A user data sharing method for a furniture platform and related devices
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN HESHECASA TECH CO LTD
- Filing Date
- 2025-03-18
- Publication Date
- 2026-07-03
Smart Images
Figure CN120198200B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of furniture platform technology, and more specifically, to a user data sharing method and related equipment for a furniture platform. Background Technology
[0002] Furniture platform technology is a database platform that integrates technologies such as database management, recommendation systems, big data, security, and privacy protection. It is used for users to share data and order furniture. By collecting basic data on registered users and the furniture on the platform, and combining data analysis algorithms with users' basic information, the furniture platform recommends customized furniture to users. With the development of furniture platforms, furniture recommendations have become more efficient and accurate for each user.
[0003] Furniture platform user data sharing involves sharing basic information from user registration, as well as data such as furniture ordering and browsing history during platform usage. This data sharing can improve the accuracy of furniture recommendations for each registered user and reduce data clutter. However, current technologies only allow for furniture recommendations based on a target user's registration information, ordering and browsing history, neglecting recommendations for furniture that a target user might order even without prior ordering or browsing history. Therefore, achieving personalized shared recommendations for potential furniture orders from target users is a pressing issue that needs to be addressed. Summary of the Invention
[0004] This application provides a user data sharing method and related equipment for a furniture platform, which can realize personalized sharing and recommendation of potential furniture orders from target users.
[0005] In a first aspect, this application provides a method for sharing user data on a furniture platform, comprising the following steps:
[0006] Obtain shared data from a specified furniture platform, and determine the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data;
[0007] Based on all furniture feature vectors, determine the set of convergent values for each user's feature vector, and determine the degree of synergy between two corresponding users based on every two sets of convergent values;
[0008] Determine the target user's hot-start furniture decision domain based on all synergies;
[0009] Select one type of furniture in the hot-start furniture decision domain, determine the shared predicted value of this type of furniture based on all the synergies between the target user and other users, determine the adjustment coefficient of the target user for this type of furniture based on the shared predicted value and the target user's convergent value set, and continue to determine the adjustment coefficient of the target user for the remaining furniture in the hot-start furniture decision domain;
[0010] The furniture recommendation information for the target user is adjusted based on the adjustment coefficient for each type of furniture, and the adjusted furniture recommendation information is shared to the furniture platform's shared database.
[0011] In some embodiments, determining the set of approximate values for each user feature vector based on all furniture feature vectors specifically includes:
[0012] Obtain a user feature vector;
[0013] Determine the convergent value between the user feature vector and all furniture feature vectors;
[0014] The set of all convergent values is taken as the convergent value set of the user's feature vector;
[0015] Repeat the above steps to determine the set of approximate values for the remaining user feature vectors.
[0016] In some embodiments, determining the target user's hot-start furniture decision domain based on all degrees of synergy specifically includes:
[0017] Based on all the synergies, the feature vector layer of the target user is determined, and then the hot-start furniture decision domain of the target user is determined through the feature vector layer of the target user.
[0018] In some embodiments, adjusting the furniture recommendation information for the target user based on the adjustment coefficient for each type of furniture specifically includes:
[0019] Obtain the adjustment coefficient of one type of furniture in the hot-start furniture decision domain;
[0020] The recommended furniture grade for this type of furniture is determined based on this adjustment factor;
[0021] Repeat the above steps to determine the furniture recommendation level of the remaining furniture in the hot-start furniture decision domain;
[0022] The furniture recommendation information for the target user is adjusted based on the furniture recommendation level of all furniture in the hot-start furniture decision domain.
[0023] In some embodiments, determining the furniture recommendation level based on the adjustment factor specifically includes:
[0024] Based on the value of the adjustment coefficient, the furniture recommendation level is divided into strong recommendation level, secondary recommendation level, and weak recommendation level, thereby determining the furniture recommendation level of this type of furniture.
[0025] In some embodiments, the basic characteristics of each listed piece of furniture and the basic characteristics of each registered user in the shared database of the furniture platform are used as shared data in the furniture platform.
[0026] In some embodiments, a feature vector composed of the basic features of a piece of furniture in a specified furniture platform is used as the furniture feature vector.
[0027] Secondly, this application provides a device for sharing user data on a furniture platform, including:
[0028] The acquisition module is used to acquire shared data from a specified furniture platform and determine the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data.
[0029] The processing module is used to determine the convergence set of each user's feature vector based on all furniture feature vectors, and to determine the degree of synergy between two corresponding users based on every two convergence sets.
