Data quality determination method and device

Abstract

The present invention discloses a data quality determination method, comprising: determining a data quality definition model corresponding to a target object according to a basic model; determining quality assessment parameters of the data to be evaluated of the target object according to the data quality definition model; inputting the data to be evaluated and the quality assessment parameters into a data quality calculation model to obtain the data quality of the data to be evaluated. The present invention also discloses a data quality determination device.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method and device for determining data quality. Background Art

[0002] As more and more smart electrical appliances enter people's lives, the types and amount of data collected by the big data system based on smart cooking equipment have shown an explosive growth, and data quality management is becoming more and more important. Most of them determine the data quality of the data to be evaluated based on the established data quality specifications, and the above data quality determination methods are not accurate and reasonable enough. Summary of the invention

[0003] The embodiments of the present invention provide a method and device for determining data quality.

[0004] The technical solution of the present invention is achieved in this way:

[0005] In one aspect, a method for determining data quality is provided, comprising:

[0006] According to the basic model, determine the data quality definition model corresponding to the target object;

[0007] Determining quality assessment parameters of the target object's to-be-assessed data according to the data quality definition model;

[0008] The data to be evaluated and the quality evaluation parameters are input into a data quality calculation model to obtain the data quality of the data to be evaluated.

[0009] Furthermore, determining the quality assessment parameters of the target object's to-be-assessed data according to the data quality definition model includes:

[0010] Determine, according to the data quality definition model, a quality assessment dimension of the to-be-assessed data of the target object, wherein the quality assessment dimension includes: at least one of an accuracy dimension, a consistency dimension, a completeness dimension, and a timeliness dimension;

[0011] Obtain the quality assessment parameter corresponding to the quality assessment dimension.

[0012] Furthermore, the step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes:

[0013] Based on the data to be evaluated and the quality assessment parameter of the accuracy dimension, a measurement value of the accuracy dimension of the data to be evaluated is determined.

[0014] and / or,

[0015] The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes:

[0016] Based on the data to be evaluated and the quality assessment parameter of the consistency dimension, a consistency dimension measurement value of the data to be evaluated is determined.

[0017] and / or,

[0018] The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes:

[0019] Based on the data to be evaluated and the quality assessment parameters of the integrity dimension, a measure value of the integrity dimension of the data to be evaluated is determined.

[0020] and / or,

[0021] The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes:

[0022] Based on the quality assessment parameters of the timeliness dimension of the data to be evaluated, a timeliness dimension measurement value of the data to be evaluated is determined.

[0023] Furthermore, the data to be evaluated and the quality evaluation parameters are input into a data quality calculation model to obtain the data quality of the data to be evaluated, including:

[0024] Determine the dimension weights of the data to be evaluated, the dimension weights comprising: at least one of: accuracy dimension weight w1, consistency dimension weight w2, completeness dimension weight w3, and timeliness dimension weight w4;

[0025] Based on the dimension weights of the data to be evaluated and the data to be evaluated, the data quality of the data to be evaluated is determined.

[0026] Furthermore, before determining the data quality definition model corresponding to the target object according to the basic model, the method further includes:

[0027] Determine the variety and type of cooking equipment corresponding to the data to be evaluated;

[0028] Based on the variety and the type, the base model is determined.

[0029] Further, the variety includes cooking methods of cooking equipment;

[0030] and / or,

[0031] The type includes at least one of the following: operation data of the current user, historical data of the user, and attribute information of the cooking device.

[0032] Furthermore, the method further comprises:

[0033] Determine the actual interval between two consecutive reporting times of the data to be evaluated;

[0034] The missing rate of the data to be evaluated is determined based on the set data reporting interval and the actual interval.

[0035] Furthermore, the basic model includes at least one of the following: target objects and mapping relationships between target objects, data collection standard specifications, indicator classification, common indicator definition, and constraint rule specifications.

[0036] The present invention also provides a data quality determination device, comprising:

[0037] A first determining unit, configured to determine a data quality definition model corresponding to a target object according to a basic model;

[0038] A second determining unit, configured to determine quality assessment parameters of the to-be-assessed data of the target object according to the data quality definition model;

[0039] The acquisition unit is used to input the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated.

[0040] Further, the second determination unit is specifically used to determine the quality assessment dimension of the to-be-assessed data of the target object according to the data quality definition model, wherein the quality assessment dimension includes: at least one of: accuracy dimension, consistency dimension, completeness dimension and timeliness dimension;

[0041] Used to obtain the quality assessment parameters corresponding to the quality assessment dimension.

[0042] The data quality determination method and device provided by the present invention determine the data quality definition model corresponding to the target object according to the basic model; determine the quality assessment parameters of the data to be evaluated of the target object according to the data quality definition model; input the data to be evaluated and the quality assessment parameters into the data quality calculation model to obtain the data quality of the data to be evaluated. The present invention determines the data quality definition model corresponding to the target object through the basic model, thereby determining the quality assessment parameters of the data to be evaluated of the target object, and then obtaining the data quality of the data to be evaluated. The data quality of the data to be evaluated in the present invention is determined according to the target object corresponding to the data to be evaluated. Since different target objects often have different data quality requirements, compared with the technical solution of determining the data quality of the data to be evaluated through a unified data quality specification, the present invention can determine different data quality definition models according to the different needs of different target objects, thereby more accurately and reasonably determining the data quality of the data to be evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of a method for determining data quality provided by an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of the structure of a data quality determination device provided by an embodiment of the present invention;

[0045] Figure 3 A schematic diagram of the structure of another data quality determination device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the embodiments of the present invention more clearly understood, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0047] Figure 1 A flow chart of a method for determining data quality provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the data quality determination method includes the following steps:

[0048] Step 101: Determine a data quality definition model corresponding to a target object according to a basic model;

[0049] Step 102: Determine the quality assessment parameters of the to-be-assessed data of the target object according to the data quality definition model;

[0050] Step 103: input the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated.

[0051] The present invention is mainly aimed at data quality management of intelligent electrical appliances, which include: intelligent rice cookers, intelligent water heaters, intelligent washing machines, etc.

[0052] Optionally, the basic model includes at least one of the following: target objects and mapping relationships between target objects, data collection standard specifications, indicator classification, common indicator definition, and constraint rule specifications.

[0053] The basic model may include target objects and mapping relationships between target objects. The mapping relationships between target objects and target objects may be determined according to the corresponding relationships between different types (user data, product data), different categories (rice cookers, pressure cookers) and target objects; the basic model may also include the corresponding relationship between target objects and quality definition models; the basic model may also include: data collection standard specifications, indicator classification, general indicator definition, constraint rule specifications, among which the constraint rule specifications include the definition of default values ​​for different numerical types.

[0054] Before determining the data quality definition model corresponding to the target object according to the basic model, the method further includes:

[0055] Determine the variety and type of cooking equipment corresponding to the data to be evaluated;

[0056] Based on the variety and the type, the base model is determined.

[0057] The types of the above-mentioned cooking equipment include the cooking methods of the cooking equipment. For example, the cooking method of the rice cooker is boiling, and the cooking method of the electric baking pan is baking. The types of the above-mentioned cooking equipment include at least one of the following: the operation data of the current user, the historical data of the user, and the attribute information of the cooking equipment. The historical data of the user can be the statistical data of the user within a week, or it can be the statistical data of the user within a month. The time period corresponding to the historical data of the user can be set according to specific needs.

[0058] The target object is the object to which the data quality is to be determined. For example, if the data quality is to be determined is the fire power and temperature of the rice cooker, then the corresponding target object is the rice cooker; if the data quality is to be determined is the set temperature and actual temperature of the water heater, then the corresponding target object is the water heater.

[0059] The data quality definition model defines data quality specifications, which are the basis and foundation for data quality analysis and evaluation. Data quality specifications can be described using different dimensions of quality characteristics, such as data accuracy, data consistency, data integrity, data timeliness, data validity, data usefulness, data legitimacy, and other dimensional characteristics.

[0060] The quality assessment parameters are parameters defined in the data quality definition model for evaluating data quality. The quality assessment parameters can first determine the different dimensions corresponding to the target object based on the business characteristics, and then further determine according to the different dimensions, and can be divided into the first type of parameters and the second type of parameters. The first type of parameters can be indicator feature information determined based on the business. The second type of parameters can be a scoring standard determined based on the correspondence between the data to be evaluated and the business indicator type parameters. For example: to evaluate the accuracy of the firepower data of the rice cooker, the target object is the rice cooker, the indicator name is firepower, and the corresponding first type of parameters can be: data value range 0~200. The data value range 0~200 is determined according to the business characteristics shown in the use of the rice cooker; the corresponding second type of parameters can be a scoring standard determined based on the distribution of the firepower data of the rice cooker in the corresponding data value range.

[0061] It should be noted that when the target object is kitchen equipment, the target object focuses more on the data quality of cooking effects, such as data on firepower, temperature, cooking method, cooking time, etc. The data in the above aspects are different from the data of interest of target objects in other fields. Therefore, the basic model and data quality definition model involved in the embodiment of the present invention are different from the models in traditional fields.

[0062] Since different target objects and mapping relationships between objects are defined in the basic model, and different data quality definition models are established according to different target objects and their mapping relationships, to determine the quality of the data, the corresponding data quality definition model can be determined based on the basic model corresponding to the target object to which it belongs, so as to finally obtain the data quality of the data to be evaluated based on the data quality specifications in the determined data quality definition model.

[0063] The data quality calculation model can obtain the data quality of the data to be evaluated based on the data to be evaluated and the quality evaluation parameters. The data quality of the data to be evaluated can be expressed as a score, such as 90, 80, etc., or as different levels, such as excellent, good, etc.

[0064] The above-mentioned data to be evaluated can come from the after-sales system, sales system, and production system of the smart appliance manufacturer, or from the smart appliance equipment in use by users, so as to timely collect and analyze the data quality generated by each link in the manufacturer's production and the actual use of the smart appliance equipment by users, timely discover various data quality problems, and deal with them to reduce the occurrence of more serious consequences due to data quality problems.

[0065] The above-mentioned data to be evaluated can be the specific data of the electrical equipment obtained by the smart electrical equipment based on the sensor at a fixed time, or it can be the data uploaded to the data quality system for analysis when the specific data obtained by the smart electrical equipment based on the sensor exceeds a certain set threshold. Through the above-mentioned scheme, the actual data of the smart electrical equipment in use can be flexibly collected and analyzed, and some abnormal situations that occur during the use of the electrical equipment can be paid attention to, so as to continuously improve the product in the subsequent product development process to improve the user experience.

[0066] The above-mentioned data to be evaluated can be actively reported to the data quality determination system by intelligent electrical equipment or various production systems at a certain period, or the data quality determination system can extract data at a certain period, or it can be extracted from various production systems to the data quality determination system through processing tools such as data extraction, transformation and loading (ETL). The above-mentioned multiple data collection methods can be flexibly selected according to the specific data environment and network conditions to reasonably allocate system and network resources.

[0067] Optionally, the step 103 further includes the following steps:

[0068] The data to be evaluated is cleaned.

[0069] The above-mentioned data cleaning mainly includes processing invalid values ​​and missing values ​​in the data to be evaluated. Invalid values ​​and missing values ​​can be modified and recorded according to the source and statistical characteristics of the data to reduce the situation where the data to be evaluated cannot accurately correspond to the basic data model, thereby affecting the following data quality parameter determination process.

[0070] Optionally, the basic model includes defining different data collection cycles for relevant data of different target objects. The urgency of collecting and analyzing relevant data of different target objects is often different. For example, the intelligent air-conditioning equipment in the intensive care unit of a hospital needs to be collected and analyzed more strictly, and the temperature and humidity of the intelligent air-conditioning equipment can be collected every five minutes or every ten minutes; correspondingly, the intelligent air-conditioning equipment in a family does not need to be collected and analyzed more strictly, and the temperature and humidity of the intelligent air-conditioning equipment can be collected every half an hour or every hour. Specifically, the data that needs to be collected and analyzed more strictly needs to have a shorter collection cycle, while the data that does not need to be collected and analyzed more strictly needs to have a longer collection cycle. Therefore, defining different data collection cycles for relevant data of different target objects is conducive to formulating different collection strategies for different target objects according to actual needs, so as to achieve rational use of resources.

[0071] Optionally, the step 103 further includes the following steps:

[0072] Based on the data quality of the data to be evaluated, an alarm is issued.

[0073] If the data quality of the data to be evaluated is lower than a set threshold, it means that the corresponding smart electrical device is likely to be in an abnormal state. In order to avoid further losses to users and manufacturers, an alarm needs to be issued in time so that the problem can be dealt with as soon as possible.

[0074] Furthermore, the step 102 includes:

[0075] Determine, according to the data quality definition model, a quality assessment dimension of the to-be-assessed data of the target object, wherein the quality assessment dimension includes: at least one of an accuracy dimension, a consistency dimension, a completeness dimension, and a timeliness dimension;

[0076] Obtain the quality assessment parameter corresponding to the quality assessment dimension.

[0077] The quality assessment dimensions can be determined based on business characteristics, actual needs and statistical characteristics of data, and may include: data accuracy, data consistency, data completeness, data timeliness, data validity, data usefulness, data legality, etc.

[0078] The data quality definition model defines specifications of different dimensions for different target objects. Different data to be evaluated can be evaluated based on specifications of different dimensions. The data quality of the data to be evaluated is a comprehensive measurement based on multiple dimensions, thereby more comprehensively reflecting the quality of the data to be evaluated.

[0079] Furthermore, the step 103 includes:

[0080] Based on the data to be evaluated and the quality assessment parameter of the accuracy dimension, a measurement value of the accuracy dimension of the data to be evaluated is determined.

[0081] The accuracy dimension measurement value is: the measurement value determined by measuring according to the accuracy dimension specification defined in the data quality definition model, which can be expressed as a specific numerical value.

[0082] The data quality definition model defines the accuracy dimension specification. The accuracy of data is used to reflect the precision and reliability of data. The indicators used to measure the accuracy of data include but are not limited to the accuracy rate and / or unreliability rate of data. The accuracy of data refers to whether the data objectively reflects the business characteristics, which can be reflected in whether the data value threshold of each indicator is accurate. In the data quality definition model, a model definition table is established for each type of data, including: indicator name, value type and data value threshold.

[0083] The following table is a rice cooker model definition representation provided by an embodiment of the present invention. It can be seen that the target object is the data to be evaluated for the rice cooker, the corresponding value type and value range, so as to determine whether the data to be evaluated is accurate, and determine the data accuracy rate based on whether the data is accurate. Specifically, data accuracy rate = accurate data amount / total data amount.

[0084]

[0085]

[0086] The following table is a schematic diagram of a data accuracy and score mapping provided by an embodiment of the present invention. Through the following table, the score corresponding to the accuracy rate can be accurately determined, thereby determining the accuracy dimension measurement value of the data to be evaluated with the target object being the rice cooker.

[0087] Accuracy score 100％ 100 99％～100％ 99 … …

[0088] Furthermore, the step 103 further includes:

[0089] Based on the data to be evaluated and the quality assessment parameter of the consistency dimension, a consistency dimension measurement value of the data to be evaluated is determined.

[0090] The consistency dimension measurement value is: the measurement value determined by measuring according to the consistency dimension specification defined in the data quality definition model, which can be expressed as a specific numerical value.

[0091] The consistency dimension specification is defined in the data quality definition model. The consistency of data is used to reflect the consistency of the business relationship expressed by the data. Data consistency can be determined based on data differences and data contradictions between different systems. Data verification conditions are set according to some related data, such as sales volume>activated user volume>active user volume, where sales volume is the overall sales volume of a target object, the number of activated users is the number of registered users who use the corresponding target object online, and the number of active users is the number of users who show a certain interest in the target object among the activated users of the corresponding target object. Active users can be determined based on the number of user posts, the number of user logins and time, etc.; for another example, production volume>sales volume, where production volume is the total production volume of a target object, and sales volume is the overall sales volume of the corresponding target object. Then determine the consistency rate of the data to be evaluated. Specifically, data consistency rate = number of consistent conditions / total number of verification conditions.

