Attribute-based weight distribution method and system and computer equipment

Abstract

The invention provides an attribute-based weight distribution method and system and computer equipment, and the method comprises the steps: setting a plurality of attributes, and configuring weight scores for the attributes in a segmented manner; receiving request data sent by the client; analyzing the request data, and splitting all fields of the request data; matching the split fields with the attributes, and calculating a total score; evaluating a recommendation priority according to the total score; and sorting the recommendation priorities according to a sorting rule, and presenting a sorting result to the client. According to the method, the weight score of the attribute is configured, the weight score of the attribute can be self-defined according to actual requirements, the total score of each product is dynamically calculated in combination with a plurality of key indexes, the recommendation priority of the product is evaluated according to the total score, and the product with the high recommendation priority is presented to the client. The objectivity and the accuracy of weight distribution are remarkably improved, the flexibility and the user friendliness of the system are greatly enhanced, and the user can easily deal with complex and changeable application scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly to an attribute-based weight allocation method, system, and computer device. Background Art

[0002] At present, with the rapid development of information technology, information processing and information decision-making are particularly important in application scenarios such as business card recommendation and e-commerce systems. It is necessary to evaluate the advantages and disadvantages of an object according to a series of attributes or indicators, and convert these attributes or indicators into a comprehensive score through a weight system to assist information decision-making. However, the traditional weight system relies on manually set weight values, that is, it relies on experts' experience, historical data, or industry standards for manual judgment to allocate weights, resulting in the weight allocation being easily affected by subjectivity, reducing the accuracy and reliability of the final evaluation results.

[0003] In the face of complex and changeable application scenarios, due to the fixed existing weight allocation scheme, it is impossible to flexibly adjust according to the actual application scenario and requirements, resulting in low adaptability and flexibility, and it is difficult to accurately reflect the relative importance between attributes. Moreover, the importance of different attributes will change with time, environment, or other factors, and the weight system cannot dynamically adjust according to these changes, resulting in low dynamic adjustment ability.

[0004] Furthermore, the interface of the existing weight allocation system is complex, the operation is cumbersome, and the documentation is incomplete, making it difficult for users to understand and use, resulting in a decline in user-friendliness and applicability. In actual use, with the continuous expansion and change of application scenarios, it will also lead to poor scalability and maintainability of the weight system, and it is difficult to update and optimize in a timely manner when facing new requirements or changes, so that the system cannot operate and develop stably in the long term. Summary of the Invention

[0005] The present invention aims to solve the problems in the above-mentioned existing technology that the weight system is easily affected by subjectivity, lacks flexibility and dynamic adjustment ability, and is difficult to accurately reflect the relative importance between attributes, and provides an attribute-based weight allocation method, system, and computer device.

[0006] The present invention provides an attribute-based weight allocation method, which includes the following steps:

[0007] Set multiple attributes, and configure weight scores for the attributes 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 split fields;

[0010] Match the split fields with the attributes and calculate the total score;

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

[0012] Present the sorting result to the client.

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

[0014] Set the basic threshold of the key indicators, and use the basic threshold as the reference point for the weight scores; wherein, the key indicators include the recent view volume and the user order success rate of the product;

[0015] Judge whether the key indicators are greater than the basic threshold;

[0016] If so, calculate the ratio of the key indicators of the part greater than the basic threshold to the key indicators, and increase the weight scores according to the ratio; if not, calculate the ratio of the key indicators of the part less than the basic threshold to the key indicators, and decrease the weight scores according to the ratio.

[0017] Further, in the step of if so, calculating the ratio of the key indicators of the part greater than the basic threshold and increasing the weight scores according to the ratio, it includes:

[0018] When the key indicator is the recent view volume, use a piecewise function to adjust the increased value of the weight scores;

[0019] When the key indicator is the user order success rate, use a linear function to adjust the weight scores.

[0020] Further, in the step of matching the split fields with the attributes and calculating the total score, it includes:

[0021] Calculate the total score according to the weight scores corresponding to the attributes.

[0022] Further, in the step of calculating the total score according to the weight scores corresponding to the attributes, it includes:

[0023] Add the weight scores of the recent view volume and the user order success rate to obtain the comprehensive score of each product.

[0024] Further, in the step of evaluating the recommendation priority according to the total score, it includes:

[0025] Sort the products according to the comprehensive score;

[0026] Place the products in a preset recommended list respectively; among them, the higher the comprehensive score, the greater the recommended priority, and the more forward the position in the recommended list.

