Data analysis method, device, medium and electronic equipment for virtual resource products

Abstract

The present application discloses a method, device, medium and electronic device for data analysis of virtual resource products, the method comprising: when a data analysis instruction for a specified object is detected, determining the current user category of the current user corresponding to the data analysis instruction; the specified object includes a virtual resource product; scoring the specified object respectively through multiple evaluation models to obtain multiple scores of the specified object; wherein, one evaluation model scores the specified object from one evaluation dimension; multiple scores are integrated according to the current user category to obtain a comprehensive score of the specified object; and data analysis results of the specified object are generated according to the comprehensive score and the multiple scores. The present application enables the data analysis results to be adjusted according to different user categories, which not only meets the different data analysis needs of users of different categories, but also multiple scores and comprehensive scores can perform data analysis from different scoring dimensions and levels, making the data analysis more comprehensive.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and specifically relates to a data analysis method, device, medium and electronic equipment for virtual resource products. Background Art

[0002] Data analysis is a crucial task for extracting information from data. For example, comparing data can reveal changes in the data. Generally, analyzing data from different perspectives can reveal changes in that aspect of the data. These different perspectives reflect the data analysis needs of different users. However, existing data analysis methods generally analyze data from a single perspective and fail to account for the data analysis needs of different users. This results in relatively single data analysis results, making it difficult for users with different needs to quickly extract the information they need from the analyzed data, which, to a certain extent, reduces the efficiency of data analysis.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, medium and electronic device for data analysis of virtual resource products to solve the problem in related technologies that it is difficult to perform data analysis based on different users.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to one aspect of an embodiment of the present application, a method for analyzing data of a virtual resource product is provided, comprising:

[0007] When a data analysis instruction for a specified object is detected, determining a current user category of a current user corresponding to the data analysis instruction; wherein the specified object includes a virtual resource product;

[0008] Scoring the designated object using multiple evaluation models to obtain multiple scores for the designated object; wherein one evaluation model scores the designated object based on one evaluation dimension;

[0009] fusing the multiple scores according to the current user category to obtain a comprehensive score for the designated object;

[0010] A data analysis result of the designated object is generated according to the comprehensive score and the multiple scores.

[0011] According to one aspect of an embodiment of the present application, there is provided a device for analyzing data of a virtual resource product, comprising:

[0012] A user category determination module is configured to, when a data analysis instruction for a specified object is detected, determine a current user category of a current user corresponding to the data analysis instruction; wherein the specified object includes a virtual resource product;

[0013] A scoring module is used to score the specified object using multiple evaluation models to obtain multiple scores for the specified object; wherein one evaluation model scores the specified object based on one evaluation dimension;

[0014] a rating fusion module, configured to fuse the multiple ratings according to the current user category to obtain a comprehensive rating of the designated object;

[0015] An analysis result generating module is used to generate a data analysis result of the specified object according to the comprehensive score and the multiple scores.

[0016] In one embodiment of the present application, the user category determination module includes:

[0017] a category label determination unit, configured to determine whether the current user corresponding to the data analysis instruction has a historical user category label;

[0018] a first user category determination unit, configured to, if the current user has a historical user category tag, use the user category indicated by the historical user category tag as the current user category;

[0019] The second user category determination unit is configured to determine the current user category according to the current user's response information to the user classification questionnaire if the current user does not have a historical user category label.

[0020] In one embodiment of the present application, the second user category determination unit is specifically configured to:

[0021] When detecting that the current user has completed an instruction for the user classification questionnaire, determining whether response information of the current user to a specified number of preset questions in the user classification questionnaire has been obtained;

[0022] If the number of preset questions corresponding to the obtained answer information is less than the specified number, the current user is prompted that there are unanswered questions, and the preset questions that the current user has not answered in the user classification questionnaire are redisplayed until the current user's answer information for the specified number of preset questions in the user classification questionnaire is obtained;

[0023] The current user category is determined based on the answer information of the specified number of preset questions.

[0024] In one embodiment of the present application, the scoring fusion module is specifically used to:

[0025] Build multiple scoring fusion models based on the multivariate linear regression algorithm, and set the initial model parameters for each scoring fusion model according to the preset user categories;

[0026] Use training data to train each scoring fusion model after setting the initial model parameters;

[0027] A rating fusion model corresponding to the current user category is determined, and the multiple ratings are fused using the rating fusion model corresponding to the current user category to obtain a comprehensive rating of the designated object.

[0028] In one embodiment of the present application, the apparatus further comprises:

[0029] a compliance detection module, configured to, when detecting a data analysis request for the specified object, determine whether a current user corresponding to the data analysis request is a compliant user;

[0030] A user changing module, configured to instruct the current user to change to a compliant user according to feedback information of the current user regarding the protocol guidance information if the current user is not a compliant user;

[0031] A permission determination module, configured to determine the data analysis permission of the current user if the current user is a compliant user;

[0032] The instruction generation module is configured to generate a data analysis instruction when the data analysis permission indicates that the current user has permission to issue a data analysis request for the designated object.

[0033] In one embodiment of the present application, the data analysis result includes at least one of a text analysis result and a chart analysis result; and the analysis result generation module includes:

[0034] a text analysis result generating unit, configured to obtain industry information of the designated object and generate a text analysis result of the designated object based on the comprehensive score and the industry information;

[0035] A chart analysis result generating unit is configured to generate a chart analysis result of the specified object based on the multiple scores and the evaluation dimensions corresponding to each score.

[0036] In one embodiment of the present application, the apparatus further comprises:

[0037] A similar object analysis module is used to obtain multiple similar objects of the specified object, and score each similar object according to multiple evaluation models corresponding to the current user category to obtain multiple scores for each similar object; and generate data comparison analysis results between the multiple similar objects and the specified object based on the multiple scores of the similar objects and the multiple scores of the specified object.

