CN115826833B - Implementation method of building block assembly system based on Internet - Google Patents
Implementation method of building block assembly system based on Internet Download PDFInfo
- Publication number
- CN115826833B CN115826833B CN202310101328.1A CN202310101328A CN115826833B CN 115826833 B CN115826833 B CN 115826833B CN 202310101328 A CN202310101328 A CN 202310101328A CN 115826833 B CN115826833 B CN 115826833B
- Authority
- CN
- China
- Prior art keywords
- user
- building block
- data
- model
- information
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses an implementation method of a building block assembly system based on the Internet, which relates to the technical field of electronic specifications and the technical field of user behavior analysis, and comprises the steps of obtaining a model file from a model server, analyzing, drawing and displaying assembly; recording and distinguishing different users; collecting and recording user information and data and sending the user information and the data to a feedback server; acquiring user data and preprocessing; modeling and analyzing the preprocessed user basic information and interaction behavior, predicting user preference, evaluating assembly experience of specific products and product sales in various areas in the future; and counting and integrating the preprocessed user information and the preprocessed use information and the results of user analysis and behavior prediction, and displaying, detecting potential risk points according to preset rules or algorithms, and performing early warning. The building block assembly system is convenient for users to understand and assemble correctly, and can provide data support and early warning for the design, production and sales of products.
Description
Technical Field
The invention relates to the technical field of electronic specifications, in particular to an implementation method of a building block assembly system based on the Internet.
Background
Building block products are often accompanied by instructions to guide the user in the construction. Existing solutions typically print the assembly method in steps on paper, each step showing one or several views at specific angles for the user to understand. The paper description scheme has the following disadvantages: (1) because the building blocks are three-dimensional articles, the three-dimensional relationship among the building block parts is required to be clarified during assembly, and the paper instruction book can only display two-dimensional static pictures, so that the three-dimensional relationship is not easy to describe, and the understanding and assembly of a user are difficult; (2) paper specifications often require color printing for ease of understanding by the user, and if there are many assembly steps, a large amount of space is required, which increases costs and is not environmentally friendly; (3) the paper instruction book does not have an interactive feedback function, and manufacturers are difficult to collect difficulties or problems encountered by users during assembly; (4) paper instructions must be pre-printed and attached to the product, which increases the development and production cycle of the building block product; (5) the paper instruction cannot be automatically updated, once the product is sold, the manufacturer cannot correct errors in the paper instruction or optimize the content, and once the errors exist, the paper instruction can lead to extensive user dissatisfaction; (6) paper specifications are not easy to store and are easy to damage, and the assembly of building blocks can be influenced after the paper specifications are lost or damaged.
Meanwhile, in the building block industry, the two-dimensional paper assembly instruction book is used to cause data to be closed-loop, a brand party and a design party are difficult to directly contact with each other to reach users, user feedback is often collected only in limited-range market research or active feedback of few active users, hand data of the products used by the users cannot be obtained directly, interest of the users to the products can be evaluated only through sales data of channel parties, and larger errors and time delay are necessarily caused, so that stock pressure of a supply chain is often caused.
Disclosure of Invention
The invention aims to provide an implementation method of a building block assembly system based on the Internet, which aims to solve the following technical problems: (1) In the prior art, the paper instruction book can only display two-dimensional static pictures, so that the three-dimensional relation is not easy to describe and clear, and the understanding and assembly of a user are difficult; (2) In the prior art, the paper instruction book only plays a role in displaying, and user information and data cannot be collected and fed back; (3) The manufacturer has difficulty in accessing the first hand data of the user, so that the user preference is not known, the advertisement recommendation lacks personalization, and potential risk points in the product and supply chains cannot be pre-warned in advance.
The invention provides an Internet-based building block assembly system, which consists of a building block electronic instruction system for building block users and a user behavior analysis system for building block manufacturers, wherein the two systems can work in a matched mode.
The implementation method of the building block assembly system based on the Internet comprises the following steps:
the method comprises the steps of obtaining a model file from a model server through an assembly display module, analyzing, drawing and displaying an assembly step;
the user tracking module records user information and sends the user information to the feedback server, and the feedback communication module records user behaviors and user evaluations when the user uses the instruction book system and sends the user behaviors and the user evaluations to the feedback server so as to realize information interaction between the user and a manufacturer;
acquiring recommended content from a recommendation server through a content recommendation module and displaying the recommended content to a user after the assembly description is finished;
collecting and storing user data sent by the electronic instruction system through a feedback server;
user data is obtained through a data collection and preprocessing module, preprocessing is carried out, and effective data stored in a specific form is obtained for the user analysis and behavior prediction module to use;
modeling and analyzing the preprocessed user basic information and interaction behaviors through a user analysis and behavior prediction module, predicting user preference, evaluating assembly experience of specific products and product sales in various areas in the future;
the preprocessed user information and the preprocessed use information and the preprocessed user analysis and behavior prediction results are counted and integrated through a visual display and early warning module, and are displayed through a visual data large screen, and meanwhile potential risk points are detected according to a certain rule or algorithm and early warning is carried out.
