Business modeling guiding method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a business modeling guiding method and system, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining object label information of a target object and model demand information input by the object in response to a modeling guide instruction of the object on a visual interface, and then performing model recommendation processing according to the object label information and the model demand information to obtain a recommended model list; the model recommendation processing comprises model recommendation based on similar users and model recommendation based on object demands, displaying a recommendation model list which comprises a plurality of recommendation models meeting user preferences and demands, determining a target model in response to a model selection instruction for the recommendation model list, and recommending the target model to the user. And determining a business model according to the target model and the target parameters thereof. According to the invention, personalized business modeling guidance can be provided for the user, and the business modeling efficiency of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a business modeling guidance method, system, electronic device and storage medium. Background Art

[0002] With the development of the big data industry, big data application capabilities are getting closer and closer to business lines, and the market demand for lowering modeling thresholds and improving modeling efficiency is becoming increasingly urgent. Based on this, visual modeling tools are widely used in the field of business modeling.

[0003] Although visual modeling tools eliminate the need for programming technology for business personnel, they still require basic knowledge of data mining and modeling experience, which still hinders modeling efficiency and the promotion of model applications. In related technologies, in order to lower the threshold for using visual modeling tools, "automatic modeling" and "fast modeling" functions can be set. Business personnel only need to follow the system modeling guidance to gradually enter some key information, and the system will automatically generate a "standard template" model. Users only need to configure a few simple parameters, but "standard template" models are often general models that cannot provide personalized modeling guidance based on user needs. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a business modeling guidance method, system, electronic device and storage medium, aiming to provide users with personalized business modeling guidance and improve the user's business modeling efficiency.

[0005] To achieve the above object, an embodiment of the present application provides a business modeling guidance method, comprising the following steps:

[0006] In response to a modeling guidance instruction of the object, obtaining object label information of the target object and model requirement information of the object input;

[0007] Performing model recommendation processing according to the object tag information and the model requirement information to obtain a recommended model list, wherein the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements;

[0008] Displaying the recommended model list, wherein the recommended model list includes a plurality of recommended models;

[0009] In response to a model selection instruction for the recommended model list, determining a target model;

[0010] Obtaining target parameters of the target model;

[0011] A business model is determined according to the target model and the target parameters.

[0012] In some embodiments, obtaining the target parameters of the target model comprises the following steps:

[0013] Displaying a parameter configuration interface of the target model, wherein the parameter configuration interface is used to display parameter configuration controls of multiple components of the target model;

[0014] In response to a first operation instruction on the parameter configuration control, determining a component configuration parameter;

[0015] According to the component configuration parameters of each component, the target parameters are determined.

[0016] In some embodiments, the determining the component configuration parameter in response to the first operation instruction on the parameter configuration control comprises the following steps:

[0017] In response to a first operation instruction on the parameter configuration control, determining a parameter configuration mode, wherein the parameter configuration mode is one of manual configuration or automatic configuration;

[0018] When the parameter configuration mode is manual configuration, determining component configuration parameters in response to a second operation instruction on a parameter input control in the parameter configuration control;

[0019] When the parameter configuration mode is automatic configuration, parameter optimization is performed according to a preset parameter scheme of the component to determine the component configuration parameters.

[0020] In some embodiments, performing model recommendation processing according to the object tag information and the model requirement information to obtain a recommended model list includes the following steps:

[0021] Obtaining model usage statistics information, and performing popularity-based model recommendation processing according to the model usage statistics information to obtain a first recommendation list, wherein the first recommendation list includes a plurality of recommended models and corresponding popularity values;

[0022] Performing model recommendation processing based on a user collaborative filtering algorithm according to the object tag information to obtain a second recommendation list, wherein the second recommendation list includes multiple recommendation models and corresponding recommendation coefficients;

[0023] Performing model recommendation processing based on demand matching according to the model demand information to obtain a third recommendation list, wherein the third recommendation list includes multiple recommended models and corresponding demand matching degrees;

[0024] A recommendation model list is determined according to the first recommendation list, the second recommendation list and the third recommendation list.

[0025] In some embodiments, performing model recommendation processing based on a user collaborative filtering algorithm according to the object tag information to obtain a second recommendation list includes the following steps:

[0026] Determine similar objects to the target object according to the object label information;

[0027] Determining a plurality of first candidate models according to behavior information of each of the similar objects, wherein the behavior information represents the association between the object and the model;

[0028] Selecting similar objects associated with the first candidate model from all the similar objects as analysis objects, and synthesizing the similarities between each analysis object and the target object to obtain a recommendation coefficient of the first candidate model;

[0029] A second recommendation list is determined according to the recommendation coefficients of the first candidate models.

