Method, device, equipment and storage medium for determining standard data element

By obtaining feature information from the standard data element database and the historical benchmarking record library, and determining the standard data element in combination with the matching degree and recommendation score, the problem of low matching accuracy of standard data elements in the existing technology is solved, and more accurate Standard data element recommendation.

CN114328600BActive Publication Date: 2024-11-29ANHUI IFLYTEK INTELLIGENT SYST
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202111674685.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-31
Publication Date
2024-11-29
Estimated Expiration
2041-12-31

AI Technical Summary

Technical Problem

The prior art is difficult to accurately match standard data elements, resulting in a low matching accuracy of standard data elements.

Method used

By obtaining the characteristic information of the target data element, comprehensively match and score from the standard data element database and the historical benchmarking record library, combining the matching degree and recommendation score, the candidate standard data element is determined, and the characteristic information of the data element and historical standardized behavior are considered. Generate a standardized list.

Benefits of technology

Improve the accuracy of standard data element matching, ensure that more suitable standard data elements are recommended for standardization, and reduce the situation where standard data elements cannot be matched.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114328600B_ABST
    Figure CN114328600B_ABST
Patent Text Reader

Abstract

The present application provides a method, device, equipment and storage medium for determining standard data elements, the method comprising: obtaining at least one feature information of a target data element; based on each feature information of the target data element, determining a first data element set matching the target data element from a standard data element library, and determining a second data element set corresponding to the target data element from a historical benchmarking record library; determining a recommended score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized; combining the matching degree of each first standard data element in the first data element set and the recommended score of each second standard data element in the second data element set, determining at least one first candidate standard data element for standardizing the target data element from the first data element set and the second data element set. The scheme of the present application can improve the accuracy of standard data element matching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and more specifically, to a method, device, equipment and storage medium for determining a standard data element. Background Art

[0002] With the continuous development of informatization and digitalization, enterprises can organize data based on the data middle platform.

[0003] Data elements need to be standardized during the data regularization stage. Data element standardization refers to converting data elements into standard data elements that meet industry standards or national standards. Based on this, in the process of data element standardization, it is necessary to determine the standard data elements that match the data elements. At present, it is difficult to accurately match the standard data elements that are suitable for the data elements from the standard data element library, resulting in a low matching accuracy rate for standard data elements. Summary of the invention

[0004] In view of the above problems, the present application provides a method, device, equipment and storage medium for determining standard data elements to improve the accuracy of standard data element matching. The specific scheme is as follows:

[0005] In a first aspect of the present application, a method for determining a standard data element is provided, comprising:

[0006] Obtaining at least one feature information of a target data element to be standardized;

[0007] Based on each feature information of the target data element, determine a first data element set matching the target data element from a standard data element library, wherein the first data element set includes: each first standard data element matching the target data element in the standard data element library, and a matching degree between the first standard data element and the target data element;

[0008] Based on each characteristic information of the target data element, a second data element set corresponding to the target data element is determined from a historical benchmarking record library, wherein the historical benchmarking record library stores: characteristic information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized into each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to;

[0009] Determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element;

[0010] In combination with the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, at least one first candidate standard data element for standardizing the target data element is determined from the first data element set and the second data element set.

[0011] In a possible implementation, combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set to determine at least one first candidate standard data element for standardizing the target data element from the first data element set and the second data element set includes:

[0012] Determine a first comprehensive score for each standard data element in the first data element set and the second data element set by combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set;

[0013] A first candidate standardization list for standardizing the target data element is generated, wherein the first candidate standardization list includes: at least one first candidate standard data element with a higher first comprehensive score determined from the first data element set and the second data element set.

[0014] In yet another possible implementation, the first candidate standardization list further includes: a first comprehensive score of the first candidate standard data element;

[0015] The method further comprises:

[0016] Based on at least one feature information of the target data element, construct a feature word set of the target data element, wherein the feature word set includes at least one feature word segmented from the at least one feature information;

[0017] Based on the characteristic word segmentation set, determining a third data element set similar to the target data element in the standard data element library, the third data element set comprising: at least one third standard data element whose characteristic information set has a high similarity with the characteristic word segmentation set, and a first similarity between the characteristic information set of the third standard data element and the characteristic word segmentation set; the characteristic information set of the standard data element comprises each characteristic information of the standard data element;

[0018] Based on the first similarities corresponding to each third standard data element and the first comprehensive scores of each first candidate standard data element in the first candidate standardization list, at least one target standard data element for standardizing the target data element is determined from the third data element set and the first candidate standardization list.

[0019] In a second aspect of the present application, a device for determining a standard data element is provided, comprising:

[0020] An information obtaining unit, used to obtain at least one feature information of a target data element to be standardized;

[0021] a first set determining unit, configured to determine, from a standard data element library, a first data element set matching the target data element based on each feature information of the target data element, wherein the first data element set includes: each first standard data element in the standard data element library matching the target data element, and a matching degree between the first standard data element and the target data element;

[0022] A second set determination unit is used to determine, based on each feature information of the target data element, a second data element set corresponding to the target data element from a historical benchmarking record library, wherein the historical benchmarking record library stores: feature information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized to each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to;

[0023] a recommendation scoring unit, configured to determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element;

[0024] The first data element determination unit is used to determine at least one first candidate standard data element for standardizing the target data element from the first data element set and the second data element set, based on the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set.

[0025] In a third aspect of the present application, a computer device is provided, comprising: a memory and a processor;

[0026] The memory is used to store programs;

[0027] The processor is used to execute the program to implement each step of the method for determining the standard data element in any embodiment of the present application.

[0028] In a fourth aspect of the present application, a storage medium is provided on which a computer program is stored, characterized in that when the computer program is executed by a processor, each step of the method for determining a standard data element in any embodiment of the present application is implemented.

[0029] By means of the above technical scheme, the present application will not only search for the first standard data element that matches the target data element from the standard data element library, but also determine the second standard data elements that have been standardized in the history of the target data element and the number of standardized times that the target data element has been standardized as each second standard data element based on the characteristic information of the target data element. Since the number of standardized times of the second standard data element reflects the number of times that the target data element has been standardized as the second standard data element in history, the recommended score of the second standard data element determined based on the number of standardized times of each second standard data element can reflect the degree of suitability of the second standard data element for standardizing the target data element. On this basis, the present application comprehensively considers the matching degree of each first standard data element with the target data element and the recommended score of each second standard data element, determines the target data element for standardization, takes into account the matching situation of the characteristic information of the target data element with the standard data element, and takes into account some behavioral information that has been standardized in the history of the target data element, so that the standard data element suitable for standardizing the target data element can be determined more accurately, and the standard data element for standardizing the data element can be recommended more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0031] Figure 1 A schematic diagram of a flow chart of a method for determining a standard data element provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a storage structure for storing standard data elements that have been historically standardized as non-standard data elements in a historical benchmarking record library provided in an embodiment of the present application;

[0033] Figure 3 A schematic diagram of a flow chart of a method for determining a standard data element provided in an embodiment of the present application;

[0034] Figure 4 A schematic diagram of an implementation flow of constructing a feature segmentation set based on at least one feature information of a target data element provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of an implementation process for determining the overall score of a candidate standard data element provided in an embodiment of the present application;

[0036] Figure 6 A schematic diagram of an implementation principle framework of a method for determining standard data elements provided in an embodiment of the present application;

[0037] Figure 7 A schematic diagram of a composition structure of an apparatus for determining standard data elements provided in an embodiment of the present application;

[0038] Figure 8 A schematic diagram of the composition architecture of a computer device applicable to the solution of an embodiment of the present application. DETAILED DESCRIPTION

[0039] Different industries or different fields in the same industry may have different naming methods for the same data element. When it is necessary to use data middle platform and other technologies to manage data in a unified manner, the data elements need to be standardized. This requires determining at least one standardized data element that can be used to standardize the data element, so that users can select a standard data element as the standardized data element of the data element.

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] The inventor of the present application has studied the matching process of standard data elements and found that: for data elements to be standardized, the characteristic information of the data elements can be used to match the standard data elements from the standard data element library. However, this method can only match a standard data element that is strongly related to the characteristic information of the data element. If the characteristic information of the data element to be standardized is a common word, it is difficult to accurately match a suitable standard data element.

[0042] In order to more accurately match the standard data element and reduce the situation where the standard data element cannot be matched, the present application will match the standard data element from the standard data element library based on the characteristic information of the target data element to be matched, and will also detect the various standard data elements that the target data element has been standardized into in history from the pre-built historical benchmarking record library in combination with the characteristic information of the target data element. Combined with the detection results of the standard data element library and the historical benchmarking record library, the standard data element used to standardize the target data element is comprehensively determined, so that the standard data element can be comprehensively determined by combining the matching results of multiple dimensions, and the standard data element suitable for standardizing the target data element can be more accurately determined.