[0038] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the data analysis method in the above technical solution is implemented.

[0039] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor executes the executable instructions so that the electronic device executes the data analysis method for virtual resource products as in the above technical solution.

[0040] According to one aspect of an embodiment of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the data analysis method for a virtual resource product as described in the above technical solution.

[0041] In the technical solution provided in the embodiments of the present application, users are classified and designated objects are scored respectively through multiple evaluation models to obtain multiple scores for the designated objects; wherein, one evaluation model scores the designated object from one evaluation dimension; then, the multiple scores are fused according to the current user category to obtain a comprehensive score for the designated object, and finally, data analysis results are generated based on the comprehensive score and the multiple scores; the data analysis results can be adjusted according to different user categories, which not only meets the different data analysis needs of users of different categories, but also multiple scores and comprehensive scores can be used for data analysis from different scoring dimensions and levels, making the data analysis more comprehensive and improving the comprehensiveness and accuracy of product evaluation analysis.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0044] Figure 1 The following schematically shows an exemplary system architecture block diagram applying the technical solution of the present application.

[0045] Figure 2 The flowchart of the data analysis method for virtual resource products provided by one embodiment of the present application is schematically shown.

[0046] Figure 3 The flowchart of the data analysis method for virtual resource products provided by one embodiment of the present application is schematically shown.

[0047] Figure 4 The structural block diagram of the data analysis device for virtual resource products provided in an embodiment of the present application is schematically shown.

[0048] Figure 5 The following schematically shows a block diagram of a computer system structure of an electronic device suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION

[0049] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0050] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0051] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0052] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0053] It is understandable that in the specific implementation of this application, related data such as user information is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0054] Figure 1 The following schematically shows an exemplary system architecture block diagram applying the technical solution of the present application.

[0055] like Figure 1 As shown, system architecture 100 may include terminal device 110, network 120, and server 130. Terminal device 110 may include a smartphone, tablet computer, laptop computer, intelligent voice interaction device, smart home appliance, in-vehicle terminal, etc. Server 130 may be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal device 110 and server 130, such as a wired communication link or a wireless communication link.

[0056] Depending on implementation needs, the system architecture in the embodiments of the present application can have any number of terminal devices, networks, and servers. For example, server 130 can be a server group consisting of multiple server devices. In addition, the technical solutions provided in the embodiments of the present application can be applied to terminal device 110, server 130, or can be implemented by both terminal device 110 and server 130, and this application does not impose any special restrictions on this.

[0057] For example, an embodiment of the present application is implemented by the server 130. When the server 130 detects a data analysis instruction for a specified object, it determines the current user category of the current user corresponding to the data analysis instruction, wherein the data analysis instruction can be triggered by the user on the terminal device 110 and then sent to the server 130 by the terminal device 110. Next, the server 130 scores the specified object respectively through multiple evaluation models to obtain multiple scores of the specified object; wherein, an evaluation model scores the specified object from one evaluation dimension. The server 130 then fuses the multiple scores according to the current user category to obtain a comprehensive score of the specified object. Finally, the server 130 generates a data analysis result for the specified object based on the comprehensive score and the multiple scores. After obtaining the data analysis result, the server 130 can feed the data analysis result back to the terminal device 110, and then the terminal device 110 can display the data analysis result to the user through a user graphical interface.

[0058] The data analysis method for virtual resource products provided by this application is described in detail below in conjunction with specific implementation methods.

[0059] Figure 2 The flowchart of the data analysis method for virtual resource products provided by an embodiment of the present application is schematically shown. The method can be implemented by a server, such as Figure 1 The method can also be implemented by a terminal device, such as Figure 1 The terminal device 110 shown in FIG. Figure 2 As shown, the data analysis method for virtual resource products provided in the embodiment of the present application includes steps 210 to 240, which are specifically as follows:

[0060] Step 210: When a data analysis instruction for a designated object is detected, a current user category of a current user corresponding to the data analysis instruction is determined, wherein the designated object includes a virtual resource product.

[0061] Specifically, a data analysis instruction is generated when a user needs to analyze the data of a specified object to obtain corresponding data analysis results. The specified object can be an individual, a company, an organization, etc. For example, a data analysis instruction can be generated to analyze a class's test scores or a company's sales revenue. When a data analysis instruction is detected, the user who issued the instruction is recorded as the current user.

[0062] In addition, the designated objects may also include virtual resource products, such as stocks, funds, options, digital currencies, etc. This solution can be used to analyze and process the above virtual resource products to draw relevant investment conclusions as data analysis results.

[0063] In the embodiment of the present application, different user types indicate different focuses of the data analysis for a specific object. For example, when analyzing company turnover data, a salesperson for product A might focus on the turnover of product A, while a salesperson for product B might focus on the turnover of product B. Therefore, when a data analysis instruction is detected, the focus of the data analysis process can be determined by determining the current user type, thereby making the final data analysis results more consistent with the needs of the user who initiated the data analysis instruction.

[0064] In one embodiment of the present application, the method for determining the current user category specifically includes: determining whether the current user corresponding to the data analysis instruction has a historical user category label; if the current user has a historical user category label, then using the user category indicated by the historical user category label as the current user category; if the current user does not have a historical user category label, then determining the current user category based on the current user's response information to the user classification questionnaire.

[0065] Specifically, since the data analysis in the embodiments of the present application needs to be performed based on user type, if the current user has already undergone data analysis at a historical moment, the current user should have a historical user category label. In this case, the user category indicated by the historical user category label can be used as the current user category of the user at the current moment. If the current user is undergoing data analysis for the first time, the current user needs to be classified. The classification method uses the form of a user classification questionnaire, that is, a user classification questionnaire (hereinafter referred to as the classification questionnaire) is displayed to the current user, the current user's response information to the user classification questionnaire is obtained, and then the current user category is determined based on the response information.