[0092] The following table is a schematic diagram of a data consistency rate and score mapping provided by an embodiment of the present invention. Through the following table, the consistency dimension measurement value of the data to be evaluated can be accurately determined.

[0093]

[0094]

[0095] Furthermore, the step 103 further includes:

[0096] Based on the data to be evaluated and the quality assessment parameters of the integrity dimension, a measure value of the integrity dimension of the data to be evaluated is determined.

[0097] The integrity dimension measurement value is: the measurement value determined by measuring according to the integrity dimension specification defined in the data quality definition model, which can be expressed as a specific numerical value.

[0098] Furthermore, the method further comprises:

[0099] Determine the actual interval between two consecutive reporting times of the data to be evaluated;

[0100] Based on the set data reporting interval and the actual interval, determine the missing rate of the data to be evaluated. The integrity dimension specification is defined in the data quality definition model. The integrity of the data is used to reflect the completeness of the data. The indicators used to measure the completeness of the data include but are not limited to the missing rate and / or completeness rate of the data. The higher the missing rate of the data, the lower the completeness rate. The integrity of the data mainly includes: checking whether the continuously reported data is lost during the use of smart electrical equipment. By comparing the interval time H1 between two consecutive data reporting times with the specified data reporting interval time H2, the number of missing items can be calculated by H1 / H2, and then the consistency rate of the data to be evaluated can be determined. Specifically, the data missing rate = number of missing items / total amount of data.

[0101] The following table is a schematic diagram of a data missing rate and score mapping provided by an embodiment of the present invention. Through the following table, the integrity dimension measurement value of the data to be evaluated can be accurately determined.

[0102] Missing rate score 0～1％ 99 0～2％ 98 … …

[0103] Furthermore, the step 103 further includes:

[0104] Based on the quality assessment parameters of the timeliness dimension of the data to be evaluated, a timeliness dimension measurement value of the data to be evaluated is determined.

[0105] The timeliness dimension measurement value is: the measurement value determined by measuring according to the timeliness dimension specification defined in the data quality definition model, which can be expressed as a specific numerical value.

[0106] The timeliness dimension specification is defined in the data quality definition model. Data timeliness is used to reflect the degree of delay in data entering the system. The indicators used to measure data timeliness include but are not limited to data delay rate and / or timeliness rate. The higher the degree of data delay, the worse the data timeliness. The timeliness of data can be determined based on the difference between the data reporting time T1 and the final data storage time T2. If the difference between T1 and T2 is greater than the set threshold, it indicates a delay. Then determine the consistency rate of the data to be evaluated. Specifically, data delay rate = delayed data volume / total data volume.

[0107] The following table is a schematic diagram of a data delay rate and score mapping provided by an embodiment of the present invention. Through the following table, the timeliness dimension measurement value of the data to be evaluated can be accurately determined.

[0108] Delay Rate score 0～1％ 99 0～2％ 98 … …

[0109] Furthermore, the step 103 further includes:

[0110] Determine the dimension weights of the data to be evaluated, the dimension weights comprising: at least one of: accuracy dimension weight w1, consistency dimension weight w2, completeness dimension weight w3, and timeliness dimension weight w4;

[0111] Based on the dimension weights of the data to be evaluated and the data to be evaluated, the data quality of the data to be evaluated is determined.

[0112] It should be noted that the weight corresponding to each dimension can be determined according to actual business needs and the importance of each dimension, so that the data quality of the data to be evaluated can reflect the data quality more reasonably and effectively.

[0113] A specific implementation method is given below. The scores of data accuracy, data consistency, data completeness, and data timeliness are set as s1, s2, s3, and s4, respectively, and the weights are w1, w2, w3, and w4, respectively. S1, s2, s3, and s4 can be obtained through the above mapping table. The final data quality score s is calculated as:

[0114] s=s1*w1+s2*w2+s3*w3+s4*w4.

[0115] Calculation results are stored in the database: The score values ​​of various types of data can be calculated through the data quality scoring calculation model and the data of the big data platform and written into the database.

[0116] Scoring result display: The scoring results are displayed on the web or mobile terminal for data managers and data users to view.

