Article intelligent distribution method, device and equipment and storage medium

Abstract

The embodiment of the invention provides an intelligent article distribution method and device, equipment and a storage medium, and the method comprises the steps: carrying out the automatic evaluation of the article information corresponding to a pre-obtained target article based on a preset evaluation strategy, obtaining an article color grade corresponding to the target article, and obtaining an article color grade corresponding to the target article based on the article information and the article color grade; screening in a preset demand user group to obtain a plurality of target demand users, and sending an online acquisition request corresponding to the target article to each target demand user, so that each target demand user feeds back value attribute data based on the online acquisition request, and based on the value attribute data corresponding to each target demand user and a preset dynamic portrait library, determining a final target demand user. According to the method, whole-process automation of article distribution is realized, man-made subjectivity and randomness in each link are eliminated, and through accurate matching and competitive bidding, it is ensured that each article can be transacted at the optimal price and the fastest speed under the current market condition.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a method, apparatus, device and storage medium for intelligent allocation of items. Background Technology

[0002] With the popularization of the circular economy and green consumption concepts, the second-hand goods trading market is booming. Online recycling platforms, as an important hub connecting individual sellers and professional users, have the core function of efficiently and accurately allocating recycling orders to the most suitable users, thereby maximizing the value of items and improving transaction efficiency and user experience.

[0003] Currently, existing technologies typically allocate items through manual dispatch or list-based methods. However, traditional allocation methods rely heavily on manual operation and static rules, making it difficult to cope with the processing needs of massive, non-standardized secondhand goods. This has become a technological bottleneck restricting the industry's large-scale and intelligent development.

[0004] In conclusion, how to achieve smarter and more efficient recycling and distribution is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for intelligent item allocation, in order to solve the problem of how to achieve more intelligent and efficient recycling and allocation.

[0006] In a first aspect, embodiments of this application provide a method for intelligent allocation of items, including:

[0007] Based on a preset evaluation strategy, the item information corresponding to the target item is automatically evaluated to obtain the item quality grade corresponding to the target item.

[0008] Based on the item information and the item quality grade, multiple target users are selected from the preset user groups.

[0009] Send an online acquisition request for the target item to each target user, so that each target user can provide value attribute data based on the online acquisition request;

[0010] Based on the value attribute data corresponding to each target user and a preset dynamic profile library, the final target user is determined. The dynamic profile library includes dynamic profiles of multiple target users.

[0011] In one possible implementation, the evaluation strategy is structured data, including multiple category identifiers, multiple evaluation indicators corresponding to each category identifier and the weight of each evaluation indicator, as well as the quality grade classification standard.

[0012] In one possible implementation, the automated evaluation of the pre-acquired item information corresponding to the target item based on a preset evaluation strategy to obtain the item quality grade corresponding to the target item includes:

[0013] Based on the category identifier of the target item, extract each evaluation indicator corresponding to the category identifier from the item information;

[0014] The evaluation result for the target item is obtained by calculating the weight corresponding to each evaluation indicator.

[0015] Based on the evaluation results and the quality grade classification standard, the quality grade of the target item is determined.

[0016] In one possible implementation, the method further includes:

[0017] Receive historical value attribute data for each user with a need in real time;

[0018] For each user with a need, multiple key value indicators are calculated based on the historical value attribute data corresponding to the user with a need.

[0019] The dynamic profile library is constructed based on multiple key value indicators corresponding to each user's needs.

[0020] In one possible implementation, the method further includes:

[0021] Based on the value attribute data corresponding to the final target user, calculate multiple key value indicators corresponding to the final target user.

[0022] Based on multiple key value indicators corresponding to the users with the final target needs, the dynamic profiles of the users with the final target needs in the dynamic profile library are updated.

[0023] In one possible implementation, the step of filtering multiple target users from a preset user group based on the item information and the item's quality grade includes:

[0024] Based on the category identifier and geographical information in the item information, matching users are selected from the user group in demand and determined as the initial user group in demand.

[0025] Based on the quality grade of the items and the key value indicators corresponding to each user in the initial user group, the multiple target users are determined.

[0026] Secondly, embodiments of this application provide an intelligent item distribution device, comprising:

[0027] The evaluation module is used to automatically evaluate the item information corresponding to the pre-acquired target item based on a preset evaluation strategy, and obtain the item quality grade corresponding to the target item.

