Analysis method and device based on user evaluation data, storage medium and electronic device

Abstract

The invention provides an analysis method and device based on user evaluation data, a storage medium and an electronic device, and relates to the technical field of smart home, and the method comprises the steps: obtaining user evaluation data for a target object, and carrying out the data cleaning of the user evaluation data, and obtaining effective evaluation data; respectively inputting the effective evaluation data into each evaluation model of the evaluation system to obtain an evaluation result of each evaluation model; and based on the weight corresponding to the evaluation target, performing weighted calculation on the evaluation result output by each evaluation model to obtain an evaluation score. The analysis method and device based on the user evaluation data, the storage medium and the electronic device are used for cleaning the user evaluation data through a large language model and evaluating the cleaned data through different evaluation models. And finally, performing weighted calculation based on the evaluation result of each evaluation model and an evaluation target specified by a user to obtain accurate evaluation of the target object.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to an analysis method, device, storage medium and electronic device based on user evaluation data. Background Art

[0002] With the development of big data analysis technology, users' evaluation data on products, corporate images or public figures are collected and analyzed through big data to obtain the real evaluation results of users on products, corporate images or public figures.

[0003] In related technologies, natural language processing is usually used to clean and analyze data to obtain analysis results. However, the analysis results obtained by this analysis method not only have low accuracy, but also require a lot of manual correction and adjustment, and can only be analyzed and evaluated for specific evaluation targets, with poor flexibility. Summary of the invention

[0004] The purpose of this application is to provide an analysis method, device, storage medium and electronic device based on user evaluation data, which is used to clean the user evaluation data through a large language model, and evaluate the cleaned data through different evaluation models, and finally perform weighted calculation based on the evaluation results of each evaluation model and the evaluation goals specified by the user to obtain an accurate evaluation of the target object.

[0005] The present application provides an analysis method based on user evaluation data, including: Obtain user evaluation data for the target object, and perform data cleaning on the user evaluation data to obtain valid evaluation data; input the valid evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; based on the weight corresponding to the evaluation target, perform weighted calculation on the evaluation result to obtain the evaluation score; wherein the evaluation model of the evaluation system includes: industry grading model, sentiment model, question classification model, industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target.

[0006] Optionally, the data cleaning of the user evaluation data to obtain valid evaluation data includes: inputting the user evaluation data into a natural language model, and controlling the natural language model to perform data cleaning on the user evaluation data based on preset cleaning prompt words to obtain the valid evaluation data; wherein the data cleaning is used to identify and remove invalid information in the user evaluation data.

[0007] Optionally, the valid evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: inputting the valid evaluation data into the industry grading model of the evaluation system, identifying the industry to which the valid evaluation data belongs through the industry grading model, and dividing each user evaluation data into multiple industries according to the industry identification result and the industry code to obtain an industry grading result; wherein the industry identification result includes: multiple industries to which the content contained in the valid evaluation data belongs; the industry code is used to indicate the industry category of each industry in the multiple industries.

[0008] Optionally, the valid evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: inputting the valid evaluation data into the emotion model of the evaluation system, and performing emotion classification on the content described in each user comment through the emotion model to obtain the emotion classification result; wherein the emotion model is used to classify each user evaluation data in the valid evaluation data into any one of the following items: positive emotion, neutral emotion and negative emotion.

[0009] Optionally, the inputting of the valid evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model includes: inputting the valid evaluation data into the question classification model of the evaluation system, classifying the valid evaluation data based on the questions fed back by users, and obtaining the question classification result.

[0010] Optionally, the valid evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: inputting the valid evaluation data into the industry label model of the evaluation system, using the industry label model to label each user evaluation data in the valid evaluation data, and obtaining a multi-level industry label corresponding to each user evaluation data.

[0011] Optionally, the evaluation results are weighted calculated based on the weights corresponding to the evaluation targets to obtain an evaluation score, including: obtaining a weight set corresponding to the evaluation targets from a target comparison table, and performing a weighted calculation on the evaluation results of each evaluation model based on each weight in the weight set to obtain the evaluation score; wherein the weight set includes: weight values ​​corresponding to each evaluation indicator in the evaluation results of each evaluation model; the target comparison table contains a weight set corresponding to each evaluation target, and one evaluation target corresponds to one weight set.

