WO2020224263A1 - 商品推荐 - Google Patents

商品推荐 Download PDF

Info

Publication number
WO2020224263A1
WO2020224263A1 PCT/CN2019/125255 CN2019125255W WO2020224263A1 WO 2020224263 A1 WO2020224263 A1 WO 2020224263A1 CN 2019125255 W CN2019125255 W CN 2019125255W WO 2020224263 A1 WO2020224263 A1 WO 2020224263A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
target user
user
probability
product
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/125255
Other languages
English (en)
French (fr)
Inventor
卢浩
李达
孙国良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Publication of WO2020224263A1 publication Critical patent/WO2020224263A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0254—Targeted advertisements based on statistics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location

Definitions

  • This application relates to the computer field, especially to product recommendation.
  • offline shopping venues attract users to purchase products through marketing methods such as product discounts, new product recommendations, and event promotions. While improving the user's shopping experience, it also promotes the sales of products in the shopping venues.
  • whether a user will buy a product in a shopping area is not only related to the user's own preferences, but may also be related to the user's travel route in the shopping place. For example, after a user purchases a steak through the steak area, the more likely it is to purchase red wine when they arrive at the red wine area.
  • the products recommended by the shopping place to the user are often determined by the marketing strategy of the shopping place. Therefore, the actual recommended products may not be what the user needs. Therefore, how to recommend products to users based on the user's travel route in a shopping place and improve the accuracy of product recommendation is an urgent problem to be solved.
  • the embodiments of the present application provide a method and device for recommending commodities.
  • This application provides a method for product recommendation, including:
  • the commodity to be recommended to the target user is determined, and the commodity corresponding to the geographic location is recommended to the target user.
  • This application provides a product recommendation device, including:
  • the first determination module is used to determine the current geographic location of the target user and the first path taken by the target user to reach the geographic location;
  • a second determining module configured to determine, according to the first path, a second path whose similarity with the first path exceeds a preset similarity
  • the probability determination module is configured to determine, for each product corresponding to the geographic location, the probability of each user who has passed the second path in history to purchase the product, and use it as the probability of the target user to purchase the product;
  • the recommendation module is configured to determine the commodity recommended to the target user and recommend the commodity corresponding to the geographic location to the target user according to the determined probability of the target user purchasing each commodity corresponding to the geographic location.
  • the present application provides a computer-readable storage medium, the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for recommending commodities is realized.
  • the present application provides an electronic device including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the above-mentioned method of product recommendation when the program is executed.
  • this method can determine which products in the geographic location may be needed by the target user when the target user follows the path to reach the current geographic location by analyzing the path taken by the target user. That is, it is realized that the product recommended to the target user is determined based on the actual walking route of the target user, thereby effectively improving the accuracy of product recommendation.
  • FIG. 1 is a schematic flowchart of a method for recommending commodities in an embodiment of this application
  • Fig. 2 is a schematic diagram of dividing the walking passages of shopping places into road sections according to an embodiment of the application;
  • FIG. 3 is a schematic diagram showing the paths passed by the user through each divided road section provided by an embodiment of the application.
  • Figure 4 is a schematic diagram of a product recommendation device provided by this application.
  • FIG. 5 is a schematic diagram of the electronic device corresponding to FIG. 1 provided by this application.
  • users may determine which products should be purchased in the current geographic location based on the geographic locations that they have passed. For example, after a user purchases minced meat through the fresh food area, the probability of purchasing soy sauce, vinegar and other seasonings through the seasoning area is greater; for another example, after purchasing clothes through the clothing area, users are more likely to purchase shoes through the shoe area. . Therefore, in this application, it is possible to determine which products in the geographic location have a higher probability of purchasing based on the path the user has traveled, and then recommend products to the user.
  • the geographic location mentioned in this application can be actual geographic coordinates, or it can refer to an area in a certain place, such as a shopping area in a shopping place, or it can refer to an actual building, such as a shopping mall, a supermarket , Department stores, etc.
  • the product recommendation method provided in this application is applicable, that is, it can be determined based on the department stores, supermarkets, shops, etc. that the user passes through when shopping online, to determine whether the user should be recommended to the user.
  • the products in the shopping mall where the user is currently located can also be determined based on the shopping area the user passes through in the shopping place to recommend the products in the shopping area where the user is currently located. Since the specific process of applying the method of product recommendation provided by this application to various scenarios is basically similar, for the convenience of description, the following will only take the scenario of a user doing offline shopping in a shopping place as an example. The method of applying for the recommended product is explained.
  • Fig. 1 is a schematic flowchart of a method for recommending commodities in an embodiment of the application, including the following steps:
  • S101 Determine the current geographic location of the target user and the first path taken by the target user to reach the geographic location.
  • a shopping place usually contains multiple shopping areas.
  • a shopping mall ie, a shopping place
  • shopping areas such as a wine area, a fresh food area, a vegetable area, a fruit area, and a clothing area.
  • the location of the target user in the shopping place can be monitored in real time to determine the target The geographic location where the user is currently located, and at the same time the first path taken by the target user to reach the geographic location can be determined.
  • the geographical location mentioned here can refer to the shopping area in the shopping place.
  • the target user mentioned here is an ordinary user. The reason why it is called the target user is mainly used to distinguish the current user from the users in the history mentioned later. There is nothing special about it. Meaning.
  • a mobile terminal such as a mobile phone, smart bracelet, tablet computer, etc.
  • WiFi wireless Fidelity
  • the designated device determines the current geographic location of the target user and the first path taken by the target user to reach the geographic location.
  • the target user may carry an Ultra Wideband (UWB) tag, and multiple signal receivers are provided in the shopping place to receive the pulse signal transmitted by the UWB tag. Therefore, when the target user carries the UWB tag for shopping in the shopping place, the designated device of the shopping place can receive the pulse signal emitted by the UWB tag according to the multiple signal receivers set in the shopping place, so as to achieve the target Real-time positioning and recording of the user's location.
  • the UWB tag can be set on the mobile device carried by the target user, or on the shopping bag, shopping basket, or shopping cart provided to the user by the shopping place.
  • the designated device of the shopping place can determine the target user’s journey to the current geographical location based on the records of the geographical locations that the target user has passed through in the shopping place. The first path.
  • the above-mentioned designated device for determining the current geographic location of the target user and the first path traversed by the target user may be a device set in a shopping place for locating the target user, such as A computer, etc., can also be a server used by a shopping place to locate target users.
  • the server used by a shopping place to locate target users.
  • the first path mentioned above is the actual path taken by the target user to reach the current geographic location. It is called the first path and is mainly used to distinguish it from the second path mentioned later. , "First” and “Second” mentioned in this application have no other special meanings.
  • S102 According to the first path, determine a second path whose similarity with the first path exceeds a preset similarity.
  • the server may determine a second path whose similarity with the first path exceeds the preset similarity from among the historical paths that each user passes through in the shopping place in the stored history.
  • the server may determine the road segments included in the first path, that is, the road segments that the user passes in the shopping place when the user arrives at the current geographic location.
  • the road section mentioned here may be obtained by dividing each walking passage in the shopping place in units of road sections according to the actual layout of the shopping place in advance.
  • the walking channel may consist of at least one road section. Each walking channel in the entire shopping place can be represented by each road section, as shown in Figure 2.
  • Fig. 2 is a schematic diagram of dividing the walking passages of shopping places into sections according to an embodiment of the application.