As an embodiment of the present invention, obtaining and analyzing a model file specifically includes:
step 101, obtaining model files of corresponding building block structures and assembling processes;
step 102, analyzing the model file to obtain a first-level part referenced by the corresponding building block structure;
step 103, obtaining and analyzing a sub-model file of one of the first-level parts to obtain a referenced second-level part;
step 104, repeating step 103 until all the first-stage components are acquired and analyzed.
As an embodiment of the present invention, in step 101, the obtaining a model file mainly includes:
step 105, obtaining the latest update time of the model file from the model server;
step 106, checking whether a model file to be acquired exists in the local cache, if not, jumping to step 108, and if so, jumping to step 107;
step 107, comparing the cache time with the latest update time in the metadata, if the cache time is later than the latest update time, jumping to step 109, otherwise jumping to step 108;
step 108, downloading the latest model file from a remote model server, and storing the downloaded model file and the current time into a cache for use;
And 109, extracting the model file from the cache to finish the acquisition.
As an embodiment of the present invention, the drawing and displaying assembly steps specifically include:
step 110, establishing a blank drawing;
step 111, reading an assembling step recorded in a model file, analyzing each statement in the step, if the statement is a drawing instruction, drawing according to the instruction, if other parts are referenced, reading the model file of the part, executing the step 111 on the model file of the part, and then carrying out translation, rotation, scaling, coloring and other transformations on the drawn part according to transformation rules recorded in the model file referencing the part;
step 112, repeating the step 111 until all the parts are drawn;
step 113, displaying the assembling step and listing the parts to be used in the current step so as to facilitate the user to find.
As one embodiment of the invention, when each part of the model is drawn, the current step number is recorded; when the assembling step is displayed, all parts drawn in the current step and the previous step are displayed according to the currently set step number, so that the display effect is the same as the actual assembling state of the user.
As one implementation mode of the invention, when the user exits the specification system, the assembling step carried out before the user exits is stored in a cookie of the user browser, and the cookie is read when the user enters the specification system next time, so that the user is allowed to directly jump to the assembling step when the user exits and continue assembling.
As one implementation mode of the invention, the user tracking module judges whether the current user is a tracked user or an untracked user by detecting cookies in a user browser; for untracked users, generating a unique identity identifier for a single user, storing the unique identity identifier in a browser cookie, and providing the unique identity identifier as the identity identifier of the current user to other modules; for tracked users, the identity identifier is extracted from the cookie and provided to other modules.
As an implementation mode of the invention, the feedback communication module comprises a behavior recorder, a feedback sending unit and a comment display unit, and the implementation of information interaction between a user and a building block manufacturer specifically comprises the following steps:
collecting user information through an information collector;
recording user behaviors and operation data of the electronic specification when a user uses the specification system through a behavior recorder;
The feedback sending unit creates a platform so that a user can give an evaluation to the current step or the whole assembly specification, and sends the user behavior and the user evaluation to a feedback server along with user information;
the comment display system obtains the user comments of the current step from the feedback server and displays the comments so as to enable interaction between users and manufacturers.
As one embodiment of the present invention, the content recommendation module sends the identity identifier of the current user to the recommendation server to obtain personalized recommended content based on the user identity.
As one embodiment of the invention, the feedback server collects data generated during the use of the electronic instruction system by a user, including user information, user behavior, user evaluation and operation data. The user information includes: the building block product is obtained from a user tracking module, namely a user identity identifier, a current IP address of a user, identifiers of equipment and a browser used by the user and a building block product currently viewed by the user; the user behavior includes: the method comprises the steps of staying time of a user at each step, rotating angle when the user views a model, scaling when the user views the model, jumping step by clicking a button at the last step or the next step or inputting a step number, entering and exiting the electronic specification system, and locating the steps and time; the user evaluation includes: scoring and commenting issued by a user in the process of using the electronic specification system; the operation data includes: performance parameters and logs during the operation of the electronic instruction system.
As an embodiment of the present invention, the data collection and preprocessing module may obtain the data of the user using the electronic specification system and registration, purchase, etc. from the feedback server and other servers (such as a server storing the user purchase record, a server storing the registered user basic information, etc.), and based on the user identity identifier, try to match and integrate the data of the electronic specification system with the data from other servers, and then perform preprocessing such as deduplication, compression, cleaning, sorting, etc. according to a specific rule.
As an embodiment of the present invention, the data collection and preprocessing module may store the preprocessed data in a database or in text form, so as to facilitate querying and use by other modules.
As one implementation mode of the invention, the user analysis and behavior prediction module trains the data output by the data collection and preprocessing module through a neural network algorithm to obtain a model, and then evaluates and predicts user preference, building block products, specification quality and future sales.
When the user analysis and behavior prediction module analyzes and predicts the user preference through the neural network model, the user basic information and the spliced building block information are directly introduced into the neural network model as discrete features, the user behavior information is introduced into the neural network model as time sequence data through a time sequence model method, the user comment content is abstracted through keyword detection and an NLP-based text emotion analysis technology and introduced into the neural network model as discrete features, and finally a multidimensional preference map comprising aspects of difficulty, type, price, IP, brand and the like is formed for each user.