[0066] In one embodiment of the present application, the user classification questionnaire includes a plurality of preset questions, and the user's response information to the classification questionnaire is the user's response information to these preset questions. The method for determining the current user category may be: when detecting that the current user has completed the instruction of the user classification questionnaire, determining whether the current user's response information to a specified number of preset questions in the user classification questionnaire has been obtained; if the number of preset questions corresponding to the obtained response information is less than the specified number, prompting the current user that there are unanswered questions, and redisplaying the preset questions that the current user has not answered in the user classification questionnaire until the current user's response information to the specified number of preset questions in the user classification questionnaire is obtained; and determining the current user category based on the response information to the specified number of preset questions.

[0067] Specifically, when a user completes a classification questionnaire, an instruction to complete the user's classification questionnaire is issued. When this instruction is detected, it indicates that the classification questionnaire has been filled out. However, the user classification questionnaire includes multiple preset questions. When the user confirms that the classification questionnaire is completed, they may only provide response information for some of the preset questions. If the amount of response information is insufficient, the determination of the user's category will result in a large error. Therefore, when the user confirms that the classification questionnaire is completed, it is detected whether the user has provided response information for a specified number of preset questions (such as all questions, 80% of the total number of questions, etc.). If the user does not provide response information for the specified number of preset questions, the amount of response information is too small. In this case, the preset questions that the user has not answered are redisplayed so that the user can provide response information for the unanswered preset questions. This ensures that a sufficient amount of response information data can be obtained to accurately classify the user.

[0068] When categorizing users based on their response information, the response information can first be clustered to determine the response information category, and then the user category can be determined based on the response information category. For example, if the number of response information belonging to the first category is the largest, the user category is determined to be the first category. For another example, if the response information to a preset question is associated with a preset user category, and if the current user's response information matches the response information of a preset user category, the corresponding preset user category is considered to be the current user category.

[0069] In one embodiment of the present application, before detecting a data analysis instruction, the data analysis method for a virtual resource product provided by the embodiment of the present application also includes: when a data analysis request for a specified object is detected, determining whether the current user corresponding to the data analysis request is a compliant user; if the current user is not a compliant user, instructing the current user to change to a compliant user based on the current user's feedback information on the protocol guidance information; if the current user is a compliant user, determining the current user's data analysis authority; when the data analysis authority indicates that the current user has the authority to issue a data analysis instruction for the specified object, generating a data analysis instruction.

[0070] Specifically, a data analysis request refers to a request generated based on a user-selected data analysis operation. For example, in a graphical user interface, a data analysis request is generated when a user selects a specific object and clicks the corresponding data analysis button. A data analysis request is used to generate data analysis instructions. A compliant user is a legal user that complies with regulations. Compliant users can be registered users, enrolled users, or users with an account. Therefore, determining whether the current user is a compliant user can include checking whether the user has registered, enrolled, or opened an account. If the current user is not a compliant user, the user must be instructed to change to a compliant user; otherwise, the user will not be able to continue data analysis. Guiding the current user to change to a compliant user involves providing the current user with protocol guidance information. This protocol guidance information provides instructions on how to change to a compliant user, such as user registration guidance information, user registration guidance information, or user account opening guidance information. Feedback is obtained from the current user as they perform operations in accordance with the protocol guidance information. If the feedback is correct or legal, the current user can be changed to a compliant user.

[0071] After determining that the current user is a compliant user, the current user's data analysis permissions are determined. Data analysis permissions refer to the permissions for data analysis functions available to the user. When data analysis permissions are too low, the user cannot perform data analysis on certain data. For example, data analysis permissions can be divided into: no permissions, low-level permissions, and high-level permissions. No permissions prohibit data analysis, low-level permissions allow partial data analysis, and high-level permissions allow full data analysis. Therefore, the corresponding data analysis instructions are only generated when the current user's data analysis permissions indicate that the current user has the authority to issue data analysis instructions for the specified object.

[0072] Step 220: Score the specified object using multiple evaluation models to obtain multiple scores for the specified object; wherein one evaluation model scores the specified object based on one evaluation dimension.

[0073] Specifically, an evaluation model is a model for scoring a specified object. In the embodiments of the present application, there are multiple evaluation models for scoring a specified object, and each evaluation model can score the specified object from a single evaluation dimension. For example, evaluation dimension A corresponds to evaluation model A. Using evaluation model A to score the specified object results in score a; evaluation dimension B corresponds to evaluation model B. Using evaluation model B to score the specified object results in score b; and evaluation dimension C corresponds to evaluation model C. Using evaluation model C to score the specified object results in score c.

[0074] An evaluation model scores a specified object and obtains a score for the specified object. Then, by using multiple evaluation models to score the specified object respectively, multiple scores for the specified object can be obtained. Each score actually reflects the performance of the specified object in each evaluation dimension.

[0075] In one embodiment of the present application, before obtaining the evaluation model, the data analysis method for virtual resource products provided in the embodiment of the present application also includes: constructing multiple evaluation models based on a multivariate linear regression algorithm, and training each evaluation model separately through training data.

[0076] Specifically, the evaluation model uses a multivariate linear regression algorithm, which makes the model highly interpretable and computationally fast. The evaluation model is trained using training data to obtain a trained evaluation model, which can then be used to score specific objects.

[0077] Step 230: A plurality of ratings are integrated according to the current user category to obtain a comprehensive rating of the specified object.

[0078] Specifically, in order to meet the data analysis needs of users of different categories, after obtaining multiple scores, the technical solution of this application integrates the multiple scores according to the current user category to obtain a comprehensive score of the specified object, so that there is a certain correlation between the comprehensive score and the current user category.

