An attribute-based weight distribution method, system and computer device

Abstract

The application provides an attribute-based weight distribution method, system and computer device, comprising setting multiple attributes, and configuring weight scores for the attributes in a segmented manner; receiving request data sent by a client; parsing the request data and splitting all fields of the request data; matching the split fields with the attributes and calculating total scores; evaluating recommendation priorities according to the total scores; sorting the recommendation priorities according to a sorting rule, and presenting the sorting result to the client. By configuring weight scores for the attributes, the application can customize the weight scores of the attributes according to actual needs, dynamically calculate total scores of various products in combination with multiple key indicators, evaluate the recommendation priorities of the products according to the total scores, and present the products with high recommendation priorities to the client. The application significantly improves the objectivity and accuracy of weight distribution, greatly enhances the flexibility and user friendliness of the system, and enables users to easily cope with complex and changeable application scenarios.

Description

Technical Field

[0001] This invention relates to the field of information processing technology, and in particular to an attribute-based weight allocation method, system, and computer device. Background Technology

[0002] Currently, with the rapid development of information technology, information processing and decision-making are particularly important in application scenarios such as business card recommendations and e-commerce systems. These systems require evaluating the merits of objects based on a series of attributes or indicators, and then converting these attributes or indicators into a comprehensive score through a weighting system to assist in information-based decision-making. However, traditional weighting systems rely on manually set weight values, that is, on expert experience, historical data, or industry standards for manual judgment to allocate weights. This makes weight allocation susceptible to subjective influence, reducing the accuracy and reliability of the final evaluation results.

[0003] When faced with complex and ever-changing application scenarios, existing weight allocation schemes are fixed and cannot be flexibly adjusted according to actual application scenarios and needs, resulting in low adaptability and flexibility, and making it difficult to accurately reflect the relative importance of each attribute. Furthermore, the importance of different attributes changes with time, environment, or other factors, and the weight system cannot dynamically adjust according to these changes, resulting in low dynamic adjustment capability.

[0004] Furthermore, existing weight allocation systems suffer from complex interfaces, cumbersome operations, and incomplete documentation, making them difficult for users to understand and use, thus reducing user-friendliness and applicability. In actual use, as application scenarios continue to expand and change, the scalability and maintainability of the weight system also deteriorate, making it difficult to update and optimize in a timely manner to meet new requirements or changes, thereby preventing the system from operating and developing stably in the long term. Summary of the Invention

[0005] The present invention aims to solve the problems of the existing weight system being easily affected by subjective factors, lacking flexibility and dynamic adjustment capabilities, and failing to accurately reflect the relative importance of each attribute, and provides an attribute-based weight allocation method, system and computer device.

[0006] This invention provides an attribute-based weight allocation method, comprising the following steps:

[0007] Set multiple attributes and configure weight scores for each attribute in a segmented manner;

[0008] Receive request data sent by a preset client; wherein, the request data includes, but is not limited to, user information and product information;

[0009] Parse the request data and split all fields of the request data to obtain the split fields;

[0010] Match the splitting field with the attribute and calculate the total score;

[0011] Sort according to the preset sorting rules to obtain the sorted result;

[0012] The sorting results are presented to the client.

[0013] Furthermore, the step of setting multiple attributes and configuring weight scores for the attributes in a segmented manner includes:

[0014] Set basic thresholds for key indicators and use these basic thresholds as reference points for the weight scores; wherein, the key indicators include the recent page views of the product and the user order success rate;

[0015] Determine whether the key indicator is greater than the basic threshold;

[0016] If yes, calculate the ratio of the key indicator portion exceeding the basic threshold to the key indicator, and increase the weight score based on the ratio; if no, calculate the ratio of the key indicator portion below the basic threshold to the key indicator, and decrease the weight score based on the ratio.

[0017] Further, if so, the step of calculating the ratio of the key indicator greater than the basic threshold to the key indicator, and increasing the weight score according to the ratio, includes:

[0018] When the key metric is the recent pageviews, a piecewise function is used to adjust the increase in the weight score.