[0043] The method for determining standard data elements provided in this application is introduced below with reference to a flowchart.

[0044] like Figure 1 As shown, it shows a flow chart of a method for determining a standard data element provided in an embodiment of the present application. The method of this embodiment may include:

[0045] S101, obtaining at least one feature information of a target data element to be standardized.

[0046] Data element refers to a data unit maintained by different industries. For example, data element can be name, ID number, postal code, etc.

[0047] It can be understood that, for the sake of easy distinction, the present application refers to the data elements that need to be standardized as target data elements.

[0048] The characteristic information of the target data element may include the name of the data element, such as one or both of the English code and the Chinese name of the data element. The characteristic information of the data element may also be descriptive information used to characterize the characteristics of the data element, such as one or more of the data type of the data element, the description information of the data element, and the industry to which the data element belongs.

[0049] In the present application, at least one characteristic information of the target data element includes at least the name of the data element, such as the English code of the data element, and may also include other characteristics of the data element, which are not limited.

[0050] S102: Based on each feature information of the target data element, determine a first data element set matching the target data element from a standard data element library.

[0051] The first data element set includes: each first standard data element in the standard data element library that matches the target data element, and the matching degree between the first standard data element and the target data element.

[0052] The standard data element library may store characteristic information of multiple standard data elements. The characteristic information of the standard data element may also include the English code and Chinese name of the standard data element, and may also include one or more of the following information: the description of the standard data element, the industry to which it belongs, the representation format, the category, etc.

[0053] For example, the standard data element library may record the characteristic information of each standard data element in the form of Table 1 below.

[0054] Table 1

[0055]

[0056] In Table 1, each row corresponds to the characteristic information of a standard data element.

[0057] Each standard data element has an English code and a Chinese name. For example, the first row in Table 1 records the standard data element with the English code "GMSFHM" and the Chinese name of the standard data element is "Citizen ID Number". At the same time, the standard data element library also has the description, synonyms, data types, object categories represented by the standard data element, representation formats of the standard data element, and code length labels.

[0058] The object categories may include: people, roads, time, documents, vehicles, etc., without restriction.

[0059] The representation format is the number of digits used to represent a standard data element, such as the representation format of a citizen's ID number is 18 digits.

[0060] Since the representation format is too detailed, it is easy to cause confusion when matching the standardized data elements. This application also proposes the use of code length labels to indicate the length of standard data elements. In this application, code length labels can be divided into two categories, one is a fixed code length label, and the other is a dynamic code length label. The fixed code length label is manifested as a standard data element with a specific coding length (such as an ID card, license plate number, mobile phone number, etc.), type value length, time field length, etc. The dynamic code length label is manifested as the coding length floating within a certain range (such as a name, address, description, etc.).

[0061] Of course, the dynamic code length tag can be further divided into narrow code and wide code. The division method can divide the confidence value based on the length distribution of the data element sample. For example, the narrow code is the length of the code length tag <= 10, and the wide code is the length of the code length tag > 10.

[0062] It is understandable that for each characteristic information of the target data element, the standard data element can be matched from the standard database element library, and finally the standard data element to which at least one characteristic information of the target data element is matched can be obtained. This application does not limit the specific implementation method of matching the standard data element from the standard database element.

[0063] For the sake of distinction, the present application refers to the standard data element matched from the standard data element library as the first standard data element.

[0064] Among them, the first standard data element that matches the target data element can be: a standard data element whose characteristic information matches one or more characteristic information of the target data element to a degree exceeding a set threshold; or a set number of standard data elements whose characteristic information matches the characteristic information of the target data element to a high degree.

[0065] The matching degree between the first standard data element and the target data element is the similarity between the feature information of the first standard data element and the feature information of the target data element.

[0066] S103: Based on each feature information of the target data element, determine a second data element set corresponding to the target data element from a historical benchmarking record library.

[0067] The historical benchmarking record library stores: characteristic information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized into each standard data element in history.

[0068] Among them, non-standardized data elements are data elements obtained historically that need to be standardized.

[0069] The standard data element after the non-standard data element is standardized in history may be: the standard data element that the user has historically selected to standardize the non-standard data element. Accordingly, the historical benchmarking record library may be constructed based on the behavior records of different users historically selecting standard data elements for the data elements to be standardized.

[0070] It is understandable that due to different business scenarios, the standard data element selected by the user for the same data element may also be different. In addition, due to other reasons such as misoperation, the user may also select different standardized data elements for the same data element in different standardization processes. Based on this, each non-standard data element in the historical benchmarking record library may correspond to multiple standard data elements, and each standard data element corresponds to a different number of standardizations.

[0071] For example, the historical benchmarking record library may record at least one standard data element corresponding to the English code (or Chinese name) of each non-standard data element and the number of times each standard data element has been standardized. In the historical benchmarking record library, each standard data element corresponding to a non-standard data element is a standard data element that the non-standard data element has been selected by the user to be standardized in the past.

[0072] For example, the historical benchmarking record library can be used as follows Figure 2 Each non-standard data element and its historical standardized information are recorded in the form of

[0073] Depend on Figure 2 It can be seen that a non-standard data element can correspond to one or more standard data elements that have been standardized in history, and the number after each standard data element is the number of times the non-standard data element has been selected and standardized as the standard data element in history. Figure 2 The number of times that the Chinese and African standard data elements have been standardized as standard data element 1 is 2 times in history, and the number of times that they have been selected for standardization as standard data element 2 is 5 times in history.

[0074] It is understandable that the present application can combine the types of characteristic information of non-standard data elements recorded in the historical benchmarking record library to compare the characteristic information of the corresponding types of target data elements with the characteristic information of each non-standard data element in the historical benchmarking record library. For example, if the historical benchmarking record library records at least the English encoding of the non-standard data element, then at least the English encoding of the target data element can be matched with the English encoding of each non-standard data element in the historical benchmarking record library to match the second data element set.

[0075] In the present application, the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of standardizations corresponding to the second standard data element.

[0076] For the sake of ease of distinction, the standard data element matched from the historical benchmarking record library is called the second standard data element. However, it is understandable that the standard data element matched from the historical benchmarking record library may be repeated with the standard data element matched from the standard data element library, and it is possible that a second standard data element may be the same standard data element as a first standard data element.

[0077] S104: Determine a recommendation score of the second standard data element according to the number of normalizations of the second standard data element in the second data element set.

[0078] Among them, the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element.

[0079] It can be understood that the more times the second standard data element is standardized, the more times the second standard data element is selected by the user as the standard data element, which means that the second standard data element is more suitable for standardizing the corresponding non-standard data element. Based on this, the more times the second standard data element is standardized, the more suitable the second standard data element is as the standardized data element of the standardized target data element, and therefore, its recommendation score is also high. It can also be seen that the recommendation score of the second standard data element can be used to characterize the suitability of the second standard data element as the standard data element of the target data element.

[0080] It is understandable that, for a second standard data element corresponding to a non-standard data element, the closer the time when the second standard data element was last selected as a standardized data element is to the current time, the greater the possibility that the second standard data element will be selected again as the standardized data element of the non-standard data element, that is, the more suitable the second standard data element is for standardizing the non-standard data element (or the target data element). Based on this, in this application, the historical benchmarking record library also stores: the standard time when each non-standard data element was last standardized into each standard data element in history.

[0081] For the sake of distinction, the time when a non-standardized data element was most recently standardized into a standard data element in history is referred to as the time when the standard data element was most recently standardized as the standard data element of the non-standardized data.

[0082] Correspondingly, the second data element set may also include the most recent normalization time corresponding to the second standard data element. On this basis, the present application may also determine the recommended score of the second standard data element in combination with the number of normalization times of the second standard data element in the second data element set and the most recent normalization time. Among them, the more the number of normalization times of the second standard data element and the shorter the time from the most recent normalization time to the current time, the higher the recommended score of the second standard data element.

[0083] There are many possible specific ways to determine the recommendation score of the second standard data element, and there is no limitation to this.

[0084] For ease of understanding, the following is an example of calculating a recommendation score for a second standard data element:

[0085] If the number of the determined second standard data element is only one, the recommendation score of the second standard data element may be set to 100;

[0086] If the number of the second standard data elements determined is more than one:

[0087] For the second standard data element with the largest number of standardization times among the plurality of second standard data elements, the second standard data element may be set to 100 points;

[0088] For each second standard data element whose number of normalization times is not the largest among the multiple standard data elements, the recommendation score Y of the second standard data element can be calculated by the following formula 1:

[0089] Y=119.91X -0.286 *e (-λ*max(0,t-d)) (Formula 1);

[0090] Among them, X is the difference between the normalization number of the second standard data element and the maximum normalization number, and the maximum normalization number is the maximum value of the normalization numbers of multiple second standard data elements matched by the target data element; λ is the set rate of decay based on time score, which can be set according to actual needs; t is the difference in days between the most recent normalization time corresponding to the second standard data element and the current day, and d is the set number of days in the time interval that does not need to be decayed. For example, assuming that 7 days can ignore the impact of time on the recommendation score, the value of d is 7.