[0079] In one embodiment of the present application, multiple ratings are fused, and multiple ratings may be statistically processed. For example, the weights of each rating dimension are determined according to the current user category, and then the multiple ratings are weighted and summed according to the weights of each rating dimension to obtain a comprehensive rating of the specified object. For example, for the first category of users, the weight of evaluation dimension A is α1, the weight of evaluation dimension B is β1, and the weight of evaluation dimension C is γ1. If the current user category is the first category of users, the comprehensive rating of the specified object is: α1*a+β1*b+γ1*c. For the second category of users, the weight of evaluation dimension A is α2, the weight of evaluation dimension B is β2, and the weight of evaluation dimension C is γ2. If the current user category is the second category of users, the comprehensive rating of the specified object is: α2*a+β2*b+γ2*c.

[0080] In one embodiment of the present application, multiple ratings can be fused through a rating fusion model, and the specific process includes: constructing multiple rating fusion models based on a multivariate linear regression algorithm, and setting model initial parameters for each rating fusion model according to preset user categories; training each rating fusion model after setting the model initial parameters through training data; determining the rating fusion model corresponding to the current user category, and fusing the multiple ratings through the rating fusion model corresponding to the current user category to obtain a comprehensive score for the specified object.

[0081] Specifically, first, multiple scoring fusion models are constructed based on the multivariate linear regression algorithm. The scoring fusion models correspond to the preset user categories one by one, that is, one preset user category corresponds to one scoring fusion model. For example, if there are three preset user categories, there are three scoring fusion models.

[0082] Then, the model initial parameters are set for the corresponding scoring fusion model according to the preset user category. Generally, the model initial parameters are usually determined randomly, but in the embodiment of the present application, in order to enhance the data processing accuracy of the evaluation model, the model initial parameters are pre-set and are set according to the preset user category. For example, the model initial parameters can be obtained by relevant personnel based on objective data and experience, and the model initial parameters of the scoring fusion model corresponding to different preset user categories are different. After setting the model initial parameters, the scoring fusion model can be trained using training data, and the scoring fusion model can adaptively adjust its own model parameters during the training process. The training data of the scoring fusion model includes the scores output by each scoring model, and can also include industry information of the sample object (such as industry ranking, etc.).

[0083] After obtaining the trained rating fusion models corresponding to each preset user category, when performing rating fusion on the current user category, first obtain the corresponding rating fusion model based on the current user category, and then use the rating fusion model to fuse multiple ratings to obtain a comprehensive rating for the specified object.

[0084] The embodiments of the present application, by setting initial model parameters for the scoring fusion model based on preset user categories, can solve the cold start problem caused by insufficient training data during the use of the scoring fusion model. In other words, the amount of training data is small, making it difficult for the scoring fusion model to learn parameters. In this case, directly training the scoring fusion model with a small amount of data can easily lead to low data processing accuracy of the scoring fusion model. By setting reasonable initial model parameters for the scoring fusion model, the scoring fusion model can learn the training data based on more accurate model parameters, thereby improving the data processing accuracy of the scoring fusion model.

[0085] Step 240: Generate a data analysis result of the specified object based on the comprehensive score and the multiple scores.

[0086] Specifically, after obtaining the comprehensive score and multiple scores, the data analysis results for the specified object can be generated. Individual scores analyze the specified object across various evaluation dimensions, representing a lower-level analysis; the comprehensive score is actually a holistic (i.e., macroscopic) analysis of the specified object, representing a higher-level analysis. Therefore, the data analysis results reflect both the analysis of the specified object from multiple evaluation dimensions and a top-down (or bottom-up) analysis of the specified object.

[0087] In one embodiment of the present application, the data analysis results include at least one of text analysis results and chart analysis results. The text analysis results refer to data analysis results expressed in text form, while the chart analysis results refer to data analysis results expressed in the form of graphics or tables.

[0088] In one embodiment of the present application, the process of generating a text analysis result includes: obtaining industry information of a specified object, and generating a text analysis result of the specified object based on the comprehensive score and the industry information.

[0089] Specifically, the industry information of the specified object includes the industry ranking and industry score of the specified object. The comprehensive score and industry information are combined according to the set template to form a text analysis result. Optionally, the comprehensive score can also be mapped to a corresponding comprehensive rating, and then the comprehensive rating and industry information are combined according to the set template to form a text analysis result. For example, when the comprehensive score is 4-5 points, it is mapped to grade A (indicating excellent); when the comprehensive score is 3-4 points, it is mapped to grade B (indicating good); when the comprehensive score is 2-3 points, it is mapped to grade C (indicating qualified); when the comprehensive score is 0-2 points, it is mapped to grade D (indicating unqualified).

[0090] In one embodiment of the present application, before mapping the comprehensive rating, the comprehensive score can be standardized, such as Z-Score standardization, to map the comprehensive score to a data range with a smaller value, and then the standardized comprehensive score is subjected to comprehensive rating mapping.

[0091] In one embodiment of the present application, the process of generating a chart analysis result includes: generating a chart analysis result of a specified object according to a plurality of scores and evaluation dimensions corresponding to each score.

[0092] Specifically, the chart analysis result can be a graph or a table. In the embodiment of the present application, the chart analysis result adopts a radar chart, in which an axis in the radar chart represents an evaluation dimension, and the value of the axis represents the score of the corresponding evaluation dimension.

[0093] By combining the text analysis results with the chart analysis results, we can see not only the comprehensive score of the specified object, but also the score of the specified object in each evaluation dimension, thereby conducting a top-down or bottom-up analysis of the specified object, reflecting a certain depth of data analysis.

[0094] In one embodiment of the present application, the data analysis method for virtual resource products provided by the present application also includes: obtaining multiple similar objects of the specified object, and scoring each similar object according to multiple evaluation models corresponding to the current user category to obtain multiple scores for each similar object; generating data comparison analysis results of multiple similar objects and the specified object based on the multiple scores of each similar object and the multiple scores of the specified object.