[0027] Further, before the step of placing the products in the preset recommended list, it includes:

[0028] Judge whether the products meet the preset constraint conditions;

[0029] If so, perform a secondary sorting and place the products in front of the recommended list.

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

[0031] A setting module, used to set multiple attributes and configure weight scores for the attributes in a segmented manner;

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

[0033] An analysis module, used to analyze the request data and split all fields of the request data to obtain split fields;

[0034] A calculation module, used to match the split fields with the attributes and calculate the total score;

[0035] An evaluation module, used to evaluate the recommended priority according to the total score;

[0036] A sorting module, used to sort according to a preset sorting rule to obtain a sorting result;

[0037] A display module, used to present the sorting result to the client.

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

[0039] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above methods are implemented.

[0040] The present invention provides an attribute-based weight distribution method, system and computer device, having the following beneficial effects:

[0041] By pre-configuring the weight scores of attributes, it is possible to customize the weight scores of attributes according to actual needs, dynamically calculate the total scores of each product in combination with multiple key indicators, then evaluate the recommendation priorities of products based on the total scores, and finally present the products or business cards with high recommendation priorities to the client. This not only significantly improves the objectivity and accuracy of weight allocation, but also greatly enhances the flexibility and user-friendliness of the system. It can easily handle complex and changing application scenarios, configure weight scores that meet the requirements, be more objective, flexible, efficient, user-friendly, and easy to expand and maintain, and can provide a more scientific and accurate weight allocation scheme for information decision-making. Brief Description of the Drawings

[0042] Figure 1 It is a schematic diagram of the method steps of a method for attribute-based weight allocation in the present invention;

[0043] Figure 2 It is a system structure block diagram of a system for attribute-based weight allocation in the present invention;

[0044] Figure 3 It is a structure block diagram of a computer device of the present invention;

[0045] Figure 4 It is a schematic diagram of the process of an embodiment of a method for attribute-based weight allocation in the present invention;

[0046] Figure 5 It is a schematic diagram of the steps of an embodiment of a method for attribute-based weight allocation in the present invention.

[0047] Marking Explanation: Setting module 10, receiving module 20, parsing module 30, calculating module 40, evaluating module 50, sorting module 60, displaying module 70. Detailed Embodiment

[0048] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0050] Refer to Figure 1 and Figure 4 , a method for attribute-based weight allocation in an embodiment of the present invention, includes:

[0051] S1. Set multiple attributes and configure weight scores for the attributes in a segmented manner;

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

[0053] S3. Analyze the request data and split all fields of the request data to obtain split fields;

[0054] S4. Match the split fields with the attributes and calculate the total score;

[0055] S5. Evaluate the recommendation priority according to the total score;

[0056] S6. Sort according to a preset sorting rule to obtain a sorting result;

[0057] S7. Present the sorting result to the client.

[0058] In the above steps, first, set multiple attributes and, according to actual requirements, flexibly configure corresponding weight scores for each attribute. Then, the user can input request data on a preset client; wherein, the client can be a communication device or a display screen. In a specific embodiment, the request data is an HTTP (HyperText Transfer Protocol) request, a response protocol for communication between a client and a server, and the request data includes the status information of the request and the request content. Then, receive the request data, analyze the request data, split all fields of the request data to obtain multiple split fields, then match the attributes of each split field, and calculate the total score. Evaluate the recommendation priority according to the total score, then sort the products or business cards according to a preset sorting rule, and finally present the sorting result to the client. Among them, the sorting rule can be descending order or ascending order. In a specific embodiment, if the sorting rule is from high to low, then sort the products according to the recommendation priority from high to low, place the products with high recommendation priority in the front, place the products with low recommendation priority at the back, and present this sorting result to the client.

[0059] In a specific embodiment, the present application is applied to a business card recommendation scenario. Specifically, business card recommendation usually has a business card list for display. The traditional business card list is sorted in a relatively simple manner, such as sorting in reverse order of registration time, which will cause the business cards registered later to be ranked in the front position, and then cause the business cards with low activity and incomplete business card information to be displayed in the front position of the business card list. The present application can set business card attributes, such as age, gender, last login time, number of active days, registration time, and configure different weight scores for each attribute. After receiving the user's request data, the request data is first parsed, and all fields of the request data are split to obtain the split fields; then the pre-set attributes are matched, and the total score is calculated according to the weight score corresponding to the attribute and returned. Finally, the business cards are sorted in the business card list according to the total score and presented to the client. When it is necessary to sort again later, only the new request data needs to be input. The business cards that meet the user's needs can be placed in the front position of the business card list, which is easy to find and meets the user's usage needs.