[0091] Of course, this is just an example of a method for calculating the recommendation score. Other methods for calculating the recommendation score are also applicable to this application and are not limited thereto.

[0092] S105, combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, determining at least one first candidate standard data element for standardizing the target data element from the first data element set and the second data element set.

[0093] For the sake of easy distinction, the standard data element selected from the first data element set and the second data element set is referred to as the first candidate standard data element.

[0094] It is understandable that the matching degree and recommendation score of the standard data element essentially reflect the suitability of the standard data element for standardizing the target data element. Moreover, in many cases, the standard data elements in the first data element set and the second data element set will overlap. Based on this, combined with whether each standard data element in the first data element set and the second data element set exists in both data element sets, and at least one of the matching degree and recommendation score of each standard data element, it is possible to comprehensively determine the standard data elements in the first data element set and the second data element set that are more suitable or more likely to be selected by the user for standardization as candidate standard data elements.

[0095] There are many possible specific implementation methods for determining the first candidate standard data element, and there is no limitation to this.

[0096] For example, in a possible implementation, the first comprehensive score of each standard data element in the first data element set and the second data element set can be determined by combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set. Then, a first candidate standardized list for standardizing the target data element is generated by combining the first comprehensive score of each standard data element.

[0097] The first candidate standardized list includes: at least one first candidate standard data element with a higher first comprehensive score determined from the first data element set and the second data element set.

[0098] Of course, as an optional method, the first candidate standardization list may also include: the first comprehensive score of each first candidate standard data element. Based on this, at least one first candidate standard data element may be sorted and output in combination with the first comprehensive score of each first candidate standard data element, so that the user can select the required standard data element.

[0099] Among them, for any standard data element in the first data element set and the second data element set, if the standard data element exists in both the first data element set and the second data element set, then the first comprehensive score of the standard data element is related to the matching degree and recommendation score of the standard data element; if the standard data element only belongs to the first data element set or the second data element set, then the first comprehensive score of the standard data element is only related to its matching degree or recommendation score.

[0100] Of course, there are many possible ways to determine the first comprehensive score. The following is an example of a possible implementation method:

[0101] First, the matching degree and the recommendation score can be unified into the same numerical range. For example, the matching degree and the recommendation score are both percentage values. For any first standard data element, if the matching degree is a probability value belonging to 0-1, the matching degree can be standardized first.

[0102] For example, the matching degree of the first standard data element may be standardized by the following formula 2, and the matching degree score of the first standard data element after the normalization is the matching degree score':

[0103]

[0104] Wherein, max(score) is the maximum value of the matching degree of all the first standard data elements in the first data element set; min(score) is the minimum value of the matching degree of all the first standard data elements in the first data element set. Of course, if the normalized matching degree has been used as the matching degree of the first standard data element when determining the matching degree corresponding to the first standard data element, there is no need to perform matching degree normalization processing.

[0105] Secondly, for any standard data element in the first data element set and the second data element set, for the matching degree (normalized matching degree) of the standard data element and any score socre(i) in the recommendation score, the post-incentive score Item_socre(i) of the score socre(i) can be calculated by the following formula 3:

[0106] Item_socre(i)=socre(i)+(max_socre-socre(i))*hitBoost (Formula 3);

[0107] Among them, max_score is the set top score. When the standardized matching degree and recommendation score are both in percentage, the top score can be 100. The hitBoost is the set incentive weight. Among them, the same incentive weight can be used for the matching degree and the recommendation score, or the incentive weights of the matching degree and the recommendation score can be set separately as needed.

[0108] Finally, for any standard data element in the first data element set and the second data element set, the average value of all post-stimulation scores corresponding to the standard data element can be calculated, and the calculated score value can be used as the first comprehensive score of the standard data element.

[0109] For example, if the standard data element belongs to both the first data element set and the second data element set, then the standard data element has both the corresponding matching degree and recommendation score, then the average of the post-incentive score of the matching degree and the post-incentive score of the recommendation score of the standard data element can be calculated to obtain the first comprehensive score. If the standard data element only belongs to the first data element set or the second data element set, then the first comprehensive score of the standard data element is the post-incentive score of the matching degree or the post-incentive score of the recommendation score.

[0110] It is understandable that, considering that directly matching the standard data element from the standard data element library based on the characteristic information of the target data element is a relatively accurate data element matching method, in actual applications, the user can also set whether to enable the option of directly recommending a single standard data element as needed. If the user chooses to enable the option of directly recommending a single data element, and only one identical standard data element is matched from the standard data element library and the historical benchmarking record library, then the standard data element can be directly determined as the first candidate standard data element, and there is no need to perform the operation of calculating the first comprehensive score.

[0111] As can be seen from the above, the present application will not only search for the first standard data element that matches the target data element from the standard data element library, but also determine the second standard data elements that have been standardized in the history of the target data element and the number of standardized times that the target data element has been standardized as each second standard data element based on the characteristic information of the target data element. Since the number of standardized times of the second standard data element reflects the number of times the target data element has been standardized as the second standard data element in history, the recommended score of the second standard data element determined based on the number of standardized times of each second standard data element can reflect the suitability of the second standard data element for standardizing the target data element. On this basis, the present application comprehensively considers the matching degree of each first standard data element with the target data element and the recommended score of each second standard data element, determines the target data element for standardization, takes into account the matching situation of the characteristic information of the target data element with the standard data element, and takes into account some behavioral information of the target data element that has been standardized in history, so that the standard data element suitable for standardizing the target data element can be determined more accurately, and the standard data element used to standardize the data element can be recommended more accurately.

[0112] In addition, since the target data element is a non-standardized data element, the format or content of the characteristic information of the target data element is not standardized, which may result in the inability to accurately match the characteristic information based on the target data element from the standard data element library or even to match the standard data element. However, since the characteristic information of the non-standard data element is recorded in the historical benchmarking record library, it is easier to accurately locate the matching non-standard data element from the historical benchmarking record library based on the characteristic information of the target data element, and then obtain the information of the standard data element that the non-standard data element that matches the target data element has been standardized to in history, so as to reduce the situation where the standard data element used for standardization cannot be determined because the characteristic information of the target data element cannot be covered by the standard data element library.

[0113] It can be understood that in the above embodiments of the present application, the first candidate standard data element is obtained by directly matching the standard database meta-repository and the historical benchmarking record library using the characteristic information of the target data element, that is, it is obtained by precise matching based on the characteristic information of the target data element.

[0114] However, in actual applications, due to various reasons such as the non-standardization of the characteristic information of the target data element, it may be impossible to match the standard data element from the standard data element library and the historical benchmarking record library based on the characteristic information of the target data element. Moreover, if the target data element has not been standardized in history, it may also be impossible to match the historically adopted standard data element from the historical benchmarking record library.

[0115] Based on this, in order to improve the probability of matching the standard data element from the standard data element library based on the characteristic information of the target data element, the present application also provides a method of fuzzy matching the standard data element library based on the characteristic information of the target data element. On this basis, the present application can comprehensively determine the candidate standard data element for standardizing the target data element by combining the standard data elements matched by the two methods of precise matching and fuzzy matching.

[0116] Furthermore, the present application can also match the standard data elements corresponding to different non-standard data elements in the historical benchmarking record library based on the characteristic information of the target data elements, thereby obtaining the matched standard data elements, and then combine the various standard data elements obtained by precise matching and fuzzy matching to finally determine the standard data elements used to standardize the target data elements.

[0117] The following is an introduction to the process of combining exact matching with fuzzy matching to determine standard data elements with the help of a flowchart.

[0118] like Figure 3 As shown, it shows another flow chart of a method for determining a standard data element of the present application. The method of this embodiment may include:

[0119] S301, obtaining at least one feature information of a target data element to be standardized.

[0120] S302: Based on each feature information of the target data element, determine a first data element set matching the target data element from a standard data element library.

[0121] The first data element set includes: each first standard data element in the standard data element library that matches the target data element, and the matching degree between the first standard data element and the target data element.

[0122] S303: Based on each feature information of the target data element, determine a second data element set corresponding to the target data element from a historical benchmarking record library.

[0123] The second data element set includes: each second standard data element after the target data element has been standardized in history and the number of standardizations corresponding to the second standard data element.

[0124] S304: Determine a recommendation score of the second standard data element according to the number of normalizations of the second standard data element in the second data element set.

[0125] Among them, the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element.

[0126] S305 , combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, to determine a first comprehensive score of each standard data element in the first data element set and the second data element set.

[0127] S306: Generate a first candidate standardization list for standardizing the target data element in combination with the first comprehensive score of each standard data element.

[0128] The first candidate standardized list includes: at least one first candidate standard data element with a higher first comprehensive score determined from the first data element set and the second data element set, and the first comprehensive score of each first candidate standard data element.