  • the walking channel may be divided into units of road sections, and each line segment in FIG. 2 is the divided road section. It can be seen from Fig. 2 that each walking channel can be represented by at least one road section. In actual applications, the path that the user travels in the shopping place can be represented by the road sections shown in FIG. 2, as shown in FIG. 3.
  • FIG. 3 is a schematic diagram showing the paths passed by the user through each divided road section provided by an embodiment of the application.
  • the user walks from the location A of the shopping place to the location B in the direction of the arrow shown in FIG. 3, and the path that the user travels can be represented in accordance with the road segments in FIG. Among them, the road section passed by the user can be represented by a solid line, and the dotted road section represents a road section the user has not passed. Through the road sections of each solid line shown in FIG. 3, the path taken by the user from position A to position B can be determined.
  • the server can determine which road sections the target user has passed by locating the target user in real time. Therefore, when it is determined that the target user arrives at the current geographic location (that is, the current shopping area), the server can determine where the target user arrives at the geographic location based on the various road sections that the target user has traveled to reach the geographic location. The first path through.
  • the historical path that includes at least a part of these road segments can be determined from the historical paths of each user in history, and the similarity with the first path exceeds the preset
  • the path of similarity is regarded as the second path.
  • S103 For each commodity corresponding to the geographic location, determine the probability of each user passing the second path in history to purchase the commodity, and use it as the probability of the target user purchasing the commodity.
  • the server can, for each product corresponding to the geographic location, according to the probability of each user purchasing the product in history, and the probability of each user passing through each section of the second path when purchasing the product in history , To determine the probability of each user who passed the second path in history to purchase the product, and use it as the probability of the target user to purchase the product.
  • the server may determine the probability of each user purchasing the product in the history for each product in the shopping place in advance.
  • the server can determine the quantity of the commodity purchased and the quantity of all commodities purchased in the shopping place according to the historical shopping records of each user, and then determine that each user purchased the item in history. The probability of the product.
  • the server determines that 500 items of item A are sold based on the historical shopping records of each user in history, and the number of items sold in the shopping place is 8,000, then each user in the history purchased the item
  • the server may purchase all commodities corresponding to the geographic location of the commodity (that is, all commodities contained in the shopping area to which the commodity belongs) according to the quantity of the commodity purchased in the history The number of, determines the probability of each user buying the product in history.
  • the server determines the probability of each user buying each product in history based on the first method described above, the result of the product recommendation obtained, and the result of product recommendation determined by the second method described above. Probability of the product, the result of product recommendation should be consistent.
  • the first path and the second path are also exactly the same, that is, each historical path of each user in the history saved by the server There is a path that is exactly the same as the first path. Therefore, when determining the second path whose similarity to the first path exceeds the preset similarity, it may refer to determining a historical path that is exactly the same as the first path from each historical path as the second path. Correspondingly, when determining the probability of each user passing through the second path in history to purchase the commodity, it is actually determining the probability of each user passing through the first path in history buying the commodity.
  • a historical path whose similarity with the first path exceeds the preset similarity can be selected from each historical path as the first path.
  • Two paths wherein, for any historical path, if the degree of overlap between the road section included in the historical path and the road section included in the first path is higher, the similarity between the historical path and the first path is higher.
  • the server may also directly use the first path as the second path to determine the probability of each user who has passed the second path (that is, the first path) in history to purchase the commodity.
  • the server may use a vector to represent the determined second path, that is, it may determine the path vector corresponding to the second path based on each road segment traversed by the target user. Specifically, after dividing each walking passage in the shopping place into various road sections, each road section can be numbered. Correspondingly, the server may use the predetermined number of each road section to transform the determined second path to obtain the path vector corresponding to the second path.
  • the road sections in the process of dividing the road sections in the shopping place, can be numbered, and the road section sequence of the road sections in the shopping place can be determined according to the sequence of the numbers.
  • the server determines the second path, it can determine which road segments in the road segment sequence exist in the second path according to the number corresponding to each road segment included in the second path, and then determine the second path.
  • the path vector corresponding to the path is the path vector corresponding to the path.
  • each walkway in a shopping place into 10 sections, and assign a number to each section.
  • the server can sort the 10 road segments according to the number corresponding to each road segment to obtain the road segment sequence: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].
  • the server can determine that the road sections included in the second path are: road section 1, road section 3, road section 5, road section 6, and road section 7.
  • the second path can be expressed as: [1, 3, 5, 6, 7].
  • the server can determine which road segments in the sequence of road segments appear in the second path according to the second path, and then can determine the path vector corresponding to the second path: [1,0,1,0,1,1, 1,0,0,0].
  • the position marked as 1 means that the second path contains the road section corresponding to that position, and correspondingly, the position marked as 0 means that the second path does not contain the The road segment corresponding to the location.
  • the server can determine the probability of each user passing through the road segment when purchasing the product in history for each road segment in advance.
  • the server may determine the history of each user's purchase of the commodity according to the historical path of each user in the shopping place in the saved history, combined with the historical purchase record of each user in the shopping place in the history, Historical path. Then, the server can further count the number of road segments passed by these historical paths, and then can determine the probability of each user passing the road segment when purchasing the commodity in history.
  • the server may also determine the path vector corresponding to each historical path through which each user purchased the product in history according to the above-mentioned path vector determination method, and then determine the path vector corresponding to each historical path through which each user purchases the product in history. The probability of each road segment.
  • the server can determine the historical path vector corresponding to each historical path through which each user purchases the commodity in history according to the method in the above example. After determining each historical path vector, the server can further determine the path matrix formed by these historical path vectors.
  • the server may respectively determine the historical path vectors corresponding to the four historical paths for the four historical paths, and then combine the four historical path vectors to obtain the path matrix formed by the four historical path vectors.
  • the historical path vectors corresponding to the four historical paths are: [1,0,1,1,1,1,0,0,0], [0,0,1,0,0,1, 1,0,1,0], [1,0,1,0,1,0,1,0,0,1], [1,0,0,1,1,1,1,1,0, 0].
  • the server can use these four historical path vectors as row vectors to merge into a path matrix, which is as follows:
  • each column corresponds to a road segment. Therefore, for each road segment, the server can determine the column corresponding to the road segment in the path matrix according to the number of the road segment, and then according to all the columns in the The sum of the numerical values and the sum of all numerical values in the path matrix determine the probability of each user passing through the road section when purchasing the product in history.
  • the server may add up each column of the obtained path matrix to obtain a one-dimensional vector, and determine the sum obtained by adding the one-dimensional vector and each value in the one-dimensional vector The probability of each user passing through each road segment when purchasing the product in history, where each bit in the one-dimensional vector corresponds to a road segment.
  • the server after the server determines the path matrix, it can add up the values of each column of the path matrix to obtain: [3,0,3,2,3,3,4,1,1,1 ] This one-dimensional vector.
  • the server can add up each value in the one-dimensional vector to obtain a sum of 21, and then divide each bit in the one-dimensional vector by the sum of 21 to obtain a vector: [3/21,0,3/ 21,2/21,3/21,3/21,4/21,1/21,1/21,1/21].
  • each value in the one-dimensional vector is the probability corresponding to each road section. From the above process, it can be seen that adding up the values of each column in the path matrix is actually counting the number of times each road section appears in each determined historical path, and each of the above-mentioned one-dimensional vectors Adding the bit values is actually counting the total number of times each road section appears in each determined historical path. Therefore, in this way, the probability of each user passing through each road segment when purchasing the product in history is determined by this method. In fact, the method of calculating the number of times each user passed each road segment when purchasing the product in history determines that each user in the history purchased the product. The probability of passing through each section of the product is essentially the same.