[0030] In some embodiments, performing model recommendation processing based on demand matching according to the model demand information to obtain a third recommendation list, wherein the third recommendation list includes multiple recommendation models and corresponding matching degrees, includes the following steps:

[0031] Acquire label sets of multiple second candidate models, wherein the label set of each second candidate model includes a data source subset, an algorithm subset, and a model label subset;

[0032] Determine a first number of identical data sources according to the data source requirements in the model requirement information and the data source subset of the second candidate model, and determine a data source matching degree according to a ratio of the first number to a total number of data sources;

[0033] Determining a second number of identical algorithms according to the algorithm requirements in the model requirement information and the algorithm subset of the second candidate model, and determining an algorithm matching degree according to a ratio of the second number to the total number of algorithms;

[0034] Determine a third number of identical label semantics according to the label requirements in the model requirement information and the model label subset of the second candidate model, and determine the label matching degree according to the ratio of the third number to the total number of labels;

[0035] Performing weighted calculation on the data source matching degree, the algorithm matching degree and the label matching degree to determine the requirement matching degree of the second candidate model;

[0036] A third recommendation list is determined according to the requirement matching degrees of the plurality of second candidate models.

[0037] In some embodiments, determining a recommendation model list according to the first recommendation list, the second recommendation list and the third recommendation list comprises the following steps:

[0038] Obtaining a recommendation algorithm weight set for the target object, wherein the recommendation algorithm weight set includes weight coefficients of the first recommendation list, weight coefficients of the second recommendation list, and weight coefficients of the third recommendation list, and the recommendation algorithm weight set is updated according to the recommendation algorithm corresponding to the target model selected by the target object;

[0039] Determine all recommendation lists to which the recommendation model belongs, and determine the comprehensive recommendation degree of the recommendation model according to the values ​​of the recommendation model in all recommendation lists according to the weight coefficients corresponding to the recommendation lists to which the recommendation model belongs, wherein the recommendation model belongs to at least one of the first recommendation list, the second recommendation list and the third recommendation list, and the values ​​of the recommendation model in all recommendation lists are correspondingly at least one of the heat value, the recommendation coefficient or the demand matching degree;

[0040] The recommended model list is determined according to the comprehensive recommendation degree of each recommended model.

[0041] To achieve the above object, another aspect of the embodiment of the present application provides a business modeling guidance system, including:

[0042] The first module is used to obtain object label information of the target object and model requirement information of the object input in response to the modeling guidance instruction of the object;

[0043] The second module is used to perform model recommendation processing according to the object tag information and the model requirement information to obtain a recommended model list, wherein the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements;

[0044] A third module is used to display the recommended model list, wherein the recommended model list includes multiple recommended models;

[0045] A fourth module is used to determine a target model in response to a model selection instruction for the recommended model list;

[0046] A fifth module is used to obtain target parameters of the target model;

[0047] The sixth module is used to determine the business model according to the target model and target parameters.

[0048] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program implements the method described in the above embodiment when executed by the processor.

[0049] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method described in the above embodiment.

[0050] The business modeling guidance method, system, electronic device and storage medium proposed in the present application obtain the object label information of the target object and the model requirement information of the object input by responding to the modeling guidance instruction of the object on the visual interface, and then perform model recommendation processing based on the object label information and the model requirement information to obtain a recommended model list, the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements, and displaying the recommended model list, the recommended model list includes multiple recommended models that meet the user's preferences and requirements, and determines the target model in response to the model selection instruction of the recommended model list, and then determines the business model according to the target model and its target parameters. The present application obtains the user's model requirement information and object label information through the guidance of the front-end visual interface, and the back-end performs model recommendation based on similar users and model recommendation based on object requirements based on the information obtained by the front-end, and displays multiple recommended models that meet the user's preferences and requirements on the front-end visual interface, thereby guiding the user to perform personalized modeling and improving the user's business modeling efficiency and experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of the business modeling guidance method provided in an embodiment of the present application;

[0052] Figure 2 yes Figure 1 Flow chart of step S105 in FIG.

[0053] Figure 3 yes Figure 2 Flow chart of step S202 in FIG.

[0054] Figure 4 yes Figure 1 Flow chart of step S102 in FIG.

[0055] Figure 5 yes Figure 4 Flow chart of step S402 in FIG.

[0056] Figure 6 yes Figure 4 Flow chart of step S403 in FIG.

[0057] Figure 7 yes Figure 4 Flow chart of step S404 in FIG.

[0058] Figure 8 is a schematic diagram of a business modeling guidance system provided in an embodiment of the present application;

[0059] Fig. 9 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application;

[0060] Fig.10 It is a schematic diagram of the deployment of each recommendation algorithm server provided in the embodiment of the present application;

[0061] Fig.11 This is a schematic diagram of a modeling guide page provided in an embodiment of the present application;

[0062] Fig.12 is a schematic diagram of a parameter configuration interface of a target model provided in an embodiment of the present application;

[0063] Fig.13 It is a schematic diagram of the overall process of modeling guidance provided by an embodiment of the present application;

[0064] Fig.14 It is a schematic diagram of the system business modeling process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] It should be noted that, although the functional modules are divided in the system and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0068] The embodiments of the present application provide a business modeling guidance method, system, electronic device and storage medium, which aim to provide users with personalized business modeling guidance and improve the user's business modeling efficiency.

[0069] The business modeling guidance method, system, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the business modeling guidance method in the embodiments of the present application is described.

[0070] The business modeling guidance method provided in the embodiment of the present application relates to the field of computer technology. The business modeling guidance method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the business modeling guidance method, etc., but is not limited to the above forms.