[0129] The above steps S302 to S306 are actually a process of accurately matching the standard data element library and the historical benchmarking database based on the characteristic information of the target data element to obtain the candidate standard data element.

[0130] The above steps S301 to S306 can refer to the relevant description of the previous embodiment, and will not be repeated here.

[0131] S307: construct a feature segmentation set of the target data element based on at least one feature information of the target data element.

[0132] The feature word set includes at least one feature word segmented from at least one feature information segmentation.

[0133] The purpose of segmenting at least one feature information is to reduce the situation where a single feature information as a whole cannot be matched to a standard data element with similar features.

[0134] For example, in a possible implementation, at least one feature information of the target data element may be first combined into a text; then, the text may be segmented to obtain a feature segmentation set consisting of at least one feature segmentation obtained from the text segmentation.

[0135] Furthermore, considering that the format of the feature information of the target data element may be non-standard, which is not conducive to hitting the feature information of the standard data element from the standard data element library, based on this, the present application also needs to standardize the feature information of the target data element before combining at least one feature information of the target data element into text, and then perform word segmentation and construct a feature word segmentation set.

[0136] like Figure 4 , is a schematic diagram of an implementation process of constructing a feature segmentation set based on at least one feature information of a target data element in the present application, the process comprising:

[0137] S41, for each feature information of the target data element, based on multiple standard features stored in the standard feature library, determine a standard feature matching the feature information, and standardize the feature information based on the standard feature.

[0138] Among them, the standard feature library can be a corpus constructed based on the collected standard feature names of different scenarios and industries. Therefore, the standard feature library stores standardized names of different feature information.

[0139] In an example, multiple standard features in the standard feature library can also be divided into three types: trunk type, branch type and leaf type.

[0140] Among them, for the standard features of the trunk type, if the feature information of the target data element matches the standard feature, the feature information will be completely replaced with the standard feature information. For example, the definition of "name", the Chinese name field of the data element in different business scenarios has different descriptions such as "name", "nickname", "flower name", "nickname", etc., but the semantics of the descriptions are consistent, then these feature information will be replaced with the only standard semantic feature "name".

[0141] For branch-type Branch, the standard feature is a feature with a modified noun. When matching the standard feature based on the feature information of the target data element, it is possible to detect whether the feature information of the target data element contains some feature information that matches the standard feature of this type. If so, the part of the feature information is replaced with the standard feature. For example, for the feature information "Chinese name of the administrative division of the place of origin", the standard features "implementation code" and "name" are matched through the inclusion rule. It is only necessary to replace "administrative division" with "city and county code" and "Chinese name" with "name", and finally standardize it to "city and county code name of the place of origin".

[0142] For the standard features of the leaf type Leaf, after the feature information of the target data element matches this type of standard features, the suffix in the feature information can be expanded, for example, "xxxid" is adapted to the ending "id" and expanded to "xxxid primary key".

[0143] As shown in Table 2 below, Table 2 is the relevant information of various types of standard features in the standard feature library.

[0144]

[0145]

[0146] As shown in Table 2, the second column is the name of each standard feature, and the first column is the description of the non-standard feature information corresponding to the standard feature. If the feature information of the target data element matches the non-standard feature information of the standard feature, the feature information of the target data element can be standardized based on the standard feature.

[0147] Among them, the part-of-speech tag represents the category of each standard feature.

[0148] In the present application, for each feature information of the target data element, standard feature matching can be performed in the order of Trunk type, Branch type, and Leaf type. Specifically, it can be first detected whether there is a standard feature matching the feature information in the standard features of the trunk type. If so, the feature is standardized based on the matched standard feature; if there is no standard feature matching the feature information in the standard features of the trunk type, continue to monitor whether there is a standard feature matching the feature information in the standard features of the Branch type, and if it still does not exist, detect whether there is a standard feature matching the feature information in the standard features of the Leaf type.

[0149] It can be understood that, through step S41, at least one standardized feature information corresponding to the target data element can be finally obtained.

[0150] S42, combining at least one feature information of the target data element into text.

[0151] S43, segmenting the text to obtain a feature segmentation set consisting of at least one feature segmentation obtained by segmenting the text.

[0152] For example, assuming that the English code of the target data element "payment amount" is "payNum" and its Chinese name is "payment amount", the feature information of the target data element is standardized and cleaned and finally formed into a text "payment amount amount limit narrow code payNum". By segmenting the text, multiple feature segmentations can be obtained, and these multiple feature segmentations can constitute a feature segmentation set. For example, the feature segmentation set can be {payment amount amount limit narrow code paynum}, and the feature segmentation set can be regarded as a vector composed of multiple feature segmentations.

[0153] There are many ways to segment text. For example, the present application may use IK segmentation method for segmentation, and there is no limitation on this.

[0154] S308: Determine a third data element set similar to the target data element in the standard data element library based on the feature segmentation set.

[0155] The third data element set includes: at least one third standard data element having a high similarity between a feature information set and the feature segmentation set, and a first similarity between the feature information set of the third standard data element and the feature segmentation set.

[0156] The characteristic information set of the standard data element includes each characteristic information of the standard data element.

[0157] The similarity between the feature segmentation set and the feature information set of the standard data element can be calculated using a currently commonly used similarity calculation algorithm, such as a vector space model (VSM) model or a BIM model, without limitation.

[0158] It can be understood that since the feature segmentation set contains each segmentation after at least one feature information combination, the standard data element is selected based on the similarity between the feature segmentation set composed of these segmentations and the set composed of each feature information of the standard data element. It is not an exact match of the standard data element, but it can reduce the situation where the standard data element cannot be matched due to directly matching the feature information of the target data element with the feature information of the standard data element.

[0159] It is understandable that, considering that the content of each standard data element and its characteristic information in the standard data element library is relatively large, it is not conducive to quickly retrieving each third standard data element. The present application can also pre-construct a standard data element index library corresponding to the standard data element library.

[0160] The standard data element index library may store data element index files of different standard data elements, and the data element index files of the standard data elements store characteristic information of the standard data elements recorded in the standard data element library.

[0161] In one example, the present application may use the Lucene engine to create an index for each standard data element in the standard data element library. The details may be as follows:

[0162] First, for each standard data element, the English code of the standard data element is used as the file name of the data element index file of the standard data element, and the characteristic information such as "English code", "Chinese name", "synonyms" and "description" of the standard data element is used as the content item of the data element index file.

[0163] Secondly, Lucene is used to create a corresponding index for the data element index file of each standard data element, wherein the file name and file content of the data element index file are written into the index library as different fields in the index.

[0164] Among them, the standard data element index library can use the IK word segmentation engine to perform index query.

[0165] Based on the constructed standard data element index library, this embodiment can directly determine a third data element set whose data element index file is similar to the feature segmentation set from the standard data element index library based on the data element index files corresponding to different standard data elements stored in the standard data element index library.

[0166] Correspondingly, the third data element set includes: at least one third standard data element having a high similarity between the data element index file and the characteristic word segmentation set, and the first similarity between the data element index file of the third standard data element and the characteristic word segmentation set.

[0167] It can be understood that since the standard data element index library uses each feature of each standard data element as the content item of the data element index file, each data element index file can be directly indexed and queried based on the feature segmentation set, which is conducive to improving the matching speed, so that the third data element set can be determined more quickly.

[0168] It should be noted that this embodiment is explained by taking the example of fuzzy matching of the standard data element library and the historical benchmarking record library based on the characteristic word segmentation set of the target data element. However, it can be understood that if the third standard data element set is matched only based on the characteristic word segmentation set of the target data element, then it can also be combined with the first similarity corresponding to each third standard data element in the third data element set and the first comprehensive score of each first candidate standard data element in the first candidate standardization list, and at least one target standard data element for standardizing the target data element is determined from the third data element set and the first candidate standardization list, so that there is no need to perform subsequent operations.

[0169] S309: Based on the feature segmentation set, determine a fourth data element set in the historical benchmarking record library that is similar to the target data element.

[0170] The fourth data element set includes: at least one fourth standard data element whose feature information of the corresponding non-standard data element has a high similarity with the feature segmentation set and a second similarity between the feature information of the non-standard data element corresponding to the fourth standard data element and the feature segmentation set.

[0171] In step S309, for each standard data element appearing in the historical benchmarking record library, the feature information of each non-standard data element corresponding to the standard data element can be taken as a set, and then the similarity is calculated with the feature segmentation set, and finally at least one fourth standard data element whose feature information of the corresponding non-standard data element has a high similarity with the feature segmentation set is determined.

[0172] In one possible implementation, in order to increase the speed of determining the fourth standard data element, the embodiment of the present application may also pre-construct a historical benchmarking record index library based on at least one standard data element corresponding to the characteristic information of each non-standard data element in the historical benchmarking record library.