[0060] As attached Figure 5 As shown, in another specific embodiment, the present application is applied to a product recommendation system of an e-commerce platform. First, attributes are pre-set, such as product sales, number of user reviews, average user ratings, and recent page views. Then, weight scores are assigned to each attribute according to business needs. When the client initiates an HTTP request, both user data and product data will be 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 a pre-set attribute, and the total score is calculated according to the weight score corresponding to the attribute. This is used to evaluate the recommendation priority of the product for the user, and the products with the highest to lowest recommendation priority are sorted and presented to the client.

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

[0062] Set basic thresholds for key indicators and use them as reference points for weighted scores; key indicators include the product's recent page views and user order success rate;

[0063] Determine whether the key indicator is greater than the basic threshold;

[0064] If so, calculate the ratio of the key indicators of the part greater than the basic threshold to the key indicators, and increase the weight score according to the ratio; if not, calculate the ratio of the key indicators of the part less than the basic threshold to the key indicators, and reduce the weight score according to the ratio.

[0065] In this embodiment, a basic threshold for a key indicator is set, and the basic threshold is used as a reference point for the weight score. Then, it is determined whether the key indicator is greater than the basic threshold, that is, it is determined whether the recent view volume or the user order placement success rate is greater than the basic threshold. If so, the proportion of the part exceeding the basic threshold in the total key indicator is calculated, and the weight score is increased according to the proportion. If not, the proportion of the part less than the basic threshold in the total key indicator is calculated, and the weight score is decreased according to the proportion.

[0066] Specifically, when this application is applied to the scenario of product recommendation on an e-commerce platform, scoring is based on the number of times and the success rate. Specifically, according to two key indicators of the "recent view volume" and "user order placement success rate" of the product, the weight score of the product is dynamically adjusted. By comprehensively considering these two factors of "recent view volume" and "user order placement success rate", it can more accurately reflect the user's interest in the product and the purchase potential of the product, thereby optimizing the sorting result.

[0067] More specifically, the recent view volume refers 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 basic threshold is set. In this embodiment, the basic threshold is the basic view volume threshold and serves as the starting point of the weight score. When the recent view volume of the product exceeds the set basic view volume threshold, the proportion of the part exceeding the basic view volume in the total recent view volume is calculated, and the weight score is increased according to the proportion. When the recent view volume of the product is lower than the set basic view volume threshold, the proportion of the part lower than the basic view volume in the total recent view volume is calculated, and the weight score is decreased according to the proportion.

[0068] In another specific embodiment, the key indicator is the user order placement success rate, which refers to the proportion of users who have viewed the product and finally placed an order to purchase the product. A user order placement success rate benchmark value is set as a reference point for the weight score. When the user order placement success rate of the product is higher than the benchmark value, the proportion of the part higher than the benchmark value in the total user order placement success rate is calculated, and the weight score is increased according to the calculated proportion. When the order placement success rate of the product is lower than the benchmark value, the proportion of the part lower than the benchmark value in the total user order placement success rate is calculated, and the weight score is decreased according to the calculated proportion.

[0069] In one embodiment, if so, in the step of calculating the ratio value of the key indicator of the part greater than the basic threshold to the key indicator and increasing the weight score according to the ratio value, it includes:

[0070] When the key indicator is the recent view volume, a piecewise function is used to adjust the increase value of the weight score;

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

[0072] In this embodiment, when the set key indicator is the recent view volume, the increase value of the weight score is adjusted by using a piecewise function to smooth the growth of the weight score and avoid the influence of extreme values on the distribution of the weight score.

[0073] More specifically, when the recent view volume is less than 100 times, the growth of the weight score is relatively slow; when the recent view volume is between 100 and 1000 times, the growth of the weight score is relatively fast; when the recent view volume is higher than 1000 times, the growth of the weight score tends to be gentle again.

[0074] When the set key indicator is the user order placement success rate, a linear function is used to adjust the increase or decrease value of the weight score. It is a direct proportional relationship, and through linear mapping, the importance of the user order placement success rate to the user's purchase decision can be reflected.