[0095] Furthermore, in this embodiment, when determining similar objects of a specified object, similar objects may include products associated with the specified object, such as fund products or derivatives corresponding to a certain stock. Specifically, when determining similar objects, the object information of the specified object is first obtained, and the object information may be information such as product identification and product information; then, based on the set character correspondence, the above object information is normalized and replaced to obtain information with a unified data type; this information is concatenated to generate character information, and the character information Cha_in is sequentially searched in the character Cha_da in the database to determine the similarity coefficient Sim(Cha_in, Cha_da):

[0096]

[0097] Among them, num() is used to represent the number of characters in the string, and α and β represent preset character factors.

[0098] After the similarity coefficient is calculated, the object corresponding to the character information corresponding to the maximum similarity coefficient is determined and used as the similar object corresponding to the specified object. In this way, accurate and comprehensive similar objects can be obtained.

[0099] Specifically, after analyzing a specific object, multiple similar objects of the specific object can be obtained and analyzed. The data analysis results of each similar object are then compared with the data analysis results of the specific object to generate a data comparison analysis result. The data analysis process for similar objects is the same as that for the specific object and will not be repeated here.

[0100] In the technical solution provided in the embodiments of the present application, users are classified and designated objects are scored respectively through multiple evaluation models to obtain multiple scores for the designated objects; wherein, one evaluation model scores the designated object from one evaluation dimension; then, the multiple scores are fused according to the current user category to obtain a comprehensive score for the designated object, and finally, data analysis results are generated based on the comprehensive score and the multiple scores; the data analysis results can be adjusted according to different user categories, which not only meets the different data analysis needs of users of different categories, but also multiple scores and comprehensive scores can be used for data analysis from different scoring dimensions and levels, making the data analysis more comprehensive and improving the comprehensiveness and accuracy of product evaluation analysis.

[0101] The following is a specific example to illustrate the implementation process of the data analysis method for virtual resource products provided in the embodiment of the present application.

[0102] Figure 3 The flowchart of the data analysis method for virtual resource products provided by an embodiment of the present application is schematically shown. The method is applied to the scenario of stock analysis. In this scenario, the designated object is a stock selected by the user, such as Figure 3 As shown, the method includes:

[0103] Step 301: When a data analysis request for a specified object is detected, determine whether the current user corresponding to the data analysis request is a compliant user.

[0104] For example, when a user selects a stock and clicks the corresponding data analysis button, a data analysis request is generated. A compliant user in this embodiment of the application refers to a user who has opened an account. When a user requests data analysis for a specified stock, it is determined whether the current user has opened an account.

[0105] Step 302: If the current user is not a compliant user, instruct the current user to change to a compliant user based on the feedback information of the current user with respect to the protocol guidance information.

[0106] Specifically, if the current user has not opened an account, they are not a compliant user. In this case, guidance information can be displayed to the user. For example, a pop-up window with account opening instructions can be displayed on the user's terminal device to guide the user through the account opening process. Once the user completes the account opening process, the user becomes a compliant user. If the current user does not complete the account opening process, the current user's data analysis request will be blocked.

[0107] Step 303: If the current user is a compliant user, determine the data analysis authority of the current user; when the data analysis authority indicates that the current user has the authority to issue a data analysis request for the specified object, generate a data analysis instruction.

[0108] Specifically, when it is determined that the current user has opened an account, that is, the current user is a compliant user, the data analysis permission of the current user is obtained. In an embodiment of the present application, data analysis permission includes three levels: no permission, low-level permission, and high-level permission. When the data analysis permission is no permission, the user cannot use the data analysis function, and the current user's data analysis request is intercepted. When the data analysis permission is a low-level permission, the user can use some data analysis functions, and at this time, it is determined whether the data analysis of the specified object is within the current permission range. When the data analysis permission is a high-level permission, the user can use all data analysis functions.

[0109] Optionally, when data analysis permission acquisition fails, the current user's data analysis permission is assumed to be no permission.

[0110] Step 304: When a data analysis instruction for a specified object is detected, it is determined whether the current user corresponding to the data analysis instruction has a historical user category label.

[0111] Specifically, determining whether the current user has a historical user category tag is equivalent to determining whether the current user is using the data analysis function for the first time. If this is not the first time the current user has used the data analysis function, the user should have a historical user category tag; if this is the first time the current user has used the data analysis function, the user does not have a historical user category tag.

[0112] Step 305: If the current user has a historical user category tag, the user category indicated by the historical user category tag is used as the current user category.

[0113] Specifically, when a user has a historical user category label, the historical user category label is the current user category of the current user.

[0114] Step 306: If the current user does not have a historical user category label, the current user category is determined based on the current user's response information to the user classification questionnaire.

[0115] Specifically, this step includes: when it is detected that the current user has completed the instruction of the user classification questionnaire, determining whether the current user's response information for a specified number of preset questions in the user classification questionnaire has been obtained; if the number of preset questions corresponding to the obtained response information is less than the specified number, prompting the current user that there are unanswered questions, and redisplaying the preset questions that the current user has not answered in the user classification questionnaire until the current user's response information for the specified number of preset questions in the user classification questionnaire is obtained; determining the current user category based on the response information for the specified number of preset questions.

[0116] Specifically, step 306 is to determine the current user category according to the user classification questionnaire when the current user uses the data analysis function for the first time. The specific implementation process can be referred to the relevant description above and will not be repeated here.