[0019] When the key indicator is the user's order success rate, a linear function is used to adjust the weight score.

[0020] Furthermore, the step of matching the attributes to the splitting field and calculating the total score includes:

[0021] The total score is calculated based on the weighted scores corresponding to the attributes.

[0022] Furthermore, the step of calculating the total score based on the weighted scores corresponding to the attributes includes:

[0023] The weighted scores of the recent page views and the user order success rate are added together to obtain the comprehensive score for each product.

[0024] Furthermore, the step of evaluating the recommendation priority based on the total score includes:

[0025] The products are ranked according to the comprehensive score.

[0026] The products are placed in a preset recommendation list; wherein, the higher the overall score, the greater the recommendation priority and the higher the position in the recommendation list.

[0027] Furthermore, before the step of placing the product in the preset recommendation list, the following steps are included:

[0028] Determine whether the product meets the preset constraints;

[0029] If so, a second sorting process is performed, and the product is placed at the top of the recommended list.

[0030] The present invention also provides an attribute-based weight allocation system, comprising:

[0031] The settings module is used to set multiple attributes and configure the weight scores of the attributes in segments;

[0032] The receiving module is used to receive request data sent by a preset client;

[0033] The parsing module is used to parse the request data and split all fields of the request data to obtain the split fields;

[0034] The calculation module is used to match the splitting fields with the attributes and calculate the total score;

[0035] The evaluation module is used to assess the recommendation priority based on the total score;

[0036] The sorting module is used to sort according to preset sorting rules and obtain the sorting result;

[0037] The display module is used to present the sorting results to the client.

[0038] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the steps in any of the above methods.

[0039] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the above methods.

[0040] This invention provides an attribute-based weight allocation method, system, and computer device, which have the following beneficial effects:

[0041] By pre-configuring attribute weights, users can customize attribute weights according to actual needs. The system dynamically calculates the total score for each product based on multiple key indicators, evaluates the product recommendation priority based on the total score, and finally presents products or business cards with high recommendation priority to the client. This significantly improves the objectivity and accuracy of weight allocation, greatly enhances system flexibility and user-friendliness, easily handles complex and ever-changing application scenarios, configures weights to meet requirements, and is more objective, flexible, efficient, user-friendly, and easy to expand and maintain. It provides a more scientific and accurate weight allocation scheme for information decision-making. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the method steps of an attribute-based weight allocation method in this invention;

[0043] Figure 2 This is a system structure block diagram of an attribute-based weight allocation system in this invention;

[0044] Figure 3 This is a structural block diagram of a computer device according to the present invention;

[0045] Figure 4 This is a flowchart illustrating an embodiment of an attribute-based weight allocation method according to the present invention.

[0046] Figure 5 This is a schematic diagram illustrating the steps of an embodiment of an attribute-based weight allocation method according to the present invention.

[0047] Labeling description: Setting module 10, receiving module 20, parsing module 30, calculation module 40, evaluation module 50, sorting module 60, display module 70. Detailed Implementation

[0048] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] refer to Figure 1 and Figure 4 This is an embodiment of an attribute-based weight allocation method according to the present invention, comprising:

[0051] S1, set multiple attributes and configure the weight scores of the attributes in segments;

[0052] S2, receiving request data sent by a preset client; wherein, the request data includes, but is not limited to, user information and product information;

[0053] S3, parse the request data and split all fields of the request data to obtain the split fields;

[0054] S4 matches the split fields with the attributes and calculates the total score;

[0055] S5, Priority is recommended based on the total score;

[0056] S6, Sort according to the preset sorting rules to obtain the sorting result;

[0057] S7 presents the sorting results to the client.