As one implementation mode of the invention, the user analysis and behavior prediction module analyzes and evaluates each building block product through a neural network model, directly introduces product basic information into the neural network model as discretization characteristics, introduces behavior interaction information of a user into the neural network model as time sequence data through a time sequence model method, and finally forms reference data comprising various aspects of difficulty, complexity, predicted assembly time, instruction quality index, user evaluation index and the like for each product.
As one implementation mode of the invention, the user analysis and behavior prediction module analyzes and predicts the use condition of each product in each region through a neural network model, and the future sales prediction data of each product in each region is formed by introducing information such as user purchase data, instruction access data, the region where the user is located and the like into the neural network model as discretization characteristics, introducing information such as product price, regional personnel income, urban and rural differences and the like into the neural network model as discretization characteristics, and introducing the use change condition of a single product instruction in time into the model as time sequence data. The visual display and early warning module counts the data output by the data collection and preprocessing module, and displays statistical data such as sales volume, user region distribution, average assembly completion time, user scoring distribution, assembly completion rate and the like of each building block product in a chart form; and integrating various evaluation and prediction information output by the user analysis and behavior prediction module, and displaying data such as user group portraits and proportions, difficulty, complexity, instruction quality, future sales prediction and the like of various products in a chart form.
As an implementation mode of the invention, the visual display and early warning module can be matched and early warn potential risk points according to manually set rules, and can also automatically detect and early warn the potential risk points by adopting a neural network algorithm.
As an embodiment of the present invention, the potential risk points that the visual display and early warning module may early warn include: products with possibly reduced future sales, products with unreasonable pricing, products with possibly insufficient inventory or backlog of inventory predicted from the future sales, products with lower user evaluation index, products with lower user completion assembly rate, products with lower specification quality, products with possibly problems or design defects.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the embodiment of the invention, the three-dimensional model is drawn on the electronic equipment, and the user is allowed to zoom and rotate to check, so that the three-dimensional relation among parts can be better described, and the user can understand and assemble correctly;
(2) The electronic instruction in the embodiment of the invention does not need to be printed, so that the method is more environment-friendly and saves cost, meanwhile, the instruction is not needed to be prepared during the production of the product, and the electronic instruction is prepared before formal sale, so that the research and development production period of the product can be shortened;
(3) In the embodiment of the invention, a manufacturer can obtain the time consumption, operation and evaluation and comment given by the user in each step through the feedback collection communication module, so that the difficulty and problem encountered when the user is assembled can be better known and can be positively solved; the method has the advantages that the user is allowed to interact with manufacturers and other users, the interestingness is increased, meanwhile, the manufacturers can modify and adjust the content of the instruction book at any time, the instruction book is maintained by the manufacturers, the users can check at any time only by using equipment with a browser (such as a smart phone, a computer and the like), and the problems of losing and damaging are avoided;
(4) The embodiment of the invention can directly contact the terminal user and collect the first hand data and information from the use process of the user, thereby realizing accurate preference prediction and advertisement recommendation aiming at the user and improving the click rate and conversion rate of the advertisement;
(5) According to the invention, more objective product data based on the user is obtained by analyzing the user use data, future product sales are predicted, and risk points possibly having problems or needing to be optimized in the product and the market are automatically detected, so that data support and early warning can be provided for the design, production and sales of the product, and decision assistance is provided for manufacturers;
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart for obtaining and parsing a model file according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an implementation method of the building block assembly system based on the internet according to the embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown.
The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The embodiment of the invention provides an Internet-based building block assembly system, which comprises a building block electronic specification system and a user behavior analysis system, wherein the building block electronic specification system comprises a model server, an assembly step display module, a user tracking module, a feedback communication module and a content recommendation module, and the user behavior analysis system comprises a feedback server, a recommendation server, a data collection and preprocessing module, a user analysis and behavior prediction module and a visual display and early warning module. The building block toy electronic specification system is mainly developed based on front-end technology and can be operated on equipment (including but not limited to a smart phone, a tablet personal computer and the like) provided with browser (or browser function) software. The user can access the system and obtain the electronic assembly instruction of the corresponding building blocks by scanning and purchasing the two-dimension codes attached to the building blocks or accessing the corresponding links through a browser. The user behavior analysis system may be run on a variety of general purpose or special purpose computer devices including, but not limited to, desktop computers, notebook computers, servers, cell phones, tablet computers, computing cards, and the like.
The invention adopts files with specific format (hereinafter referred to as model files) to record building block models or building block parts. The building block parts are non-detachable parts with specific specifications provided by manufacturers in the building block toy, and are basic constituent elements of the building block toy; the building block model is an integral body formed by splicing and combining building block parts according to a certain mode and steps, such as a cartoon small-person-shaped building block toy. A building block model may sometimes include a plurality of sub-models, each of which is a relatively independent, shaped model of building block parts joined together in specific steps and manners, such as the head of a cartoon small humanoid building block toy. The building block file is a digital representation method of a building block model and can be used for recording the shape, the size, the number, the color and other attributes of building block parts; the method can also be used for recording the properties of the building block model, each step in the assembly of the building block model, the used part numbers, the part coordinates, the part rotation state, the part colors, the part texture patterns and the like. One or more models can be recorded in a model file, other models (sub-models) or parts can be referenced in the models, and drawing instructions can be used for describing the structure of the models. Since the model files may represent building block parts or building block models, no distinction is made in the figure.
