
  • Step 3033 in response to determining that the type of the input information is a commodity identifier, determine a search term corresponding to the commodity identifier; determine related information according to the search term.
  • Step 3043 determining commodity information similar to the associated information in the preset commodity information set as matching commodity information.
  • the execution subject may first determine the search term corresponding to the commodity identifier. Specifically, the execution subject may first query the commodity information corresponding to the commodity identifier, and then determine the search term corresponding to the commodity identifier according to the preset correspondence between the commodity information and the search term. Then, the execution subject can use the above search terms to perform a search to obtain matching product information. For example, the execution subject can use the above search terms to search in the ES index through the ES search engine to obtain matching product information.
  • the execution subject periodically (for example, every day) calculates the correlation score between the search term and the product offline based on the user's search click log, combined with search click frequency, search exposure position and other information, and stores it In Distributed File System (HDFS).
  • Product information is stored in HDFS, such as the correlation score between search terms and products, attributes, titles, tags, and OCR of business details.
  • the big data platform writes the commodity information in HDFS to the Elasticsearch (ES) index through network transmission by executing scheduled Spark tasks.
  • ES Elasticsearch
  • Step 305 output commodity information.
  • Step 306 storing the input information and associated information.
  • the execution subject may also store the input information and associated information for subsequent association of the input information offline.
  • FIG. 4 shows a schematic diagram of an application scenario of the method for outputting information according to the present disclosure.
  • the operator is setting up a venue for the event “Girlfriend Clothes for the Double Seventh Festival” and enters “pink” to associate descriptors such as “rose red, peach red, apricot...” and so on. Enter “lace skirt”, then search for the nearest neighbor similar words in the pre-created word vector index, and then associate related words such as "floral skirt, printed skirt, mermaid skirt, suspender skirt.". Operators can check the recommended words, and each time they check, they support "cascading" display.
  • fishtail skirt If “fishtail skirt” is checked, it will continue to display the associated words most related to fishtail skirts "one-shoulder, slim dress ". If you end this round of association, you can choose to continue to manually enter in the input box. The selected words will remain in the display area. Finally, the matching commodity information is retrieved, sorted and displayed.
  • the method for outputting information can associate input information and perform retrieval based on the association information, thereby enriching retrieved product information and improving retrieval efficiency.
  • the present disclosure provides an embodiment of a device for outputting information.
  • This device embodiment corresponds to the method embodiment shown in FIG. 2 .
  • the device can be specifically applied to various electronic devices.
  • the apparatus 500 for outputting information in this embodiment includes: an information acquiring unit 501 , a type determining unit 502 , an information determining unit 503 and an information outputting unit 504 .
  • the information acquiring unit 501 is configured to acquire user input information.
  • the type determining unit 502 is configured to determine the type of the input information.
  • the related information determining unit 503 is configured to determine related information of the input information according to the above types.
  • the information determining unit 504 is configured to determine commodity information that matches the associated information.
  • the commodity information output unit 505 is configured to output commodity information.
  • the input information includes a target picture.
  • the associated information determining unit 503 may be further configured to: determine a target vector of the picture; and determine associated information of the input information according to the target vector.
  • the product information determining unit 504 may be further configured to: determine a vector similar to the target vector according to the associated information and the pre-stored vector set; and use the product information corresponding to the determined vector as the matched product information.
  • the input information includes text.
  • the related information determining unit 503 may be further configured to: perform association on the text to determine the associated information; in response to receiving filtering information for the associated information, determine related information according to the filtering information.
  • the associated information determining unit 503 may be further configured to: perform word segmentation on the text, and determine the obtained vector of each word; according to the vector of each word, determine the synonym of each word as an association information.
  • the associated information determining unit 503 may be further configured to: determine a category tree corresponding to the text; and determine a subcategory of the text as association information according to the category tree.
  • the input information includes commodity identifiers.
  • the associated information determining unit 503 may be further configured to: determine a search term corresponding to the product identifier; and determine product information similar to the search term in a preset product information set as matching product information.
  • the product information determining unit 504 may be further configured to: determine the degree of matching between each product information in the preset product information set and the associated information; product information.
  • the apparatus 500 may further include a storage unit configured to: store input information and associated information.
  • the device 500 may further include a history management unit configured to: determine the historical input information according to the historical input information and the historical click information and historical exposure information corresponding to the historical input information.
  • a history management unit configured to: determine the historical input information according to the historical input information and the historical click information and historical exposure information corresponding to the historical input information.
  • the associated information determining unit 503 may be further configured to: determine the associated information of the input information according to the associated information of historical input information of the same type as the input information.
  • the units 501 to 505 described in the apparatus 500 for outputting information respectively correspond to the steps in the method described with reference to FIG. 2 . Therefore, the operations and features described above for the method for outputting information are also applicable to the device 500 and the units contained therein, and will not be repeated here.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 6 shows a block diagram of an electronic device 600 performing a method for outputting information according to an embodiment of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • an electronic device 600 includes a processor 601, which can execute according to a computer program stored in a read-only memory (ROM) 602 or loaded from a memory 608 into a random access memory (RAM) 603. Various appropriate actions and treatments. In the RAM 603, various programs and data necessary for the operation of the electronic device 600 can also be stored.
  • the processor 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An I/O interface (input/output interface) 605 is also connected to the bus 604 .
  • the I/O interface 605 includes: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a memory 608, such as a magnetic disk, an optical disk, etc. ; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
  • Processor 601 may be various general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 601 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the processor 601 executes various methods and processes described above, such as a method for outputting information.
  • the method for outputting information may be implemented as a computer software program tangibly embodied on a machine-readable storage medium, such as memory 608 .
  • part or all of the computer program may be loaded and/or installed on the electronic device 600 via the ROM 602 and/or the communication unit 609 .
  • the computer program When the computer program is loaded into RAM 603 and executed by processor 601, one or more steps of the method for outputting information described above may be performed.
  • the processor 601 may be configured in any other suitable manner (for example, by means of firmware) to execute the method for outputting information.
  • Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system of systems
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages.
  • the above program code can be packaged into a computer program product.
  • These program codes or computer program products may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the program codes, when executed by the processor 601, make the flow diagrams and/or block diagrams specified The function/operation is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • the machine-readable storage medium may be a machine-readable signal storage medium or a machine-readable storage medium.
  • a machine-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage devices or any suitable combination of the foregoing.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problem of traditional physical host and VPS service ("Virtual Private Server", or "VPS”) Among them, there are defects such as difficult management and weak business scalability.
  • the server can also be a server of a distributed system, or a server combined with a blockchain.
  • steps may be reordered, added or deleted using the various forms of flow shown above.
  • each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution of the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Fuzzy Systems (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present disclosure relates to the field of big data, and provides a method and apparatus for outputting information, a device, and a storage medium. The specific implementation scheme comprises: acquiring input information of a user; determining the type of the input information; determining associated information of the input information according to the described type; determining commodity information matching the associated information; and outputting the commodity information. The present implementation can improve commodity retrieval efficiency.

