WO2020155788A1

WO2020155788A1 - Data determination method, apparatus and device, and medium

Info

Publication number: WO2020155788A1
Application number: PCT/CN2019/119344
Authority: WO
Inventors: 周扬; 于君泽
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2019-01-30
Filing date: 2019-11-19
Publication date: 2020-08-06
Also published as: CN109919357A; CN109919357B

Abstract

A data determination method, apparatus and device, and a medium. The data determination method comprises: determining a reference feature value and an actual feature value of each feature of a target event (S101); determining a prediction result of target data according to actual feature values of one or more features (S102); determining, according to the actual feature values and reference feature values of the one or more features, whether the prediction result meets a condition (S103); and if so, taking the prediction result as an actual result of the target data (S104).

Description

Method, device, equipment and medium for determining data

Technical field

This application relates to the field of computer technology, and in particular to a method, device, equipment and medium for determining data.

Background technique

In the prior art, in many cases, it is also necessary to manually determine the data that needs to be obtained. For example, in a traffic expense reimbursement scenario, it is necessary to manually determine the origin and destination of the traffic itinerary. The method of manually determining data often takes a long time and is relatively inefficient.

In view of this, a more efficient data determination scheme is needed.

Summary of the invention

The embodiments of this specification provide a data determination method, device, equipment and medium to solve the technical problem of how to determine data more efficiently.

To solve the above technical problems, the embodiments of this specification are implemented as follows:

The embodiment of this specification provides a data determination method, including:

Determine the reference feature value and actual feature value of each feature of the target event;

Determine the prediction result of the target data according to the actual feature value of one or more features;

Determine whether the prediction result meets the conditions according to the actual feature value and the reference feature value of one or more features;

If it matches, the predicted result is taken as the actual result of the target data.

The embodiment of this specification provides a data determining device, including:

The value determination module is used to determine the reference characteristic value and the actual characteristic value of each characteristic of the target event;

The prediction module is used to determine the prediction result of the target data according to the actual feature value of one or more features;

The judgment module is used to determine whether the prediction result meets the condition according to the actual feature value and the reference feature value of one or more features;

The result determination module is configured to use the prediction result as the actual result of the target data if the prediction result meets the condition.

The embodiment of this specification provides a data determination device, including:

At least one processor;

as well as,

A memory connected in communication with the at least one processor;

among them,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can:

The embodiments of this specification provide a computer-readable storage medium that stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the following steps are implemented:

The above at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

The prediction result of the target data is automatically determined by the actual feature value of one or more features, which is fast, efficient and effective; automatically determines whether the prediction result meets the conditions according to the actual feature value of one or more features and the reference feature value , To further ensure the accuracy of the prediction results; when the prediction results meet the conditions, the prediction results are automatically regarded as the actual results of the target data, which can determine the actual results of the target data more quickly and efficiently, and guarantees the target data The accuracy of actual results.

Description of the drawings

In order to explain the embodiments of this specification or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the embodiments of the specification or the description of the prior art. Obviously, the drawings in the following description These are just some of the embodiments described in this specification. For those of ordinary skill in the art, other drawings may be obtained from these drawings without creative labor.

Fig. 1 is a working schematic diagram of the data determination system in the first embodiment of this specification.

Fig. 2 is a schematic flowchart of the data determination method in the second embodiment of this specification.

Fig. 3 is a schematic diagram of the data determination process in the second embodiment of this specification.

Fig. 4 is a flow chart of data determination in the second embodiment of this specification.

Fig. 5 is a schematic diagram of clustering in the third embodiment of this specification.

Fig. 6 is a schematic diagram of determining points of interest in the third embodiment of this specification.

FIG. 7 is a schematic diagram of the structure of the data determining device in the fourth embodiment of this specification.

Fig. 8 is a schematic diagram of another structure of the data determining device in the fourth embodiment of this specification.

detailed description

In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the drawings in the embodiments of this specification. Obviously, the described The embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

As shown in Figure 1, the first embodiment of this specification provides a data determination system. Specifically, the data determination system determines the reference feature value and actual feature value of each feature of the target event; the data determination system is based on one or more The actual feature value of the feature determines the prediction result of the target data; the data determination system determines whether the prediction result meets the conditions based on the actual feature value of one or more features and the reference feature value; if it does, the data determination system will As the actual result of the target data.