The implementation method of the building block electronic specification system comprises the following steps:
the assembling step display module is responsible for acquiring and analyzing the model file, and then gradually drawing and displaying the model assembling step. When the model file is acquired, firstly, the latest update time of the model is acquired from a server, then whether the file to be acquired exists in a local cache or not is checked, if not, the downloaded model file can be stored in the cache for later use, so that the network download time and bandwidth resource consumption are reduced, and the loading speed is increased; if yes, comparing the caching time with the latest updating time, if the latest updating time is later than the latest updating time, directly using the latest version, otherwise downloading and acquiring the latest version from the server, and ensuring that the instruction accessed by the user is always in the latest state.
Specifically, when the model file is obtained and parsed, the method shown in fig. 1 is adopted, namely, firstly, the model file describing the corresponding building block structure and the assembly process (called a main model file) is obtained and parsed to obtain other parts referenced therein, and then, the model file describing each part is obtained and parsed to obtain the referenced parts until the model files of all the parts to be used are obtained and parsed.
When drawing and assembling steps, firstly initializing a blank canvas (the canvas can be regarded as a blank three-dimensional space), initializing a step number to be 1, then starting from a main model file, reading one assembling step recorded in the model file each time, analyzing each statement in the step, drawing according to instructions if the statement is a drawing instruction, and setting the step number of each drawn component as a current step number; if the sub-model or the part is referenced, the model or the part is firstly drawn recursively, and then the drawn model or the part is transformed into translation, rotation, scaling and the like, coloring and the like according to the coordinates, the transformation and the color recorded in the sentence. After each statement of the current step is drawn, the step number is added with 1. During the drawing process, each drawn part is set to an invisible state and is not displayed to the user.
When the assembly step is displayed, the parts to be used in the current step can be listed to facilitate the user to find, and the parts added in the current step can be highlighted to facilitate the user to assemble. If a part is composed of a plurality of parts, a model file describing the part is recursively read, and the transformation such as rotation, scaling and the like is performed according to the transformation rules recorded in the model file, then the part is drawn on the correct coordinate position according to the coordinates and colors recorded in the model file, and the correct color is given until all the parts are drawn. When the assembly step is displayed, a current step number, a last step button and a next step button are also displayed, and a user can enter the next step or return to the last step by clicking the buttons or jump to the designated step by inputting the step number. When the assembling step is displayed, a user is allowed to rotate and zoom the model, so that the user can better observe and understand the three-dimensional relationship between parts, and the assembling is convenient for the user.
In addition, the assembling step display module can also place a cookie on the user's equipment for recording the current assembling progress of the user, thereby allowing the user to directly jump to the last assembling progress when accessing the system next time and optimizing the user experience.
The user tracking module is used for tracking registered or unregistered users, so that the assembly progress and interaction behavior of single users are recorded, and manufacturers can know and count user experience and behavior, and optimize product and instruction quality. The user tracking module may work for logged-in or logged-out users.
Specifically, a logged-in user refers to a user who has registered, logged in and accessed the present electronic specification in a specific APP, applet or website; the unregistered user refers to a user who accesses the electronic specification system without registering or logging in the specific APP, applet, or website, and typically, the user accesses the electronic specification system directly by scanning a two-dimensional code or clicking a link using a browser (or other application having a browser function).
For logged-on users, when accessing the electronic description system through a specific APP, applet or website, the APP, applet or website will generate an identifier that uniquely identifies the current user, carry the identifier in the parameters of the link to the electronic description system, and place a special cookie on the user's device containing the identifier. The user tracking module of the electronic instruction system can read the identifier from the link parameter or the cookie, so as to correlate the user currently accessing the electronic instruction with the information of the user registered in the APP, the applet or the website.
For an unregistered user, the user tracking module tries to read a cookie storing a user identity identifier when the user accesses the electronic specification system, and if the cookie cannot be read, the user is considered to be a new user, a unique identity identifier is generated for the user, and the unique identity identifier is placed on user equipment as the cookie; if so, the current user is associated with the identity identifier in the cookie.
The feedback communication module consists of a behavior recorder, a feedback sending unit and a comment display system. The behavior recorder will record various types of behavior of the user when using the description system, including but not limited to: the time that each step stays, the angle of rotation when viewing the model, the scale when viewing the model, the behavior of clicking on the previous step/next step or step jump by inputting the step number, the behavior and time of entering and exiting the electronic specification system, etc. These user behaviors are sent to the feedback server together with the user identity identifier provided by the user tracking module, so that manufacturers can know the assembly difficulty of each step and analyze the user behaviors and preferences, and the product design and assembly steps are optimized.
The feedback sending unit allows the user to give evaluation or comment to the current step or the whole assembly instruction book and send the evaluation or comment to the feedback server together with the user identity identifier, so that a manufacturer can know the subjective ideas of the user or perform interaction among the users. The comment display system is responsible for acquiring user comments of the current step from the feedback server, so that interaction between users is allowed, a manufacturer can be allowed to give text description to the current step, and the user can conveniently assemble correctly.