[0173] The historical benchmarking record index library stores: historical benchmarking index files corresponding to each standard data element appearing in the historical benchmarking record library. The historical benchmarking index files of each standard data element include: at least one standard data element corresponding to the feature information of different non-standard data elements in the historical benchmarking database, and feature information of each non-standard data element corresponding to the standard data element determined.

[0174] Accordingly, a fourth data element set whose historical benchmarking index files are similar to the characteristic segmentation set can be directly determined from the historical benchmarking index library, thereby improving the speed of retrieving the fourth data element set.

[0175] In this possible implementation, the fourth data element set includes: at least one fourth standard data element having a high similarity between the historical benchmarking index file and the feature segmentation set, and a second similarity between the historical benchmarking index file of the fourth standard data element and the feature segmentation set.

[0176] S310, determining a second comprehensive score for each standard data element in the third data element set and the fourth data element set based on a first similarity corresponding to each third standard data element in the third data element set and a second similarity corresponding to each fourth standard data element in the fourth data element set.

[0177] The process of determining the second comprehensive score may be similar to the process of determining the first comprehensive score.

[0178] For example, first, the first similarity and the second similarity can be standardized respectively according to Formula 2. Secondly, the post-incentive score corresponding to the first similarity of each standard data element and the post-incentive score corresponding to the second similarity of each standard data element can be determined and calculated respectively according to Formula 3. Finally, for each standard data element in the third data element set and the fourth data element set, the average of the post-incentive score of the first similarity and the post-incentive score of the second similarity can be calculated, and the score value is the second comprehensive score of the standard data element.

[0179] Among them, if a standard data element only belongs to the third data element set or the fourth data element set, then its post-incentive score of the first similarity or the post-incentive score of the second similarity can be considered to be zero. On this basis, the second comprehensive score of the standard data element is actually its post-incentive score of the first similarity or the post-incentive score of the second similarity.

[0180] S311, generating a second candidate normalization list for normalizing the target data element.

[0181] The second candidate standardized list includes: at least one second candidate standard data element with a higher second comprehensive score determined from the third data element set and the fourth data element set, and the second comprehensive score of the second candidate standard data element.

[0182] In this embodiment, another possible candidate standardization list is determined by fuzzy matching from S307 to S311 to make up for the problem that the candidate standard data elements cannot be matched or the matching effect is poor through the precise matching method of steps S302 to S306.

[0183] It can be understood that steps S302 to S306 and steps S307 to S311 can be executed synchronously, or steps S302 to S306 can be executed first and then steps S307 to S311; or steps S307 to S311 can be executed first and then steps S302 to S306.

[0184] S312, combining the first comprehensive score of each first candidate standard data element in the first candidate standardization list and the second comprehensive score of the second candidate standardization data element in the second candidate standardization list, to determine the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list.

[0185] It can be understood that the overall score of the candidate standard data element is determined by combining whether each candidate standard data element in the first candidate standardization list and the second candidate standardization list appears in both lists at the same time, and at least one of the first comprehensive score and the second comprehensive score of each candidate standard data element. The overall score can reflect the integration suitability of the candidate standard data element for standardizing the target data element.

[0186] There are many possible ways to determine the overall score.

[0187] For example, in one possible implementation, weights of the first comprehensive score and the second comprehensive score can be set, and then, for each candidate standard data element in the first candidate standardized list and the second candidate standardized list, a weighted sum of the first comprehensive score and the second comprehensive score of the candidate standard data element can be calculated, and the result of the weighted sum is used as the overall score of the candidate standard data element.

[0188] Of course, if a candidate standard data element only belongs to the first candidate standardization list or the second candidate standardization list, then during weighted summation, the value of the first comprehensive score or the second comprehensive score that the candidate standard data element does not have can be considered to be zero.

[0189] In another possible implementation, for each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, a first weight and a second weight corresponding to the candidate standardized data element can be determined based on the feature information of the candidate standardized data element and at least one of the first comprehensive score and the second comprehensive score of the candidate standardized data element using a pre-trained weight evaluation model.

[0190] Among them, if a candidate standardized data element only has a first comprehensive score but not a second comprehensive score, its second comprehensive score can be considered to be zero; if a candidate standard data element only has a second comprehensive score, its first comprehensive score can be considered to be zero, so that the first comprehensive score, the second comprehensive score and reward and punishment score of the candidate standard data element are all input into the weight evaluation model to predict the two weights.

[0191] The first weight is the weight proportion of the first comprehensive score of the candidate standard data element, and the second weight is the weight proportion of the second comprehensive score of the candidate standard data element.

[0192] The weight evaluation model is trained by using feature information, a first comprehensive score and a second comprehensive score corresponding to a plurality of data element samples labeled with labels of whether they are selected by the user. The data element samples may be a plurality of standard data elements recommended to the user determined in history, and the labels of the data element samples indicate whether the data element is selected by the user as the standard data element.

[0193] The weight evaluation model may be obtained by training a random forest or an extreme gradient boosting (eXtreme GradientBoosting, XGBOOST) model.

[0194] S313, combining the overall scores of the candidate standard data elements in the first candidate standardization list and the second candidate standardization list, and determining at least one target standard data element from the first candidate standardization list and the second candidate standardization list for standardizing the target data element.

[0195] For example, a set number of candidate standard data elements with higher overall scores may be selected as target standard data elements, so as to recommend the target standard data elements to the user for selection.

[0196] In this embodiment, on the basis of matching the standard data elements directly from the standard data element library and the historical benchmarking records in combination with the characteristic information of the target data element to be standardized, the text composed of the characteristic information of the target data element will be segmented, and based on the characteristic segmentation set composed of the individual segmentations segmented from the text, the standard data element library and the historical benchmarking records will be fuzzy matched, so that the standard data elements matching the target data elements can be queried more comprehensively, and the situation where the standard data elements cannot be matched due to the fact that the characteristic information based on the target data elements is not covered by the standard data element library can be reduced.

[0197] Moreover, combining the comprehensive scores of the standard data elements matched by these two methods to determine the target standard data elements ultimately used to standardize the target data elements is conducive to more comprehensive and accurate selection of target standard data elements and improving the applicability of the determined target standard data elements to the standardized target data elements.

[0198] It is understandable that the standard data element suitable for standardizing the target data element generally belongs to the same entity category as the target data element. On this basis, the present application can also comprehensively consider whether the entity category of each candidate standard data element in the first candidate standardization list and the second candidate standardization list is consistent with the entity category of the target data element to determine the overall score of the candidate standard data element.

[0199] like Figure 5 , which shows a schematic diagram of an implementation process of determining the overall score of a candidate standard data element in the present application. The method of this embodiment may include:

[0200] S501, determining the entity category to which the target data element belongs based on at least one feature information of the target data element and a pre-built entity rule base.

[0201] The entity category to which the data element belongs can be used to characterize the type of object guaranteed by the data element.

[0202] The entity rule base records the feature matching rules that feature information of different entity categories must satisfy. If at least one feature information of a target data element matches a feature matching rule corresponding to a certain entity category in the entity rule base, then the target data element belongs to the entity category.

[0203] In an example, the data format recorded in the entity rule library may be as shown in the following Table 1:

[0204] Table 3

[0205]

[0206] In Table 3, each entity name corresponds to an entity type (also called an entity category) and the regular expression that the characteristic information belonging to the entity type needs to satisfy. For example, taking the ID card number as an example, the entity type of the ID card number entity is "person". If the characteristic information of the target data element to be standardized can match the regular expression corresponding to the ID card number, then the entity type of the target data element is "person".

[0207] S502: Determine the entity category of each candidate standard data element in the first candidate standardization list and the second candidate standardization list.

[0208] It is understandable that if the standard data element repository stores the entity type of the standard data element, then the entity category corresponding to the candidate standard data element can be directly queried from the standard data element repository.

[0209] If the entity type of the standard data element is not stored in the standard data element library, the entity category corresponding to the candidate standard data element can be matched from the entity rule library according to the feature information of the candidate standard data element.

[0210] S503: For each candidate standard data element in the first candidate standardization list and the second candidate standardization list, determine a reward or punishment score for the candidate standard data element.

[0211] If the entity category of the candidate standard data element is the same as the entity category of the target data element, the reward or penalty score of the candidate standard data element is a positive number, such as a set positive score value. If the entity type of the candidate standard data element is different from the entity category of the target data element, the reward or penalty score of the candidate standard data element is a negative number, such as a set negative score value.

[0212] S504, combining the first comprehensive score and reward and punishment score of each first candidate standard data element in the first candidate standardization list, and the second comprehensive score and reward and punishment score of the second candidate standard data element in the second candidate standardization list, to determine the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list.

[0213] For example, the overall score can be determined by combining whether the candidate standardized data element belongs to both candidate standardized lists, its comprehensive score, and the value of the reward and punishment score. For example, for a candidate standardized data element included in both the first candidate standardized list and the second candidate standardized list, if the reward and punishment score of the candidate standardized data element is a positive number, the higher the first comprehensive score and the second comprehensive score of the candidate standardized data element, the higher the overall score of the candidate standardized data element.