Description

用于输出信息的方法、装置、设备以及存储介质Method, device, device and storage medium for outputting information
本专利申请要求于2021年11月03日提交的、申请号为202111292656.1、发明名称为“用于输出信息的方法、装置、设备以及存储介质”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申请中。This patent application claims the priority of the Chinese patent application with the application number 202111292656.1 and the title of the invention "method, device, equipment and storage medium for outputting information" submitted on November 03, 2021. The full text of the application is as follows: The way of citing is incorporated in this application.
技术领域technical field
本公开涉及计算机技术领域,具体涉及大数据技术领域,尤其涉及用于输出信息的方法、装置、设备以及存储介质。The present disclosure relates to the field of computer technology, specifically to the field of big data technology, and in particular to a method, device, device, and storage medium for outputting information.
背景技术Background technique
电商平台种类繁多的促销活动背后都有一套搭建活动会场和选品的***支持。平台运营人员通过***中的各类工具,实现对各种活动场景的创建和相关商品的提报。虽然电商平台会为商品打上各类标签,以便运营人员圈选商品,但标签量少且覆盖商品数有限,最重要的是活动场景搭建过程中,需要运营人员根据自己的业务经验进行标签选取。但这对运营人员的行业经验要求很高,且选品效率低。Behind the various promotional activities on the e-commerce platform, there is a set of system support for building event venues and product selection. Platform operators use various tools in the system to realize the creation of various activity scenarios and the reporting of related products. Although the e-commerce platform will put various labels on the products so that the operators can circle the products, but the number of labels is small and the number of covered products is limited. The most important thing is that during the construction of the event scene, the operators need to select labels based on their own business experience . However, this requires high industry experience for operators, and the efficiency of product selection is low.
发明内容Contents of the invention
本公开提供了一种用于输出信息的方法、装置、设备以及存储介质。The present disclosure provides a method, device, device and storage medium for outputting information.
本申请的一些实施例提供了一种用于输出信息的方法,包括:获取用户的输入信息;确定输入信息的类型;根据类型,确定输入信息的关联信息;确定与关联信息匹配的商品信息;输出商品信息。Some embodiments of the present application provide a method for outputting information, including: acquiring user input information; determining the type of the input information; determining associated information of the input information according to the type; determining commodity information matching the associated information; Output product information.
本申请的一些实施例提供了一种用于输出信息的装置,包括:信息获取单元,被配置成获取用户的输入信息;类型确定单元,被配置成确定输入信息的类型;关联信息确定单元,被配置成根据类型,确定输入信息的关联信息;商品信息确定单元,被配置成确定与关联信息匹配的商品信息; 信息输出单元,被配置成输出商品信息。Some embodiments of the present application provide an apparatus for outputting information, including: an information acquisition unit configured to acquire user input information; a type determination unit configured to determine the type of input information; an associated information determination unit, It is configured to determine associated information of the input information according to the type; the item information determining unit is configured to determine item information matching the associated information; the information output unit is configured to output item information.
本申请的一些实施例提供了一种电子设备,包括:至少一个处理器;以及与上述至少一个处理器通信连接的存储器;其中,存储器存储有可被至少一个处理器执行的指令,上述指令被至少一个处理器执行,以使至少一个处理器能够执行如第一方面所描述的方法。Some embodiments of the present application provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by Executed by at least one processor, so that at least one processor can execute the method as described in the first aspect.
本申请的一些实施例提供了一种存储有计算机指令的非瞬时计算机可读存储介质,上述计算机指令用于使计算机执行如第一方面所描述的方法。Some embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to make a computer execute the method as described in the first aspect.
本申请的一些实施例提供了一种计算机程序产品,包括计算机程序,上述计算机程序在被处理器执行时实现如第一方面所描述的方法。Some embodiments of the present application provide a computer program product, including a computer program. The above computer program implements the method as described in the first aspect when executed by a processor.
应当理解,本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征,也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will be readily understood through the following description.
附图说明Description of drawings
附图用于更好地理解本方案,不构成对本公开的限定。其中:The accompanying drawings are used to better understand the present solution, and do not constitute a limitation to the present disclosure. in:
图1是本公开的一个实施例可以应用于其中的示例性***架构图;FIG. 1 is an exemplary system architecture diagram to which an embodiment of the present disclosure can be applied;
图2是根据本公开的用于输出信息的方法的一个实施例的流程图;FIG. 2 is a flowchart of one embodiment of a method for outputting information according to the present disclosure;
图3是根据本公开的用于输出信息的方法的另一个实施例的流程图;FIG. 3 is a flowchart of another embodiment of a method for outputting information according to the present disclosure;
图4是根据本公开的用于输出信息的方法的一个应用场景的示意图;Fig. 4 is a schematic diagram of an application scenario of a method for outputting information according to the present disclosure;
图5是根据本公开的用于输出信息的装置的一个实施例的结构示意图;Fig. 5 is a schematic structural diagram of an embodiment of an apparatus for outputting information according to the present disclosure;
图6是用来实现本公开实施例的用于输出信息的方法的电子设备的框图。FIG. 6 is a block diagram of an electronic device for implementing a method for outputting information of an embodiment of the present disclosure.
具体实施方式Detailed ways
以下结合附图对本公开的示范性实施例做出说明,其中包括本公开实施例的各种细节以助于理解,应当将它们认为仅仅是示范性的。因此,本领域普通技术人员应当认识到,可以对这里描述的实施例做出各种改变和修改,而不会背离本公开的范围和精神。同样,为了清楚和简明,以下的 描述中省略了对公知功能和结构的描述。Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
需要说明的是,在不冲突的情况下,本公开中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本公开。It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.
图1示出了可以应用本公开的用于输出信息的方法或用于输出信息的装置的实施例的示例性***架构100。FIG. 1 shows an exemplary system architecture 100 to which embodiments of the method for outputting information or the apparatus for outputting information of the present disclosure can be applied.
如图1所示,***架构100可以包括终端设备101、102、103,网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型,例如有线、无线通信链路或者光纤电缆等等。As shown in FIG. 1 , a system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.
用户可以使用终端设备101、102、103通过网络104与服务器105交互,以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用,例如检索类应用等。Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like. Various communication client applications, such as retrieval applications, can be installed on the terminal devices 101, 102, and 103.
终端设备101、102、103可以是硬件,也可以是软件。当终端设备101、102、103为硬件时,可以是各种电子设备,包括但不限于智能手机、平板电脑、电子书阅读器、车载电脑、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时,可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块(例如用来提供分布式服务),也可以实现成单个软件或软件模块。在此不做具体限定。The terminal devices 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, including but not limited to smart phones, tablet computers, e-book readers, vehicle-mounted computers, laptop computers, desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as a plurality of software or software modules (for example, to provide distributed services), or as a single software or software module. No specific limitation is made here.
服务器105可以是提供各种服务的服务器,例如对终端设备101、102、103上显示的信息提供支持的后台服务器。后台服务器可以根据用户通过终端设备101、102、103输入的信息,得到匹配的商品信息,并将商品信息反馈给终端设备101、102、103。The server 105 may be a server that provides various services, such as a background server that provides support for information displayed on the terminal devices 101 , 102 , 103 . The background server can obtain matching product information according to the information input by the user through the terminal devices 101 , 102 , 103 , and feed back the product information to the terminal devices 101 , 102 , 103 .
需要说明的是,服务器105可以是硬件,也可以是软件。当服务器105为硬件时,可以实现成多个服务器组成的分布式服务器集群,也可以实现成单个服务器。当服务器105为软件时,可以实现成多个软件或软件模块(例如用来提供分布式服务),也可以实现成单个软件或软件模块。在此不做具体限定。It should be noted that the server 105 may be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.
需要说明的是,本公开实施例所提供的用于输出信息的方法一般由服务器105执行。相应地,用于输出信息的装置一般设置于服务器105中。It should be noted that, the method for outputting information provided by the embodiments of the present disclosure is generally executed by the server 105 . Accordingly, means for outputting information is generally provided in the server 105 .
应该理解,图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要,可以具有任意数目的终端设备、网络和服务器。It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.
继续参考图2,示出了根据本公开的用于输出信息的方法的一个实施例的流程200。本实施例的用于输出信息的方法,包括以下步骤:Continuing to refer to FIG. 2 , a flow 200 of an embodiment of a method for outputting information according to the present disclosure is shown. The method for outputting information in this embodiment includes the following steps:
步骤201,获取用户的输入信息。 Step 201, acquire user input information.