It should be noted that, after the user data collected by the module is sent to the server, statistics, analysis and presentation of the user data will be performed. For example, the user assembly completion rate, the discard rate, the average total time spent, the average time spent of each step, etc. can be counted; the automatic detection system for difficult steps based on rules or machine learning is used, and the difficulty of each step in the assembly instruction is evaluated through the assembly instruction and the characteristics of the user behavior (such as the number of parts increased in steps, the sizes and the color of the parts, the coordinate position distribution of the parts, the time spent by the user in the current step, the abandoning rate of the user in the current step, the switching behavior of the user in the adjacent step and the like), so that manufacturers can optimize the building blocks and the instruction.
The content recommendation module is responsible for acquiring recommended content from the server and displaying the recommended content to a user after the assembly description is finished. The recommended content may include, but is not limited to, a building instruction of other building blocks, a brief introduction or purchase link of other building blocks, other models in which parts of the current building block can be spelled out, other content authored by the user and uploaded by the user, and the like. When the content recommendation module acquires recommended content from the server, the identity identifier of the current user is sent to the server, so that more personalized recommended content based on the identity of the user can be acquired. For example, the server may analyze the user's preferences based on user behavior, purchase records, access records, etc., and give recommended content that may be of interest to the user.
Further, the recommendation server of the content recommendation module will make recommendations based on a preference analysis of the user. The preference analysis may calculate a user representation (e.g., user gender, age, knowledge level, proficiency, hobbies, etc.) for the current user based on the user's historical purchase data, assembly completion, behavior during assembly (e.g., step stay time, step switch, discard, etc.), and recommend appropriate content and products for the user (e.g., recommend products more suitable for children to children; recommend larger, more complex building block products to building block lovers or users who like the challenge) using knowledge graph, machine learning, etc.
The implementation method of the user behavior analysis system in the embodiment of the invention comprises the following steps: user information and data are collected from a feedback server and other servers stored with related data through a data collection and preprocessing module, then modeling and analysis are carried out through a user analysis and behavior prediction module, evaluation and prediction results of user preference, product data and future sales are obtained, analysis and display are carried out through a visual display and early warning module, and automatic detection and early warning are carried out on potential risk points; the recommendation server is also updated to provide personalized recommended advertisements to the user based on the user preferences.
The main function of the data collection and preprocessing module is to collect user data recorded by front-end electronic instruction and other servers (such as servers for storing user registration information in APP/applet, servers for storing user purchase records, etc.) for matching and synthesizing based on the identity identifier, and then preprocessing means such as data desensitization, cleaning, denoising, compression, etc. are adopted to finally obtain effective data stored in a specific form for analysis of subsequent algorithms, wherein the collected data is mainly shown in the following table. The pretreatment means of desensitizing, cleaning, denoising, compressing and the like on the sparse data are common methods in the mobile internet industry, and are not described in detail herein.
The user analysis and behavior prediction module has the functions of realizing three types of targets by modeling basic information of a user and time sequence characteristics of interaction behaviors and understanding deep reasons of the user behaviors through an algorithm: (1) more accurate user advertisement recommendation; (2) more optimized building block product assembling experience; (3) faster supply chain throughput is reacted.
For the target of more accurate user advertisement recommendation, the invention directly introduces the user basic information as a discretization characteristic into a model in a user behavior construction and prediction system; behavior information of a user during applet use, such as clicking, waiting, discarding, etc., is introduced into the model as time series data by a time series model method, including, but not limited to RNN, transformer, etc. Finally, a multidimensional map including aspects of difficulty, type, price, IP, brand and the like is formed, user preference is modeled, and accuracy and possibility of accurate sales of the multidimensional map are improved. For example, a user may not be interested in a warship class product after purchasing a street view building class product multiple times; for another example, a user may prefer a less difficult product if the assembly is not successfully completed after purchasing a more difficult building block product. The basic evaluation index of the target is the index commonly used in industry such as click rate after advertisement exposure and conversion rate after clicking.
For the aim of optimizing building block assembly experience, the invention models a single product based on sequence information data of assembly behaviors of different users, directly introduces product basic information as discretization characteristics into a model, and introduces behavior interaction information of users in the assembly process such as rotation, zooming, stay and the like into the model as time sequence data. By means of the splicing logic which is closer to a user, the evaluation and detection of the design and splicing process of the sold products are achieved, and the possibility of optimizing subsequent product research and development and current product iteration is provided. For example, having more users stay or repeatedly rotate the viewing angle at a certain step time may mean that the design or assembly steps herein may be difficult or confusing, requiring optimization. The actual assembly difficulty and complexity of the existing product can be rated through the model, and the model is used for the reference of a building block product designer and the accurate recommendation of the product. The basic evaluation index is active and passive, the former is active scoring and active feedback of the user, and the latter is index such as proportional relation of average time length of each step and single step time length.
For the goal of quicker supply chain production reaction, the invention models the distribution of user use data in regions and time domains, the data represent actual purchasing, box disassembling and assembling behaviors of the user, and compared with pure channel sales data, the invention is closer to the actual situation, and can show the distinction of user self-use and gift. At the regional level, basic information such as average income of residents, urban and rural differences and the like is introduced as discretization characteristics, the time use change of a single product is used as time sequence data to be introduced into a model so as to predict the use condition of each region in the future, and the use condition is compared with the stock condition of a channel manufacturer, so that the prediction of the product demand in the future region is formed, and the production judgment of a supply chain is assisted.
