Data processing method, device, electronic device and computer readable medium

Abstract

The embodiments of the present disclosure disclose a data processing method, device, electronic device and computer-readable medium. A specific implementation of the method includes: obtaining a target business data set, data application information and data cost information; generating data disclosure evaluation information; using a data quality evaluation information generation model to generate data quality evaluation information; determining the indicator weights corresponding to each evaluation indicator to obtain an indicator weight set; multiplying the data disclosure evaluation information with the corresponding indicator weight to generate a first multiplication information, and multiplying the data cost information with the corresponding indicator weight in the indicator weight set to generate a second multiplication information; determining the information with the largest value in the first multiplication information and the second multiplication information as the target information; generating data value evaluation information; and performing corresponding value processing operations. This implementation can reasonably perform corresponding value processing operations for accurately determined data value evaluation information.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a data processing method, device, electronic device, and computer-readable medium. Background Art

[0002] At present, with the advent of the big data era, data sets have become one of the important assets of various enterprises. The method usually adopted to generate the value assessment information corresponding to the data set is: relevant technical personnel manually perform value analysis on the data set to generate value assessment information for the data set.

[0003] However, when using the above method to generate value assessment information, the following technical problems often occur:

[0004] Value analysis is cumbersome and time-consuming, and the generated value assessment information is not accurate enough, resulting in large deviations in subsequent value processing operations on the data set.

[0005] In the process of adopting technical solutions to solve the above-mentioned technical problem one, the following technical problem two is often accompanied: how to accurately generate data availability information for the above-mentioned target business data set. For the above-mentioned technical problem two, the conventional solution is generally: relevant technical personnel manually conduct availability analysis to generate data availability information corresponding to the target business data set. However, the above-mentioned conventional solution still has the following problems: availability analysis is cumbersome, time-consuming, and the generated data availability information is not accurate enough, resulting in large deviations in subsequent value processing operations for the data set.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0007] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0008] Some embodiments of the present disclosure propose data processing methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0009] In a first aspect, some embodiments of the present disclosure provide a data processing method, including: obtaining a target business data set, data application information and data cost information for the target business data set; generating data disclosure evaluation information for the target business data set using a data disclosure evaluation information generation model; generating data quality evaluation information for the target business data set using a data quality evaluation information generation model; determining indicator weights corresponding to each evaluation indicator for the target business data set to obtain an indicator weight set; multiplying the data disclosure evaluation information with the corresponding indicator weight in the indicator weight set to generate first multiplication information, and multiplying the data cost information with the corresponding indicator weight in the indicator weight set to generate second multiplication information; determining the information with the largest numerical value between the first multiplication information and the second multiplication information as target information; generating data value evaluation information for the target business data set based on the target information, the data quality evaluation information and the data application information; and performing corresponding value processing operations on the target business data set based on the data value evaluation information.

[0010] In a second aspect, some embodiments of the present disclosure provide a data processing device, including: an acquisition unit, configured to acquire a target business data set, data application information and data cost information for the target business data set; a first generation unit, configured to generate data disclosure evaluation information for the target business data set using a data disclosure evaluation information generation model; a second generation unit, configured to generate data quality evaluation information for the target business data set using a data quality evaluation information generation model; a first determination unit, configured to determine the indicator weights corresponding to the various evaluation indicators for the target business data set to obtain an indicator weight set; a multiplication unit, configured to multiply the above data sets by the weights corresponding to the various evaluation indicators for the target business data set; The first multiplication information is generated by multiplying the public evaluation information with the corresponding indicator weight in the above-mentioned indicator weight set, and the second multiplication information is generated by multiplying the above-mentioned data cost information with the corresponding indicator weight in the above-mentioned indicator weight set; the second determination unit is configured to determine the information with the largest numerical value among the above-mentioned first multiplication information and the above-mentioned second multiplication information as the target information; the third generation unit is configured to generate data value evaluation information for the above-mentioned target business data set according to the above-mentioned target information, the above-mentioned data quality evaluation information and the above-mentioned data application information; the execution unit is configured to perform corresponding value processing operations on the above-mentioned target business data set according to the above-mentioned data value evaluation information.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0013] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the data processing method of some embodiments of the present disclosure, the corresponding value processing operation can be reasonably performed for the accurately determined data value assessment information. Specifically, the reason why the relevant data value assessment information is not accurate enough and the corresponding value processing operation has a large deviation is that the value analysis is cumbersome, the time is wasted for a long time, and the generated value assessment information is not accurate enough, resulting in a large deviation in the subsequent value processing operation for the data set. Based on this, the data processing method of some embodiments of the present disclosure first obtains the target business data set, the data application information and data cost information for the above target business data set as data support for the subsequent determination of data value assessment information. Then, using the data public assessment information generation model, the data public assessment information for the above target business data set can be accurately generated. Here, the obtained data public assessment information is used for the subsequent generation of data value assessment information. Then, using the data quality assessment information generation model, the data quality assessment information for the above target business data set can be accurately generated. Here, from the aspect of data quality, it is helpful to accurately generate data value assessment information in the subsequent period. Next, determine the indicator weights corresponding to each evaluation indicator of the target business data set, and obtain the indicator weight set to determine the indicator importance of the corresponding indicators of each data level corresponding to the target business data set, so as to facilitate the subsequent accurate generation of data value assessment information. Furthermore, multiply the above-mentioned data disclosure assessment information with the corresponding indicator weight in the above-mentioned indicator weight set to generate the first multiplication information, and multiply the above-mentioned data cost information with the corresponding indicator weight in the above-mentioned indicator weight set to generate the second multiplication information. Here, the obtained first multiplication information and second multiplication information can remind the importance of subsequent data value assessment information. Further, determine the information with the largest value in the above-mentioned first multiplication information and the above-mentioned second multiplication information as the target information to determine the preliminary data value for the target business data set. Next, according to the above-mentioned target information, the above-mentioned data quality assessment information and the above-mentioned data application information, the data value assessment information for the above-mentioned target business data set can be accurately generated from many aspects. Finally, according to the above-mentioned data value assessment information, the corresponding reasonable and effective value processing operation is performed on the above-mentioned target business data set. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0015] Figure 1 are flow charts of some embodiments of the data processing method according to the present disclosure;