[0028] The filtering module is used to filter multiple target users from a preset user group based on the item information and the item quality grade.

[0029] The sending module is used to send an online acquisition request corresponding to the target item to each target user, so that each target user can provide feedback on value attribute data based on the online acquisition request.

[0030] The determination module is used to determine the final target user based on the value attribute data corresponding to each target user and a preset dynamic profile library, wherein the dynamic profile library includes dynamic profiles of multiple target users.

[0031] In one possible implementation, the evaluation strategy is structured data, including multiple category identifiers, multiple evaluation indicators corresponding to each category identifier and the weight of each evaluation indicator, as well as the quality grade classification standard.

[0032] In one possible implementation, the evaluation module specifically includes:

[0033] Based on the category identifier of the target item, extract each evaluation indicator corresponding to the category identifier from the item information;

[0034] The evaluation result for the target item is obtained by calculating the weight corresponding to each evaluation indicator.

[0035] Based on the evaluation results and the quality grade classification standard, the quality grade of the target item is determined.

[0036] In one possible implementation, the device further includes:

[0037] The receiving module is used to receive historical value attribute data corresponding to each user in real time.

[0038] The first calculation module is used to calculate multiple key value indicators corresponding to each user based on the historical value attribute data of the user.

[0039] The module is used to build the dynamic profile library based on multiple key value indicators corresponding to each user with needs.

[0040] In one possible implementation, the device further includes:

[0041] The second calculation module is used to calculate multiple key value indicators corresponding to the final target user based on the value attribute data corresponding to the final target user.

[0042] The update module is used to update the dynamic profile of the user with the final target demand in the dynamic profile library based on multiple key value indicators corresponding to the user with the final target demand.

[0043] In one possible implementation, the filtering module specifically includes:

[0044] Based on the category identifier and geographical information in the item information, matching users are selected from the user group in demand and determined as the initial user group in demand.

[0045] Based on the quality grade of the items and the key value indicators corresponding to each user in the initial user group, the multiple target users are determined.

[0046] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0047] The memory stores computer-executed instructions;

[0048] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0049] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0050] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0051] The intelligent item allocation method, apparatus, device, and storage medium provided in this application automatically evaluates the item information corresponding to pre-acquired target items based on a preset evaluation strategy to obtain the item quality grade corresponding to the target item. Based on the item information and item quality grade, multiple target users are selected from a preset user group. An online acquisition request corresponding to the target item is sent to each target user, so that each target user provides value attribute data based on the online acquisition request. Based on the value attribute data corresponding to each target user and a preset dynamic profile library, the final target user is determined. The above method realizes full automation from item information entry to final user determination, improving the processing speed from hours or even days in the traditional mode to minutes. It eliminates human subjectivity and arbitrariness in each link, making the results consistent, traceable, and verifiable. Through precise matching and competitive bidding, it ensures that each item can be sold at the best price and fastest speed under the current market conditions. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0053] Figure 1 Flowchart of the intelligent item allocation method provided in this application Figure 1 ;

[0054] Figure 2 Flowchart of the intelligent item allocation method provided in this application Figure 2 ;

[0055] Figure 3 Flowchart of the intelligent item allocation method provided in this application Figure 3 ;

[0056] Figure 4 Flowchart of the intelligent item allocation method provided in this application Figure 4 ;

[0057] Figure 5 A schematic diagram of the intelligent item distribution device provided in this application;

[0058] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.

[0059] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0060] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0061] With the popularization of the circular economy and green consumption concepts, the second-hand goods trading market is booming. Online recycling platforms, as a crucial hub connecting individual sellers and professional recyclers, focus on efficiently and accurately allocating recycling orders to the most suitable recyclers to maximize commodity value and improve transaction efficiency and user experience. Traditional order allocation models rely heavily on manual operation and static rules, making it difficult to handle the massive and non-standardized processing demands of second-hand goods. This has become a technological bottleneck restricting the industry's large-scale and intelligent development.