[0030] The processing module is also used to determine the target user's hot-start furniture decision domain based on all the degrees of collaboration;
[0031] The processing module is further configured to select a type of furniture in the hot-start furniture decision domain, determine the shared predicted value of the furniture based on all the synergies between the target user and other users, determine the adjustment coefficient of the target user for the furniture based on the shared predicted value and the target user's convergent value set, and continue to determine the adjustment coefficient of the target user for the remaining furniture in the hot-start furniture decision domain.
[0032] The sharing module is used to adjust the furniture recommendation information for the target user based on the adjustment coefficient of each type of furniture, and then share the adjusted furniture recommendation information to the shared database of the furniture platform.
[0033] Thirdly, this application provides a computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described user data sharing method for a furniture platform.
[0034] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described user data sharing method for a furniture platform.
[0035] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:
[0036] In this embodiment, after acquiring shared data from a designated furniture platform, the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data are determined. Based on all furniture feature vectors, a set of convergent values for each user feature vector is determined. The degree of collaboration between two users is determined based on every two sets of convergent values. The hot-start furniture decision domain for the target user is determined based on all degrees of collaboration. One type of furniture is selected from the hot-start furniture decision domain. The shared predicted value of this type of furniture is determined based on all degrees of collaboration between the target user and other users. The adjustment coefficient for this type of furniture is determined based on the shared predicted value and the target user's convergent value set. The adjustment coefficients for the remaining furniture in the hot-start furniture decision domain are then determined. The furniture recommendation information for the target user is adjusted based on the adjustment coefficients for each type of furniture. The adjusted furniture recommendation information is then shared on the furniture platform. In this application, the shared database of the platform is used to characterize the similarity between any two users by the degree of collaboration among users, thereby finding similar users of the target user. Based on the furniture ordering records of similar users, the furniture that the target user has not used is identified as furniture that the target user will order. The set of all furniture that the target user will order is used as the hot-start furniture decision domain. Then, the shared prediction value of all furniture in the hot-start furniture decision domain is determined. The shared prediction value is used to predict the target user's preference for selected furniture. Then, the adjustment coefficient of all furniture in the hot-start furniture decision domain is determined based on the preference. Finally, the furniture recommendation information of the target user is adjusted according to the adjustment coefficient, thereby increasing the proportion of potential order furniture recommended when recommending furniture to the target user. In summary, personalized shared recommendation of potential order furniture for the target user is realized. Attached Figure Description
[0037] Figure 1 This is an exemplary flowchart of a user data sharing method for a furniture platform according to some embodiments of this application;
[0038] Figure 2 This is a flowchart illustrating the process of determining the set of approximate values for each user feature vector according to some embodiments of this application;
[0039] Figure 3 This is a schematic diagram illustrating the process of adjusting furniture recommendation information for a target user according to some embodiments of this application;
[0040] Figure 4 This is a schematic diagram of the module composition of a user data sharing system for a furniture platform, according to some embodiments of this application;
[0041] Figure 5This is a schematic diagram of the structure of a computer device implementing a user data sharing method for a furniture platform, according to some embodiments of this application. Detailed Implementation
[0042] The core of this application is to obtain shared data from a designated furniture platform, determine the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data, determine the convergence set of each user's feature vector based on all furniture feature vectors, determine the degree of collaboration between two users based on every two convergence sets, determine the hot-start furniture decision domain of the target user based on all collaboration degrees, determine the shared predicted value of each piece of furniture in the hot-start furniture decision domain, and then determine the adjustment coefficient of the target user for each piece of furniture. Based on the adjustment coefficient of the target user for each piece of furniture, the furniture recommendation information of the target user is adjusted, and the adjusted furniture recommendation information is shared to the shared database of the furniture platform, which can realize personalized shared recommendations for the target user's potential furniture orders.
[0043] To better understand the above technical solutions, a detailed description of the solutions will be provided below in conjunction with the accompanying drawings and specific implementation methods. (Reference) Figure 1 The figure is an exemplary flowchart of a user data sharing method for a furniture platform according to some embodiments of this application. The user data sharing method 100 for a furniture platform mainly includes the following steps:
[0044] In step 101, the shared data in the specified furniture platform is obtained, and the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data are determined.
[0045] In specific implementation, shared data from a designated furniture platform can be obtained through the platform's shared database. It should be noted that the shared database of the furniture platform is a database containing basic user information and basic furniture information for information sharing. The shared data from the designated furniture platform includes the basic characteristics of each listed piece of furniture and the basic characteristics of each registered user. The basic characteristics of the furniture include material, design style, price, size, and color. The basic characteristics of the user include name, age, address, hobbies, and consumption preferences. The furniture feature vector is a feature vector composed of the basic characteristics of a piece of furniture on the designated furniture platform, and the user feature vector is a feature vector composed of the basic characteristics of a user on the designated furniture platform. Furthermore, this application sorts each furniture feature vector according to the filing time order of each piece of furniture in the shared database of the furniture platform, and sorts each user feature vector according to the registration time order of each user.