[0016] Figure 2 is a schematic diagram of the structure of some embodiments of the data processing device according to the present disclosure;

[0017] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] refer to Figure 1 , shows a process 100 of some embodiments of the data processing method according to the present disclosure. The data processing method comprises the following steps:

[0025] Step 101: Acquire a target business data set, data application information and data cost information for the target business data set.

[0026] In some embodiments, the execution subject of the above data processing method can obtain the target business data set, data application information and data cost information for the above target business data set through a wired connection or a wireless connection. Among them, the target business data set is a data set to be valued. In practice, for the credit investigation scenario, the value assessment can be a data asset value assessment. That is, the target business data set can be a data set associated with the target business and to be valued by the data asset. For example, the target business can be a user credit investigation related business. The data application information can be the application information of the relevant data application of the data set. In practice, the data application information can include but is not limited to at least one of the following: the number of calling institutions, the call volume (the amount queried and the amount found), and the number of personal information subjects covered. The data cost information can be the cost information consumed to obtain the target business data set.

[0027] In some optional implementations of some embodiments, the data cost information is determined by the following steps:

[0028] The first step is to obtain direct cost information for the above target business data set. The direct cost information can be the direct data acquisition cost. In practice, for credit investigation scenarios, the direct cost information can be the data procurement cost. The data procurement cost can be calculated based on the data procurement unit price, total price and total volume.

[0029] The second step is to obtain the construction cost information, equipment cost information, processing cost information and risk cost information for the above target business data set. Among them, the construction cost information may include: business system construction cost and data processing platform construction cost. Equipment cost information may include: data storage hardware cost. Processing cost information may include: labor cost and service outsourcing cost. Labor cost can be the cost consumed by data product configuration, data cleaning and integration, data processing and mining, platform operation and maintenance, etc. Risk cost information can be the data risk cost caused by compliance, objection, etc.

[0030] The third step is to add the above direct cost information, the above construction cost information, the equipment cost information, the processing cost information and the risk cost information accordingly to obtain the above data cost information.

[0031] Step 102: Generate data disclosure assessment information for the target business data set using a data disclosure assessment information generation model.

[0032] In some embodiments, the execution entity may generate data disclosure evaluation information for the target business data set using a data disclosure evaluation information generation model. The data disclosure evaluation information generation model may be a neural network model for generating data disclosure evaluation information. The data disclosure evaluation information may be data market evaluation value information corresponding to the target business data set. In practice, the data disclosure evaluation information generation model may be a convolutional neural network model with multiple layers connected in series + a neural network model with a fully connected layer.

[0033] In some optional implementations of some embodiments, the above-mentioned use of the data disclosure evaluation information generation model to generate the data disclosure evaluation information for the above-mentioned target business data set may include the following steps:

[0034] The first step is to obtain the historical value flow information for the target business data set. In practice, the historical value flow information can be the historical transaction price of the target business data set at a historical time.

[0035] The second step is to determine the indicator information set corresponding to the above-mentioned target business data set and whose corresponding indicator importance is greater than the first numerical value. Among them, the indicator information set can be an attribute indicator information set related to the attribute parsed from the target business data set. The indicator importance can represent the importance of the corresponding attribute indicator relative to the target business data set. In practice, the indicator importance can be a numerical value between 0 and 1. The larger the numerical value, the higher the importance. In practice, the indicator importance can be a number between 0 and 1 set for the attribute indicator of the target business data set. The first numerical value can be a pre-set numerical value. For example, the first numerical value can be 0.5.

[0036] The third step is to divide the indicator information in the above indicator information set into indicator importance levels to obtain indicator information group sets, wherein the indicator information in each indicator information group has the same indicator importance level.

[0037] As an example, the execution entity may determine each indicator information with a value between 0 and 0.25 as a first indicator information group, each indicator information with a value between 0.25 and 0.5 as a second indicator information group, each indicator information with a value between 0.5 and 0.75 as a third indicator information group, and each indicator information with a value between 0.75 and 1 as a fourth indicator information group. The first indicator information group, the second indicator information group, the third indicator information group, and the fourth indicator information group are determined as an indicator information group set.

[0038] The fourth step is to randomly extract a predetermined number of indicator information from each indicator information group to obtain an extracted indicator information set.

[0039] As an example, the execution subject may randomly extract 4 from the first indicator information group to obtain a first indicator information subgroup. The execution subject may randomly extract 4 from the second indicator information group to obtain a second indicator information subgroup. The execution subject may randomly extract 4 from the third indicator information group to obtain a third indicator information subgroup. The execution subject may randomly extract 4 from the fourth indicator information group to obtain a fourth indicator information subgroup. The first indicator information subgroup, the second indicator information subgroup, the third indicator information subgroup and the fourth indicator information subgroup are determined as the extracted indicator information set.

[0040] Step 5: According to the extracted indicator information set, determine at least one business data set that meets the indicator similarity condition with the target business data set. The indicator similarity condition may be that the business data set has at least three indicator information that are the same as the corresponding at least three indicator information in the extracted indicator information set.

[0041] Step 6: Determine the actual data public information corresponding to each business data set in the at least one business data set to obtain an actual data public information set. The actual data public information may be actual data set market value information. Specifically, the actual data public information may be market value information of the corresponding business data set in recent transactions.

[0042] The seventh step is to determine the average information corresponding to each piece of actual data public information in the above actual data public information set.

[0043] The eighth step is to divide the above historical value flow information by the above average information to obtain the first candidate data public evaluation information.

[0044] The ninth step is to use the data disclosure evaluation information generation model to generate second candidate data disclosure evaluation information for the target business data set.

[0045] As an example, first, the execution subject may perform data preprocessing on the target business data set to generate a preprocessed data set, and then input the preprocessed data set into the data disclosure evaluation information generation model to generate the second candidate data disclosure evaluation information.

[0046] In the tenth step, the first candidate data public evaluation information is multiplied by the first value to generate a first multiplication result, wherein the first value can represent the difference between the first candidate data public evaluation information and the actual data public evaluation information.

[0047] In the eleventh step, the second candidate data public evaluation information is multiplied by a second value to generate a second multiplication result, wherein the second value can represent the difference between the second candidate data public evaluation information and the actual data public evaluation information.

[0048] Step 12: In response to determining that the difference between the first multiplication result and the second multiplication result is less than a second value, a weighted sum of the first multiplication result and the second multiplication result is determined as data disclosure evaluation information. The second value may be a preset value. For example, the second value may be 4.

[0049] Optionally, in response to determining that the difference between the first multiplication result and the second multiplication result is greater than or equal to a second numerical value, the second multiplication result is determined as data disclosure evaluation information.

[0050] Step 103: Generate data quality assessment information for the target business data set using a data quality assessment information generation model.

[0051] In some embodiments, the execution subject may generate data quality assessment information for the target business data set using a data quality assessment information generation model. The data quality assessment information generation model may be a neural network model for generating data quality assessment information. The larger the data quality assessment information, the better the data quality corresponding to the target business data set.

[0052] In some optional implementations of some embodiments, the above-mentioned use of the data quality assessment information generation model to generate the data quality assessment information for the above-mentioned target business data set may include the following steps:

[0053] The first step is to perform data consistency determination on the target business data set to generate data consistency information, wherein the data consistency determination may be a data format consistency determination.

[0054] As an example, the execution entity may use a pre-written format consistency determination script to perform data consistency determination on the target business data set to generate data consistency information.

[0055] In the second step, the data quality assessment information generation model is used to perform data accuracy verification on the target business data set to generate data accuracy verification information. The data accuracy verification information can represent the accuracy of the target business data set. The data accuracy verification information can include: information representing that the target business data set has passed the data accuracy verification, and information representing that the target business data set has not passed the data accuracy verification.

[0056] As an example, the above-mentioned execution entity can use the multiple convolution models included in the data quality assessment information generation model to perform data accuracy verification on the above-mentioned target business data set to generate data accuracy verification information.

[0057] The third step is to use the data availability determination model included in the data quality assessment information generation model to perform data availability verification on the target business data set to generate data availability information. The data availability information can be extensive information on the data availability domain. In practice, the data availability information can be a numerical value between 0 and 10. The larger the numerical value, the more domain data that characterizes the data availability domain corresponding to the target business data set. The data availability determination model may include: multiple neural network models under multiple domains. There is a one-to-one correspondence between the domains in the multiple domains and the neural network models in the multiple neural network models.

[0058] The fourth step is to perform timeliness verification on the above target business data set to generate data timeliness verification information.

[0059] The timeliness check may measure the timeliness of the data, that is, the update frequency and time delay of the data. The data timeliness check information may be check information indicating whether the target business data set is the latest business data set.

[0060] The fifth step is to perform a credibility check on the target business data set to generate data feasibility verification information, wherein the data credibility verification information may be the credibility of the data.

[0061] Among them, credibility verification can be used to measure the credibility and authority of data, including the credibility of the data source and the transparency of the data collection process.

[0062] The sixth step is to perform data integrity verification on the target business data set to generate data integrity verification information, wherein the data integrity verification information can represent the degree of missingness of each data in the target business data set.

[0063] The seventh step is to digitize the above data consistency information, the above data accuracy verification information, the above data availability information, the above data timeliness verification information, the above data feasibility verification information and the above data integrity verification information to generate data consistency values, data accuracy values, data availability values, data timeliness values, data feasibility values ​​and data integrity values. For specific implementation methods, please refer to the generation of data source scarcity values, data service stability values ​​and docking object feedback values.

[0064] In the eighth step, weighted summation is performed on the above-mentioned data consistency value, the above-mentioned data accuracy value, the above-mentioned data availability value, the above-mentioned data timeliness value, the above-mentioned data feasibility value and the above-mentioned data integrity value to generate data quality assessment information.

[0065] Considering the problems of the above conventional solutions, facing the above technical problem 2: the value analysis is cumbersome, time-consuming, and the generated value assessment information is not accurate enough, resulting in large deviations in the subsequent value processing operations for the data set. Combining the advantages / technical status, we can decide to adopt the following solution.

[0066] In some optional implementations of some embodiments, using the data availability determination model included in the data quality assessment information generation model, performing data availability verification on the target business data set to generate data availability information includes the following steps:

[0067] The first step is to input the above target business data set into the data encoding model included in the above data quality assessment information generation model to generate encoding information and obtain an encoding information set.

[0068] In the second step, the above-mentioned encoded information set is input into the attention mechanism model based on the domain association relationship to generate a related association array corresponding to each encoded information, and obtain a related association array set. Among them, the association coefficient in the related association array has a one-to-one correspondence with the data available domain information in the data available domain information set. Among them, the relationship coefficient can represent the close relationship between the corresponding business data and the corresponding data available domain information. The association coefficient can be a value between 0-1. The larger the value, the closer the relationship between the business data and the corresponding data available domain information.

[0069] The third step is to group the target business data sets into data available domains according to the above association relationship groups to generate target business data sets. Each target business data set in the target business data set has corresponding data available domain information. There may be duplicate business data between each target business data set.

[0070] As an example, for each target business data in the target business data set, first, determine the associated relationship array corresponding to the target business data. Then, filter out the coefficients whose corresponding correlation coefficients are greater than the target value from the associated relationship array to obtain the filtered associated relationship array. Next, place the target business data in the data available field information group corresponding to the filtered associated relationship array. Summarize the business data corresponding to each data available field information to generate a target business data set.

[0071] The fourth step is to perform data enhancement on each target service data group in the target service data group set to generate an enhanced data group, thereby obtaining an enhanced data group set.

[0072] In the fifth step, for each enhanced data group in the enhanced data group set, the enhanced data group is input into the data domain association model corresponding to the data domain information to generate an accuracy rate for the enhanced data group. For example, if the data domain information is the image recognition field, the corresponding data domain association model may be an image recognition model.

[0073] In the sixth step, data available field information having a corresponding accuracy greater than a target value is selected from the above data available field information set to obtain at least one data available field information.

[0074] In the seventh step, the at least one data availability field information is determined as data availability information.

[0075] The above-mentioned contents in some optional implementation methods of some embodiments, as an inventive point of the present disclosure, solve the technical problem mentioned in the background technology that "the value analysis is cumbersome, a long time is wasted, and the generated value assessment information is not accurate enough, resulting in large deviations in the subsequent value processing operations on the data set". Based on this, the present disclosure uses an attention mechanism model based on domain association relationships to achieve a preliminary match between business data and data domain information. Then, the accuracy set for the above-mentioned target business data set is determined through the domain association model set corresponding to the data domain information set. Finally, the accuracy set is used to accurately determine the data available domain information that has an available association relationship with the target business data set, and at least one data available domain information is obtained as data availability information.

[0076] In some optional implementations of some embodiments, the above-mentioned use of the data quality assessment information generation model to generate the data quality assessment information for the above-mentioned target business data set may include the following steps:

[0077] The first step is to perform data encoding on each target business data in the target business data set to generate encoding information and obtain an encoding information set.

[0078] The second step is to input the above-mentioned encoded information set into the feature extraction model set for multiple quality indicators included in the above-mentioned data quality assessment information generation model to generate a feature extraction information set. There is a one-to-one correspondence between the quality indicators in the multiple quality indicators and the feature extraction models in the feature extraction model set. There is a one-to-one correspondence between the feature extraction models in the feature extraction model set and the feature extraction information in the feature extraction information set.

[0079] The third step is to input each feature extraction information in the feature extraction information set into the convolution model under the corresponding quality index to generate quality index information.

[0080] The fourth step is to perform data evaluation on the target business data set according to the obtained quality indicator information set to generate the data quality evaluation information.

[0081] Step 104: determine the indicator weight corresponding to each evaluation indicator of the target business data set to obtain an indicator weight set.

[0082] In some embodiments, the above-mentioned execution entity may determine the indicator weights corresponding to each evaluation indicator for the above-mentioned target business data set to obtain an indicator weight set. Among them, the evaluation indicator may be a relevant indicator for evaluating the value of data. For example, each evaluation indicator may include but is not limited to at least one of the following: a data disclosure evaluation indicator, a data quality evaluation indicator. The data disclosure evaluation indicator corresponds to the data disclosure evaluation information. The data quality evaluation indicator corresponds to the data quality evaluation information. The indicator weight can characterize the indicator importance of the evaluation indicator. For example, the indicator weight corresponding to the data quality evaluation indicator is greater than the indicator weight corresponding to the data disclosure evaluation indicator, and relative to the actual data value information, the importance of the information features related to the data quality evaluation information is greater than the importance of the information features related to the data disclosure evaluation information.

[0083] As an example, the above-mentioned execution entity can use a multi-head attention mechanism model to determine the indicator weights corresponding to each evaluation indicator of the above-mentioned target business data set to obtain an indicator weight set.

[0084] Step 105, multiplying the above-mentioned data disclosure evaluation information with the corresponding indicator weight in the above-mentioned indicator weight set to generate first multiplication information, and multiplying the above-mentioned data cost information with the corresponding indicator weight in the above-mentioned indicator weight set to generate second multiplication information.

[0085] In some embodiments, the execution entity may multiply the data disclosure evaluation information with the corresponding indicator weight in the indicator weight set to generate first multiplication information, and multiply the data cost information with the corresponding indicator weight in the indicator weight set to generate second multiplication information. The indicator weight corresponding to the first multiplication information is the indicator weight corresponding to the data disclosure evaluation information, in the indicator weight set, and corresponding to the data disclosure evaluation indicator. The indicator weight corresponding to the second multiplication information is the indicator weight corresponding to the data cost information, in the indicator weight set, and corresponding to the data cost indicator.

[0086] Step 106, determining the information with the largest value between the first multiplication information and the second multiplication information as the target information.

[0087] In some embodiments, the execution entity may determine information with the largest value between the first multiplication information and the second multiplication information as target information.

[0088] Step 107: Generate data value assessment information for the target business data set based on the target information, the data quality assessment information and the data application information.

[0089] In some embodiments, the execution entity may generate data value assessment information for the target business data set based on the target information, the data quality assessment information and the data application information.