In this embodiment, the prediction result of the target data is automatically determined by the actual feature value of one or more features, the prediction speed is fast, the efficiency is high, and the effect is good; according to the actual feature value of one or more features and the reference feature value automatically Determining whether the prediction result meets the conditions further ensures the accuracy of the prediction result; when the prediction result meets the conditions, the prediction result is automatically regarded as the actual result of the target data, which can determine the actual result of the target data more quickly and efficiently. And the accuracy of the actual results of the target data is guaranteed.

From a program point of view, the execution subject of the above process can be a computer or a server or a corresponding data determination system. In addition, a third-party application client can also assist the execution subject in executing the above process.

Figure 2 is a schematic flow diagram of the data determination method in the second embodiment of this specification, Figure 3 is a schematic diagram of the data determination process in this embodiment, and Figure 4 is a schematic diagram of the data determination flow in this embodiment, combined with Figure 2 3 and 4, the data determination method in this embodiment includes:

S101: Determine the reference feature value and the actual feature value of each feature of the target event.

In this embodiment, the "target event" can be any event, and the event type, event time, or other conditions are not necessarily distinguished. You can specify any event as the target event, or specify the conditions that the target event needs to meet. The determination of target data in this embodiment may be performed for one or more target events, and the targeted one or more target events may be referred to as target events.

In this embodiment, it is possible to determine the characteristics that the target event (that is, the target event) has or should have, such as geographic location characteristics, time characteristics, etc. (the characteristics here can also be used as the conditions that the target event needs to meet, that is, it will have The event of the determined characteristic is regarded as the target event). Determining features can be before or after the target event occurs, and the content and quantity of features determined by different target events (for example, different times, different locations, and different types of target events) may be the same or different .

In this embodiment, after the characteristics of the target event (ie, the target event) are determined, the reference characteristic value and the actual characteristic value of each characteristic of the target event can be determined. Specifically, methods for determining the reference feature value of each feature of the target event include but are not limited to:

S1011, for any feature of the target event, determine the historical value or sample value of the feature;

For any feature of the target event (ie, target event), it may be recorded as feature A, and the historical value or sample value of feature A can be determined. For example, the same target event may have occurred, and feature A can be identified in one or more target events in the past, then the feature value of feature A in the past one or more target events can be used as the target event The historical value or sample value of the feature value A in.

S1012. Determine a reference feature value of the feature according to the historical value or sample value.

After the historical value or sample value of feature A is determined, the reference characteristic value of feature A can be determined based on the historical value or sample value. Specifically, the methods that can be used to determine the reference feature value of the feature according to the historical value or sample value include but are not limited to:

1.1. Use the historical value of the feature or the mean or median or average value of the sample value as the reference feature value of the feature.

Following feature A, if it is determined that the historical value or sample value of feature A includes A1,... Ai, the average or median or average value of A1,... Ai can be used as the reference feature value of feature A.

1.2. Cluster the historical value or sample value of the feature to obtain each category, and use the average value of each category as the reference feature value of the category.

Using feature A, if it is determined that its historical value or sample value includes A1,...Ai, clustering can be performed if it is determined that its historical value or sample value includes A1,...Ai, so that one or more categories can be obtained . For each category, the historical value or the average value of the sample value in the category can be used as the reference feature value of the category, that is, the reference feature value of feature A. For example, if a category contains Am,..., An (all historical values or sample values of feature A, 1≤m≤n≤i), then the average value of Am,..., An can be used as the reference feature of the category Value, which is the reference feature value of feature A. It can be seen that in this way, if the historical value or sample value of feature A is divided into multiple categories, feature A can have multiple reference feature values.

In this embodiment, the actual feature value of feature A can also be determined. The actual feature value of feature A is the actual feature value determined by feature A in the target event (ie, target event); for example, if feature A is a time feature, The actual feature value of feature A is the actual occurrence time of the target event (ie, target event); if feature A is a geographic location feature, the actual feature value of feature A is the actual location of the target event (ie, target event).

S102: Determine the prediction result of the target data according to the actual feature value of one or more features.

In this embodiment, the "target data" can be any data, and the data type, data time, or other conditions are not necessarily distinguished. You can specify any data as the target data, and you can also specify the conditions that the target data needs to meet.

In this embodiment, the actual feature value of one or more features may be used to determine the prediction result of the target data. Specifically, methods for determining the prediction result of the target data based on the actual feature value of one or more features include but are not limited to:

S1021: Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature.

