Systems and methods for multi-stage online ordering
The system addresses the inefficiencies in current online procurement systems by classifying and controlling the disclosure of information, using machine learning to match buyers and suppliers effectively, ensuring secure and efficient procurement processes for complex orders.
Patent Information
- Application Number
- PCT/US2024/029101
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-16
- Filing Date
- 2024-05-13
- Publication Date
- 2024-11-21
AI Technical Summary
Current online procurement systems lack features for efficient information exchange between buyers and suppliers, making it difficult to identify and match suitable partners, especially for complex products requiring hundreds to tens of thousands of components, and they do not allow for controlled disclosure of proprietary information, posing a risk during the procurement process.
A system and method that classify order and user information into public and privileged data, progressively disclosing them in a controlled manner, using machine learning models to match buyers and suppliers based on their information and profiles, allowing for secure information sharing and negotiation on a multi-stage online ordering platform.
Facilitates efficient supplier discovery and matchmaking, enabling buyers to find suitable partners for complex orders while protecting proprietary information, improving supply chain efficiency and product design through secure and controlled information exchange.
Smart Images

Figure US2024029101_21112024_PF_FP_ABST
Abstract
Description
SYSTEMS AND METHODS FOR MULTI-STAGE ONLINE ORDERINGCROSS-REFERENCE
[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 502,476, filed May 16, 2023, which is hereby incorporated by reference in its entirety.BACKGROUND
[0002] E-commerce networks provide a means for electronically connecting buyers and suppliers. Buyers can enhance their supplier network by being electronically connected to a variety of suppliers. As a result, buyers can obtain better selection and pricing, and suppliers can realize additional sales.
[0003] However, current online procurement systems do not provide features that allow information exchange between buyers and suppliers at a large scale. Although some of the online procurement systems allow users to manage existing partners, it is difficult for buyers and suppliers to identify new partners efficiently. As a product can often involve hundreds to tens of thousands of components to manufacture or assemble, supplier discovery has become a bottleneck that gates supply chain improvement and advanced product design.
[0004] Moreover, current online procurement systems do not allow information exchange between buyers and suppliers in a highly controllable manner. It is beneficial to disclose sufficient order and product information to quickly locate buyers or suppliers that perfectly match. Nevertheless, it raises a risk of disclosing proprietary technical and business information during the procurement process.SUMMARY
[0005] There are needs for an online procurement platform that facilitates buyers and suppliers in fulfilling purchase orders. The systems and methods disclosed herein classify order information and user information into public data and privileged data, and progressively disclose them in a controlled manner. The system and methods disclosed herein also match buyers and suppliers based at least in part on their order information, product information and business profiles. Buyers and suppliers are allowed to access a large scale of business partner candidates, share and exchange information in a highly controllable manner, quickly locate potential business partners, and perform negotiations and business transactions on the platform.
[0006] The systems and methods disclosed herein have a variety of potential uses. For example, the system and methods as described herein may allow gathering supplier information in support of various procurement processes including Requests for Information (RFI), Requests for Proposal (RFP), Requests for Quote (RFQ), and other procurement processes (RFX). Thesystem and methods as described herein may be used as a collaborative communication tool in support of various design processes including hardware design, for example, in soliciting supplier feedback on the manufacturability of a part as designed, or in re-designing a part to make it more manufacturable (e.g., the Design for Manufacture or DFM process). The system and methods as described herein may be used as a uniquely effective buyer and supplier matchmaking tool. A buyer may send a public section of a multi-stage order to a large number of suppliers via the ordering platform as described herein, where each supplier may individually have some or all of the known capabilities associated with the order (e.g., access to stainless steel and the equipment to machine, paint, and assemble). The multi-stage ordering platform as described herein may allow buyers to share public details about their orders at scale, and allow suppliers who are especially capable of producing the given part with exceptional pricing, quality, or speed to respond and present their unique capabilities.
[0007] An aspect of the present disclosure provides a computer-implemented method for providing online procurement between a buyer and suppliers, comprising receiving a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product, classifying the dataset as public data or nonpublic data based at least in part on the description of the order, the description of the product, or the image, and controlling suppliers’ access to the dataset based at least in part on the classification.
[0008] In some embodiments, classifying the dataset may comprise automatically classifying the dataset.
[0009] In some embodiments, classifying the dataset may comprise applying a classification model to the dataset. The classification model may comprise a machine learning model.
[0010] In some embodiments, the public data may comprise one or more of a quantity of the product, an expected date of order fulfillment, or an estimated price.
[0011] In some embodiments, the privileged data may comprise a technical specification of the product and a business identification of the buyer.
[0012] In some embodiments, controlling suppliers’ access to the dataset may comprise allowing access to the public data and restricting access to the privileged data.
[0013] In some embodiments, the method may further comprise displaying the public data and the privileged data via a user interface (UI). In some embodiments, the UI may comprise a graphical user interface (GUI).
[0014] In some embodiments, the method may further comprise displaying public data in a first display region of the UI and privileged data in a second display region of the UI, whereinthe second display region may be separate from the first display region. The first and second display regions may be color-coded.
[0015] In some embodiments, the UI may further comprise a text chat display region.
[0016] In some embodiments, the method may further comprise automatically generating an agreement comprising a unique identifier of the buyer and a unique identifier of a supplier.
[0017] In some embodiments, the method may further comprise identifying one or more supplier profiles that match the dataset associated with the order using a matching engine. In some embodiments, the matching engine may process one or more input comprising the dataset associated with the order, a geographical location of the buyer, an industrial field of the order, and an industrial code associated with the order. In some embodiments, the matching engine may comprise a machine learning model.
[0018] In some embodiments, the method may further comprise automatically sending notifications to one or more suppliers corresponding to the one or more supplier profiles that match the dataset associated with the order.
[0019] In some embodiments, the method may further comprise categorizing a supplier profile using a categorization engine. In some embodiments, the categorization engine may process one or more input comprising products and services that a supplier provides, an equipment that the supplier uses, a previously fulfilled order or an active order associated with the supplier.
[0020] In some embodiments, the method may further comprise monitoring a status of the order.
[0021] In some embodiments, the method may further comprise storing the dataset in a database.
[0022] Another aspect of the present disclosure provides a system comprising one or more computer processors and computer memory coupled thereto. The computer memory comprises machine executable code that, upon execution by the one or more computer processors, implements any of the methods above or elsewhere herein.
[0023] Another aspect of the present disclosure provides a non-transitory computer readable medium comprising machine executable code that, upon execution by one or more computer processors, implements any of the methods above or elsewhere herein.
[0024] Additional aspects and advantages of the present disclosure will become readily apparent to those skilled in this art from the following detailed description, wherein only illustrative embodiments of the present disclosure are shown and described. As will be realized, the present disclosure is capable of other and different embodiments, and its several details are capable of modifications in various obvious respects, all without departing from the disclosure.Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The novel features of the present disclosure are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present disclosure will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the present disclosure are utilized, and the accompanying drawings (also “Figure” and “FIG.” herein), of which:
[0026] FIG. l is a block diagram of a networked system for providing multi-stage online ordering between buyers and suppliers, in accordance with some embodiments of the present disclosure;
[0027] FIG. 2 is a block diagram of classification of a buy-initiated order, in accordance with some embodiments of the present disclosure;
[0028] FIG. 3 is a workflow diagram of a multi-stage online ordering process for classifying order information and controlling user access, in accordance with some embodiments of the present disclosure;
[0029] FIG. 4 is a workflow diagram of a multi-stage online ordering process for matching business partners and notifying matching partners, in accordance with some embodiments of the present disclosure;
[0030] FIG. 5 is a system signaling program for performing multi-stage online ordering, in accordance with some embodiments of the present disclosure;
[0031] FIG. 6 is an example user interface of the multi-stage ordering system, in accordance with some embodiments of the present disclosure;
[0032] FIG. 7 is an example public display region on the user interface of the multi-stage online ordering system, in accordance with some embodiments of the present disclosure;
[0033] FIG. 8 is an example user interface of the multi-stage online ordering system for generating agreements, in accordance with some embodiments of the present disclosure;
[0034] FIG. 9 is an example non-disclosure agreement generated by the multi-stage online ordering system, in accordance with some embodiments of the present disclosure;
[0035] FIG. 10 is an example user interface of the multi-stage online ordering system including a private display region and a negotiation region, in accordance with some embodiments of the present disclosure;
[0036] FIG. 11 is an example negotiation region on the user interface of the multi-stage online ordering system, in accordance with some embodiments of the present disclosure;
[0037] FIG. 12 is an example of technical compilation generated by the multi-stage online ordering system, in accordance with some embodiments of the present disclosure;
[0038] FIG. 13 is an example user interface of the multi-stage online ordering system for business negotiation, in accordance with some embodiments of the present disclosure;
[0039] FIG. 14 is an example user interface of the multi-stage online ordering system for user management and notification, in accordance with some embodiments of the present disclosure;
[0040] FIG. 15 is an example user interface of the multi-stage online ordering system for order management, in accordance with some embodiments of the present disclosure;
[0041] FIG. 16 is an example user interface of the multi-stage online ordering system for product and material tracking, in accordance with some embodiments of the present disclosure;
[0042] FIG. 17 is an example user interface of the multi-stage online ordering system for order tracking, in accordance with some embodiments of the present disclosure;
[0043] FIG. 18 is another example user interface of the multi-stage online ordering system for order tracking, in accordance with some embodiments of the present disclosure; and
[0044] FIG. 19 shows a computer system that is programmed or otherwise configured to provide multi-stage online ordering between buyers and suppliers.DETAILED DESCRIPTION
[0045] While various embodiments of the present disclosure have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions may occur to those skilled in the art without departing from the present disclosure. It should be understood that various alternatives to the embodiments of the present disclosure described herein may be employed.Definitions
[0046] Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present subject matter belongs.
[0047] As used in this specification, “some embodiments,” “further embodiments,” or “a particular embodiment,” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase “in some embodiments,” or “in further embodiments,” or “in a particular embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0048] As used in this specification and the appended claims, the terms “artificial intelligence,” “artificial intelligence techniques,” “artificial intelligence operation,” and “artificial intelligence algorithm” generally refer to any system or computational procedure that may take one or more actions to enhance or maximize a chance of achieving a goal. The term “artificial intelligence” may include “generative modeling,” “machine learning” (ML), or “reinforcement learning” (RL). As used in this specification and the appended claims, the terms “machine learning,” “machine learning techniques,” “machine learning operation,” and “machine learning model” generally refer to any system or analytical or statistical procedure that may progressively improve computer performance of a task.
[0049] As used in this specification and the appended claims, when the term “no more than,” “less than,” or “less than or equal to” precedes the first numerical value in a series of two or more numerical values, the term “no more than,” “less than,” or “less than or equal to” applies to each of the numerical values in that series of numerical values. For example, less than or equal to 3, 2, or 1 is equivalent to less than or equal to 3, less than or equal to 2, or less than or equal to 1. When the term “at least,” “greater than,” or “greater than or equal to” precedes the first numerical value in a series of two or more numerical values, the term “at least,” “greater than” or “greater than or equal to” applies to each of the numerical values in that series of numerical values. For example, greater than or equal to 1, 2, or 3 is equivalent to greater than or equal to 1, greater than or equal to 2, or greater than or equal to 3.