[0090] In some optional implementations of some embodiments, generating data value assessment information for the target business data set according to the target information, the data quality assessment information and the data application information may include the following steps:

[0091] The first step is to determine the data source scarcity information, data service stability information and docking object feedback information for the above-mentioned target business data set. Among them, the data source scarcity information may include: information indicating whether it is an exclusive data source and information on the rarity of the data source. The data service stability information may include: data service stability information (i.e., the proportion of call failures). The docking object feedback information may be information indicating whether the feedback from the credit reporting agency’s customers is valid. The docking object feedback information may be the feedback information of the docking object. Specifically, the docking object feedback information includes: negative feedback information, neutral feedback information and positive feedback information.

[0092] The second step is to quantify the above data source scarcity information, data service stability information and docking object feedback information to generate data source scarcity values, data service stability values ​​and docking object feedback values.

[0093] As an example, the execution subject may classify the data source scarcity information, data service stability information, and docking object feedback information to generate scarcity category information corresponding to the data source scarcity information, stability category information corresponding to the data service stability information, and feedback category information corresponding to the docking feedback information. Then, through the numerical association table, the data source scarcity value corresponding to the scarcity category information, the data service stability value corresponding to the stability category information, and the docking object feedback value corresponding to the feedback category information are generated.

[0094] The third step is to multiply the data source scarcity value by the corresponding indicator weight in the indicator weight set to generate sixth multiplication information, wherein the sixth multiplication information corresponds to the data source scarcity indicator.

[0095] The fourth step is to multiply the data service stability value by the corresponding indicator weight in the indicator weight set to generate seventh multiplication information, wherein the seventh multiplication information corresponds to the data service stability indicator.

[0096] The fifth step is to multiply the above-mentioned feedback value of the docking object with the corresponding indicator weight in the above-mentioned indicator weight set to generate the eighth multiplication information. Among them, the seventh multiplication information corresponds to the feedback indicator of the docking object.

[0097] The sixth step is to multiply the above data quality assessment information with the corresponding indicator weight in the above indicator weight set to generate third multiplication information, and to multiply the above data application information with the corresponding indicator weight in the above indicator weight set to generate fourth multiplication information.

[0098] The seventh step is to multiply the target information, the third multiplication information, the fourth multiplication information, the sixth multiplication information, the seventh multiplication information and the eighth multiplication information to generate ninth multiplication information as the first candidate data value assessment information.

[0099] Step 8: Generate the above data value assessment information based on the above first candidate data value assessment information.

[0100] As an example, the execution entity may directly determine the first candidate data value assessment information as the data value assessment information.

[0101] In some optional implementations of some embodiments, generating the data value assessment information according to the first candidate data value assessment information may include the following steps:

[0102] In the first step, the target information, the data quality assessment information and the data application information are input into a pre-trained first data value assessment information generation model to generate second candidate data value assessment information. The first data value assessment information generation model may be a neural network model for generating data value assessment information. In practice, the first data value assessment information generation model may be a convolutional neural network model with multiple layers connected in series.

[0103] The second step is to determine a first evaluation information difference between the first candidate data value evaluation information and the second candidate data value evaluation information.

[0104] In the third step, in response to determining that the first evaluation information difference is less than or equal to the first predetermined value, the weighted information between the first candidate data value evaluation information and the second candidate data value evaluation information is determined as the data value evaluation information. The first predetermined value may be a pre-set value. The information weight corresponding to the first candidate data value evaluation information and the information weight corresponding to the second candidate data value evaluation information may be pre-set.

[0105] In the fourth step, in response to determining that the first evaluation information difference is greater than the first predetermined value, each target business data in the target business data set is encoded to generate encoding information to obtain an encoding information set.

[0106] As an example, the execution subject may input each target business data in the target business data set into a data encoding model to generate encoding information and obtain an encoding information set. In practice, the data encoding model may be a word embedding model.

[0107] In the fifth step, the above-mentioned encoded information set is input into a pre-trained second data value assessment information generation model to generate third candidate data value assessment information. The second data value assessment information generation model may be a neural network model for generating data value assessment information. In practice, the second data value assessment information generation model may include: a plurality of convolutional neural network models connected in series.

[0108] The sixth step is to determine the second evaluation information difference between the third candidate data value evaluation information and the first candidate data value evaluation information, and to determine the third evaluation information difference between the third candidate data value evaluation information and the second candidate data value evaluation information.

[0109] In the seventh step, in response to determining that the second evaluation information difference is greater than the third evaluation information difference, weighted information between the third candidate data value evaluation information and the second candidate data value evaluation information is determined as the data value evaluation information.

[0110] In step 8, in response to determining that the third evaluation information difference is greater than the second evaluation information difference, the weighted information between the third candidate data value evaluation information and the first candidate data value evaluation information is determined as the data value evaluation information. The weight information corresponding to the third candidate data value evaluation information and the weight information corresponding to the first candidate data value evaluation information can be preset.

[0111] In step 9, in response to determining that the third evaluation information difference is equal to the second evaluation information difference, generating evaluation interval information with the third evaluation information as the information center and an interval length of a predetermined length, wherein the predetermined length may be a preset interval length.

[0112] The tenth step is to generate the above data value assessment information based on the above assessment interval information.

[0113] Optionally, the step of generating the data value assessment information according to the assessment interval information may include the following steps:

[0114] The first step is to obtain a third data value assessment information generation model based on the attention mechanism, wherein the third data value assessment information generation model has corresponding output constraints, and the output constraints are generated based on the evaluation interval information. The output constraint can be a constraint formula that characterizes that the corresponding output result of the third data value assessment information generation model is in the evaluation interval. The third data value assessment information generation model based on the attention mechanism is: word embedding model + multi-layer convolution layer + multi-head attention mechanism model + multi-layer convolution layer + fully connected layer.