One or more features can be selected from the features of the target event (ie, object event), and for any selected feature, the reference feature value corresponding to the actual feature value of the feature is determined from the reference feature value of the feature. Assume that feature B is any one of the features selected in this step for the target event (ie, target event), the actual feature value of feature B is b, and the reference feature values are B1, ..., Bj (j≥1) , Then the reference feature value of feature B corresponding to the actual feature value b of feature B can be determined from B1, ..., Bj.

S1022: Determine the prediction result of the target data according to the reference feature value corresponding to the actual feature value of the selected one or more features.

For the one or more features selected in S1021, the corresponding reference feature values can be found through the actual feature values of the selected features, and then the prediction results of the target data can be determined by the corresponding reference feature values. For example, these corresponding reference feature values can be used as the prediction result of the target data.

S103: Determine whether the prediction result meets the condition according to the actual feature value and the reference feature value of one or more features.

In this embodiment, the actual feature value and reference feature value of one or more features can be used to determine whether the prediction result of the target data meets the conditions. Specifically, methods for determining whether the prediction result meets the conditions according to the actual feature value and reference feature value of one or more features include but are not limited to:

S1031: Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature.

The process is the same as S1021, but the feature number selected in this step is not necessarily the same or different from the feature number selected in A1021. At the same time, it is assumed that feature C is the target event (ie object event) among the features selected in this step It is assumed that the actual feature value of feature C is c, and the reference feature value corresponding to c is Co.

S1032: For any feature selected in S1031, determine whether the difference between the actual feature value of the feature and the corresponding reference feature value exceeds the preset range corresponding to the feature.

Using feature C, it can be determined whether the difference between the actual feature value c of feature C and the reference feature value Co corresponding to c exceeds the preset range corresponding to feature C (referred to as whether feature C exceeds the range).

S1033: Among the features selected in S1031: if the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or greater than the first threshold, the prediction result meets the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value exceeds the range is equal to or less than the second threshold, the prediction result meets the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or less than the third threshold, the prediction result does not meet the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value exceeds the range is equal to or greater than the fourth threshold, the prediction result does not meet the condition.

That is, in the one or more features selected in S1031, if the number of features that does not exceed the range is equal to or greater than the first threshold, the prediction result meets the condition;

and / or,

If the number of out-of-range features is equal to or less than the second threshold, the prediction result meets the condition;

and / or,

If the number of features not exceeding the range is equal to or less than the third threshold, the prediction result does not meet the conditions;

and / or,

If the number of out-of-range features is equal to or greater than the fourth threshold, the prediction result does not meet the conditions.

The above-mentioned first threshold, second threshold, third threshold, and fourth threshold may be determined or changed as required, for example, the feature number selected in S1031 may be used. The above-mentioned first threshold, second threshold, third threshold, and fourth threshold can be used in combination, but no conflicts may arise. For example, if the number of features not exceeding the range is equal to or greater than the first threshold, the prediction result meets the conditions and If the number of features that does not exceed the range is equal to or less than the third threshold, the first threshold and the third threshold cannot be the same when the prediction result does not meet the condition and both are used at the same time.

In this embodiment, if the reference feature value of a feature is determined using the method 1.2, for any selected feature, the methods for determining the reference feature value corresponding to the actual feature value of the feature include but are not limited to:

For any selected feature, determine the category clustered by historical values or sample values to which the actual feature value of the feature belongs, and use the reference feature value of the category as the reference feature value corresponding to the actual feature value. Use feature B (available in the same way for feature C). After clustering the historical value or sample value of feature B, the reference feature value of each category can be obtained; determine the history of feature B to which actual feature value b belongs Values or sample values are clustered, and the reference feature value of the category to which the actual feature value b belongs is used as the reference feature value corresponding to the actual feature value b.

The above method of determining the reference feature value corresponding to the actual feature value is applicable to both S1021 and S1031.

In addition, in S1031, the following methods may be used to determine the reference characteristic value corresponding to the actual characteristic value:

As explained above, there may be multiple reference feature values for each feature, and the corresponding relationship between the reference feature values can be determined. For example, feature D has reference feature values D1,..., Dp, feature E has reference feature values E1,..., Eq, then the correspondence between feature D and feature E can be determined, for example, D1 corresponds to E1, D2 Corresponding to E2,... In this way, the corresponding relationship between the reference feature values can be determined.

Assuming that for any feature B selected in S1021, the reference feature value Bj corresponding to the actual feature value of the feature has been determined, then for any feature C selected in S1031, if the reference feature C is The feature value corresponding to Bj is Co, and then Co is used as the reference feature value corresponding to the actual feature value of feature C in S1031.