[0050] As used in this specification, “or” is intended to mean an “inclusive or” or what is also known as a “logical OR,” wherein when used as a logic statement, the expression “A or B” is true if either A or B is true, or if both A and B are true, and when used as a list of elements, the expression “A, B or C” is intended to include all combinations of the elements recited in the expression, for example, any of the elements selected from the group consisting of A, B, C, (A, B), (A, C), (B, C), and (A, B, C); and so on if additional elements are listed. As such, any reference to “or” herein is intended to encompass “and / or” unless otherwise stated.
[0051] As used in this specification and the appended claims, the indefinite articles “a” or “an,” and the corresponding associated definite articles “the” or “said,” are each intended to mean one or more unless otherwise stated, implied, or physically impossible. Yet further, it should be understood that the expressions “at least one of A and B, etc.,” “at least one of A or B, etc.,” “selected from A and B, etc.” and “selected from A or B, etc.” are each intended to mean either any recited element individually or any combination of two or more elements, for example, any of the elements from the group consisting of “A,” “B,” and “A AND B together,” etc.
[0052] As used in this specification and the appended claims, the term “about” or “approximately” may mean within an acceptable error range for the value, which will depend in part on how the value is measured or determined, e.g., the limitations of the measurement system. For example, “about” may mean within 1 or more than 1 standard deviation, per the practice in the art. Alternatively, “about” may mean a range of up to 20%, up to 10%, up to 5%, or up to 1% of a given value. Where values are described in the application and claims, unless otherwise stated the term “about” meaning within an acceptable error range for the particular value may be assumed.
[0053] As used in this specification and the appended claims, the term “order”, “ordering”, “procurement” may be used interchangeably.Overview
[0054] Disclosed herein is a system for providing online procurement between a buyer and suppliers. The system may comprise at least one processor having access to a memory, wherein the memory stores instructions executable by the at least one processor that, when executed by the at least one processor, cause the at least one processor to perform operations comprising receiving a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product, classifying the dataset as public data or privileged data based at least in part on the description of the order, the description of the product, or the image, and controlling suppliers’ access to the dataset based at least in part on the classification.
[0055] FIG. l is a block diagram of a networked system for providing multi-stage online procurement between buyers and suppliers, in accordance with some embodiments of the present disclosure. The networked system 100 comprises one or more buyer devices 110, one or more supplier devices 120, and a multi-stage online ordering system 150, all of which are connected to a network 140. The multi-stage online ordering system 150 is also connected to one or more servers 130.
[0056] The buyer devices 110 and supplier devices 120 may be computing devices that provide access to the multi-stage online ordering (or progressively disclosed ordering, PDO) system 150. A computing device may be a desktop computer, laptop computer, supercomputer, or mainframe computer. A computing device may also be a mobile computing device, comprising a smartphone, wearable device, personal digital assistant (PDA), tablet computer, or the like. The buyer devices 110 and supplier devices 120 may comprise a user application that allows buyers and suppliers to access the multi-stage online ordering system 150. Users may be allowed to review and post order information, control the level of information exchange with business partners, conduct business negotiations and transactions with partners, and trackingorders, products, etc. In some embodiments, the user application may comprise one or more of a desktop application, a web application, a mobile application, and a cloud application. A desktop application may be implemented using MICROSOFT WINDOWS, APPLE MACINTOSH, or other operating systems. A mobile application may be implemented using ANDROID, iOS, or other operating systems.
[0057] The multi-stage online ordering system 150 comprises a classification engine 152 configured to classify order information and user information. In some embodiment, the order information may comprise a dataset associated with a buyer-initiated order, including a description of an order, a description of a product to be ordered, an image of the product to be ordered. The user information may comprise business profile (e.g., business identification) of the user. The classification engine 152 may classify the order and user information as public data or privileged data. In some embodiment, public data may comprise technical field of the order, quantity of the product, desired order fulfillment or product delivery time, desired price, types of raw or processed materials to produce the product in the order, equipment required to produce or assemble the product. Private data may comprise a business profile or identification of the buyer, a technical description of the product, instructions of manufacturing and / or assembling the product, an image of a prototype, a drawing of the product.
[0058] The classification engine 152 may automatically partition the order information and user information and classify the partitioned information as public or privileged. In some embodiments, a buyer may provide abundant information from various input channels on the user interface of the system 150. For example, she may select desired quantity of the product to be order and delivery date from a scroll down menu on the user interface, type a brief technical description of the product in a text box, and upload various forms of documents via the user interface of the multi-stage online ordering system 150. The classification engine 152 may partition the information and classify which part may contain privileged data and which part may be public. In some embodiments, the classification engine 152 may comprises a classification model (e.g., a machine learning model). The classification model may be a natural language processing (NLP) model that identifies the order information and user information for the classification. The classification model may be an image processing model that identifies the images and drawings uploaded by the users for the classification. The classification engine 152 will be described in further detail in accordance with FIG. 2.
[0059] The multi-stage online ordering system 150 may control access to the dataset based at least in part on their classification. In some embodiments, the system 150 may provide a user interface (UI) to place classified dataset in different display regions of the UI. The UI may comprise a graphical user interface (GUI). The UI may comprise a first region displaying publicdata of a buyer-initiated order, a second region with controlled access to privileged data. The first and second regions may be separate from one another, and color coded for visualization. In some embodiments, the user interface may provide a private / confidential region only accessible to user themselves, including the business goal, internal name of the product or project, private notes, etc.
[0060] Users may have access to order information in the public display region. In some embodiments, the user interface may only show the public display region while having other regions hidden from the users. In other embodiments, the user interface may display a plurality of blurred out or locked regions with a corresponding notification that the user has no authority to access. The user interface may provide one or more representative images indicating later stages of the business transaction, for example, a sample negotiation page and statistics of the same type of orders fulfilled in the past, to encourage users to register or log into the platform and send bids for the order.
[0061] The system 150 may allow buyers to adjust the level of information sensitivity based at least in part on their need and navigate information between different display regions. In some embodiments, the classification engine 152 may classify a drawing of the product as privileged and post it in the display region with limited access. The buyer may decide to share the drawing and move it to the public display region regardless the recommended classification.
[0062] In some embodiments, the multi-stage online ordering system 150 may generate a scope statement based at least in part on the buyer-initiated order. The scope statement, as part of the public data displayed in the UI, may comprise a concise and structured summary of the order that lists critical order information and / or buyer requirement, for example, “we need a non-standard connector (see attached picture),” “it is an urgent order with one week lead time,” etc. The system 150 may comprise a rule-based engine or a machine learning model that processes the keywords and / or images provided in the buyer-initiated order and recommend the scope statement. Upon reviewing the scope statement, suppliers may determine in an efficient manner whether the supplier has the necessary equipment, expertise, and access to materials to produce the order, and whether the order is profitable based at least in part on the desired price and delivery date. For orders of a given commodity type or technical field, the format of the statement may be consistent to further improve its efficacy in providing key information in the order.
[0063] In some embodiments, the rule-based engine or machine learning model in the system 150 may generate a scope statement based at least in part on public information associated with the order. The system 150 may comprise a tracking engine 156 that tracks production and trade information of products as well as raw and processed materials in thepublic domain or from third-party servers / databases. The rule-based engine or machine learning model may process the production and trade information along with the current order information, and generate a corresponding scope statement. For example, the system 150 may identify a supply shortage or price change of lithium-ion batteries. When a buyer initiates a lithium-ion battery order via the user interface of the system 150, the rule-based engine or machine learning model may generate a scope statement prioritizing the quantity of the product, desired price and delivery date based at least in part on the order information. In other embodiments, the rule-based engine or machine learning model may process the buyer’s prior order information and based at least in part on which, generate a scope statement for the current order. The prior order information may comprise one or more prior orders ranked and / or scored by successful supplier conversions. A percentage of successful supplier conversions may be defined as a ratio between a number of suppliers who inquired on a previous order and a number of suppliers who registered on the multi-stage online ordering system 150 as a new user or signed in as an existing user.
[0064] The multi-stage online ordering system 150 may provide various mechanisms to facilitate the communication between buyers and suppliers while controlling information exchange. In some embodiments, the system 150 may assign a unique identifier to each user, which may be used throughout the procurement process without disclosing business or personal profiles until necessary. The unique identifier may correspond to a buyer or a supplier as corporation or individual. The unique identifier may be used in isolation, for example, in a single business transaction or used repeatedly.
[0065] In some embodiments, the multi-stage online ordering system 150 may generate an anonymous agreement between business partners to facilitate information exchange. The system 150 may generate a non-disclosure agreement (ND A) between a buyer and supplier candidates. When a supplier reviews a buyer-initiated order via the user interface of the system 150 and is interested, the system may generate a customized NDA based at least in part on the buyer profile, supplier profile, and buyer-initiated order. The NDA may comprise unique identifiers of the buyer and supplier candidate. When the NDA is signed and approved by both parties, the system 150 may update the supplier’s authority of accessing different levels of information provided by the buyer.
[0066] The multi-stage online ordering system 150 may provide one or more user interfaces for business negotiation. In some embodiments, the user interface may display one or more negotiation regions separate from the public display region. For each round of negotiation, the system 150 may provide a designated negotiation region on the user interface such that the parties can keep on track of the process. The negotiation region may comprise a desired priceand an order delivery date from both parties, description of the products to be produced, raw and processed materials, necessary equipment, customization requirement, uploaded documents.
[0067] The multi-stage online ordering system 150 may provide one or more communication regions, for example, a text chat session on the user interface. The text chat session may be separate from the negotiation regions on the user interface. Alternatively, the text chat record may be integrated into each round of negotiation and displayed in the corresponding negotiation region. The text chat session may allow buyers and suppliers to negotiate in real time while having quick access to technical information, business information and documents via the user interface. In some embodiments, the multi-stage online ordering system 150 may allow users to conduct anonymous chat on an order. When a buyer posts an order, the business identification of the buyer may be classified as privileged data by the classification engine 152. When suppliers found the order on the user interface, they may be allowed to anonymously initiate a chat with the buyer via the user interface. The anonymity may be preserved throughout the bid and communication process.
[0068] In some embodiments, the multi-stage online ordering system 150 may provide artificial intelligence (Al) text chat functions. The user interface may be configured to display an Al text chat session with a user. The Al text chat session may comprise a chatbot that processes text input by a user and responds with relevant information. For example, the chatbot may answer questions from the user regarding an order, a product, or a supplier. The chatbot may interpret text using one or more natural language processing (NLP) and / or natural language understanding (NLU) models. The chatbot may use an autoregressive model to produce output text. The chatbot may produce output text using a transformer-based model. A transformer model may comprise an encoder and / or a decoder stage. A transformer-based model may be a generative pre-trained transformer (GPT) model. For example, when the user inputs an inquiry, the chatbot may determine the intent of the user by identifying one or more keywords in the inquiry and one or more contexts of the inquiry and previous inquiries, at least in part by processing the inquiry of the user. The chatbot may provide answers to the inquiry or ask targeted questions for specific information. In some embodiment, the chatbot may be built or integrated with GOOGLE Dialogflow, AMAZON Lex, IBM Watson Assistant, ChatGPT or the like. The user interface may be further configured to enable a user to end the Al text chat session and initiate a person-to-person text chat with the subject. The user interface may provide a visualization indicating that the Al text chat session has ended, and the person-to-person text chat session has begun. The visualization may comprise text, image, and / or video content. The user interface may further be configured to enable users to end the Al text chat session and initiate a person-to-person conversation. The user interface may further provide a visualizationindicating that the Al text chat session has ended, and the person-to-person text chat session has begun.