[0115] The second step is to input the above-mentioned data source scarcity value, data service stability value, docking object feedback value, the above-mentioned data quality assessment information, the above-mentioned data application information and the above-mentioned target business data set into the above-mentioned third data value assessment information generation model to generate the above-mentioned data value assessment information.

[0116] Step 108: Perform corresponding value processing operations on the target business data set according to the data value assessment information.

[0117] In some embodiments, the execution subject may perform corresponding value processing operations on the target business data set according to the data value assessment information. The value processing operation may be a processing operation that is to be determined whether to be executed and is directly associated with the data value assessment information. That is, if the data value assessment information is less than a predetermined value, the value processing operation is not performed. If the data value assessment information is greater than or equal to a predetermined value, the value processing operation is performed. In practice, for credit investigation scenarios, the value processing operation may be a target business data set packaging and sales operation.

[0118] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the data processing method of some embodiments of the present disclosure, the corresponding value processing operation can be reasonably performed for the accurately determined data value assessment information. Specifically, the reason why the relevant data value assessment information is not accurate enough and the corresponding value processing operation has a large deviation is that the value analysis is cumbersome, the time is wasted for a long time, and the generated value assessment information is not accurate enough, resulting in a large deviation in the subsequent value processing operation for the data set. Based on this, the data processing method of some embodiments of the present disclosure first obtains the target business data set, the data application information and data cost information for the above target business data set as data support for the subsequent determination of data value assessment information. Then, using the data public assessment information generation model, the data public assessment information for the above target business data set can be accurately generated. Here, the obtained data public assessment information is used for the subsequent generation of data value assessment information. Then, using the data quality assessment information generation model, the data quality assessment information for the above target business data set can be accurately generated. Here, from the aspect of data quality, it is helpful to accurately generate data value assessment information in the subsequent period. Next, determine the indicator weights corresponding to each evaluation indicator of the target business data set, and obtain the indicator weight set to determine the indicator importance of the corresponding indicators of each data level corresponding to the target business data set, so as to facilitate the subsequent accurate generation of data value assessment information. Furthermore, multiply the above-mentioned data disclosure assessment information with the corresponding indicator weight in the above-mentioned indicator weight set to generate the first multiplication information, and multiply the above-mentioned data cost information with the corresponding indicator weight in the above-mentioned indicator weight set to generate the second multiplication information. Here, the obtained first multiplication information and second multiplication information can remind the importance of subsequent data value assessment information. Further, determine the information with the largest value in the above-mentioned first multiplication information and the above-mentioned second multiplication information as the target information to determine the preliminary data value for the target business data set. Next, according to the above-mentioned target information, the above-mentioned data quality assessment information and the above-mentioned data application information, the data value assessment information for the above-mentioned target business data set can be accurately generated from many aspects. Finally, according to the above-mentioned data value assessment information, the corresponding reasonable and effective value processing operation is performed on the above-mentioned target business data set.

[0119] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a data processing device. These device embodiments are Figure 1 Corresponding to the method embodiments shown, the data processing device can be specifically applied to various electronic devices.

[0120] like Figure 2As shown, a data processing device 200 includes: an acquisition unit 201, a first generation unit 202, a second generation unit 203, a first determination unit 204, a multiplication unit 205, a second determination unit 206, a third generation unit 207 and an execution unit 208. The acquisition unit 201 is configured to acquire a target business data set, data application information and data cost information for the target business data set; the first generation unit 202 is configured to generate data disclosure evaluation information for the target business data set using a data disclosure evaluation information generation model; the second generation unit 203 is configured to generate data quality evaluation information for the target business data set using a data quality evaluation information generation model; the first determination unit 204 is configured to determine the indicator weights corresponding to the various evaluation indicators for the target business data set to obtain an indicator weight set; the multiplication unit 205 is configured to combine the data disclosure evaluation information with the data disclosure evaluation information; The corresponding indicator weights in the indicator weight set are multiplied to generate the first multiplication information, and the above-mentioned data cost information is multiplied with the corresponding indicator weights in the above-mentioned indicator weight set to generate the second multiplication information; the second determination unit 206 is configured to determine the information with the largest numerical value among the above-mentioned first multiplication information and the above-mentioned second multiplication information as the target information; the third generation unit 207 is configured to generate the data value assessment information for the above-mentioned target business data set according to the above-mentioned target information, the above-mentioned data quality assessment information and the above-mentioned data application information; the execution unit 208 is configured to perform corresponding value processing operations on the above-mentioned target business data set according to the above-mentioned data value assessment information.

[0121] It is understood that the units described in the data processing device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the data processing device 200 and the units included therein, and will not be described in detail here.

[0122] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0123] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0124] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0125] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0126] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0127] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0128] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a target business data set, data application information and data cost information for the target business data set; generates data public evaluation information for the target business data set using a data public evaluation information generation model; generates data quality evaluation information for the target business data set using a data quality evaluation information generation model; determines the indicator weights corresponding to each evaluation indicator for the target business data set to obtain an indicator weight set; multiplies the data public evaluation information with the corresponding indicator weight in the indicator weight set to generate first multiplication information, and multiplies the data cost information with the corresponding indicator weight in the indicator weight set to generate second multiplication information; determines the information with the largest value in the first multiplication information and the second multiplication information as the target information; generates data value evaluation information for the target business data set according to the target information, the data quality evaluation information and the data application information; performs corresponding value processing operations on the target business data set according to the data value evaluation information.

[0129] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0131] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a first generation unit, a second generation unit, a first determination unit, a multiplication unit, a second determination unit, a third generation unit, and an execution unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring a target business data set, data application information for the above target business data set, and data cost information".