[0075] In one embodiment, in the step of calculating the total score for the split field matching attributes, it includes:

[0076] Calculate the total score according to the weight score corresponding to the attribute.

[0077] In this embodiment, when calculating the total score, it is calculated according to the weight scores corresponding to the attributes respectively. For example, if the attributes for split field matching are Attribute 1 and Attribute 2, the weight score of Attribute 1 is 2, and the weight score of Attribute 2 is 3, then the calculated total score is 5.

[0078] In one embodiment, in the step of calculating the total score according to the weight score corresponding to the attribute, it includes:

[0079] Add the weight scores of the recent view volume and the user order placement success rate to obtain the comprehensive score of each product.

[0080] In this embodiment, in the application of the e-commerce platform, it is necessary to calculate the comprehensive score of each commodity, that is, add the weight scores of the recent view volume and the user order placement success rate of the commodity to obtain the comprehensive score of each commodity.

[0081] In addition, the distribution of the weight score can be adjusted according to business requirements and scenario characteristics. In a specific embodiment, for a platform with more new users, more attention is paid to the view volume, so it is necessary to increase the weight score of the recent view volume. For a platform with more old users, more attention is paid to the user order placement success rate, so it is necessary to increase the weight score of the user order placement success rate.

[0082] In one embodiment, in the step of evaluating the recommendation priority according to the total score, it includes:

[0083] Sort the products according to the comprehensive score;

[0084] Place the products in the preset recommended lists respectively; among them, the higher the comprehensive score, the greater the recommendation priority, and the more forward the position in the recommended list.

[0085] In this embodiment, the products are sorted according to the comprehensive score and sorted in the recommended list. The higher the comprehensive score, the greater the recommendation priority, and the more forward the position in the recommended list. And the lower the comprehensive score, the smaller the recommendation priority, and the more backward the position in the recommended list.

[0086] Specifically, there are product A and product B. The recent view volume of product A is 1500 times, and the user order success rate is 20%; the recent view volume of product B is 800 times, and the user order success rate is 40%. Since the recent view volume of product A is relatively high, the weight score of its recent view volume will be relatively high. However, since the user order success rate is relatively low, the weight score of its user order success rate will be correspondingly reduced. While the recent view volume of product B is relatively low, but its user order success rate is relatively high. Therefore, the weight score of its user order success rate will be relatively high. Since the weight score of the recent view volume of product A is relatively high, the comprehensive score of product A will be slightly higher than that of product B. However, the ranking in the recommended list will be lowered to reflect the relatively low user order success rate. While product B, although its recent view volume is relatively low, but its user order success rate is relatively high, will be ranked in a more forward position in the recommended list. Through the algorithm of comprehensive score, it can more accurately reflect the user interest and purchase potential of the products, thereby optimizing the ranking of the recommended list and improving user satisfaction and purchase conversion rate.

[0087] In an embodiment, before the step of placing the products in the preset recommended lists, it includes:

[0088] Judge whether the product meets the preset constraint conditions;

[0089] If so, perform a secondary sorting and place the product in the front of the recommended list.

[0090] In this embodiment, judge whether the product meets the preset constraint conditions, where the constraint conditions can be whether it is a new product or a popular category. If so, place this product in the front of the recommended list. By adding constraint conditions, the recommended results can be further optimized.

[0091] In summary, in specific implementation, first, set multiple attributes and configure weight scores for the attributes in a segmented manner; then set the base threshold of the key indicators and use the base threshold as the reference point for the weight scores; then determine whether the key indicators are greater than the base threshold; if so, calculate the ratio of the key indicators of the part greater than the base threshold to the key indicators, and increase the weight scores according to the ratio; the increase method is that when the key indicator is the recent view volume, use a piecewise function to adjust the increased value of the weight scores; when the key indicator is the user order success rate, use a linear function to adjust the weight scores. If not, calculate the ratio of the key indicators of the part less than the base threshold to the key indicators, and reduce the weight scores according to the ratio. Then, receive the request data sent by the preset client; parse the request data and split all fields of the request data to obtain the split fields; then match the split fields with the attributes and calculate the total score; calculate the total score according to the weight scores corresponding to the attributes; add the weight scores of the recent view volume and the user order success rate to obtain the comprehensive score of each product; evaluate the recommendation priority according to the total score; sort the products according to the comprehensive score; determine whether the products meet the preset constraint conditions; if so, perform a secondary sorting and place the products in front of the recommendation list; place the products in the preset recommendation lists respectively; then sort according to the preset sorting rules to obtain the sorting result; finally, present the sorting result to the client. This application can add attributes according to requirements and is applicable to more application scenarios and usage requirements. Whether in the scenario of sorting the user information completeness or the scenario of recommending products on an e-commerce platform, appropriate attributes can be selected specifically for weight score allocation, making the system have strong versatility and adaptability and not being limited to the mode of fixed and small number of attributes. Moreover, when new key indicators appear subsequently, users can conveniently adjust the attributes, such as adding or deleting, and then input the request data again, and the weight scores can be configured according to the new attribute configuration, perform weight score calculation and subsequent processing, so that the system can respond quickly and change dynamically according to requirements to ensure that the output result meets the actual requirements.