[0058] In the above steps, multiple attributes are first set, and corresponding weight scores are flexibly configured for each attribute according to actual needs. Then, the user inputs request data into a preset client; the client can be a communication device or a display screen. In one specific embodiment, the request data is an HTTP (HyperText Transfer Protocol) request, a response protocol for communication between a client and a server, and includes request status information and request content. Next, the request data is received and parsed, and all fields of the request data are split into multiple split fields. Then, the attributes of each split field are matched, and the total score is calculated. The recommendation priority is evaluated based on the total score, and then the products or business cards are sorted according to a preset sorting rule. Finally, the sorting result is presented to the client. The sorting rule can be either descending or ascending. In one specific embodiment, the sorting rule is from high to low, so the products are sorted according to their recommendation priority from high to low, with products with higher recommendation priority placed first and products with lower recommendation priority placed last, and this sorting result is presented to the client.

[0059] In one specific embodiment, this application is applied to a business card recommendation scenario. Specifically, business card recommendations typically involve a business card list for display. Traditional business card lists use a relatively simple sorting method, such as sorting by registration time in descending order. This results in business cards registered later being displayed at the top, leading to business cards with low activity levels and incomplete information appearing prominently in the list. This application, however, allows setting business card attributes, such as age, gender, last login time, number of active days, and registration time, and assigning different weight scores to each attribute. Upon receiving user request data, the application first parses the request data, splitting all fields into their individual segments. Then, it matches the pre-set attributes and calculates a total score based on the attribute's corresponding weight score, returning the result. Finally, the business cards are sorted in the business card list based on the total score and presented to the client. Subsequent sorting only requires inputting new request data. This ensures that business cards meeting user needs are placed prominently in the business card list, making them easy to find and fulfilling user requirements.

[0060] As attached Figure 5 As shown, in another specific embodiment, this application is applied to a product recommendation system of an e-commerce platform. First, attributes such as product sales volume, number of user reviews, average user rating, and recent pageviews are pre-set. Then, the weight score of each attribute is assigned according to business needs. When the client initiates an HTTP request, user data and product data are transmitted. After receiving the request data, the weight system parses the request data and splits it into multiple data fields. Then, each data field is matched with the pre-set attributes, and the total score is calculated according to the weight score corresponding to the attribute. This assesses the recommendation priority of the product for the user, and the products with the highest recommendation priority are sorted from highest to lowest and presented to the client.

[0061] In one embodiment, the step of setting multiple attributes and configuring weight scores for each attribute in a segmented manner includes:

[0062] Set basic thresholds for key metrics and use these basic thresholds as reference points for weighting scores; among these, key metrics include recent pageviews of the product and user order success rate.

[0063] Determine whether the key indicators are greater than the basic threshold;

[0064] If yes, calculate the ratio of key indicators to key indicators for the portion exceeding the basic threshold, and increase the weight score based on the ratio; if no, calculate the ratio of key indicators to key indicators for the portion below the basic threshold, and decrease the weight score based on the ratio.

[0065] In this embodiment, a base threshold is set for key metrics, and this base threshold is used as a reference point for weighting scores. Next, it is determined whether the key metrics exceed the base threshold, i.e., whether recent pageviews or user order success rate exceed the base threshold. If so, the proportion of the portion exceeding the base threshold to the total key metrics is calculated, and the weighting score is increased accordingly. If not, the proportion of the portion below the base threshold to the total key metrics is calculated, and the weighting score is decreased accordingly.

[0066] Specifically, when this application is applied to product recommendation scenarios on e-commerce platforms, the scoring is based on frequency and success rate. Specifically, the weight score of a product is dynamically adjusted according to two key indicators: "recent page views" and "user order success rate". By comprehensively considering these two factors, it can more accurately reflect users' interest in the product and the product's purchase potential, thereby optimizing the ranking results.

[0067] More specifically, recent pageviews refer to the number of times a product is viewed by users within a specific time window, such as within 24 hours, 7 days, or 30 days. First, a base threshold is set; in this embodiment, the base threshold is the basic pageview threshold and serves as the starting point for the weighted score. When a product's recent pageviews exceed the set base threshold, the proportion of the excess pageviews to the total recent pageviews is calculated, and the weighted score is increased proportionally. When a product's recent pageviews are below the set base threshold, the proportion of the deficiency pageviews to the total recent pageviews is calculated, and the weighted score is decreased proportionally.