  • the server For each commodity in the shopping place, the server has determined in advance the probability of each user buying the commodity in the history, and the probability of each road segment passed by each user in the history when purchasing the commodity. Therefore, after determining the second path, the server can, for each product corresponding to the geographic location, determine in advance the probability of each user purchasing the product in history, and each user's history when purchasing the product. The probability of a road section and the determined second path determine the probability of the target user to purchase the commodity.
  • the server may determine the sum of the probabilities of each user passing through these road sections when purchasing the commodity in history according to the road sections included in the second path, and compare the sum with the value of the sum of the probabilities of each user purchasing the product in history. The probability of the product is multiplied, and then the probability of the target user buying the product is determined according to the obtained product.
  • the server determines the path vector corresponding to the second path, it can multiply each bit in the path vector corresponding to the second path by the probability of the corresponding road segment to obtain the path vector corresponding to the second path.
  • the probability of the user passing the path when purchasing the product can be combined with the previously determined probability of each user purchasing the product in history to determine the probability of each user passing the second path in the history purchasing the product.
  • the server determines the probability that each user who has passed the second path in history purchases the product according to the above method.
  • the target user follows the first path.
  • the server may recommend each product in the geographic location to the user according to the determined probability that the target user will purchase each commodity when the target user arrives at the current geographic location along the first path.
  • S104 According to the determined probability that the target user purchases each commodity corresponding to the geographic location, determine the commodity to be recommended to the target user and recommend it to the target user.
  • the server may sort the commodities according to the determined probabilities of the commodities, and finally determine which commodities in the geographic location to recommend to the target user based on the obtained sorting results.
  • the server may recommend the product before the set ranking to the target user.
  • the recommended commodities may be displayed on the display screen set in the geographic location (ie, shopping area) for the target user to view;
  • the server may also recommend commodities corresponding to the geographic location to the target user in an application (App) by means of information push.
  • App application
  • the server can also recommend the product corresponding to the geographic location to the target user in other ways, which will not be illustrated here.
  • the server can respectively determine the product recommendation results for different target users according to the first path taken by different target users, and then can send the product information of the common products in these product recommendation results to the Display on the geographic location.
  • the application also provides a corresponding commodity recommendation device, as shown in FIG. 4.
  • FIG. 4 is a schematic diagram of a product recommendation device provided by this application, which specifically includes:
  • the first determining module 401 is configured to determine the current geographic location of the target user and the first path taken by the target user to reach the geographic location;
  • the second determining module 402 is configured to determine, according to the first path, a second path whose similarity with the first path exceeds a preset similarity;
  • the probability determination module 403 is configured to determine, for each product corresponding to the geographic location, the probability of each user passing the second path in history to purchase the product, and use it as the probability of the target user to purchase the product;
  • the recommendation module 404 is configured to determine the commodity recommended to the target user and recommend to the target user according to the determined probability of the target user purchasing each commodity corresponding to the geographic location.
  • the first path is composed of at least one road section
  • the second determining module 402 is configured to determine each road segment included in the first path; from each historical path of each user in history, determine a historical path that includes at least a part of each road segment , Taking the path whose similarity with the first path exceeds the preset similarity as the second path.
  • the probability determination module 403 is configured to, for each road section, determine the probability of each user passing through each road section when purchasing the commodity in history;
  • the probability determination module 403 is configured to determine the historically passing through the second path according to the probability of each user purchasing the product in history and the probability of each user passing through each section of the second path when purchasing the product in history. The probability that each user of the route purchases the product.
  • the probability determination module 403 is configured to determine each historical path through which each user purchases the commodity in history; for each historical path, determine the historical path according to the preset number of each road section Corresponding historical path vector; determine the path matrix corresponding to each historical path according to each determined historical path vector; determine the corresponding column of the road segment in the path matrix according to the number of each said road segment, and According to the sum of all the numerical values in the column and the sum of all the numerical values in the path matrix, the probability of each user passing through the road segment when purchasing the commodity in history is determined.
  • the probability determination module 403 is configured to determine the probability of each road segment included in the second path according to the probability of each user passing through each road segment included in the second path when purchasing the commodity in history. The sum of the probabilities; determining the product of the sum and the probability of each user purchasing the product in history; determining the probability of each user who has passed the second path in history purchasing the product according to the product.
  • the recommendation module 404 is configured to sort the commodities according to the determined probability that the target user purchases the commodities corresponding to the geographic location to obtain the sorting result; and to determine according to the sorting result Commodities to be recommended to the target user and recommended to the target user.
  • the target user carries an ultra-wideband UWB tag, and the UWB tag is used to locate the target user;
  • the first determining module 401 is configured to determine the current geographic location of the target user through an ultra-wideband UWB tag carried by the target user;
  • the first determining module 401 is configured to receive the pulse signal transmitted by the UWB tag through multiple signal receivers matched with the UWB tag, and according to the record of the pulse signal received by the multiple signal receivers Query each geographic location passed by the target user; and determine the path taken by the target user to reach the geographic location where the target user is currently located as the first path according to each geographic location.
  • the recommendation module 404 is configured to send the product information recommended to the target user to the display screen corresponding to the geographic location for display.
  • the embodiment of the present application also provides a computer-readable storage medium, the storage medium stores a computer program, and the computer program can be used to execute the above-mentioned method for recommending commodities.
  • the embodiment of the present application also provides a schematic structural diagram of the electronic device shown in FIG. 5.
  • the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory.
  • the processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, so as to implement the method recommended by the commodity.
  • this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc. That is to say, the execution body of the following processing flow is not limited to each logic unit, and can also Is a hardware or logic device.
  • a programmable logic device Programmable Logic Device, PLD
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression Language
  • AHDL Altera Hardware Description Language
  • HDCal JHDL
  • Lava Lava
  • Lola MyHDL
  • PALASM RHDL
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • the controller can be implemented in any suitable manner.
  • the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor.
  • controllers include but are not limited to the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the memory control logic.
  • controller in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for implementing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.
  • a typical implementation device is a computer.
  • the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.
  • the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.
  • the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.
  • processors CPU
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape/disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network perform tasks.
  • program modules can be located in local and remote computer storage media including storage devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种商品推荐的方法和装置，在该方法中可以确定目标用户当前所处的地理位置，以及该目标用户到达该地理位置所走过的第一路径（S101），并确定出与该第一路径相似度超过预设相似度的第二路径（S102），而后，可以针对该地理位置对应的每个商品，确定出历史上经过该第二路径的各用户购买该商品的概率，并作为该目标用户购买该商品的概率（S103），进而根据确定出的目标用户购买该地理位置对应的各商品的概率，向该目标用户推荐该地理位置对应的商品（S104）。通过分析目标用户所走过的路径，来确定目标用户按照该路径到达当前所处的地理位置时，该地理位置中的哪些商品可能是目标用户需要的，可以有效的提高商品的推荐准确率。