In the prior art, various common models and algorithms in industries such as DIN, SIM, wide and Deep can be applied to the system, and the basic thought is as follows: (1) After collecting the user data, these large-scale sparse features will be mapped to a lower dimensional space with higher information density; (2) Then, through operations such as a pooling layer of the model, behavior information with an indefinite length is converted into characteristic quantities with a fixed dimension; (3) Aggregating the features of fixed dimension together and inputting to the MLP network; (4) And through the loss function, after model training is completed, the prediction of the behavior sequence is realized.
The visual display and early warning module has the functions of displaying the counted user assembly data and the user analysis and behavior prediction results through a visual data large screen, so that project managers manage and control potential risk points, sales managers know sales and user experience conditions of various product lines, early warning of a design end and a production end is realized, more efficient and more real product iteration or production decision is performed, and risks of the whole product research and development and an industrial system are reduced. The statistical user splice data may include, but is not limited to, sales for each region or time period of a particular product, stock for each product and region, user completion splice rate, user discard splice rate, user active feedback, user score, and the like. The result data of the user analysis and behavior prediction may include, but is not limited to, design or assembly steps that may require optimization in a particular product, comprehensive difficulty/complexity ratings of a particular product, advertisement click-through/conversion rates of a recommendation system, predicted sales for a particular time period for each region, correctness of pricing policies, and the like.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
The user information collected in the invention is agreed by the user and is used for legal use.
Claims (20)
1. The implementation method of the building block assembly system based on the Internet is characterized by comprising the following steps of: the system consists of a building block electronic instruction system for building block users and a user behavior analysis system for building block manufacturers; the method comprises the following steps:
the method comprises the steps of obtaining a model file from a model server through an assembly display module, analyzing, drawing and displaying an assembly step;
recording and distinguishing different users through a user tracking module;
collecting and recording user information and data through a feedback communication module and sending the user information and the data to a feedback server;
The user tracking module records user information and sends the user information to the feedback server, and the feedback communication module records user behaviors and user evaluations when the user uses the instruction system and sends the user behaviors and the user evaluations to the feedback server, so that information interaction between the user and a manufacturer is realized;
the drawing and displaying assembly steps specifically comprise:
step 110, establishing a blank drawing;
step 111, reading an assembling step recorded in a model file, analyzing each statement in the step, if the statement is a drawing instruction, drawing according to the instruction, if other parts are cited, reading the model file of the part, executing the step 111 on the model file of the part, and then carrying out part transformation on the drawn part according to transformation rules recorded in the model file of the part, wherein the part transformation comprises translation, rotation, scaling and coloring;
step 112, repeating the step 111 until all the parts are drawn;
step 113, displaying the assembling step and listing the parts to be used in the current step so as to facilitate the user to find.
2. The method for implementing an internet-based building block assembly system according to claim 1, wherein the method for obtaining and analyzing the model file by the building block assembly system specifically comprises:
Step 101, obtaining model files of corresponding building block structures and assembling processes;
step 102, analyzing the model file to obtain parts referenced by corresponding building block structures, and adding the parts to an unresolved part set;
step 103, selecting a part from the unresolved part set, acquiring and resolving a model file of the part, obtaining a sub-part referenced in the part, judging whether the sub-part is resolved, and adding the sub-part into the unresolved part set if the sub-part is not resolved;
step 104, repeating step 103 until the unresolved component set is empty, wherein all components are acquired and resolved.
3. The method according to claim 2, wherein in step 101, obtaining the model file mainly includes:
step 105, obtaining the latest update time of the model file from the model server;
step 106, checking whether a model file to be acquired exists in the local cache, if not, jumping to step 108, and if so, jumping to step 107;
step 107, comparing the cache time with the latest update time in the metadata, if the cache time is later than the latest update time, jumping to step 109, otherwise jumping to step 108;
Step 108, downloading the latest model file from a remote model server, and storing the downloaded model file and the current time into a cache for use;
and 109, extracting the model file from the cache to finish the acquisition.
4. The method of claim 3, wherein in step 112, when each part of the model is drawn, a current step number is recorded, and when the assembly step is displayed, all parts drawn in the current step and the previous step are displayed according to the currently set step number, so that the presentation effect is the same as the actual assembly state of the user.
5. The method for implementing an internet-based building block assembly system according to claim 1, wherein the user tracking module determines whether the current user is a tracked user or an untracked user by detecting a cookie in a user browser; for untracked users, a unique identifier is generated for a single user and stored in a browser cookie.
6. The method for implementing the building block assembly system based on the internet according to claim 1, wherein the feedback communication module comprises an information collector, a behavior recorder and a feedback sending unit, and the implementing of the information interaction between the user and the merchant specifically comprises:
Collecting user information through an information collector;
recording user behaviors and system operation logs of a user when using the building block assembly system through a behavior recorder;
the feedback sending unit sends the user information, the user behavior and the operation data to the feedback server together.
