Scoring template-based processing method, apparatus, device, storage medium, and product

Abstract

The application discloses a processing method and device based on a scoring template, equipment, a storage medium and a product, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a scoring scene feature corresponding to a target business link in a preset type of business, wherein the scoring scene feature comprises a business element feature, a user operation feature and an object category feature of a preset object, the preset object is provided by a candidate subject to be scored, the scoring scene feature is input into a preset template recommendation model corresponding to the target business link, a recommended scoring template is determined from a preset scoring template library according to the output of the preset template recommendation model, and the recommended scoring template is used for scoring the candidate subject. Through the above technical solution, the preset template recommendation model is used to recommend a scoring template according to the current scoring scene feature, so that when the candidate subject is scored, a more flexible scoring template that is more suitable for a specific scoring scene can be used for scoring.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of artificial intelligence, in particular to a processing method and device based on a scoring template, equipment, a storage medium and a product. BACKGROUND

[0002] At present, in many business scenarios, a subject involved in the business scenario needs to be scored to select a suitable subject to carry out relevant business. For example, in a procurement business scenario, a supplier needs to be scored to select a suitable supplier to carry out procurement of relevant goods or services.

[0003] When scoring, an inherent scoring template is usually used for scoring, which has poor flexibility and inaccurate scoring results. SUMMARY

[0004] The embodiment of the present application provides a processing method and device based on a scoring template, equipment, a storage medium and a product, which can optimize an existing processing scheme based on a scoring template.

[0005] In a first aspect, the embodiment of the present application provides a processing method based on a scoring template, comprising:

[0006] obtaining scoring scene features corresponding to a target business link in a preset type of business, wherein the scoring scene features comprise business element features, user operation features and object category features of a preset object, and the preset object is provided by a candidate subject to be scored;

[0007] inputting the scoring scene features into a preset template recommendation model corresponding to the target business link;

[0008] determining a recommended scoring template from a preset scoring template library according to an output of the preset template recommendation model, wherein the recommended scoring template is used for scoring the candidate subject.

[0009] In a second aspect, the embodiment of the present application further provides a processing device based on a scoring template, comprising:

[0010] a scoring scene feature acquisition module, configured to obtain scoring scene features corresponding to a target business link in a preset type of business, wherein the scoring scene features comprise business element features, user operation features and object category features of a preset object, and the preset object is provided by a candidate subject to be scored;

[0011] a feature input module, configured to input the scoring scene features into a preset template recommendation model corresponding to the target business link;

[0012] The recommendation template determination module is configured to determine a recommended scoring template from a preset scoring template library according to an output of the preset template recommendation model, wherein the recommended scoring template is used to score the candidate subject.

[0013] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the scoring template-based processing method according to any of the embodiments of the present application when executing the program.

[0014] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the program is executable on a processor to implement the scoring template-based processing method according to any of the embodiments of the present application.

[0015] In a fifth aspect, a computer program product is provided, which includes a computer program, and the computer program is executable on a processor to implement the scoring template-based processing method according to any of the embodiments of the present application.

[0016] The scoring template-based processing scheme provided by the embodiments of the present application obtains scoring scene features corresponding to a target business link in a preset type of business, wherein the scoring scene features include business element features, user operation features, and object category features of a preset object, the preset object is provided by a candidate subject to be scored, the scoring scene features are input into a preset template recommendation model corresponding to the target business link, a recommended scoring template is determined from a preset scoring template library according to an output of the preset template recommendation model, and the recommended scoring template is used to score the candidate subject. By using the above technical scheme, for a business link currently concerned in a preset type of business, the current scoring scene is comprehensively represented based on the business element features, the user operation features, and the object category features of the preset object, and a corresponding preset template recommendation model is used to recommend a scoring template according to the current scoring scene features, so that when scoring the candidate subject, a scoring template that is more flexible and fits a specific scoring scene can be used for scoring, and the scoring result is more in line with the actual situation and more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0018] Figure 1A flow chart of a processing method based on a scoring template provided by an embodiment of the present application;

[0019] Figure 2 A flow chart of another processing method based on a scoring template provided by an embodiment of the present application;

[0020] Figure 3 A structural schematic diagram of a processing device based on a scoring template provided by an embodiment of the present application;

[0021] Figure 4 A structural schematic diagram of an electronic device implementing a processing method based on a scoring template according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The present application will be further described below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely intended for the purpose of interpretation of the present application and are not limiting of the present application. In addition, it should be noted that only the parts related to the present application are shown in the accompanying drawings for the purpose of description.

[0023] It should be noted that similar reference numerals and letters refer to similar items in the accompanying drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are merely used for differentiation and cannot be understood as indicating or implying relative importance. The acquisition, storage, use, processing, and the like of data in the technical solutions of the present application all comply with the relevant provisions of national laws and regulations.