本实施例中,用于输出信息的方法的执行主体可以通过各种方式获取用户的输入信息。例如,执行主体可以与用户所使用的终端设备进行交互以接收用户的输入信息。上述输入信息可以包括文字、图片和链接,还可以包括SKU(stock keeping unit,库存量单位)。在本实施例的可选实现方式中,执行主体通过输入接口获取用户的输入信息。在一个可选实现方式中,执行主体向用户提供并呈现输入框,用户通过输入框输入的信息被执行主体获取,该输入框可接收文字、图片、链接、SKU等信息的输入。In this embodiment, the subject of execution of the method for outputting information may acquire the user's input information in various ways. For example, the execution subject may interact with the terminal device used by the user to receive input information from the user. The above input information may include text, pictures and links, and may also include SKU (stock keeping unit, stock keeping unit). In an optional implementation manner of this embodiment, the execution subject acquires user input information through an input interface. In an optional implementation, the execution subject provides and presents an input box to the user, and the information input by the user through the input box is obtained by the execution subject. The input box can receive input of text, pictures, links, SKU and other information.
步骤202,确定输入信息的类型。 Step 202, determine the type of input information.
执行主体在接收到输入信息后,可以对输入信息进行分析,确定输入信息的类型。上述类型可以包括但不限于:文字、图片、链接、SKU等等。具体的,执行主体对上述输入信息进行格式分析,如果检测到输入信息为图片格式的文件,则可以确定输入信息的类型为图片。如果检测到输入信息包括网址或文件地址,则可以确定输入信息的类型为链接。或者,执行主体可以将上述输入信息输入预先训练的卷积神经网络中,以识别输入信息的类型。After the execution subject receives the input information, it can analyze the input information and determine the type of the input information. The above types may include but not limited to: text, picture, link, SKU, etc. Specifically, the execution body analyzes the format of the above-mentioned input information, and if it detects that the input information is a file in a picture format, it can determine that the type of the input information is a picture. If it is detected that the input information includes a web address or a file address, it can be determined that the type of the input information is a link. Alternatively, the execution subject may input the above-mentioned input information into the pre-trained convolutional neural network to identify the type of the input information.
步骤203,根据类型,确定输入信息的关联信息。 Step 203, according to the type, determine the associated information of the input information.
本实施例中,执行主体在确定输入信息的类型后,可以根据上述类型,确定输入信息的关联信息。例如,如果输入信息的类型为图片,则可以将图片的向量或特征图作为关联信息,或者将图片中包括的对象的属性信息作为关联信息。例如,图片中包括的对象为包,则执行主体可以将包的形状(马鞍包、水桶包、云朵包等等)、包的颜色等等作为关联信息。如果输入信息的类型为链接,则可以将链接对应的网页中的标题、关键词或图片等作为关联信息。In this embodiment, after determining the type of the input information, the execution subject may determine the related information of the input information according to the above type. For example, if the type of input information is a picture, the vector or feature map of the picture may be used as the associated information, or the attribute information of the object included in the picture may be used as the associated information. For example, if the object included in the picture is a bag, the execution subject may use the shape of the bag (saddle bag, bucket bag, cloud bag, etc.), the color of the bag, etc. as associated information. If the type of the input information is a link, a title, a keyword, or a picture in a web page corresponding to the link may be used as associated information.
步骤204,确定与类型关联信息匹配的商品信息。 Step 204, determining commodity information matching the type association information.
执行主体在确定输入信息的关联信息后,可以进一步确定与上述关联 信息匹配的商品信息。具体的,执行主体可以根据关联信息进行检索,根据检索结果得到匹配的商品信息。例如,执行主体可以将关联信息中的不同项分别作为检索词,进行商品检索。将与各检索词最相关的商品作为匹配的商品信息。After the executive body determines the related information of the input information, it can further determine the product information that matches the above related information. Specifically, the execution subject can search according to the associated information, and obtain matching commodity information according to the search results. For example, the executive body may use different items in the associated information as search terms to perform commodity search. The product most relevant to each search term is used as the matching product information.
在一个可选的实现方式中,执行主体可以根据关联信息在预先存储的向量集合进行检索和匹配,或者利用Elasticsearch搜索引擎在预先存储的Elasticsearch索引中进行检索,以得到匹配的商品信息。In an optional implementation, the execution subject can search and match in the pre-stored vector set according to the associated information, or use the Elasticsearch search engine to search in the pre-stored Elasticsearch index, so as to obtain the matching product information.
步骤204,输出上述商品信息。 Step 204, outputting the above commodity information.
执行主体在确定出匹配的商品信息后,可以将上述商品信息输出,以供用户查看。例如,执行主体可以在终端展示匹配的商品的图片,以供用户查看。这里,用户可以指运营人员,用于布置参与促销活动的商品。用户也可以是购物人员,用于检索合适的商品。After the execution subject determines the matching product information, it can output the above product information for the user to view. For example, the execution subject may display pictures of matching commodities on the terminal for users to view. Here, the user may refer to an operator who is used to arrange commodities participating in promotional activities. A user can also be a shopper, retrieving suitable items.
本公开的上述实施例提供的用于输出信息的方法,可以根据用户的输入信息确定出匹配的商品信息,提高商品的检索效率。The method for outputting information provided by the above-mentioned embodiments of the present disclosure can determine matching commodity information according to user input information, and improve commodity retrieval efficiency.
继续参见图3,其示出了根据本公开的用于输出信息的方法的另一个实施例的流程300。如图3所示,本实施例的方法可以包括以下步骤:Continue referring to FIG. 3 , which shows a flow 300 of another embodiment of the method for outputting information according to the present disclosure. As shown in Figure 3, the method of this embodiment may include the following steps:
步骤301,获取用户的输入信息。 Step 301, acquiring user input information.
在本实施例的一些可选的实现方式中,上述输入信息不仅限于“识别”(保留),还支持“过滤”(剔除)。如识别属性为“适用人群/女士”,但是过滤掉“适用年龄:10岁以下”。需要说明的是,如果输入信息中包括过滤信息,则执行主体可以首先过滤不适合的商品信息,然后对其余的商品信息进行排序。In some optional implementations of this embodiment, the above input information is not limited to "recognition" (retention), but also supports "filtering" (elimination). For example, the identification attribute is "applicable people/women", but filter out "applicable age: under 10 years old". It should be noted that if the input information includes filter information, the execution subject may first filter unsuitable product information, and then sort the rest of the product information.
步骤302,确定输入信息的类型。 Step 302, determine the type of input information.
步骤3031,响应于确定输入信息的类型为图片,确定图片的目标向量;根据目标向量,确定输入信息的关联信息。 Step 3031, in response to determining that the type of the input information is a picture, determine a target vector of the picture; and determine related information of the input information according to the target vector.
本实施例中,如果输入信息的类型为图片,则执行主体首先可以确定图片的目标向量。具体的,执行主体可以通过各种特征提取算法确定图片的目标向量。例如,可以将图片输入特征提取网络,得到图片的目标向量。然后,执行主体可以对上述向量进行扩展,例如确定出相似的向量,将目标向量与相似向量作为关联信息。In this embodiment, if the type of input information is a picture, the execution subject may first determine the target vector of the picture. Specifically, the execution subject can determine the target vector of the picture through various feature extraction algorithms. For example, a picture can be fed into the feature extraction network to obtain the target vector of the picture. Then, the execution subject may expand the above vectors, for example, determine similar vectors, and use the target vector and similar vectors as associated information.
步骤3041,根据关联信息以及预先存储的向量集合,确定与目标向量相似的向量;将所确定的向量对应的商品信息作为匹配的商品信息。 Step 3041, according to the associated information and the pre-stored vector set, determine a vector similar to the target vector; use the product information corresponding to the determined vector as the matched product information.
执行主体可以将上述关联信息与预先存储的向量集合中的各向量进行对比,确定与关联信息中的各向量相似的向量。这里,上述向量集合中的各向量与商品信息的各主图一一对应。即向量集合中的不同向量对应不同的商品信息。执行主体可以将上述确定的向量对应的商品信息作为与输入信息匹配的商品信息。The execution subject may compare the above-mentioned associated information with each vector in the pre-stored vector set, and determine a vector similar to each vector in the associated information. Here, each vector in the above vector set is in one-to-one correspondence with each main image of commodity information. That is, different vectors in the vector set correspond to different commodity information. The execution subject may use the commodity information corresponding to the determined vector as the commodity information matching the input information.
在一个可选的实现方式中,该预先存储的向量集合为预先离线生成的向量集合。在一个实施方式中,执行主体预先构建图嵌入算法模型,并通过该图嵌入算法模型可以将电商平台的存量商品的主图嵌入到有限维向量空间,并存储为向量库(即,向量集合)。In an optional implementation manner, the pre-stored vector set is a pre-generated offline vector set. In one embodiment, the execution subject pre-constructs a graph embedding algorithm model, and through this graph embedding algorithm model, the main graph of stock commodities on the e-commerce platform can be embedded into a finite-dimensional vector space, and stored as a vector library (that is, a vector collection ).
步骤3032,响应于确定输入信息的类型为文字,对文字进行联想,确定联想信息;响应于接收到针对联想信息的筛选信息,根据筛选信息确定关联信息。 Step 3032, in response to determining that the type of the input information is text, perform association on the text, and determine association information; in response to receiving filtering information for the association information, determine associated information according to the filtering information.