7. The method for implementing an internet-based building block assembly system according to claim 6, wherein the user information collected by the information collector comprises: the building block product is obtained from a user tracking module, namely a user identity identifier, a current IP address of a user, identifiers of equipment and a browser used by the user and a building block product currently viewed by the user;
the user behavior recorded by the behavior recorder when a user uses the building block assembly system comprises the following steps: the method comprises the steps of staying time of a user at each step, rotating angle of the user when viewing a model, scaling of the user when viewing the model, jumping-over of the step by clicking a button of the last step or a button of the next step or inputting a step number, entering and exiting of the building block assembly system by the user, and steps and time of the user;
the operation data of the building block assembly system recorded by the behavior recorder comprises: performance parameters and logs in the running process of the building block assembly system.
8. The method of claim 6, wherein the feedback communication module is further capable of creating a platform to enable a user to give an evaluation and comment on a current step, a current product, or a current building block assembly system and send the evaluation and comment to a feedback server;
the feedback communication module can acquire evaluation, comment or information from a manufacturer or other users from the feedback server for display.
9. The implementation method of the building block assembly system based on the internet according to claim 1, wherein the building block assembly system can acquire personalized recommended content based on user identity from a recommendation server through a content recommendation module and display the personalized recommended content to a user after assembly description is finished.
10. The method for implementing an internet-based building block assembly system according to claim 1, further comprising the steps of:
receiving user data through a feedback server;
user data are obtained through a data collection and preprocessing module, preprocessing is carried out, and effective data stored in a preset form are obtained;
modeling and analyzing the preprocessed user basic information and interaction behaviors through a user analysis and behavior prediction module, predicting user preference, evaluating assembly experience of specific products and product sales in various areas in the future;
The preprocessed user information and the preprocessed usage information and the preprocessed user analysis and behavior prediction results are counted and integrated through a visual display and early warning module, the preprocessed user information and the preprocessed user analysis and behavior prediction results are displayed through a visual method, and potential risk points are detected and early warned according to preset rules or algorithms.
11. The method for implementing an internet-based building block assembly system according to claim 10, wherein the user data collected by the feedback server comprises: user information, user behavior, user evaluation and operation data;
the user information includes: the building block product is obtained from a user tracking module, namely a user identity identifier, a current IP address of a user, identifiers of equipment and a browser used by the user and a building block product currently viewed by the user;
the user behavior includes: the method comprises the steps of staying time of a user at each step, rotating angle of the user when viewing a model, scaling of the user when viewing the model, jumping-over of the step by clicking a button of the last step or a button of the next step or inputting a step number, entering and exiting of the building block assembly system by the user, and steps and time of the user;
the user evaluation includes: evaluation and comment issued by users in the process of using the building block assembly system;
The operation data includes: performance parameters and logs in the running process of the building block assembly system.
12. The method for implementing an internet-based building block assembling system according to claim 10, wherein the data collecting and preprocessing module obtains basic information and behavior data of a user using the building block assembling system from a feedback server, obtains other information and data of user registration, purchase and registration from other servers, matches and synthesizes the data of the building block assembling system and the data from the other servers based on a user identity identifier, and then performs preprocessing according to preset rules, wherein preprocessing includes deduplication, compression, cleaning and finishing.
13. The method for realizing the building block assembly system based on the internet according to claim 10, wherein the user analysis and behavior prediction module trains the data output by the data collection and preprocessing module to obtain a model through a neural network algorithm, and then evaluates and predicts user preference, building block products, quality of the building block assembly system and future sales.
14. The method for implementing the building block assembly system based on the internet according to claim 13, wherein when the user analysis and behavior prediction module analyzes and predicts the user preference through a neural network model, the user basic information and the assembled building block information are directly introduced into the neural network model as discretization features, the user behavior information is introduced into the neural network model as time sequence data through a time sequence model method, the user comment content is abstracted through keyword detection and an NLP-based text emotion analysis technology, the user comment content is introduced into the neural network model as discretization features, and finally a multidimensional preference map is formed for each user, wherein the multidimensional preference map comprises difficulty, type, price, IP and brand.
15. The method for implementing the building block assembly system based on the internet according to claim 13, wherein the user analysis and behavior prediction module analyzes and evaluates each building block product through a neural network model, directly introduces basic product information into the neural network model as discretization characteristics, introduces behavior interaction information of a user into the neural network model as time sequence data through a time sequence model method, and finally forms reference data for each product, wherein the reference data comprises difficulty, complexity, expected assembly time, quality index of the building block assembly system and user evaluation index.
16. The method for implementing the building block assembly system based on the internet according to claim 13, wherein the user analysis and behavior prediction module analyzes and predicts the use condition of each product in each region through a neural network model, and the future sales prediction data of each product in each region is formed by introducing user purchase data, building block assembly system access data and the region where the user is located into the neural network model as discretization features, introducing product price, regional people income and urban and rural differences into the neural network model as discretization features, and introducing the time-varying use condition of the building block assembly system of a single product into the model as time sequence data.
17. The method according to claim 10, wherein the user analysis and behavior prediction module is capable of updating the recommendation server using the predicted user preference model and the product reference data, so that the recommendation server can provide personalized recommendation to the user using the latest user preference information.