[0068] In another specific embodiment, the key metric is the user order success rate, which refers to the proportion of users who browsed the product and ultimately placed an order. A benchmark value for the user order success rate is set as a reference point for the weighted score. When the user order success rate of a product is higher than the benchmark value, the proportion of the portion exceeding the benchmark value to the total user order success rate is calculated, and the weighted score is increased accordingly. When the user order success rate of a product is lower than the benchmark value, the proportion of the portion below the benchmark value to the total user order success rate is calculated, and the weighted score is decreased accordingly.

[0069] In one embodiment, if so, the step of calculating the ratio of the key indicator to the key indicator for the portion exceeding the basic threshold, and increasing the weight score based on the ratio, includes:

[0070] When the key metric is recent pageviews, a piecewise function is used to adjust the increase in the weight score.

[0071] When the key metric is the user order success rate, a linear function is used to adjust the weighting score.

[0072] In this embodiment, when the key metric is recent pageviews, the increase in weight score is adjusted by using a piecewise function to smooth the growth of weight score and avoid extreme values ​​affecting the allocation of weight score.

[0073] More specifically, when the recent pageviews are less than 100, the weight score increases relatively slowly; when the recent pageviews are between 100 and 1000, the weight score increases relatively quickly; and when the recent pageviews are more than 1000, the weight score increases again.

[0074] When the key metric is the user order success rate, a linear function is used to adjust the increase or decrease of the weight score. This linear relationship reflects the importance of the user order success rate to the user's purchasing decision.

[0075] In one embodiment, the step of calculating the total score by matching attributes of split fields includes:

[0076] The total score is calculated based on the weight score corresponding to the attribute.

[0077] In this embodiment, when calculating the total score, the weight score corresponding to each attribute is used. For example, if the attributes matched by the split field are attribute one and attribute two, the weight score of attribute one is 2 and the weight score of attribute two is 3, then the total score is 5.

[0078] In one embodiment, the step of calculating the total score based on the weighted scores corresponding to the attributes includes:

[0079] The overall score for each product is obtained by adding the weighted scores of recent page views and user order success rate.

[0080] In this embodiment, in the application of the e-commerce platform, it is necessary to calculate the comprehensive score of each product, which is to add the weighted scores of the product's recent page views and the user's order success rate to obtain the comprehensive score of each product.

[0081] Furthermore, the allocation of weighting scores can be adjusted according to business needs and scenario characteristics. In one specific embodiment, for platforms with a large number of new users, more emphasis will be placed on pageviews, thus requiring an increase in the weighting score for recent pageviews. Conversely, for platforms with a large number of returning users, more emphasis will be placed on order success rates, thus requiring an increase in the weighting score for order success rates.

[0082] In one embodiment, the step of evaluating recommendation priority based on the total score includes:

[0083] Products are ranked based on their overall scores;

[0084] Products are placed in a preset recommendation list; the higher the overall rating, the greater the recommendation priority and the higher the position in the recommendation list.

[0085] In this embodiment, products are sorted according to their overall rating and placed in the recommendation list. The higher the overall rating, the greater the recommendation priority and the higher the position in the recommendation list. Conversely, the lower the overall rating, the lower the recommendation priority and the lower the position in the recommendation list.

[0086] Specifically, consider products A and B. Product A has 1500 recent views and a 20% order success rate; Product B has 800 recent views and a 40% order success rate. Because Product A has a higher recent view count, its recent view count score will be relatively higher, but because of its lower order success rate, its order success rate score will be correspondingly lower. Product B has a lower recent view count but a higher order success rate, so its order success rate score will be relatively higher. Due to the higher weighting of recent view count, Product A's overall score will be slightly higher than Product B's, but its ranking in the recommendation list will be lower to reflect the lower order success rate. Product B, despite having a lower recent view count, will be ranked higher in the recommendation list due to its higher order success rate. This comprehensive scoring algorithm more accurately reflects user interest and purchase potential, thereby optimizing the recommendation list ranking and improving user satisfaction and purchase conversion rates.