本实施例中,如果输入信息为文字,则执行主体可以首先确定文字的关联信息。具体的,执行主体可以将上述文字的近义词或字形相近的词作为关联信息。或者,如果文字代表某一类目,则执行主体还可以将类目的相近类目作为关联信息,或者将类目的下级类目作为关联信息。或者,执行主体可以在接收到文字后,可以进行联想,确定联想信息。具体的,执行主体可以将文字的近义词、相近词作为联想信息。或者,执行主体还可以根据用户的历史输入信息,确定在文字之后或之前的文字,将上述文字作为联想信息。或者,如果文字表示类目或工业属性,则执行主体还可以将上述类目的平行类目作为联想信息。In this embodiment, if the input information is text, the execution subject may first determine the associated information of the text. Specifically, the execution subject may use synonyms of the above-mentioned words or words with similar shapes as related information. Or, if the text represents a certain category, the executive body can also use a similar category of the category as associated information, or use a lower-level category of the category as associated information. Or, after receiving the text, the execution subject can make associations and determine association information. Specifically, the execution subject may use synonyms and similar words of the text as association information. Alternatively, the execution subject may also determine the text after or before the text according to the historical input information of the user, and use the above text as association information. Or, if the words represent categories or industrial attributes, the executive body can also use the parallel categories of the above categories as association information.
如搭建“七夕节送女友服饰”活动会场,输入“粉色”,执行主体会联想出“玫红色、桃红色、杏色…”等相关描述词。输入“蕾丝裙”,执行主体会在预先创建的词向量索引中查找最近邻的相似词,然后联想出“碎花裙、印花裙、鱼尾裙、吊带裙…”等相关词。运营人员可勾选推荐的词,每次勾选支持“级联”展示,如勾选了“鱼尾裙”,则会继续展示与鱼尾裙最相关的联想词“一字肩、修身连衣裙…”。若结束本轮联想,可以选择继续在输入框手动输入。已选中的词会保留在展示区。For example, if you set up an activity venue for "Gift Girlfriend Clothes for Qixi Festival", input "pink", and the execution subject will associate related descriptors such as "rose red, peach red, apricot..." and so on. Enter "lace skirt", the execution subject will search for the nearest neighbor similar words in the pre-created word vector index, and then associate related words such as "floral skirt, printed skirt, mermaid skirt, suspender skirt...". Operators can check the recommended words, and each time they check, they support "cascading" display. If "fishtail skirt" is checked, it will continue to display the associated words most related to fishtail skirts "one-shoulder, slim dress ...". If you end this round of association, you can choose to continue to manually enter in the input box. The selected words will remain in the display area.
执行主体在确定联想信息后,可以输出上述联想信息。例如,将联想出的相关描述词或相关词以可勾选的方式呈现给用户。用户可以对上述联想信息进行反馈,即进一步输入,或对输出的联想信息进行勾选或删减等等。具体的,上述联想信息可以以多个词语的形式显示,每个词语前都关联有一个勾选框。如果用户点击了某个勾选框则表示选中了联想信息中的相应的词。执行主体可以将用户勾选了的词作为新的输入信息,然后根据新的输入信息进行进一步联想,直至用户输入文字或者点击结束按钮以结束联想。执行主体可以根据用户的反馈信息以及上述联想信息,确定最终的匹配的商品信息。After the execution subject determines the association information, it may output the above association information. For example, the associative related descriptors or related words are presented to the user in a checkable manner. The user can give feedback on the above association information, that is, further input, or check or delete the output association information, and the like. Specifically, the above association information may be displayed in the form of multiple words, and each word is associated with a check box. If the user clicks a check box, it means that the corresponding word in the association information is selected. The executive body can use the words checked by the user as new input information, and then make further associations based on the new input information until the user enters text or clicks the end button to end the association. The execution subject can determine the final matching commodity information according to the user's feedback information and the above association information.
在本实施例的一些可选的实现方式中,执行主体可以通过以下步骤确定关联信息:对文字进行分词,确定得到的各词语的向量;根据各词语的向量,确定各词语的近义词作为联想信息。In some optional implementations of this embodiment, the execution subject can determine the related information through the following steps: segment the text into words, and determine the vector of each word obtained; according to the vector of each word, determine the synonyms of each word as association information .
本实现方式中,执行主体可以对文字进行分词,得到至少一个词语。然后确定各个词语的向量。具体的,执行主体可以利用Word2vec等算法确定各个词语的向量。然后,执行主体可以根据各个词语的向量寻找与各词语语义相近的词语作为近义词,并将上述近义词作为联想信息。In this implementation manner, the execution subject may perform word segmentation on the text to obtain at least one word. Then determine the vector for each word. Specifically, the execution subject can use algorithms such as Word2vec to determine the vector of each word. Then, according to the vector of each word, the execution subject can find words with similar semantics to each word as synonyms, and use the above synonyms as association information.
在本实施例的一些可选的实现方式中,执行主体可以通过以下步骤确定关联信息:确定文字所对应的类目树;根据类目树,确定文字的下级类目为联想信息。In some optional implementations of this embodiment, the executive body may determine associated information through the following steps: determine the category tree corresponding to the text; and determine the subcategory of the text as association information according to the category tree.
本实现方式中,执行主体还可以确定文字所对应的类目树。这里,类目树可以包括多级类目,上级类目可以对应多个下级类目。执行主体可以将上述文字与类目树中的各级类目进行比较,如果二者相同或相近,则可以确定上述类目的下级类目为联想信息。In this implementation manner, the execution subject may also determine the category tree corresponding to the text. Here, the category tree may include multi-level categories, and an upper-level category may correspond to multiple lower-level categories. The executive body can compare the above-mentioned text with the categories at all levels in the category tree, and if the two are the same or similar, it can be determined that the lower-level category of the above-mentioned category is association information.
在本实施例的一些可选的实现方式中,执行主体可以通过以下步骤确定联想信息:根据历史输入信息以及与历史输入信息对应的历史点击信息以及历史曝光信息,确定历史输入信息的关联信息。根据与输入信息类型相同的历史输入信息的关联信息,确定输入信息的关联信息。In some optional implementations of this embodiment, the executive body may determine association information through the following steps: determine associated information of historical input information according to historical input information and historical click information and historical exposure information corresponding to the historical input information. The associated information of the input information is determined according to the associated information of the historical input information of the same type as the input information.
本实现方式中,执行主体还可以获取历史输入信息以及与海量用户针对各历史输入信息生成的历史点击信息以及历史曝光信息,并据此确定联想信息。这里,历史点击信息可以包括在特定的历史输入信息下,海量用 户对每个商品信息的点击次数。历史曝光信息可以包括在特定的历史输入信息下,海量用户浏览到的各商品信息的次数。具体的,对于每个历史输入信息,执行主体可以对该历史输入信息的历史点击信息进行分析,将历史点击信息中点击次数最多的商品信息作为与该历史输入信息最相关的商品信息。则执行主体可以将上述最相关的商品信息中的标题词、关键词、或工业属性等作为该历史输入信息的关联信息。或者,执行主体还可以对该历史输入信息的历史曝光信息进行分析,将曝光次数最多的商品信息中的标题词、关键词、或工业属性等作为该历史输入信息的关联信息。然后,执行主体可以利用历史输入信息的关联信息,来确定与历史输入信息相同类型的输入信息的关联信息。在该实现方式中,所有的输入最终都将以数字化的形式保存下来。在相对长的时间窗口内,活动场景的选品策略可重复使用,也可在不同运营人员之间共享,从而可以形成活动场景相关的知识体系。In this implementation, the executive body can also obtain historical input information and historical click information and historical exposure information generated by a large number of users for each historical input information, and determine association information accordingly. Here, the historical click information may include the number of clicks on each product information by a large number of users under specific historical input information. The historical exposure information may include the number of times that a large number of users have browsed each product information under specific historical input information. Specifically, for each historical input information, the execution subject may analyze the historical click information of the historical input information, and use the item information with the most clicks in the historical click information as the item information most relevant to the historical input information. Then the execution subject can use the title words, keywords, or industrial attributes in the above-mentioned most relevant commodity information as the related information of the historical input information. Alternatively, the execution subject can also analyze the historical exposure information of the historical input information, and use the title words, keywords, or industrial attributes in the product information with the most exposure times as the associated information of the historical input information. Then, the execution subject can use the associated information of the historical input information to determine the associated information of the input information of the same type as the historical input information. In this implementation, all input will eventually be saved in digital form. In a relatively long time window, the product selection strategy of the event scene can be reused, and can also be shared among different operators, so that a knowledge system related to the event scene can be formed.
步骤3042,确定预设的商品信息集合中的各商品信息与关联信息的匹配度;根据匹配度,确定匹配的商品信息。 Step 3042, determine the matching degree of each commodity information in the preset commodity information set and the associated information; according to the matching degree, determine the matching commodity information.