Description

商品推荐 技术领域
本申请涉及计算机领域，尤其涉及商品推荐。
背景技术
当前，线下购物场所通过商品打折、新品推荐、活动促销等营销方式，吸引用户进行商品购买，在提高用户购物体验的同时，也促进了购物场所的商品销量。
在线下购物场景中，用户是否会购买一个购物区域中的商品，除了跟用户自身的喜好有关外，还可能和用户在购物场所中的行进路线有关。例如，用户经过牛排区购买牛排后，到达红酒区域时购买红酒的几率也越大。而在现有技术中，购物场所向用户推荐的商品往往都是由购物场所的营销策略而定的，所以，实际推荐的商品可能并不是用户所需要的。因此，如何能够基于用户在购物场所中的行进路线，对用户进行商品推荐，提高商品推荐的准确率，则是一个亟待解决的问题。
发明内容
本申请实施例提供一种商品推荐的方法及装置。
本申请采用下述技术方案：
本申请提供了一种商品推荐的方法，包括：
确定目标用户当前所处的地理位置，以及所述目标用户到达所述地理位置所经过的第一路径；
根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径；
针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，并作为所述目标用户购买该商品的概率；
根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定出要推荐给所述目标用户的商品，并向所述目标用户推荐所述地理位置对应的商品。
本申请提供了一种商品推荐的装置，包括：
第一确定模块，用于确定目标用户当前所处的地理位置，以及所述目标用户到达所述地理位置所经过的第一路径；
第二确定模块，用于根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径；
概率确定模块，用于针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，并作为所述目标用户购买该商品的概率；
推荐模块，用于根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定向所述目标用户推荐的商品并向所述目标用户推荐所述地理位置对应的商品。
本申请提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述商品推荐的方法。
本申请提供了一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现上述商品推荐的方法。
本申请采用的上述至少一个技术方案能够达到以下有益效果：
从上述方法中可以看出，该方法可以通过分析目标用户所经过的路径，来确定目标用户按照该路径到达当前所处的地理位置时，该地理位置中的哪些商品可能是目标用户需要的，即，实现了基于目标用户实际行走路线来确定向目标用户推荐的商品，从而有效的提高了商品的推荐准确率。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1为本申请实施例中一种商品推荐的方法的流程示意图；
图2为本申请实施例提供的将购物场所的各行走通道进行路段划分的示意图；
图3为本申请实施例提供的通过划分的各路段表示用户所经过的路径的示意图；
图4为本申请提供的一种商品推荐的装置示意图；
图5为本申请提供的对应于图1的电子设备示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请具体实施例及相应的附图对本申请技术方案进行清楚、完整地描述。显然，所描述的实施例仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
用户在线下购物场景中，可能会根据已经经过的各地理位置，来确定在当前地理位置时应该购买哪些商品。例如，用户经过生鲜区购买了肉馅后，再经过调料区购买酱油、醋等调味料的概率较大；再例如，用户经过服饰区购买衣服后，再经过鞋区购买鞋的概率较大。因此，在本申请中，可以基于用户所经过的路径，来确定用户处于当前地理位置时，购买该地理位置中哪些商品的概率较高，进而向用户进行商品推荐。
其中，本申请中提到的地理位置可以是实际的地理坐标，也可以指某一场所中的区域，如，购物场所中的购物区域，亦或是指实际的建筑，如，购物商厦、超市、百货商场等。而无论地理位置具体为哪种情况，本申请提供的商品推荐方法均可适用，即，可以基于用户在线下购物时所经过的各百货商场、超市、商铺等，来确定应向该用户推荐该用户当前所处的购物商场中的哪些商品，也可以基于用户在购物场所中进行购物所经过的购物区域，来确定应向该用户推荐该用户当前所处购物区域中的哪些商品。而由于将本申请提供的商品推荐的方法应用在各种场景中时具体过程基本相似，所以，为了方便进行描述，下面将仅以用户在购物场所中进行线下购物的场景为例，来对本申请提供的商品推荐的方法进行说明。
以下结合附图，详细说明本申请各实施例提供的技术方案。
图1为本申请实施例中一种商品推荐的方法的流程示意图，包括以下步骤：
S101：确定目标用户当前所处的地理位置，以及所述目标用户到达所述地理位置所经过的第一路径。
在实际场景中，购物场所通常包含有多个购物区域，如，在一个商场(即购物场所)中，通常设有酒水区、生鲜区、蔬菜区、水果区、服饰区等购物区域。而为了能够基于用户在购物场所中行走的路线，来确定购物区域中的哪些商品可能是用户需要的，在一实施例中， 可以实时监测目标用户在购物场所中所处的位置，以确定目标用户当前所处的地理位置，同时可以确定目标用户到达该地理位置时所经过的第一路径。这里提到的地理位置可以指该购物场所中的购物区域。而这里提到的目标用户是一个普通的用户，之所以称之为目标用户，主要用于在时间上将当前的用户，与后续提到的历史上的各用户进行区分，其本身并没有特殊的含义。
在本申请实施例中，包括多种确定目标用户当前所处的地理位置以及目标用户到达该地理位置时所经过的路径的方式。在一实施例中，目标用户处于购物场所时，可以通过移动终端(如手机、智能手环、平板电脑等设备)连接该购物场所中的无线保真(Wireless Fidelity，WiFi)，购物场所可以通过指定设备，基于WiFi定位，确定目标用户当前所处的地理位置以及目标用户到达该地理位置时所经过的第一路径。
在另一实施例中，目标用户可以携带有超宽带(Ultra Wideband，UWB)标签，在购物场所中设有配套的多个信号接收器，用于接收UWB标签发射的脉冲信号。因此，目标用户携带有该UWB标签在购物场所中进行购物时，购物场所的指定设备可以根据该购物场所中设置的多个信号接收器，接收该UWB标签所发射的脉冲信号，从而实现对目标用户所处位置的实时定位以及记录。在一实施例中，UWB标签可以设置在目标用户携带的移动设备上，也可以设置在购物场所向用户提供的购物袋、购物篮、购物车上。
在确定目标用户所经过的路径时，该购物场所的指定设备可以根据该目标用户在该购物场所中所经过的各地理位置的记录，确定该目标用户到达当前所处的地理位置时所经过的第一路径。
除了上述提到的两种方式外，还可以通过其他的方式来确定目标用户当前所处的地理位置，以及目标用户到达该地理位置时所经过的路径，在此不进行详细举例说明了。
在一实施例中，上述提到的用于确定目标用户当前所处的地理位置以及所经过的第一路径的指定设备可以是设置在购物场所中的用于对目标用户进行定位的设备，如电脑等，也可以是购物场所用于对目标用户进行定位的服务器。为了便于后续描述，下面将仅以服务器为执行主体，对本申请提供的商品推荐的方法进行说明。
上述提到的第一路径，即为目标用户到达当前所处的地理位置时所经过的实际路径，之所以称之为第一路径，主要用于跟后续提到的第二路径进行区分，所以，本申请中提到的“第一”和“第二”没有其他的特殊含义。
S102：根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径。
在确定出第一路径后，服务器可以从保存的历史上各用户在该购物场所经过的各历史路径中，确定与该第一路径的相似度超过预设相似度的第二路径。在一实施例中，服务器可以确定出该第一路径中所包含的各路段，也即用户到达当前所处的地理位置时在该购物场所中所经过的各路段。其中，这里提到的路段可以是事先根据该购物场所的实际布局，将该购物场所中的各行走通道以路段为单位进行划分得到的。对于每个行走通道来说，该行走通道可以由至少一个路段组成。整个购物场所中的各行走通道可由各路段进行表示，如图2所示。