[0024] Figure 1 A flow chart of a processing method based on a scoring template provided by an embodiment of the present application, the present embodiment of the present disclosure is applicable to the case of evaluating a candidate subject based on a scoring template. The method can be executed by a processing device based on a scoring template, which can be implemented in the form of software and / or hardware, and can be implemented by an electronic device, which can be a mobile terminal such as a mobile phone, a smart watch, a tablet computer, and a personal digital assistant, or a device such as a personal computer (PC) or a server.

[0025] In step 101, a scoring scene feature corresponding to a target business link in a preset type of business is acquired, wherein the scoring scene feature includes a business element feature, a user operation feature, and an object category feature of a preset object, and the preset object is provided by a candidate subject to be scored.

[0026] In the embodiment of the present application, the candidate subject can be understood as a subject to be evaluated associated with a preset type of business, and the specific type can be determined according to the preset type of business. The above-mentioned subject is used to provide a preset object, and the type of the preset object can also be determined according to the preset type of business. For example, the preset type of business can be a procurement business (or procurement management business), and the corresponding subject can include a supplier, and the corresponding preset object can include a procurement object, etc. For example, the preset type of business can also be a video pushing business, and the corresponding subject can include a video publisher or a video producer, and the corresponding preset object can include a video. For the convenience of description, the procurement business is taken as an example for description hereinafter.

[0027] For example, the business flow usually includes a plurality of business links. For example, the business link can include a procurement information publishing link, a supplier bidding link, a supplier negotiation link, a supplier performance link, and an acceptance link, etc. For different business links, the focus of attention on the candidate subject and the degree of attention of different focuses of attention can be different. In the embodiment of the present application, the corresponding scoring template can be determined for the specific business link, and the target business link can be understood as the business link currently focused in the preset type of business, or the business link currently in the preset type of business.

[0028] In the related art, when scoring the supplier, a preset fixed scoring template is usually used for scoring. However, in the actual business development process, there are often a variety of factors that can make the focus of attention on the candidate subject and the degree of attention of different focuses of attention in the same business link different. The fixed scoring template is difficult to score specifically, resulting in inaccurate scoring results, so that it is difficult to reasonably select the supplier to be used according to the scoring results.

[0029] In the embodiment of the present application, the related information of the factors affecting the scoring focus is obtained as the scoring scene feature, and a preset template recommendation model is used for accurate scoring template recommendation. In the scoring scene feature, the business element feature, the user operation feature, and the object category feature of the preset object are included, and more rich scene features can also be set according to the actual needs. The business element feature can be understood as a static feature related to the business, and the user operation feature can be understood as a dynamic feature related to the business. The user can be understood as a business personnel of the preset type of business, such as a procurement management personnel, etc.

[0030] Optionally, the business element feature includes at least one of whether a primary subject exists, a primary subject name, whether a historical subject exists, a historical subject name, whether a business plan data has been generated, and the business plan data. The advantage of this arrangement is that it can accurately describe the static features related to the business. Taking the procurement business as an example, the business element feature can include whether a pre-selected supplier exists, and if so, the name of the pre-selected supplier; whether a supplier that has been used exists, and if so, the name of the supplier that has been used; and whether a procurement business plan has been generated, and if so, the relevant data in the procurement business plan.

[0031] Optionally, the user operation feature includes at least one of whether a subject selection operation has been performed, whether a business plan creation operation has been performed, and whether a re-recommendation operation has been input. The advantage of this arrangement is that it can accurately describe the dynamic features related to the business. Taking the procurement business as an example, it can include whether a supplier selection operation has been performed by the user, whether a procurement plan creation operation has been performed by the user, and whether a re-initiation of the recommendation of the scoring template has been performed by the user in the case that the user is not satisfied with the recommendation.

[0032] Taking the procurement business as an example, the preset object includes a procurement object, the object category feature can include products and services, and the scoring focus points of different categories can be different. The product category can focus more on product quality and product supply, while the service category can focus more on service quality and service experience. Optionally, more fine-grained categories can also be included. Taking products as an example, it can include office supplies, daily necessities, electronic products, and food, etc. Taking services as an example, it can include engineering services, property services, and software development services, etc.

[0033] Step 102, inputting the scoring scenario feature into the preset template recommendation model corresponding to the target business link.

[0034] Taking the procurement business as an example, the preset object includes a procurement object, the object category feature can include products and services, and the scoring focus points of different categories can be different. The product category can focus more on product quality and product supply, while the service category can focus more on service quality and service experience. Optionally, more fine-grained categories can also be included. Taking products as an example, it can include office supplies, daily necessities, electronic products, and food, etc. Taking services as an example, it can include engineering services, property services, and software development services, etc.