[0087] In one embodiment, before the step of placing the product in a preset recommendation list, the steps include:

[0088] Determine whether the product meets the preset constraints;

[0089] If so, perform a second sort and place the product at the top of the recommended list.

[0090] In this embodiment, it is determined whether a product meets preset constraints, whereby the constraints may include whether it is a new product or a popular category. If so, the product is placed at the top of the recommendation list. By adding constraints, the recommendation results can be further optimized.

[0091] In summary, during implementation, firstly, multiple attributes are set, and weight scores are configured for each attribute in a segmented manner. Next, a base threshold for key metrics is set, and this base threshold is used as a reference point for the weight scores. Then, it is determined whether the key metrics exceed the base threshold. If so, the ratio of the portion of the key metrics exceeding the base threshold to the total key metrics is calculated, and the weight score is increased based on this ratio. The increase is achieved as follows: when the key metric is recent pageviews, a piecewise function is used to adjust the increase in weight score; when the key metric is user order success rate, a linear function is used to adjust the weight score. If not, the ratio of key indicators to key indicators below the basic threshold is calculated, and the weight score is reduced accordingly. Then, request data sent by a pre-defined client is received; the request data is parsed and all fields are split to obtain the split fields; the split fields are then matched with attributes, and the total score is calculated; the total score is calculated based on the weight score corresponding to the attribute; the weight scores of recent page views and user order success rate are added together to obtain the comprehensive score for each product; the recommendation priority is evaluated based on the total score; products are sorted according to the comprehensive score; it is determined whether the product meets the pre-defined constraints; if so, a second sort is performed, and the product is placed at the top of the recommendation list; the products are placed in the pre-defined recommendation lists; then, they are sorted according to the pre-defined sorting rules to obtain the sorting result; finally, the sorting result is presented to the client. This application can add attributes according to needs, making it applicable to more application scenarios and usage requirements. Whether in user information completeness sorting scenarios or e-commerce platform product recommendation scenarios, appropriate attributes can be selected for weight score allocation, giving the system strong versatility and adaptability, and not limited to a fixed and limited number of attributes. Furthermore, when new key indicators emerge, users can easily adjust the attributes, such as adding or deleting them, and re-enter the request data. The system can then configure weight scores according to the new attributes, perform weight score calculations and subsequent processing, enabling the system to respond quickly and dynamically change according to needs, ensuring that the output results match actual requirements.

[0092] Furthermore, attribute adjustments can be made by replacing manual additions or deletions by users through automated feature selection. Automated feature selection refers to using algorithms or tools to automatically filter useful features from the dataset to improve performance and reduce computational costs. For example, filtering methods evaluate the relationship between features and target variables based on statistical indicators and select the most relevant features.

[0093] Reference Appendix Figure 2 An attribute-based weighting system includes:

[0094] The settings module is used to set multiple attributes and configure the weight scores of the attributes in segments;

[0095] The setting unit is used to set the basic threshold of key indicators and to use the basic threshold as a reference point for weight scores.

[0096] The first judgment unit is used to determine whether the key indicator is greater than the basic threshold.

[0097] The calculation unit is used to calculate the ratio of the key indicators to the key indicators in the part that is greater than the basic threshold if the threshold is met, and to increase the weight score according to the ratio; otherwise, it calculates the ratio of the key indicators to the key indicators in the part that is less than the basic threshold, and to decrease the weight score according to the ratio.

[0098] The first adjustment subunit is used to adjust the increase in the weight score using a piecewise function when the key metric is recent pageviews.

[0099] The second adjustment subunit is used to adjust the weight score using a linear function when the key indicator is the user order success rate.

[0100] The receiving module is used to receive request data sent by a preset client;

[0101] The parsing module is used to parse the request data and split all fields of the request data to obtain the split fields;

[0102] The calculation module is used to match the split fields with the attributes and calculate the total score;

[0103] The calculation unit is used to calculate the total score based on the weight score corresponding to the attribute.