[0069] Depending on the progress of the negotiation, the multi-stage online ordering system 150 may further adjust the supplier’s authority to access information. In some embodiments, the system 150 may provide one or more technical documentation regions on the user interface for disclosing information with a higher level of sensitivity. The technical documentation region may be separate from public regions and negotiation regions, and with a different color code. The region may display a detailed description of the product, specific instructions of manufacturing or assembling the product, and intellectual property (e.g., patents, trade secrets). The system 150 may request further authentications from suppliers and approval from buyers.
[0070] As further illustrated in FIG. 1, the multi-stage online ordering system 150 comprises a matching engine 154 that identifies matching business partners. The matching engine 154 may comprise a rule-based engine or machine learning model. The input to the matching engine 154 may comprise information stored in the database 164 of the system, including buyer profiles, supplier profiles, previous orders, products, raw and processed materials to produce the products, accessibility to equipment, industrial fields of the products, industrial codes of the products. In some embodiments, the supplier profile used as an input to the matching engine 154 may comprise geographical location of the business and / or manufacturing site, business operation information (e.g., number of employees, annual revenue), products and services, available equipment, long-term and short-term availability, history of business transactions, and ratings. The input to the matching engine 154 may also comprise public and privileged data associated with the current order. The matching engine 154 may process these inputs and predict business partners that match the order or the need of the users. The system 150 may also allow users to refine the matching process. In some embodiments, the system 150 may allow buyers to select one or more matching criteria to determine supplier candidates. Based at least in part on the selected matching criteria, the matching engine 154 may recommend suppliers that match the buyer’s need.
[0071] In some embodiments, the matching engine 154 may identify matching business partners based at least in part on keywords in the business profiles and / or orders. For example, some of the technical terms may be used in the same or substantially similar technical fields and thus, frequently appear in the buyer and supplier profiles, previous and current orders, and business information in the public or third-party databases. The matching engine 154 may identify these keywords and generate a list of business partners that use the same keywords. When buyers and suppliers post information via the user interface of the system 150, the matching engine 154 may also recommend keywords based at least in part on their existingbusiness profiles and technical information of the products and orders, to maintain the consistency of the technical terms. The matching engine 154 may use an algorithm that includes weights for different factors and / or keywords described above. Some keywords may have a greater weight than others based on importance and / or relevance of the keywords. For example, a keyword that includes the name of the part may have a greater weight than a color of the part. As another example, a size of the part may have the same weight as the number of parts. In some embodiments, the user may set how important certain factors / keywords are. In some embodiments, the matching engine 154 may automatically determine or include pre-determined weights for certain categories of keywords.
[0072] The multi-stage online ordering system 150 may provide various user management functions. In some embodiments, the system 150 may provide buyers a marketing campaign mechanism to initiate targeted communications with multiple suppliers. The matching engine 154 may recommend a list of supplier candidates to a buyer who may have a new order or look for new business partners in general. The system 150 may allow the buyer to send automatic notifications to each supplier candidate on the list along with the order information and business profile of the buyer. For example, the system may comprise a rule-based engine configured to send notifications to selected supplier candidates and when no reply is received after a predetermined time period, to send automatic follow-up notifications. Similarly, suppliers may be allowed to manage potential buyer candidates via the marketing campaign mechanism. Hence, instead of seeking business partners individually via in-person and online meetings, both buyers and suppliers are provided with a large pool of potential business partners. More importantly, the system 150 may enable the users to quickly identify and manage matching partners at a large scale.
[0073] As further illustrated in FIG. 1, the multi-stage online ordering system 150 may comprise a multi-functional tracking engine 156. In some embodiments, the tracking engine 156 may track each order from the time the order is initiated to the completion or termination. The tracking engine 156 may also track the progress of negotiations between buyers and suppliers. In other embodiments, the tracking engine 156 may track and analyze public information associated with users of the system and orders thereof. The tracking engine 156 may crawl or otherwise scan the Internet and other related sites and databases to identify business information associated with buyers and suppliers, for example, technical fields of their business, business operation information (e.g., number of employees, key stakeholders, annual revenues), existing product lines, new product lines that may be under development, components and materials required in manufacturing and / or assembling the products. The tracking engine 156 may also track production and trade information of products and raw / processed materials required inmanufacturing and assembling the products. The production and trade information may be collected from existing business transactions occurred via the platform 150. In addition or alternatively, the production and trade information may be collected from public domain or third-party servers / database with a large geographical and temporal coverage. For example, the tracking engine 156 may track production and trade flow of lithium-ion batteries and lithium hydroxide, a material used in the production of lithium batteries over the past one day, three days, one week, two weeks, three weeks, one month, two months, four months, six months, eight months, ten months, one year, two years, three years, four years, and five years. The information collected by the tracking engine 156, comprising content of an order, duration of the order, bids received for the order, number and duration of negotiations, result of the order, production and trade information of the products and materials associated with the order, may be stored in the database 164 of the system 150. The information may also be as part of the input to the matching engine 154, categorization engine 158, and aggregation engine 162 to establish and maintain the buyer and supplier profiles.
[0074] The multi-stage online ordering system 150 may comprise a categorization engine 158. In some embodiments, the categorization engine 158 may process order information collected by the tracking engine 156 and categorize the orders. Based at least in part on their status, orders may be categorized as unfilled or filled. An unfilled order may refer to an open order that has not been fulfilled. An unfilled order may be searchable by all suppliers. Alternatively, an unfilled order may refer to an order that is sent to a list of supplier candidates via the marketing campaign. A filled order may refer to an order that is fulfilled by a supplier. A filled order may not be searchable by other suppliers.
[0075] In some embodiments, the categorization engine 158 may categorize an order as continuous. Depending on the nature of the industry, an order can be fulfilled quickly, leaving a short time window for buyers to access a larger scale of suppliers and for other suppliers on the market to be aware of the order and compete for it. A continuous order may refer to an open order even after the original order event is already fulfilled. In some embodiments, the categorization engine 158 may process one or more of the records of previous orders, frequency of reorders from the same buyer in a pre-determined time period, negotiations history, rating of the current supplier, and generate a predicted order status as continuous. Hence, the order is still open to bids from suppliers, providing an opportunity for the buyer to locate alternative suppliers.
[0076] In some embodiments, the categorization engine 158 may rate and score buyer and supplier profiles. In some embodiments, the categorization engine 158 may process user activities collected by the tracking engine 156 corresponding to each buyer and supplier,including a number of orders posted by a buyer and / or fulfilled by a supplier, numbers and duration of negotiations prior to conclusion of an order, success rate of fulfilling an order, delivery time, etc. The categorization engine 158 may also process public information collected by the tracking engine 156 regarding business information associated with buyers and suppliers, for example, technical fields of their business, business operation information, existing product lines, new product lines that may be under development, components and materials required in manufacturing and / or assembling the products. In other embodiments, the system may provide self-evaluation for users to fill in via the user interface, and user questionnaires to evaluate a current or previous order. The categorization engine 158 may process these evaluations and categorize the buyer / supplier profiles by ratings and scores.
[0077] In some embodiments, the categorization engine 158 may partition the buyer and supplier profiles and generate ratings or scores for a plurality of categories. The categories may comprise timeliness in response, accuracy in posted information, price, on time delivery, longterm and short-term availability, accessibility to specialized equipment, capability of customized products, etc. In other embodiments, the categorization engine 158 may generate evaluations, ratings or scores in more specialized categories, including interest and capability in working on prototypes, and production of a priced quote from hand drawings. The generated ratings or scores for both buyers and suppliers may be viewable by other users to form informed decision in their ordering process. The generated ratings or scores may also be used as input to the matching engine 154 to identify business partners with high ratings and / or capabilities in specialized areas.
[0078] The multi-stage online ordering system 150 may comprise an aggregation engine 162 that aggregates information. In some embodiments, the aggregation engine 162 may aggregate orders by different categories, for example, technical fields, industries, products, and raw / processed materials required to produce or assemble the product. The aggregation engine 162 may also aggregate production and trade information of products and materials collected by the tracking engine 156, and generate a trade history comprising quantity, price, duration, trade flow, etc.
[0079] As further illustrated in FIG. 1, the multi-stage online ordering system 150 is connected to one or more servers 130 via the network 140. In some embodiments, the servers 130 may provide data storage functions. The server may implement storage of data using one or more databases. A database may comprise storage containing a variety of data consistent with disclosed embodiments, comprising buyer and supplier profiles, order history, negotiation history, etc. In other embodiments, the server 130 may be a third-party server, comprising a third-party electronic commerce platform, a payment service provider, a shipping serviceprovider, a financial institution system, in communication with one or more of the buyer devices 110, supplier devices 120, and multi-stage online ordering system 150.
[0080] The multi-stage online ordering system 150 further comprises a database 164. The database 164 may be implemented as a computer system with a storage device. In some embodiments, the database 164 such as a local database and a cloud database may be used by components of the system to perform one or more operations consistent with the disclosed embodiments. One or more cloud databases and local databases may utilize any suitable database techniques. Database content may be viewable based at least in part on permissions associated with buyer and supplier profiles.
[0081] The database 164 may store order information comprising current orders, order history associated with each buyer and supplier, negotiation history of each order, classifications of order information (e.g., public and private data) generated by the classification engine 152, categorizations of orders (e.g., filled, unfilled, continuous) generated by the categorization engine 158. The database 164 may also store buyer and supplier profiles, comprising example, name and geographical location of the business, number of employees, key stakeholders, technical field, manufacture capability, accessibility to equipment and materials, long-term and short-term availability, operational customization capability. The database 164 may also store categorizations and evaluations (e.g., ratings and scores) of buyer and supplier profiles determined by the categorization engine 158. The database may also store business and technical information associated with buyers and suppliers collected by the tracking engine 156 and aggregation engine 162 from the public and third-party databases.
[0082] The network 140 may be a wired or wireless network that connects the multi-stage online ordering system 150 with devices 110, 120 and servers 130. Examples of the network 140 may include, but are not limited to, a distributed computing system, a cloud computing system, a wide area network (WAN) (e.g., the Internet, an enterprise network), a local area network (LAN) (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a direct connection between two computing devices, a peer-to-peer network, and any combinations thereof. The network 140, may employ a wired and / or a wireless mode of communication. In general, any network topology may be used.Examples of Machine Learning Models
[0083] The systems, methods, computer-readable storage media, and platforms described herein may implement one or more machine learning models. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may comprise a machine learning model. The machine learning model may implement one or more machine learning algorithms. Machine learning maygenerally involve identifying and recognizing patterns in existing data to facilitate making predictions for subsequent data. Machine learning, whether analytical or statistical in nature, may provide deductive or abductive inference based at least in part on real or simulated data. The machine learning model may be a trained model. The machine learning model may be a trained model for image analysis or natural language processing. For example, the machine learning model may be a trained model that is trained through supervised learning (e.g., various parameters are determined as weights or scaling factors). Machine learning may comprise one or more of regression analysis, regularization, classification, dimensionality reduction, ensemble learning, meta learning, association rule learning, cluster analysis, anomaly detection, deep learning, or ultra-deep learning. Machine learning may comprise, but is not limited to: k-means, k-means clustering, k-nearest neighbors, learning vector quantization, linear regression, nonlinear regression, least squares regression, partial least squares regression, logistic regression, stepwise regression, multivariate adaptive regression splines, ridge regression, principal component regression, least absolute shrinkage and selection operation (LASSO), least angle regression, canonical correlation analysis, factor analysis, independent component analysis, linear discriminant analysis, multidimensional scaling, non-negative matrix factorization, principal components analysis, principal coordinates analysis, projection pursuit, Sammon mapping, t-distributed stochastic neighbor embedding, AdaBoosting, boosting, gradient boosting, bootstrap aggregation, ensemble averaging, decision trees, conditional decision trees, boosted decision trees, gradient boosted decision trees, random forests, stacked generalization, Bayesian networks, Bayesian belief networks, naive Bayes, Gaussian naive Bayes, multinomial naive Bayes, hidden Markov models, hierarchical hidden Markov models, support vector machines, encoders, decoders, auto-encoders, stacked auto-encoders, perceptrons, multi-layer perceptrons, artificial neural networks, feedforward neural networks, convolutional neural networks, recurrent neural networks, long short-term memory, deep belief networks, deep Boltzmann machines, deep convolutional neural networks, deep recurrent neural networks, generative adversarial networks, transformers, long short-term memory networks (LSTM), masked autoencoders, etc.