[0012] The present application also provides an analysis device based on user evaluation data, comprising: A data processing module is used to obtain user evaluation data for a target object and perform data cleansing on the user evaluation data to obtain valid evaluation data; a data evaluation module is used to input the valid evaluation data into each evaluation model of the evaluation system to obtain an evaluation result of each evaluation model; an evaluation calculation module is used to perform weighted calculation on the evaluation result based on the weight corresponding to the evaluation target to obtain an evaluation score; wherein the evaluation model of the evaluation system includes: an industry grading model, a sentiment model, a question classification model, and an industry labeling model; the evaluation score is used to characterize the evaluation level of the evaluation target.

[0013] Optionally, the data processing module is specifically used to input the user evaluation data into a natural language model, and control the natural language model to perform data cleaning on the user evaluation data based on preset cleaning prompt words to obtain the valid evaluation data; wherein, the data cleaning is used to identify and remove invalid information in the user evaluation data.

[0014] Optionally, the data evaluation module is specifically used to input the valid evaluation data into the industry grading model of the evaluation system, identify the industry to which the valid evaluation data belongs through the industry grading model, and divide each user evaluation data into multiple industries according to the industry identification result and the industry code to obtain an industry grading result; wherein the industry identification result includes: multiple industries to which the content contained in the valid evaluation data belongs; the industry code is used to indicate the industry category of each of the multiple industries.

[0015] Optionally, the data evaluation module is specifically used to input the valid evaluation data into the sentiment model of the evaluation system, and perform sentiment classification on the content described in each user comment through the sentiment model to obtain a sentiment classification result; wherein the sentiment model is used to divide each user evaluation data in the valid evaluation data into any one of the following items: positive sentiment, neutral sentiment and negative sentiment.

[0016] Optionally, the data evaluation module is specifically used to input the valid evaluation data into a problem classification model of the evaluation system, classify the valid evaluation data based on the problems fed back by users, and obtain problem classification results.

[0017] Optionally, the data evaluation module is specifically used to input the valid evaluation data into the industry label model of the evaluation system, and use the industry label model to label each user evaluation data in the valid evaluation data to obtain a multi-level industry label corresponding to each user evaluation data.

[0018] Optionally, the evaluation calculation module is specifically used to obtain a weight set corresponding to the evaluation target from a target comparison table, and perform weighted calculation on the evaluation results of each evaluation model based on the weights in the weight set to obtain the evaluation score; wherein the weight set includes: the weight values ​​corresponding to each evaluation indicator in the evaluation results of each evaluation model; the target comparison table contains a weight set corresponding to each evaluation target, and one evaluation target corresponds to one weight set.

[0019] The present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of any of the above-mentioned analysis methods based on user evaluation data.

[0020] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned analysis methods based on user evaluation data are implemented.

[0021] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of any of the above-mentioned analysis methods based on user evaluation data are implemented.

[0022] The analysis method, device, storage medium and electronic device based on user evaluation data provided by the present application first obtain user evaluation data for the target object, and perform data cleaning on the user evaluation data to obtain valid evaluation data; then, input the valid evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; finally, based on the weight corresponding to the evaluation target, perform weighted calculation on the evaluation result to obtain the evaluation score; wherein the evaluation model of the evaluation system includes: industry classification model, sentiment model, question classification model, industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target. In this way, the user evaluation data is cleaned by a large language model, and the cleaned data is evaluated by different evaluation models. Finally, a weighted calculation is performed based on the evaluation result of each evaluation model and the evaluation target specified by the user to obtain an accurate evaluation of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 is a schematic diagram of a hardware environment of an interaction method of a smart device according to an embodiment of the present application; Figure 2 It is a schematic diagram of the architecture of the analysis system based on user evaluation data provided by this application; Figure 3 It is a flowchart of the analysis method based on user evaluation data provided by this application; Figure 4 It is a schematic diagram of the structure of the analysis device based on user evaluation data provided by the present application; Figure 5 It is a schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims 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.