In particular, in this embodiment, the actual feature value used to determine the predicted result of the target data in S102 and the actual feature value used to determine whether the predicted result meets the conditions in S103 are different features, that is, the actual feature value used in S1021 is The selected one or more features are different from the one or more selected features in S1031, so that the relative independence between the result prediction and the prediction result evaluation can be further ensured, and the accuracy of the result evaluation can be improved.

S104: If the prediction result meets the condition, use the prediction result as the actual result of the target data.

In this embodiment, if the prediction result meets the condition, the prediction result can be used as the actual result of the target data. For example, if the target event is the transaction time, the target data is the consumption amount, the predicted result is 100 yuan, and the predicted result meets the conditions, the predicted result can be regarded as the actual result of the target data.

In this embodiment, the prediction result of the target data is automatically determined by the actual feature value of one or more features, and the prediction speed is fast and the efficiency is high; the corresponding relationship between the actual feature value and the reference feature value is also combined when determining the prediction result. The prediction result depends not only on the actual feature value, but also on the reference feature value, which can improve the accuracy and effect of the prediction result; automatically determine whether the prediction result meets the conditions according to the actual feature value and reference feature value of one or more features, thereby The evaluation of the prediction results is realized, and the evaluation of the prediction results also combines the corresponding relationship between the actual feature value and the reference feature value, so that the prediction result evaluation depends not only on the actual feature value, but also on the reference feature value, which further ensures the prediction Results and the accuracy of the prediction result evaluation; when the prediction result meets the conditions, the prediction result is automatically regarded as the actual result of the target data, which can determine the actual result of the target data more quickly and efficiently, and the accuracy of the prediction result is also The accuracy of the actual results of the target data is guaranteed.

The third embodiment of this specification provides a method for determining data in specific scenarios. Among them, the specific scenario described is a traffic expense reimbursement scenario. In this embodiment, the target event can be determined as a traffic travel event (in this embodiment, it is a reimbursable traffic travel event), and the characteristics of the determined target event can include the origin, destination, time-consuming, and Amount. Origin and destination characteristics can be collectively referred to as location features. The actual feature value and reference feature value of the location feature can be latitude and longitude data; the actual feature value and reference feature value of the time-consuming feature and the amount feature can be the specific time-consuming value And the amount value. Generally, when reimbursing transportation expenses, you need to fill in the origin and destination in the reimbursement remarks column, where the origin and destination are the text representation of the specific location (such as XX square), which can be used as the target to be determined for the target event data.

The data determination method in this embodiment may include:

S301: Determine the reference feature value and the actual feature value of each feature of the target event.

For an employee, it is assumed that the target data to be determined is for one or more traffic trip events, and this one or more traffic trip events can be regarded as the target event. The reference feature value and the actual feature value of each feature of the object event can be determined. For example, the employee has had one or more traffic travel incidents before the object event. It may be called a historical event, and each historical event can be determined Origin, destination, time-consuming, and amount of money and other characteristics, so that for each of these characteristics, the value of the characteristic in historical events (can be all historical events in the past, or selected historical events) can be determined, As the historical value or sample value of the feature. Assume that the employee’s historical events and the specific values of each feature in the historical events are shown in Table 1:

Table 1

LBS: Location-based service; among them, the value of time-consuming and monetary characteristics can be obtained through OCR identification of travel invoices (other methods can also be used). Since the templates of the bills such as taxi invoices are fixed, after marking the range that needs to be identified, information such as time and amount can be identified on the bill through OCR;

Through the historical value or sample value of each feature, the reference feature value of each feature can be determined. For origin and destination features, the reference feature value can also be latitude and longitude data; for time-consuming and monetary features, the reference feature value is a numerical value.

In this embodiment, the reference feature values of the origin feature and the destination feature can be calculated using the method 1.1 or 1.2 in the second embodiment. If the method of 1.2 is adopted, specifically, dbscan clustering (other clustering algorithms or methods can also be used) can be used to obtain the historical values of the origin and destination characteristics or the LBS clusters of the sample values (equivalent to For category), for example, the clusters shown in Figure 5; for the origin clusters, take the new cluster of each cluster as the center of the cluster, and the calculation method for the new cluster is (average longitude, average latitude), That is, for each cluster, the longitude average and latitude average of the cluster are used as the center; the center is the reference feature value of the cluster, that is, the reference feature value of the origin feature (the same is true for the destination cluster Available reference characteristic values).