[0062] Currently, existing technologies typically employ the following methods for order allocation: First, manual order assignment, where platform operators assign orders to specific recyclers based on experience, personal relationships, or simple rules (such as geographical proximity) via instant messaging tools or telephone; second, order-grabbing, where the platform simply pushes order information to a large group of recyclers, who then decide whether to accept the order without platform intervention in priority; and third, fixed-rule matching, where the system performs simple screening and allocation based on preset, unchanging static conditions (such as the recycler's registered recycling categories). These existing solutions have the following significant drawbacks: First, in the product evaluation stage, they heavily rely on the manual experience of recyclers or appraisers to determine the condition, lacking a unified, quantifiable standard rule engine, resulting in highly subjective and inconsistent evaluation results. Second, the above order allocation mechanisms are both inefficient and blind, failing to consider dynamic key indicators such as the user's historical bidding performance (e.g., high-price rate), willingness to accept orders (e.g., bid rate), and operational service quality (e.g., complaint rate), leading to high-value orders not being matched with the highest-paying and best-service recyclers, resulting in platform revenue losses and a decline in user experience. Finally, the systems generally lack the ability to dynamically track and mine multidimensional data of users, and their profile indicators are outdated and have only one dimension, which cannot provide data support for intelligent decision-making.

[0063] To address the aforementioned problems, this application provides a method, apparatus, device, and storage medium for intelligent item allocation, achieving more intelligent and efficient recycling and allocation. Specifically, existing technologies typically allocate items through manual order dispatch or a list-based approach. However, traditional allocation methods heavily rely on manual operation and static rules, making it difficult to handle the massive, non-standardized processing demands of secondhand items, thus becoming a technological bottleneck restricting the industry's large-scale and intelligent development. Considering these issues, the inventors investigated whether constructing a standardized item evaluation rule engine and a dynamic demand user profiling system could achieve intelligent, real-time, and accurate order allocation and bidding for item recycling, replacing manual experience with data-driven approaches to maximize recycling efficiency and commodity value. Based on this, the solution proposed in this application is presented.

[0064] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0065] Figure 1 Flowchart of the intelligent item allocation method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0066] S101: Based on a preset evaluation strategy, automatically evaluate the item information corresponding to the target item obtained in advance to obtain the item quality grade corresponding to the target item.

[0067] In this step, the assessment of an item's condition typically relies heavily on human experience. Appraisers, such as employees of secondhand platforms or recyclers, judge the item's condition based on their personal experience by reviewing the text descriptions and photos submitted by users. This method is highly subjective; different appraisers may have vastly different opinions on the same item, leading to inconsistent and unfair assessments that can easily cause transaction disputes.

[0068] To address the aforementioned issues, an evaluation strategy is pre-set. Upon receiving the item information corresponding to the target item submitted by the user, the evaluation is automatically performed based on the evaluation strategy to determine the item's quality level.

[0069] The target items can be secondhand goods, or any item that can be evaluated, priced, and matched to users with suitable needs. The evaluation strategy uses structured data, such as JSON format, and includes multiple category identifiers, multiple evaluation indicators for each category identifier, weights for each indicator, and a condition grading standard. For example, if the category identifier is a mobile phone, the evaluation indicators could be screen scratches, body dents, functional integrity, and usage time. The indicator weights represent the degree of influence each indicator has on the final condition grade, such as screen condition accounting for 30% and battery health accounting for 20%. The grading standard maps the calculated total score to specific condition grades, such as Grade A, Grade B, and Grade C.

[0070] For example, after receiving the item information, the system automatically matches the category identifier, extracts the corresponding data from the item information (such as the user selecting "the screen has minor scratches"), substitutes it into the formula for weighted calculation, and finally outputs a quantitative and objective condition grade.

[0071] It should be noted that the weighting formula can be preset according to different scenarios, and the embodiments of this application do not impose specific limitations.

[0072] S102: Based on item information and item quality grade, select multiple target users from the preset user groups.

[0073] In this step, traditional allocation methods are often extremely crude. For example, manual order assignment involves operations staff sending orders to familiar users based on intuition or personal relationships. Another method is broadcast order bidding, where order information is thrown into a large group chat, allowing all users to bid for the highest bidder, completely disregarding the users' expertise and service quality. Furthermore, simple filtering based on basic rules (such as "User A only accepts mobile phones from CC regions") is insufficient to handle complex situations.

[0074] It should be noted that the users mentioned above usually refer to recyclers on second-hand platforms.

[0075] However, the screening process in this step is no longer a simple matching, but a multi-dimensional and precise user profile matching process.

[0076] Specifically, based on the category identifier and geographical information in the item information, matching users are selected from the target user group to form the initial target user group. Based on the item quality grade and the key value indicators corresponding to each user in the initial target user group, multiple target users are identified.