[0027] According to one aspect of an embodiment of the present application, an analysis method based on user evaluation data is provided. The analysis method based on user evaluation data is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above-mentioned analysis method based on user evaluation data can be applied to Figure 2 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 2As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0028] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing equipment, a smart dishwasher, a smart projection equipment, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart speaker, a smart fresh air equipment, a smart kitchen and bathroom equipment, a smart bathroom equipment, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification equipment, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0029] In view of the above technical problems existing in the related art, the embodiment of the present application provides an analysis system based on user evaluation data, such as Figure 2 The figure shows the architecture of the system. The system includes: a large language model for cleaning user evaluation data, an industry classification model for industry classification of user evaluation data, a sentiment model for sentiment classification of user evaluation data, a question classification model for question classification of user evaluation data, and an industry labeling model for labeling user evaluation data.

[0030] The following is a detailed description of the analysis method based on user evaluation data provided by the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0031] like Figure 3 As shown, an analysis method based on user evaluation data provided by an embodiment of the present application may include the following steps 301 to 303: Step 301: Obtain user evaluation data for a target object, and perform data cleaning on the user evaluation data to obtain valid evaluation data.

[0032] Exemplarily, in an embodiment of the present application, a natural language model can be used to clean up the original user evaluation data, and the corresponding cleaning prompt words can be used to remove invalid information such as advertising and marketing in the user evaluation data.

[0033] Specifically, the above step 301 may further include the following step 301a: Step 301a: input the user evaluation data into a natural language model, and control the natural language model to perform data cleaning on the user evaluation data based on preset cleaning prompt words to obtain the valid evaluation data.

[0034] The data cleaning is used to identify and remove invalid information in the user evaluation data.

[0035] Exemplarily, the above natural language model can clean the user evaluation data according to the cleaning rules shown in the following Table 1, thereby obtaining the above valid evaluation data.

[0036]

[0037] Table 1

[0038] For example, the preset cleaning prompt words may be: delete the rental information, property sales information, home appliance repair information, advertising information, stock fund information, etc. in the input text. By using the preset cleaning prompt words, the natural language model can be controlled to clean the user evaluation data to obtain effective evaluation data.

[0039] Step 302: Input the valid evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model.

[0040] Among them, the evaluation models of the evaluation system include: industry grading model, sentiment model, question classification model, and industry label model.

[0041] Specifically, the step of outputting the evaluation result of the industry classification model in the above step 302 may include the following steps 302a: Step 302a, input the valid evaluation data into the industry classification model of the evaluation system, identify the industry to which the valid evaluation data belongs through the industry classification model, and divide each user evaluation data into multiple levels of industries according to the industry identification result and the industry code to obtain the industry classification result.

[0042] The industry identification result includes: multiple industries to which the content contained in the valid evaluation data belongs; and the industry code is used to indicate the industry category of each industry in the multiple industries.

[0043] For example, in the embodiment of the present application, the industry can be divided into three levels according to the industry code, including: primary industry, secondary industry and tertiary industry. The industry classification model can identify the industry type of each user evaluation data in the valid evaluation data, and perform multi-level industry classification on the user evaluation data based on the industry code corresponding to the industry type according to the pre-set industry multi-level classification rules.

[0044] Specifically, the step of outputting the evaluation result by the emotion model in the above step 302 may include the following steps 302b: Step 302b: input the valid evaluation data into the sentiment model of the evaluation system, and perform sentiment classification on the content described in each user comment through the sentiment model to obtain a sentiment classification result.

[0045] The sentiment model is used to divide each user evaluation data in the valid evaluation data into any one of the following items: positive sentiment, neutral sentiment and negative sentiment.

[0046] For example, in the embodiment of the present application, the user evaluation data in the valid evaluation data can be sentimentally divided by the sentiment model. For example, a positive evaluation of the target object can be divided into positive sentiment, and vice versa, it can be divided into negative sentiment.