[0071] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0072] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0073] Figure 1 is an optional flowchart of the business modeling guidance method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0074] Step S101, in response to a modeling guidance instruction of an object, obtaining object label information of a target object and model requirement information of an object input;

[0075] Step S102, performing model recommendation processing according to the object tag information and the model requirement information to obtain a recommended model list, wherein the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements;

[0076] Step S103, displaying a recommended model list, wherein the recommended model list includes a plurality of recommended models;

[0077] Step S104, determining a target model in response to a model selection instruction for the recommended model list;

[0078] Step S105, obtaining target parameters of the target model;

[0079] Step S106, determining the business model according to the target model and the target parameters.

[0080] In step S101 of some embodiments, the business modeling guidance method of this embodiment provides a visual interactive interface, which can be displayed on the client, and the client can be a mobile phone APP, a computer webpage or a small program, etc., which is not specifically limited in the embodiments of this application. After the user enters the account to log in to the system, the modeling guidance interface is entered. After the user enters the modeling requirements on the modeling guidance interface, the user can click "modeling guidance" to form a modeling guidance instruction. The system (i.e., the backend) responds to the modeling guidance instruction of the user (i.e., the object) to obtain the object label information of the target object and the model requirement information input by the object. Among them, the object label information can be obtained by querying the object label information corresponding to the account in the database according to the account when the user logs in to the system. The object label information represents the user's characteristics, such as the user's department, position, business category, etc. The model requirement information is the modeling requirements entered by the user on the modeling guidance interface. The model requirement information may include the data source type, algorithm type and model label required by the model, such as product label, marketing theme label, marketing policy label, target group label, value label, preference label, function label, etc.

[0081] In step S102 of some embodiments, after the system responds to the modeling guidance instruction, it obtains relevant data for model recommendation processing, thereby obtaining a model recommendation list. Model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements, and may further include model recommendation processing based on popularity. The model recommendation algorithm based on similar users needs to use object label information to determine users with similar characteristics to the target object, and then make recommendations based on the preference models of similar users. The model recommendation algorithm based on object requirements needs to use the model requirement information input by the current user to match the models in the database, so as to find models that meet the requirements for recommendation. The model recommendation algorithm based on popularity needs to use the system's model historical usage statistics to determine multiple models with higher usage times for recommendation.

[0082] In some embodiments, the model recommendation processing algorithm can be encapsulated into a recommendation service application. After the system obtains the relevant data, it calls the recommendation service application through the APP interface of the recommendation service application, so that the recommendation service application obtains the recommendation list it returns. Specifically, the system automatically extracts the data required by the recommendation algorithm (i.e., the recommendation service application). The data input into the recommendation algorithm includes but is not limited to model usage statistics, object label information (such as department, role, etc.), behavioral information characterizing the association between users and models stored in the database, model requirement information, and a set of model labels stored in the database. Among them, the data source, engine type, model label and other related information input by the user, together constitute the model requirement information. Please refer to Fig.10, distinguish the data required by different recommendation algorithms in recommendation service applications. The model recommendation algorithm based on popularity requires data 1 (including platform model usage statistics), the collaborative filtering recommendation algorithm based on user analysis (i.e., the model recommendation algorithm based on similar users) requires data 2 (including user tag information and user model association data), and the recommendation algorithm based on demand matching (for example, it can be a recommendation algorithm for digital marketing scenario demand matching) requires data 3 (including the model tag set of the corresponding scenario extracted by the system and the model tag requirements input by the user, etc.). Data 2 and its corresponding recommendation algorithm are deployed on the nearline server. This part of data has a large amount of data and requires a large amount of computing resources. At the same time, the real-time requirements for the recommendation results are not high, so it is deployed on the nearline server. The nearline server takes a T+1 period to push the recommendation results to the online application server. Data 1 and its corresponding recommendation algorithm, data 3 and its corresponding recommendation algorithm can be directly deployed on the online server.

[0083] In step S103 of some embodiments, after the system obtains the recommendation list output by the model recommendation algorithm, the recommendation list can be displayed on the front-end visual interactive interface to guide the user to perform business modeling. Fig.11 The modeling guidance page includes multiple recommended models in the model recommendation list. The corresponding area of ​​each recommended model can display the brief information of the model, including model thumbnail, model name, introduction, application scenario classification label, creation information and other information.

[0084] In step S104 of some embodiments, the user may click on a recommended model in the recommended model list to form a model selection instruction. The system responds to the user's model selection instruction on the recommended model list and determines the target model according to one or more recommended models selected by the user. Fig.11 , the user can perform modeling operations in the editing workspace. During the modeling process, one or more recommended models in the recommended model list can be selected to be inserted into the editing workspace, and the target model can be determined after editing operations such as model arrangement.

[0085] In step S105 of some embodiments, after determining the architecture of the target model, it is necessary to further determine the parameters of the model. All or part of the parameters of the target model may be manually input by the user or automatically generated by the system.

[0086] See also Figure 2 In some embodiments, step S105 may include but is not limited to steps S201 to S203:

[0087] Step S201, displaying a parameter configuration interface of a target model, wherein the parameter configuration interface is used to display parameter configuration controls of multiple components of the target model;

[0088] Step S202, determining component configuration parameters in response to a first operation instruction on a parameter configuration control;

[0089] Step S203, determining target parameters according to component configuration parameters of each component.