[0046] Additionally, it should be noted that the process of assembling the feature vector from the basic features is implemented using the one-hot encoding technique in the prior art. In other embodiments, other methods can also be used to assemble the basic features of each user and furniture into corresponding feature vectors, which is not limited here.
[0047] In step 102, the convergence set of each user's feature vector is determined based on all furniture feature vectors, and the degree of collaboration between the corresponding two users is determined based on every two convergence sets.
[0048] In some embodiments, reference Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining the convergent value set of each user feature vector in some embodiments of this application. In this embodiment, determining the convergent value set of each user feature vector based on all furniture feature vectors can be achieved using the following steps:
[0049] First, in step 1021, a user feature vector is obtained;
[0050] Then, in step 1022, the convergence value between the user feature vector and all furniture feature vectors is determined;
[0051] Secondly, in step 1023, the set of all the convergent values is taken as the convergent value set of the user feature vector;
[0052] Finally, in step 1024, the above steps are repeated to determine the set of approximate values for the remaining user feature vectors.
[0053] In some embodiments, determining the convergence value between the user feature vector and all furniture feature vectors can be achieved using the following steps:
[0054] Get the Furniture feature vectors ;
[0055] Obtain the user feature vector ;
[0056] According to the first Furniture feature vectors This user feature vector Determine the first The convergent value between a furniture feature vector and a user feature vector, wherein the first... The convergence value between a furniture feature vector and a user feature vector can be achieved using the following formula:
[0057]
[0058] in, This is the convergent value between the furniture feature vector and the user feature vector. Indicates the first The dot product of the furniture feature vector and the user feature vector. For the first The vector length of each furniture feature vector. This is the length of the feature vector for that user.
[0059] It should be noted that the approximation value is a quantitative value used to fit the user's preference for furniture. The larger the approximation value, the higher the user's preference for the furniture corresponding to the selected furniture feature vector.
[0060] In addition, it should be noted that the set of convergent values has a one-to-one correspondence with each user, and the order of each convergent value in the set of convergent values has a one-to-one correspondence with the order of each furniture feature vector.
[0061] In some embodiments, determining the degree of collaboration between two corresponding users based on every two sets of convergent values in this step can be achieved using the following steps:
[0062] Get the The first in the set of approaching values Approximate values ;
[0063] Get the The first in the set of approaching values Approximate values ;
[0064] Cooperative amplification parameters for determining the recommended furniture quantity ;
[0065] According to the first The first in the set of approaching values Approximate values , No. The first in the set of approaching values Approximate values Co-amplification parameters of the recommended furniture quantity Determine the first The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to the set of convergent values, wherein the th The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to a set of convergent values can be achieved using the following formula:
[0066]
[0067] in For the first The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to a set of approximate values. For the first The average of the nearest values of a set of nearest values For the first The average of the nearest values of a set of nearest values The number of furniture items in the shared database of the furniture platform.
[0068] It should be noted that the average convergence value mentioned in this application is the average of all convergence values in the convergence value set, and the coherence degree is a quantitative value that characterizes the similarity between two users. The larger the coherence degree, the greater the similarity between the two users corresponding to that coherence degree. The value of the coherence degree is between -1 and 1. By using all coherence degrees to characterize the similarity between users corresponding to each pair of convergence value sets, the furniture recommendation for the target user can be made by considering the basic registration data, furniture ordering records, and browsing records of similar users of the target user to find the furniture that the target user will order, thereby realizing personalized shared recommendation of potential furniture orders for the target user.
[0069] Additionally, it should be noted that the collaborative amplification parameter is used to control the magnitude of the collaborative degree, thereby affecting the number of furniture recommended to the user. The collaborative amplification parameter can be preset according to the furniture platform's requirement for the number of recommended furniture to the user, and is generally a constant value of [1, 1.8].
[0070] In step 103, the hot-start furniture decision domain for the target user is determined based on all the synergies.
[0071] In some embodiments, determining the target user's hot-start furniture decision domain based on all degrees of synergy in this step can be achieved using the following steps:
[0072] Determine the feature vector layer of the target user based on all degrees of synergy;
[0073] The hot-start furniture decision domain for the target user is determined through the feature vector layer.