[0035] Optionally, after obtaining the multi-dimensional scoring scenario feature, the multi-dimensional feature can be flattened into a single-dimensional feature through dimension reduction, as the input of the model, to improve the operation efficiency of the model.

[0036] Optionally, the preset template recommendation model can be trained based on a decision tree model, for example. In the model training stage, a large amount of scoring scene feature data can be collected, the collected data can be labeled according to the experience of the business party, a training set can be obtained, and the training of the corresponding template recommendation model can be performed for different business links.

[0037] In step 103, a recommended scoring template is determined from a preset scoring template library according to the output of the preset template recommendation model, wherein the recommended scoring template is used to score the candidate subject.

[0038] Optionally, a preset scoring template library can be constructed in advance, the preset scoring template library can include a plurality of scoring templates, the scoring templates can be stored according to template names, and the scoring templates can be further classified. The preset template recommendation model can output a first recommendation probability value corresponding to each scoring template in the preset scoring template library, or can output a second recommendation probability value corresponding to each scoring template category in the preset scoring template library. Optionally, the first recommendation probability values can be sorted from high to low, and the scoring templates corresponding to the top N first recommendation probability values can be selected as the recommended scoring templates; or the second recommendation probability values can be sorted from high to low, and the scoring template category corresponding to the top M first recommendation probability values can be selected as the recommended scoring template category, and the scoring templates included in the recommended scoring template category can be used as the recommended scoring templates.

[0039] The processing method based on a scoring template provided by the embodiment of the application includes the following steps: acquiring scoring scene features corresponding to a target business link in a preset type of business, wherein the scoring scene features include business element features, user operation features, and object category features of a preset object, the preset object is provided by a candidate subject to be scored, inputting the scoring scene features into a preset template recommendation model corresponding to the target business link, and determining a recommended scoring template from a preset scoring template library according to the output of the preset template recommendation model, wherein the recommended scoring template is used to score the candidate subject. By using the above technical solution, for the current business link in the preset type of business, the current scoring scene is comprehensively represented based on the business element features, the user operation features, and the object category features of the preset object, and the corresponding preset template recommendation model is used to recommend a scoring template according to the current scoring scene features, so that when the candidate subject is scored, a scoring template that is more flexible and more suitable for the specific scoring scene can be used for scoring, and the scoring result is more in line with the actual situation and more accurate.

[0040] In some embodiments, after the recommended scoring template is determined, the method further comprises: outputting the recommended scoring template; receiving a selection operation input by a user for the recommended scoring template, and determining the selected recommended scoring template as a target scoring template according to the selection operation. This arrangement has the advantage that the target scoring template used for evaluating the candidate subject is determined from the recommended scoring template according to the operation of the user, further improving the rationality of scoring template selection and improving the scoring accuracy.

[0041] For example, a plurality of recommended scoring templates and corresponding selection controls can be displayed in a front-end page, and the user selects a recommended scoring template by triggering the selection control.

[0042] In some embodiments, after the recommended scoring template is determined, the method further comprises: outputting the recommended scoring template; displaying a template filtering page in response to a rejection operation of the user for the recommended scoring template; receiving a target scoring dimension and a target object category input by the user based on the template filtering page; determining a target scoring template name according to the target business link, the target scoring dimension, and the target object category; and obtaining a corresponding target scoring template from the preset scoring template library according to the target scoring template name. This arrangement has the advantage that when the user is not satisfied with the recommended scoring template, the user can independently select a scoring template flexibly, further improving the rationality of scoring template selection and improving the scoring accuracy.

[0043] For example, after the recommended scoring template is output, the user can be asked whether to select the recommended scoring template by displaying prompt information. If the user triggers the "No" option, it is considered that a rejection operation is input, and the template filtering page is displayed. The scoring templates in the preset scoring template library can be named by business link-scoring dimension-object category. The user can input a target scoring dimension and a target object category on the template filtering page, and a target scoring template name is combined according to the target business link, the target scoring dimension, and the target object category. Then, a scoring template consistent with the target scoring template name is obtained from the preset scoring template library as the target scoring template.

[0044] For example, in a procurement scenario, the scoring dimensions can include, for example, basic information dimensions, business execution dimensions, and performance dimensions. A plurality of scoring dimensions can be displayed on the template filtering page for the user to select, and a target scoring dimension selected by the user is determined. There can be a plurality of scoring indicators under different scoring dimensions. For example, the basic information dimensions can include attribute information of a supplier, such as establishment time, number of employees, and production capacity; the business execution dimensions can include, for example, the cooperation degree of the supplier; and the performance dimensions can include, for example, contract completion, such as completion quality and whether there are default items.