[0117] Figure 2A schematic diagram of the structure of a data quality determination device provided in an embodiment of the present invention includes:

[0118] A first determining unit 201 is used to determine a data quality definition model corresponding to a target object according to a basic model;

[0119] A second determining unit 202 is used to determine the quality assessment parameters of the to-be-assessed data of the target object according to the data quality definition model;

[0120] The acquisition unit 203 is used to input the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated.

[0121] Further, the second determination unit 202 is specifically configured to determine the quality assessment dimension of the to-be-assessed data of the target object according to the data quality definition model, wherein the quality assessment dimension includes: at least one of an accuracy dimension, a consistency dimension, a completeness dimension, and a timeliness dimension;

[0122] Used to obtain the quality assessment parameters corresponding to the quality assessment dimension.

[0123] Furthermore, the second determining unit 202 is further configured to determine a measurement value of the accuracy dimension of the data to be evaluated based on the data to be evaluated and the quality assessment parameter of the accuracy dimension.

[0124] Furthermore, the second determining unit 202 is further configured to input the data to be evaluated and the quality evaluation parameter into a data quality calculation model to obtain the data quality of the data to be evaluated, including:

[0125] Based on the data to be evaluated and the quality assessment parameter of the consistency dimension, a consistency dimension measurement value of the data to be evaluated is determined.

[0126] Furthermore, the second determining unit 202 is further configured to input the data to be evaluated and the quality evaluation parameter into a data quality calculation model to obtain the data quality of the data to be evaluated, including:

[0127] Based on the data to be evaluated and the quality assessment parameters of the integrity dimension, a measure value of the integrity dimension of the data to be evaluated is determined.

[0128] Furthermore, the second determining unit 202 is further configured to determine a timeliness dimension measurement value of the data to be evaluated based on a quality assessment parameter of the timeliness dimension of the data to be evaluated.

[0129] Furthermore, the acquisition unit 203 is specifically configured to input the data to be evaluated and the quality evaluation parameter into a data quality calculation model to obtain the data quality of the data to be evaluated, including:

[0130] Determine the dimension weights of the data to be evaluated, the dimension weights comprising: at least one of: accuracy dimension weight w1, consistency dimension weight w2, completeness dimension weight w3, and timeliness dimension weight w4;

[0131] Used to determine the data quality of the data to be evaluated based on the dimension weight of the data to be evaluated and the data to be evaluated.

[0132] Figure 3 A schematic diagram of the structure of another data quality determination device provided in an embodiment of the present invention includes: a data quality scoring module, a calculation module, and a scoring display module.

[0133] Data quality scoring module: Establish a data quality scoring model, including the basic model, data quality definition model, and data quality scoring calculation model.

[0134] Calculation module: performs calculations based on the model and data, and writes the results into the database.

[0135] Rating display module: displays the rating data on a web page or mobile terminal.

[0136] The data quality determination device also mainly includes four modules: a data acquisition module, a calculation module, a control module, and a prompt module.

[0137] Data collection module: used to collect data from the smart electrical devices currently being used by users and the production libraries of electrical appliance manufacturers, and put it into the data quality determination system.

[0138] Calculation module: performs calculations based on the model and data, and writes the results into the database.

[0139] Control module: schedules and controls the normal operation of other modules.

[0140] Prompt module: If the data quality of the data to be evaluated is lower than a set threshold, an alarm will be issued.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for determining data quality, characterized in that: Applied to intelligent electrical equipment, the method comprises: Determine a data quality definition model corresponding to the target object according to the basic model; the basic model includes the target object and the mapping relationship between the target objects; the mapping relationship between the target object and the target object is determined according to the type of the smart electrical device and the corresponding relationship between the category of the smart electrical device and the target object; According to the data quality definition model, quality assessment parameters of the target object's data to be assessed are determined; the quality assessment parameters include first-category parameters and second-category parameters; the first-category parameters are indicator feature information determined based on the business; the second-category parameters are scoring criteria determined based on the correspondence between the data to be assessed and the business indicator parameters; Inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated; The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes: Determine the dimension weights of the data to be evaluated, the dimension weights comprising: at least one of: accuracy dimension weight w1, consistency dimension weight w2, completeness dimension weight w3, and timeliness dimension weight w4; Determining the data quality of the data to be evaluated based on the dimension weights of the data to be evaluated and the data to be evaluated; Before determining the data quality definition model corresponding to the target object according to the basic model, the method further includes: Determine the type of cooking equipment and cooking equipment corresponding to the data to be evaluated; Determining the basic model based on the variety and the type; The variety includes cooking methods of cooking equipment; and / or, The type includes at least one of the following: operation data of the current user, historical data of the user, and attribute information of the cooking device.