[0074] In specific implementation, the feature vector layer of the target user is determined based on all the degrees of collaboration. That is, all user feature vectors are clustered according to all the degrees of collaboration to determine the feature vector layers of multiple users, and the user feature vector layer where the user feature vector corresponding to the target user is located is taken as the feature vector layer of the target user.
[0075] In specific implementation, the hot-start furniture decision domain of the target user is determined through the feature vector layer. That is, users corresponding to all user feature vectors other than the user feature vector of the target user in the feature vector layer are regarded as similar users, and the furniture set consisting of all furniture that the target user has not ordered or viewed, and furniture that similar users have ordered or viewed, is regarded as the hot-start furniture decision domain of the target user.
[0076] It should be noted that in the process of clustering all user feature vectors based on all synergy and determining multiple user feature vector layers, the clustering of all user feature vectors is achieved by using the existing K-means clustering algorithm after characterizing the similarity between each pair of users based on the aforementioned synergy. In other embodiments, other methods may be used to cluster all user feature vectors, which are not limited here.
[0077] In addition, the similar users mentioned in this application are determined based on the similarity between all users in the shared database of the furniture platform and the target user. The hot-start furniture decision domain represents the set of furniture that the target user will reserve among all furniture that has not been used by the target user in the furniture platform, which will not be elaborated here.
[0078] In step 104, select one type of furniture in the hot-start furniture decision domain, determine the shared predicted value of this type of furniture based on all the synergies between the target user and other users, determine the adjustment coefficient of the target user for this type of furniture based on the shared predicted value and the target user's convergent value set, and continue to determine the adjustment coefficient of the target user for the remaining furniture in the hot-start furniture decision domain.
[0079] In some embodiments, determining the predicted sharing value of such furniture based on all the synergies between the target user and other users can be achieved through the following steps:
[0080] Get the corresponding furniture number The nearest values in a set of nearest values ;
[0081] Obtain target users and Coordination among approximate value sets ;
[0082] Determine the number of sensitive time periods for the furniture platform. ;
[0083] Time-weighted coefficients for determining furniture preference ;
[0084] Determine the type of furniture in the first Furniture sensitive parameters corresponding to each sensitive time period ;
[0085] According to the corresponding number of this type of furniture The nearest values in a set of nearest values The target user and the first Collaboration between users The number of sensitive time periods of the furniture platform The time-weighted coefficient of the furniture preference degree This type of furniture in the first Furniture sensitive parameters corresponding to each sensitive time period The predicted sharing value of this type of furniture by target users is determined, which can be determined according to the following formula:
[0086]
[0087] in The predicted sharing value of this type of furniture among target users. For target users and the The absolute value of the degree of collaboration between individual users. The number of users in the shared database of the furniture platform.
[0088] It should be noted that the shared prediction value mentioned in this application is a quantitative value used to predict the user's preference for furniture. The larger the shared prediction value, the higher the predicted preference of the target user for that type of furniture. By predicting the target user's preference for that type of furniture through the shared prediction value, the system can find furniture that the target user might order by considering the basic registration data, furniture ordering records, and browsing records of similar users, thus achieving personalized shared recommendations for the target user's potential furniture orders. The number of sensitive time periods is used to characterize the number of time periods in a year that will affect the target user's preference for furniture. The more sensitive time periods there are, the more time periods in a year will affect the target user's preference for furniture. The time-series weighting coefficient is a value used to balance the magnitude of the target user's preference for furniture. The time-series weighting coefficient is a constant with a value between 0 and 1. The furniture sensitivity parameter is used to characterize the sensitivity of furniture in different time periods. The furniture sensitivity parameter has a value of 0 and 1. When the furniture sensitivity parameter is 1, it means that the furniture is sensitive in the [number]th time period. The sensitivity is high during the most sensitive time period. When the sensitivity parameter of the furniture is 0, it means that the furniture is sensitive during the most sensitive time period. The sensitivity is low when there are only a few sensitive time periods. In some embodiments, the number of sensitive time periods can be preset to 4. In this application, the year is divided into 4 sensitive time periods, the sensitive time period corresponding to the current date is obtained, and then the furniture sensitivity parameters of the furniture in the sensitive time period corresponding to the current date are determined.
[0089] In addition, the sensitive time period mentioned in this application is the time period within a year that will affect the number of reservations for the furniture; the value of the furniture sensitivity parameter is determined based on the number of reservations for the selected furniture in the sensitive time period corresponding to the current date in the shared database of the furniture platform. The higher the sensitivity of the selected furniture, the higher the predicted inclination of the target user for the selected furniture; the lower the sensitivity of the selected furniture, the lower the predicted inclination of the target user for the selected furniture.