图2为本申请实施例提供的将购物场所的各行走通道进行路段划分的示意图。
购物场所中设有多个购物区域，在购物区域之间，设有行走通道。在一实施例中，可以路段为单位，将行走通道进行划分，如图2中的各线段即为划分出的各路段。而从图2中可以看出，每个行走通道可由至少一个路段来进行表示。在实际应用中，用户在购物场所中所经过的路径，均可由图2中所示的各路段进行表示，如图3所示。
图3为本申请实施例提供的通过划分的各路段表示用户所经过的路径的示意图。
在图3中，用户从购物场所的位置A按照如图3所示的箭头方向走到位置B，可将用户所经过的路径按照如图3中的各路段进行表示。其中，用户经过的路段可以用实线进行表示，而虚线的路段则表示用户未经过的路段。通过图3中所示的各实线的路段，可以确定出用户从位置A到位置B所经过的路径。
在步骤S101中提到的确定目标用户到达当前地理位置所经过的路径过程中，服务器可以通过对目标用户进行实时定位，确定目标用户经过了哪些路段。从而在确定出目标用户到达当前所处的地理位置(即当前所处的购物区域)时，服务器可以根据该目标用户到达该地理位置所经过的各路段，确定出目标用户到达该地理位置时所经过的第一路径。
在确定出该第一路径中包含的各路段后，可以从历史上各用户的各历史路径中确定出包含这些路段中至少一部分的历史路径，并将与该第一路径的相似度超过预设相似度的路径作为第二路径。
S103：针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，并作为所述目标用户购买该商品的概率。
在确定第二路径后，服务器可以针对该地理位置对应的每个商品，根据历史上各用户购买该商品的概率，以及历史上各用户购买该商品时经过该第二路径中每个路段的概率，来确定历史上经过该第二路径的各用户购买该商品的概率，并作为该目标用户购买该商品的 概率。
在本申请实施例中，服务器可以预先针对该购物场所中的每个商品，确定出历史上各用户购买该商品的概率。在一实施例中，针对每个商品，服务器可以根据各用户的历史购物记录，确定出该商品被购买的数量以及该购物场所中所有商品被购买的数量，进而确定出历史上各用户购买该商品的概率。
例如，对于商品A来说，服务器根据历史上各用户的历史购物记录，确定出售出了500个商品A，而该购物场所中所有商品的售出数量为8000，则历史上各用户购买该商品A的概率即为500/8000＝6.25％。
在另一实施例中，服务器可以针对每个商品，根据历史上该商品被购买的数量，以及该商品所属的地理位置对应的所有商品(即该商品所属购物区域所包含的所有商品)被购买的数量，确定出历史上各用户购买该商品的概率。
例如，对于商品B来说，服务器根据历史上各用户的历史购物记录，确定出售出了300个商品B，而商品B所属的购物区域所包含的所有商品的售出数量为6000，则历史上各用户购买该商品B的概率即为300/6000＝5％。
需要说明的是，服务器无论通过上述哪种方式来确定历史上各用户购买每个商品的概率，其最终得出的商品推荐结果并不会出现差别。换句话说，服务器基于上述第一种方式所确定出的历史上各用户购买每个商品的概率，得到的商品推荐结果，和基于上述第二种方式所确定出的历史上各用户购买每个商品的概率，得到的商品推荐结果应是一致的。
在一实施例中，若第二路径包含的路段与第一路径中包含的路段完全相同，则第一路径和第二路径也完全相同，也即，服务器保存的历史上各用户的各历史路径中存在与该第一路径完全相同的路径。因此，在确定与该第一路径的相似度超过预设相似度的第二路径时，可以是指从各历史路径中确定出与该第一路径完全相同的历史路径作为第二路径。相应的，在确定历史上经过第二路径的各用户购买该商品的概率时，实际上就是确定历史上经过该第一路径的各用户购买该商品的概率。
在另一实施例中，各历史路径中不存在与该第一路径完全相同的路径，则可以从各历史路径中，选取与该第一路径的相似度超过预设相似度的历史路径作为第二路径。其中，对于任意一个历史路径，若是该历史路径中包含的路段与该第一路径中包含的路段的重合度越高，则该历史路径与该第一路径的相似度越高。在一实施例中，服务器也可以将该第一路径直接作为第二路径，来确定历史上经过该第二路径(也即第一路径)的各用户购买该 商品的概率。
在一实施例中，服务器可以将确定出的第二路径用向量进行表示，即，可以基于目标用户所经过的各路段，确定出该第二路径所对应的路径向量。具体的，在将购物场所中的各行走通道划分成各路段后，可以将各路段进行编号。相应的，服务器可以利用预先确定出的各路段的编号，将确定出的第二路径进行转化，得到该第二路径对应的路径向量。
其中，在对购物场所中的各路段进行划分的过程中，可以将各路段进行编号，并按照编号的顺序，确定出该购物场所中各路段的路段序列。而服务器在确定出第二路径后，可以根据该第二路径中包含的各路段所对应的编号，确定出该路段序列中哪些路段是存在于该第二路径中的，进而确定出该第二路径所对应的路径向量。
例如，将购物场所中的各行走通道划分成10个路段，并为各路段分配编号。服务器可以根据各路段对应的编号，对这10个路段进行排序，得到路段序列：[1，2，3，4，5，6，7，8，9，10]。服务器可以确定出第二路径中所包含的路段为：路段1、路段3、路段5、路段6、路段7。该第二路径可以表示为：[1，3，5，6，7]。服务器可以根据该第二路径，确定出路段序列中的哪些路段在该第二路径中出现，进而可以确定出该第二路径对应的路径向量：[1,0,1,0,1,1,1,0,0,0]。
在该第二路径向量中，被标为1的位置，表示该第二路径中包含有该位置所对应的路段，相应的，被标为0的位置，表示该第二路径中不包含有该位置所对应的路段。
对于该购物场所中的每个商品来说，服务器可以预先针对每个路段，确定出历史上各用户购买该商品时经过该路段的概率。在一实施例中，服务器可以根据保存的历史上各用户在该购物场所中的各历史路径，结合历史上各用户在购物场所中的历史购买记录，确定出历史上各用户购买该商品所经过的历史路径。而后，服务器可以进一步地统计出这些历史路径中各路段被经过的数量，进而可以确定出历史上各用户购买该商品时经过该路段的概率。
例如，服务器确定出历史上各用户购买该商品所经过的各历史路径后，进一步统计出在这些历史路径中，路段1出现了30次，路段2出现了32次，路段3出现了40次，路段4出现了13次，路段5出现了8次。服务器可以根据这5个路段出现的总次数，以及路段1出现的次数，确定出历史上各用户购买该商品时经过该路段1的概率为：30/123＝24.9％。其他路段同理。
在一实施例中，服务器也可以按照上述路径向量的确定方法，确定出历史上各用户购买 该商品所经过的各历史路径所对应的路径向量，进而确定出历史上各用户购买该商品时经过各路段的概率。
具体的，针对每个商品，服务器可以按照上述示例中的方式，确定出历史上各用户购买该商品所经过的各历史路径所对应的历史路径向量。而在确定出各历史路径向量后，服务器可以进一步地确定出由这些历史路径向量所构成的路径矩阵。
例如，历史上各用户购买商品B所经过的历史路径一共有四条。服务器可以针对这四条历史路径，分别确定出这四条历史路径所对应的历史路径向量，进而通过将这四个历史路径向量进行组合，得到这四个历史路径向量所构成的路径矩阵。其中，这四个历史路径对应的历史路径向量分别为：[1,0,1,1,1,1,1,0,0,0]、[0,0,1,0,0,1,1,0,1,0]、[1,0,1,0,1,0,1,0,0,1]、[1,0,0,1,1,1,1,1,0,0]。服务器可以将这四个历史路径向量作为行向量，以合并成一个路径矩阵，该路径矩阵如下：
Figure PCTCN2019125255-appb-000001
从该路径矩阵中可以看出，每一列均对应一个路段，所以，针对每个路段，服务器可以根据该路段的编号，确定出该路径矩阵中该路段所对应的列，进而根据该列中所有数值的和值，以及该路径矩阵中所有数值的和值，确定出历史上各用户购买该商品时经过该路段的概率。
具体的，服务器可以将得到的路径矩阵的每列进行加和，得到一个一维的向量，并通过该一维向量，以及该一维向量中每位数值进行加和所得到的和值，确定历史上各用户购买该商品时经过各路段的概率，其中，该一维向量中的每一位均对应一个路段。
在上述实施例中，服务器确定出该路径矩阵后，可以将该路径矩阵的每列数值进行加和，进而得到：[3,0,3,2,3,3,4,1,1,1]这个一维向量。服务器可以将该一维向量中的每位数值进行加和，得到和值21，进而将该一维向量中的每位除以该和值21，得到向量：[3/21,0,3/21,2/21,3/21,3/21,4/21,1/21,1/21,1/21]。