18. The method for implementing the building block assembly system based on the internet according to claim 10, wherein the visual display and early warning module counts the data output by the data collection and preprocessing module and displays the statistical data in a chart form, and the statistical data comprises sales volume, user regional distribution, average assembly completion time, user scoring distribution and assembly completion rate of each building block product; and integrating various evaluation and prediction information output by the user analysis and behavior prediction module, and displaying reference data and prediction data in a chart form, wherein the reference data comprises difficulty, complexity, quality index of a building block assembly system and user evaluation index of each product, and the prediction data comprises user group portraits and proportions and future sales predictions of each region.
19. The method for realizing the building block assembly system based on the internet according to claim 10, wherein the visual display and early warning module can match and early warn potential risk points according to manually set rules, and can automatically detect and early warn the potential risk points by adopting a neural network algorithm.
20. The method for implementing an internet-based building block assembly system according to claim 19, wherein the visual presentation and early warning module is capable of early warning of potential risk points, comprising: products with possibly reduced future sales, products with unreasonable pricing, products with possibly insufficient inventory or overstocked inventory predicted from the future sales, products with lower user evaluation index, products with lower user completion assembly rate, products with lower quality of building block assembly systems, products with possibly problems or design defects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310101328.1A CN115826833B (en) | 2023-02-13 | 2023-02-13 | Implementation method of building block assembly system based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310101328.1A CN115826833B (en) | 2023-02-13 | 2023-02-13 | Implementation method of building block assembly system based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115826833A CN115826833A (en) | 2023-03-21 |
| CN115826833B true CN115826833B (en) | 2023-05-26 |
Family
ID=85521055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310101328.1A Active CN115826833B (en) | 2023-02-13 | 2023-02-13 | Implementation method of building block assembly system based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115826833B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DK177170B1 (en) * | 2008-07-04 | 2012-04-16 | Lego As | Method and system for product development |
| CN103197845A (en) * | 2013-04-02 | 2013-07-10 | 乐淘奇品网络技术（北京）有限公司 | Method for selecting commodity components by utilizing option boxes through web pages |
| CN105978959B (en) * | 2016-04-29 | 2019-08-30 | 腾讯科技（深圳）有限公司 | Dummy model methods of exhibiting, device and system |
| CN107261490A (en) * | 2017-07-06 | 2017-10-20 | 腾讯科技（深圳）有限公司 | Realize intelligent toy interactive method, client and intelligent toy |
| CN110427132A (en) * | 2019-07-27 | 2019-11-08 | 厦门城市职业学院（厦门市广播电视大学） | A kind of 3D specification and its method for pushing |
| CN111598978B (en) * | 2020-05-08 | 2023-09-26 | 上海实迅网络科技有限公司 | Article instruction book display system and display method based on AR technology |
| CN114518816A (en) * | 2020-11-16 | 2022-05-20 | 北京六十六号互动科技有限公司 | Demonstration method, device, terminal and storage medium for splicing process of splicing toys |
| CN113778408A (en) * | 2021-07-29 | 2021-12-10 | 深圳点猫科技有限公司 | Building block code serialization method, device, system and medium |
-
2023
- 2023-02-13 CN CN202310101328.1A patent/CN115826833B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115826833A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564414A (en) | Method of Commodity Recommendation based on behavior under line and system | |
| CN111859160B (en) | Session sequence recommendation method and system based on graph neural network | |
| CN108665355A (en) | Financial product recommends method, apparatus, equipment and computer storage media | |
| US11275596B2 (en) | System and method for optimizing a user interface and a system and method for manipulating a user's interaction with an interface | |
| CN104978665A (en) | Brand evaluation method and brand evaluation device | |
| CN109145245A (en) | Predict method, apparatus, computer equipment and the storage medium of clicking rate | |
| CN111949887B (en) | Article recommendation method, apparatus and computer readable storage medium | |
| CN109670104A (en) | Information-pushing method, unit and storage medium based on machine learning | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN110348895A (en) | A kind of personalized recommendation method based on user tag, device and electronic equipment | |
| CN110096681A (en) | Contract terms analysis method, device, equipment and readable storage medium storing program for executing | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN112149352B (en) | Prediction method for marketing activity clicking by combining GBDT automatic characteristic engineering | |
| CN114266443A (en) | Data evaluation method and device, electronic equipment and storage medium | |
| CN115147130A (en) | Problem prediction method, apparatus, storage medium, and program product | |
| CN115222433A (en) | Information recommendation method and device and storage medium | |
| CN115826833B (en) | Implementation method of building block assembly system based on Internet | |
| CN111695625A (en) | Mobile application popularity prediction method based on multi-level attention mechanism network | |
| CN110209944A (en) | A kind of stock analysis teacher recommended method, device, computer equipment and storage medium | |
| CN109119157A (en) | A kind of prediction technique and system of infant development | |
| CN116127188A (en) | Target feedback value determining method and device, electronic equipment and storage medium | |
| CN115631008B (en) | Commodity recommendation method, device, equipment and medium | |
| CN109445581B (en) | Large-scale scene real-time rendering method based on user behavior analysis | |
| CN113971581A (en) | Robot control method and device, terminal equipment and storage medium | |
| CN109960777B (en) | Personalized recommendation method and system for article comment, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |