Data auditing method applied to market research

Abstract

The invention relates to the technical field of data auditing, in particular to a data auditing method applied to market research, which comprises the following steps of: 1, receiving business data sent by a server, and obtaining content data uploaded by a target user; 2, dividing research fields of market investigation according to the investigation direction and the investigation method; 3, preprocessing the obtained content data of the target user; 4, extracting data features, and constructing a multi-dimensional data auditing model; and 5, generating a questionnaire according to an audit result through the data manager, and uploading the questionnaire to the cloud processing terminal. According to the method, invalid data can be removed by preprocessing the obtained content data of the target user so as to improve the data quality, and research fields of market research are divided by determining the research direction and the investigation method, so that research standard indexes and index standard options of the research fields are conveniently formulated, a research standard library is formed, and the research efficiency is improved. And the investigation efficiency and the data accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data auditing, and in particular to a data auditing method applied to market research. Background Art

[0002] Market research uses scientific methods to purposefully and systematically collect, organize, and analyze various information and materials about supply and demand resources. It is an important basis for companies to make decisions on market strategies, product development, brand promotion, and other aspects. In the process of market research, it is usually necessary to review and analyze a large amount of collected data to obtain valuable market information. Data review is an important part of controlling and ensuring data quality. It mainly involves identifying and correcting errors, omissions, and other problems in the data to ensure the accuracy and reliability of the data. Market research is an indispensable part of market forecasting and business decision-making.

[0003] Traditional data audit methods mostly rely on manual review, which is not only inefficient but also easily affected by human factors, making it difficult to ensure the accuracy and completeness of the data, thus leading to a decline in the quality of survey data. Therefore, it is necessary to develop a data audit method for market research. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the deficiencies in the prior art, the present invention provides a data review method for market research, which has the advantages of high efficiency and good accuracy, and solves the above-mentioned problems.

[0006] (II) Technical solution

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A data review method for market research includes the following steps:

[0009] Step 1: Receive business data sent by the server and obtain content data uploaded by the target user;

[0010] Step 2: Divide the research areas of market research according to the research direction and survey method;

[0011] Step 3: pre-processing the acquired content data of the target user;

[0012] Step 4: Extract data features and build a multi-dimensional data audit model;

[0013] Step 5: The audit results are generated by the data manager and the questionnaire is uploaded to the cloud processing terminal;

[0014] Step 6: Manual review;

[0015] Step 7: Data output and model optimization.

[0016] Preferably, the step one also includes obtaining target behavior characteristics of the target user.

[0017] Preferably, the step 2 also includes formulating research standard indicators and indicator standard options for each research field to form a research standard library.

[0018] Preferably, the preprocessing in step three includes parsing the data structure and reviewing the target data.

[0019] Preferably, the data feature extraction in step four utilizes a machine learning algorithm to extract features related to data quality, and the construction of a multi-dimensional data audit model is a model for judging the authenticity of the survey data based on the extracted data features and constructed using a machine learning algorithm.

[0020] Preferably, the manual review in step six is ​​performed by manually reviewing and confirming the erroneous data and abnormal data marked in the rule engine review step to ensure the accuracy and completeness of the survey data.

[0021] Preferably, the data output in step seven is performed through a visual report or a data analysis tool. After the manual review is completed, the model optimization is adjusted to the rule engine and the multi-dimensional data audit model according to the manual review results to improve the accuracy of the rule engine and the multi-dimensional data audit model.

[0022] (III) Beneficial effects

[0023] Compared with the prior art, the present invention provides a data review method for market research, which has the following beneficial effects:

[0024] 1. The present invention can remove invalid data to improve data quality by pre-processing the content data of the acquired target users. By determining the research direction and investigation method, the research field of market research is divided, thereby facilitating the formulation of research standard indicators and indicator standard options for each research field, forming a research standard library, and improving research efficiency and data accuracy.