[0090] In this embodiment, the user clicks Fig.11 After confirming the target model generation by clicking the "Confirm" button in the editing workspace, enter the following Fig.12 The target model parameter configuration interface shown. The target model includes multiple components, and the user needs to configure the parameters of the corresponding components in each parameter configuration control 100 in the parameter configuration interface. The system determines the component configuration parameters in response to the first operation instruction of the parameter configuration control, and determines the target parameters according to the component configuration parameters of each component.

[0091] See also Figure 3 In some embodiments, step S202 may include but is not limited to steps S301 to S303:

[0092] Step S301, in response to a first operation instruction on a parameter configuration control, determining a parameter configuration mode, wherein the parameter configuration mode is one of manual configuration or automatic configuration;

[0093] Step S302, when the parameter configuration mode is manual configuration, determining the component configuration parameters in response to a second operation instruction on the parameter input control in the parameter configuration control;

[0094] Step S303: when the parameter configuration mode is automatic configuration, parameter optimization is performed according to the preset parameter scheme of the component to determine the component configuration parameters.

[0095] In this example, please continue with the parameters Fig.12 , the parameter configuration control of each component is provided with a manual configuration control and an automatic configuration control. When the user selects the parameter input control and inputs the parameter in the parameter input control, the system determines that the parameter configuration mode is manual configuration in response to the first operation instruction of the parameter configuration control, and determines that the input parameter is a component configuration parameter in response to the second operation instruction of the parameter input control in the parameter configuration control. When the user selects the parameter input control and inputs the parameter in the parameter input control, the system determines that the parameter configuration mode is automatic configuration in response to the first operation instruction of the parameter configuration control, and runs one by one according to the parameter scheme set for each component, and automatically selects the optimal parameter scheme as the component configuration parameter according to the algorithm evaluation index.

[0096] In step S106 of some embodiments, the system determines the business model according to the target model and the target parameters. The system can display relevant information of the business model on the visual interactive interface, and the user can further edit the business model according to actual needs and save the business model to the database, which can be recommended to the user as a preset model when the user models next time.

[0097] According to some embodiments of the present application, referring to Fig.13 , taking digital marketing scenario modeling as an example, the overall process of modeling guidance in the embodiment of the present application is explained. Before the user builds the model, it is necessary to input information related to the model application requirement scenario, and build a recommendation algorithm based on the data characteristics of the digital marketing business scenario. The system automatically calls this business scenario recommendation algorithm, and uses the recommendation algorithm to find the N models that best meet the user's needs among the existing models in the system, and recommends them to the user together with the preset models (automatically shielding sensitive information). The user can insert the call with one click. At the same time, in the visual modeling process, as the data mining steps proceed, the user can manually configure some parameters, or choose the system to automatically adjust the parameters for modeling. The new model parameters will become the new data added to the recommendation algorithm. The next time the system can provide the model that the user may use again based on the training results of the recommendation algorithm, thereby improving the recommendation hit rate.

[0098] See also Figure 4 In some embodiments, step S102 may include but is not limited to steps S401 to S404:

[0099] Step S401, obtaining model usage statistics information, and performing model recommendation processing based on popularity according to the model usage statistics information to obtain a first recommendation list, wherein the first recommendation list includes multiple recommended models and corresponding popularity values;

[0100] Step S402, performing model recommendation processing based on a user collaborative filtering algorithm according to the object tag information to obtain a second recommendation list, wherein the second recommendation list includes multiple recommendation models and corresponding recommendation coefficients;

[0101] Step S403, performing model recommendation processing based on demand matching according to the model demand information to obtain a third recommendation list, wherein the third recommendation list includes multiple recommended models and corresponding demand matching degrees;

[0102] Step S404: determine a recommendation model list according to the first recommendation list, the second recommendation list and the third recommendation list.

[0103] In step S401 of some embodiments, the model recommendation process based on current popularity is as follows:

[0104] Take the top N popular models and set them as MR{mr1,mr2...mr N}. Among them, mr i It is the i-th popular model. Let x represent the number of users who have copied and called the model in the past year. Select the largest N x and sort them in descending order X{x1,x2...x N}, and its corresponding model is MR{mr1,mr2...mr N}.

[0105] Then calculate the heat H{h1,h2...h N},in

[0106] For example, the platform model usage statistics extracted by the system, such as the user execution log data of the model, are used for the model recommendation algorithm based on the current popularity. The model usage statistics are shown in Table 1:

[0107] Table 1 Model usage statistics

[0108] Model ID Statistics* M00001 5 M00002 3 M00003 21 ...... .......

[0109] The statistical number refers to the number of people using the model, excluding repeated calls.

[0110] Sort the data in Table 1 in descending order according to the statistical numbers, select the top 5 models, and obtain the usage statistics of the candidate models, as shown in Table 2.