[0045] In some embodiments, the method further includes: obtaining candidate subject data corresponding to the target scoring indicators in the target scoring template; and determining the score of the candidate subject based on the target scoring template, the candidate subject data, and the target weight coefficients corresponding to the target scoring indicators. The advantage of this approach is that when scoring candidate subjects using the target scoring template, determining corresponding target weight coefficients for different scoring indicators makes the scoring results more accurate.

[0046] In some embodiments, the target rating template includes multiple templates, each corresponding to a different target rating dimension. The system obtains a set of scores for the candidate subject based on different target rating templates. The scores in the set, along with the associated target rating dimensions, are input into a preset rating model. Based on the output of the preset rating model, the rating level for the candidate subject is determined. This approach allows the model to output rating levels for the candidate subject across multiple rating dimensions. These rating levels can serve as profile tags for evaluating the candidate subject, further assisting users in rationally selecting target subjects.

[0047] For example, the preset rating model is trained based on a convolutional neural network model, specifically a classification model based on a deep convolutional neural network (DCNN). The AdaDelta adaptive learning rate optimization method is used to accelerate the optimization speed of the model. In the initial training stage, the model can be made more accurate by correcting the dataset labels.

[0048] In some embodiments, the method further includes: obtaining combination information of the candidate entity and historical competitors, wherein the combination information includes the number of times the candidate entity is combined with the same historical competitors; wherein, inputting the scores in the score set and the target rating dimension associated with the scores into the preset rating model includes: inputting the scores in the score set, the target rating dimension associated with the scores, and the combination information into the preset rating model. The advantage of this setting is that it can further enrich the evaluation profile labels, which is beneficial for identifying the deduction behavior of candidate entities.

[0049] For example, in a procurement scenario, multiple candidate suppliers may be in competition. Malicious behavior, such as bid-rigging, can be identified based on combined information. For instance, using projects a candidate supplier has participated in as a basis, the combinations of suppliers participating in each project negotiation can be analyzed. For example, the number of times a candidate supplier and a competing supplier appear together in a project can be counted. If the number of times a candidate supplier appears with multiple competing suppliers in a project is greater than 1, these counts can be accumulated. For example, if candidate supplier E and competing supplier F have appeared together in 5 projects, and E and competing supplier G have appeared together in 4 projects, the count is 9. A higher number of combinations indicates a higher probability of malicious behavior, which will be a negative factor for the candidate.

[0050] In some embodiments, determining the evaluation level corresponding to the candidate entity based on the output of the preset evaluation model includes: determining multiple evaluation levels corresponding to the candidate entity based on the output of the preset evaluation model, wherein the multiple evaluation levels include a first evaluation level corresponding to each target scoring dimension and a second evaluation level corresponding to the combined information; calculating the first evaluation level and the second evaluation level based on preset calculation rules to obtain the comprehensive level corresponding to the candidate entity; and determining the recommended entity corresponding to the target business process based on the comprehensive level. The advantage of this setup is that a comprehensive level can be calculated for each candidate entity, providing users with more comprehensive reference information and helping them quickly and accurately select a suitable target entity.

[0051] Figure 2 The flowchart illustrates another processing method based on a scoring template provided in this embodiment of the invention, which is an optimization based on the above-mentioned optional embodiments, such as... Figure 2 As shown, the method may include:

[0052] Step 201: Obtain the scoring scenario features corresponding to the target business process in the preset business type.

[0053] The scoring scenario features include business element features, user operation features, and object category features of preset objects, which are provided by the candidate subjects to be scored. Business element features include whether there is an initial subject selection, whether there are historical subjects, and whether business plan data has been generated; user operation features include whether a subject selection operation has been performed, whether a business plan creation operation has been performed, and whether a re-recommendation operation has been entered.

[0054] Step 202: Input the scoring scenario features into the preset template recommendation model corresponding to the target business process. Based on the output of the preset template recommendation model, determine the recommended scoring template from the preset scoring template library and output the recommended scoring template.

[0055] The preset template recommendation model is trained based on a decision tree model.

[0056] Optionally, the preset rating template library is obtained through the following methods: For each rating dimension, a correspondence between object categories and rating indicators is established to form an indicator library; for each object category of each rating dimension under each business process, multiple candidate indicators selected by the user from the indicator library are obtained repeatedly to form multiple initial templates; the proportion of each candidate indicator in the multiple initial templates is calculated; the candidate indicators are sorted according to the proportion; and the selected indicators are determined from the candidate indicators according to the sorting results; a standard evaluation template is generated based on the selected indicators; and the preset rating template library is constructed based on the standard evaluation templates. The advantage of this setup is that it allows for the reasonable construction of a rich and accurate preset rating template library, laying the foundation for accurate recommendation of rating templates.