[0117] In the embodiment of the present application, user categories (that is, the preset user categories hereinafter) include three categories: balanced investors, fundamental investors, and technical investors. Balanced investors: They consider fundamentals, technical aspects, and capital aspects comprehensively, that is, they focus on buying and selling timing, while also considering medium- and long-term returns. Fundamental investors: Compared with technical and capital aspects, they focus more on fundamentals. They are investors who focus on the intrinsic value and medium- and long-term returns of the target. Short-term fluctuations are not important to them. Technical investors: Compared with fundamentals, they focus more on technical and fundamentals. They are short-term investors who pay attention to the short-term buying and selling imbalance opportunities of the target.

[0118] For example, the user classification questionnaire includes three questions (Question 1, Question 2, Question 3), each with four possible answers (Answer A, Answer B, Answer C, Answer D). The responses to a specified number of pre-set questions represent the responses to all three questions. If the user's responses contain a higher number of Answer A answers, the user is determined to be a fundamental investor. If the user's responses contain a higher number of Answer B answers, the user is determined to be a technical investor. In other cases, the user is determined to be a balanced investor. (It will be appreciated that user classification can be flexibly adjusted based on the question and answer settings; this is merely an example of categorizing users based on their responses.)

[0119] Step 307: Score the specified object using multiple evaluation models to obtain multiple scores for the specified object; wherein one evaluation model scores the specified object based on one evaluation dimension.

[0120] This embodiment includes three evaluation models: a technical evaluation model, a fundamental evaluation model, and a funding evaluation model, corresponding to three evaluation dimensions: technical, fundamental, and funding. These three evaluation models are used to score the specified stock selected by the user, resulting in a score for the stock across these three evaluation dimensions: technical score, fundamental score, and funding score.

[0121] Step 308: Construct multiple scoring fusion models based on the multivariate linear regression algorithm, and set the initial model parameters for each scoring fusion model according to the preset user category; train each scoring fusion model after setting the initial model parameters using the training data; determine the scoring fusion model corresponding to the current user category, and fuse the multiple scores using the scoring fusion model corresponding to the current user category to obtain a comprehensive score for the specified object.

[0122] The specific process of building the scoring fusion model can be found in the previous section and will not be repeated here. When the scoring fusion model is used to fuse the scoring data output by multiple scoring models, the industry information of the current user's selected stock is also used as input data for the scoring fusion model. In other words, the scoring fusion model fuses multiple scores based on this industry information to produce a comprehensive score.

[0123] Based on the scoring fusion model and the three scoring models, it can be seen that this application actually uses a multiple linear regression model. "Multiple" refers to the application of multiple linear regression models at multiple levels, divided into three layers: the top layer is the comprehensive score, which is obtained by integrating the scores of the three evaluation dimensions; the middle layer is the evaluation dimension layer, which has a total of three evaluation dimensions: technical, fundamental, and financial, each dimension is obtained by its own scoring model; and the bottom layer is the scoring model for each dimension.

[0124] Step 309: Obtain industry information of the designated object, and generate a text analysis result of the designated object based on the comprehensive score and the industry information.

[0125] Specifically, the comprehensive score is first mapped to a comprehensive rating. The mapping rule is: when the comprehensive score is greater than 4 points, the comprehensive rating is S; when the comprehensive score is between 3 and 4 points, the comprehensive rating is A; when the comprehensive score is between 2 and 3 points, the comprehensive rating is B; when the comprehensive score is between 1 and 2 points, the comprehensive rating is C; when the comprehensive score is less than 1 point, the comprehensive rating is D. SABCD represents the order from good to bad.

[0126] The text analysis results are formed according to the combination of industry information (including industry name and industry ranking) and comprehensive rating according to the set template. For example, the template for generating the text analysis results is: the comprehensive rating of the stock is "comprehensive rating", the ranking in the "industry name" industry is "industry ranking", and "splicing copy". In this template, the "comprehensive rating", "industry name" and "industry ranking" fields are all filled with the values ​​corresponding to the stock selected by the current user, and the "splicing copy" field is pre-set text information, which can establish an association relationship with the "comprehensive rating" field. For example, the relationship between "splicing copy" and "comprehensive rating" is: when the "comprehensive rating" is S, the "splicing copy" is: has a high investment value; when the "comprehensive rating" is A, the "splicing copy" is: has a certain investment value; when the "comprehensive rating" is B or C, the "splicing copy" is: it is recommended to keep paying attention; when the "comprehensive rating" is D, the "splicing copy" is: has to wait and see. For example, a text analysis result is: the comprehensive rating of the stock is S, it ranks first in industry X, and has high investment value.

[0127] In one embodiment of the present application, when the text analysis results are displayed on a terminal device, the "Comprehensive Rating," "Industry Name," and "Industry Ranking" fields can be highlighted. The comprehensive rating can be represented by a single color. For example, a five-color comprehensive rating color bar can be displayed on the display page, with the color area corresponding to the comprehensive rating of the current user-selected stock highlighted.

[0128] Since the comprehensive score is determined based on the user category, when the user category is different, the comprehensive score obtained for the same specified object may be different, and the corresponding comprehensive rating may also be different, so that the data analysis results fully consider the user's personal needs and are conducive to improving the user experience.

[0129] Step 310: Generate a chart analysis result of the specified object based on the multiple scores and the evaluation dimensions corresponding to each score.

[0130] The chart analysis results in this embodiment are generated as radar charts based on multiple ratings and evaluation dimensions. For example, the ratings include technical, fundamental, and financial ratings. The radar chart uses three coordinate axes to represent the scores corresponding to these three evaluation dimensions. Furthermore, the color of the radar chart matches the color of the overall rating, so that users can also obtain the overall rating through the radar chart.

[0131] Combining the text analysis results with the chart analysis results not only provides users with a macro-level comprehensive stock score as a reference, but also retains the analysis reference of each scoring dimension, making the data analysis comprehensive and detailed.

[0132] Step 311: Acquire multiple similar objects of the specified object, and score each similar object according to multiple evaluation models corresponding to the current user category to obtain multiple scores for each similar object; generate data comparison and analysis results of the multiple similar objects and the specified object based on the multiple scores of each similar object and the multiple scores of the specified object.

[0133] In an embodiment of the present application, after generating the data analysis results of a specified stock, similar stocks of the specified stock are further obtained to generate a radar chart of the similar stocks. For example, radar charts of four similar stocks are generated to compare the similar stocks with the specified stock.

[0134] In one embodiment of the present application, historical data of a specified stock may also be analyzed, for example, to generate a chart showing changes in the specified stock's comprehensive rating and a chart showing stock price trends over the past two months.

[0135] It should be noted that although the steps of the method of the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0136] The following introduces an embodiment of the device of the present application, which can be used to execute the data analysis method for virtual resource products in the above-mentioned embodiment of the present application. Figure 4 The structure block diagram of the data analysis device for virtual resource products provided by the embodiment of the present application is schematically shown. Figure 4 As shown, the data analysis device for the virtual resource product includes:

[0137] A user category determination module 410 is configured to, when a data analysis instruction for a specified object is detected, determine a current user category of a current user corresponding to the data analysis instruction;

[0138] Scoring module 420, configured to score the designated object using multiple evaluation models to obtain multiple scores for the designated object; wherein one evaluation model scores the designated object based on one evaluation dimension;

[0139] A rating fusion module 430 is configured to fuse the multiple ratings according to the current user category to obtain a comprehensive rating of the specified object;

[0140] The analysis result generating module 440 is configured to generate a data analysis result of the designated object according to the comprehensive score and the multiple scores.

[0141] In one embodiment of the present application, the user category determination module 410 includes:

[0142] a category label determination unit, configured to determine whether the current user corresponding to the data analysis instruction has a historical user category label;

[0143] a first user category determination unit, configured to, if the current user has a historical user category tag, use the user category indicated by the historical user category tag as the current user category;

[0144] The second user category determination unit is configured to determine the current user category according to the current user's response information to the user classification questionnaire if the current user does not have a historical user category label.

[0145] In one embodiment of the present application, the second user category determination unit is specifically configured to:

[0146] When detecting that the current user has completed an instruction for the user classification questionnaire, determining whether response information of the current user to a specified number of preset questions in the user classification questionnaire has been obtained;

[0147] If the number of preset questions corresponding to the obtained answer information is less than the specified number, the current user is prompted that there are unanswered questions, and the preset questions that the current user has not answered in the user classification questionnaire are redisplayed until the current user's answer information for the specified number of preset questions in the user classification questionnaire is obtained;

[0148] The current user category is determined based on the answer information of the specified number of preset questions.

[0149] In one embodiment of the present application, the scoring fusion module 430 is specifically configured to:

[0150] Build multiple scoring fusion models based on the multivariate linear regression algorithm, and set the initial model parameters for each scoring fusion model according to the preset user categories;

[0151] Use training data to train each scoring fusion model after setting the initial model parameters;

[0152] A rating fusion model corresponding to the current user category is determined, and the multiple ratings are fused using the rating fusion model corresponding to the current user category to obtain a comprehensive rating of the designated object.

[0153] In one embodiment of the present application, the apparatus further comprises:

[0154] a compliance detection module, configured to, when detecting a data analysis request for the specified object, determine whether a current user corresponding to the data analysis request is a compliant user;

[0155] A user changing module, configured to instruct the current user to change to a compliant user according to feedback information of the current user regarding the protocol guidance information if the current user is not a compliant user;

[0156] A permission determination module, configured to determine the data analysis permission of the current user if the current user is a compliant user;

[0157] The instruction generation module is configured to generate a data analysis instruction when the data analysis permission indicates that the current user has permission to issue a data analysis request for the designated object.

[0158] In one embodiment of the present application, the data analysis result includes at least one of a text analysis result and a chart analysis result; the analysis result generation module 440 includes:

[0159] a text analysis result generating unit, configured to obtain industry information of the designated object and generate a text analysis result of the designated object based on the comprehensive score and the industry information;

[0160] A chart analysis result generating unit is configured to generate a chart analysis result of the specified object based on the multiple scores and the evaluation dimensions corresponding to each score.

[0161] In one embodiment of the present application, the apparatus further comprises:

[0162] A similar object analysis module is used to obtain multiple similar objects of the specified object, and score each similar object according to multiple evaluation models corresponding to the current user category to obtain multiple scores for each similar object; and generate data comparison analysis results between the multiple similar objects and the specified object based on the multiple scores of the similar objects and the multiple scores of the specified object.

[0163] The specific details of the data analysis device for virtual resource products provided in each embodiment of the present application have been described in detail in the corresponding method embodiments and will not be repeated here.

[0164] Figure 5 The block diagram schematically shows a computer system structure of an electronic device used to implement an embodiment of the present application.

[0165] It should be noted that Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0166] like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 into the random access memory (RAM) 503. Various programs and data required for system operation are also stored in the random access memory 503. The CPU 501, the read-only memory 502, and the random access memory 503 are connected to each other via a bus 504. An input / output interface 505 (i.e., an I / O interface) is also connected to the bus 504.

[0167] The following components are connected to the input / output interface 505: an input section 506 including a keyboard, a mouse, and the like; an output section 507 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 508 including a hard disk; and a communication section 509 including a network interface card such as a local area network card or a modem. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 510 as needed, so that a computer program read therefrom can be installed into the storage section 508 as needed.

[0168] In particular, according to an embodiment of the present application, the processes described in the various method flow charts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods shown in the flow charts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication portion 509 and / or installed from a removable medium 511. When the computer program is executed by the central processing unit 501, the various functions defined in the system of the present application are performed.