[0090] In some embodiments, determining the adjustment coefficient for the target user for this type of furniture based on the shared predicted value and the target user's approximate value set in this step can be achieved using the following steps:
[0091] Obtain the proximity values between the target user and the type of furniture from the proximity value set corresponding to the target user. ;
[0092] Obtain the target users' predicted sharing value for this type of furniture ;
[0093] Positive adjustment factor for determining the recommended furniture quantity ;
[0094] Obtain the furniture feature vector of this type of furniture. ;
[0095] Obtain the user feature vector of the target user ;
[0096] Based on the proximity value between the target user and this type of furniture The target user's predicted sharing value for this type of furniture The positive adjustment factor for the recommended furniture quantity The furniture feature vector of this type of furniture The user feature vector of the target user The adjustment factor for this type of furniture is determined, and the adjustment factor for this type of furniture can be achieved using the following formula:
[0097]
[0098] in, This is the adjustment coefficient for this type of furniture. is the length of the furniture feature vector of this type of furniture, and is the length of the user feature vector of the target user.
[0099] It should be noted that the positive adjustment factor mentioned in this application represents a parameter value indicating the target user's expectation of the number of recommended furniture items. The larger the positive adjustment factor, the larger the adjustment coefficient for that type of furniture. By controlling the adjustment coefficient corresponding to that type of furniture, the number of recommended furniture items for the target user can be controlled. The positive adjustment factor is generally set to a value of [value missing]. The constants between.
[0100] Furthermore, the adjustment coefficient mentioned in this application is a mapping parameter for the confidence level of the shared predicted value, and generally takes the value of... The larger the adjustment coefficient is, the higher the reliability of the shared prediction value corresponding to the adjustment coefficient.
[0101] In step 105, the furniture recommendation information for the target user is adjusted according to the adjustment coefficient for each type of furniture, and the adjusted furniture recommendation information is shared to the shared database of the furniture platform.
[0102] In some embodiments, reference Figure 3 As shown in the figure, this is a flowchart illustrating the process of adjusting furniture recommendation information for a target user in some embodiments of this application. In this embodiment, adjusting the furniture recommendation information for the target user based on the adjustment coefficient for each type of furniture can be achieved using the following steps:
[0103] First, in step 1031, the adjustment coefficient of one type of furniture in the hot-start furniture decision domain is obtained;
[0104] Then, in step 1032, the furniture recommendation level of this type of furniture is determined based on the adjustment coefficient;
[0105] Secondly, in step 1033, the above steps are repeated to determine the furniture recommendation level of the remaining furniture in the hot-start furniture decision domain;
[0106] Finally, in step 1034, the furniture recommendation information for the target user is adjusted based on the furniture recommendation level of all furniture in the hot-start furniture decision domain.
[0107] In specific implementation, the furniture recommendation level for this type of furniture is determined based on the adjustment coefficient. Specifically, the furniture recommendation level is categorized into strong recommendation, secondary recommendation, and weak recommendation levels based on the value of the adjustment coefficient, thereby determining the overall furniture recommendation level. Specifically, when the adjustment coefficient is within a certain range... When the adjustment coefficient is in the range of 1, the furniture corresponding to that adjustment coefficient is classified as strongly recommended; when the magnitude of the adjustment coefficient is within 1, the furniture is classified as strongly recommended. When the adjustment coefficient is in the range of [specific values], the furniture corresponding to that adjustment coefficient is classified as a sub-recommendation level; when the magnitude of the adjustment coefficient is [specific value], ... At that time, the furniture corresponding to the adjustment coefficient is classified as weakly recommended.
[0108] In specific implementation, the furniture recommendation information for the target user is adjusted based on the furniture recommendation level of all furniture in the hot-start furniture decision domain. Specifically, the proportion and duration of each piece of furniture on the target user's furniture platform interface are adjusted according to its recommendation level. Specifically, the proportion and duration of strongly recommended furniture on the target user's furniture platform interface are adjusted to the optimal level; the proportion and duration of moderately recommended furniture on the target user's furniture platform interface are adjusted to the next best level; and the proportion and duration of weakly recommended furniture on the target user's furniture platform interface are adjusted to the worst level. In some embodiments, the specific proportion and duration of each furniture recommendation level can be set according to the user's usage habits, which will not be elaborated here.