[0111] Table 2 Usage statistics of candidate models

[0112]

[0113]

[0114] Calculate the heat value set H{h1,h2...h N},in The first recommendation list shown in Table 3 is obtained:

[0115] Table 3 First Recommendation List

[0116] Model ID heat M00231 1.00 M00092 0.84 M00303 0.21 M00074 0.19 M00111 0.18

[0117] See also Figure 5 In some embodiments, step S402 may also include but is not limited to steps S501 to S502:

[0118] Step S501, determining similar objects of the target object according to the object tag information;

[0119] Step S502, determining a plurality of first candidate models according to the behavior information of each similar object, wherein the behavior information represents the association between the object and the model;

[0120] Step S503, selecting similar objects associated with the first candidate model from all similar objects as analysis objects, and synthesizing the similarities between each analysis object and the target object to obtain a recommendation coefficient for the first candidate model;

[0121] Step S504: determine a second recommendation list according to the recommendation coefficients of the first candidate models.

[0122] In this embodiment, the collaborative filtering recommendation algorithm based on user analysis is as follows:

[0123] Take the first N collaborative filtering recommendation models and set them as MXT{mxt1,mxt2...mxt N}. Among them, mxt i It indicates the i-th recommended model. Specifically:

[0124] ① Calculate similar users, obtain the user similarity table, and set the user similarity:

[0125]

[0126] Where L i Indicates user User i The label collection of L j Indicates user User j Collection of labels. Then the user similarity table is formed. is the user model table, and the user's use of the model (i.e., behavior information) is:

[0127]

[0128] ②Use the currently logged in user User o Filter similar users (greater than the threshold ɑ) from the user similarity table and get Where User i o Indicates the current logged in user User o Similar users, which is a subset of all users, Indicates similar users User i o A collection of tags. Then use User i o Related User Model Table Find the model usage data of these similar users Calculate the associated first candidate model recommendation coefficient:

[0129]

[0130] where fj () represents the jth model Model j The recommendation coefficient, m represents the current logged-in user User o Similar users of Take f j The model corresponding to the largest N values ​​in () is the recommended MXT {mxt1,mxt2...mxt N},F{f1,f2...f N} is the recommended coefficient, f i represents the f of the i-th model j ()use Normalized recommendation coefficient.

[0131] Exemplarily, the system obtains object label information, including department, position, business category, etc.; obtains user-model association data (i.e., behavior information), including user execution logs of models and user favorited model data, for collaborative filtering recommendations based on user analysis. The user execution logs of models obtained by the system are cleaned to obtain various cleaned data, as follows.

[0132] Table 4 User tag information

[0133] User ID User Tags U00001 (1,2,7) U00002 (3,2,4) U00003 (1,2,12) U00004 (1,2,7) U00005 (2,7,8)

[0134] Among them, (1,2,7) is the encoding process of user labels.

[0135] Table 5 User and model association data

[0136] User ID Model ID used or collected U00001 M00001 U00001 M00002 U00002 M00005 U00002 M00021 ...... ......

[0137] The collaborative filtering recommendations based on user analysis are as follows:

[0138] ① The current target user is U00001. Combined with the data in Table 4, according to the user similarity formula The similarity results of users are obtained, as shown in Table 6:

[0139] Table 6 Similarity results of target users

[0140]

[0141]

[0142] Assuming the threshold is 0.5, we can see that U00003, U00004, and U00005 are similar users to U00001.

[0143] Then query the association model of U00003, U00004, and U00005 in Table 5, and obtain the similar user behavior information shown in Table 7:

[0144] Table 7 Similar user behavior information

[0145] User ID Model ID used or collected U00003 M00012 U00003 M00212 U00003 M00111 U00003 M00074 U00004 M00074 U00004 M00098 U00004 M00004 U00004 M00061 U00005 M00111 U00005 M00074 U00005 M00003

[0146] ②According to the formula as well as The calculation results are as follows:

[0147] Table 8 Recommendation coefficient analysis table of the first candidate model

[0148] Model ID U00003 (similarity 0.5) U00004 (similarity 1.0) U00005 (similarity 0.5) <![CDATA[f j () value]]> M00012 1 0 0 0.5 M00212 1 0 0 0.5 M00111 1 0 1 1.0 M00074 1 1 1 2.0 M00003 0 0 1 0.5 M00098 0 1 0 1.0 M00004 0 1 0 1.0 M00061 0 1 0 1.0

[0149] Take f from Table 8 j () values ​​of the 5 models with the largest values, and use Normalized, the second recommendation list is obtained, as shown in Table 9:

[0150] Table 9 Second Recommendation List

[0151] Model ID Recommendation factor M00074 1.00 M00111 0.50 M00098 0.50 M00004 0.50 M00061 0.50

[0152] See also Figure 6 In some embodiments, step S403 includes but is not limited to steps S601 to S606:

[0153] Step S601, obtaining label sets of multiple second candidate models, each label set of the second candidate model including a data source subset, an algorithm subset and a model label subset;

[0154] Step S602, determining a first number of identical data sources according to the data source requirements in the model requirement information and the data source subset of the second candidate model, and determining a data source matching degree according to a ratio of the first number to the total number of data sources;

[0155] Step S603, determining a second number of identical algorithms according to the algorithm requirements in the model requirement information and the algorithm subset of the second candidate model, and determining the algorithm matching degree according to the ratio of the second number to the total number of algorithms;

[0156] Step S604, determining a third number of identical label semantics according to the label requirements in the model requirement information and the model label subset of the second candidate model, and determining a label matching degree according to a ratio of the third number to the total number of labels;

[0157] Step S605, performing weighted calculation on the data source matching degree, algorithm matching degree and label matching degree to determine the requirement matching degree of the second candidate model;

[0158] Step S606: determining a third recommendation list according to the requirement matching degrees of the plurality of second candidate models.