[0214] In one example, for each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, a first weight, a second weight, and a third weight corresponding to the candidate standardized data element can be determined based on the feature information of the candidate standardized data element and at least two of the first comprehensive score, the second comprehensive score, and the reward and punishment score of the candidate standardized data element using a pre-trained weight evaluation model.

[0215] The first weight and the second weight correspond to the weight proportion of the first comprehensive score and the second comprehensive score of the candidate standardized data element, respectively, as described above. The third weight is the weight proportion of the reward and punishment score of the candidate standard data element.

[0216] Similar to the above, the weight evaluation model is trained by using the feature information, the first comprehensive score, the second comprehensive score and the reward and punishment scores corresponding to multiple data element samples marked with labels of whether they are selected by the user.

[0217] Correspondingly, for each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, the overall score of the candidate standard data element is determined by combining the first weight, second weight and third weight corresponding to the candidate standard data element, as well as the first comprehensive score, second comprehensive score and reward and punishment score of the candidate standard data element.

[0218] It is understandable that after the overall scores of the candidate standard data elements are determined, at least one target standard data element for standardizing the target data elements may also be determined in combination with the overall scores of the candidate standard data elements.

[0219] exist Figure 5 The overall score of the candidate standard data element is determined by comprehensively considering whether the entity type of the candidate standard data element is consistent with that of the target data element, so that the overall score can more accurately reflect the suitability of the candidate standard data element as the standard data element of the target data element, which is conducive to more accurately determining the standard data element used to standardize the target data element.

[0220] In order to facilitate understanding of the solution of the present application, the following is an explanation in conjunction with the implementation block diagram of the solution of the present application. Figure 6 As shown, it shows a schematic diagram of the implementation principle framework of the method for determining standard data elements provided in an embodiment of the present application.

[0221] Depend on Figure 6 It can be seen that after obtaining the feature information of the target data element to be standardized, the present application will perform fine matching and fuzzy matching based on the feature information.

[0222] On the one hand, in the process of fine matching, the present application will match standard data elements with similar characteristic information to the target data element from the standard data element library and the historical benchmarking record library based on the characteristic information of the target data element.

[0223] In the present application, at least one feature information of the target data element may all be one or more feature information input by the user, or may be multiple feature information mined on the basis of obtaining at least one feature information input by the user.

[0224] For example, the characteristic information of the target data element that can be obtained by the present application may include at least: at least one of the English code of the target data element and the Chinese name of the target data element.

[0225] The at least one characteristic information of the target data element may also include: a description of the target data element, a historical standard data element to which the target data element is historically standardized, and information of a reference data element of the same category as the target data element.

[0226] Among them, the English code, Chinese name, description and reference data element information of the target data element can be input by the user.

[0227] The historical standard data element corresponding to the target data element may be input by the user, or may be queried from the historical standardization records on the user side according to the English code or Chinese name of the target data element.

[0228] Furthermore, in order to improve the accuracy of standard data element matching, the present application can also obtain characteristic information of the target data element and analyze the code length label category, entity name and entity category of the target data element.

[0229] The code length label category of the target data element may be determined in combination with the lengths of each reference data element corresponding to the target data element.

[0230] For example, if the difference between the maximum value of the length of each reference data element and the minimum value of the length of each reference data element is zero, it can be determined that the code length label category of the target data element is a fixed code.

[0231] If the length of each reference data element is less than or equal to the narrow code confidence (such as 10), the code length tag category of the target data element is narrow code.

[0232] The entity name of the target data element may be matched from an entity rule base based on other characteristic information of the target data element; or the entity name may be identified through named entity recognition (NER) technology.

[0233] The entity category of the target data element can be obtained by querying the entity rule library, as described in the previous embodiment.

[0234] Based on the above, the present application can match standard data elements with similar feature information from the standard data element library according to the English code, Chinese name, information of historical standard data elements and entity type of the target data element, and obtain the matching degree between the feature information of the standard data element and the feature information of the target data element.

[0235] At the same time, according to the English code (or Chinese name) of the target data element, the non-standard data element whose English code matches the English code of the target data element can be matched from the historical benchmarking record library, and the standard data elements to which the non-standard data element has been standardized in history and the number of standardizations corresponding to each standard data element can be determined. Then, combined with the number of standardizations of each standard data element matched from the historical benchmarking records, the recommendation score of each standard data element can be determined.

[0236] like Figure 6 As shown in the precise matching part, combined with one or two of the matching degrees and recommended scores of each standard data element matched from the standard data element library and the historical benchmarking record library, the precise matching part can finally determine the first standardized list, which includes the first comprehensive scores of multiple first candidate standardized data elements.

[0237] Figure 6 The specific implementation of exact matching can be found in the previous Figure 3 Relevant introduction of steps S302 to S306 in the embodiment.

[0238] On the other hand, in the fuzzy matching process, the present application constructs a characteristic word segmentation set of the target data element based on the characteristic information of the target data element, searches and matches the standard data element index library and the historical benchmark record index library respectively, and finally generates a second standardized list by combining the standard data elements obtained by searching the two index libraries. The second standardized list includes the second comprehensive scores of multiple second candidate data elements.

[0239] On the other hand, for each candidate standard data element in the first standardized list and the second standardized list obtained by fuzzy matching and exact matching, the present application can also Figure 5 The process method shown in the embodiment determines the reward and punishment scores of the candidate standard data elements.

[0240] like Figure 6 As shown, if the candidate standard data element and the target data element belong to the same entity category, the reward and punishment score of the candidate standard data element is actually a reward score, and the reward score is a positive number; otherwise, the reward and punishment score of the candidate standard data element is a penalty score, and the penalty score is a negative number.

[0241] On the basis of the above, this application combines the first comprehensive score, the second comprehensive score and the reward and punishment score of each candidate standard data element to perform weighted score integration, and finally obtains the overall score of each candidate standard data element. For details, see Figure 5 Relevant introduction of step S504 in the embodiment.

[0242] In combination with the overall scores of the candidate standard data elements, at least one target standard data element suitable for recommendation as a target data element for standardization may be determined, and a ranking of the at least one target standard data element may be determined.

[0243] On the other hand, corresponding to the method for determining standard data elements provided in the embodiments of the present application, the present application also provides a device for determining standard data elements.

[0244] like Figure 7 As shown, it shows a schematic diagram of a composition structure of a device for determining a standard data element provided in an embodiment of the present application. The device of this embodiment may include:

[0245] The information obtaining unit 701 is used to obtain at least one feature information of the target data element to be standardized;

[0246] A first set determining unit 702 is configured to determine a first data element set matching the target data element from a standard data element library based on each feature information of the target data element, wherein the first data element set includes: each first standard data element matching the target data element in the standard data element library, and a matching degree between the first standard data element and the target data element;

[0247] The second set determination unit 703 is used to determine the second data element set corresponding to the target data element from the historical benchmarking record library based on each feature information of the target data element, wherein the historical benchmarking record library stores: feature information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized to each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to;

[0248] A recommendation scoring unit 704 is used to determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element;

[0249] The first data element determination unit 705 is used to determine at least one first candidate standard data element for standardizing the target data element from the first data element set and the second data element set, based on the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set.

[0250] In a possible implementation, the historical benchmarking record library further stores: the most recent normalization time when the non-standard data element was most recently normalized to each standard data element in history;

[0251] Correspondingly, the second data element set determined by the second set determination unit also includes the most recent standardization time corresponding to the second standard data element;

[0252] The recommended scoring unit includes:

[0253] The recommendation score subunit is used to determine the recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized and the time of the most recent standardization, wherein the more times the second standard data element is standardized and the shorter the time from the most recent standardization to the current time, the higher the recommendation score of the second standard data element.

[0254] In yet another possible implementation, the first data element determining unit includes:

[0255] A first comprehensive scoring unit, configured to determine a first comprehensive score for each standard data element in the first data element set and the second data element set by combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set;

[0256] The first list generating unit is used to generate a first candidate standardized list for standardizing the target data element, wherein the first candidate standardized list includes: at least one first candidate standard data element with a higher first comprehensive score determined from the first data element set and the second data element set.

[0257] In yet another possible implementation, the first candidate standardized list generated by the first list generating unit further includes: a first comprehensive score of the first candidate standard data element;

[0258] The device also includes:

[0259] A word segmentation set construction unit, configured to construct a characteristic word segmentation set of the target data element based on at least one characteristic information of the target data element, wherein the characteristic word set includes at least one characteristic word segmented from the at least one characteristic information;

[0260] A third set determination unit is used to determine, based on the characteristic segmentation set, a third data element set similar to the target data element in the standard data element library, wherein the third data element set includes: at least one third standard data element whose characteristic information set has a high similarity with the characteristic segmentation set, and a first similarity between the characteristic information set of the third standard data element and the characteristic segmentation set; the characteristic information set of the standard data element includes each characteristic information of the standard data element;

[0261] A target determination unit is used to determine at least one target standard data element for standardizing the target data element from the third data element set and the first candidate standardization list based on the first similarity corresponding to each third standard data element and the first comprehensive score of each first candidate standard data element in the first candidate standardization list.