If the origin feature has multiple clusters, the origin feature can have multiple reference feature values. Similarly, if the destination feature has multiple clusters, the destination feature can have multiple reference feature values. In this embodiment, the Geocoding service (a service that reversely encodes the names of points of interest from latitude and longitude) can be used to convert reference feature values into geographic points of interest (written expressions of landmarks in the field of geographic location mining), such as XX square, XX building, W community, Z square, as shown in Figure 6. Geographic interest points and reference feature values are interlinked. The aforementioned target data also belongs to the form of geographic points of interest.

The calculation of the reference feature value of the time-consuming and monetary features can adopt the method 1.1 or 1.2 in the second embodiment. For example, it can be calculated by means of historical values or sample values, median, or average, or it can be obtained by clustering. In addition, you can also calculate the variance of the historical value or sample value of each feature.

Assume that each feature in this embodiment has two reference feature values, and the reference feature values are shown in Table 2 (the time-consuming average is the reference feature value of the time-consuming feature; the amount average is the reference feature value of the money feature; The reference feature values of origin and destination features are represented by points of interest):

Table 2

In this embodiment, the reference feature value between each feature can be corresponding. For example, when the employee’s origin point of interest and destination point of interest are X square and Y building, the reference feature value of the time-consuming feature is 60 minutes, and the amount is The reference feature value of the feature is 141.12 yuan, and the origin point of interest and the destination point of interest are X square and Y building, and the corresponding time-consuming feature and the reference feature value of the monetary feature are 60min and 141.12 yuan respectively; if When the employee’s point of origin and destination point of interest are W district and Z square, the reference feature value of the time-consuming feature is 70 minutes, and the reference feature value of the amount feature is 160 yuan, then the point of interest and destination point of interest are passed The points are W district and Z square, and the corresponding reference feature values of the time-consuming special diagnosis and the amount of money can be obtained as 70 min and 160 yuan respectively. This reflects the compatibility of reference feature values in addition to each feature.

If the object event is the most recent traffic travel event of the above-mentioned employee, the actual feature value of each feature of the object event can be determined, as shown in Table 3:

员工工号Employee ID	始发地LBSOrigin LBS	目的地LBSDestination LBS	耗时time consuming	金额Amount
1234512345	100.04，180.00100.04, 180.00	101.04，181.00101.04, 181.00	63min63min	144.12144.12

table 3

S302: Determine the prediction result of the target data according to the actual feature value of one or more features.

Since the target data in this embodiment are origin and destination data, the origin and destination characteristics can be selected to determine the prediction result of the target data. Suppose the actual feature value of each feature in the object event is shown in Table 4:

Table 4

For the origin and destination features, determine the reference feature value corresponding to the actual feature value (that is, which cluster it belongs to). In this embodiment, the actual feature value of the origin belongs to the cluster where X square is located, that is, the reference feature value corresponding to the cluster where X square is (ie the latitude and longitude data of X square); the actual feature value of the destination belongs to the Y building where The cluster of, that is, the reference feature value corresponding to the cluster of Y building (ie the latitude and longitude data of Y building), then X square and Y building can be used as the prediction results of the target data, that is, to predict the origin of the above-mentioned employees in the target event The ground is X square and the destination is Y building.

S303: Determine whether the prediction result meets the condition according to the actual feature value and the reference feature value of one or more features.

In this embodiment, the time-consuming feature and the monetary feature can be selected to determine whether the above prediction result meets the conditions. Specifically, for the time-consuming and monetary characteristics, the reference characteristic value corresponding to the actual characteristic value is determined. Here, the reference feature value corresponding to the actual feature value can be determined with the origin and destination feature, depending on the cluster to which the actual feature value belongs, or because the reference feature value between the various features of the target event can have a corresponding relationship, it is determined After the reference feature values corresponding to the actual feature values of the origin and destination features are X square and Y building, the corresponding relationship between the reference feature values between the features is used to determine the reference features corresponding to the actual feature values of the time-consuming and monetary features The values are 60min and 141.12 yuan respectively.

For time-consuming features or monetary features, determine whether the difference between the actual feature value and the corresponding reference feature value exceeds the corresponding preset range. Specifically, for time-consuming features, the difference between the actual eigenvalue 63 and the corresponding reference eigenvalue 60 is 3. You can use the time-consuming variance in Table 2 to verify whether the difference is out of range, difference 3/variance 5=0.6 , You can set conditions, for example, if the ratio of the difference to the variance is less than and/or less than or equal to the fifth threshold, the time-consuming feature does not exceed the range; similarly, for the monetary feature, the actual feature value of 144.12 and the corresponding reference feature value of 141.12 The difference is 3, you can use the variance of the amount in Table 2 to verify whether the difference is out of range, the difference 3/variance 10=0.3, you can set conditions, for example, if the ratio of the difference to the variance is less than and/or less than or equal to the first The six thresholds means that the monetary characteristics do not exceed the range.