[0025] 2. The present invention uses machine learning algorithms to extract features related to data quality through data feature extraction, and constructs a multi-dimensional data audit model to use the extracted data features to construct a model for judging the authenticity of the survey data using machine learning algorithms, thereby effectively improving the quality of data audit. DETAILED DESCRIPTION

[0026] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] The present invention relates to a data review method applied to market research, comprising the following steps:

[0028] Step 1: Receive business data sent by the server and obtain content data uploaded by the target user;

[0029] It also includes obtaining target behavior characteristics of target users;

[0030] Step 2: Divide the research areas of market research according to the research direction and survey method;

[0031] It also includes formulating research standard indicators and indicator standard options for each research field to form a research standard library;

[0032] Step 3: Preprocess the acquired content data of the target user, including analyzing the data structure, reviewing the target data, and cleaning, denoising and formatting the data;

[0033] Step 4: Extract data features and build a multi-dimensional data audit model. Data feature extraction uses machine learning algorithms to extract features related to data quality. The multi-dimensional data audit model is a model that uses machine learning algorithms to judge the authenticity of survey data based on the extracted data features.

[0034] Step 5: The audit results are generated by the data manager and the questionnaire is uploaded to the cloud processing terminal;

[0035] Step 6: Manual review: Manual review involves manually reviewing and confirming the erroneous data and abnormal data marked in the rule engine review step to ensure the accuracy and completeness of the survey data.

[0036] Step 7: Data output and model optimization. Data output is performed through visual reports or data analysis tools. After the manual review is completed, the model optimization is adjusted according to the manual review results to improve the accuracy of the rule engine and the multi-dimensional data audit model. For the target security level corresponding to the target user, if the target security level corresponding to the target user is higher, it can be considered that the content data uploaded by the target user is more likely to be high-quality data, and the content data uploaded by the target user can be inserted at the head of the data audit queue.

[0037] According to the needs of market research, relevant data is collected, including but not limited to information such as consumer demand, product performance, and market trends. The original data collected in the data collection step includes various types of data such as text, numbers, and images. The collection methods in the data collection step include using crawler technology to capture data related to the research objectives from data sources such as social media, e-commerce platforms, and news websites, using questionnaires, interview records, and online searches.

[0038] The staff can also adjust and optimize the dimensional data audit and rule engine based on the review results to realize the audit of market research data. This method not only improves the efficiency and accuracy of data audit, but also reduces the cost and error rate of manual audit. This data audit method can be applied to various market research scenarios, such as consumer behavior research, product market analysis, competitor analysis, etc. This data audit method can improve the accuracy and reliability of market research data, reduce the risk of data errors and anomalies, and can also output the audited data in the form of visual reports or data analysis tools, thereby helping companies better understand the market and consumer needs and provide more valuable references for corporate decision-making.

[0039] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data audit method for market research, characterized in that: The following steps are involved: Step 1: Receive business data sent by the server and obtain content data uploaded by the target user; Step 2: Divide the research areas of market research according to the research direction and survey method; Step 3: pre-processing the acquired content data of the target user; Step 4: Extract data features and build a multi-dimensional data audit model; Step 5: The audit results are generated by the data manager and the questionnaire is uploaded to the cloud processing terminal; Step 6: Manual review; Step 7: Data output and model optimization.

2. The data review method for market research according to claim 1, characterized in that: The step one also includes obtaining the target behavior characteristics of the target user.

3. The data review method for market research according to claim 1, characterized in that: The step 2 also includes formulating research standard indicators and indicator standard options for each research field to form a research standard library.

4. The data review method for market research according to claim 1, characterized in that: The preprocessing in step three includes parsing the data structure and reviewing the target data.

5. The data review method for market research according to claim 1, characterized in that: The data feature extraction in step 4 utilizes a machine learning algorithm to extract features related to data quality, and the construction of a multi-dimensional data audit model is a model constructed using a machine learning algorithm based on the extracted data features to judge the authenticity of the survey data.

6. The data review method for market research according to claim 1, characterized in that: The manual review in step six is ​​performed by manually reviewing and confirming the erroneous data and abnormal data marked in the rule engine review step to ensure the accuracy and completeness of the survey data.

7. The data review method for market research according to claim 1, characterized in that: The data output in step seven is performed through a visual report or a data analysis tool. After the manual review is completed, the model optimization is performed by adjusting the rule engine and the multi-dimensional data audit model according to the manual review results to improve the accuracy of the rule engine and the multi-dimensional data audit model.