[0262] In yet another possible implementation, the device further includes:

[0263] a fourth set determination unit, configured to determine, before the target determination unit determines at least one target standard data element for standardizing the target data element, a fourth data element set similar to the target data element in the historical benchmarking record library based on the feature segmentation set, wherein the fourth data element set includes: at least one fourth standard data element whose feature information of the corresponding non-standard data element has a high similarity with the feature segmentation set and a second similarity between the feature information of the non-standard data element corresponding to the fourth standard data element and the feature segmentation set;

[0264] Accordingly, the target determination unit includes:

[0265] a second comprehensive scoring unit, configured to determine a second comprehensive score for each standard data element in the third data element set and the fourth data element set based on a first similarity corresponding to each third standard data element in the third data element set and a second similarity corresponding to each fourth standard data element in the fourth data element set;

[0266] A second list generating unit is used to generate a second candidate standardized list for standardizing the target data element, wherein the second candidate standardized list includes: at least one second candidate standard data element with a higher second comprehensive score determined from the third data element set and the fourth data element set, and the second comprehensive score of the second candidate standard data element;

[0267] An overall scoring unit, configured to determine an overall score of each candidate standard data element in the first candidate standard list and the second candidate standard list by combining a first comprehensive score of each first candidate standard data element in the first candidate standard list and a second comprehensive score of a second candidate standard data element in the second candidate standard list;

[0268] The target comprehensive determination unit is used to combine the overall scores of each candidate standard data element in the first candidate standardization list and the second candidate standardization list, and determine at least one target standard data element from the first candidate standardization list and the second candidate standardization list for standardizing the target data element.

[0269] In yet another possible implementation, the device further includes:

[0270] A category query unit, used for determining the entity category to which the target data element belongs based on at least one feature information of the target data element and a pre-constructed entity rule base before the overall scoring unit determines the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list, wherein the entity rule base records feature matching rules that feature information of different entity categories needs to satisfy;

[0271] A category determination unit, configured to determine an entity category of each candidate standard data element in the first candidate standardization list and the second candidate standardization list;

[0272] a reward and punishment score determination unit, configured to determine, for each candidate standard data element in the first candidate standardization list and the second candidate standardization list, a reward and punishment score of the candidate standard data element, wherein if the entity category of the candidate standard data element is the same as the entity category of the target data element, the reward and punishment score of the candidate standard data element is a positive number; otherwise, the reward and punishment score of the candidate standard data element is a negative number;

[0273] Correspondingly, the overall scoring unit is specifically used to determine the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list by combining the first comprehensive score and reward and punishment score of each first candidate standard data element in the first candidate standardization list, and the second comprehensive score and reward and punishment score of the second candidate standard data element in the second candidate standardization list.

[0274] In another possible implementation, the overall scoring unit includes

[0275] a weight determination subunit, for determining, for each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, a first weight, a second weight, and a third weight corresponding to the candidate standardized data element based on feature information of the candidate standardized data element and at least two of the first comprehensive score, the second comprehensive score, and the reward and punishment score of the candidate standardized data element, using a pre-trained weight evaluation model;

[0276] an overall scoring subunit, for determining, for each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, an overall scoring of the candidate standardized data element by combining the first weight, the second weight and the third weight corresponding to the candidate standardized data element, and the first comprehensive score, the second comprehensive score and the reward and punishment score of the candidate standardized data element;

[0277] The first weight is the weight proportion of the first comprehensive score of the candidate standard data element, the second weight is the weight proportion of the second comprehensive score of the candidate standard data element, and the third weight is the weight proportion of the reward and punishment score of the candidate standard data element;

[0278] The weight evaluation model is trained by using feature information corresponding to a plurality of data element samples labeled with whether they are selected by the user, a first comprehensive score, a second comprehensive score, and reward and punishment scores.

[0279] In another possible implementation, the third set determining unit is specifically configured to determine, based on data element index files corresponding to different standard data elements stored in the standard data element index library, a third data element set whose data element index files are similar to the feature segmentation set from the standard data element index library;

[0280] The data element index file of the standard data element stores the characteristic information of the standard data element recorded in the standard data element library;

[0281] The third data element set includes: at least one third standard data element having a high similarity between a data element index file and the characteristic word segmentation set, and a first similarity between the data element index file of the third standard data element and the characteristic word segmentation set.

[0282] In another possible implementation, the fourth set determination unit is specifically configured to determine, based on historical benchmarking index files corresponding to different standard data elements stored in the historical benchmarking record index library, a fourth data element set whose historical benchmarking index files are similar to the feature segmentation set from the historical benchmarking index library;

[0283] The historical benchmarking index file corresponding to the standard data element includes: characteristic information of each non-standard data element corresponding to the standard data element determined based on at least one standard data element corresponding to characteristic information of different non-standard data elements in the historical benchmarking database;

[0284] The fourth data element set includes: at least one fourth standard data element having a high similarity between the historical benchmarking index file and the characteristic word segmentation set, and a second similarity between the historical benchmarking index file of the fourth standard data element and the characteristic word segmentation set.

[0285] In another possible implementation, the word segmentation set construction unit includes:

[0286] A text combining unit, used for combining at least one characteristic information of the target data element into text;

[0287] The text segmentation unit is used to segment the text to obtain a feature segmentation set consisting of at least one feature segmentation obtained by segmenting the text.

[0288] In yet another possible implementation, the device further includes:

[0289] The feature cleaning unit is used to determine, for each feature information of the target data element, a standard feature matching the feature information based on a plurality of standard features stored in a standard feature library before the text combining unit combines the at least one feature information of the target data element into text, and standardize the feature information based on the matched standard feature to obtain at least one standardized feature information corresponding to the target data element.

[0290] The apparatus for determining standard data elements provided in the embodiment of the present application can be applied to a computer device. The computer device can be an independent server, or a server in a cloud platform or a distributed system. Optionally, Figure 8 The hardware structure block diagram of the computer device to which the solution of the present application is applicable is shown. Figure 8 , the hardware structure of the computer device may include: at least one processor 801, at least one communication interface 802, at least one memory 803 and at least one communication bus 804;

[0291] In the embodiment of the present application, the number of the processor 801, the communication interface 802, the memory 803, and the communication bus 804 is at least one, and the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804;

[0292] The processor 801 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;

[0293] The memory 803 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0294] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0295] Obtaining at least one feature information of a target data element to be standardized;

[0296] Based on each feature information of the target data element, determine a first data element set matching the target data element from a standard data element library, wherein the first data element set includes: each first standard data element matching the target data element in the standard data element library, and a matching degree between the first standard data element and the target data element;

[0297] Based on each characteristic information of the target data element, a second data element set corresponding to the target data element is determined from a historical benchmarking record library, wherein the historical benchmarking record library stores: characteristic information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized into each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to;

[0298] Determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element;

[0299] In combination with the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, at least one first candidate standard data element for standardizing the target data element is determined from the first data element set and the second data element set.

[0300] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0301] The embodiment of the present application further provides a storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0302] Obtaining at least one feature information of a target data element to be standardized;

[0303] Based on each feature information of the target data element, determine a first data element set matching the target data element from a standard data element library, wherein the first data element set includes: each first standard data element matching the target data element in the standard data element library, and a matching degree between the first standard data element and the target data element;

[0304] Based on each characteristic information of the target data element, a second data element set corresponding to the target data element is determined from a historical benchmarking record library, wherein the historical benchmarking record library stores: characteristic information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized into each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to;

[0305] Determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element;

[0306] In combination with the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, at least one first candidate standard data element for standardizing the target data element is determined from the first data element set and the second data element set.

[0307] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0308] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0309] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0310] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a standard data element, characterized in that: include: Obtaining at least one feature information of a target data element to be standardized; Based on each feature information of the target data element, determine a first data element set matching the target data element from a standard data element library, wherein the first data element set includes: each first standard data element matching the target data element in the standard data element library, and a matching degree between the first standard data element and the target data element; Based on each characteristic information of the target data element, a second data element set corresponding to the target data element is determined from a historical benchmarking record library, wherein the historical benchmarking record library stores: characteristic information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized into each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to; Determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element; In combination with the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, at least one first candidate standard data element for standardizing the target data element is determined from the first data element set and the second data element set.