[0084] The systems, methods, computer-readable storage media, and platforms described herein may implement one or more deep-learning techniques. Deep learning is an example of machine learning that may be based at least in part on a set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers, with complex structures or otherwise, composed of multiple non-linear transformations. In some embodiments, a drop out method may be used to reduce overfitting. At each training stage, individual nodes are either “dropped out” of the net (e.g., ignored) with a probability 1-p or kept with probability p, so thata reduced network is left; incoming and outgoing edges to a dropped-out node may also be removed. In some embodiments, the reduced network may be trained on the data in that stage. The removed nodes may then be reinserted into the network with their original weights. Convolutional Neural Network
[0085] The systems, methods, computer-readable storage media, and platforms described herein may implement one or more machine learning models. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may comprise a convolution neural network. The convolutional neural network 400 comprises a deep learning algorithm that takes in input (e.g., images and drawings provided by users) and generates a precited output classification. The convolutional neural network may have one or more of convolution layers and pooling layers. The convolution layers may perform convolution operations between the input and convolution filters (matrix of parameters) that are learned over many gradient update iterations during the training. Convolutions operate over 3D tensors, called feature maps, with two spatial axes (height and width) as well as a depth axis (i.e., channel axis). The convolution operation may extract patches from its input feature map and applies the same transformation to all of these patches, producing an output feature map. This output feature map may be a 3D tensor: it has a width and a height. Its depth may be arbitrary, because the output depth is a parameter of the layer, and different channels in the depth axis stand for filters that encode specific aspects of the input.
[0086] A pooling layer may operate a pooling function that divides input into nonoverlapping two-dimensional spaces. For example, the feature maps may comprise output generated from previous convolution operations and used as input to subsequent pooling layers, respectively. A filter with a size of 2 * 2 is slid over the feature maps using a stride of 2. For a receptive field with a size of 2 * 2 (e.g., the part of the feature maps under the filter), an average pooling operation may produce an average value of the four pixels in the receptive field, whereas a maximum pooling operation may select a maximum value of the four pixels in the receptive field. As such, pooling operations may consolidate the features learned by the convolutional neural network and gradually reduce the spatial dimension of the feature maps to minimize the numbers of parameters and computations in the network.
[0087] An input may be processed via a convolution operation to generate feature maps, which in turn are processed by a pooling operation to generate pooled features maps. As the convolutional neural network may comprise a plurality of convolution layers and pooling layers where output from a previous layer may be input to a next layer, the convolution and pooling operations may repeat, thereby generating feature maps and pooled feature maps, respectively.In some embodiments, the pooled feature maps which are 2-dimensional arrays, may be processed via a flattening operation, which generates a 1 -dimensional vector. The vector may be processed via a fully connected layer, which generates predicted output classification.
[0088] In some embodiments, the convolutional neural network may be scaled to construe machine learning models with better accuracy and efficiency. For example, one or more of depth, width, resolution of the convolutional neural network may be scaled. Depending on the input, the convolutional neural network may be scaled in a single dimension or multiple dimensions. For example, for higher resolution input data, the width and depth of the convolutional neural network may be scaled, such that larger receptive fields are able to capture similar features that include more pixels in larger images.Recurrent Neural Network
[0089] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more recurrent neural networks. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may implement recurrent neural networks. A recurrent neural network allows previous output generated from a previous step to be used as input to the current step. For example, when a recurrent neural network processes natural language, it may account for the position and meaning of each word in a sentence and use that information to predict the next word in the sequence. In some embodiments, a recurrent neural network may take as input a one-hot encoded vector corresponding to a word in a sentence at a current time step t and generate a hidden representation at the current time step t that acts a “memory” of the network, based at least in part on the current input and a hidden representation generated at a previous time step t-1. The recurrent neural network may have input to hidden connections parameterized by a weight matrix U, hidden-to-hidden recurrent connections parameterized by a weight matrix W, and hidden-to-output connections parameterized by a weight matrix V. The weights may be the same across each layer of the network. During the training via backpropagation and gradient descent, the weights may be optimized.Long Short-Term Memory
[0090] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more long short-term memory (LSTM) techniques. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may implement LSTM techniques. Unlike standard feedforward neural networks, LSTM may use feedback connections. The LSTM architecture may provide a short-term memory for a recurrent neural network (RNN). Such RNN may process not only single data points (e.g., images), but also entiresequences of data. The connection weights and biases in the RNN may change once per episode of training, analogously to how physiological changes in synaptic strengths store long-term memories. The activation patterns in the network may change once per time-step, analogously to how the moment-to-moment change in electric firing patterns in the brain store short-term memories. The LSTM architecture may provide a short-term memory for a RNN that may last many (e.g., thousands) timesteps.
[0091] In some embodiments, a LSTM unit may comprise a cell, an input gate, an output gate, and a forget gate. The cell may remember values over arbitrary time intervals and the input gate, the output gate, and the forget gate may regulate the flow of information into and out of the cell. Forget gates may be used to decide what information to discard from a previous state by assigning a previous state, compared to a current input, a value between 0 and 1 (e.g., a (rounded) value of 1 may mean to keep the information, and a value of 0 means to discard the information). The input gate may decide which pieces of new information to store in the current state, using the same system as the forget gates. The output gate may control which pieces of information in the current state to output (e.g., by assigning a value from 0 to 1 to the information, considering the previous and current states). Selectively outputting relevant information from the current state may allow that the LSTM network maintains useful, longterm dependencies to make predictions, both in current and future time-steps. LSTM networks may be well-suited to classifying, processing, and making predictions based at least in part on time series data, since lags of unknown duration between important events in a time series may occur. LSTMs may resolve the vanishing gradient problem that may be encountered when training traditional RNNs. Relative insensitivity to gap length may be an advantage of LSTM over RNNs, hidden Markov models, and other sequence learning methods in numerous applications.
[0092] In some embodiments, LSTMs may be used with one or more various types of neural networks (e.g., convolutional neural networks (CNNs), deep neural network (DNNs), recurrent neural networks (RNNs), etc.). In some embodiments, CNNs, LSTM, and DNNs are complementary in modeling capabilities and may be combined in a unified architecture. For example, in such unified architecture, CNNs may be well-suited at reducing frequency variations, LSTMs may be well-suited at temporal modeling, and DNNs may be well-suited for mapping features to a more separable space. For example, input features to a machine learning model using LSTM techniques in the unified architecture may include segment features for each of a plurality of segments. To process the input features for each of the plurality of segments, the segment features for the segment may be processed using one or more CNN layers to generate first features for the segment. The first features may be processed using one or more LSTM relayers to generate second features for the segment. The second features may be processed using one or more fully connected neural network layers to generate third features for the segments, where the third features may be used for classification operations. In some embodiments, to process the first features using the one or more LSTM layers to generate the second features, the first features may be processed using a linear layer to generate reduced features having a reduced dimension from a dimension of the first features. The reduced features may be processed using the one or more LSTM layers to generate the second features. Short-term features having a first number of contextual frames may be generated based at least in part on the input features, where features generated using the one or more CNN layers may include long-term features having a second number of contextual frames that are more than the first number of contextual frames of the short-term features. In some embodiments, the one or more CNN layers, the one or more LSTM layers, and the one or more fully connected neural network layers may be jointly trained to determine trained values of parameters of the one or more CNN layers, the one or more LSTM layers, and the one or more fully connected neural network layers. In some embodiments, the input features include log-mel features having multiple dimensions. The input features include one or more contextual frames indicating a temporal context of a signal (e.g., input data). Implementations for such unified architecture may leverage complementary advantages associated with each of a CNN, LSTM, and DNN. For example, convolutional layers may reduce spectral variation in input and help the modeling of LSTM layers. Having DNN layers after LSTM layers may help reduce variation in the hidden states of the LSTM layers. Training the unified architecture jointly may provide a better overall performance. Training in the unified architecture may also remove the need to have separate CNN, LSTM and DNN architectures. By adding multi-scale information into the unified architecture, information may be captured at different time scales.Decision Tree and Random Forest
[0093] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more decision tree or random forest techniques. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may implement decision tree or random forest techniques. A decision tree may be a supervised machine learning algorithm that may be applied to both regression and classification problems. Decision trees may mimic the decisionmaking process of a human brain. For example, a decision tree may grow from a root (base condition), and when the tree meets a condition (internal node / feature), the tree splits into multiple branches. The end of the branch that does not split anymore is an outcome (leaf). A decision tree may be generated using a training data set according to the following operations:(1) starting from a root node (the entire dataset), the algorithm may split the dataset in two branches using a decision rule or branching criterion; (2) each of the two branches may generate a new child node; (3) for each new child node, the branching process may be repeated until the dataset cannot be split any further; (4) each branching criterion can be chosen to maximize information gain (e.g., a quantification of how much a branching criterion reduces a quantification of how mixed the labels are in the children nodes). The labels may be the data or the classification that is predicted by the decision tree.
[0094] A random forest regression is an extension of the decision tree model that tends to yield more robust predictions by stretching the use of the training data partition. Whereas a decision tree may make a single pass through the data, a random forest regression may bootstrap 50% of the data (e.g., with replacement) and build many trees. Rather than using all explanatory variables as candidates for splitting, a random subset of candidate variables may be used for splitting to produce trees that have different data and different variables. The predictions from the trees, collectively referred to as the forest, are then averaged to produce the final prediction. Many trees (e.g., one hundred trees) may be included in a random forest model, with a number (e.g., 3, 6, 10, etc.) of terms sampled per split, a minimum of number (e.g., 1, 2, 4, 10, etc.) of splits per tree, and a minimum split size (e.g., 16, 32, 64, 128, 256, etc.). Random forests may be trained in a similar way as decision trees. Training a random forest may include the following operations: (1) select randomly k features from the total number of features; (2) create a decision tree from these k features using the same operations as for generating a decision tree; and (3) repeat the previous two operations until a target number of trees is created. Support Vector Machines
[0095] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more support vector machine learning techniques. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may implement support vector machine learning techniques. Support vector machines (SVMs) may be supervised learning models with associated learning algorithms that analyze data for classification and regression analysis. SVMs may be a robust prediction method, being based at least in part on statistical learning. SVMs may be well-suited for domains characterized by the existence of large amounts of data, noisy patterns, or the absence of general theories.
[0096] SVMs may map input vectors into high dimensional feature space through non-linear mapping function, chosen a priori. In this high dimensional feature space, an optimal separating hyperplane may be constructed. The optimal hyperplane may then be used to determine things such as class separations, regression fit, or accuracy in density estimation. More formally, aSVM constructs a hyperplane or set of hyperplanes in a high or infinite-dimensional space, which may be used for classification, regression, or other tasks like outlier detection.