[0047] Specifically, the step of outputting the evaluation result by the question classification model in the above step 302 may include the following steps 302c: Step 302c: input the valid evaluation data into the question classification model of the evaluation system, classify the valid evaluation data based on the questions fed back by the users, and obtain question classification results.

[0048] Exemplarily, after the valid evaluation data is input into the question classification model, the question classification model can be used to determine the question type corresponding to the user evaluation data, and the user evaluation data can be classified based on the question type.

[0049] For example, in the embodiment of the present application, the problem classification model can identify the following types of problems: after-sales problems, quality problems, marketing problems, customer service problems, e-commerce customer service problems, brand comparisons, safety accidents, business disputes, listing-related, labor-management-related, policy and regulation-related, and other problems.

[0050] Specifically, the step of outputting the evaluation result by the industry label model in the above step 302 may include the following steps 302d: Step 302d: input the valid evaluation data into the industry label model of the evaluation system, and use the industry label model to label each user evaluation data in the valid evaluation data to obtain a multi-level industry label corresponding to each user evaluation data.

[0051] For example, in the embodiment of the present application, the industry tags can be divided into three levels, including: primary tags, secondary tags and tertiary tags. For details, please refer to the following Table 2:

[0052] Table 2

[0053] Step 303: Based on the weights corresponding to the evaluation targets, weighted calculation is performed on the evaluation results to obtain an evaluation score.

[0054] The evaluation score is used to represent the evaluation level of the evaluation target.

[0055] Exemplarily, in an embodiment of the present application, different weight sets can be set for different evaluation objectives, and the weight sets include the weights corresponding to each sub-item in the evaluation results of each evaluation model. Based on different weight sets, evaluations can be performed for different evaluation objectives.

[0056] Specifically, the above step 303 may further include the following step 303a: Step 303a: Obtain a weight set corresponding to the evaluation target from the target comparison table, and perform weighted calculation on the evaluation result of each evaluation model based on each weight in the weight set to obtain the evaluation score.

[0057] Among them, the weight set includes: the weight value corresponding to each evaluation indicator in the evaluation result of each evaluation model; the target comparison table contains the weight set corresponding to each evaluation target, and one evaluation target corresponds to one weight set.

[0058] For example, when a user wants to evaluate the function of a product, the weight of the evaluation index data related to the function can be increased, and the weight of other irrelevant evaluation index data can be reduced, thereby obtaining the user's true evaluation result on the function of the product.

[0059] The analysis method based on user evaluation data provided in the embodiment of the present application first obtains user evaluation data for the target object, and performs data cleaning on the user evaluation data to obtain valid evaluation data; then, the valid evaluation data is respectively input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; finally, based on the weight corresponding to the evaluation target, the evaluation results output by each evaluation model are weighted and calculated to obtain the evaluation score; wherein, the evaluation model of the evaluation system includes: industry classification model, sentiment model, question classification model, industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target. In this way, the user evaluation data is cleaned by the large language model, and the cleaned data is evaluated by different evaluation models. Finally, based on the evaluation results of each evaluation model and the evaluation target specified by the user, a weighted calculation is performed to obtain an accurate evaluation of the target object.

[0060] It should be noted that the analysis method based on user evaluation data provided in the embodiment of the present application can be executed by an analysis device based on user evaluation data, or a control module in the analysis device based on user evaluation data for executing the analysis method based on user evaluation data. In the embodiment of the present application, an analysis device based on user evaluation data executing the analysis method based on user evaluation data is taken as an example to illustrate the analysis device based on user evaluation data provided in the embodiment of the present application.

[0061] It should be noted that in the embodiments of the present application, the analysis methods based on user evaluation data shown in the above-mentioned method drawings are all illustrated by combining an accompanying drawing in the embodiments of the present application as an example. In specific implementation, the analysis methods based on user evaluation data shown in the above-mentioned method drawings can also be implemented in combination with any other drawings that can be combined as shown in the above-mentioned embodiments, which will not be repeated here.

[0062] The following is a description of an analysis device based on user evaluation data provided by the present application. The analysis method based on user evaluation data described below and described above can refer to each other.