[0057] For example, taking a procurement scenario, scoring dimensions can include basic information, business execution, and contract fulfillment. By collecting relevant supplier data, a set of scoring indicators that can be used to evaluate suppliers is obtained. These indicators are then grouped according to object categories, so that specific scoring indicators fall into a grid with the scoring indicator as the horizontal axis and the object category as the vertical axis, forming an indicator library.

[0058] For example, a visual evaluation template generation program can be provided. Taking a procurement scenario as an example, procurement managers can input business processes through the template configuration interface on the front end to configure an initial template for the input business process. For instance, for the currently input business process, the user can further input the current scoring dimension and the current object category in the template configuration interface. Subsequently, the template configuration interface can display all or recommended scoring indicators corresponding to the current object category under the current scoring dimension in the indicator library, allowing the user to select candidate indicators to form the corresponding initial template. Multiple retrievals can include retrieving candidate indicators selected by multiple users. For example, the initial templates are categorized and stored using business process-scoring dimension-object category as unique identifiers, i.e., multiple initial template sets are stored, each initial template set corresponding to a template identifier. For initial templates of the same category, the proportion of each candidate indicator appearing can be calculated to determine the selected indicators. For example, in the initial template set corresponding to business process A - rating dimension A - object category A, there are 3 initial templates. Initial template 1 contains candidate indicators a, b, c, and d; initial template 2 contains candidate indicators a, b, e, and f; and initial template 3 contains candidate indicators a, e, f, and g. This results in a total of 7 candidate indicators. The proportion of each candidate indicator is calculated; for example, a might have a proportion of 3 / 7, b might have a proportion of 2 / 7, etc. Candidate indicators with higher proportions or proportions greater than or equal to a preset threshold are selected as included indicators. Assuming the preset threshold is 2 / 7, the included indicators could include a, b, e, and f. Therefore, the standard evaluation template corresponding to business process A - rating dimension A - object category A contains evaluation indicators a, b, e, and f.

[0059] For example, a corresponding standard evaluation template is generated for each template identifier in the manner described above, and a preset scoring template library is constructed based on all the generated standard evaluation templates.

[0060] Optionally, constructing a preset scoring template library based on the standard evaluation template includes: for each standard evaluation template, obtaining multiple weight combinations input by the user; for each of the multiple weight combinations, calculating candidate scores for the standard evaluation template using historical subject data; determining a target weight combination based on the distribution of candidate scores; and determining the target weight combination as the standard weight coefficient; and constructing a preset scoring template library based on each standard evaluation template and the corresponding standard weight coefficient. The advantage of this approach is that it allows for the reasonable setting of the standard weight coefficients corresponding to the standard evaluation templates, further improving the accuracy of scoring using the standard evaluation templates.

[0061] For example, for each standard evaluation template, users can set multiple weight combinations, each containing the weight coefficients of each scoring indicator in the current standard evaluation template. For each weight combination, historical supplier data is obtained, and the supplier's candidate score is calculated based on the standard evaluation template and the current weight combination. A suitable target weight combination is selected based on the distribution of the candidate scores; for example, the weight combination corresponding to the median of the candidate scores is determined as the target weight combination.

[0062] Step 203: Determine whether the user chooses to use the recommended rating template. If yes, proceed to step 204; otherwise, proceed to step 205.

[0063] For example, if a user makes a selection action for the recommended rating template, it is considered that the user has chosen to use the recommended rating template. If no user action is received within a preset time after the recommended rating template is output, or if the user enters a rejection action, it is considered that the user has not chosen to use the recommended rating template.

[0064] Step 204: Based on the user's selection operation for the recommended rating template, the selected recommended rating template is determined as the target rating template.

[0065] Step 205: Display the template filtering page, receive the target rating dimension and target object category input by the user based on the template filtering page, determine the target rating template name according to the target business process, target rating dimension and target object category, and obtain the corresponding target rating template from the preset rating template library according to the target rating template name.

[0066] Step 206: Obtain candidate subject data corresponding to the target scoring indicators in the target scoring template. Based on the target scoring template, candidate subject data, and target weight coefficients corresponding to the target scoring indicators, determine the score of the candidate subject.

[0067] Step 207: Obtain the score set corresponding to the candidate subject based on different target scoring templates, and obtain the combination information of the candidate subject and historical competing subjects.

[0068] Step 208: Input the scores in the score set, the target rating dimensions associated with the scores, and the combination information into the preset level evaluation model.

[0069] Step 209: Based on the output of the preset rating model, determine multiple rating levels corresponding to the candidate subjects. The multiple rating levels include the first rating level corresponding to each target scoring dimension and the second rating level corresponding to the combined information.