The methods that can be used to determine whether the prediction result meets the conditions include but are not limited to:

If the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or greater than the first threshold, the prediction result meets the condition;

and / or,

S304: If the prediction result meets the condition, use the prediction result as the actual result of the target data.

In this embodiment, it is assumed that the method “if the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to the first threshold value, then the prediction result meets the condition” is assumed, and the first threshold value is 2. Assuming that neither the time-consuming nor the amount of money characteristics exceed the range, it can be determined that the predicted result meets the conditions, so that the origin of the above-mentioned employee in the target event is X square and the destination is Y building, that is, the actual result of the target data is determined .

In this embodiment, if the prediction result meets the conditions, the prediction result can be submitted for processing according to the prediction result, for example, settlement processing of the target event based on the prediction result, including but not limited to settlement of reimbursement expenses. There is no absolute precedence between submitting forecast results and S304.

This embodiment can also be used as a verification function. The origin and destination obtained in this embodiment can be used to verify the origin and destination provided by the employee.

As shown in FIG. 7, the fourth embodiment of this specification provides a data determining device, including:

The value determining module 401 is used to determine the reference characteristic value and the actual characteristic value of each characteristic of the target event;

The prediction module 402 is used to determine the prediction result of the target data according to the actual feature value of one or more features;

The judging module 403 is configured to determine whether the prediction result meets the condition according to the actual feature value and reference feature value of one or more features;

The result determination module 404 is configured to use the prediction result as the actual result of the target data if the prediction result meets the condition.

Optionally, the reference feature value for determining each feature of the target event includes:

For any feature of the target event, determine the historical value or sample value of the feature;

The reference characteristic value of the characteristic is determined according to the historical value or the sample value.

Optionally, determining the reference characteristic value of the characteristic according to the historical value or the sample value includes:

Use the historical value or the mean value or median value or average value of the sample value of the characteristic as the reference characteristic value of the characteristic;

or,

Cluster the historical value or sample value of the feature, and use the average value of each category as the reference feature value of the feature and the category.

Optionally, determining the prediction result of the target data according to the actual feature value of one or more features includes:

Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature;

The prediction result of the target data is determined according to the reference feature value corresponding to the actual feature value of the selected one or more features.

Optionally, determining whether the prediction result meets the conditions according to the actual feature value and the reference feature value of one or more features includes:

For any selected feature, determine whether the difference between the actual feature value of the feature and the corresponding reference feature value exceeds the preset range corresponding to the feature;

and / or,

Clustering the historical value or sample value of the feature, and using the average value of each category as the reference feature value of the feature and the category;

For any selected feature, determining the reference feature value corresponding to the actual feature value of the feature includes:

For any selected feature, determine the category clustered by historical values or sample values to which the actual feature value of the feature belongs, and use the reference feature value of the category as the reference feature value corresponding to the actual feature value.

Optionally, the feature includes a location feature, and the actual feature value and/or reference feature value includes latitude and longitude data.

Optionally, the target data includes geographic points of interest.

According to Geocoding, the actual latitude and longitude data of the location features are converted into geographic points of interest.

Optionally, the actual feature value used to determine the prediction result of the target data and the actual feature value used to determine whether the prediction result meets the condition are different features.

Optionally, as shown in FIG. 8, the device further includes:

The submission module 405 is configured to submit the prediction result if the prediction result meets the conditions, so as to perform settlement processing on the target event according to the prediction result. The settlement process may be a settlement module or device or equipment.

The fifth embodiment of this specification provides a data determination device, including:

At least one processor;

as well as,

A memory connected in communication with the at least one processor;

among them,

The sixth embodiment of this specification provides a computer-readable storage medium that stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the following steps are implemented:

The above embodiments can be used in combination.

The specific embodiments of this specification have been described above, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than in the embodiments and still achieve desired results. In addition, the processes depicted in the drawings do not necessarily have to be in the specific order or sequential order shown to achieve desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial description of the method embodiments.