[0063] Figure 4 A schematic diagram of the structure of an analysis device based on user evaluation data provided in an embodiment of the present application, such as Figure 4 As shown, specifically including: The data processing module 401 is used to obtain user evaluation data for the target object and perform data cleaning on the user evaluation data to obtain valid evaluation data; the data evaluation module 402 is used to input the valid evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; the evaluation calculation module 403 is used to perform weighted calculation on the evaluation result based on the weight corresponding to the evaluation target to obtain the evaluation score; wherein the evaluation model of the evaluation system includes: industry grading model, sentiment model, question classification model, industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target.

[0064] Optionally, the data processing module 401 is specifically used to input the user evaluation data into a natural language model, and control the natural language model to perform data cleaning on the user evaluation data based on preset cleaning prompt words to obtain the valid evaluation data; wherein, the data cleaning is used to identify and remove invalid information in the user evaluation data.

[0065] Optionally, the data evaluation module 402 is specifically used to input the valid evaluation data into the industry grading model of the evaluation system, identify the industry to which the valid evaluation data belongs through the industry grading model, and divide each user evaluation data into multiple industries according to the industry identification result and the industry code to obtain an industry grading result; wherein the industry identification result includes: multiple industries to which the content contained in the valid evaluation data belongs; the industry code is used to indicate the industry category of each industry in the multiple industries.

[0066] Optionally, the data evaluation module 402 is specifically used to input the valid evaluation data into the sentiment model of the evaluation system, and perform sentiment classification on the content described in each user comment through the sentiment model to obtain a sentiment classification result; wherein the sentiment model is used to divide each user evaluation data in the valid evaluation data into any one of the following items: positive sentiment, neutral sentiment and negative sentiment.

[0067] Optionally, the data evaluation module 402 is specifically configured to input the valid evaluation data into a question classification model of the evaluation system, classify the valid evaluation data based on questions fed back by users, and obtain question classification results.

[0068] Optionally, the data evaluation module 402 is specifically used to input the valid evaluation data into the industry label model of the evaluation system, and use the industry label model to label each user evaluation data in the valid evaluation data to obtain a multi-level industry label corresponding to each user evaluation data.

[0069] Optionally, the evaluation calculation module 403 is specifically used to obtain a weight set corresponding to the evaluation target from the target comparison table, and perform weighted calculation on the evaluation results of each evaluation model based on the weights in the weight set to obtain the evaluation score; wherein the weight set includes: the weight values ​​corresponding to each evaluation indicator in the evaluation results of each evaluation model; the target comparison table contains a weight set corresponding to each evaluation target, and one evaluation target corresponds to one weight set.

[0070] The analysis device based on user evaluation data provided by the present application first obtains user evaluation data for a target object, and performs data cleaning on the user evaluation data to obtain valid evaluation data; then, the valid evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; finally, based on the weight corresponding to the evaluation target, the evaluation result is weighted and calculated to obtain the evaluation score; wherein the evaluation model of the evaluation system includes: an industry classification model, a sentiment model, a question classification model, and an industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target. In this way, the user evaluation data is cleaned by a large language model, and the cleaned data is evaluated by different evaluation models. Finally, a weighted calculation is performed based on the evaluation result of each evaluation model and the evaluation target specified by the user to obtain an accurate evaluation of the target object.

[0071] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the analysis method based on the user evaluation data, the method comprising: obtaining the user evaluation data for the target object, and performing data cleaning on the user evaluation data to obtain the effective evaluation data; inputting the effective evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; performing weighted calculation on the evaluation result based on the weight corresponding to the evaluation target to obtain the evaluation score; wherein the evaluation model of the evaluation system comprises: an industry classification model, a sentiment model, a question classification model and an industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target.

[0072] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0073] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the analysis method based on user evaluation data provided by the above-mentioned methods, and the method includes: obtaining user evaluation data for a target object, and performing data cleaning on the user evaluation data to obtain valid evaluation data; inputting the valid evaluation data into each evaluation model of an evaluation system to obtain an evaluation result of each evaluation model; based on the weight corresponding to the evaluation target, performing weighted calculation on the evaluation result to obtain an evaluation score; wherein the evaluation model of the evaluation system includes: an industry grading model, a sentiment model, a question classification model, and an industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target.