其中，该一维向量中的每个数值，即为各路段所对应的概率。而从上述过程中可以看出，将路径矩阵中的各列数值进行加和，实际上就是在统计各路段在确定出的各历史路径中所出现的次数，而将上述一维向量中的每位数值进行加和，实际上就是在统计各路段在确定 出的各历史路径中所出现的总次数。所以，通过这种方式确定历史上各用户购买该商品时经过各路段的概率，实际上与上述通过统计历史上各用户购买该商品时经过各路段的次数的方式来确定历史上各用户购买该商品时经过各路段的概率，本质上是相同的。
由于服务器事先已针对该购物场所中的每个商品，确定出历史上各用户购买该商品的概率，以及历史上各用户购买该商品时经过的每个路段的概率。所以，服务器在确定出该第二路径后，可以针对该地理位置所对应的每个商品，根据事先确定出的历史上各用户购买该商品的概率、历史上各用户购买该商品时经过的每个路段的概率，以及确定出的该第二路径，确定该目标用户购买该商品的概率。
在一实施例中，服务器可以根据该第二路径中所包含的各路段，确定出历史上各用户购买该商品时经过这些路段的概率的和值，将该和值与历史上各用户购买该商品的概率进行相乘，进而根据得到的乘积确定出该目标用户购买该商品的概率。
在一实施例中，若服务器确定出了该第二路径所对应的路径向量，则可以将该第二路径对应路径向量中的每一位乘以与之对应的路段的概率，得到历史上各用户购买该商品时经过该路径的概率，进而可以结合事先确定出的历史上各用户购买该商品的概率，确定出历史上经过该第二路径的各用户购买该商品的概率。
需要说明的是，若是第一路径和第二路径完全相同，则服务器按照上述方法确定出的历史上经过该第二路径的各用户购买该商品的概率，实际上是目标用户按照该第一路径到达当前所处的地理位置时，购买该商品的概率。相应的，服务器可以根据确定出的该目标用户按照该第一路径到达当前所处的地理位置时购买各商品的概率，向用户推荐该地理位置的各商品。
S104：根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定出要推荐给所述目标用户的商品并向所述目标用户推荐。
服务器可以根据确定出的各商品的概率，对各商品进行排序，最终基于得到的排序结果，确定向该目标用户推荐该地理位置中的哪些商品。在一实施例中，在得到排序结果后，服务器可以将位于设定排位之前的商品推荐给该目标用户。
在一实施例中，服务器在确定出需要推荐给目标用户的商品后，可以将推荐的各商品显示在设置于该地理位置(即，购物区域)的显示屏中，供该目标用户进行查看；服务器也可以通过信息推送的方式，在应用(Application，App)中向该目标用户推荐该地理位置对应的商品。当然，服务器还可以通过其他的方式，向该目标用户推荐该地理位置对应的商 品，在此就不一一举例说明了。
需要说明的是，在实际应用中，该目标用户当前所处的地理位置中可能还存在其他的目标用户，而由于各目标用户到达该地理位置所经过的第一路径可能不尽相同，所以，基于不同目标用户所经过的第一路径所确定出的商品推荐结果可能也不尽相同。
对于这种情况来说，服务器可以针对不同目标用户所经过的第一路径，分别确定出针对不同目标用户的商品推荐结果，进而可以将这些商品推荐结果中共有商品的商品信息发送给设置于该地理位置上的显示屏进行显示。
从上述方法中可以看出，通过分析目标用户所经过的路径，来确定目标用户按照该路径到达当前所处的地理位置时，该地理位置中的哪些商品可能是目标用户需要的，即，实现了基于目标用户实际行走路线来确定向目标用户推荐的商品，从而有效的提高了商品的推荐准确率。
以上为本申请的一个或多个实施例提供的商品推荐的方法，基于同样的思路，本申请还提供了相应的商品推荐的装置，如图4所示。
图4为本申请提供的一种商品推荐的装置示意图，具体包括：
第一确定模块401，用于确定目标用户当前所处的地理位置，以及所述目标用户到达所述地理位置所经过的第一路径；
第二确定模块402，用于根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径；
概率确定模块403，用于针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，并作为所述目标用户购买该商品的概率；
推荐模块404，用于根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定向所述目标用户推荐的商品并向所述目标用户推荐。
所述第一路径由至少一个路段构成；
可选地，所述第二确定模块402用于，确定所述第一路径中所包含的各路段；从历史上各用户的各历史路径中，确定包含所述各路段中至少一部分的历史路径，将与所述第一路径的相似度超过预设相似度的路径作为第二路径。
可选地，所述概率确定模块403用于，预先针对每个路段，确定历史上各用户购买该商品时经过每个所述路段的概率；
所述概率确定模块403用于，根据历史上各用户购买该商品的概率以及历史上各用户购买该商品时经过所述第二路径中的每个路段的概率，确定历史上经过所述第二路径的各用户购买该商品的概率。
可选地，所述概率确定模块403用于，确定历史上各用户购买该商品所经过的各历史路径；针对每个历史路径，按照预设的每个所述路段的编号，确定该历史路径所对应的历史路径向量；根据确定出的各历史路径向量，确定所述各历史路径对应的路径矩阵；根据每个所述路段的编号，确定所述路径矩阵中该路段所对应的列，并根据所述列中所有数值的和值，以及所述路径矩阵中所有数值的和值，确定历史上各用户购买该商品时经过该路段的概率。
可选地，所述概率确定模块403用于，根据历史上各用户购买该商品时经过所述第二路径中包含的每个路段的概率，确定所述第二路径中包含的每个路段的概率的和值；确定所述和值与历史上各用户购买该商品的概率的乘积；根据所述乘积确定历史上经过所述第二路径的各用户购买该商品的概率。
可选地，所述推荐模块404用于，按照确定出的所述目标用户购买所述地理位置对应的各商品的概率，将各商品进行排序，得到排序结果；根据所述排序结果，确定出要推荐给所述目标用户的商品并向所述目标用户推荐。
所述目标用户携带有超宽带UWB标签，所述UWB标签用于对所述目标用户进行定位；
可选地，所述第一确定模块401用于，通过所述目标用户携带的超宽带UWB标签，确定所述目标用户当前所处的地理位置；
所述第一确定模块401用于，通过与所述UWB标签配套的多个信号接收器接收所述UWB标签发射的脉冲信号，，根据所述多个信号接收器所接收到的脉冲信号的记录，查询所述目标用户经过的各地理位置；根据查询出的各地理位置，确定所述目标用户到达当前所处地理位置所经过的路径作为所述第一路径。
可选地，所述推荐模块404用于，将向所述目标用户推荐的商品信息发送至所述地理位置对应的显示屏中显示。
本申请实施例还提供了一种计算机可读存储介质，该存储介质存储有计算机程序，计算机程序可用于执行上述商品推荐的方法。
本申请实施例还提供了图5所示的电子设备的示意结构图。如图5所述，在硬件层面， 该电子设备包括处理器、内部总线、网络接口、内存以及非易失性存储器，当然还可能包括其他业务所需要的硬件。处理器从非易失性存储器中读取对应的计算机程序到内存中然后运行，以实现上述商品推荐的方法。当然，除了软件实现方式之外，本说明书并不排除其他实现方式，比如逻辑器件亦或软硬件结合的方式等等，也就是说以下处理流程的执行主体并不限定于各个逻辑单元，也可以是硬件或逻辑器件。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算 机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本申请时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算 机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体，可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带/磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本申请可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实 施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (11)