本实施例中,输入信息可以包括工业属性、标题词、关键词、种子商品、图片等等。上述各项信息可以认为是规则,执行主体可以记录每个商品命中的规则次数以及商品和关键词的相关性得分。如某商品S命中工业属性a次、标题词b次、关键词c次、是种子商品的扩展商品、是商品图片返回的相似款,则命中规则(a+b+c+1+1)次。这里,商品命中规则的次数可以理解为匹配度。按商品命中规则的次数倒排序,同次数的商品按关键词或图片的相关性的最高得分倒排(如某商品命中“印花连衣裙”时相关性得分0.75,命中“鱼尾裙”时的相关性得分0.92,命中商品图片相关性得分0.81,则取最大值0.92作为排序依据)。In this embodiment, the input information may include industrial attributes, title words, keywords, seed commodities, pictures and so on. The above items of information can be regarded as rules, and the execution subject can record the number of times each product hits the rule and the correlation score between the product and the keyword. If a product S hits the industrial attribute a time, the title word b times, the keyword c times, is an extended product of the seed product, and is a similar item returned by the product image, it hits the rule (a+b+c+1+1) times . Here, the number of times a product hits a rule can be understood as a matching degree. Sort by the number of times the product hits the rule, and the products with the same number of times are sorted by the highest correlation score of the keyword or picture (for example, when a product hits "printed dress", the correlation score is 0.75, and when it hits "fishtail skirt", the correlation score is 0.75; 0.92, and 0.81 is the correlation score of the hit product image, then take the maximum value of 0.92 as the sorting basis).
可以理解的是,技术人员可以根据实际应用场景对规则中的信息进行调整,以增加或删减影响相关性得分的影响因子。It can be understood that technical staff can adjust the information in the rules according to the actual application scenario, so as to increase or delete the influencing factors that affect the correlation score.
步骤3033,响应于确定输入信息的类型为商品标识,确定商品标识对应的检索词;根据检索词确定关联信息。 Step 3033, in response to determining that the type of the input information is a commodity identifier, determine a search term corresponding to the commodity identifier; determine related information according to the search term.
步骤3043,确定预设的商品信息集合中与关联信息相似的商品信息作为匹配的商品信息。 Step 3043, determining commodity information similar to the associated information in the preset commodity information set as matching commodity information.
本实施例中,如果输入信息的类型为商品标识,则执行主体可以首先确定商品标识对应的检索词。具体的,执行主体可以首先查询商品标识对应的商品信息,然后根据预先设置的商品信息与检索词的对应关系,确定出商品标识对应的检索词。然后,执行主体可以利用上述检索词进行检索,得到匹配的商品信息。例如,执行主体可以利用上述检索词通过ES搜索引擎在ES索引中进行检索,得到匹配的商品信息。In this embodiment, if the type of input information is a commodity identifier, the execution subject may first determine the search term corresponding to the commodity identifier. Specifically, the execution subject may first query the commodity information corresponding to the commodity identifier, and then determine the search term corresponding to the commodity identifier according to the preset correspondence between the commodity information and the search term. Then, the execution subject can use the above search terms to perform a search to obtain matching product information. For example, the execution subject can use the above search terms to search in the ES index through the ES search engine to obtain matching product information.
在一个可选的实现方式中,执行主体定期(例如,每天)根据用户的搜索点击日志,结合搜索点击频次,搜索曝光位置等信息,离线计算搜索词与商品的相关性得分,并将其存储在分布式文件***(HDFS)中。HDFS中存储有商品信息,如搜索词与商品的相关性得分、属性、标题、标签、商详OCR等。大数据平台以执行定时调度Spark任务的方式将HDFS中的商品信息通过网络传输写入Elasticsearch(ES)的索引。In an optional implementation, the execution subject periodically (for example, every day) calculates the correlation score between the search term and the product offline based on the user's search click log, combined with search click frequency, search exposure position and other information, and stores it In Distributed File System (HDFS). Product information is stored in HDFS, such as the correlation score between search terms and products, attributes, titles, tags, and OCR of business details. The big data platform writes the commodity information in HDFS to the Elasticsearch (ES) index through network transmission by executing scheduled Spark tasks.
步骤305,输出商品信息。 Step 305, output commodity information.
步骤306,存储输入信息以及关联信息。 Step 306, storing the input information and associated information.
本实施例中,执行主体还可以将输入信息和关联信息进行存储,以供后续在离线情况下对输入信息进行联想。In this embodiment, the execution subject may also store the input information and associated information for subsequent association of the input information offline.
继续参见图4,其示出了根据本公开的用于输出信息的方法的一个应用场景的示意图。在图4的应用场景中,运营人员在搭建“七夕节送女友服饰”活动会场,输入“粉色”,则联想出“玫红色、桃红色、杏色…”等相关描述词。输入“蕾丝裙”,则在预先创建的词向量索引中查找最近邻的相似词,然后联想出“碎花裙、印花裙、鱼尾裙、吊带裙…”等相关词。运营人员可勾选推荐的词,每次勾选支持“级联”展示,如勾选了“鱼尾裙”,则会继续展示与鱼尾裙最相关的联想词“一字肩、修身连衣裙…”。若结束本轮联想,可以选择继续在输入框手动输入。已选中的词会保留在展示区。最后,检索出匹配的商品信息,并对商品信息进行排序后予以显示。Continue referring to FIG. 4 , which shows a schematic diagram of an application scenario of the method for outputting information according to the present disclosure. In the application scenario shown in Figure 4, the operator is setting up a venue for the event “Girlfriend Clothes for the Double Seventh Festival” and enters “pink” to associate descriptors such as “rose red, peach red, apricot…” and so on. Enter "lace skirt", then search for the nearest neighbor similar words in the pre-created word vector index, and then associate related words such as "floral skirt, printed skirt, mermaid skirt, suspender skirt...". Operators can check the recommended words, and each time they check, they support "cascading" display. If "fishtail skirt" is checked, it will continue to display the associated words most related to fishtail skirts "one-shoulder, slim dress ...". If you end this round of association, you can choose to continue to manually enter in the input box. The selected words will remain in the display area. Finally, the matching commodity information is retrieved, sorted and displayed.
本公开的上述实施例提供的用于输出信息的方法,可以对输入信息进行联想,并依据联想信息进行检索,从而能够丰富检索出的商品信息,提高检索效率。The method for outputting information provided by the above embodiments of the present disclosure can associate input information and perform retrieval based on the association information, thereby enriching retrieved product information and improving retrieval efficiency.
进一步参考图5,作为对上述各图所示方法的实现,本公开提供了一 种用于输出信息的装置的一个实施例,该装置实施例与图2所示的方法实施例相对应,该装置具体可以应用于各种电子设备中。Further referring to FIG. 5 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for outputting information. This device embodiment corresponds to the method embodiment shown in FIG. 2 . The device can be specifically applied to various electronic devices.
如图5所示,本实施例的用于输出信息的装置500包括:信息获取单元501、类型确定单元502、信息确定单元503和信息输出单元504。As shown in FIG. 5 , the apparatus 500 for outputting information in this embodiment includes: an information acquiring unit 501 , a type determining unit 502 , an information determining unit 503 and an information outputting unit 504 .
信息获取单元501,被配置成获取用户的输入信息。The information acquiring unit 501 is configured to acquire user input information.
类型确定单元502,被配置成确定输入信息的类型。The type determining unit 502 is configured to determine the type of the input information.
关联信息确定单元503,被配置成根据上述类型,确定输入信息的关联信息。The related information determining unit 503 is configured to determine related information of the input information according to the above types.
信息确定单元504,被配置成确定与关联信息匹配的商品信息。The information determining unit 504 is configured to determine commodity information that matches the associated information.
商品信息输出单元505,被配置成输出商品信息。The commodity information output unit 505 is configured to output commodity information.
在本实施例的一些可选的实现方式中,输入信息包括目标图片。关联信息确定单元503可以进一步被配置成:确定图片的目标向量;根据所述目标向量,确定所述输入信息的关联信息。相应地,商品信息确定单元504可以进一步被配置成:根据关联信息以及预先存储的向量集合,确定与目标向量相似的向量;将所确定的向量对应的商品信息作为匹配的商品信息。In some optional implementation manners of this embodiment, the input information includes a target picture. The associated information determining unit 503 may be further configured to: determine a target vector of the picture; and determine associated information of the input information according to the target vector. Correspondingly, the product information determining unit 504 may be further configured to: determine a vector similar to the target vector according to the associated information and the pre-stored vector set; and use the product information corresponding to the determined vector as the matched product information.
在本实施例的一些可选的实现方式中,输入信息包括文字。关联信息确定单元503可以进一步被配置成:对文字进行联想,确定联想信息;响应于接收到针对联想信息的筛选信息,根据筛选信息确定关联信息。In some optional implementation manners of this embodiment, the input information includes text. The related information determining unit 503 may be further configured to: perform association on the text to determine the associated information; in response to receiving filtering information for the associated information, determine related information according to the filtering information.
在本实施例的一些可选的实现方式中,关联信息确定单元503可以进一步被配置成:对文字进行分词,确定得到的各词语的向量;根据各词语的向量,确定各词语的近义词作为联想信息。In some optional implementations of this embodiment, the associated information determining unit 503 may be further configured to: perform word segmentation on the text, and determine the obtained vector of each word; according to the vector of each word, determine the synonym of each word as an association information.