[0074] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned analysis methods based on user evaluation data, the methods comprising: obtaining user evaluation data for a target object, and performing data cleaning on the user evaluation data to obtain valid evaluation data; inputting the valid evaluation data into each evaluation model of an evaluation system to obtain an evaluation result of each evaluation model; performing weighted calculation on the evaluation result based on the weight corresponding to the evaluation target to obtain an evaluation score; wherein the evaluation models of the evaluation system include: an industry grading model, a sentiment model, a question classification model, and an industry label model; the evaluation score is used to characterize the evaluation level of the evaluation target.

[0075] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An analysis method based on user evaluation data, characterized in that: include: Acquire user evaluation data for the target object, and perform data cleaning on the user evaluation data to obtain valid evaluation data; Inputting the effective evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; Based on the weights corresponding to the evaluation targets, weighted calculation is performed on the evaluation results to obtain an evaluation score; The evaluation score is used to represent the evaluation level of the evaluation target.

2. The analysis method based on user evaluation data according to claim 1, characterized in that: The step of performing data cleaning on the user evaluation data to obtain valid evaluation data includes: Inputting the user evaluation data into a natural language model, and controlling the natural language model to clean the user evaluation data based on preset cleaning prompt words to obtain the valid evaluation data; The data cleaning is used to identify and remove invalid information in the user evaluation data.

3. The analysis method based on user evaluation data according to claim 1, characterized in that: The effective evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: Input the valid evaluation data into the industry classification model of the evaluation system, identify the industry to which the valid evaluation data belongs through the industry classification model, and divide each user evaluation data into multiple industries according to the industry identification result and the industry code to obtain the industry classification result; The industry identification result includes: multiple industries to which the content contained in the valid evaluation data belongs; and the industry code is used to indicate the industry category of each industry in the multiple industries.

4. The analysis method based on user evaluation data according to claim 1, characterized in that: The effective evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: Inputting the valid evaluation data into the sentiment model of the evaluation system, and performing sentiment classification on the content described in each user comment through the sentiment model to obtain a sentiment classification result; The sentiment model is used to divide each user evaluation data in the valid evaluation data into any one of the following items: positive sentiment, neutral sentiment and negative sentiment.

5. The analysis method based on user evaluation data according to claim 1, characterized in that: The effective evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: The valid evaluation data is input into the question classification model of the evaluation system, and the valid evaluation data is classified based on the questions fed back by the users to obtain the question classification results.

6. The analysis method based on user evaluation data according to claim 1, characterized in that: The effective evaluation data is input into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model, including: The valid evaluation data is input into the industry label model of the evaluation system, and each user evaluation data in the valid evaluation data is labeled using the industry label model to obtain a multi-level industry label corresponding to each user evaluation data.

7. The analysis method based on user evaluation data according to any one of claims 1 to 6, characterized in that: The weighted calculation of the evaluation results based on the weights corresponding to the evaluation targets to obtain the evaluation scores includes: Obtaining a weight set corresponding to the evaluation target from the target comparison table, and performing weighted calculation on the evaluation result of each evaluation model based on each weight in the weight set to obtain the evaluation score; Among them, the weight set includes: the weight value corresponding to each evaluation indicator in the evaluation result of each evaluation model; the target comparison table contains the weight set corresponding to each evaluation target, and one evaluation target corresponds to one weight set.

8. An analysis device based on user evaluation data, characterized in that: The device comprises: A data processing module is used to obtain user evaluation data for a target object and clean the user evaluation data to obtain valid evaluation data; A data evaluation module, used for inputting the effective evaluation data into each evaluation model of the evaluation system to obtain the evaluation result of each evaluation model; An evaluation calculation module, used to perform weighted calculation on the evaluation results based on the weights corresponding to the evaluation targets to obtain evaluation scores; The evaluation score is used to represent the evaluation level of the evaluation target.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the analysis method based on user evaluation data as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the analysis method based on user evaluation data as claimed in any one of claims 1 to 7 are implemented.

Images