[0070] For example, assuming that the target scoring template currently in use includes two, corresponding to the basic information dimension and the business execution dimension respectively, the first evaluation level includes the evaluation level x corresponding to the basic information dimension and the evaluation level y corresponding to the business execution dimension, and the second evaluation level includes the evaluation level z of malicious combination behavior.

[0071] Optionally, multiple rating levels can be displayed for each candidate on the page to help users understand the evaluation status of each candidate from different dimensions.

[0072] Step 210: Based on the preset calculation rules, calculate the first evaluation level and the second evaluation level to obtain the comprehensive level corresponding to the candidate subject.

[0073] For example, since the second evaluation level corresponds to the candidate's deduction behavior, a corresponding penalty can be applied when determining the overall evaluation level. The preset calculation rule could be, for example, a weighted summation, where the weighting coefficient for the first evaluation level is positive, and the weighting coefficient for the second evaluation level is negative. For instance, the overall evaluation level could be calculated as: Overall Evaluation Level = k1*x + k2*y - k3*z, where k, k2, and k3 are all greater than 0.

[0074] Step 211: Determine the recommended entity corresponding to the target business segment based on the overall rating.

[0075] For example, if there are 10 candidate entities, they are sorted according to their comprehensive rating, and the top-ranked candidate entities are identified as the recommended entities for the current business process and provided to the user.

[0076] The scoring template-based processing method provided in this invention, based on the output of recommended scoring templates by a preset template recommendation model corresponding to the target business process and the characteristics of the current scoring scenario, allows users to independently select templates from a preset scoring template library by inputting template name components such as scoring dimensions and object categories. This allows for flexible selection of suitable scoring templates, and scoring is performed using the selected templates. When multiple target scoring templates are determined, a preset rating model is used to rate different combinations of scoring dimensions and candidate subjects, flexibly considering multiple rating factors to obtain rating results that are more in line with the current scenario, thus providing users with accurate evaluation reference information.

[0077] Figure 3 This is a schematic diagram of a processing device based on a scoring template provided in an embodiment of the present invention. The device includes:

[0078] The scoring scenario feature acquisition module 301 is used to acquire the scoring scenario features corresponding to the target business link in the preset type of business. The scoring scenario features include business element features, user operation features, and object category features of preset objects. The preset objects are provided by the candidate subjects to be scored.

[0079] Feature input module 302 is used to input the scoring scenario features into the preset template recommendation model corresponding to the target business process;

[0080] The recommendation template determination module 303 is used to determine a recommendation scoring template from a preset scoring template library based on the output of the preset template recommendation model, wherein the recommendation scoring template is used to score the candidate subject.

[0081] The processing device based on scoring templates provided in this embodiment of the invention comprehensively characterizes the current scoring scenario for the currently concerned business links in a preset type of business based on business element features, user operation features, and object category features of preset objects. It then uses a corresponding preset template recommendation model to recommend scoring templates based on the features of the current scoring scenario. This allows for the use of more flexible scoring templates that fit the specific scoring scenario when scoring candidate subjects, resulting in scoring results that are more consistent with the actual situation and more accurate.

[0082] Optionally, the device may also include:

[0083] The recommended rating template output module is used to output the recommended rating template after the recommended rating template is determined;

[0084] The target rating template determination module is used to receive the user's selection operation for the recommended rating template, and determine the selected recommended rating template as the target rating template according to the selection operation.

[0085] Optionally, the business element features include at least one of the following: whether there is a preliminary subject, the name of the preliminary subject, whether there is a historical subject, the name of the historical subject, whether business plan data has been generated, and the business plan data; the user operation features include at least one of the following: whether a subject selection operation has been performed, whether a business plan creation operation has been performed, and whether a re-recommendation operation has been entered.

[0086] Optionally, the device may also include:

[0087] The recommended rating template output module is used to output the recommended rating template after the recommended rating template is determined;

[0088] The template filtering page display module is used to display the template filtering page in response to the user's rejection operation on the recommended rating template;

[0089] The receiving module is used to receive the target rating dimension and target object category input by the user based on the template filtering page;

[0090] The template name determination module is used to determine the target scoring template name based on the target business process, the target scoring dimension, and the target object category.

[0091] The target scoring template acquisition module is used to acquire the corresponding target scoring template from the preset scoring template library according to the target scoring template name.

[0092] Optionally, the device may also include:

[0093] The candidate subject data acquisition module is used to acquire candidate subject data corresponding to the target scoring indicators in the target scoring template.

[0094] The scoring determination module is used to determine the score of the candidate subject based on the target scoring template, the candidate subject data, and the target weight coefficient corresponding to the target scoring index.