[0092] Furthermore, the adjustment of attributes can be achieved by means of automated feature selection instead of the way of manual addition or deletion by users; among them, automated feature selection refers to automatically screening out useful features from the dataset by using algorithms or tools to improve performance and reduce computational costs, such as the filtering method, that is, based on statistical indicators to evaluate the relationship between features and target variables and select the most relevant features.

[0093] Refer to the appendix Figure 2 , a weight allocation system based on attributes, including:

[0094] A setting module, used to set multiple attributes and configure weight scores for the attributes in a segmented manner;

[0095] A setting unit for setting a basic threshold of a key indicator and using the basic threshold as a reference point for weight scores;

[0096] A first judgment unit for judging whether the key indicator is greater than the basic threshold;

[0097] A calculation unit for, if so, calculating the ratio of the key indicator of the part greater than the basic threshold to the key indicator and increasing the weight score according to the ratio; if not, calculating the ratio of the key indicator of the part less than the basic threshold to the key indicator and decreasing the weight score according to the ratio;

[0098] A first adjustment subunit for, when the key indicator is the recent view volume, adjusting the increased value of the weight score by using a piecewise function;

[0099] A second adjustment subunit for, when the key indicator is the user order success rate, adjusting the weight score by using a linear function;

[0100] A receiving module for receiving request data sent by a preset client;

[0101] An analysis module for analyzing the request data and splitting all fields of the request data to obtain split fields;

[0102] A calculation module for matching the split fields with attributes and calculating the total score;

[0103] A calculation unit for calculating the total score according to the weight score corresponding to the attribute;

[0104] A calculation subunit for adding the weight scores of the recent view volume and the user order success rate to obtain the comprehensive score of each product;

[0105] An evaluation module for evaluating the recommendation priority according to the total score;

[0106] A first sorting unit for sorting the products according to the comprehensive score;

[0107] A second judgment unit for judging whether the product meets the preset constraint conditions;

[0108] A second sorting unit for, if so, performing a secondary sorting and placing the product in front of the recommendation list;

[0109] A placement unit for placing the products in a preset recommendation list respectively;

[0110] A sorting module for sorting according to a preset sorting rule to obtain a sorting result;

[0111] A display module for presenting the sorting result to the client.

[0112] In this embodiment, it 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 weight scores for the attributes in a segmented manner; first, the setting unit sets the basic threshold of the key indicators and uses the basic threshold as a reference point for the weight scores; then, the first judgment unit judges whether the key indicators are greater than the basic threshold. If so, the calculation unit calculates the ratio of the key indicators of the part greater than the basic threshold to the key indicators and increases the weight scores according to the ratio; if not, the calculation unit calculates the ratio of the key indicators of the part less than the basic threshold to the key indicators and decreases the weight scores according to the ratio. During this period, when the key indicator is the recent view volume, the first adjustment subunit adjusts the increased value of the weight scores using a piecewise function; when the key indicator is the user order success rate, the second adjustment subunit adjusts the weight scores using a linear function. Then, after the user issues a request on the client side, the receiving module receives the request data. First, the parsing module parses the request data and splits all fields of the request data to obtain the split fields; the calculation module matches the split fields with the attributes and calculates the total score; then, the calculation unit calculates the total score according to the weight scores corresponding to the attributes; the calculation subunit adds the weight scores of the recent view volume and the user order success rate to obtain the comprehensive score of each product; the evaluation module evaluates the recommendation priority according to the total score; then, the first sorting unit sorts the products according to the comprehensive score; the second judgment unit judges whether the products meet the preset constraint conditions; if so, the second sorting unit performs a secondary sorting, and the placement unit places the products in the preset recommendation lists respectively; then, the sorting module sorts according to the preset sorting rules to obtain the sorting result; finally, the display module presents the sorting result on the client side.