[0159] In this embodiment, taking the digital marketing scenario as an example, the model recommendation process based on demand matching is as follows:

[0160] Take the first N models that best match the requirements and set them as MXQ{mxq1,mxq2...mxq N}, where mxq i represents the i-th model. Let S i ,A i ,L i Respectively represent the i-th model Model i The data source subset, algorithm subset, and digital marketing scenario model label subset are set as S o ,A o ,L o Respectively represent the model requirement information Model input by the user o Data source requirements, algorithm requirements, and digital marketing scenario model label requirements. i With Model o The demand matching calculation formula is as follows:

[0161] F i (Model o ,Model i )=μ1f1(S o ,S i )+μ2f2(A o ,A i )+μ3f3(L o ,L i );

[0162] Among them, μ1, μ2, μ3 represent coefficients, and their sum is 1. f1(S o ,S i ) represents model requirement information Model o With the i-th model Model i The matching degree of data sources between them is the ratio of the number of identical data sources to the total number of data sources of the two, that is:

[0163]

[0164] Similarly, f2(A o ,A i ) represents Model o With Model i The matching degree between algorithms, f3(L o ,L i ) represents the digital marketing scenario label matching degree, which is calculated using the same method as the data source matching degree, and will not be repeated here. It can be understood that the same label means the same semantics, for example, "marketing" and "sales" are considered to be the same label.

[0165] By adding F i (Model o ,Model i ) Sort from large to small, and take the model corresponding to the first N values ​​as MXQ{mxq1,mxq2...mxq N}, and get the top N demand matching degrees C{c1,c2...c N}, where c i use The normalized F i (Model o ,Model i )value.

[0166] Exemplarily, the system obtains a model tag set, including model data source, algorithm, product tag, marketing theme tag, marketing policy tag, target group tag, value enhancement tag, preference tag, function tag, etc., and obtains the model requirement information input by the user. The system parses the model requirement information and the model tag set of each model in the database for recommendation based on requirement matching. After data cleaning, the data is as follows:

[0167] Table 10 Model requirement information

[0168] Model requirement information Contents of each requirement / [(T1, T2), (A1), (L1, L2, L3)]

[0169] Table 11 Label set system model of the second candidate model

[0170] Model ID Contents of each sub-collection M00074 [(T1),(A1,A2),(L1,L2,L3)] M00002 [(T4),(A4),(L4,L5,L6)] M00003 [(T5,T12),(A3),(L2,L5)] ...... .......

[0171] The model recommended based on digital marketing scenario demand matching is as follows:

[0172] According to formula F i (Model o ,Model i )=μ1f1(S o ,S i )+μ2f2(A o ,A i )+μ3f3(L o ,L i )and Calculate the matching degree between the model requirement information and the requirement of the second candidate model. For example, if the model requirement information is [(T1, T2), (A1), (L1, L2, L3)] and the label set of the system model M00074 is [(T1), (A1, A2), (L1, L2, L3)], then:

[0173]

[0174] Similarly, we can get f2(A o ,A i ) is 0.5, f3(L o ,L i ) is 1, μ1, μ2, μ3 are 0.5, 0.2, 0.3 respectively, according to F i (Model o ,Model i ) formula, the matching degree between the model demand information and the M00074 model is 0.65. Similarly, the matching degree between the model demand information and the demand of other models is calculated, and the calculation result of the demand matching degree of the second candidate model is obtained as shown in Table 12.

[0175] Table 12 Demand matching calculation results of the second candidate model

[0176] Model ID Demand matching M00074 0.650 M00098 0.581 M00092 0.560 M00100 0.550 M00099 0.549 ...... ......

[0177] Take the five models with the largest demand matching degree in Table 12 and use After normalization, the third recommendation list shown in Table 13 is obtained:

[0178] Table 13 The third recommended list

[0179] Model ID Match M00074 1.00 M00098 0.89 M00092 0.86 M00100 0.85 M00099 0.84

[0180] See also Figure 7 In some embodiments, step S404 may include but is not limited to steps S701 to S703:

[0181] Step S701, obtaining a recommendation algorithm weight set for the target object, wherein the recommendation algorithm weight set includes weight coefficients of a first recommendation list, a second recommendation list, and a third recommendation list, and the recommendation algorithm weight set is updated according to the recommendation algorithm corresponding to the target model selected by the target object;

[0182] Step S702, determining all recommendation lists to which the recommendation model belongs, and determining the comprehensive recommendation degree of the recommendation model according to the weight coefficient corresponding to the recommendation list to which the recommendation model belongs, for the value of the recommendation model in all recommendation lists, wherein the recommendation model belongs to at least one of the first recommendation list, the second recommendation list and the third recommendation list, and the value of the recommendation model in all recommendation lists is correspondingly at least one of the heat value, the recommendation coefficient or the demand matching degree;

[0183] Step S703: determining a recommendation model list according to the comprehensive recommendation degree of each recommendation model.