[0109] It should be noted that in the process of sharing the adjusted furniture recommendation information to the shared database of the furniture platform, a set of user information interfaces is first provided. Through the user information interfaces, users can request and obtain data. The user information interfaces are information transmission channels that define transmission functions, transmission methods, transmission protocols and transmission tools. In some embodiments, the user information interfaces can be obtained through application programming interface technology in the prior art, which is not limited here.
[0110] In another aspect, in some embodiments, this application provides a user data sharing system for a furniture platform, see reference. Figure 4 The figure is a schematic diagram of the module composition of a user data sharing system according to some embodiments of this application. The user data sharing system 200 includes: an acquisition module 201, a processing module 202, and a sharing module 203, which are described below:
[0111] The acquisition module 201 in this application is mainly used to acquire shared data in a specified furniture platform and determine the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data.
[0112] Processing module 202, in this application, is mainly used to determine the convergence set of each user's feature vector based on all furniture feature vectors, and to determine the degree of collaboration between two corresponding users based on every two convergence sets;
[0113] It should be noted that the processing module 202 in this application is also used to determine the hot-start furniture decision domain of the target user based on all the degrees of collaboration;
[0114] In addition, the processing module 202 in this application is also used to select a type of furniture in the hot-start furniture decision domain, determine the shared predicted value of the furniture based on all the synergies between the target user and other users, determine the adjustment coefficient of the target user for the furniture based on the shared predicted value and the target user's convergent value set, and continue to determine the adjustment coefficient of the target user for the remaining furniture in the hot-start furniture decision domain;
[0115] The sharing module 203 in this application is mainly used to adjust the furniture recommendation information of the target user according to the adjustment coefficient of the target user for each type of furniture, and share the adjusted furniture recommendation information to the shared database of the furniture platform.
[0116] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, the processor being configured to acquire the code and execute the above-described user data sharing method for a furniture platform.
[0117] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device using a user data sharing method for a furniture platform, according to some embodiments of this application. The user data sharing method for a furniture platform described in the above embodiments can... Figure 5 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.
[0118] The processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the user data sharing method for the furniture platform in this application.
[0119] The communication bus 302 may include a path for transmitting information between the aforementioned components.
[0120] The memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or it may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via a communication bus 302. The memory 303 may also be integrated with the processor 301.
[0121] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. The user data sharing method for the furniture platform in the above embodiments can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.
[0122] Communication interface 304 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
[0123] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).
[0124] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.
[0125] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described user data sharing method for a furniture platform.
[0126] In summary, the user data sharing method for a furniture platform disclosed in this application firstly obtains shared data from a designated furniture platform, determines the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data, determines the convergence set of each user feature vector based on all furniture feature vectors, determines the degree of collaboration between two users based on every two convergence sets, determines the hot-start furniture decision domain for the target user based on all collaboration degrees, determines the shared prediction value of each type of furniture in the hot-start furniture decision domain, then determines the adjustment coefficient for each type of furniture for the target user, adjusts the furniture recommendation information for the target user based on the adjustment coefficient for each type of furniture, and shares the adjusted furniture recommendation information to the shared database of the furniture platform, thereby enabling personalized shared recommendations for the target user's potential furniture orders.
[0127] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.
[0128] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.
Claims
1. A user data sharing method for a furniture platform, characterized by, Includes the following steps: Obtain shared data from a specified furniture platform, and determine the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data; Based on all the furniture feature vectors, determine the set of convergent values for each user's feature vector, and then determine the degree of synergy between two corresponding users based on every two sets of convergent values; Determine the target user's hot-start furniture decision domain based on all synergies; Select one type of furniture in the hot-start furniture decision domain, determine the shared predicted value of this type of furniture based on all the synergies between the target user and other users, determine the adjustment coefficient of the target user for this type of furniture based on the shared predicted value and the target user's convergent value set, and continue to determine the adjustment coefficient of the target user for the remaining furniture in the hot-start furniture decision domain; The furniture recommendation information for the target user is adjusted according to the adjustment coefficient of each type of furniture, and the adjusted furniture recommendation information is shared to the shared database of the furniture platform. The following steps can be used to determine the convergence value between the user feature vector and all furniture feature vectors: Get the Furniture feature vectors ; Obtain the user feature vector ; According to the first Furniture feature vectors This user feature vector Determine the first The convergent value between a furniture feature vector and a user feature vector, wherein the first... The convergence value