[0113] Refer to the appendix Figure 3 , in the embodiment of the present application, a computer device is further provided. The computer device can be a server, and its internal structure can be as Figure 3As shown. The computer device includes a processor, a memory, a network interface, and a database. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system, the computer program, and the database in the non-volatile storage medium. The database of the computer device is used to store data such as templates, tables, and preset fields. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for weight assignment based on attributes, including the following steps:

[0114] Set multiple attributes and configure weight scores for the attributes in a segmented manner;

[0115] Receive request data sent by a preset client; among them, 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 split fields;

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

[0118] Evaluate the recommendation priority according to the total score;

[0119] Sort according to a preset sorting rule to obtain a sorting result;

[0120] Present the sorting result to the client.

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

[0122] Set a basic threshold for key indicators and use the basic threshold as a reference point for weight scores; among them, the key indicators include the recent view volume of the product and the user order success rate;

[0123] Judge whether the key indicator is greater than the basic threshold;

[0124] If so, calculate the ratio of the key indicator of the part greater than the basic threshold to the key indicator, and increase the weight score according to the ratio; if not, calculate the ratio of the key indicator of the part less than the basic threshold to the key indicator, and decrease the weight score according to the ratio.

[0125] In one embodiment, if so, in the step of calculating the ratio of the key indicator of the part greater than the basic threshold and increasing the weight score according to the ratio, it includes:

[0126] When the key indicator is the recent page view volume, a piecewise function is used to adjust the increased value of the weight score;

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

[0128] In one embodiment, in the step of calculating the total score for the split field matching attribute, it includes:

[0129] Calculate the total score according to the weight score corresponding to the attribute.

[0130] In one embodiment, in the step of calculating the total score according to the weight score corresponding to the attribute, it includes:

[0131] Add the weight scores of the recent page view volume and the user order success rate to obtain the comprehensive score of each product.

[0132] In one embodiment, in the step of evaluating the recommendation priority according to the total score, it includes:

[0133] Sort the products according to the comprehensive score;

[0134] Place the products in the preset recommendation lists respectively; among them, the higher the comprehensive score, the greater the recommendation priority, and the more forward the position in the recommendation list.

[0135] In one embodiment, before the step of placing the products in the preset recommendation lists, it includes:

[0136] Judge whether the products meet the preset constraint conditions;

[0137] If so, perform a secondary sorting and place the products in the front of the recommendation list.

[0138] Those skilled in the art can understand that Figure 3 the structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied.

[0139] One embodiment of this application also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a weight allocation method based on attributes, including the following steps:

[0140] Set multiple attributes and configure the weight scores for the attributes in a segmented manner;

[0141] Receive the request data sent by a preset client; among them, 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] Evaluate the recommendation priority according to the total score;

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

[0146] Present the sorting result to the client.

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

[0148] Set the basic threshold of the key indicators and use the basic threshold as the reference point for the weight scores; among them, the key indicators include the recent view volume of the product and the user order success rate;

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

[0150] If so, calculate the ratio value of the key indicators greater than the basic threshold to the key indicators, and increase the weight scores according to the ratio value; if not, calculate the ratio value of the key indicators less than the basic threshold to the key indicators, and reduce the weight scores according to the ratio value.

[0151] In one embodiment, if so, in the step of calculating the ratio value of the key indicators greater than the basic threshold and increasing the weight scores according to the ratio value, it includes:

[0152] When the key indicator is the recent view volume, use a piecewise function to adjust the increased value of the weight scores;

[0153] When the key indicator is the user order success rate, use a linear function to adjust the weight scores.

[0154] In one embodiment, in the step of matching the split fields with the attributes and calculating the total score, it includes:

[0155] Calculate the total score according to the weight scores corresponding to the attributes.

[0156] In one embodiment, in the step of calculating the total score according to the weight scores corresponding to the attributes, it includes:

[0157] Add the weight scores of the recent view volume and the user order success rate to obtain the comprehensive score of each product.

[0158] In one embodiment, in the step of evaluating the recommendation priority according to the total score, it includes:

[0159] Sort the products according to the comprehensive score;

[0160] Place the products in the preset recommended lists respectively; among them, the higher the comprehensive score, the higher the recommendation priority, and the more forward the position in the recommended list.