[0184] In this embodiment, a recommendation algorithm weight set of the target object is obtained, which includes λ1, λ2, and λ3, which are weight coefficients of the first recommendation list obtained based on the heat recommendation algorithm, the second recommendation list obtained based on the collaborative filtering recommendation algorithm based on user analysis, and the third recommendation list obtained based on the demand matching recommendation algorithm. All recommendation models appearing in the three recommendation lists are counted, and the recommendation list M to which the recommendation model belongs is selected. i The weight is calculated by the following formula:

[0185]

[0186] Among them, MR, MXT, and MXQ represent the first recommendation list, the second recommendation list, and the third recommendation list, respectively. i Indicates the heat value, f i represents the recommendation coefficient, c i Indicates the degree of demand matching.

[0187] According to the final f i () values ​​(i.e., comprehensive recommendation degrees) are sorted from large to small, and the corresponding model is the final recommendation list M (m1, m2...m M ).

[0188] Exemplarily, the comprehensive recommendation degrees of the recommendation models in the first recommendation list of Table 3, the second recommendation list of Table 9, and the third recommendation list of Table 13 are calculated through the above process to obtain the recommendation list shown in Table 14:

[0189] Table 14 Recommended list

[0190] Model ID Comprehensive recommendation M00074 2.19 M00092 1.70 M00098 1.39 M00231 1.00 M00100 0.85 M00099 0.84 M00111 0.68 M00004 0.50 M00061 0.50 M00303 0.21

[0191] In the visual interactive interface, the comprehensive recommendation degree of each recommendation model in the recommendation list can be displayed for reference, and the recommendation algorithm used by each recommendation model can be further displayed.

[0192] According to some embodiments of the present application, the recommendation algorithm weight set can be updated in combination with user preferences. Specifically, the default initial value of the weight coefficient in the recommendation algorithm weight set [λ1, λ2, λ3] is [1, 1, 1]. Each time the user selects a model from the recommendation list, the coefficient of the recommendation algorithm list to which the selected model belongs is increased by 1 (or other values). When the selected model belongs to the recommendation lists corresponding to multiple algorithms at the same time, 1 is added to the coefficients of these algorithms. This makes the final recommendation list obtained by comprehensively calculating the first recommendation list, the second recommendation list, and the third recommendation list based on the recommendation algorithm weight set more in line with user preferences.

[0193] According to some embodiments of this application, please refer to Fig.14, taking the digital marketing scenario as an example, the business modeling process of the embodiment of the present application is described in detail.

[0194] Step S1, obtaining model requirement information input by the user;

[0195] Step S2, the system extracts data from the database, including the target user's object tag information, the model's tag set, the model's usage statistics, and the user's behavior information associated with the model;

[0196] Step S3, integrating the user input and system extracted data into the algorithm input data;

[0197] Step S4, inputting the input data into the algorithm for processing to obtain a corresponding recommendation algorithm list, the recommendation algorithm includes a popularity-based recommendation algorithm, a user collaborative filtering-based recommendation algorithm, and a digital marketing scenario demand matching-based recommendation algorithm;

[0198] Step S5, weighted mixing of each recommendation algorithm list to obtain a recommendation list;

[0199] Step S6, displaying the recommendation list;

[0200] Step S7, the user selects a recommended model in the recommendation list and generates a target model, and adjusts the preference coefficient of step S5, i.e., the weight of the corresponding recommendation algorithm list, according to the selected model;

[0201] Step S8, the system automatically models the target model to obtain a business model;

[0202] Step S9, save the business model and feed back the model information to the system database in step S2.

[0203] See also Figure 8 The present application also provides a business modeling guidance system, including:

[0204] The first module is used to obtain object label information of the target object and model requirement information of the object input in response to the modeling guidance instruction of the object;

[0205] The second module is used to perform model recommendation processing based on object label information and model requirement information to obtain a recommended model list, wherein the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements;

[0206] The third module is used to display a recommended model list, wherein the recommended model list includes multiple recommended models;

[0207] A fourth module is used to determine a target model in response to a model selection instruction for the recommended model list;

[0208] The fifth module is used to obtain target parameters of the target model;

[0209] The sixth module is used to determine the business model according to the target model and target parameters.

[0210] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0211] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned business modeling guidance method. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0212] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0213] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0214] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the business modeling guidance method of the embodiment of this application;

[0215] Input / output interface 903, used to implement information input and output;

[0216] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0217] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0218] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0219] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned business modeling guidance method.

[0220] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0221] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0222] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0223] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0224] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0225] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0226] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0227] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0228] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0229] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0230] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0231] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A business modeling guidance method, characterized in that: The following steps are involved: In response to the modeling guidance instruction of the object, obtaining object label information of the target object and model requirement information of the object input; Performing model recommendation processing according to the object tag information and the model requirement information to obtain a recommended model list, wherein the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements; Displaying the recommended model list, wherein the recommended model list includes a plurality of recommended models; In response to a model selection instruction for the recommended model list, determining a target model; Obtaining target parameters of the target model; A business model is determined according to the target model and the target parameters.