[0132] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0133] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A data processing method, comprising: Acquire a target business data set, data application information and data cost information for the target business data set; Generate data disclosure assessment information for the target business data set using a data disclosure assessment information generation model; The data quality assessment information generation model is used to generate data quality assessment information for the target business data set, wherein: The generating model using the data quality assessment information to generate data quality assessment information for the target business data set includes: Performing data consistency determination on the target business data set to generate data consistency information; Using the data quality assessment information generation model, the target business data set is verified for data accuracy to generate data accuracy verification information; Using the data availability determination model included in the data quality assessment information generation model, the target business data set is subjected to data availability verification to generate data availability information; Performing a timeliness check on the target business data set to generate data timeliness check information; Performing a credibility check on the target business data set to generate data feasibility check information; Performing data integrity verification on the target business data set to generate data integrity verification information; Numerizing the data consistency information, the data accuracy check information, the data availability information, the data timeliness check information, the data feasibility check information, and the data integrity check information to generate a data consistency value, a data accuracy value, a data availability value, a data timeliness value, a data feasibility value, and a data integrity value; The data consistency value, the data accuracy value, the data availability value, the data timeliness value, the data feasibility value and the data integrity value are weighted and summed to generate data quality assessment information, wherein: The step of using the data availability determination model included in the data quality assessment information generation model to perform data availability verification on the target business data set to generate data availability information includes: Inputting the target business data set into the data encoding model included in the data quality assessment information generation model to generate encoding information to obtain an encoding information set; Input the encoded information set into the attention mechanism model based on the domain association relationship to generate a correlation relationship array corresponding to each encoded information, and obtain a correlation relationship array set, wherein the correlation coefficient in the correlation relationship array has a one-to-one correspondence with the data available domain information in the data available domain information set, wherein the relationship coefficient represents the close relationship between the corresponding business data and the corresponding data available domain information, and the larger the value, the closer the relationship between the business data and the corresponding data available domain information; According to the association relationship group set, the target business data set is grouped into data available fields to generate a target business data group set, wherein each target business data group in the target business data group set has corresponding data available field information; For each target service data group in the target service data group set, data enhancement is performed on the target service data group to generate an enhanced data group, thereby obtaining an enhanced data group set; For each enhanced data group in the enhanced data group set, inputting the enhanced data group into a data domain association model corresponding to data domain information to generate an accuracy rate for the enhanced data group, wherein the data domain information is an image recognition domain and the corresponding data domain association model is an image recognition model; Filter out data available field information with a corresponding accuracy greater than a target value from the data available field information set to obtain at least one data available field information; Determining the at least one data availability field information as data availability information; Determine the indicator weight corresponding to each evaluation indicator of the target business data set to obtain an indicator weight set; Multiplying the data disclosure evaluation information by the corresponding indicator weight in the indicator weight set to generate first multiplication information, and multiplying the data cost information by the corresponding indicator weight in the indicator weight set to generate second multiplication information; Determine information having the largest value between the first multiplication information and the second multiplication information as target information; Generating data value assessment information for the target business data set according to the target information, the data quality assessment information and the data application information; According to the data value assessment information, a corresponding value processing operation is performed on the target business data set.

2. The method according to claim 1, wherein: The generating model using the data disclosure evaluation information to generate data disclosure evaluation information for the target business data set includes: Obtaining historical value flow information for the target business data set; Determine an indicator information set corresponding to the target business data set and having a corresponding indicator importance greater than a first value; Dividing the indicator information in the indicator information set by indicator importance to obtain an indicator information group set, wherein the indicator importance level corresponding to each indicator information in each indicator information group is the same; Randomly extracting a predetermined number of indicator information from each indicator information group to obtain an extracted indicator information set; Determining, according to the extracted indicator information set, at least one business data set that satisfies an indicator similarity condition with the target business data set; Determine that each business data set in the at least one business data set corresponds to actual data public information, and obtain an actual data public information set; Determine average information corresponding to each piece of actual data public information in the actual data public information set; Dividing the historical value circulation information by the average information to obtain first candidate data public evaluation information; Using the data disclosure evaluation information generation model, generating second candidate data disclosure evaluation information for the target business data set; multiplying the first candidate data public evaluation information by a first value to generate a first multiplication result; multiplying the second candidate data public evaluation information by a second numerical value to generate a second multiplication result; In response to determining that the difference between the first multiplication result and the second multiplication result is less than a second value, a weighted sum of the first multiplication result and the second multiplication result is determined as data disclosure evaluation information.

3. The method according to claim 2, wherein: The data cost information is determined by the following steps: Obtaining direct cost information for the target business data set; Acquiring construction cost information, equipment cost information, processing cost information and risk cost information for the target business data set; The direct cost information, the construction cost information, the equipment cost information, the processing cost information and the risk cost information are added together accordingly to obtain the data cost information.

4. The method according to claim 3, wherein: The step of generating data value assessment information for the target business data set according to the target information, the data quality assessment information and the data application information includes: Determine data source scarcity information, data service stability information, and docking object feedback information for the target business data set; Numerically processing the data source scarcity information, data service stability information and docking object feedback information to generate a data source scarcity value, a data service stability value and a docking object feedback value; multiplying the data source scarcity value by the corresponding indicator weight in the indicator weight set to generate sixth multiplication information; Multiplying the data service stability value by the corresponding indicator weight in the indicator weight set to generate seventh multiplication information; Multiplying the feedback value of the docking object by the corresponding indicator weight in the indicator weight set to generate eighth multiplication information; multiplying the data quality assessment information by the corresponding indicator weight in the indicator weight set to generate third multiplication information, and multiplying the data application information by the corresponding indicator weight in the indicator weight set to generate fourth multiplication information; multiplying the target information, the third multiplication information, the fourth multiplication information, the sixth multiplication information, the seventh multiplication information, and the eighth multiplication information to generate ninth multiplication information as first candidate data value assessment information; The data value assessment information is generated according to the first candidate data value assessment information.