2. The method according to claim 1, characterized in that Determining the quality assessment parameters of the target object's to-be-assessed data according to the data quality definition model includes: Determine, according to the data quality definition model, a quality assessment dimension of the to-be-assessed data of the target object, wherein the quality assessment dimension includes: at least one of an accuracy dimension, a consistency dimension, a completeness dimension, and a timeliness dimension; Obtain the quality assessment parameter corresponding to the quality assessment dimension.

3. The method according to claim 1, characterized in that The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes: Determining a measurement value of the accuracy dimension of the data to be evaluated based on the data to be evaluated and the quality evaluation parameter of the accuracy dimension; and / or, The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes: Determining a consistency dimension measurement value of the data to be evaluated based on the data to be evaluated and the quality assessment parameter of the consistency dimension; and / or, The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes: Determine the integrity dimension measurement value of the data to be evaluated based on the quality assessment parameters of the data to be evaluated and the integrity dimension; and / or, The step of inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated includes: Based on the quality assessment parameters of the timeliness dimension of the data to be evaluated, a timeliness dimension measurement value of the data to be evaluated is determined.

4. The method according to claim 1, characterized in that: The method further comprises: Determine the actual interval between two consecutive reporting times of the data to be evaluated; The missing rate of the data to be evaluated is determined based on the set data reporting interval and the actual interval.

5. The method according to claim 1, characterized in that The basic model includes at least one of the following: target objects and mapping relationships between target objects, data collection standard specifications, indicator classification, general indicator definition, and constraint rule specifications.

6. A data quality determination device, characterized in that: Applied to intelligent electrical equipment, the device comprises: A first determination unit is used to determine a data quality definition model corresponding to a target object according to a basic model; the basic model includes the target object and a mapping relationship between target objects; the mapping relationship between the target object and the target object is determined according to the type of the smart electrical device and the corresponding relationship between the category of the smart electrical device and the target object; A second determination unit is used to determine the quality assessment parameters of the data to be assessed of the target object according to the data quality definition model; the quality assessment parameters include first-category parameters and second-category parameters; the first-category parameters are indicator feature information determined based on the business; the second-category parameters are scoring criteria determined based on the correspondence between the data to be assessed and the business indicator parameters; An acquisition unit, used for inputting the data to be evaluated and the quality evaluation parameters into a data quality calculation model to obtain the data quality of the data to be evaluated; Wherein, the acquisition unit is used to input the data to be evaluated and the quality assessment parameters into the data quality calculation model to obtain the data quality of the data to be evaluated, including: determining the dimension weight of the data to be evaluated, the dimension weight including: at least one of the accuracy dimension weight w1, the consistency dimension weight w2, the integrity dimension weight w3, and the timeliness dimension weight w4; and determining the data quality of the data to be evaluated based on the dimension weight of the data to be evaluated and the data to be evaluated; The first determination unit is also used to determine the variety of cooking equipment and the type of cooking equipment corresponding to the data to be evaluated; determine the basic model based on the variety and the type; the variety includes the cooking method of the cooking equipment; and / or the type includes at least one of the following: the current user's operating data, the user's historical data, and the attribute information of the cooking equipment.

7. The device according to claim 6, characterized in that The second determination unit is specifically configured to determine the quality assessment dimension of the to-be-assessed data of the target object according to the data quality definition model, wherein the quality assessment dimension includes: at least one of an accuracy dimension, a consistency dimension, a completeness dimension, and a timeliness dimension; Used to obtain the quality assessment parameters corresponding to the quality assessment dimension.

Images