2. The business modeling guidance method according to claim 1, characterized in that: The step of obtaining the target parameters of the target model comprises the following steps: Displaying a parameter configuration interface of the target model, wherein the parameter configuration interface is used to display parameter configuration controls of multiple components of the target model; In response to a first operation instruction on the parameter configuration control, determining a component configuration parameter; According to the component configuration parameters of each component, the target parameters are determined.

3. The business modeling guidance method according to claim 2, characterized in that: The step of determining the component configuration parameters in response to the first operation instruction on the parameter configuration control comprises the following steps: In response to a first operation instruction on the parameter configuration control, determining a parameter configuration mode, wherein the parameter configuration mode is one of manual configuration or automatic configuration; When the parameter configuration mode is manual configuration, determining component configuration parameters in response to a second operation instruction on a parameter input control in the parameter configuration control; When the parameter configuration mode is automatic configuration, parameter optimization is performed according to a preset parameter scheme of the component to determine the component configuration parameters.

4. The business modeling guidance method according to claim 1, characterized in that: The step of performing model recommendation processing according to the object tag information and the model requirement information to obtain a recommended model list includes the following steps: Obtaining model usage statistics information, and performing popularity-based model recommendation processing according to the model usage statistics information to obtain a first recommendation list, wherein the first recommendation list includes a plurality of recommended models and corresponding popularity values; Performing model recommendation processing based on a user collaborative filtering algorithm according to the object tag information to obtain a second recommendation list, wherein the second recommendation list includes multiple recommendation models and corresponding recommendation coefficients; Performing model recommendation processing based on demand matching according to the model demand information to obtain a third recommendation list, wherein the third recommendation list includes multiple recommended models and corresponding demand matching degrees; A recommendation model list is determined according to the first recommendation list, the second recommendation list and the third recommendation list.

5. The business modeling guidance method according to claim 4, characterized in that: The performing model recommendation processing based on the user collaborative filtering algorithm according to the object tag information to obtain a second recommendation list includes the following steps: Determine similar objects to the target object according to the object label information; Determining a plurality of first candidate models according to behavior information of each of the similar objects, wherein the behavior information represents the association between the object and the model; Selecting similar objects associated with the first candidate model from all the similar objects as analysis objects, and synthesizing the similarities between each analysis object and the target object to obtain a recommendation coefficient of the first candidate model; A second recommendation list is determined according to the recommendation coefficients of the first candidate models.

6. The business modeling guidance method according to claim 4, characterized in that: The step of performing model recommendation processing based on demand matching according to the model demand information to obtain a third recommendation list, wherein the third recommendation list includes a plurality of recommended models and corresponding matching degrees, comprises the following steps: Acquire label sets of multiple second candidate models, wherein the label set of each second candidate model includes a data source subset, an algorithm subset, and a model label subset; Determine a first number of identical data sources according to the data source requirements in the model requirement information and the data source subset of the second candidate model, and determine a data source matching degree according to a ratio of the first number to a total number of data sources; Determining a second number of identical algorithms according to the algorithm requirements in the model requirement information and the algorithm subset of the second candidate model, and determining an algorithm matching degree according to a ratio of the second number to the total number of algorithms; Determine a third number of identical label semantics according to the label requirements in the model requirement information and the model label subset of the second candidate model, and determine the label matching degree according to the ratio of the third number to the total number of labels; Performing weighted calculation on the data source matching degree, the algorithm matching degree and the label matching degree to determine the requirement matching degree of the second candidate model; A third recommendation list is determined according to the requirement matching degrees of the plurality of second candidate models.

7. The business modeling guidance method according to claim 4, characterized in that: The step of determining a recommendation model list according to the first recommendation list, the second recommendation list, and the third recommendation list comprises the following steps: Obtaining a recommendation algorithm weight set for the target object, wherein the recommendation algorithm weight set includes weight coefficients of the first recommendation list, weight coefficients of the second recommendation list, and weight coefficients of the third recommendation list, and the recommendation algorithm weight set is updated according to the recommendation algorithm corresponding to the target model selected by the target object; Determine all recommendation lists to which the recommendation model belongs, and determine the comprehensive recommendation degree of the recommendation model according to the values ​​of the recommendation model in all recommendation lists according to the weight coefficients corresponding to the recommendation lists to which the recommendation model belongs, wherein the recommendation model belongs to at least one of the first recommendation list, the second recommendation list and the third recommendation list, and the values ​​of the recommendation model in all recommendation lists are correspondingly at least one of the heat value, the recommendation coefficient or the demand matching degree; The recommended model list is determined according to the comprehensive recommendation degree of each recommended model.

8. A business modeling guidance system, characterized in that: include: The first module is used to obtain object label information of the target object and model requirement information of the object input in response to the modeling guidance instruction of the object; The second module is used to perform model recommendation processing according to the object label information and the model requirement information to obtain a recommended model list, wherein the model recommendation processing includes model recommendation based on similar users and model recommendation based on object requirements; A third module is used to display the recommended model list, wherein the recommended model list includes multiple recommended models; A fourth module is used to determine a target model in response to a model selection instruction for the recommended model list; A fifth module is used to obtain target parameters of the target model; The sixth module is used to determine the business model according to the target model and target parameters.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of claims 1 to 7.

Images