[0077] S103: Send an online acquisition request for the target item to each target user, so that each target user can provide feedback on value attribute data based on the online acquisition request.

[0078] In this step, existing technologies often involve sending product information via phone, SMS, or social media to request user feedback on pricing, and the methods vary widely (such as app replies, phone quotes, etc.). Platform staff need to manually collect, record, and compare all quotes, a tedious, error-prone, and extremely inefficient process.

[0079] Specifically, to improve efficiency, online requests for the target item can be sent to each user with the target demand via online methods. For example, the online request can be pushed directly to each user's business terminal through application programming interface (API) calls, APP push notifications, or system messages.

[0080] The online request is used to enable each target user to provide feedback on value attribute data based on the online request. It also includes a time limit, which limits the time for the user to provide feedback on value attribute data, which is the user's price quote for the target item.

[0081] After receiving an online request, each user provides the value attribute data of the target item, i.e., the price information, based on the item information in the online request, and feeds it back to the platform.

[0082] S104: Based on the value attribute data corresponding to each target user and the preset dynamic profile library, determine the final target user.

[0083] In this step, existing technologies, after obtaining the value attribute data of the target user, rely on human decision-making. Operations personnel compare all the value attribute data and directly select the user with the highest bid as the final target user, completely ignoring the user's historical service quality.

[0084] To address the aforementioned issues, this application embodiment, upon receiving the value attribute data from each target user, determines the final target user based on a pre-set dynamic profile library.

[0085] Specifically, the dynamic profile library includes dynamic profiles of multiple users with different needs, which can reflect the historical performance of each user. Then, through a weighted scoring algorithm, a comprehensive score is calculated for each target user, and the user with the highest comprehensive score is selected as the final target user.

[0086] Optionally, the dynamic profile of each user includes several key value indicators, such as the price-high rate, order quotation rate, and customer complaint rate. The price-high rate is the ratio of historical total quotation amount to historical total transaction amount; the order quotation rate is the ratio of historical quotation order quantity to the total number of pushed orders received; and the customer complaint rate is the ratio of historical complaint count to the total number of historical orders.

[0087] In one possible implementation, the weighted scoring algorithm can assign weights to each key value indicator and then perform a comprehensive score. The specific settings can be determined according to the actual application scenario, and this application embodiment does not impose any specific limitations.

[0088] The intelligent item allocation method provided in this application automatically evaluates the item information corresponding to pre-acquired target items based on a preset evaluation strategy to obtain the item quality grade. Based on the item information and quality grade, multiple target users are selected from a preset user group. An online acquisition request for the target item is sent to each target user, allowing each target user to provide value attribute data based on the online acquisition request. Based on the value attribute data corresponding to each target user and a preset dynamic profile library, the final target user is determined. The above method automates the entire process from item information entry to final user determination, reducing processing speed from hours or even days in traditional models to minutes. It eliminates human subjectivity and arbitrariness in each step, ensuring consistent, traceable, and verifiable results. Through precise matching and competitive bidding, it ensures that each item can be sold at the best price and fastest speed under current market conditions.

[0089] Figure 2 Flowchart of the intelligent item allocation method provided in this application Figure 2 ,like Figure 2 As shown, based on the above embodiments, step S101 specifically includes:

[0090] S201: Based on the category identifier of the target item, extract each evaluation indicator corresponding to the category identifier from the item information.

[0091] In this step, traditional manual assessments rely on the assessor's personal experience and knowledge to observe and inquire about various characteristics after receiving the item information. The entire process is arbitrary and subjective: different assessors focus on different things (some look at the screen first, some at the bezel), and the questions they ask vary in depth. For example, for the same mobile phone, assessor A might carefully check the camera for dust, while assessor B might overlook this. The lack of a standardized, mandatory checklist leads to uncertainty and omissions in the data collection phase.

[0092] To ensure the uniformity and comprehensiveness of the evaluation, each evaluation indicator corresponding to the category identifier can be extracted from the item information based on the category identifier of the target item. For example, if the category identifier of the target item is a smartphone, the corresponding evaluation rules will be automatically retrieved and loaded in the preset evaluation strategy, and each evaluation indicator corresponding to the category identifier will be extracted. Taking smartphones as an example, the evaluation indicators can be screen scratches, body bumps, battery health, functional integrity, repair history, etc., and then the data information corresponding to each evaluation indicator can be found in the item information.

[0093] S202: Calculate the evaluation result for the target item based on the weight corresponding to each evaluation indicator.