[0104] The calculation sub-unit is used to add the weighted scores of recent page views and user order success rate to obtain the comprehensive score of each product;

[0105] The evaluation module is used to assess recommendation priority based on the total score;

[0106] The first sorting unit is used to sort products based on the overall score;

[0107] The second judgment unit is used to determine whether the product meets the preset constraints.

[0108] The second sorting unit is used to perform a secondary sort if the product is selected, and to place the product at the top of the recommended list.

[0109] Placement unit, used to place products into a preset recommendation list;

[0110] The sorting module is used to sort according to preset sorting rules and obtain the sorting result;

[0111] The display module is used to present the sorting results to the client.

[0112] This embodiment includes a setting module, a receiving module, a parsing module, a calculation module, an evaluation module, a sorting module, a display module, a setting unit, a first judgment unit, a calculation unit, a first adjustment subunit, a second adjustment subunit, a calculation unit, a calculation subunit, a first sorting unit, a second judgment unit, a second sorting unit, and a placement unit. First, the setting module sets multiple attributes and configures segmented weight scores for each attribute. The setting unit first sets a base threshold for key indicators and uses this base threshold as a reference point for the weight scores. Then, the first judgment unit determines whether the key indicator is greater than the base threshold. If so, the calculation unit calculates the ratio of the portion of the key indicator greater than the base threshold to the total key indicator and increases the weight score accordingly. If not, it calculates the ratio of the portion of the key indicator less than the base threshold to the total key indicator and decreases the weight score accordingly. During this process, when the key indicator is recent pageviews, the first adjustment subunit uses a piecewise function to adjust the increase in the weight score; when the key indicator is user order success rate, the second adjustment subunit uses a linear function to adjust the weight score. After the user sends a request on the client, the receiving module receives the request data. First, the parsing module parses the request data and breaks down all fields into sub-fields. The calculation module matches the sub-fields with attributes and calculates the total score. Then, the calculation unit calculates the total score based on the weighted scores of the attributes. The calculation sub-unit adds the weighted scores of recent pageviews and user order success rate to obtain the comprehensive score for each product. The evaluation module evaluates the recommendation priority based on the total score. Next, the first sorting unit sorts the products based on the comprehensive score. The second judgment unit judges whether the products meet the preset constraints. If so, the second sorting unit performs a second sort and places the products in the preset recommendation list through the placement unit. Then, the sorting module sorts according to the preset sorting rules to obtain the sorting result. Finally, the display module presents the sorting result to the client.

[0113] Reference Appendix Figure 3 This application also provides a computer device, which can be a server, and its internal structure can be as follows: Figure 3As shown. The computer device includes a processor, memory, a network interface, and a database. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and the database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The database stores data such as templates, tables, and preset fields. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements an attribute-based weight allocation method, including the following steps:

[0114] Set multiple attributes and configure the weight scores of the attributes in segments;

[0115] Receive request data sent by a preset client; wherein, the request data includes, but is not limited to, user information and product information;

[0116] Parse the request data and split all fields of the request data to obtain the split fields;

[0117] Match the split fields with the attributes and calculate the total score;

[0118] Priority recommendations will be based on the total score.

[0119] Sort according to the preset sorting rules to obtain the sorted result;

[0120] The sorting results are presented to the client.

[0121] In one embodiment, the step of setting multiple attributes and configuring weight scores for each attribute in a segmented manner includes:

[0122] Set basic thresholds for key metrics and use these basic thresholds as reference points for weighting scores; among these, key metrics include recent pageviews of the product and user order success rate.

[0123] Determine whether the key indicators are greater than the basic threshold;

[0124] If yes, calculate the ratio of key indicators to key indicators for the portion exceeding the basic threshold, and increase the weight score based on the ratio; if no, calculate the ratio of key indicators to key indicators for the portion below the basic threshold, and decrease the weight score based on the ratio.