The apparatus, equipment, non-volatile computer readable storage medium, and method provided in the embodiments of this specification correspond to each other. Therefore, the apparatus, equipment, and non-volatile computer storage medium also have beneficial technical effects similar to the corresponding method. The beneficial technical effects of the method have been described in detail above, therefore, the beneficial technical effects of the corresponding device, equipment, and non-volatile computer storage medium will not be repeated here.

In the 1990s, the improvement of a technology can be clearly distinguished between hardware improvements (for example, improvements in circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements in method flow). However, with the development of technology, the improvement of many methods and procedures can be regarded as the direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by hardware entity modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. It is programmed by the designer to "integrate" a digital system on a piece of PLD, instead of asking the chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly realized by using "logic compiler" software, which is similar to the software compiler used in program development and writing, but before compilation The original code must also be written in a specific programming language, which is called Hardware Description Language (HDL), and there is not only one HDL, but many, such as ABEL (Advanced Boolean Expression) Language), AHDL (Altera Hardware DescrIP address Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware DescrIP address Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Address) Language) and so on, the most commonly used at present are VHDL (Very-High-Speed Integrated Circuit Hardware DescrIP Address Language) and Verilog. It should also be clear to those skilled in the art that just a little bit of logic programming of the method flow in the above-mentioned hardware description languages and programming into an integrated circuit can easily obtain the hardware circuit that implements the logic method flow.

The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, MicrochIP addresses PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the memory control logic. Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code manner, it is completely possible to program the method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for implementing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.

The systems, devices, modules or units explained in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.

For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in one or more software and/or hardware.

Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of this specification may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

This specification is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment can be generated A device that implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

In a typical configuration, the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory in a computer readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.

Computer-readable media includes permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

It should also be noted that the terms "including", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or equipment including a series of elements not only includes those elements, but also includes Other elements that are not explicitly listed, or also include elements inherent to such processes, methods, commodities, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, commodity, or equipment that includes the element.

This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the part of the description of the method embodiment.

The above descriptions are only examples of this specification and are not intended to limit this application. For those skilled in the art, this application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the scope of the claims of this application.

Claims

A method for determining data, characterized in that:

Determine the reference feature value and actual feature value of each feature of the target event;

Determine the prediction result of the target data according to the actual feature value of one or more features;

Determine whether the prediction result meets the conditions according to the actual feature value and the reference feature value of one or more features;

If it matches, the predicted result is taken as the actual result of the target data.
The method according to claim 1, wherein determining the reference characteristic value of each characteristic of the target event comprises:

For any feature of the target event, determine the historical value or sample value of the feature;

The reference characteristic value of the characteristic is determined according to the historical value or the sample value.
3. The method of claim 2, wherein determining the reference feature value of the feature according to the historical value or sample value comprises:

Use the historical value or the mean value or median value or average value of the sample value of the characteristic as the reference characteristic value of the characteristic;

or,

Clustering the historical value or sample value of the feature to obtain each category, and taking the average value of each category as the reference feature value of the feature and the category.
The method according to claim 1, wherein determining the prediction result of the target data according to the actual feature value of one or more features comprises:

Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature;

The prediction result of the target data is determined according to the reference feature value corresponding to the actual feature value of the selected one or more features.
The method according to claim 1, wherein determining whether the prediction result meets the condition according to the actual feature value and the reference feature value of one or more features comprises:

Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature;

For any selected feature, determine whether the difference between the actual feature value of the feature and the corresponding reference feature value exceeds the preset range corresponding to the feature;

If the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or greater than the first threshold, the prediction result meets the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value exceeds the range is equal to or less than the second threshold, the prediction result meets the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or less than the third threshold, the prediction result does not meet the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value exceeds the range is equal to or greater than the fourth threshold, the prediction result does not meet the condition.
The method according to claim 4 or 5, wherein determining the reference feature value of each feature of the target event comprises:

For any feature of the target event, determine the historical value or sample value of the feature;

Clustering the historical value or sample value of the feature to obtain each category, and using the average value of each category as the reference feature value of the feature and the category;

For any selected feature, determining the reference feature value corresponding to the actual feature value of the feature includes:

For any selected feature, determine the category clustered by historical values or sample values to which the actual feature value of the feature belongs, and use the reference feature value of the category as the reference feature value corresponding to the actual feature value.
The method according to claim 1, wherein the feature includes a location feature, and the actual feature value and/or reference feature value includes latitude and longitude data.
The method according to claim 7, wherein the target data includes geographic points of interest.
The method according to claim 8, wherein determining the prediction result of the target data according to the actual feature value of one or more features comprises:

According to Geocoding, the actual latitude and longitude data of the location features are converted into geographic points of interest.
The method according to any one of claims 1 to 5 and 7 to 9, wherein:

The actual feature value used to determine the prediction result of the target data and the actual feature value used to determine whether the prediction result meets the condition are different features.
The method according to any one of claims 1 to 5 and 7 to 9, wherein the method further comprises: if the prediction result meets the condition, submitting the prediction result to be based on the prediction result Perform settlement processing on the target event.
A data determining device, characterized in that it comprises:

The value determination module is used to determine the reference characteristic value and the actual characteristic value of each characteristic of the target event;

The prediction module is used to determine the prediction result of the target data according to the actual feature value of one or more features;

The judgment module is used to determine whether the prediction result meets the condition according to the actual feature value and the reference feature value of one or more features;

The result determination module is configured to use the prediction result as the actual result of the target data if the prediction result meets the condition.
The device according to claim 12, wherein determining the reference feature value of each feature of the target event comprises:

For any feature of the target event, determine the historical value or sample value of the feature;

The reference characteristic value of the characteristic is determined according to the historical value or the sample value.
The device of claim 13, wherein determining the reference characteristic value of the characteristic according to the historical value or the sample value comprises:

Use the historical value or the mean value or median value or average value of the sample value of the characteristic as the reference characteristic value of the characteristic;

or,

Cluster the historical value or sample value of the feature, and use the average value of each category as the reference feature value of the feature and the category.
The device of claim 12, wherein determining the prediction result of the target data according to the actual feature value of one or more features comprises:

Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature;

The prediction result of the target data is determined according to the reference feature value corresponding to the actual feature value of the selected one or more features.
The device of claim 12, wherein:

Determining whether the prediction result meets the conditions according to the actual feature value and the reference feature value of one or more features includes:

Select one or more features, and for any selected feature, determine the reference feature value corresponding to the actual feature value among the reference feature values of the feature;

For any selected feature, determine whether the difference between the actual feature value of the feature and the corresponding reference feature value exceeds the preset range corresponding to the feature;

If the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or greater than the first threshold, the prediction result meets the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value exceeds the range is equal to or less than the second threshold, the prediction result meets the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value does not exceed the range is equal to or less than the third threshold, the prediction result does not meet the condition;

and / or,

If the number of features whose difference between the actual feature value and the corresponding reference feature value exceeds the range is equal to or greater than the fourth threshold, the prediction result does not meet the condition.
The device according to claim 15 or 16, wherein the reference feature value for determining each feature of the target event comprises:

For any feature of the target event, determine the historical value or sample value of the feature;

Clustering the historical value or sample value of the feature, and using the average value of each category as the reference feature value of the feature and the category;

For any selected feature, determining the reference feature value corresponding to the actual feature value of the feature includes:

For any selected feature, determine the category clustered by historical values or sample values to which the actual feature value of the feature belongs, and use the reference feature value of the category as the reference feature value corresponding to the actual feature value.
The device according to claim 12, wherein the feature includes a location feature, the actual feature value and/or the reference feature value includes latitude and longitude data; and the target data includes geographic points of interest.
The device of claim 18, wherein determining the prediction result of the target data according to the actual feature value of one or more features comprises:

According to Geocoding, the actual latitude and longitude data of the location features are converted into geographic points of interest.
The device according to any one of claims 12 to 16, 18 to 19, characterized in that:

The actual feature value used to determine the prediction result of the target data and the actual feature value used to determine whether the prediction result meets the condition are different features.
The device according to any one of claims 12 to 16, 18 to 19, wherein the device further comprises:

The submission module is configured to submit the prediction result if the prediction result meets the condition, so as to perform settlement processing on the target event according to the prediction result.
A data determining device is characterized in that it comprises:

At least one processor;

as well as,

A memory connected in communication with the at least one processor;

among them,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can:

Determine the reference feature value and actual feature value of each feature of the target event;

Determine the prediction result of the target data according to the actual feature value of one or more features;

Determine whether the prediction result meets the conditions according to the actual feature value and the reference feature value of one or more features;

If it matches, the predicted result is taken as the actual result of the target data.
A computer-readable storage medium that stores computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the following steps:

Determine the reference feature value and actual feature value of each feature of the target event;

Determine the prediction result of the target data according to the actual feature value of one or more features;

Determine whether the prediction result meets the conditions according to the actual feature value and the reference feature value of one or more features;

If it matches, the predicted result is taken as the actual result of the target data.