[0094] In this step, traditional methods rely on the appraiser's personal, unquantifiable experience to assess each inspection item of the target item. For example, an appraiser might think a minor scratch on the screen is insignificant, but a replacement motherboard would significantly reduce the item's value. Different appraisers have vastly different "inner weights": a cautious appraiser might heavily penalize scratches, while a more lenient one might focus more on functionality. The result is a vague assessment of the item's condition, which cannot be verified or explained with data.

[0095] Therefore, after determining the evaluation indicators, the evaluation results are obtained by calculating the weight corresponding to each evaluation indicator in the evaluation strategy.

[0096] For example, the extracted specific data values ​​(such as "minor scratches") are converted into an initial score (e.g., "minor scratches" > 80 points) according to a predefined mapping table in the evaluation strategy. Then, the initial score of each indicator is multiplied by its corresponding weight (e.g., the weight of screen scratches is 0.3) to obtain the weighted score of that indicator. Finally, the weighted scores of all indicators are summed to obtain a total score representing the overall condition of the item, which is the evaluation result.

[0097] S203: Determine the fineness grade of the target item based on the assessment results and the fineness grading standards.

[0098] In this step, in the traditional method, the assessor directly gives a conclusion of 90% new or grade B based on their own internal standard. However, this standard varies from person to person and may even be affected by the assessor's mood.

[0099] Therefore, after obtaining the evaluation results, this application embodiment can directly and accurately determine the quality grade of the target item based on the quality grade classification standard in the evaluation strategy.

[0100] For example, the quality grading standard can be A grade 90-100 points, B grade 80-89 points, and C grade 60-79 points. If the evaluation result is 85.5 points, it is determined to be grade B.

[0101] The intelligent item allocation method provided in this application extracts each evaluation index corresponding to the category identifier of the target item from the item information, calculates the evaluation result corresponding to the target item based on the weight of each evaluation index, and determines the item's quality grade based on the evaluation result and the quality grading standard. This method improves processing efficiency, reduces labor costs, completely eliminates interference from subjective human factors, and ensures the objectivity, fairness, and consistency of the evaluation results.

[0102] Figure 3 Flowchart of the intelligent item allocation method provided in this application Figure 3 ,like Figure 3 As shown, based on the above embodiments, the method further includes:

[0103] S301: Receives historical value attribute data for each user in real time.

[0104] S302: For each user with a demand, calculate multiple key value indicators corresponding to the user based on the user's historical value attribute data.

[0105] S303: Build a dynamic profile library based on multiple key value indicators corresponding to each user with needs.

[0106] In the traditional model, historical behavioral data of users is either not systematically recorded or scattered across different isolated systems. Data collection relies on periodic manual export, organization, and summarization of tables, such as weekly or monthly Excel spreadsheets exported from the database backend by operations staff. This approach is severely outdated, fails to reflect the latest status of users, and is inefficient and prone to errors.

[0107] To improve efficiency, a fully automatic real-time access method is adopted. After receiving the online access request sent by the system on the terminal, users can directly operate on the terminal, and the data is transmitted to the system in real time.

[0108] Optionally, historical value attribute data may include not only price information but also transaction data, as well as complaint and performance data.

[0109] The specific implementation method can be: the system can embed data points in various business processes (quotation, transaction, customer service ticket closure) through message queues or real-time stream processing platforms.

[0110] Once these events occur, the corresponding data (such as the user's ID, order ID, quote amount, and timestamp) will be immediately encapsulated into a message and sent to the message queue.

[0111] The profile building service acts as a message consumer, subscribing to these message streams in real time to achieve real-time data reception.

[0112] After receiving the historical value attribute data of each user, the system calculates key value indicators and then builds a dynamic profile library.

[0113] For example, the system uses a scheduled task to query the database for all historical behavioral data of each user within a specified time window (such as the last 30 or 90 days). Based on predefined business rules and algorithm models, a series of key value indicators are calculated. These indicators typically include:

[0114] Historical bid / sold price ratio (high bid rate): ∑bid amount / ∑sold amount. This measures the bidding power and willingness of demanding users. A higher ratio indicates more aggressive bidding and a greater likelihood of a higher bid.

[0115] Order quotation rate: Number of quoting orders / Total number of push orders received. Measures the activity and responsiveness of users with needs. A higher ratio indicates higher engagement.