[0125] In one embodiment, if so, the step of calculating the ratio of the key indicator to the key indicator for the portion exceeding the basic threshold, and increasing the weight score based on the ratio, includes:

[0126] When the key metric is recent pageviews, a piecewise function is used to adjust the increase in the weight score.

[0127] When the key metric is the user order success rate, a linear function is used to adjust the weighting score.

[0128] In one embodiment, the step of calculating the total score by matching attributes of split fields includes:

[0129] The total score is calculated based on the weight score corresponding to the attribute.

[0130] In one embodiment, the step of calculating the total score based on the weighted scores corresponding to the attributes includes:

[0131] The overall score for each product is obtained by adding the weighted scores of recent page views and user order success rate.

[0132] In one embodiment, the step of evaluating recommendation priority based on the total score includes:

[0133] Products are ranked based on their overall scores;

[0134] Products are placed in a preset recommendation list; the higher the overall rating, the greater the recommendation priority and the higher the position in the recommendation list.

[0135] In one embodiment, before the step of placing the product in a preset recommendation list, the steps include:

[0136] Determine whether the product meets the preset constraints;

[0137] If so, perform a second sort and place the product at the top of the recommended list.

[0138] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment on which the present application is applied.

[0139] One embodiment of this application also provides a computer storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements an attribute-based weight allocation method, including the following steps:

[0140] Set multiple attributes and configure the weight scores of the attributes in segments;

[0141] Receive request data sent by a preset client; wherein, the request data includes, but is not limited to, user information and product information;

[0142] Parse the request data and split all fields of the request data to obtain the split fields;

[0143] Match the split fields with the attributes and calculate the total score;

[0144] Priority recommendations will be based on the total score.

[0145] Sort according to the preset sorting rules to obtain the sorted result;

[0146] The sorting results are presented to the client.

[0147] In one embodiment, the step of setting multiple attributes and configuring weight scores for each attribute in a segmented manner includes:

[0148] Set basic thresholds for key metrics and use these basic thresholds as reference points for weighting scores; among these, key metrics include recent pageviews of the product and user order success rate.

[0149] Determine whether the key indicators are greater than the basic threshold;

[0150] If yes, calculate the ratio of key indicators to key indicators for the portion exceeding the basic threshold, and increase the weight score based on the ratio; if no, calculate the ratio of key indicators to key indicators for the portion below the basic threshold, and decrease the weight score based on the ratio.

[0151] In one embodiment, if so, the step of calculating the ratio of the key indicator to the key indicator for the portion exceeding the basic threshold, and increasing the weight score based on the ratio, includes:

[0152] When the key metric is recent pageviews, a piecewise function is used to adjust the increase in the weight score.

[0153] When the key metric is the user order success rate, a linear function is used to adjust the weighting score.

[0154] In one embodiment, the step of calculating the total score by matching attributes of split fields includes:

[0155] The total score is calculated based on the weight score corresponding to the attribute.

[0156] In one embodiment, the step of calculating the total score based on the weighted scores corresponding to the attributes includes:

[0157] The overall score for each product is obtained by adding the weighted scores of recent page views and user order success rate.

[0158] In one embodiment, the step of evaluating recommendation priority based on the total score includes:

[0159] Products are ranked based on their overall scores;

[0160] Products are placed in a preset recommendation list; the higher the overall rating, the greater the recommendation priority and the higher the position in the recommendation list.

[0161] In one embodiment, before the step of placing the product in a preset recommendation list, the steps include:

[0162] Determine whether the product meets the preset constraints;

[0163] If so, perform a second sort and place the product at the top of the recommended list.

[0164] In summary, the attribute-based weight allocation method, system, and computer device provided in this application embodiment, by pre-configuring weight scores for attributes, allows for customization of attribute weight scores according to actual needs. It dynamically calculates the total score for each product based on multiple key indicators, evaluates the product recommendation priority based on the total score, and then presents products with higher recommendation priority to the client. This not only significantly improves the objectivity and accuracy of weight allocation but also greatly enhances the system's flexibility and user-friendliness. Users can easily handle complex and ever-changing application scenarios, configure weight scores that meet requirements, and achieve a more objective, flexible, efficient, user-friendly, and easily expandable and maintainable system. This provides a more scientific and accurate weight allocation scheme for information decision-making.