在本实施例的一些可选的实现方式中,关联信息确定单元503可以进一步被配置成:确定文字所对应的类目树;根据类目树,确定文字的下级类目为联想信息。In some optional implementation manners of this embodiment, the associated information determining unit 503 may be further configured to: determine a category tree corresponding to the text; and determine a subcategory of the text as association information according to the category tree.
在本实施例的一些可选的实现方式中,输入信息包括商品标识。关联信息确定单元503可以进一步被配置成:确定商品标识对应的检索词;确定预设的商品信息集合中与检索词相似的商品信息作为匹配的商品信息。In some optional implementations of this embodiment, the input information includes commodity identifiers. The associated information determining unit 503 may be further configured to: determine a search term corresponding to the product identifier; and determine product information similar to the search term in a preset product information set as matching product information.
在本实施例的一些可选的实现方式中,商品信息确定单元504可以进一步被配置成:确定预设的商品信息集合中的各商品信息与关联信息的匹 配度;根据匹配度,确定匹配的商品信息。In some optional implementations of this embodiment, the product information determining unit 504 may be further configured to: determine the degree of matching between each product information in the preset product information set and the associated information; product information.
在本实施例的一些可选的实现方式中,装置500还可以包括存储单元,被配置成:存储输入信息以及关联信息。In some optional implementation manners of this embodiment, the apparatus 500 may further include a storage unit configured to: store input information and associated information.
在本实施例的一些可选的实现方式中,装置500还可以包括历史管理单元,被配置成:根据历史输入信息以及与历史输入信息对应的历史点击信息以及历史曝光信息,确定历史输入信息的关联信息。相应地,关联信息确定单元503可以进一步被配置成:根据与所述输入信息类型相同的历史输入信息的关联信息,确定所述输入信息的关联信息。In some optional implementations of this embodiment, the device 500 may further include a history management unit configured to: determine the historical input information according to the historical input information and the historical click information and historical exposure information corresponding to the historical input information. Associated information. Correspondingly, the associated information determining unit 503 may be further configured to: determine the associated information of the input information according to the associated information of historical input information of the same type as the input information.
应当理解,用于输出信息的装置500中记载的单元501至单元505分别与参考图2中描述的方法中的各个步骤相对应。由此,上文针对用于输出信息的方法描述的操作和特征同样适用于装置500及其中包含的单元,在此不再赘述。It should be understood that the units 501 to 505 described in the apparatus 500 for outputting information respectively correspond to the steps in the method described with reference to FIG. 2 . Therefore, the operations and features described above for the method for outputting information are also applicable to the device 500 and the units contained therein, and will not be repeated here.
本公开的技术方案中,所涉及的用户个人信息的收集、存储、使用、加工、传输、提供和公开等处理,均符合相关法律法规的规定,且不违背公序良俗。In the technical solution of this disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved are all in compliance with relevant laws and regulations, and do not violate public order and good customs.
根据本公开的实施例,本公开还提供了还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
图6示出了根据本公开实施例的执行用于输出信息的方法的电子设备600的框图。电子设备旨在表示各种形式的数字计算机,诸如,膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置,诸如,个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例,并且不意在限制本文中描述的和/或者要求的本公开的实现。FIG. 6 shows a block diagram of an electronic device 600 performing a method for outputting information according to an embodiment of the present disclosure. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
如图6所示,电子设备600包括处理器601,其可以根据存储在只读存储器(ROM)602中的计算机程序或者从存储器608加载到随机访问存储器(RAM)603中的计算机程序,来执行各种适当的动作和处理。在RAM 603中,还可存储电子设备600操作所需的各种程序和数据。处理器601、ROM 602以及RAM 603通过总线604彼此相连。I/O接口(输入/输出接口)605也连接至总线604。As shown in FIG. 6, an electronic device 600 includes a processor 601, which can execute according to a computer program stored in a read-only memory (ROM) 602 or loaded from a memory 608 into a random access memory (RAM) 603. Various appropriate actions and treatments. In the RAM 603, various programs and data necessary for the operation of the electronic device 600 can also be stored. The processor 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An I/O interface (input/output interface) 605 is also connected to the bus 604 .
电子设备600中的多个部件连接至I/O接口605,包括:输入单元606,例如键盘、鼠标等;输出单元607,例如各种类型的显示器、扬声器等;存储器608,例如磁盘、光盘等;以及通信单元609,例如网卡、调制解调器、无线通信收发机等。通信单元609允许电子设备600通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。Multiple components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a memory 608, such as a magnetic disk, an optical disk, etc. ; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
处理器601可以是各种具有处理和计算能力的通用和/或专用处理组件。处理器601的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的处理器、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。处理器601执行上文所描述的各个方法和处理,例如用于输出信息的方法。例如,在一些实施例中,用于输出信息的方法可被实现为计算机软件程序,其被有形地包含于机器可读存储介质,例如存储器608。在一些实施例中,计算机程序的部分或者全部可以经由ROM602和/或通信单元609而被载入和/或安装到电子设备600上。当计算机程序加载到RAM 603并由处理器601执行时,可以执行上文描述的用于输出信息的方法的一个或多个步骤。备选地,在其他实施例中,处理器601可以通过其他任何适当的方式(例如,借助于固件)而被配置为执行用于输出信息的方法。 Processor 601 may be various general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 601 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 601 executes various methods and processes described above, such as a method for outputting information. For example, in some embodiments, the method for outputting information may be implemented as a computer software program tangibly embodied on a machine-readable storage medium, such as memory 608 . In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 600 via the ROM 602 and/or the communication unit 609 . When the computer program is loaded into RAM 603 and executed by processor 601, one or more steps of the method for outputting information described above may be performed. Alternatively, in other embodiments, the processor 601 may be configured in any other suitable manner (for example, by means of firmware) to execute the method for outputting information.
本文中以上描述的***和技术的各种实施方式可以在数字电子电路***、集成电路***、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上***的***(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括:实施在一个或者多个计算机程序中,该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程***上执行和/或解释,该可编程处理器可以是专用或者通用可编程处理器,可以从存储***、至少一个输入装置、和至少一个输出装置接收数据和指令,并且将数据和指令传输至该存储***、该至少一个输入装置、和该至少一个输出装置。Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。上述程序代码可以封装成计算机程序产品。这些程序代 码或计算机程序产品可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器,使得程序代码当由处理器601执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行,作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. The above program code can be packaged into a computer program product. These program codes or computer program products may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the program codes, when executed by the processor 601, make the flow diagrams and/or block diagrams specified The function/operation is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
在本公开的上下文中,机器可读存储介质可以是有形的介质,其可以包含或存储以供指令执行***、装置或设备使用或与指令执行***、装置或设备结合地使用的程序。机器可读存储介质可以是机器可读信号存储介质或机器可读存储介质。机器可读存储介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体***、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学存储设备、磁存储设备、或上述内容的任何合适组合。In the context of the present disclosure, a machine-readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The machine-readable storage medium may be a machine-readable signal storage medium or a machine-readable storage medium. A machine-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
为了提供与用户的交互,可以在计算机上实施此处描述的***和技术,该计算机具有:用于向用户显示信息的显示装置(例如,CRT(阴极射线管)或者LCD(液晶显示器)监视器);以及键盘和指向装置(例如,鼠标或者轨迹球),用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互;例如,提供给用户的反馈可以是任何形式的传感反馈(例如,视觉反馈、听觉反馈、或者触觉反馈);并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
可以将此处描述的***和技术实施在包括后台部件的计算***(例如,作为数据服务器)、或者包括中间件部件的计算***(例如,应用服务器)、或者包括前端部件的计算***(例如,具有图形用户界面或者网络浏览器的用户计算机,用户可以通过该图形用户界面或者该网络浏览器来与此处描述的***和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算***中。可以通过任何形式或者介质的数字数据通信(例如,通信网络)来将***的部件相互连接。通信网络 的示例包括:局域网(LAN)、广域网(WAN)和互联网。The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
计算机***可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器,又称为云计算服务器或云主机,是云计算服务体系中的一项主机产品,以解决了传统物理主机与VPS服务(“Virtual Private Server”,或简称“VPS”)中,存在的管理难度大,业务扩展性弱的缺陷。服务器也可以是分布式***的服务器,或者是结合了区块链的服务器。A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problem of traditional physical host and VPS service ("Virtual Private Server", or "VPS") Among them, there are defects such as difficult management and weak business scalability. The server can also be a server of a distributed system, or a server combined with a blockchain.
应该理解,可以使用上面所示的各种形式的流程,重新排序、增加或删除步骤。例如,本公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行,只要能够实现本公开的技术方案所期望的结果,本文在此不进行限制。It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution of the present disclosure can be achieved, no limitation is imposed herein.
上述具体实施方式,并不构成对本公开保护范围的限制。本领域技术人员应该明白的是,根据设计要求和其他因素,可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等,均应包含在本公开的保护范围之内。The specific implementation manners described above do not limit the protection scope of the present disclosure. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall fall within the protection scope of the present disclosure.