[0116] Customer complaint rate (operational quality score): Number of complaints / Total number of completed orders. Measures the service and quality provided to customers. A lower rate indicates better service in areas such as product inspection, quality control, and fulfillment.

[0117] The system links these metrics with the basic information of users in need, forming a complete, multi-dimensional user profile.

[0118] This profile is stored in a high-performance database (such as an in-memory database like Redis to ensure real-time performance), and is called a dynamic profile library.

[0119] Each profile picture is timestampd, indicating its update time. The profile picture library supports quick queries based on the user ID requested.

[0120] Optionally, after allocation, based on the value attribute data corresponding to the users with the final target needs, multiple key value indicators are calculated for those users. Based on these key value indicators, the dynamic profiles of the users with the final target needs in the dynamic profile library are updated. This avoids misjudgments caused by data lag and completely changes the shortcomings of slow data feedback and delayed management measures in traditional management models.

[0121] The intelligent item allocation method provided in this application receives historical value attribute data corresponding to each user in real time. For each user, multiple key value indicators are calculated based on the historical value attribute data, and a dynamic profile library is constructed based on these key value indicators. This method improves the intelligence of allocation, eliminates reliance on personal experience, and achieves precise automatic allocation.

[0122] Figure 4 Flowchart of the intelligent item allocation method provided in this application Figure 4 ,like Figure 4 As shown, based on the above embodiments, step S102 specifically includes:

[0123] S401: Based on the category identifier and geographical information in the item information, filter out matching users from the user group and determine them as the initial user group.

[0124] S402: Based on the quality grade of the item and the key value indicators corresponding to each user in the initial user group, identify multiple target users.

[0125] To achieve more intelligent and efficient allocation and match more suitable users with needs, multi-layered screening can be implemented. First, it ensures that the user has the necessary business qualifications and capabilities to recycle the target item. For example, if an order is for "smartphones," the system will first filter out all users registered to operate businesses with "smartphones" in their product category. This avoids sending a phone order to a user who only wants to recycle furniture.

[0126] Secondly, it ensures that the service area of ​​the users with the demand covers the seller's location. For example, if the order location is "A City", the system will filter out users with demand whose service area includes "A City". This ensures logistical feasibility, ease of assessment, and after-sales service capabilities.

[0127] Specifically, by using category identifiers and geographic information as search criteria, users with initial needs who simultaneously meet these two basic conditions can be quickly identified.

[0128] Then, based on the quality grade of the items, multiple target users are identified according to the key value indicators of each target user.

[0129] The intelligent item allocation method provided in this application, based on the category identifier and geographical information in the item information, filters out matching users from the demand user group to determine the initial demand user group. Then, based on the item quality grade and the key value indicators corresponding to each user in the initial demand user group, multiple target demand users are determined. This method upgrades the traditional extensive, inefficient, and subjective allocation model to a precise, efficient, and objective automated decision-making process based on data and algorithms. This maximizes the overall resource utilization efficiency and benefits of the platform.

[0130] Figure 5 A schematic diagram of the intelligent item distribution device provided in this application is shown below. Figure 5 As shown, the intelligent item distribution device 500 provided in this embodiment includes:

[0131] The evaluation module 501 is used to automatically evaluate the item information corresponding to the target item based on the preset evaluation strategy, and obtain the item quality grade corresponding to the target item.

[0132] The filtering module 502 is used to filter multiple target users from a preset user group based on item information and item quality grade.

[0133] The sending module 503 is used to send an online acquisition request corresponding to the target item to each target demand user, so that each target demand user can provide feedback value attribute data based on the online acquisition request.

[0134] The determination module 504 is used to determine the final target user based on the value attribute data corresponding to each target user and the preset dynamic profile library. The dynamic profile library includes dynamic profiles of multiple users.

[0135] In one possible implementation, the evaluation strategy consists of structured data, including multiple category identifiers, multiple evaluation indicators corresponding to each category identifier, weights corresponding to each evaluation indicator, and quality grade classification standards.

[0136] In one possible implementation, the evaluation module 501 specifically includes:

[0137] Based on the category identifier of the target item, extract each evaluation indicator corresponding to the category identifier from the item information;

[0138] The evaluation result for the target item is obtained by calculating the weight corresponding to each evaluation indicator.

[0139] Based on the assessment results and the fineness grading standards, the fineness grade corresponding to the target item is determined.