[0097] Support vectors may be defined as the data points that lie closest to the decision surface (or hyperplane). Support vectors may therefore be the data points that are most difficult to classify and may have direct bearing on the optimum location of the decision surface. Given a set of training examples, each marked as belonging to one of two categories, a SVM training algorithm may build a model that assigns new examples to one category or the other, making the algorithm a non-probabilistic binary linear classifier. SVM may map training examples to points in space to maximize the width of the gap between the two categories. New examples may then be mapped into that same space and predicted to belong to a category based at least in part on which side of the gap the examples fall. In addition to performing linear classification, SVMs may efficiently perform a non-linear classification using what is called the kernel trick, implicitly mapping inputs into high-dimensional feature spaces.
[0098] Within a support vector machine, the dimensionally of the feature space may be large. For example, a fourth-degree polynomial mapping function may cause a 200-dimensional input space to be mapped into a 1.6 billionth dimensional feature space. SVMs assist in discovering knowledge from vast amounts of input data.Gradient Boosting
[0099] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more gradient boosting techniques. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may implement gradient boosting techniques. Gradient boosting may be a machine learning technique used in regression and classification tasks, among others. Gradient boosting may give a prediction model in the form of an ensemble of weak prediction models, which are typically decision trees. When a decision tree is the weak learner, the resulting algorithm is called gradient-boosted trees. A gradient-boosted trees model is built in a stage-wise fashion as in other boosting methods, but generalizes the other methods by allowing optimization of an arbitrary differentiable loss function. k-Nearest Neighbors
[0100] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more K-nearest neighbors (KNN) techniques. In some embodiments, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may implement KNN techniques. KNN is a non-parametric classification method. In KNN classification, the output is a class membership. An object is classified by a plurality vote of neighbors, with the object beingassigned to the class most common among the k nearest neighbors (k is a positive integer, typically small). If k=l, then the object is assigned to the class of that single nearest neighbor. In KNN regression, the output is the property value for the object. This value is the average of the values of k nearest neighbors. KNN is a type of classification wherein the function is approximated locally, and computation is deferred until function evaluation. Since this algorithm relies on distance for classification, if the features represent different physical units or come in vastly different scales, then normalizing the training data may improve accuracy.Training and Validation of Machine Learning Models
[0101] In some embodiments, the machine learning model used to implement the systems, methods, computer-readable media, and techniques disclosed herein may be trained by way of supervised learning. A data set of cell images may be divided into a training set, a test set, and, in some cases, a validation set. In supervised learning, training dataset and validation dataset may be annotated with ground truth labels. During the training process, training dataset may be repeatedly presented to the machine learning model, and for each sample presented during training, output generated by the machine learning model may be compared with the corresponding ground truth labels. The difference between the ground truth and the predicted output may be calculated, and the machine learning model may be modified to cause the output to more closely approximate or predict the ground truth. In some embodiments, a backpropagation algorithm may be utilized to cause the output to more closely approximate the ground truth. During many training iterations, the machine learning may generate outputs that progressively match the corresponding ground truth labels. Subsequently, when new and previously unseen input is presented, the machine learning model may generate an output classification value indicating which of the categories the new sample is most likely to fall into. In other words, the machine learning model may “generalize” from its training to new, previously unseen input.
[0102] In some embodiments, the machine learning model may be validated using a validation dataset (e.g., distinct from training data set) to determine accuracy and robustness of the model. Such validation may include applying the model to the validation dataset to make predictions derived from the validation dataset. The machine learning model may then be evaluated to determine whether the performance is sufficient based upon the derived predictions. The sufficiency criteria applied to the machine learning model may vary depending upon the size of the training data set available for training, the performance of previous iterations of trained models, or user-specified performance requirements. If the machine learning model does not achieve sufficient performance, additional training may be performed. Additional training may include refinement of the model or retraining on a different training dataset, after which thenewly trained model may again be validated and assessed. When the machine learning model has achieved sufficient performance, in some cases, the machine learning model may be stored for present or future use. The model may be stored as sets of parameter values or weights for analysis of further input (e.g., further relevant parameters to use as further predicted variables, further explanatory variables, further user interaction data, etc.), which may also include analysis logic or indications of model validity. In some embodiments, a plurality of machine learning models may be stored for generating predictions under different sets of input data conditions. In some embodiments, the plurality of machine learning models may be stored in a database (e.g., associated with a server).
[0103] In some embodiments, the machine learning model may be an individual learning model. An individual learning model is based at least in part on a machine learning software module having trained on data from a single individual and thus, a machine learning software module that utilizes an individual learning model is configured to be used on a single individual on whose data the module was trained. For example, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may comprise an individual learning model trained on training data including user activities corresponding to individual buyers and suppliers. In other embodiments, the machine training model may be a global training model. A global training model is based at least in part on a machine training software module having trained on data from multiple individuals and thus, a machine training software module that utilizes a global training model is configured to be used on multiple individuals. For example, one or more of the classification engine 152, matching engine 154, tracking engines 156, categorization engine 158, and aggregation engine 162 may comprise a global learning model trained on training data comprising user activities across the multi-stage online order platform and / or from third-party sites, servers, and databases.
[0104] In some embodiments, the classification engine 152 may be trained on dataset associated with previous and current orders across the platform, comprising order description, product description, customization requirement, images and drawings. When the classification engine 152 is trained via supervised learning, the classification record of previous orders determined by the buyer may be used as ground truth to train the engine. The buyer may determine a technical description of a product as privileged. The classification engine 152 may be trained on the technical description and the classification determined by the buyer. When a newly seen description that contains similar technical terms is posted, the classification engine 152 may predict it as privileged. As another example, the buyer may upload an image of a product via the user interface and determine it as public. The classification engine 152 may betrained on the image and the classification determined by the buyer. When a new image that contains a similar object is posted, the classification engine 152 may predict it as public data.
[0105] In some embodiments, the matching engine 154 may be trained on business profiles of buyers and suppliers stored in the multi-stage online order platform and user activities. The training data may comprise technical field of the business, previous orders posted by buyers and fulfilled by suppliers, ratings of buyers and suppliers, etc. When the matching engine 154 is trained via supervised learning, the final determination from buyers and suppliers may be used as ground truth to train the engine. For example, the matching engine 154 may identify twenty supplier candidates that match the buyer’s order or business profile. The buyer may initiate business negotiation with three of them and eventually decide to select one supplier to fulfill the order. The matching engine 154 may compare the ground truth with the prediction and adjust parameters of the model for optimization.Prediction of Machine Learning Models
[0106] Following training, the machine learning model may be used to process new and unseen data and generate predictions. In some embodiments, the trained classification engine 152 may classify new orders posted by buyers and predict which part of the order as public and which as privileged. The trained matching engine 154 may identify supplier profiles that may fulfill newly posted orders, and business partners that may match technical and business interest of a new user. The categorization engine 158 may predict the categorization of a newly fulfilled order as continuous.
[0107] The prediction phase uses constructed and optimized hypothesis function from the training phase to predict a probability of the classification. In some embodiments, a probability threshold may be used to tune the sensitivity of the trained model. For example, the probability threshold may be 1%, 2%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95%, 98%, or 99%. In some embodiments, the probability threshold may be adjusted if the accuracy, sensitivity, or specificity falls below a predefined adjustment threshold. For example, if the accuracy of the probability threshold falls below the adjustment threshold, the system may extend the training period and / or require additional input data.
[0108] FIG. 2 is a block diagram of classification of a buy-initiated order, in accordance with some embodiments of the present disclosure. The classification system 200 comprises a classification engine 210 (e.g., classification engine 152 in FIG. 1) that processes one or more inputs comprising order information 220, product information 230, and buyer information 240, and classify the inputs or a subset thereof as public data 250 or privileged data 260. One or more of the order information 220, product information 230 and buyer information 240 may beprovided by the buyer via the user interface of the multi-stage ordering system. In addition or alternatively, one or more of the order information 220, product information 230 and buyer information 240 may previously be stored in the database (e.g., database 164 in FIG. 1) of the system or crawled from public or other third-party databases or servers. The information 220, 230, and 240 may be in a variety of forms including text, images, drawings, videos, links, or any combination thereof.
[0109] In some embodiments, the order information 220 may comprise technical or industrial field of the order, a description of the order, expected order fulfillment or delivery date, desired price. The product information 230 may comprise technical field of the product to be produced, quantity of the product, description of the product, equipment and raw / processed materials that may be required to produce the product, technical specification of the product, customization requirement. The buyer information 240 may comprise a business profile of the buyer including name, location, size, business and technical interest, existing product lines, and new product lines that may be under development.
[0110] The classification engine 210 may process one or more of the inputs 220, 230 and 240 and classify the input or a subset of the input as public data 250 or privileged data 260. In some embodiments, the public data 250 may comprise technical or industrial area of the order, expected order fulfillment or delivery time, technical or industrial area of the product to be ordered, quantity of the product, equipment and raw / processed materials that may be required to produce the product. The privileged data 260 may comprise technical specification of the product, requirement of customization, and business profiles of the buyer.
[0111] In some embodiments, the classification engine 210 may comprise a classification model. The classification model may be a neural network. The classification model may comprise a trained neural network for natural language processing or image processing. The classification engine may process text in the order information 220 and product information 230 and classify which word or combination of words may comprise privileged information. The classification engine may process images and / or drawings uploaded by the buyer and classify whether one or more objects in the images and / or drawings may be privileged data.
[0112] Disclosed herein is a computer-implemented method for providing online procurement between buyers and suppliers. In some embodiments, the method may comprise classifying a dataset associated with a buyer-initiated order as public data or privileged data and controlling suppliers’ access to the dataset based at least in part on the classification. In other embodiments, the method may comprise identifying business partners that match a user’s need and sending automatic notifications to the business partners.
[0113] FIG. 3 is a workflow diagram of a multi-stage online ordering process 300 for classifying order information and controlling user access, in accordance with some embodiments of the present disclosure. The multi-stage online ordering system may receive a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product (see 310). The buyer-initiated order may be placed by the buyer via the user interface of the online ordering system. In some embodiments, the system may comprise a classification engine (e.g., 152 in FIG. 1 and 210 in FIG. 2) that classifies the dataset as public data or privileged data based at least in part on the description of the order, the description of the product, or the image (see 320). The system may control the suppliers’ access to the dataset based at least in part on the classification (see 330). In some embodiments, suppliers may only access to public data. The system may automatically generate an agreement (e.g., non-disclosure agreement) between the buyer and a supplier who may be interested in the posted order. When the agreement is signed and approved by both parties, the system may update the supplier’s access authority and disclose some or all of the privileged data.
[0114] FIG. 4 is a workflow diagram of a multi-stage online ordering process 400 for matching business partners and notifying matching partners, in accordance with some embodiments of the present disclosure. The multi-stage online ordering system may receive a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product (see 410). In some embodiments, the system may comprise a matching engine that identifies one or more supplier profiles matching one or more of a description of the order, a description of a product to be ordered, or an image of the product (see 420). The system may provide marketing campaign functions by sending automatic notifications to the matching suppliers and disclosing order information and business profile of the buyer (see 430). The system may also send automatic follow-up notifications to keep track of the broadcast.
[0115] FIG. 5 is a system signaling program for performing multi-stage online ordering, in accordance with some embodiments of the present disclosure. The multi-stage online ordering process 500 may be implemented among one or more buyer devices 510, one or more supplier devices 530, and a multi-stage ordering system 520. Buyers and suppliers may access the respective user interface of the system 520 to accomplish the procurement from posting an order to negotiate the order, and to fulfill the order. At each step of the process, the system 520 may provide a variety of functions on the user interface, some of which will be illustrated in FIG. 6- 18 and described in further detail below.