[0165] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0166] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, system, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, system, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, system, article, or method that includes that element.

[0167] The above description is only a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural changes made based on the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An attribute-based weight allocation method, characterized in that, Includes the following steps: Set multiple attributes and configure weight scores for each attribute in a segmented manner; Receive request data sent by a preset client; wherein, the request data includes user information and product information; Parse the request data and split all fields of the request data to obtain the split fields; Match the splitting field with the attribute and calculate the total score; The recommendation priority is assessed based on the total score. Sort according to the preset sorting rules to obtain the sorted result; The sorting results are presented to the client. The step of setting multiple attributes and configuring weight scores for the attributes in a segmented manner includes: Set basic thresholds for key indicators and use these basic thresholds as reference points for the weight scores; wherein, the key indicators include the product's recent pageviews and the user order success rate; Determine whether the key indicator is greater than the basic threshold; If yes, calculate the ratio of the key indicator portion exceeding the basic threshold to the key indicator, and increase the weight score based on the ratio; if no, calculate the ratio of the key indicator portion below the basic threshold to the key indicator, and decrease the weight score based on the ratio. If so, the step of calculating the ratio of the key indicator greater than the basic threshold to the key indicator, and increasing the weight score according to the ratio, includes: When the key metric is the recent pageviews of the product, a piecewise function is used to adjust the increase in the weight score. When the key indicator is the user's order success rate, a linear function is used to adjust the weight score.

2. The attribute-based weight allocation method according to claim 1, characterized in that, The step of matching the attributes to the splitting field and calculating the total score includes: The total score is calculated based on the weighted scores corresponding to the attributes.

3. The attribute-based weight allocation method according to claim 2, characterized in that, The step of calculating the total score based on the weighted scores corresponding to the attributes includes: The overall score for each product is obtained by adding the weighted scores of the product's recent page views and the user's order success rate.

4. The attribute-based weight allocation method according to claim 3, characterized in that, The step of evaluating recommendation priority based on the total score includes: The products are ranked according to the comprehensive score. The products are placed in a preset recommendation list; wherein, the higher the overall score, the greater the recommendation priority and the higher the position in the recommendation list.

5. The attribute-based weight allocation method according to claim 4, characterized in that, Before the step of placing the product in a preset recommendation list, the following steps are included: Determine whether the product meets the preset constraints; If so, a second sorting process is performed, and the product is placed at the top of the recommended list.

6. An attribute-based weight allocation system, characterized in that, include: The settings module is used to set multiple attributes and configure the weight scores of the attributes in segments; The receiving module is used to receive request data sent by a preset client; The requested data includes user information and product information; The parsing module is used to parse the request data and split all fields of the request data to obtain the split fields; The calculation module is used to match the splitting fields with the attributes and calculate the total score; The evaluation module is used to assess the recommendation priority based on the total score; The sorting module is used to sort according to preset sorting rules and obtain the sorting result; The display module is used to present the sorting results to the client. A setting unit is used to set the basic threshold of key indicators and use the basic threshold as a reference point for the weight score; the key indicators include the recent page views of the product and the user order success rate. The first judgment unit is used to determine whether the key indicator is greater than the basic threshold. The calculation unit is used to calculate the ratio of the key indicator to the key indicator for the portion exceeding the basic threshold if the condition is met, and to increase the weight score based on the ratio. If not, calculate the ratio of the key indicators to the key indicators for the portion below the basic threshold, and reduce the weight score according to the ratio. The first adjustment subunit is used to adjust the increase in the weight score using a piecewise function when the key indicator is the recent pageviews of the product. The second adjustment subunit is used to adjust the weight score using a linear function when the key indicator is the user order success rate.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the attribute-based weight allocation method according to any one of claims 1 to 5.

8. A computer storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the attribute-based weight allocation method according to any one of claims 1 to 5.

Images