[0140] In one possible implementation, the intelligent item distribution device 500 further includes:

[0141] The receiving module 505 is used to receive historical value attribute data corresponding to each user in real time.

[0142] The first calculation module 506 is used to calculate multiple key value indicators for each user based on the user's historical value attribute data.

[0143] Module 507 is used to build a dynamic profile library based on multiple key value indicators corresponding to each user with needs.

[0144] In one possible implementation, the intelligent item distribution device 500 further includes:

[0145] The second calculation module 508 is used to calculate multiple key value indicators corresponding to the final target user based on the value attribute data corresponding to the final target user.

[0146] Update module 509 is used to update the dynamic profile of the user with the final target demand in the dynamic profile library based on multiple key value indicators corresponding to the user with the final target demand.

[0147] In one possible implementation, the screening module 502 specifically includes:

[0148] Based on the category identifier and geographical information in the item information, the matching users in the demand group are selected and determined as the initial demand user group;

[0149] Based on the quality grade of the items and the key value indicators corresponding to each user in the initial user group, multiple target users were identified.

[0150] The intelligent item allocation device provided in this embodiment can execute the intelligent item allocation method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0151] Figure 6 A schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the electronic device further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0152] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the methods of the above embodiments.

[0153] The specific implementation process of processor 601 can be found in the above-mentioned method embodiments, and its implementation principle and technical effect are similar. Therefore, it will not be repeated here.

[0154] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0155] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0156] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0157] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the methods of the various embodiments described above.

[0158] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the methods of the above embodiments.

[0159] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0160] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0161] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0164] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0166] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for intelligent allocation of items, characterized in that, include: Based on a preset evaluation strategy, the item information corresponding to the target item is automatically evaluated to obtain the item quality grade corresponding to the target item. Based on the item information and the item quality grade, multiple target users are selected from the preset user groups. Send an online acquisition request for the target item to each target user, so that each target user can provide value attribute data based on the online acquisition request; Based on the value attribute data corresponding to each target user and a preset dynamic profile library, the final target user is determined. The dynamic profile library includes dynamic profiles of multiple target users.

2. The method according to claim 1, characterized in that, The evaluation strategy uses structured data, including multiple product category identifiers, multiple evaluation indicators corresponding to each product category identifier, weights corresponding to each evaluation indicator, and quality grade classification standards.

3. The method according to claim 2, characterized in that, The automated evaluation of the target item's information based on a preset evaluation strategy to obtain the item's quality grade includes: Based on the category identifier of the target item, extract each evaluation indicator corresponding to the category identifier from the item information; The evaluation result for the target item is obtained by calculating the weight corresponding to each evaluation indicator. Based on the evaluation results and the quality grade classification standard, the quality grade of the target item is determined.

4. The method according to claim 1, characterized in that, The method further includes: Receive historical value attribute data for each user with a need in real time; For each user with a need, multiple key value indicators are calculated based on the historical value attribute data corresponding to the user with a need. The dynamic profile library is constructed based on multiple key value indicators corresponding to each user's needs.

5. The method according to claim 4, characterized in that, The method further includes: Based on the value attribute data corresponding to the final target user, calculate multiple key value indicators corresponding to the final target user. Based on multiple key value indicators corresponding to the users with the final target needs, the dynamic profiles of the users with the final target needs in the dynamic profile library are updated.

6. The method according to any one of claims 1-5, characterized in that, Based on the item information and the item's quality grade, multiple target users are selected from a preset user group, including: Based on the category identifier and geographical information in the item information, matching users are selected from the user group in demand and determined as the initial user group in demand. Based on the quality grade of the items and the key value indicators corresponding to each user in the initial user group, the multiple target users are determined.

7. An intelligent item dispensing device, characterized in that, include: The evaluation module is used to automatically evaluate the item information corresponding to the pre-acquired target item based on a preset evaluation strategy, and obtain the item quality grade corresponding to the target item. The filtering module is used to filter multiple target users from a preset user group based on the item information and the item's quality grade. The sending module is used to send an online acquisition request corresponding to the target item to each target user, so that each target user can provide feedback on value attribute data based on the online acquisition request. The determination module is used to determine the final target user based on the value attribute data corresponding to each target user and a preset dynamic profile library, wherein the dynamic profile library includes dynamic profiles of multiple target users.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the intelligent item allocation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the intelligent item allocation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the intelligent item allocation method according to any one of claims 1-6.

Images