[0095] Optionally, the target scoring template includes multiple templates, with different templates corresponding to different target scoring dimensions; the device further includes:

[0096] The score set acquisition module is used to acquire the score set corresponding to the candidate subject based on different target scoring templates;

[0097] The model input module is used to input the scores in the score set, as well as the target rating dimension associated with the scores, into the preset level evaluation model;

[0098] The evaluation level determination module is used to determine the evaluation level corresponding to the candidate subject based on the output of the preset evaluation level model.

[0099] Optionally, the device may also include:

[0100] The combination information acquisition module is used to acquire the combination information of the candidate entity and the historical competitors, wherein the combination information includes the number of times the candidate entity is combined with the same historical competitors;

[0101] Specifically, the model input module is used to input the scores in the score set, the target rating dimension associated with the scores, and the combined information into the preset level evaluation model.

[0102] Optional, the rating level determination module includes:

[0103] The evaluation level determination subunit is used to determine multiple evaluation levels corresponding to the candidate subject based on the output of the preset evaluation model. The multiple evaluation levels include a first evaluation level corresponding to each target scoring dimension and a second evaluation level corresponding to the combined information.

[0104] The comprehensive rating determination subunit is used to calculate the first evaluation rating and the second evaluation rating based on preset calculation rules to obtain the comprehensive rating corresponding to the candidate subject;

[0105] The recommendation subject determination subunit is used to determine the recommendation subject corresponding to the target business link based on the comprehensive level.

[0106] Optionally, the preset recommendation template model is trained based on a decision tree model, and the preset rating model is trained based on a convolutional neural network model.

[0107] Optionally, the preset scoring template library is obtained in the following way:

[0108] For each scoring dimension, a correspondence between object categories and scoring indicators is established to form an indicator library;

[0109] For each object category of each rating dimension under each business process, multiple candidate indicators selected by the user from the indicator library are obtained multiple times to form multiple initial templates. The proportion of each candidate indicator in the multiple initial templates is calculated. The candidate indicators are sorted according to the proportion. The selected indicators are determined from the candidate indicators according to the sorting results. A standard evaluation template is generated according to the selected indicators.

[0110] A preset scoring template library is constructed based on the standard evaluation template.

[0111] Optionally, constructing a preset scoring template library based on the standard evaluation template includes:

[0112] For each standard evaluation template, multiple weight combinations input by the user are obtained. For each of the multiple weight combinations, the alternative scores of the standard evaluation template are calculated using historical subject data. The target weight combination is determined based on the distribution of the alternative scores. The standard weight coefficient is determined based on the target weight combination.

[0113] A pre-defined scoring template library is constructed based on each standard evaluation template and the standard weight coefficient corresponding to each standard evaluation template.

[0114] The scoring template-based processing device provided in this embodiment of the invention can execute the scoring template-based processing method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0115] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0116] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0117] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0118] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as scoring template-based processing methods.

[0119] In some embodiments, the scoring template-based processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the scoring template-based processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the scoring template-based processing method by any other suitable means (e.g., by means of firmware).

[0120] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0124] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0125] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0126] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the scoring template-based processing method provided in any embodiment of this application.

[0127] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The scoring template-based processing apparatus, device, storage medium, and product provided in the above embodiments can execute the scoring template-based processing method provided in any embodiment of this application, and have the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in the above embodiments can be found in the scoring template-based processing method provided in any embodiment of this application.

[0129] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A processing method based on a scoring template, characterized in that, include: The scoring scenario features corresponding to the target business process in the preset business type are obtained. These features include business element features, user operation features, and object category features of the preset objects. The preset objects are provided by the candidate entities to be scored. The business element features include at least one of the following: whether a preliminary entity exists, the name of the preliminary entity, whether a historical entity exists, the name of the historical entity, whether business plan data has been generated, and the business plan data itself. The user operation features include at least one of the following: whether an entity selection operation has been performed, whether a business plan creation operation has been performed, and whether a re-recommendation operation has been entered. The scoring scenario features are input into the preset template recommendation model corresponding to the target business process, wherein the preset template recommendation model is pre-trained based on a decision tree model for different business processes. Based on the output of the preset template recommendation model, a recommended scoring template is determined from the preset scoring template library, wherein the recommended scoring template is used to score the candidate subject; The method further includes: Obtain the candidate subject data corresponding to the target scoring index in the target scoring template; The score of the candidate subject is determined based on the target scoring template, the candidate subject data, and the target weight coefficient corresponding to the target scoring index. The method further includes: multiple target scoring templates, each corresponding to a different target scoring dimension; Obtain the score set corresponding to the candidate entity based on different target scoring templates, and the combination information of the candidate entity and historical competitors; wherein, the combination information includes the number of combinations of the candidate entity with the same historical competitors, and the combination information is used to identify the malicious behavior of the candidate entity; The scores in the score set, the target rating dimensions associated with the scores, and the combined information are input into the preset level evaluation model; Based on the output of the preset rating model, multiple rating levels corresponding to the candidate subject are determined, wherein the multiple rating levels include a first rating level corresponding to each target scoring dimension and a second rating level corresponding to the combined information; Based on preset calculation rules, the first evaluation level and the second evaluation level are calculated to obtain the comprehensive level corresponding to the candidate subject; The recommended entity corresponding to the target business segment is determined based on the overall rating.