[0169] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0170] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0171] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0172] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0173] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0174] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A data analysis method for virtual resource products, characterized in that: include: When a data analysis instruction for a specified object is detected, determining a current user category of a current user corresponding to the data analysis instruction; wherein the specified object includes a virtual resource product; the current user is the user who issued the data analysis instruction; wherein the user categories include balanced investors, fundamental investors, and technical investors, wherein the balanced investors consider technical, fundamental, and financial aspects comprehensively, wherein the fundamental investors pay more attention to fundamentals than to technical and financial aspects, and wherein the technical investors pay more attention to technical aspects than to fundamentals and financial aspects; Scoring the designated object using multiple evaluation models to obtain multiple scores for the designated object; wherein one evaluation model scores the designated object based on one evaluation dimension; the evaluation dimension includes technical, fundamental, and financial aspects; Build multiple scoring fusion models based on the multivariate linear regression algorithm, and set the initial model parameters for each scoring fusion model according to the preset user categories; Use training data to train each scoring fusion model after setting the initial model parameters; Determining a rating fusion model corresponding to the current user category, and fusing the multiple ratings using the rating fusion model corresponding to the current user category to obtain a comprehensive rating of the designated object; generating a data analysis result of the designated object according to the comprehensive score and the multiple scores; A data comparison analysis result of each similar object and the designated object is generated based on multiple scores of each similar object of the designated object and multiple scores of the designated object; wherein the similar object is determined based on a similarity coefficient between the designated object and other objects, and the similarity coefficient is calculated as follows: Among them, Cha_in represents the specified object string, and Cha_da represents other object strings in the database. The number of characters used to represent the string, Indicates the preset character factor.

2. The data analysis method for virtual resource products according to claim 1, characterized in that: Determining a current user category of a current user corresponding to the data analysis instruction includes: Determining whether the current user corresponding to the data analysis instruction has a historical user category label; If the current user has a historical user category tag, the user category indicated by the historical user category tag is used as the current user category; If the current user does not have a historical user category label, the current user category is determined according to the current user's response information to the user classification questionnaire.

3. The data analysis method for virtual resource products according to claim 2, characterized in that: Determining the current user category based on the current user's response information to the user classification questionnaire includes: When detecting that the current user has completed an instruction for the user classification questionnaire, determining whether response information of the current user to a specified number of preset questions in the user classification questionnaire has been obtained; If the number of preset questions corresponding to the obtained answer information is less than the specified number, the current user is prompted that there are unanswered questions, and the preset questions that the current user has not answered in the user classification questionnaire are redisplayed until the current user's answer information for the specified number of preset questions in the user classification questionnaire is obtained; The current user category is determined based on the answer information of the specified number of preset questions.

4. The data analysis method for virtual resource products according to claim 1, characterized in that: Before detecting the data analysis instruction for the specified object, the method further includes: When a data analysis request for the specified object is detected, determining whether a current user corresponding to the data analysis request is a compliant user; If the current user is not a compliant user, instructing the current user to change to a compliant user according to feedback information of the current user with respect to the protocol guidance information; If the current user is a compliant user, determining the data analysis authority of the current user; When the data analysis permission indicates that the current user has the permission to issue a data analysis request for the designated object, a data analysis instruction is generated.

5. The data analysis method for virtual resource products according to claim 1, characterized in that: The data analysis result includes at least one of a text analysis result and a chart analysis result; generating the data analysis result of the specified object according to the multiple scores includes: Acquire industry information of the designated object, and generate a text analysis result of the designated object based on the comprehensive score and the industry information; Generate a chart analysis result of the specified object according to the multiple scores and the evaluation dimensions corresponding to each score.

6. The method for analyzing data of a virtual resource product according to any one of claims 1 to 5, characterized in that: Before generating a data comparison and analysis result of each similar object and the designated object based on the multiple scores of each similar object of the designated object and the multiple scores of the designated object, the method further includes: A plurality of similar objects of the designated object are obtained, and each similar object is scored according to a plurality of evaluation models corresponding to the current user category to obtain a plurality of scores for each similar object.

7. A data analysis device for virtual resource products, characterized in that: include: A user category determination module, configured to, upon detecting a data analysis instruction for a specified object, determine a current user category of a current user corresponding to the data analysis instruction; wherein the specified object includes a virtual resource product; and the current user is the user who issued the data analysis instruction; wherein user categories include balanced investors, fundamental investors, and technical investors, wherein the balanced investors comprehensively consider technical, fundamental, and financial factors, wherein the fundamental investors place greater emphasis on fundamentals than on technical and financial factors, and wherein the technical investors place greater emphasis on technical factors than on fundamentals and financial factors; a scoring module, configured to score the designated object using multiple evaluation models to obtain multiple scores for the designated object; wherein each evaluation model scores the designated object based on one evaluation dimension; the evaluation dimensions include technical, fundamental, and financial aspects; A scoring fusion module is configured to construct multiple scoring fusion models based on a multivariate linear regression algorithm, and set initial model parameters for each scoring fusion model according to a preset user category; train each scoring fusion model after setting the initial model parameters using training data; determine the scoring fusion model corresponding to the current user category, and fuse the multiple scores using the scoring fusion model corresponding to the current user category to obtain a comprehensive score for the specified object; An analysis result generation module is configured to generate a data analysis result for the designated object based on the comprehensive score and the multiple scores; and generate a data comparison analysis result for each similar object and the designated object based on the multiple scores of each similar object of the designated object and the multiple scores of the designated object; wherein the similar object is determined based on a similarity coefficient between the designated object and the other objects, and the similarity coefficient is calculated as follows: Among them, Cha_in represents the specified object string, and Cha_da represents other object strings in the database. The number of characters used to represent the string, Indicates the preset character factor.

8. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing data of a virtual resource product according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor executes the executable instructions so that the electronic device executes the data analysis method for virtual resource products according to any one of claims 1 to 6.

Images