2. The method according to claim 1, characterized in that The historical benchmarking record library also stores: the most recent standardization time when the non-standard data element was most recently standardized to each standard data element in history; The second data element set also includes: the most recent standardization time corresponding to the second standard data element; The determining the recommendation score of the second standard data element according to the number of normalizations of the second standard data element in the second data element set includes: The recommended score of the second standard data element is determined according to the number of times the second standard data element in the second data element set is standardized and the time of the most recent standardization, wherein the more times the second standard data element is standardized and the shorter the time from the most recent standardization to the current time, the higher the recommended score of the second standard data element.

3. The method according to claim 1, characterized in that The determining, from the first data element set and the second data element set, at least one first candidate standard data element for standardizing the target data element by combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set, comprises: Determine a first comprehensive score for each standard data element in the first data element set and the second data element set by combining the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set; A first candidate standardization list for standardizing the target data element is generated, wherein the first candidate standardization list includes: at least one first candidate standard data element with a higher first comprehensive score determined from the first data element set and the second data element set.

4. The method according to claim 3, characterized in that The first candidate standardization list also includes: a first comprehensive score of the first candidate standard data element; The method further comprises: Based on at least one feature information of the target data element, construct a feature segmentation set of the target data element, wherein the feature segmentation set includes at least one feature segmentation obtained by segmenting the at least one feature information; Based on the characteristic word segmentation set, determining a third data element set similar to the target data element in the standard data element library, the third data element set comprising: at least one third standard data element whose characteristic information set has a high similarity with the characteristic word segmentation set, and a first similarity between the characteristic information set of the third standard data element and the characteristic word segmentation set; the characteristic information set of the standard data element comprises each characteristic information of the standard data element; Based on the first similarities corresponding to each third standard data element and the first comprehensive scores of each first candidate standard data element in the first candidate standardization list, at least one target standard data element for standardizing the target data element is determined from the third data element set and the first candidate standardization list.

5. The method according to claim 4, characterized in that Before determining at least one target standard data element for standardizing the target data element, the method further includes: Based on the characteristic segmentation set, determining a fourth data element set similar to the target data element in the historical benchmarking record library, wherein the fourth data element set includes: at least one fourth standard data element whose characteristic information of the corresponding non-standard data element has a high similarity with the characteristic segmentation set and a second similarity between the characteristic information of the non-standard data element corresponding to the fourth standard data element and the characteristic segmentation set; Wherein, determining at least one target standard data element for standardizing the target data element comprises: Determining a second comprehensive score for each standard data element in the third data element set and the fourth data element set based on a first similarity corresponding to each third standard data element in the third data element set and a second similarity corresponding to each fourth standard data element in the fourth data element set; Generate a second candidate standardized list for standardizing the target data element, the second candidate standardized list including: at least one second candidate standardized data element with a higher second comprehensive score determined from the third data element set and the fourth data element set, and the second comprehensive score of the second candidate standardized data element; Determine an overall score for each candidate standard data element in the first candidate standard list and the second candidate standard data element in the second candidate standard list in combination with the first comprehensive score of each first candidate standard data element in the first candidate standard list and the second comprehensive score of the second candidate standard data element in the second candidate standard list; In combination with the overall scores of the candidate standard data elements in the first candidate standardization list and the second candidate standardization list, at least one target standard data element for standardizing the target data element is determined from the first candidate standardization list and the second candidate standardization list.

6. The method according to claim 5, characterized in that Before determining the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list, the method further includes: Determine the entity category to which the target data element belongs based on at least one feature information of the target data element and a pre-built entity rule base, wherein the entity rule base records feature matching rules that feature information of different entity categories needs to satisfy; Determine the entity category of each candidate standard data element in the first candidate standardization list and the second candidate standardization list; For each candidate standard data element in the first candidate standardization list and the second candidate standardization list, determine a reward or penalty score of the candidate standard data element, wherein if the entity category of the candidate standard data element is the same as the entity category of the target data element, the reward or penalty score of the candidate standard data element is a positive number; otherwise, the reward or penalty score of the candidate standard data element is a negative number; Determining the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list includes: Based on the first comprehensive score and reward and punishment score of each first candidate standard data element in the first candidate standardization list, and the second comprehensive score and reward and punishment score of the second candidate standard data element in the second candidate standardization list, the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list is determined.

7. The method according to claim 6, characterized in that Determining the overall score of each candidate standard data element in the first candidate standardization list and the second candidate standardization list includes For each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, based on the feature information of the candidate standardized data element and at least two of the first comprehensive score, the second comprehensive score and the reward and punishment score of the candidate standardized data element, a pre-trained weight evaluation model is used to determine a first weight, a second weight and a third weight corresponding to the candidate standardized data element; For each candidate standardized data element in the first candidate standardized list and the second candidate standardized list, determine the overall score of the candidate standardized data element by combining the first weight, the second weight and the third weight corresponding to the candidate standardized data element, and the first comprehensive score, the second comprehensive score and the reward and punishment score of the candidate standardized data element; The first weight is the weight proportion of the first comprehensive score of the candidate standard data element, the second weight is the weight proportion of the second comprehensive score of the candidate standard data element, and the third weight is the weight proportion of the reward and punishment score of the candidate standard data element; The weight evaluation model is trained by using feature information corresponding to a plurality of data element samples labeled with whether they are selected by the user, a first comprehensive score, a second comprehensive score, and reward and punishment scores.

8. The method according to claim 4, characterized in that The determining, based on the characteristic segmentation set, a third data element set in the standard data element library that is similar to the target data element comprises: Based on data element index files corresponding to different standard data elements stored in the standard data element index library, determining a third data element set whose data element index files are similar to the feature segmentation set from the standard data element index library; The data element index file of the standard data element stores the characteristic information of the standard data element recorded in the standard data element library; The third data element set includes: at least one third standard data element having a high similarity between a data element index file and the characteristic word segmentation set, and a first similarity between the data element index file of the third standard data element and the characteristic word segmentation set.

9. The method according to claim 5, characterized in that The determining, based on the characteristic segmentation set, a fourth data element set in the historical benchmarking record library that is similar to the target data element comprises: Based on historical benchmarking index files corresponding to different standard data elements stored in the historical benchmarking record index library, determining a fourth data element set whose historical benchmarking index files are similar to the characteristic segmentation set from the historical benchmarking index library; The historical benchmarking index file corresponding to the standard data element includes: characteristic information of each non-standard data element corresponding to the standard data element determined based on at least one standard data element corresponding to characteristic information of different non-standard data elements in the historical benchmarking database; The fourth data element set includes: at least one fourth standard data element having a high similarity between the historical benchmarking index file and the characteristic word segmentation set, and a second similarity between the historical benchmarking index file of the fourth standard data element and the characteristic word segmentation set.

10. The method according to claim 4, characterized in that The step of constructing a characteristic word segmentation set of the target data element based on at least one characteristic information of the target data element includes: Combining at least one characteristic information of the target data element into text; The text is segmented to obtain a characteristic segmentation set consisting of at least one characteristic segmentation obtained by segmenting the text.

11. The method according to claim 10, characterized in that Before combining at least one characteristic information of the target data element into text, the method further includes: For each feature information of the target data element, a standard feature matching the feature information is determined based on multiple standard features stored in a standard feature library, and the feature information is standardized based on the matched standard feature to obtain at least one standardized feature information corresponding to the target data element.

12. A device for determining a standard data element, characterized in that: include: An information obtaining unit, used to obtain at least one feature information of a target data element to be standardized; a first set determining unit, configured to determine, from a standard data element library, a first data element set matching the target data element based on each feature information of the target data element, wherein the first data element set includes: each first standard data element in the standard data element library matching the target data element, and a matching degree between the first standard data element and the target data element; A second set determination unit is used to determine, based on each feature information of the target data element, a second data element set corresponding to the target data element from a historical benchmarking record library, wherein the historical benchmarking record library stores: feature information of non-standard data elements that have been standardized in history, at least one standard data element after the non-standard data element has been standardized in history, and the number of times the non-standard data element has been standardized to each standard data element in history; the second data element set includes: each second standard data element after the target data element has been standardized in history and the number of times the second standard data element corresponds to; a recommendation scoring unit, configured to determine a recommendation score of the second standard data element according to the number of times the second standard data element in the second data element set is standardized, wherein the more times the second standard data element is standardized, the higher the recommendation score of the second standard data element, and the recommendation score of the second standard data element is used to indicate the degree of suitability of the second standard data element as the standard data element of the target data element; The first data element determination unit is used to determine at least one first candidate standard data element for standardizing the target data element from the first data element set and the second data element set, based on the matching degree of each first standard data element in the first data element set and the recommendation score of each second standard data element in the second data element set.

13. A computer device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the method for determining a standard data element according to any one of claims 1 to 11.

14. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for determining a standard data element according to any one of claims 1 to 11 is implemented.

Citation Information

Patent Citations

  • Benchmarking method and system for data items, files and databases

    CN110196834A

  • Method and system for cleaning government affair data through standard data elements

    CN111858567A