5. The method according to claim 4, wherein: The step of generating the data value assessment information according to the first candidate data value assessment information includes: Inputting the target information, the data quality assessment information and the data application information into a pre-trained first data value assessment information generation model to generate second candidate data value assessment information; Determine a first evaluation information difference between the first candidate data value evaluation information and the second candidate data value evaluation information; In response to determining that the first evaluation information difference is less than or equal to a first predetermined value, determining weighted information between the first candidate data value evaluation information and the second candidate data value evaluation information as data value evaluation information; In response to determining that the first evaluation information difference is greater than the first predetermined value, performing data encoding on each target service data in the target service data set to generate encoding information to obtain an encoding information set; Inputting the encoded information set into a pre-trained second data value assessment information generation model to generate third candidate data value assessment information; Determine a second evaluation information difference between the third candidate data value evaluation information and the first candidate data value evaluation information, and determine a third evaluation information difference between the third candidate data value evaluation information and the second candidate data value evaluation information; In response to determining that the second evaluation information difference is greater than the third evaluation information difference, determining weighted information between the third candidate data value evaluation information and the second candidate data value evaluation information as the data value evaluation information; In response to determining that the third evaluation information difference is greater than the second evaluation information difference, determining weighted information between the third candidate data value evaluation information and the first candidate data value evaluation information as the data value evaluation information; In response to determining that the third evaluation information difference is equal to the second evaluation information difference, generating evaluation interval information with the third evaluation information as the information center and an interval length of a predetermined length; The data value assessment information is generated according to the assessment interval information.

6. The method according to claim 5, wherein: Generating the data value assessment information according to the assessment interval information includes: Acquire a third data value assessment information generation model based on an attention mechanism, wherein the third data value assessment information generation model has a corresponding output constraint, and the output constraint is generated based on the assessment interval information; The data source scarcity value, the data service stability value, the docking object feedback value, the data quality assessment information, the data application information and the target business data set are input into the third data value assessment information generation model to generate the data value assessment information.

7. A data processing device, comprising: an acquisition unit, configured to acquire a target business data set, data application information and data cost information for the target business data set; A first generating unit is configured to generate data disclosure evaluation information for the target business data set by using a data disclosure evaluation information generating model; The second generating unit is configured to generate data quality assessment information for the target business data set by using a data quality assessment information generating model, wherein the generating of data quality assessment information for the target business data set by using a data quality assessment information generating model includes: performing data consistency determination on the target business data set to generate data consistency information; performing data accuracy verification on the target business data set by using a data quality assessment information generating model to generate data accuracy verification information; performing data availability verification on the target business data set by using a data availability determination model included in the data quality assessment information generating model to generate data availability information; and performing data consistency verification on the target business data set by using a data consistency determination model included in the data quality assessment information generating model to generate data consistency information. The business data set is checked for timeliness to generate data timeliness check information; the target business data set is checked for credibility to generate data feasibility check information; the target business data set is checked for data integrity to generate data integrity check information; the data consistency information, the data accuracy check information, the data availability information, the data timeliness check information, the data feasibility check information and the data integrity check information are digitized to generate data consistency values, data accuracy values, data availability values, data timeliness values, data feasibility values ​​and data integrity values; the data consistency values, the data accuracy values, the The data availability value, the data timeliness value, the data feasibility value and the data integrity value are weighted and summed to generate data quality assessment information, wherein the data availability determination model included in the data quality assessment information generation model is used to perform data availability verification on the target business data set to generate data availability information, including: inputting the target business data set into the data encoding model included in the data quality assessment information generation model to generate encoding information and obtain an encoding information set; inputting the encoding information set into the attention mechanism model based on domain association relationships to generate a related connection array corresponding to each encoding information and obtain a related connection array set, wherein the related There is a one-to-one correspondence between the association coefficient in the contact array and the data available field information in the data available field information set, wherein the relationship coefficient represents the close relationship between the corresponding business data and the corresponding data available field information, and the larger the value, the closer the relationship between the business data and the corresponding data available field information; according to the association relationship group set, the target business data set is grouped in the data available field to generate a target business data group set, wherein each target business data group in the target business data group set has corresponding data available field information; for each target business data group in the target business data group set, the target business data group is data enhanced to generate an enhanced data group, thereby obtaining an enhanced data group set;For each enhanced data group in the enhanced data group set, input the enhanced data group into a data domain association model corresponding to data domain information to generate an accuracy rate for the enhanced data group, wherein the data domain information is an image recognition field, and the corresponding data domain association model is an image recognition model; filter out data available field information corresponding to an accuracy rate greater than a target value from the data available field information set to obtain at least one data available field information; and determine the at least one data available field information as data availability information; A first determining unit is configured to determine an indicator weight corresponding to each evaluation indicator of the target business data set to obtain an indicator weight set; a multiplication unit configured to multiply the data disclosure evaluation information by a corresponding indicator weight in the indicator weight set to generate first multiplication information, and to multiply the data cost information by a corresponding indicator weight in the indicator weight set to generate second multiplication information; A second determining unit is configured to determine information with the largest value between the first multiplied information and the second multiplied information as target information; A third generating unit is configured to generate data value assessment information for the target business data set according to the target information, the data quality assessment information and the data application information; The execution unit is configured to perform corresponding value processing operations on the target business data set according to the data value assessment information.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images