  1. 一种商品推荐的方法，包括：
    确定目标用户当前所处的地理位置，以及所述目标用户到达所述地理位置所经过的第一路径；
    根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径；
    针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，并作为所述目标用户购买该商品的概率；
    根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定出要推荐给所述目标用户的商品，并向所述目标用户推荐。
  2. 如权利要求1所述的方法，所述第一路径包括至少一个路段；
    根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径，包括：
    确定所述第一路径中所包含的所述至少一个路段；
    从历史上各用户的各历史路径中，确定包含所述至少一个路段中至少一部分的一个或多个历史路径，并将与所述第一路径的相似度超过预设相似度的历史路径作为所述第二路径。
  3. 如权利要求2所述的方法，预先针对每个路段，确定历史上各用户购买该商品时经过每个路段的概率；
    针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，包括：
    根据历史上各用户购买该商品的概率以及历史上各用户购买该商品时经过所述第二路径中的每个路段的概率，确定历史上经过所述第二路径的各用户购买该商品的概率。
  4. 如权利要求3所述的方法，预先针对每个所述路段，确定历史上各用户购买该商品时经过每个路段的概率，包括：
    确定历史上各用户购买该商品所经过的每个历史路径；
    针对每个历史路径，按照预设的每个路段的编号，确定该历史路径所对应的历史路径向量；
    根据确定出的各历史路径向量，确定该历史路径对应的路径矩阵；
    根据每个路段的编号，确定所述路径矩阵中该路段所对应的列，并根据所述列中所有数值的和值，以及所述路径矩阵中所有数值的和值，确定历史上各用户购买该商品时经过该路段的概率。
  5. 如权利要求3所述的方法，根据历史上各用户购买该商品的概率以及历史上各用户购买该商品时经过所述第二路径中的每个路段的概率，确定历史上经过所述第二路径的各用户购买该商品的概率，包括：
    根据历史上各用户购买该商品时经过所述第二路径中包含的每个路段的概率，确定所述第二路径中包含的每个路段的概率的和值；
    确定所述和值与历史上各用户购买该商品的概率的乘积；
    根据所述乘积确定历史上经过所述第二路径的各用户购买该商品的概率。
  6. 如权利要求1所述的方法，根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定出要推荐给所述目标用户的商品并向所述目标用户推荐，包括：
    按照确定出的所述目标用户购买所述地理位置对应的各商品的概率，将各商品进行排序，得到排序结果；
    根据所述排序结果，确定出要推荐给所述目标用户的商品并向所述目标用户推荐。
  7. 如权利要求1所述的方法，所述目标用户携带有超宽带UWB标签，所述UWB标签用于对所述目标用户进行定位；
    确定所述目标用户当前所处的地理位置，包括：
    通过所述目标用户携带的超宽带UWB标签，确定所述目标用户当前所处的地理位置；
    确定所述目标用户到达所述地理位置所经过的所述第一路径，包括：
    通过与所述UWB标签配套的多个信号接收器接收所述UWB标签发射的脉冲信号，
    根据所述多个信号接收器所接收到的脉冲信号的记录，查询所述目标用户经过的各地理位置；
    根据查询出的各所述地理位置，确定所述目标用户到达当前所处地理位置所经过的路径作为所述第一路径。
  8. 如权利要求6所述的方法，根据所述排序结果，确定出要推荐给所述目标用户的商品并向所述目标用户推荐，包括：
    将向所述目标用户推荐的商品的商品信息发送至所述地理位置对应的显示屏中显示。
  9. 一种商品推荐的装置，包括：
    第一确定模块，用于确定目标用户当前所处的地理位置，以及所述目标用户到达所述地理位置所经过的第一路径；
    第二确定模块，用于根据所述第一路径，确定与所述第一路径的相似度超过预设相似度的第二路径；
    概率确定模块，用于针对所述地理位置对应的每个商品，确定历史上经过所述第二路径的各用户购买该商品的概率，并作为所述目标用户购买该商品的概率；
    推荐模块，用于根据确定出的所述目标用户购买所述地理位置对应的各商品的概率，确定向所述目标用户推荐的商品并向所述目标用户推荐。
  10. 一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现上述权利要求1～8任一项所述的方法。
  11. 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现上述权利要求1～8任一项所述的方法。
PCT/CN2019/125255 2019-05-06 2019-12-13 商品推荐 Ceased WO2020224263A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910372329.3 2019-05-06
CN201910372329.3A CN110163666B (zh) 2019-05-06 2019-05-06 一种商品推荐的方法及装置