[0161] In one embodiment, before the step of placing the products in the preset recommended lists, it includes:

[0162] Judge whether the products meet the preset constraint conditions;

[0163] If so, perform a secondary sorting and place the products in front of the recommended list.

[0164] In summary, the present application provides an attribute-based weight assignment method, system and computer device in the embodiments. By pre-configuring the weight scores for attributes, it can customize the weight scores of attributes according to actual needs, dynamically calculate the total scores of each product in combination with multiple key indicators, then evaluate the recommendation priority of the products according to the total scores, and then present the products with high recommendation priority to the client. It not only significantly improves the objectivity and accuracy of weight assignment, but also greatly enhances the flexibility and user-friendliness of the system, enabling users to easily cope with complex and changeable application scenarios, configure weight scores that meet the requirements, and is more objective, flexible, efficient, user-friendly and easy to expand and maintain, and can provide a more scientific and accurate weight assignment scheme for information decision-making.

[0165] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database or other medium provided in the present application and used in the embodiments can include non-volatile and / or volatile memories. The non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. The volatile memory can include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0166] It should be noted that in this document, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, system, article or method comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such process, system, article or method. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, system, article or method comprising such element.

[0167] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present application by the same token.

Claims

1. A weight allocation method based on attributes, characterized in that: The following steps are involved: Set multiple attributes and configure weight scores for the attributes in sections; Receiving request data sent by a preset client; wherein the request data includes but is not limited to user information and product information; Parsing the request data, and splitting all fields of the request data to obtain split fields; Matching the split fields with the attributes and calculating a total score; evaluating the priority of recommendations according to the total score; Sort according to the preset sorting rules to obtain the sorting results; The sorting result is presented to the client.

2. The attribute-based weight allocation method according to claim 1, characterized in that: The step of setting a plurality of attributes and configuring weight scores for the attributes in sections includes: Setting a basic threshold value of a key indicator and using the basic threshold value as a reference point for the weight score; wherein the key indicator includes the recent page views of the product and the success rate of user orders; Determining whether the key indicator is greater than the basic threshold; If so, calculate the ratio of the key indicator of the part greater than the basic threshold to the key indicator, and increase the weight score according to the ratio; if not, calculate the ratio of the key indicator of the part less than the basic threshold to the key indicator, and reduce the weight score according to the ratio.

3. The attribute-based weight allocation method according to claim 2, characterized in that: If so, then 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 indicator is the recent page views, a piecewise function is used to adjust the increase in the weight score; When the key indicator is the success rate of the user's order, a linear function is used to adjust the weight score.

4. The attribute-based weight allocation method according to claim 3, characterized in that: The step of matching the split fields with the attributes and calculating the total score includes: The total score is calculated according to the weight scores corresponding to the attributes.

5. The attribute-based weight allocation method according to claim 4, characterized in that: The step of calculating the total score according to the weight score corresponding to the attribute includes: The weighted scores of the recent page views and the user order success rate are added together to obtain a comprehensive score for each product.

6. The attribute-based weight allocation method according to claim 5, characterized in that: The step of evaluating the recommendation priority according to the total score includes: sorting the products according to the comprehensive scores; The products are placed in a preset recommendation list respectively; wherein, the higher the comprehensive score is, the greater the recommendation priority is, and the higher the position in the recommendation list is.

7. The attribute-based weight allocation method according to claim 6, characterized in that: Before the step of placing the product in a preset recommendation list, the method includes: Determine whether the product meets the preset constraints; If so, a secondary sort is performed and the product is placed at the front of the recommendation list.

8. A weight distribution system based on attributes, characterized in that: include: A setting module, used to set multiple attributes and configure weight scores for the attributes in sections; A receiving module, used for receiving request data sent by a preset client; A parsing module, used for parsing the request data and splitting all fields of the request data to obtain split fields; A calculation module, used for matching the split fields with the attributes and calculating a total score; An evaluation module, used for evaluating the recommendation priority according to the total score; A sorting module is used to sort according to preset sorting rules to obtain sorting results; A display module is used to present the sorting result to the client.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps in the attribute-based weight assignment method described in any one of claims 1 to 7 are implemented.

10. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the attribute-based weight assignment method described in any one of claims 1 to 7 are implemented.

Images