[0116] A buyer may initiate the online ordering process by accessing the user interface of the multi-stage ordering system 520 (see 512, order initiation). FIG. 6 is an example user interface of the multi-stage ordering system, in accordance with some embodiments of the present disclosure. The user interface 600 may comprise a plurality of color-coded display regions. The display region 610 display public information of a buyer-initiated order, comprising the status of the order (e.g., unfilled, continuous), type or industrial field of the order, quantity of a product to be ordered. The buyer may provide a technical description of the product, comprising technical parameters (e.g., diameter, height, length) and detailed specifications. The display region 610 also displays the status of the order. In some embodiments, the categorization engine of the system may categorize the status of orders by types. As illustrated in FIG. 6, for example, when a buyer initiates a new order, the categorization engine may determine the default status as unfilled and thus, the order may be searchable by suppliers.
[0117] The user interface 600 may further comprise an agreement display region 620 where an agreement (e.g., non-disclosure agreement) between the buyer and suppliers who are interested in the order may be generated. The user interface 600 may further comprise a privileged data display region 630 that displays privileged information associated with the order. In some embodiments, the classification of the order information may be determined by the classification engine. As illustrated, the region 630 displays a technical description of product to be ordered and an attachment uploaded by the buyer. As this is the beginning of the ordering process, the display regions 620 and 630 may only be viewable by the buyer.
[0118] FIG. 7 is an example public display region in the user interface of the multi-stage online ordering system, in accordance with some embodiments of the present disclosure. The public display region 700 comprises a plurality of subregions 710, 720, 730, 740, and 750. The subregion 710 displays the status of the order, type or industrial field of the order, quantity of the product to be ordered, and expected delivery date. The subregion 710 also displays a frequency of reorder (e.g., one time order, order every month, order every three months, order every six months, order every year). In some embodiments, the categorization engine (e.g., 158 in FIG. 1) of the system may compare previous orders from the same buyer over a pre-determined period and determine whether there are similar orders. Based at least in part on the ordering patterns corresponding to the buyer, the categorization engine may provide a recommended frequency of reorder. In other embodiments, the categorization engine may process the frequency of reorder as part of the input and generate a predicted or recommended status of the order. For example, when a repeat order is newly fulfilled, the categorization engine may recommend the status ofthe order as continuous instead of filled. Hence, the order is viewable by other suppliers who may reach out to the buyer for future order fulfillment.
[0119] As further illustrated in FIG. 7, the subregion 730 displays additional requests from the buyer to be conveyed to suppliers. For example, the buyer may identify the material of the product as steel in the subregion 750, while being interested in alternative materials (e.g., aluminum) displayed in the subregion 730. The buyer may also upload one or more attachments in the subregion 740. In addition, the buyer may post scope and intent in the subregion 750, comprising e.g., a scope statement that summarizes the content of the order generated by the system, or specific requirements for suppliers to comply with. In some embodiments, the system may comprise a rule-based engine or machine learning model (e.g., natural language processing model) that identify the keywords provided in the buyer-initiated order and recommend the scope statement.
[0120] In some embodiments, the classification engine of the system may classify some of the order information (e.g., technical description of the product) as privileged data and recommend the information to be moved from the public display region to other display regions that display privileged data (see 522, order classification). Nevertheless, the system may provide buyers flexibility in navigating the order information among different display regions. Buyers may choose to publish technical description of the product and corresponding business identification in the public display region, regardless the recommendations from the classification engine.
[0121] Suppliers may access the user interface of the online ordering system and seek for orders of interest. In some embodiments, suppliers may only have access to information displayed in the public display region (e.g., 610 in FIG. 6 and 700 in FIG. 7). Suppliers may initiate a communication with the buyer via, for example, text chat session on the interface. Suppliers may request buyers to disclose classified information (see 532, classified information request).
[0122] Upon receiving the supplier’s request, the buyer may adjust the supplier’s access authority to the order information, in order to accelerate the ordering process. The system may provide a plurality of options for the buyer to progressively disclose information. The buyer may request a non-disclosure agreement from the supplier (see 514, non-disclosure agreement request). FIG. 8 is an example user interface of the multi-stage online ordering system for generating agreements, in accordance with some embodiments of the present disclosure. The buyer may upload company documents and technical documents to be shared with the supplier, which are listed in the display regions 810 and 820. The buyer may also request the supplier tosign a non-disclosure agreement generated and customized by the system (see display region 830).
[0123] FIG. 9 is an example non-disclosure agreement generated by the multi-stage online ordering system, in accordance with some embodiments of the present disclosure. In some embodiments, the system may designate a unique identifier to each user and generate an anonymous agreement between a buyer and a supplier. In other embodiments, the buyer and / or supplier may disclosure their business identification as desired. The supplier may sign and upload the agreement via the respective user interface.
[0124] When the signature is received and approved by the buyer, the privileged data may be accessible to the supplier (see 524, classified information disclosure). At this stage, the parties have formally started the first round of negotiation (see, 516 and 536, negotiations). In some embodiments, the supplier’s user interface may display one or more color-coded regions separate from the public display region. The color-coded regions may comprise a display region that display privileged data associated with the order and technical documents uploaded by the buyer, and a negotiation region that displays communication record for a given round of negotiation.
[0125] FIG. 10 is an example user interface of the multi-stage online ordering system including a private display region and a negotiation region, in accordance with some embodiments of the present disclosure. The system may provide the flexibility for both buyers and suppliers in the visibility and information management. For example, the user interface provides a scroll down menu 1040 for the user to easily change the visibility between anonymous and identifiable, depending on the progress of the negotiation. The buyer may access the user interface 1000 that comprises a plurality of color-coded regions displaying information with different levels of confidentiality. The display region 1010 may display private information only accessible to the buyer, comprising internal title of the order or product to be produced, internal name of the project, any private notes. The display region 1020 may display public data identified by the classification engine and shared with all suppliers. The display region 1030 named as Negotiation 1 may comprise communications between the parties, product description and related documents, desired price, customization requirement. Both the buyer and supplier may access the information in the display region 1030. Similarly, the supplier may access the user interface that comprises a plurality of color-coded regions displaying information with different levels of confidentiality. The supplier may access all information displayed in the public display region 1020 and negotiation region 1030. The supplier may also have a designated private region on the user interface.
[0126] FIG. 11 is an example negotiation region on the user interface of the multi-stage online ordering system, in accordance with some embodiments of the present disclosure. The negotiation region 1100 may list technical details of the product to be ordered, drawings of the product, and images of the prototype. The buyer may also provide additional requirements for the supplier to comply with.
[0127] During the negotiation process, the buyer may provide business and technical information to the supplier at different time and from different input channels. For example, the buyer may type a paragraph of technical description of a product in a text box, select the type of equipment or materials from a dropdown menu, and upload different forms of attachments. The aggregation engine (e.g., 162 in FIG. 1) of the system may aggregate the information and generate a compiled document. FIG. 12 is an example of technical compilation generated by the multi-stage online ordering system, in accordance with some embodiments of the present disclosure. The compilation 1200 lists all technical documents uploaded by the buyer at different time, each with a version number, name and brief description of the file. The compilation 1200 also comprises representative images of the product, and step-by-step instructions for production and / or assembly. A unique identifier (e.g., QR code) may also be included in the compilation 1200. The buyer may review and edit the compilation 1200 before sharing it to the supplier.
[0128] FIG. 13 is an example user interface of the multi-stage online ordering system for business negotiation, in accordance with some embodiments of the present disclosure. The user interface 1300 provides a text chat session corresponding to each round of negotiation. The text chat may be initiated by any party before or after the non-disclosure agreement is signed. The parties may remain anonymous or disclose their business identification. As illustrated in FIG. 13, for example, an anonymous buyer posted an order with sufficient product information and received bids from two suppliers. The user interface 1300 displays the bids in display regions 1310 and 1320, along with other information provided by the supplier (e.g., estimated lead time) and by the system (e.g., records of fulfilled orders corresponding to the supplier). Each bid may have a corresponding text chat session displaying communication records between the parties. For example, an anonymous supplier sent a new bid stating a short lead time and a text message to the buyer. The bid and message are displayed in regions 1310 and 1330, respectively.
[0129] FIG. 14 is an example user interface of the multi-stage online ordering system for user management and notification, in accordance with some embodiments of the present disclosure. The user interface 1400 comprises display regions 1410 and 1420 for displaying private and public information, respectively. As described in some of the aforementioned embodiments, the matching engine (e.g., 154 in FIG. 1) of the system may identify potential business partners that match the order information published by the buyer. As illustrated in FIG.14, for example, an anonymous buyer published an order for battery module case. Based at least in part on the order information in the public display region 1420, the matching engine may identify 98 supplier profiles that match the order. In some embodiments, the system may provide the marketing campaign function that allows the buyer to connect with suppliers on a large scale. The buyer may use the scroll down menus 1430 and 1440 to select “notify matching suppliers”. The system may send notifications to all matching suppliers to broadcast the order. The buyer may further refine the supplier candidates by, for example, accessibility to specific equipment, geographical location, record of successful business transactions of the supplier, and ratings of the supplier. The marketing campaign and broadcast function to targeted supplier candidates allows buyers to connect with matching suppliers in a highly efficient manner.
[0130] FIG. 15 is an example user interface of the multi-stage online ordering system for order management, in accordance with some embodiments of the present disclosure. The system may group the orders from the same buyer by different categories, for example, product, industrial field, time, and price. Each order within the same group may be listed with the name of the product to be order, the status of the order, expected delivery date, a brief summary of the order, etc. The system may provide color-coded notifications to indicate an update or status of the order.
[0131] The multi-stage online ordering system may provide up-to-date information of orders and products in the same or similar industrial field on a large scale (see, 526, production and trade tracking and 528, order tracking). In some embodiments, the tracking engine and aggregation engine (e.g., 156 and 162 in FIG. 1) of the multi-stage online ordering system may monitor and aggregate production and trade information of products and required raw / processed materials. The tracking engine and aggregation engine may monitor ordering activities and associated products across the platform, and aggregate orders and products in the same or similar industrial field. The tracking engine may crawl the Internet and third-party databases and servers to identify information related to the production and trading of products and materials regionwide, nationwide and even worldwide. The aggregation engine may aggregate and compile the information for users to review.
[0132] FIG. 16 is an example user interface of the multi-stage online ordering system for product and material tracking, in accordance with some embodiments of the present disclosure. As illustrated, the user interface 1600 provides price trends of lithium-ion cells and lithium hydroxide, the material used in manufacturing the cells during the past seven months. The price trends may reflect all business transactions occurred via the multi-stage online ordering system. Alternatively, the price trends may reflect transactions in a much broader range. Users maysearch products and materials of interest and have a quick overview of price, production, and industrial need.
[0133] FIG. 17 is an example user interface of the multi-stage online ordering system for order tracking, in accordance with some embodiments of the present disclosure. The user interface 1700 allows users to track orders published and fulfilled via the online ordering system. As illustrated, for example, a user may be interested coolant tubing orders in the past four months. The user may refine the search by the order categorization (e.g., unfilled, filled, continuous). The user interface provides a bar chart 1710 indicating numbers of unfilled and continuous orders over the past 120 days. The user may navigate and identify the orders for each week, which are listed in the display region 1720. The user may further refine the search. FIG.18 is another example user interface of the multi-stage online ordering system for order tracking, in accordance with some embodiments of the present disclosure. The user interface 1800 provides a scroll down menu 1810 containing a list of search criteria, comprising types of orders, types of products, status of orders, specific requests from buyers, distance, delivery date, reorder lead time, etc. The order monitoring and flexible search functions may benefit both buyers and suppliers. Buyers may know how many orders are posted and how fast they are fulfilled and thus when posting a similar post, have a reasonable expectation of number of bids, lead time, price range, etc. Supplier may also make informed decisions when sending out bids and negotiating with buyers.Computer systems
[0134] The present disclosure provides computer systems that are programmed to implement methods of the disclosure. FIG. 19 shows a computer system that is programmed or otherwise configured to provide multi-stage online ordering between buyers and suppliers. The computer system 1901 can regulate various aspects of the present disclosure, for example, for classifying order information and identifying matching business partners. The computer system 1901 can be an electronic device of a user or a computer system that is remotely located with respect to the electronic device.
[0135] The computer system 1901 includes a central processing unit (CPU, also “processor” and “computer processor” herein) 1905, which can be a single core or multi core processor, or a plurality of processors for parallel processing. The computer system 1901 also includes memory or memory location 1910 (e.g., random-access memory, read-only memory, flash memory), electronic storage unit 1915 (e.g., hard disk), communication interface 1920 (e.g., network adapter) for communicating with one or more other systems, and peripheral devices 1925, such as cache, other memory, data storage and / or electronic display adapters. The memory 1910, storage unit 1915, interface 1920 and peripheral devices 1925 are in communication with theCPU 1905 through a communication bus (solid lines), such as a motherboard. The storage unit 1915 can be a data storage unit (or data repository) for storing data. The computer system 1901 can be operatively coupled to a computer network (“network”) 1930 with the aid of the communication interface 1920. The network 1930 can be the Internet, an internet and / or extranet, or an intranet and / or extranet that is in communication with the Internet. The network 1930 in some cases is a telecommunication and / or data network. The network 1930 can include one or more computer servers, which can enable distributed computing, such as cloud computing. The network 1930, in some cases with the aid of the computer system 1901, can implement a peer-to-peer network, which may enable devices coupled to the computer system 1901 to behave as a client or a server.
[0136] The CPU 1905 can execute a sequence of machine-readable instructions, which can be embodied in a program or software. The instructions may be stored in a memory location, such as the memory 1910. The instructions can be directed to the CPU 1905, which can subsequently program or otherwise configure the CPU 1905 to implement methods of the present disclosure. Examples of operations performed by the CPU 1905 can include fetch, decode, execute, and writeback.
[0137] The CPU 1905 can be part of a circuit, such as an integrated circuit. One or more other components of the system 1901 can be included in the circuit. In some cases, the circuit is an application specific integrated circuit (ASIC).
[0138] The storage unit 1915 can store files, such as drivers, libraries and saved programs. The storage unit 1915 can store user data, e.g., user preferences and user programs. The computer system 1901 in some cases can include one or more additional data storage units that are external to the computer system 1901, such as located on a remote server that is in communication with the computer system 1901 through an intranet or the Internet.
[0139] The computer system 1901 can communicate with one or more remote computer systems through the network 1930. For instance, the computer system 1901 can communicate with a remote computer system of a user (e.g., a mobile device). Examples of remote computer systems include personal computers (e.g., portable PC), slate or tablet PC’s (e.g., Apple® iPad, Samsung® Galaxy Tab), telephones, Smart phones (e.g., Apple® iPhone, Android-enabled device, Blackberry®), or personal digital assistants. The user can access the computer system 1901 via the network 1930.
[0140] Methods as described herein can be implemented by way of machine (e.g., computer processor) executable code stored on an electronic storage location of the computer system 1901, such as, for example, on the memory 1910 or electronic storage unit 1915. The machine executable or machine-readable code can be provided in the form of software. During use, thecode can be executed by the processor 1905. In some embodiments, the code can be retrieved from the storage unit 1915 and stored on the memory 1910 for ready access by the processor 1905. In some embodiments, the electronic storage unit 1915 can be precluded, and machineexecutable instructions are stored on memory 1910.
[0141] The code can be pre-compiled and configured for use with a machine having a processer adapted to execute the code, or can be compiled during runtime. The code can be supplied in a programming language that can be selected to enable the code to execute in a precompiled or as-compiled fashion.
[0142] Aspects of the systems and methods provided herein, such as the computer system 1901, can be embodied in programming. Various aspects of the technology may be thought of as “products” or “articles of manufacture” typically in the form of machine (or processor) executable code and / or associated data that is carried on or embodied in a type of machine readable medium. Machine-executable code can be stored on an electronic storage unit, such as memory (e.g., read-only memory, random-access memory, flash memory) or a hard disk. “Storage” type media can include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide non-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer into the computer platform of an application server. Thus, another type of media that may bear the software elements includes optical, electrical and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links. The physical elements that carry such waves, such as wired or wireless links, optical links or the like, also may be considered as media bearing the software. As used herein, unless restricted to non-transitory, tangible “storage” media, terms such as computer or machine “readable medium” refer to any medium that participates in providing instructions to a processor for execution.
[0143] Hence, a machine readable medium, such as computer-executable code, may take many forms, including but not limited to, a tangible storage medium, a carrier wave medium or physical transmission medium. Non-volatile storage media include, for example, optical or magnetic disks, such as any of the storage devices in any computer(s) or the like, such as may be used to implement the databases, etc. shown in the drawings. Volatile storage media include dynamic memory, such as main memory of such a computer platform. Tangible transmission media include coaxial cables; copper wire and fiber optics, including the wires that comprise abus within a computer system. Carrier-wave transmission media may take the form of electric or electromagnetic signals, or acoustic or light waves such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media therefore include for example: a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD or DVD-ROM, any other optical medium, punch cards paper tape, any other physical storage medium with patterns of holes, a RAM, a ROM, a PROM and EPROM, a FLASH-EPROM, any other memory chip or cartridge, a carrier wave transporting data or instructions, cables or links transporting such a carrier wave, or any other medium from which a computer may read programming code and / or data. Many of these forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.
[0144] The computer system 1901 can include or be in communication with an electronic display 1935 that comprises a user interface (UI) 1940 for providing, for example, a dashboard. Examples of UI’s include, without limitation, a graphical user interface (GUI) and web-based user interface.
[0145] Methods and systems of the present disclosure can be implemented by way of one or more algorithms. An algorithm can be implemented by way of software upon execution by the central processing unit 1905.Computer program
[0146] In some embodiments, the platforms, systems, media, and methods disclosed herein include at least one computer program, or use of the same. A computer program includes a sequence of instructions, executable by one or more processor(s) of the computing device’s CPU, written to perform a specified task. Computer readable instructions may be implemented as program modules, such as functions, objects, Application Programming Interfaces (APIs), computing data structures, and the like, that perform particular tasks or implement particular abstract data types. In light of the disclosure provided herein, those of skill in the art will recognize that a computer program may be written in various versions of various languages.
[0147] The functionality of the computer readable instructions may be combined or distributed as desired in various environments. In some embodiments, a computer program comprises one sequence of instructions. In some embodiments, a computer program comprises a plurality of sequences of instructions. In some embodiments, a computer program is provided from one location. In other embodiments, a computer program is provided from a plurality of locations. In various embodiments, a computer program includes one or more software modules. In various embodiments, a computer program includes, in part or in whole, one or more webapplications, one or more mobile applications, one or more standalone applications, one or more web browser plug-ins, extensions, add-ins, or add-ons, or combinations thereof.Web application
[0148] In some embodiments, a computer program includes a web application. In light of the disclosure provided herein, those of skill in the art will recognize that a web application, in various embodiments, utilizes one or more software frameworks and one or more database systems. In some embodiments, a web application is created upon a software framework such as Microsoft .NET or Ruby on Rails (RoR). In some embodiments, a web application utilizes one or more database systems including, by way of non-limiting examples, relational, non-relational, object oriented, associative, XML, and document-oriented database systems. In further embodiments, suitable relational database systems include, by way of non-limiting examples, Microsoft SQL Server, mySQL, and Oracle. Those of skill in the art will also recognize that a web application, in various embodiments, is written in one or more versions of one or more languages. A web application may be written in one or more markup languages, presentation definition languages, client-side scripting languages, server-side coding languages, database query languages, or combinations thereof. In some embodiments, a web application is written to some extent in a markup language such as Hypertext Markup Language (HTML), Extensible Hypertext Markup Language (XHTML), or extensible Markup Language (XML). In some embodiments, a web application is written to some extent in a presentation definition language such as Cascading Style Sheets (CSS). In some embodiments, a web application is written to some extent in a client-side scripting language such as Asynchronous JavaScript and XML (AJAX), Flash ActionScript, JavaScript, or Silverlight. In some embodiments, a web application is written to some extent in a server-side coding language such as Active Server Pages (ASP), ColdFusion, Perl, Java, JavaServer Pages (JSP), Hypertext Preprocessor (PHP), Python, Ruby, Tel, Smalltalk, WebDNA, or Groovy. In some embodiments, a web application is written to some extent in a database query language such as Structured Query Language (SQL). In some embodiments, a web application integrates enterprise server products such as IBM Lotus Domino. In some embodiments, a web application includes a media player element. In various further embodiments, a media player element utilizes one or more of many suitable multimedia technologies including, by way of non-limiting examples, Adobe Flash, HTML 5, Apple QuickTime, Microsoft Silverlight, Java, and Unity.Mobile application
[0149] In some embodiments, a computer program includes a mobile application provided to a mobile computing device. In some embodiments, the mobile application is provided to a mobile computing device at the time it is manufactured. In other embodiments, the mobileapplication is provided to a mobile computing device via the computer network described herein.
[0150] In view of the disclosure provided herein, a mobile application is created by techniques known to those of skill in the art using hardware, languages, and development environments known to the art. Those of skill in the art will recognize that mobile applications are written in several languages. Suitable programming languages include, by way of nonlimiting examples, C, C++, C#, Objective-C, Java, JavaScript, Pascal, Object Pascal, Python, Ruby, VB.NET, WML, and XHTML / HTML with or without CSS, or combinations thereof.
[0151] Suitable mobile application development environments are available from several sources. Commercially available development environments include, by way of non-limiting examples, AirplaySDK, alcheMo, Appcelerator, Celsius, Bedrock, Flash Lite, .NET Compact Framework, Rhomobile, and WorkLight Mobile Platform. Other development environments are available without cost including, by way of non-limiting examples, Lazarus, MobiFlex, MoSync, and Phonegap. Also, mobile device manufacturers distribute software developer kits including, by way of non-limiting examples, iPhone and iPad (iOS) SDK, Android SDK, BlackBerry SDK, BREW SDK, Palm OS SDK, Symbian SDK, webOS SDK, and Windows Mobile SDK.Standalone application
[0152] In some embodiments, a computer program includes a standalone application, which is a program that is run as an independent computer process, not an add-on to an existing process, e.g., not a plug-in. Those of skill in the art will recognize that standalone applications are often compiled. A compiler is a computer program(s) that transforms source code written in a programming language into binary object code such as assembly language or machine code. Suitable compiled programming languages include, by way of non-limiting examples, C, C++, Objective-C, COBOL, Delphi, Eiffel, Java, Lisp, Python, Visual Basic, and VB .NET, or combinations thereof. Compilation is often performed, at least in part, to create an executable program. In some embodiments, a computer program includes one or more executable complied applications.Software modules
[0153] In some embodiments, the platforms, systems, media, and methods disclosed herein include software, server, and / or database modules, or use of the same. In view of the disclosure provided herein, software modules are created by techniques known to those of skill in the art using machines, software, and languages known to the art. The software modules disclosed herein are implemented in a multitude of ways. In various embodiments, a software module comprises a file, a section of code, a programming object, a programming structure, a distributedcomputing resource, a cloud computing resource, or combinations thereof. In further various embodiments, a software module comprises a plurality of files, a plurality of sections of code, a plurality of programming objects, a plurality of programming structures, a plurality of distributed computing resources, a plurality of cloud computing resources, or combinations thereof. In various embodiments, the one or more software modules comprise, by way of nonlimiting examples, a web application, a mobile application, a standalone application, and a distributed or cloud computing application. In some embodiments, software modules are in one computer program or application. In other embodiments, software modules are in more than one computer program or application. In some embodiments, software modules are hosted on one machine. In other embodiments, software modules are hosted on more than one machine. In further embodiments, software modules are hosted on a distributed computing platform such as a cloud computing platform. In some embodiments, software modules are hosted on one or more machines in one location. In other embodiments, software modules are hosted on one or more machines in more than one location.Databases
[0154] In some embodiments, the platforms, systems, media, and methods disclosed herein include one or more databases, or use of the same. In view of the disclosure provided herein, those of skill in the art will recognize that many databases are suitable for storage and retrieval of, by way of examples, image, cell state, protocol, and culture condition information. In various embodiments, suitable databases include, by way of non-limiting examples, relational databases, non-relational databases, object-oriented databases, object databases, entity -relationship model databases, associative databases, XML databases, document-oriented databases, and graph databases. Further non-limiting examples include SQL, PostgreSQL, MySQL, Oracle, DB2, Sybase, and MongoDB. In some embodiments, a database is Internet-based. In further embodiments, a database is web-based. In still further embodiments, a database is cloud computing-based. In a particular embodiment, a database is a distributed database. In other embodiments, a database is based at least in part on one or more local computer storage devices.
[0155] While preferred embodiments of the present disclosure have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. It is not intended that the present disclosure be limited by the specific examples provided within the specification. While the embodiments of the present disclosure have been described with reference to the aforementioned specification, the descriptions and illustrations of the embodiments herein are not meant to be construed in a limiting sense. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the embodiments of the present disclosure. Furthermore, itshall be understood that all aspects of the present disclosure are not limited to the specific depictions, configurations or relative proportions set forth herein which depend upon a variety of conditions and variables. It should be understood that various alternatives to the embodiments of the present disclosure described herein may be employed in practicing the embodiments of the present disclosure. It is therefore contemplated that the present disclosure shall also cover any such alternatives, modifications, variations or equivalents. It is intended that the following claims define the scope of the invention(s) and that methods and structures within the scope of these claims and their equivalents be covered thereby.
Claims
CLAIMSWHAT IS CLAIMED IS:
1. A computer-implemented method for providing online procurement between a buyer and suppliers, comprising: receiving a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product; classifying the dataset as public data or privileged data based at least in part on the description of the order, the description of the product, or the image; and controlling suppliers’ access to the dataset based at least in part on the classification.
2. The method according to claim 1, wherein classifying the dataset comprises automatically classifying the dataset.
3. The method according to claim 1 or 2, wherein classifying the dataset comprises applying a classification model to the dataset.
4. The method according to claim 3, wherein the classification model comprises a natural language processing model.
5. The method according to any one of claims 1-4, wherein the public data comprises one or more of a quantity of the product, an expected date of order fulfillment, and / or an estimated price.
6. The method according to any one of claims 1-4, wherein the privileged data comprises a technical specification of the product and / or a business identification of the buyer.
7. The method according to any one of claims 1-6, wherein controlling suppliers’ access to the dataset comprises allowing access to the public data and restricting access to the privileged data.
8. The method according to any one of claims 1-7, further comprising displaying the public data and the privileged data via a user interface (UI).
9. The method according to claim 8, wherein the UI is a graphical user interface (GUI).
10. The method according to claim 8 or 9, further comprising displaying public data in a first display region of the UI and privileged data in a second display region of the UI, wherein the second display region is separate from the first display region.
11. The method according to claim 10, wherein the first and second display regions are color- coded.
12. The method according to any one of claims 8-11, wherein the UI further comprises a text chat session.
13. The method according to any one of claims 1-12, further comprising automatically generating an agreement comprising a unique identifier of the buyer and a unique identifier of a supplier.
14. The method according to any one of claims 1-13, further comprising identifying one or more supplier profiles that match the dataset associated with the order using a matching engine.
15. The method according to claim 14, further comprising processing, via the matching engine, one or more input comprising the dataset associated with the order, a geographical location of the buyer, an industrial field of the order, and an industrial code associated with the order.
16. The method according to claim 14 or 15, wherein the matching engine comprises a machine learning model.
17. The method according to any one of claims 14-16, further comprising automatically sending notifications to one or more suppliers corresponding to the one or more supplier profiles.
18. The method according to any one of claims 1-17, further comprising categorizing a supplier profile using a categorization engine.
19. The method according to claim 18, further comprising processing, via the categorization engine, one or more input comprising products and service that a supplier provides, an equipment that the supplier uses, a previously fulfilled order or an active order associated with the supplier.
20. The method according to any one of claims 1-19, further comprising monitoring a status of the order.
21. The method according to any one of claims 1-20, further comprising storing the dataset in a database.
22. A system for providing online procurement between a buyer and suppliers, comprising: at least one processor having access to a memory, wherein the memory stores instructions executable by the at least one processor that, when executed by the at least one processor, cause the at least one processor to perform operations comprising: receiving a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product; classifying the dataset as public data or privileged data based at least in part on the description of the order, the description of the product, or the image; and controlling suppliers’ access to the dataset based at least in part on the classification.
23. The system according to claim 22, wherein classifying the dataset comprises automatically classifying the dataset.
24. The system according to claim 22 or 23, wherein classifying the dataset comprises applying a classification model to the dataset.
25. The system according to claim 24, wherein the classification model comprises a natural language processing model.
26. The system according to any one of claims 22-25, wherein the public data comprises one or more of a quantity of the product, an expected date of order fulfillment, or an estimated price.
27. The system according to any one of claims 22-26, wherein the privileged data comprises a technical specification of the product and a business identification of the buyer.
28. The system according to any one of claims 22-27, wherein controlling suppliers’ access to the dataset comprises allowing access to the public data and restricting access to the privileged data.
29. The system according to any one of claims 22-28, further comprising displaying the public data and the privileged data via a user interface (UI).
30. The system according to claim 29, wherein the UI is a graphical user interface (GUI).
31. The system according to claim 29 or 30, further comprising displaying public data in a first display region of the UI and privileged data in a second display region of the UI, wherein the second display region is separate from the first display region.
32. The system according to claim 31, wherein the first and second display regions are color- coded.
33. The system according to any one of claims 29-32, wherein the UI further comprises a text chat display region.
34. The system according to any one of claims 22-33, further comprising automatically generating an agreement comprising a unique identifier of the buyer and a unique identifier of a supplier.
35. The system according to any one of claims 22-34, further comprising identifying one or more supplier profiles that match the dataset associated with the order using a matching engine.
36. The system according to claim 35, wherein the matching engine processes one or more input comprising the dataset associated with the order, a geographical location of the buyer, an industrial field of the order, and an industrial code associated with the order.
37. The system according to claim 35 or 36, wherein the matching engine comprises a machine learning model.
38. The system according to any one of claims 35-37, further comprising automatically sending notifications to one or more suppliers corresponding to the one or more supplier profiles.
39. The system according to any one of claims 22-38, further comprising categorizing a supplier profile using a categorization engine.
40. The system according to claim 39, wherein the categorization engine processes one or more input comprising products and service that a supplier provides, an equipment that the supplier uses, a previously fulfilled order or an active order associated with the supplier.
41. The system according to any one of claims 22-40, further comprising monitoring a status of the order.
42. The system according to any one of claims 22-41, further comprising storing the dataset in a database.
43. A non-transitory computer-readable medium comprising machine-executable code that, upon execution by one or more computer processors, implements a method for providing online procurement between a buyer and suppliers, the method comprising: receiving a dataset associated with a buyer-initiated order, the dataset comprising one or more of a description of the order, a description of a product to be ordered, or an image of the product; classifying the dataset as public data or privileged data based at least in part on the description of the order, the description of the product, or the image; and controlling suppliers’ access to the dataset based at least in part on the classification.
44. The computer-readable medium according to claim 43, wherein classifying the dataset comprises automatically classifying the dataset.
45. The computer-readable medium according to claim 43 or 44, wherein classifying the dataset comprises applying a classification model to the dataset.
46. The computer-readable medium according to claim 45, wherein the classification model comprises a natural language processing model.
47. The computer-readable medium according to any one of claims 43-46, wherein the public data comprises one or more of a quantity of the product, an expected date of order fulfillment, or an estimated price.
48. The computer-readable medium according to any one of claims 43-47, wherein the privileged data comprises a technical specification of the product and a business identification of the buyer.
49. The computer-readable medium according to any one of claims 43-48, wherein controlling suppliers’ access to the dataset comprises allowing access to the public data and restricting access to the privileged data.
50. The computer-readable medium according to any one of claims 43-49, further comprising displaying the public data and the privileged data via a user interface (UI).
51. The computer-readable medium according to claim 50, wherein the UI is a graphical user interface (GUI).
52. The computer-readable medium according to claim 50 or 51, further comprising displaying public data in a first display region of the UI and privileged data in a second display region of the UI, wherein the second display region is separate from the first display region.
53. The computer-readable medium according to claim 52, wherein the first and second display regions are color-coded.
54. The computer-readable medium according to any one of claims 50-53, wherein the UI further comprises a text chat display region.
55. The computer-readable medium according to any one of claims 43-54, further comprising automatically generating an agreement comprising a unique identifier of the buyer and a unique identifier of a supplier.
56. The computer-readable medium according to any one of claims 43-55, further comprising identifying one or more supplier profiles that match the dataset associated with the order using a matching engine.
57. The computer-readable medium according to claim 56, wherein the matching engine processes one or more input comprising the dataset associated with the order, a geographical location of the buyer, an industrial field of the order, and an industrial code associated with the order.
58. The computer-readable medium according to claim 56 or 57, wherein the matching engine comprises a machine learning model.
59. The computer-readable medium according to any one of claims 56-58, further comprising automatically sending notifications to one or more suppliers corresponding to the one or more supplier profiles.
60. The computer-readable medium according to any one of claims 43-59, further comprising categorizing a supplier profile using a categorization engine.
61. The computer-readable medium according to claim 60, wherein the categorization engine processes one or more input comprising products and service that a supplier provides, an equipment that the supplier uses, a previously fulfilled order or an active order associated with the supplier.
62. The computer-readable medium according to any one of claims 43-61, further comprising monitoring a status of the order.
63. The computer-readable medium according to any one of claims 43-62, further comprising storing the dataset in a database.
Citation Information
Patent Citations
System and method for eCatalog supplier portal
US20050251409A1
Transaction facilitating marketplace platform
US20150073929A1
Secure distributed supply chain transactional management system
US20190258986A1
User-Specific Rule-Based Database Querying
US20200118076A1
A kind of E-commerce trading system platform consist of the manufacturer's M shop, the dealer's D shop and the consumer using functions
US20210358016A1