Publications (1)

Publication Number Publication Date
WO2020224263A1 true WO2020224263A1 (zh) 2020-11-12

Family

ID=67633474

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/125255 Ceased WO2020224263A1 (zh) 2019-05-06 2019-12-13 商品推荐

Country Status (2)

Country Link
CN (1) CN110163666B (zh)
WO (1) WO2020224263A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110163666B (zh) * 2019-05-06 2025-04-29 北京三快在线科技有限公司 一种商品推荐的方法及装置
CN110751501B (zh) * 2019-09-06 2023-08-22 平安科技（深圳）有限公司 商品导购方法、装置、设备及存储介质
CN111222822B (zh) * 2020-01-07 2023-04-07 贵阳货车帮科技有限公司 货源推送方法、装置、电子设备及可读存储介质
CN111563792B (zh) * 2020-03-31 2023-10-31 北京奇艺世纪科技有限公司 商品的划分、推荐方法、装置、电子设备和存储介质
CN111985994A (zh) * 2020-08-06 2020-11-24 上海博泰悦臻电子设备制造有限公司 商品推荐方法及相关设备
CN112102039B (zh) * 2020-09-23 2024-05-28 杭州米雅信息科技有限公司 物品推送方法、计算机系统及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101006445A (zh) * 2004-08-23 2007-07-25 株式会社流通技术 基于rfid的购物模式分析系统和方法
CN202472743U (zh) * 2012-01-13 2012-10-03 广州华迅网络科技有限公司 一种基于标签定位的商场购物向导系统
US20130103539A1 (en) * 2011-10-25 2013-04-25 International Business Machines Corporation Intelligent shopping assistant
CN108280145A (zh) * 2017-12-29 2018-07-13 五八有限公司 一种基于地理位置的个性化推荐方法、设备及存储介质
CN108694658A (zh) * 2018-07-31 2018-10-23 深圳春沐源控股有限公司 一种商品信息推送方法、相关装置及存储介质
CN109615425A (zh) * 2018-12-04 2019-04-12 北京羽扇智信息科技有限公司 一种产品推荐方法、装置、电子设备及存储介质
CN110163666A (zh) * 2019-05-06 2019-08-23 北京三快在线科技有限公司 一种商品推荐的方法及装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004227162A (ja) * 2003-01-21 2004-08-12 Nissan Motor Co Ltd 経路案内システム及び経路案内方法
JP4254392B2 (ja) * 2003-07-18 2009-04-15 トヨタ自動車株式会社 商品販売数予測装置と商品販売数予測装置の動作方法とそのためのプログラム
US9830638B2 (en) * 2012-11-30 2017-11-28 At&T Intellectual Property I, L.P. Managing vendor inventory information and shopping navigation routes based upon shopping list contents
US9652797B2 (en) * 2013-01-18 2017-05-16 24/7 Customer, Inc. Intent prediction based recommendation system using data combined from multiple channels
US9767498B2 (en) * 2013-01-31 2017-09-19 Lf Technology Development Corporation Ltd. Virtual purchasing assistant
US10296928B1 (en) * 2013-11-12 2019-05-21 Coherent Path Inc. System and methods for measuring and influencing customer trajectory within a product space
JP2016076047A (ja) * 2014-10-04 2016-05-12 ゲヒルン株式会社 商品推薦システム、商品推薦方法、商品推薦システム用プログラム
US10679274B2 (en) * 2016-09-16 2020-06-09 Conduent Business Services, Llc Method and system for data processing to recommend list of physical stores in real-time
CN108429865B (zh) * 2017-02-13 2020-10-16 中国移动通信集团广东有限公司 一种产品推荐处理方法及装置
CN108665329B (zh) * 2017-03-29 2024-09-24 北京京东尚科信息技术有限公司 一种基于用户浏览行为的商品推荐方法
CN107424273A (zh) * 2017-07-28 2017-12-01 杭州宇泛智能科技有限公司 一种无人超市的管理方法
CN108694655A (zh) * 2018-07-10 2018-10-23 淘度客电子商务股份有限公司 一种基于眼球轨迹数据采集的商品推荐方法
CN109146559A (zh) * 2018-08-01 2019-01-04 夏颖 一种用于商业综合体的商品导购系统
CN111507796A (zh) * 2020-04-07 2020-08-07 桂林电子科技大学 一种基于知识图谱的网上商城商品推荐方法
US11631122B2 (en) * 2020-09-23 2023-04-18 Shopify Inc. Computer-implemented systems and methods for in-store route recommendations
CN112308666A (zh) * 2020-10-26 2021-02-02 福建菩泰网络科技有限公司 一种网上商城商品的推荐方法及其系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101006445A (zh) * 2004-08-23 2007-07-25 株式会社流通技术 基于rfid的购物模式分析系统和方法
US20130103539A1 (en) * 2011-10-25 2013-04-25 International Business Machines Corporation Intelligent shopping assistant
CN202472743U (zh) * 2012-01-13 2012-10-03 广州华迅网络科技有限公司 一种基于标签定位的商场购物向导系统
CN108280145A (zh) * 2017-12-29 2018-07-13 五八有限公司 一种基于地理位置的个性化推荐方法、设备及存储介质
CN108694658A (zh) * 2018-07-31 2018-10-23 深圳春沐源控股有限公司 一种商品信息推送方法、相关装置及存储介质
CN109615425A (zh) * 2018-12-04 2019-04-12 北京羽扇智信息科技有限公司 一种产品推荐方法、装置、电子设备及存储介质
CN110163666A (zh) * 2019-05-06 2019-08-23 北京三快在线科技有限公司 一种商品推荐的方法及装置

Also Published As

Publication number Publication date
CN110163666A (zh) 2019-08-23
CN110163666B (zh) 2025-04-29

Similar Documents

Publication Publication Date Title
WO2020224263A1 (zh) 商品推荐
CN110033156B (zh) 一种业务活动效果的确定方法及装置
US11783324B2 (en) Resource sharing method, apparatus, and device
US9858610B2 (en) Product recommendation based on geographic location and user activities
US9595062B2 (en) Methods and systems for rendering an optimized route in accordance with GPS data and a shopping list
US9773286B2 (en) System for providing extensible location-based services
CN110413877A (zh) 一种资源推荐方法、装置及电子设备
TW202008257A (zh) 後付費交易資料處理方法、裝置、處理設備、及伺服器
US20200051114A1 (en) Method and device for processing electronic coupon link
US20160004725A1 (en) Displaying region-based search results
CN110060085B (zh) 一种解析广告目标人群线下分布的方法、系统及设备
CN110110244A (zh) 一种融合多源信息的兴趣点推荐方法
US20240281835A1 (en) Systems and methods for predicting consumer spending behavior based on historical transaction activity progressions
CN107506376A (zh) 获取区域内信息点数据的客户端
CA2975713A1 (en) Method to stop serving re-targeting ads
US20200386565A1 (en) Predicting prime locations for mobile assets
JP6814115B2 (ja) 特定装置、特定方法および特定プログラム
CN110942338A (zh) 一种营销赋能策略的推荐方法、装置和电子设备
CN114239947A (zh) 基于多特征的店铺销售效果预测方法及装置
CN107577660B (zh) 类目信息识别方法、装置及服务器
US20130304539A1 (en) User recommendation method and device
WO2018095307A1 (zh) 一种评价信息的发布方法及装置
CN110458651A (zh) 商户识别方法、装置、设备及存储介质
US9070094B2 (en) Techniques for optimizing a shopping agenda
CN116485391A (zh) 支付推荐处理方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19928190

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19928190

Country of ref document: EP

Kind code of ref document: A1