Claims (21)

  1. 一种用于输出信息的方法,包括:A method for outputting information, comprising:
    获取用户的输入信息;Obtain user input information;
    确定所述输入信息的类型;determining the type of said input information;
    根据所述类型,确定所述输入信息的关联信息;determining associated information of the input information according to the type;
    确定与所述关联信息匹配的商品信息;Determine commodity information that matches the associated information;
    输出所述商品信息。The product information is output.
  2. 根据权利要求1所述的方法,其中,所述输入信息包括目标图片;以及The method of claim 1, wherein the input information includes a target picture; and
    所述根据所述类型,确定所述输入信息的关联信息,包括:According to the type, determining the associated information of the input information includes:
    确定所述图片的目标向量;determining the target vector of the picture;
    根据所述目标向量,确定所述输入信息的关联信息;以及determining associated information of the input information according to the target vector; and
    所述确定与所述关联信息匹配的商品信息,包括:The determination of commodity information that matches the associated information includes:
    根据所述关联信息以及预先存储的向量集合,确定与所述目标向量相似的向量;determining a vector similar to the target vector according to the association information and the pre-stored vector set;
    将所确定的向量对应的商品信息作为匹配的商品信息。The commodity information corresponding to the determined vector is used as the matched commodity information.
  3. 根据权利要求1所述的方法,其中,所述输入信息包括文字;以及The method of claim 1, wherein the input information includes text; and
    所述根据所述类型,确定所述输入信息的关联信息,包括:According to the type, determining the associated information of the input information includes:
    对所述文字进行联想,确定联想信息;Associating the text to determine the association information;
    响应于接收到针对所述联想信息的筛选信息,根据所述筛选信息确定所述关联信息。In response to receiving filter information for the association information, the association information is determined according to the filter information.
  4. 根据权利要求3所述的方法,其中,所述对所述文字进行联想,确定联想信息,包括:The method according to claim 3, wherein said associating said characters and determining association information includes:
    对所述文字进行分词,确定得到的各词语的向量;Carry out word segmentation to described text, determine the vector of each word that obtains;
    根据各词语的向量,确定各词语的近义词作为所述联想信息。According to the vector of each word, a synonym of each word is determined as the association information.
  5. 根据权利要求3所述的方法,其中,所述对所述文字进行联想,确定联想信息,包括:The method according to claim 3, wherein said associating said characters and determining association information includes:
    确定所述文字所对应的类目树;determining the category tree corresponding to the text;
    根据所述类目树,确定所述文字的下级类目为所述联想信息。According to the category tree, it is determined that the subcategory of the text is the association information.
  6. 根据权利要求1-5任一项所述的方法,其中,所述输入信息包括商品标识;以及The method according to any one of claims 1-5, wherein the input information includes commodity identification; and
    所述根据所述类型,确定所述输入信息的关联信息,包括:According to the type, determining the associated information of the input information includes:
    确定所述商品标识对应的检索词;Determining the search terms corresponding to the commodity identifier;
    将所述检索词作为所述关联信息。The search term is used as the associated information.
  7. 根据权利要求1-6任一项所述的方法,其中,所述确定与所述关联信息匹配的商品信息,包括:The method according to any one of claims 1-6, wherein said determining commodity information matching said associated information comprises:
    确定预设的商品信息集合中的各商品信息与所述关联信息的匹配度;Determine the degree of matching between each commodity information in the preset commodity information set and the associated information;
    根据所述匹配度,确定匹配的商品信息。According to the matching degree, the matching product information is determined.
  8. 根据权利要求1-7任一项所述的方法,其中,所述方法还包括:The method according to any one of claims 1-7, wherein the method further comprises:
    存储所述输入信息以及所述关联信息。The input information and the associated information are stored.
  9. 根据权利要求1-8任一项所述的方法,其中,所述方法还包括:The method according to any one of claims 1-8, wherein the method further comprises:
    根据历史输入信息以及与所述历史输入信息对应的历史点击信息以及历史曝光信息,确定所述历史输入信息的关联信息;determining associated information of the historical input information according to the historical input information and historical click information and historical exposure information corresponding to the historical input information;
    所述根据所述类型,确定所述输入信息的关联信息,包括:According to the type, determining the associated information of the input information includes:
    根据与所述输入信息类型相同的历史输入信息的关联信息,确定所述输入信息的关联信息。The associated information of the input information is determined according to the associated information of the historical input information of the same type as the input information.
  10. 一种用于输出信息的装置,包括:A device for outputting information, comprising:
    信息获取单元,被配置成获取用户的输入信息;an information acquisition unit configured to acquire user input information;
    类型确定单元,被配置成确定所述输入信息的类型;a type determination unit configured to determine the type of the input information;
    关联信息确定单元,被配置成根据所述类型,确定所述输入信息的关联信息;an associated information determining unit configured to determine associated information of the input information according to the type;
    商品信息确定单元,被配置成确定与所述关联信息匹配的商品信息;a commodity information determining unit configured to determine commodity information matching the associated information;
    信息输出单元,被配置成输出所述商品信息。An information output unit configured to output the commodity information.
  11. 根据权利要求10所述的装置,其中所述输入信息包括目标图片;所述关联信息确定单元进一步被配置成:The device according to claim 10, wherein the input information includes a target picture; the associated information determining unit is further configured to:
    确定所述图片的目标向量;determining the target vector of the picture;
    根据所述目标向量,确定所述输入信息的关联信息,determining associated information of the input information according to the target vector,
    所述商品信息确定单元进一步被配置成:The commodity information determining unit is further configured to:
    根据所述关联信息以及预先存储的向量集合,确定与目标向量相似的向量;以及determining a vector similar to the target vector according to the associated information and the pre-stored set of vectors; and
    将所确定的向量对应的商品信息作为匹配的商品信息。The commodity information corresponding to the determined vector is used as the matched commodity information.
  12. 根据权利要求10所述的装置,其中所述输入信息包括文字;所述关联信息确定单元进一步被配置成:The device according to claim 10, wherein the input information includes text; the associated information determining unit is further configured to:
    对所述文字进行联想,确定联想信息;Associating the text to determine the association information;
    响应于接收到针对所述联想信息的筛选信息,根据所述筛选信息确定所述关联信息。In response to receiving filter information for the association information, the association information is determined according to the filter information.
  13. 根据权利要求12所述的装置,其中,所述关联信息确定单元进一步被配置成:The device according to claim 12, wherein the associated information determining unit is further configured to:
    对所述文字进行分词,确定得到的各词语的向量;Carry out word segmentation to described text, determine the vector of each word that obtains;
    根据各词语的向量,确定各词语的近义词作为所述联想信息。According to the vector of each word, a synonym of each word is determined as the association information.
  14. 根据权利要求12所述的装置,其中,所述关联信息确定单 元进一步被配置成:The device according to claim 12, wherein the associated information determining unit is further configured to:
    确定所述文字所对应的类目树;determining the category tree corresponding to the text;
    根据所述类目树,确定所述文字的下级类目为所述联想信息。According to the category tree, it is determined that the subcategory of the text is the association information.
  15. 根据权利要求10-14任一项所述的装置,其中,所述输入信息包括商品标识;所述关联信息确定单元进一步被配置成:The device according to any one of claims 10-14, wherein the input information includes a commodity identifier; the associated information determining unit is further configured to:
    确定所述商品标识对应的检索词;Determining the search terms corresponding to the commodity identifier;
    将所述检索词作为所述关联信息。The search term is used as the associated information.
  16. 根据权利要求10-15任一项所述的装置,其中所述商品信息确定单元进一步被配置成:The device according to any one of claims 10-15, wherein the product information determining unit is further configured to:
    确定预设的商品信息集合中的各商品信息与所述关联信息的匹配度;Determine the degree of matching between each commodity information in the preset commodity information set and the associated information;
    根据所述匹配度,确定匹配的商品信息。According to the matching degree, the matching product information is determined.
  17. 根据权利要求10-16任一项所述的装置,其中所述装置还包括存储单元,所述存储单元被配置成:存储所述输入信息以及所述关联信息。The device according to any one of claims 10-16, wherein the device further comprises a storage unit configured to: store the input information and the associated information.
  18. 根据权利要求10-17任一项所述的装置,其中所述装置还包括历史管理单元,所述历史管理单元被配置成:The device according to any one of claims 10-17, wherein the device further comprises a history management unit configured to:
    所述根据所述类型,确定所述输入信息的关联信息,包括:According to the type, determining the associated information of the input information includes:
    根据与所述输入信息类型相同的历史输入信息的关联信息,确定所述输入信息的关联信息。The associated information of the input information is determined according to the associated information of the historical input information of the same type as the input information.
  19. 一种电子设备,包括:An electronic device comprising:
    至少一个处理器;以及at least one processor; and
    与所述至少一个处理器通信连接的存储器;其中,a memory communicatively coupled to the at least one processor; wherein,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执 行权利要求1-9中任一项所述的方法。The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-9. Methods.
  20. 一种存储有计算机指令的非瞬时计算机可读存储介质,所述计算机指令用于使所述计算机执行权利要求1-9中任一项所述的方法。A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method according to any one of claims 1-9.
  21. 一种计算机程序产品,包括计算机程序,所述计算机程序在被处理器执行时实现根据权利要求1-9中任一项所述的方法。A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.
PCT/CN2022/117037 2021-11-03 2022-09-05 Method and apparatus for outputting information, device, and storage medium WO2023077944A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111292656.1 2021-11-03
CN202111292656.1A CN113987026A (en) 2021-11-03 2021-11-03 Method, apparatus, device and storage medium for outputting information