between a furniture feature vector and a user feature vector can be achieved using the following formula: in, This is the convergent value between the furniture feature vector and the user feature vector. Indicates the first The dot product of the furniture feature vector and the user feature vector. For the first The vector length of each furniture feature vector. This is the length of the feature vector for that user. Determining the degree of collaboration between two users based on every two sets of convergent values can be achieved using the following steps: Get the The first in the set of approaching values Approximate values ; Get the The first in the set of approaching values Approximate values ; Cooperative amplification parameters for determining the recommended furniture quantity ; According to the first The first in the set of approaching values Approximate values , No. The first in the set of approaching values Approximate values Co-amplification parameters of the recommended furniture quantity Determine the first The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to the set of convergent values, wherein the th The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to a set of convergent values can be achieved using the following formula: in For the first The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to a set of approximate values. For the first The average of the nearest values of a set of nearest values For the first The average of the nearest values of a set of nearest values The number of furniture items in the shared database of the furniture platform; Determining the sharing forecast value of this type of furniture based on all the synergies between the target user and other users can be achieved through the following steps: Get the corresponding furniture number The nearest values in a set of nearest values ; Obtain target users and Coordination among approximate value sets ; Determine the number of sensitive time periods for the furniture platform. ; Time-weighted coefficients for determining furniture preference ; Determine the type of furniture in the first Furniture sensitive parameters corresponding to each sensitive time period ; According to the corresponding number of this type of furniture The nearest values in a set of nearest values The target user and the first Collaboration between users The number of sensitive time periods of the furniture platform The time-weighted coefficient of the furniture preference degree This type of furniture in the first Furniture sensitive parameters corresponding to each sensitive time period The predicted sharing value of this type of furniture by target users is determined, which can be determined according to the following formula: in The predicted sharing value of this type of furniture among target users. For target users and the The absolute value of the degree of collaboration between individual users. The number of users in the shared database of the furniture platform; The adjustment coefficient for this type of furniture for the target user can be determined by the following steps based on the shared predicted value and the target user's approximate value set: Obtain the proximity values between the target user and the type of furniture from the proximity value set corresponding to the target user. ; Obtain the target users' predicted sharing value for this type of furniture ; Positive adjustment factor for determining the recommended furniture quantity ; Obtain the furniture feature vector of this type of furniture. ; Obtain the user feature vector of the target user ; Based on the proximity value between the target user and this type of furniture The target user's predicted sharing value for this type of furniture The positive adjustment factor for the recommended furniture quantity The furniture feature vector of this type of furniture The user feature vector of the target user The adjustment factor for this type of furniture is determined, and the adjustment factor for this type of furniture can be achieved using the following formula: in, This is the adjustment coefficient for this type of furniture. Let be the length of the feature vector of this type of furniture. The length of the user feature vector of the target user; Determining the target user's hot-start furniture decision domain based on all synergies can be achieved through the following steps: Determine the feature vector layer of the target user based on all degrees of synergy; The hot-start furniture decision domain for the target user is determined through the feature vector layer.
2. The method as described in claim 1, characterized in that, Determining the convergent set of each user's feature vector based on all furniture feature vectors specifically includes: Obtain a user feature vector; Determine the convergent value between the user feature vector and all furniture feature vectors; The set of all convergent values is taken as the convergent value set of the user's feature vector; Repeat the above steps to determine the set of approximate values for the remaining user feature vectors.
3. The method as described in claim 1, characterized in that, Based on all the synergies, the target user's hot-start furniture decision domain is determined, specifically including: Determine the feature vector layer of the target user based on all degrees of synergy; The hot-start furniture decision domain for the target user is determined through the feature vector layer.
4. The method as described in claim 1, characterized in that, Adjusting furniture recommendations for the target user based on the adjustment factor for each type of furniture specifically includes: Obtain the adjustment coefficient of one type of furniture in the hot-start furniture decision domain; The recommended furniture grade for this type of furniture is determined based on this adjustment factor; Repeat the above steps to determine the furniture recommendation level of the remaining furniture in the hot-start furniture decision domain; The furniture recommendation information for the target user is adjusted based on the furniture recommendation level of all furniture in the hot-start furniture decision domain.
5. The method as described in claim 4, characterized in that, The specific furniture recommendation level determined based on this adjustment factor includes: Based on the value of the adjustment coefficient, the furniture recommendation level is divided into strong recommendation level, secondary recommendation level, and weak recommendation level, thereby determining the furniture recommendation level of this type of furniture.
6. The method as described in claim 1, characterized in that, The basic characteristics of each listed piece of furniture and the basic characteristics of each registered user in the shared database of the furniture platform are used as the shared data in the furniture platform.
7. The method as described in claim 1, characterized in that, The feature vector composed of the basic features of a piece of furniture in the specified furniture platform is used as the feature vector of the furniture.
8. A user data sharing system for a furniture platform, characterized in that, include: The acquisition module is used to acquire shared data from a specified furniture platform and determine the furniture feature vector of each piece of furniture and the user feature vector of each user in the shared data. The processing module is used to determine the convergence set of each user's feature vector based on all furniture feature vectors, and to determine the degree of synergy between two corresponding users based on every two convergence sets. The processing module is also used to determine the target user's hot-start furniture decision domain based on all the degrees of collaboration; The processing module is further configured to select a type of furniture in the hot-start furniture decision domain, determine the shared predicted value of the furniture based on all the synergies between the target user and other users, determine the adjustment coefficient of the target user for the furniture based on the shared predicted value and the target user's convergent value set, and continue to determine the adjustment coefficient of the target user for the remaining furniture in the hot-start furniture decision domain. The sharing module is used to adjust the furniture recommendation information for the target user based on the adjustment coefficient of each type of furniture, and then share the adjusted furniture recommendation information to the shared database of the furniture platform. The following steps can be used to determine the convergence value between the user feature vector and all furniture feature vectors: Get the Furniture feature vectors ; Obtain the user feature vector ; According to the first Furniture feature vectors This user feature vector Determine the first The convergent value between a furniture feature vector and a user feature vector, wherein the first... The convergence value between a furniture feature vector and a user feature vector can be achieved using the following formula: in, This is the convergent value between the furniture feature vector and the user feature vector. Indicates the first The dot product of the furniture feature vector and the user feature vector. For the first The vector length of each furniture feature vector. This is the length of the feature vector for that user. Determining the degree of collaboration between two users based on every two sets of convergent values can be achieved using the following steps: Get the The first in the set of approaching values Approximate values ; Get the The first in the set of approaching values Approximate values ; Cooperative amplification parameters for determining the recommended furniture quantity ; According to the first The first in the set of approaching values Approximate values , No. The first in the set of approaching values Approximate values Co-amplification parameters of the recommended furniture quantity Determine the first The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to the set of convergent values, wherein the th The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to a set of convergent values can be achieved using the following formula: in For the first The user corresponding to the nth approximate value set and the nth... The degree of collaboration among users corresponding to a set of approximate values. For the first The average of the nearest values of a set of nearest values For the first The average of the nearest values of a set of nearest values The number of furniture items in the shared database of the furniture platform; Determining the sharing forecast value of this type of furniture based on all the synergies between the target user and other users can be achieved through the following steps: Get the corresponding furniture number The nearest values in a set of nearest values ; Obtain target users and Coordination among approximate value sets ; Determine the number of sensitive time periods for the furniture platform. ; Time-weighted coefficients for determining furniture preference ; Determine the type of furniture in the first Furniture sensitive parameters corresponding to each sensitive time period ; According to the corresponding number of this type of furniture The nearest values in a set of nearest values The target user and the first Collaboration between users The number of sensitive time periods of the furniture platform The time-weighted coefficient of the furniture preference degree This type of furniture in the first Furniture sensitive parameters corresponding to each sensitive time period The predicted sharing value of this type of furniture by target users is determined, which can be determined according to the following formula: in The predicted sharing value of this type of furniture among target users. For target users and the The absolute value of the degree of collaboration between individual users. The number of users in the shared database of the furniture platform; The adjustment coefficient for this type of furniture for the target user can be determined by the following steps based on the shared predicted value and the target user's approximate value set: Obtain the proximity values between the target user and the type of furniture from the proximity value set corresponding to the target user. ; Obtain the target users' predicted sharing value for this type of furniture ; Positive adjustment factor for determining the recommended furniture quantity ; Obtain the furniture feature vector of this type of furniture. ; Obtain the user feature vector of the target user ; Based on the proximity value between the target user and this type of furniture The target user's predicted sharing value for this type of furniture The positive adjustment factor for the recommended furniture quantity The furniture feature vector of this type of furniture The user feature vector of the target user The adjustment factor for this type of furniture is determined, and the adjustment factor for this type of furniture can be achieved using the following formula: in, This is the adjustment coefficient for this type of furniture. Let be the length of the feature vector of this type of furniture. The length of the user feature vector of the target user; Determining the target user's hot-start furniture decision domain based on all synergies can be achieved through the following steps: Determine the feature vector layer of the target user based on all degrees of synergy; The hot-start furniture decision domain for the target user is determined through the feature vector layer.
9. A computer device comprising a memory and a processor, the memory storing code, characterized in that, The processor is configured to acquire the code and execute the user data sharing method for a furniture platform as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the user data sharing method for a furniture platform as described in any one of claims 1 to 7.