2. The method according to claim 1, characterized in that, After determining the recommendation rating template, the following is also included: Output the recommended rating template; The system receives a selection operation input from the user for the recommended rating template and determines the selected recommended rating template as the target rating template based on the selection operation.

3. The method according to claim 1, characterized in that, After determining the recommendation rating template, the following is also included: Output the recommended rating template; In response to the user's rejection of the recommended rating template, the template filtering page is displayed; Receive the target rating dimensions and target object categories input by the user based on the template filtering page; The target scoring template name is determined based on the target business process, the target scoring dimension, and the target object category; The corresponding target scoring template is obtained from the preset scoring template library based on the target scoring template name.

4. The method according to claim 1, characterized in that, The preset rating model is trained based on a convolutional neural network model.

5. The method according to claim 1, characterized in that, The preset scoring template library is obtained through the following methods: For each scoring dimension, a correspondence between object categories and scoring indicators is established to form an indicator library; For each object category of each rating dimension under each business process, multiple candidate indicators selected by the user from the indicator library are obtained multiple times to form multiple initial templates. The proportion of each candidate indicator in the multiple initial templates is calculated. The candidate indicators are sorted according to the proportion. The selected indicators are determined from the candidate indicators according to the sorting results. A standard evaluation template is generated according to the selected indicators. A preset scoring template library is constructed based on the standard evaluation template.

6. The method according to claim 5, characterized in that, The step of constructing a preset scoring template library based on the standard evaluation template includes: For each standard evaluation template, multiple weight combinations input by the user are obtained. For each of the multiple weight combinations, the alternative scores of the standard evaluation template are calculated using historical subject data. The target weight combination is determined based on the distribution of the alternative scores. The standard weight coefficient is determined based on the target weight combination. A pre-defined scoring template library is constructed based on each standard evaluation template and the standard weight coefficient corresponding to each standard evaluation template.

7. A processing device based on a scoring template, characterized in that, include: The scoring scenario feature acquisition module is used to acquire scoring scenario features corresponding to target business links in preset business types. These features include business element features, user operation features, and object category features of preset objects. The preset objects are provided by candidate entities to be scored. The business element features include at least one of the following: whether a preliminary entity exists, the name of the preliminary entity, whether a historical entity exists, the name of the historical entity, whether business solution data has been generated, and the business solution data itself. The user operation features include at least one of the following: whether an entity selection operation has been performed, whether a business solution creation operation has been performed, and whether a re-recommendation operation has been entered. The feature input module is used to input the scoring scenario features into the preset template recommendation model corresponding to the target business process, wherein the preset template recommendation model is pre-trained based on a decision tree model for different business processes. The recommendation template determination module is used to determine a recommendation scoring template from a preset scoring template library based on the output of the preset template recommendation model, wherein the recommendation scoring template is used to score the candidate subject; The device further includes: The candidate subject data acquisition module is used to acquire the candidate subject data corresponding to the target scoring index in the target scoring template. The scoring determination module is used to determine the score of the candidate subject based on the target scoring template, the candidate subject data, and the target weight coefficient corresponding to the target scoring index. The target scoring template includes multiple templates, each corresponding to a different target scoring dimension; the device also includes: The score set and combination information acquisition module is used to acquire the score set corresponding to the candidate subject based on different target scoring templates, as well as the combination information of the candidate subject and historical competitors; wherein, the combination information includes the number of combinations of the candidate subject with the same historical competitors, and the combination information is used to identify the malicious behavior of the candidate subject; The model input module is used to input the scores in the score set, the target rating dimensions associated with the scores, and the combined information into the preset level evaluation model; The rating level determination module includes: The evaluation level determination subunit is used to determine multiple evaluation levels corresponding to the candidate subject based on the output of the preset evaluation model. The multiple evaluation levels include a first evaluation level corresponding to each target scoring dimension and a second evaluation level corresponding to the combined information. The comprehensive rating determination subunit is used to calculate the first evaluation rating and the second evaluation rating based on preset calculation rules to obtain the comprehensive rating corresponding to the candidate subject; The recommendation subject determination subunit is used to determine the recommendation subject corresponding to the target business link based on the comprehensive level.

8. An electronic device, characterized in that, The invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the method as described in any one of claims 1-6.

Images