Publications (1)

Publication Number Publication Date
WO2023077944A1 true WO2023077944A1 (en) 2023-05-11

Family

ID=79746037

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/117037 WO2023077944A1 (en) 2021-11-03 2022-09-05 Method and apparatus for outputting information, device, and storage medium

Country Status (2)

Country Link
CN (1) CN113987026A (en)
WO (1) WO2023077944A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113987026A (en) * 2021-11-03 2022-01-28 北京沃东天骏信息技术有限公司 Method, apparatus, device and storage medium for outputting information

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009134656A (en) * 2007-12-01 2009-06-18 Fujifilm Corp Commodity presentation system and commodity search server
CN111444424A (en) * 2020-03-25 2020-07-24 深圳市分期乐网络科技有限公司 Information recommendation method and information recommendation system
US10891673B1 (en) * 2016-12-22 2021-01-12 A9.Com, Inc. Semantic modeling for search
CN112837108A (en) * 2019-11-25 2021-05-25 阿里巴巴集团控股有限公司 Information processing method and device and electronic equipment
CN112884542A (en) * 2021-01-21 2021-06-01 北京电解智科技有限公司 Commodity recommendation method and device
CN113191858A (en) * 2021-06-10 2021-07-30 数贸科技(北京)有限公司 Commodity display method and device based on picture search
CN113987026A (en) * 2021-11-03 2022-01-28 北京沃东天骏信息技术有限公司 Method, apparatus, device and storage medium for outputting information

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009134656A (en) * 2007-12-01 2009-06-18 Fujifilm Corp Commodity presentation system and commodity search server
US10891673B1 (en) * 2016-12-22 2021-01-12 A9.Com, Inc. Semantic modeling for search
CN112837108A (en) * 2019-11-25 2021-05-25 阿里巴巴集团控股有限公司 Information processing method and device and electronic equipment
CN111444424A (en) * 2020-03-25 2020-07-24 深圳市分期乐网络科技有限公司 Information recommendation method and information recommendation system
CN112884542A (en) * 2021-01-21 2021-06-01 北京电解智科技有限公司 Commodity recommendation method and device
CN113191858A (en) * 2021-06-10 2021-07-30 数贸科技(北京)有限公司 Commodity display method and device based on picture search
CN113987026A (en) * 2021-11-03 2022-01-28 北京沃东天骏信息技术有限公司 Method, apparatus, device and storage medium for outputting information

Also Published As

Publication number Publication date
CN113987026A (en) 2022-01-28

Similar Documents

Publication Publication Date Title
CN107436875B (en) Text classification method and device
CN107330752B (en) Method and device for identifying brand words
US11514054B1 (en) Supervised graph partitioning for record matching
CN112749300B (en) Method, apparatus, device, storage medium and program product for video classification
US11294971B1 (en) Systems and methods for modeling item similarity using converted image information
CN112507098B (en) Question processing method, question processing device, electronic equipment, storage medium and program product
CN113656587B (en) Text classification method, device, electronic equipment and storage medium
WO2023125315A1 (en) Information search method and apparatus, electronic device and storage medium
WO2023077944A1 (en) Method and apparatus for outputting information, device, and storage medium
US20220198358A1 (en) Method for generating user interest profile, electronic device and storage medium
CN113128209A (en) Method and device for generating word stock
CN114756570A (en) Vertical search method, device and system for purchase scene
WO2022001349A1 (en) Method and device for information analysis
US11847599B1 (en) Computing system for automated evaluation of process workflows
US20230180917A1 (en) Method for processing makeup and electronic device
CN116955856A (en) Information display method, device, electronic equipment and storage medium
CN116597443A (en) Material tag processing method and device, electronic equipment and medium
WO2023050732A1 (en) Object recommendation method and device
US20210342379A1 (en) Method and device for processing sentence, and storage medium
CN113110782B (en) Image recognition method and device, computer equipment and storage medium
CN115048523A (en) Text classification method, device, equipment and storage medium
CN114048315A (en) Method and device for determining document tag, electronic equipment and storage medium
CN114357180A (en) Knowledge graph updating method and electronic equipment
CN113704494A (en) Entity retrieval method, device and equipment based on knowledge graph and storage medium
CN113239054A (en) Information generation method, related device and computer program product

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: 22888975

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE