Data diagnosis method, data diagnosis system, storage medium, and program product

Abstract

The invention provides a data diagnosis method, a data diagnosis system, a storage medium and a computer program product. The method comprises the following steps: performing index detection on target data to obtain a target index parameter corresponding to the target data; obtaining a target diagnosis rule corresponding to the target index parameter; performing data diagnosis on the target index parameter based on the target diagnosis rule to obtain a target diagnosis result; obtaining an evaluation value of the target diagnosis result; in response to the fact that the evaluation value is smaller than a preset evaluation threshold value, a target weight value in the target diagnosis rule is adjusted based on the evaluation value, and the adjusted target diagnosis rule is obtained; and performing data diagnosis on the target index parameter based on the adjusted target diagnosis rule, and obtaining a target diagnosis result again.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a data diagnosis method, a data diagnosis system, a storage medium, and a computer program product. Background Art

[0002] Data diagnosis is one of the important links in data analysis of statistical data, which can help determine whether there are anomalies in the statistical data. In the application scenario of data analysis of statistical data, how to effectively use statistical data, discover problems through data diagnosis of statistical data, and drive the solution of problems often highly depends on personal ability and experience. Due to the different experience and ability of the staff who perform data diagnosis, the variance of the diagnostic results obtained by data diagnosis of statistical data is large.

[0003] In some schemes, statistical data are compared horizontally and vertically based on the configured diagnostic criteria through computer software, and the rationality of the data is diagnosed based on the position and change trend of the statistical data in the same level organization. In this way, the variance of the diagnostic results is small. However, it is difficult to diagnose the problems pointed out by abnormal data and it is difficult to judge whether the diagnostic results are accurate and effective. Summary of the invention

[0004] In order to solve one of the above technical problems, the present disclosure provides a data diagnosis method, a data diagnosis system, a storage medium and a computer program product.

[0005] The first aspect of the present disclosure provides a data diagnosis method, including: performing indicator detection on target data to obtain target indicator parameters corresponding to the target data; obtaining target diagnosis rules corresponding to the target indicator parameters; performing data diagnosis on the target indicator parameters based on the target diagnosis rules to obtain target diagnosis results; obtaining an evaluation value of the target diagnosis results; in response to the evaluation value being less than a preset evaluation threshold, adjusting a target weight value in the target diagnosis rule based on the evaluation value to obtain an adjusted target diagnosis rule; and performing data diagnosis on the target indicator parameters based on the adjusted target diagnosis rules to re-obtain the target diagnosis results.

[0006] In at least one optional implementation, indicator detection is performed on the target data to obtain target indicator parameters corresponding to the target data, including: obtaining preconfigured subject information, the subject information having multiple preset data subjects, each of the preset data subjects including one or more corresponding preset data indicators; detecting the preset data subject corresponding to the target data to obtain the target data subject; and matching parameter values ​​in the target data based on one or more preset data indicators in the target data subject, and obtaining the target indicator parameters corresponding to the target data based on the matched preset data indicators and the parameter values.

[0007] In at least one optional implementation, the target diagnostic rule corresponding to the target indicator parameter also includes a target algorithm and a target indicator reference value.

[0008] In at least one optional embodiment, data diagnosis is performed on the target indicator parameter based on the target diagnosis rule to obtain a target diagnosis result, including: calculating the target result value of the target indicator parameter based on the target algorithm; and obtaining the target diagnosis result based on the size of the target result value and the product of the target weight value and the target indicator reference value; or obtaining the target diagnosis result based on the difference between the target result value and the product of the target weight value and the target indicator reference value.

[0009] In at least one optional implementation, data diagnosis is performed on the target indicator parameters based on the target diagnostic rules to obtain a target diagnostic result, including: inputting the target indicator parameters and the target diagnostic rules into a target language model to obtain the target diagnostic result output by the target language model; wherein the target language model is configured to be trained based on calibrated target diagnostic rules, and is used to output corresponding diagnostic results based on the input indicator parameters and the calibrated target diagnostic rules.

[0010] In at least one optional embodiment, obtaining the evaluation value of the target diagnosis result includes: based on the target diagnosis rule and the target diagnosis result, respectively obtaining the target algorithm score, target indicator parameter score and target indicator benchmark score of the target data; obtaining a first sub-evaluation value based on the target algorithm score; obtaining a second sub-evaluation value based on the target indicator parameter score; obtaining a third sub-evaluation value based on the target indicator benchmark score; and obtaining the evaluation value of the target diagnosis result based on a set consisting of the first sub-evaluation value, the second sub-evaluation value and the third sub-evaluation value.

[0011] In at least one optional embodiment, the target weight value in the target diagnosis rule includes a target algorithm weight value, a target indicator parameter weight value and a target indicator benchmark weight value; adjusting the target weight value in the target diagnosis rule based on the evaluation value to obtain the adjusted target diagnosis rule, including: in response to the first sub-evaluation value being less than a pre-configured first evaluation threshold, adjusting the target algorithm weight value based on the difference between the first evaluation threshold and the first sub-evaluation value; and / or in response to the second sub-evaluation value being less than a pre-configured second evaluation threshold, adjusting the target indicator parameter weight value based on the difference between the second evaluation threshold and the second sub-evaluation value; and / or in response to the third sub-evaluation value being less than a pre-configured third evaluation threshold, adjusting the target indicator benchmark weight value based on the difference between the third evaluation threshold and the third sub-evaluation value; and in response to the adjustment result based on any one or more of the target algorithm weight value, the target indicator parameter weight value and the target indicator benchmark weight value, obtaining the adjusted target diagnosis rule.

[0012] In at least one optional embodiment, the target indicator parameters corresponding to the target data include multiple ones, and each of the target indicator parameters corresponds to a target diagnostic result; the data diagnosis method also includes: in response to the evaluation value of the target diagnostic result of each of the target indicator parameters being greater than or equal to a preset evaluation threshold, obtaining a final diagnostic result based on the target diagnostic results corresponding to each of the multiple target indicator parameters.

[0013] In at least one optional embodiment, in response to the evaluation value of the target diagnostic result of each of the target indicator parameters being greater than or equal to a preset evaluation threshold, a final diagnostic result is obtained based on the target diagnostic results corresponding to each of the multiple target indicator parameters, including: sorting the multiple target diagnostic results based on the target weight values ​​of the target diagnostic rules corresponding to each of the multiple target diagnostic results to obtain a diagnostic result order; performing text generation processing on the multiple target diagnostic results based on the diagnostic result order and a preconfigured text generation template to obtain a diagnostic result text; and outputting the final diagnostic result based on the diagnostic result text.

[0014] A second aspect of the present disclosure provides a data diagnosis system, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the data diagnosis method of any embodiment of the present disclosure.

[0015] A third aspect of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the data diagnosis method of any embodiment of the present disclosure is executed.

[0016] A fourth aspect of the present disclosure provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the data diagnosis method of any embodiment of the present disclosure is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0018] Figure 1 It is a schematic diagram of a scenario in which data diagnosis is performed by a data diagnosis method according to some embodiments of the present disclosure.

[0019] Figure 2 It is a schematic diagram of the structure of a data diagnosis system of some embodiments of the present disclosure.

[0020] Figure 3 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0021] Figure 4 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0022] Figure 5 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0023] Figure 6 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0024] Figure 7 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0025] Figure 8 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0026] Fig. 9 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure.

[0027] Fig.10 It is a flowchart of a data diagnosis method according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0028] The present disclosure is further described in detail below in conjunction with the accompanying drawings and implementations. It is understood that the specific implementations described herein are only used to explain the relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only the parts related to the present disclosure are shown in the accompanying drawings.

[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] Unless otherwise specified, the exemplary embodiments / embodiments shown will be understood as providing exemplary features of various details of some ways in which the technical concept of the present disclosure can be implemented in practice. Therefore, unless otherwise specified, the features of the various embodiments / embodiments can be combined, separated, interchanged and / or rearranged without departing from the technical concept of the present disclosure.

[0031] The use of cross-hatching and / or shading in the accompanying drawings is generally used to make the boundaries between adjacent components clear. As such, unless otherwise specified, the presence or absence of cross-hatching or shading does not convey or indicate any preference or requirement for the specific materials, material properties, dimensions, proportions, commonalities between the components shown, and / or any other characteristics, attributes, properties, etc. of the components. In addition, in the accompanying drawings, the sizes and relative sizes of the components may be exaggerated for clarity and / or descriptive purposes. When the exemplary embodiments can be implemented differently, the specific process sequence can be performed in a different order than described. For example, two successively described processes can be performed substantially simultaneously or in an order opposite to the described order. In addition, the same figure numbers represent the same components.

[0032] When a component is referred to as being "on" or "over," "connected to," or "coupled to" another component, the component may be directly on, directly connected to, or directly coupled to the other component, or intervening components may be present. However, when a component is referred to as being "directly on," "directly connected to," or "directly coupled to" another component, there are no intervening components. For this purpose, the term "connected" may refer to a physical connection, an electrical connection, etc., with or without intervening components.

[0033] The terms used herein are for the purpose of describing specific embodiments, and are not intended to be restrictive. As used herein, unless the context clearly indicates otherwise, the singular forms "one (kind, person)" and "(the)" are also intended to include plural forms. In addition, when the terms "comprise" and / or "include" and their variations are used in this specification, it is explained that there are stated features, integral bodies, steps, operations, parts, assemblies and / or their groups, but one or more other features, integral bodies, steps, operations, parts, assemblies and / or their groups are not excluded from existence or addition. It should also be noted that, as used herein, the terms "substantially", "approximately" and other similar terms are used as approximate terms and not as degree terms, so that they are used to explain the inherent deviations of the measured values, calculated values ​​and / or the values ​​provided that will be recognized by those of ordinary skill in the art.

[0034] In some schemes, statistical data are compared horizontally and vertically based on the configured diagnostic criteria through computer software, and the rationality of the data is diagnosed based on the position and change trend of the statistical data in the same level organization. In this way, the variance of the diagnostic results is small. However, it is difficult to diagnose the problems pointed out by abnormal data and it is difficult to judge whether the diagnostic results are accurate and effective.

[0035] Based on the above problems, the present disclosure provides a data diagnosis method and a data diagnosis system 1000 using the data diagnosis method. The data diagnosis system 1000 may be a computer device. Figure 1 A schematic diagram of a scenario in which the data diagnosis system 1000 according to an embodiment of the present disclosure applies a data diagnosis method to perform data diagnosis is shown.

[0036] First, experts in the field provide the correlation information between multiple data indicators corresponding to the statistical data of the same topic. For example, the statistical data of a sales topic is usually related to the channel share indicator, human resource efficiency indicator, and process conversion funnel sub-topic. Among them, the process conversion funnel sub-topic includes the viewing volume indicator, consultation volume indicator, order volume indicator, and actual sales volume indicator.

[0037] For multiple data indicators corresponding to the same statistical data, experts in the field configure the initial data diagnosis rules for each data indicator. For example, for the channel share indicator, the configured diagnosis rule is: "If the channel share data is greater than or equal to 50%, the output data diagnosis result is 'qualified'; otherwise, that is, if the channel share data is less than 50%, the output data diagnosis result is 'unqualified'". In this way, when the wanted data to be diagnosed contains channel share data, the diagnosis rules corresponding to the channel share indicator can be used to diagnose the data and obtain the corresponding data diagnosis results.

[0038] For the data diagnosis results, an evaluation system is also configured to judge their rationality. For example, a corresponding evaluation value is given, and the evaluation value is used to characterize the rationality of the data diagnosis results. In this way, if the data diagnosis results are found to be unreasonable, corresponding adjustments can be made in time, such as adjusting the rules of the data diagnosis this time to improve the accuracy of the next data diagnosis. Among them, the evaluation value can be obtained by manual evaluation by experts in the field, or it can use a trained evaluation model, based on the configured evaluation criteria, to output the corresponding evaluation value according to the input data diagnosis results and data diagnosis rules.

[0039] For example, the data diagnosis rule is "if the channel proportion data s% is greater than or equal to x%, the output data diagnosis result is 'qualified'; otherwise, that is, the channel proportion data is less than x%, the output data diagnosis result is 'unqualified'". Assuming that the output data diagnosis result is "qualified", the scoring standard of the evaluation value is: in the case of x∈[45,55], the data diagnosis result is considered reasonable, and the corresponding evaluation value is 3 points; in the case of x∈[35,45)∪(55,65], the data diagnosis result is considered relatively reasonable, and the corresponding evaluation value is 2 points; in the case of x∈[25,35)∪(65,75], the data diagnosis result is considered barely reasonable, and the corresponding evaluation value is 1 point; in the case of x∈[0,25)∪(75,100], the data diagnosis result is considered unreasonable, and the corresponding evaluation value is 0 points. On this basis, assuming that the channel proportion data of a certain statistical data is s%=30%, and x=29%, the data diagnosis result is "qualified", then the evaluation value of the data diagnosis result is 1 point, indicating that the data diagnosis result is barely reasonable.

[0040] Assume that the statistical data that needs to be diagnosed is recorded as target data. When the target data is diagnosed based on the data diagnosis rules and evaluation methods configured above, the subject of the target data is first determined, and the various data indicators related to the target data are obtained, recorded as target indicators, and the indicator parameters of each target indicator are obtained, recorded as target indicator parameters. For example, the subject of the target data is a sales subject, and the relevant data indicators include channel share indicators, then the channel share indicator is marked as the target indicator. On this basis, the channel share data in the target data is the indicator parameter of the channel share indicator, recorded as the target indicator parameter. Assuming that the channel share data in the target data is 50%, the target indicator parameter corresponding to the channel share indicator is 50%.

[0041] Based on the pre-configured data diagnosis rules, different data indicators are configured with corresponding data diagnosis rules, and the data diagnosis rules corresponding to the target data indicators are recorded as target diagnosis rules. Based on this, the target diagnosis rules can be used to perform data diagnosis on the target indicator parameters to obtain corresponding data diagnosis results, which are recorded as target diagnosis results.

[0042] The data diagnosis method disclosed in the present invention, after obtaining the target diagnosis result, obtains the evaluation value given by the manual or evaluation model to the target diagnosis result, and determines whether the evaluation value is less than the preset evaluation threshold. If the evaluation value is greater than or equal to the preset evaluation threshold, that is, it indicates that the target diagnosis result is relatively accurate, the target diagnosis result can be accepted as the final diagnosis result output. If the evaluation value is less than the preset evaluation threshold, that is, it indicates that the target diagnosis result is not accurate enough, then it is necessary to adjust the target diagnosis rule based on the evaluation value to obtain the adjusted target diagnosis rule, and use the adjusted target diagnosis rule to re-diagnose the data to obtain the target diagnosis result, until the evaluation value of the obtained target diagnosis result is greater than or equal to the preset evaluation threshold, then the target diagnosis result is output.

[0043] In summary, the data diagnosis method disclosed in the present invention has a certain self-feedback capability. After obtaining the target diagnosis result, it can be judged whether the target diagnosis result is accurate based on the evaluation value of the target diagnosis result. If the target diagnosis result is inaccurate, the target diagnosis rule is adjusted and the target diagnosis result is re-obtained. In this way, the adjusted target diagnosis rule will become more reliable, so that the target diagnosis result obtained based on the target diagnosis rule can be more accurate. On the other hand, if the target data includes multiple target indicator parameters, the data diagnosis method disclosed in the present invention can be used to diagnose each target indicator parameter separately to obtain the target diagnosis result, and each target diagnosis result can be evaluated separately. In this way, the data indicator pointed to by the abnormal data can be accurately determined based on the target indicator corresponding to the unqualified target diagnosis result, and the inaccurate target diagnosis rule can be optimized in a targeted manner.

[0044] Figure 2 The data diagnosis system 1000 according to the embodiment of the present disclosure is shown in FIG. The data diagnosis system 1000 includes a processor 1200 and a memory 1300 , and the memory 1300 stores a computer program.

[0045] Please combine Figure 3 When the computer program is executed by the processor 1200, the processor 1200 may perform the following steps included in the data diagnosis method M100: S110: Perform an index detection on the target data to obtain target index parameters corresponding to the target data. This process can be implemented by the index module 1002.

[0046] S120: Obtain target diagnosis rules corresponding to target indicator parameters. This process can be implemented by rule module 1004.

[0047] S130: Perform data diagnosis on the target indicator parameter based on the target diagnosis rule to obtain the target diagnosis result. This process can be implemented by the diagnosis module 1006.

[0048] S140: Obtaining an evaluation value of the target diagnosis result. This process can be implemented by the evaluation module 1008.

[0049] S150 : In response to the evaluation value being less than a preset evaluation threshold, adjusting the target weight value in the target diagnosis rule based on the evaluation value, and acquiring the adjusted target diagnosis rule. This process can be implemented by the adjustment module 1010 .

[0050] S160: Perform data diagnosis on the target indicator parameter based on the adjusted target diagnosis rule to re-obtain the target diagnosis result. This process can be implemented by the diagnosis module 1006.

[0051] In step S110, target data refers to the data subject for data diagnosis. In some embodiments, target data includes statistical data, such as number, total number, elements in a set, average, variance, standard deviation, etc., which are not listed here one by one.

[0052] Indicator detection refers to detecting the target indicator parameters in the target data. Among them, the target indicators include data indicators in the pre-configured data topics, such as channel share indicators, human resource efficiency indicators, viewing volume indicators, consultation volume indicators, order volume indicators and actual sales volume indicators in the sales topic, etc. If the target data contains data indicators in the pre-configured data topics, the corresponding parameters of the data indicators are the target indicator parameters. For example, if the target data includes "channel share is 50%", then "channel share 50%" is a target indicator parameter in the target data, and the corresponding target indicator is the channel share indicator. In one example, the target indicator parameter has an indicator label, and the indicator label is used to characterize the data indicator corresponding to the target indicator parameter.

[0053] In step S120, the target diagnosis rule is a judgment rule for determining whether the target indicator parameter is reasonable. The target diagnosis rule can be based on conditions, formulas, algorithm rules, etc., which are not limited here. Among them, each target indicator is pre-configured with a corresponding target diagnosis rule, that is, a target diagnosis rule corresponding to the target indicator parameter, which is used to perform data diagnosis on the target indicator parameter to obtain a target diagnosis result. In an example, a query dictionary can be constructed in advance based on the data indicator and the corresponding data diagnosis rule. When obtaining the target indicator parameter, the data indicator of the target indicator parameter can be input into the query dictionary, and the data diagnosis rule output by the query dictionary is the target diagnosis rule corresponding to the target indicator parameter.

[0054] In step S130, performing data diagnosis on the target indicator parameter refers to determining whether the target indicator parameter is qualified. Whether the target indicator parameter is qualified can characterize whether the target indicator parameter is abnormal, that is, if the target indicator parameter is qualified, it characterizes that the target indicator parameter is normal, otherwise, if the target indicator parameter is unqualified, it characterizes that the target indicator parameter is abnormal. In one example, the diagnosis module 1006 includes a plurality of sub-diagnosis modules, each of which stores a corresponding data diagnosis rule. After obtaining the target diagnosis rule, the stored data diagnosis rule is queried to be a sub-diagnosis module of the target diagnosis rule, the target indicator parameter is input into the sub-diagnosis module, and the sub-diagnosis module performs data diagnosis on the target indicator parameter based on the stored data diagnosis rule, and outputs the target diagnosis result.

[0055] In step S140, the evaluation value of the target diagnosis result is an evaluation based on the target diagnosis rule and the target diagnosis result, and represents whether the target diagnosis result obtained by performing data diagnosis based on the target diagnosis rule is reasonable. Therefore, the evaluation value of the target diagnosis result can represent the accuracy of the target diagnosis result.

[0056] In some embodiments, the evaluation value of the target diagnostic result is obtained by scoring the target diagnostic result by experts in the subject field of the target data. For example, "3 points" indicates that the target diagnostic result is reasonable, "2 points" indicates that the target diagnostic result is relatively reasonable, "1 point" indicates that the target diagnostic result is barely reasonable, and "0 points" indicates that the target diagnostic result is unreasonable. In one example, the target diagnostic result is sent to the expert's terminal device via a communication module, and the communication module is also used to receive the evaluation value of the target diagnostic result sent from the expert's terminal device.

[0057] In some embodiments, the evaluation value of the target diagnostic result is obtained by scoring the target diagnostic result by a trained evaluation model. The evaluation model is configured to output a corresponding evaluation value based on the input diagnostic result. When training the evaluation model, the annotated diagnostic result with a reference score and the diagnostic rule corresponding to the diagnostic result can be used as a training set, so that the evaluation model learns the intrinsic connection between the diagnostic rule and the diagnostic result, so that the evaluation value output by the evaluation model can represent the rationality of the corresponding diagnostic result obtained based on the diagnostic rule.

[0058] In some embodiments, when a user uses the data diagnosis system 1000 to obtain a target diagnosis result for target data, the user's evaluation value for the target diagnosis result is obtained. If the user's evaluation value is less than a preset evaluation value, resulting in an adjustment of the target diagnosis rule, the adjusted target diagnosis rule is only used to re-obtain the target diagnosis result for the target data input by the user. In other words, if the evaluation value obtained based on different evaluation criteria of different users involves adjusting the target diagnosis rule, the adjusted target diagnosis rule is only applicable to the user who made the evaluation value. In this way, the adjusted target diagnosis rule can adapt to user habits.

[0059] In step S150, based on the type of evaluation value, the preset evaluation threshold value can be a numerical value, a percentage, a specific label, etc. For example, if the evaluation value is an integer value, the preset evaluation threshold value is a certain integer value; if the evaluation value is a percentage, the preset evaluation threshold value is a certain percentage; if the evaluation value is one of multiple labels, for example, one of the four labels of "reasonable", "relatively reasonable", "barely reasonable", and "unreasonable", the evaluation threshold value is one of the labels. In this case, the evaluation value is less than the preset evaluation threshold value, which means that the order corresponding to the label of the evaluation value is less than the order corresponding to the label of the preset evaluation threshold value, wherein the order corresponding to the evaluation value label is a pre-configured order, for example, the order of the four labels of "reasonable", "relatively reasonable", "barely reasonable", and "unreasonable" can be pre-configured to be 4, 3, 2, and 1, respectively.

[0060] In some embodiments, the target diagnosis rule includes performing a certain rule calculation on the target indicator parameter to obtain a calculation result, comparing the calculation result with a reference value corresponding to the target indicator, and obtaining the target diagnosis result according to the comparison result. For example, the target diagnosis rule can be represented by the following formula 1.

[0061] Formula 1: Among them, s represents the target parameter value. It represents the calculation of the target parameter value according to certain rules, such as rounding calculation, average calculation, variance calculation, etc., which are not listed here one by one. Characterizes the benchmark value corresponding to the target indicator, which is a pre-configured fixed value. Represents the target weight value in the target diagnosis rule.

[0062] When the evaluation value is less than the preset evaluation threshold, the evaluation value is considered to be relatively low. At this time, the target weight value can be increased to a certain extent based on the value of the evaluation value. The value of makes the qualification judgment of the target diagnosis rule more stringent, so as to improve the accuracy of the target diagnosis result when the data is diagnosed based on the target diagnosis rule next time.

[0063] For example, suppose the target diagnosis rule is "If the channel proportion data is greater than or equal to x%, the output data diagnosis result is 'qualified'; otherwise, that is, if the channel proportion data is less than x%, the output data diagnosis result is 'unqualified'". The preset evaluation threshold is 2 points, and the target weight value is The initial value of is 1. If the target diagnosis result is 1, the target weight value The value of is increased by 0.005; if the target diagnosis result is 1 point, the target weight value is The value of is increased by 0.010. Data diagnosis is performed on the target indicator parameter s1 of a certain target data, and the diagnostic result is , that is, the target diagnosis result is qualified. If the evaluation value of the target diagnosis result is 0 points, then in response to 0 points < 1 point, the target weight value is The value of is increased by 0.010 to make the qualification judgment of the target diagnosis rule more stringent.

[0064] In some implementations, there may be multiple target weight values ​​in the target diagnosis rule. For example, the target diagnosis rule may be represented by the following formula 2.

[0065] Formula 2: Among them, Formula 2 adds a new parameter compared to Formula 1 Represents the target weight value in the target diagnosis rule.

[0066] If the evaluation value is based on the diagnosis result being "qualified", when the evaluation value is less than the preset evaluation threshold, it indicates that the evaluation value is low because the result is judged as "qualified", so the target weight value should be increased to a certain extent based on the value of the evaluation value. The value of makes the qualified judgment of the target diagnosis rule more stringent, that is, makes the diagnosis result more likely to be judged as unqualified. If the evaluation value is made based on the diagnosis result being "unqualified", when the evaluation value is less than the preset evaluation threshold, it indicates that the evaluation value is low because the result is judged as "unqualified", so the target weight value should be reduced to a certain extent based on the value of the evaluation value. The value of makes the unqualified judgment of the target diagnosis rule more stringent, that is, makes the diagnosis result easier to be judged as qualified.

[0067] For example, the target indicator parameter s2 of a certain target data is diagnosed and the diagnostic result is , that is, the target diagnosis result is unqualified. If the evaluation value of the target diagnosis result is 0 points, then in response to 0 points < 1 point, the target weight value is The value of is reduced by 0.010, making the failure judgment of the target diagnosis rule more stringent.

[0068] In step S160, data diagnosis is performed on the target indicator parameters based on the adjusted target diagnosis rules to reacquire the target diagnosis results; the scheme adopted for obtaining the diagnosis results is similar to the scheme for obtaining the target diagnosis results in step S130, with the only difference being that the target diagnosis rules adopted for data diagnosis in step S160 have been adjusted.

[0069] Assuming that the initial target diagnosis rule is G1, and the evaluation value of the target diagnosis result obtained based on the target diagnosis rule G2 is J1, and J1 is less than the preset evaluation threshold, the target weight value in the target diagnosis rule G1 is adjusted to obtain the adjusted target diagnosis rule G2. If the evaluation value of the target diagnosis result obtained based on the target diagnosis rule G2 is J2, and J2 is greater than the preset evaluation threshold, the target diagnosis rule G2 is no longer adjusted, and the target diagnosis result obtained based on the target diagnosis rule G2 is output, and the target diagnosis result is obtained based on the target diagnosis rule G2 when the target indicator parameters of the same indicator are subjected to data diagnosis next time. If J2 is less than the preset evaluation threshold, the target weight value in the target diagnosis rule G2 is adjusted to obtain the adjusted target diagnosis rule G3, and step S160 is repeated to perform data diagnosis on the current target indicator parameters based on the target diagnosis rule G3 to obtain the target diagnosis result again.

[0070] In summary, the processor 1200 of the data diagnosis system 1000 executes the above steps S110, S120, S130, S140, S150 and S160 included in the data diagnosis method M100, so that the target diagnosis result of the data diagnosis is more accurate as the number of data diagnoses accumulates.

[0071] See also Figure 4 In some implementations, in step S110, an indicator detection is performed on the target data to obtain a target indicator parameter corresponding to the target data, including step S111, step S112 and step S113.

[0072] S111: Acquire preconfigured topic information, where the topic information includes multiple preset data topics, and each preset data topic includes one or more corresponding preset data indicators.

[0073] In one example, a database is established based on preconfigured subject information to store multiple preset data subjects. Among them, one or more preset data indicators included in each preset data subject are indicators related to the subject content. For example, a sales subject includes channel share indicators, human resource efficiency indicators, viewing volume indicators, consultation volume indicators, order volume indicators, and actual sales volume indicators, which are not listed here one by one.

[0074] S112: Detect the preset data subject corresponding to the target data, and obtain the target data subject.

[0075] The preset data subject corresponding to the target data can be detected by keyword detection, semantic recognition, label matching, etc., which are not limited here. The preset data subject corresponding to the target data is the target data subject.

[0076] In one example, based on the number of corresponding keywords in the target data and the preset data indicators in the preset data theme, the preset data theme with the largest number of corresponding keywords is determined as the preset data theme corresponding to the target data. For example, keyword detection is performed on a certain target data, and the detected keywords include "channel share", "human resource efficiency", "order quantity" and "actual sales volume", which correspond to the four preset data indicators in a certain sales theme and are the largest number, then the sales theme is the preset data theme corresponding to the target data, and the sales theme is determined as the target data theme.

[0077] In one example, semantic recognition is performed on the target data to obtain a semantic recognition result, and the semantic recognition result is matched with the preset data subject for similarity, and the preset data subject with the highest similarity is the preset data subject corresponding to the target data. For example, if semantic recognition is performed on the target data and the semantic recognition result has the highest similarity with a certain sales subject, then the sales subject is the target data subject.

[0078] In one example, the target data has a subject tag, and the preset data subject corresponding to the target data can be determined according to the subject tag.

[0079] S113: Matching parameter values ​​in the target data based on one or more preset data indicators in the target data subject, and obtaining target indicator parameters corresponding to the target data according to the matched preset data indicators and parameter values.

[0080] For example, if the parameter value "Order Quantity 1000" in the target data matches the preset data indicator "Order Quantity", the numerical value in the parameter value and the label "Order Quantity" of the preset data indicator are retained, and the corresponding target indicator parameter is "Order Quantity 1000". In this way, in the subsequent steps, the "Order Quantity" label in the target indicator parameter "Order Quantity 1000" is used to match the corresponding target diagnosis rule, and the numerical value "1000" is used for data diagnosis calculation.

[0081] In some embodiments, the target diagnostic rule corresponding to the target indicator parameter includes a target weight value, a target algorithm, and a target indicator reference value. The target algorithm is a calculation rule for calculating the target indicator parameter, and the target result value is obtained by calculating the target indicator parameter based on the target algorithm. The target indicator reference value is a pre-configured reference value corresponding to the target indicator, which is a fixed value.

[0082] See also Figure 5In one example, step S130, performing data diagnosis on the target indicator parameter based on the target diagnosis rule to obtain the target diagnosis result, includes step S131 and step S132.

[0083] S131: Calculate the target result value of the target indicator parameter based on the target algorithm.

[0084] S132: Obtain a target diagnosis result based on the size of the target result value and the product of the target weight value and the target indicator reference value.

[0085] For example, the target diagnosis rule is in the form of Formula 1 or Formula 2 above. Taking Formula 1 as an example, is the target result value, It is the product of the target weight value and the target index benchmark value. and The target diagnosis result can be obtained by adjusting the size between them.

[0086] See also Figure 6 In another example, step S130, performing data diagnosis on the target indicator parameter based on the target diagnosis rule to obtain the target diagnosis result, includes step S131 and step S133.

[0087] S131: Calculate the target result value of the target indicator parameter based on the target algorithm.

[0088] S133: Obtain a target diagnosis result based on the difference between the target result value and the product of the target weight value and the target indicator reference value.

[0089] For example, the target diagnosis rule is as shown in the following formula 3.

[0090] Formula 3: in, Characterize the target result value, Represents the product of the target weight value and the target index benchmark value, and C is the target result value and target weight Target index benchmark value The product of The difference between < < < < The smaller the value of C, the closer the target result value is to the target indicator reference value, and the better the target indicator parameter is; the larger the value of C, the farther the target result value is from the target indicator reference value, and the worse the target indicator parameter is. In this way, based on the multiple different intervals where the difference C is located, multiple different levels of target diagnosis results can be configured to make the gradient of the target diagnosis result richer, so as to improve the accuracy of the target diagnosis result.

[0091] In some implementations, step S130, performing data diagnosis on the target indicator parameter based on the target diagnosis rule to obtain the target diagnosis result, includes step S135.

[0092] S135: Input the target indicator parameters and the target diagnosis rules into the target language model, and obtain the target diagnosis result output by the target language model.

[0093] Among them, the target language model is configured to be trained based on the calibrated target diagnostic rules, and is used to output the corresponding diagnostic results according to the input index parameters and the calibrated target diagnostic rules. The calibrated target diagnostic rules refer to the initial target diagnostic rules that have not been adjusted. The target language model uses manually labeled index parameters and diagnostic results as training sets and validation sets. When the similarity between the target diagnostic results output by the target language model based on the calibrated target diagnostic rules and labeled index parameters and the manually labeled diagnostic results reaches a certain similarity threshold, the training of the target language model is completed.

[0094] See also Figure 7 In some implementations, the evaluation value of the target diagnostic result includes an evaluation of the target algorithm, an evaluation of the target indicator, and an evaluation of the target indicator benchmark. In step S140, obtaining the evaluation value of the target diagnostic result includes steps S141, S142, S143, S144, and S145.

[0095] S141: Based on the target diagnosis rules and the target diagnosis results, the target algorithm score, the target indicator parameter score and the target indicator benchmark score of the target data are respectively obtained.

[0096] S142: Obtain a first sub-evaluation value based on the target algorithm score.

[0097] S143: Obtain a second sub-evaluation value based on the target indicator parameter score.

[0098] S144: Obtain a third sub-evaluation value based on the target indicator benchmark score.

[0099] S145: Obtaining an evaluation value of the target diagnosis result based on a set of the first sub-evaluation value, the second sub-evaluation value, and the third sub-evaluation value.

[0100] For example, the target diagnosis rule is as shown in Formula 1.

[0101] Formula 1: Assuming that the target diagnostic result of the target indicator parameter s1 is "qualified", the target diagnostic result evaluation value of the target indicator parameter s1 is J1, J1={j1z1, j1z2, j1z3}, j1z1, j1z2, j1z3 are the first sub-evaluation value, the second sub-evaluation value and the third sub-evaluation value respectively. The first sub-evaluation value j1z1 is the target algorithm in the target diagnosis rule. Scoring value, target algorithm The more reasonable the use of is, the higher the score of the first sub-evaluation value j1z1 is. Conversely, the target algorithm The more unreasonable the use of , the lower the score of the first sub-evaluation value j1z1. Similarly, the second sub-evaluation value j1z2 is the score of the target indicator parameter s1. The more reasonable the target indicator parameter s1 is, the higher the score of the second sub-evaluation value j1z2 is. Conversely, the more unreasonable the target indicator parameter s1 is, the lower the score of the second sub-evaluation value j1z2 is. Similarly, the third sub-evaluation value j1z3 is the score of the target indicator benchmark. Scoring value, target indicator benchmark The more reasonable, the higher the score of the third sub-evaluation value j1z3, and vice versa. The more unreasonable, the lower the score of the third sub-evaluation value j1z3. Assuming that the scores of the first sub-evaluation value j1z1, the second sub-evaluation value j1z2, and the third sub-evaluation value j1z3 are 2 points, 3 points, and 2 points respectively, the target diagnostic result evaluation value J1 of the target indicator parameter s1 is {2, 3, 2}.

[0102] For further information, see Figure 8 In some implementations, the target weight value in the target diagnosis rule includes a target algorithm weight value, a target indicator parameter weight value, and a target indicator reference weight value. In step S150, adjusting the target weight value in the target diagnosis rule based on the evaluation value to obtain the adjusted target diagnosis rule includes: step S151, step S152, step S153, and step S154.

[0103] S151: In response to the first sub-evaluation value being less than a pre-configured first evaluation threshold, adjusting a target algorithm weight value based on a difference between the first evaluation threshold and the first sub-evaluation value.

[0104] S152: In response to the second sub-evaluation value being less than a pre-configured second evaluation threshold, adjusting the target indicator parameter weight value based on a difference between the second evaluation threshold and the second sub-evaluation value.

[0105] S153: In response to the third sub-evaluation value being less than a pre-configured third evaluation threshold, adjusting the target indicator reference weight value based on a difference between the third evaluation threshold and the third sub-evaluation value.

[0106] S154: In response to the adjustment result based on any one or more of the target algorithm weight value, the target indicator parameter weight value and the target indicator reference weight value, an adjusted target diagnosis rule is obtained.

[0107] For example, the target diagnosis rule is as shown in Formula 4.

[0108] Formula 4: in, is the target indicator parameter, is the target algorithm, As the target indicator benchmark, is the target algorithm weight value, is the target indicator parameter weight value, As an example, in response to the first sub-evaluation value being less than the pre-configured first evaluation threshold, the target algorithm weight value is set to The greater the difference between the first evaluation threshold and the first sub-evaluation value, the greater the target algorithm weight value after the increase. The larger the value, the smaller the difference between the first evaluation threshold and the first sub-evaluation value, and the increased target algorithm weight value The smaller the difference between the first evaluation threshold and the first sub-evaluation value and the target algorithm weight value is, the smaller the difference between the first evaluation threshold and the first sub-evaluation value is. The proportional relationship between the increased values ​​is not limited and can be configured according to the application scenario. Similarly, in response to the second sub-evaluation value being less than the pre-configured second evaluation threshold, the indicator parameter weight value is set to The greater the difference between the second evaluation threshold and the second sub-evaluation value, the greater the weight value of the indicator parameter after the increase. The larger the value, the smaller the difference between the second evaluation threshold and the second sub-evaluation value, and the increased indicator parameter weight value The smaller the difference between the second evaluation threshold and the second sub-evaluation value and the indicator parameter weight value is, the smaller the difference between the second evaluation threshold and the second sub-evaluation value is. The proportional relationship between the increased values ​​is not limited and can be configured according to the application scenario. Similarly, in response to the third sub-evaluation value being less than the pre-configured third evaluation threshold, the target indicator benchmark weight value is set to The greater the difference between the third evaluation threshold and the third sub-evaluation value, the greater the target indicator benchmark weight value after the increase. The larger the value, the smaller the difference between the third evaluation threshold and the third sub-evaluation value, and the increased target indicator benchmark weight value The smaller the difference between the third evaluation threshold and the third sub-evaluation value and the target indicator benchmark weight value is, the smaller the difference between the third evaluation threshold and the third sub-evaluation value is. There is no restriction on the proportional relationship between the increase values ​​and it can be configured according to the application scenario. , indicator parameter weight value and target indicator benchmark weight value When any weight value in is adjusted, the adjusted target diagnosis rule is obtained based on the adjusted corresponding weight value. In this way, the sub-weight value of the target weight value can be adjusted more carefully based on the sub-evaluation value of the target diagnosis result to accurately adjust the target diagnosis rule and improve the accuracy of data diagnosis.

[0109] See also Fig. 9 In some implementations, the target data may correspond to a plurality of target indicator parameters, and each target indicator parameter may correspond to a target diagnosis result. The data diagnosis method M100 may further include step S170.

[0110] S170: In response to the evaluation value of the target diagnosis result of each target indicator parameter being greater than or equal to a preset evaluation threshold, a final diagnosis result is obtained based on the target diagnosis results corresponding to each of the multiple target indicator parameters.

[0111] Specifically, when the evaluation value of the target diagnosis result of a target indicator parameter is greater than or equal to a preset evaluation threshold, the target diagnosis result of the target indicator parameter is cached. When the evaluation value of the target diagnosis result of each target indicator parameter in the target data is greater than or equal to the preset evaluation threshold, the cached target diagnosis results are integrated into a final diagnosis result output.

[0112] For further information, see Fig.10 In some implementations, step S170 includes: step S171, step S172, and step S173.

[0113] S171: Sort the multiple target diagnosis results based on the target weight values ​​of the target diagnosis rules corresponding to the multiple target diagnosis results, and obtain the order of the diagnosis results.

[0114] S172: Based on the diagnosis result sequence and a preconfigured text generation template, text generation processing is performed on multiple target diagnosis results to obtain diagnosis result texts.

[0115] S173: Outputting a final diagnosis result based on the diagnosis result text.

[0116] The order of the diagnostic results includes the order of each target diagnostic result. In one example, the higher the target weight value of the target diagnostic rule corresponding to the target diagnostic result, the higher the order of the target diagnostic result. In another embodiment, it can also be configured as follows: the higher the target weight value of the target diagnostic rule corresponding to the target diagnostic result, the higher the order of the target diagnostic result, which is not limited here. The final diagnostic result is output in the form of text, and the target diagnostic result with an earlier order appears first in the text of the final diagnostic result.

[0117] In one example, the diagnosis result text can be input into AIGC (Artificial Intelligence Generated Content, abbreviated as: AIGC), and AIGC can be used to beautify the diagnosis result text to a certain extent, such as adjusting the layout, adjusting the text style, adding tables, adding illustrations, adding comments, etc., to generate the final diagnosis result.

[0118] The embodiments of the present disclosure also provide a computer-readable storage medium, in which execution instructions are stored, and when the execution instructions are executed by a processor, they are used to implement the above-mentioned method. "Readable storage medium" can be any device that can contain, store, communicate, propagate or transmit programs for use in an instruction execution system, device or equipment or in combination with these instruction execution systems, devices or equipment. More specific examples of readable storage media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM), etc.

[0119] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which implements the question answering method provided in the embodiments of the present disclosure when the computer program / instruction processor is executed.

[0120] The method in the embodiment of the present disclosure can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM or other programmable device.

[0121] A computer program or instruction may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, a computer program or instruction may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. A computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. Available media may be magnetic media, such as a floppy disk, hard disk, or magnetic tape; may also be optical media, such as a digital video disk; or may be semiconductor media, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0122] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take 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 code.

[0123] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representations of the above terms are not necessarily the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments / methods or examples described in this specification and the features of the different embodiments / methods or examples, unless they are contradictory.

[0124] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0125] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present disclosure and the technical solutions of the present disclosure, rather than limiting them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art who is familiar with the present technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed in the present disclosure or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be based on the protection scope of the claims.

Claims

1. A data diagnosis method, characterized in that: include: Performing indicator detection on the target data to obtain target indicator parameters corresponding to the target data; Obtaining target diagnosis rules corresponding to the target indicator parameters; Performing data diagnosis on the target indicator parameters based on the target diagnosis rule to obtain a target diagnosis result; Obtaining an evaluation value of the target diagnosis result; In response to the evaluation value being less than a preset evaluation threshold, adjusting a target weight value in the target diagnosis rule based on the evaluation value to obtain an adjusted target diagnosis rule; as well as Perform data diagnosis on the target indicator parameter based on the adjusted target diagnosis rule to re-obtain the target diagnosis result.

2. The data diagnosis method according to claim 1, characterized in that: Performing index detection on the target data to obtain target index parameters corresponding to the target data includes: Acquire preconfigured topic information, the topic information has a plurality of preset data topics, each of the preset data topics includes one or more corresponding preset data indicators; Detecting the preset data subject corresponding to the target data to obtain the target data subject; and The parameter value in the target data is matched based on one or more of the preset data indicators in the target data subject, and the target indicator parameter corresponding to the target data is obtained according to the matched preset data indicator and the parameter value.

3. The data diagnosis method according to claim 1, characterized in that: The target diagnosis rules corresponding to the target indicator parameters also include a target algorithm and a target indicator reference value.

4. The data diagnosis method according to claim 3, characterized in that: Performing data diagnosis on the target indicator parameter based on the target diagnosis rule to obtain a target diagnosis result includes: Calculating a target result value of the target indicator parameter based on the target algorithm; and Acquire the target diagnosis result based on the size of the target result value and the product of the target weight value and the target indicator reference value; or The target diagnosis result is obtained based on the difference between the target result value and the product of the target weight value and the target indicator reference value.

5. The data diagnosis method according to claim 1, characterized in that: Performing data diagnosis on the target indicator parameter based on the target diagnosis rule to obtain a target diagnosis result includes: Inputting the target indicator parameter and the target diagnosis rule into a target language model, and obtaining the target diagnosis result output by the target language model; The target language model is configured to be trained based on calibrated target diagnostic rules, and is used to output corresponding diagnostic results according to input indicator parameters and calibrated target diagnostic rules.

6. The data diagnosis method according to claim 1, characterized in that: Obtaining the evaluation value of the target diagnosis result includes: Based on the target diagnosis rule and the target diagnosis result, respectively obtaining a target algorithm score, a target indicator parameter score and a target indicator benchmark score of the target data; Obtaining a first sub-evaluation value based on the target algorithm score; Obtaining a second sub-evaluation value based on the target indicator parameter score; Acquire a third sub-evaluation value based on the target indicator benchmark score; and An evaluation value of the target diagnosis result is acquired based on a set consisting of the first sub-evaluation value, the second sub-evaluation value, and the third sub-evaluation value.

7. The data diagnosis method according to claim 6, characterized in that: The target weight values ​​in the target diagnosis rules include target algorithm weight values, target indicator parameter weight values ​​and target indicator benchmark weight values; Adjusting the target weight value in the target diagnosis rule based on the evaluation value to obtain the adjusted target diagnosis rule includes: In response to the first sub-evaluation value being less than a pre-configured first evaluation threshold, adjusting the target algorithm weight value based on a difference between the first evaluation threshold and the first sub-evaluation value; and / or In response to the second sub-evaluation value being less than a pre-configured second evaluation threshold, adjusting the target indicator parameter weight value based on a difference between the second evaluation threshold and the second sub-evaluation value; and / or In response to the third sub-evaluation value being less than a pre-configured third evaluation threshold, adjusting the target indicator reference weight value based on a difference between the third evaluation threshold and the third sub-evaluation value; and In response to the adjustment result based on any one or more of the target algorithm weight value, the target indicator parameter weight value and the target indicator reference weight value, the adjusted target diagnosis rule is acquired.

8. The data diagnosis method according to claim 1, characterized in that: Acquiring a plurality of target indicator parameters corresponding to the target data, each of which corresponds to one target diagnosis result; The data diagnosis method further includes: In response to the evaluation value of the target diagnostic result of each of the target indicator parameters being greater than or equal to a preset evaluation threshold, a final diagnostic result is obtained based on the target diagnostic results corresponding to each of the multiple target indicator parameters.

9. The data diagnosis method according to claim 8, characterized in that: In response to the evaluation value of the target diagnostic result of each target indicator parameter being greater than or equal to a preset evaluation threshold, obtaining a final diagnostic result based on the target diagnostic results corresponding to each of the plurality of target indicator parameters, including: Based on the target weight values ​​of the target diagnosis rules corresponding to the multiple target diagnosis results, the multiple target diagnosis results are sorted to obtain a diagnosis result sequence; Based on the diagnostic result sequence and a preconfigured text generation template, performing text generation processing on the plurality of target diagnostic results to obtain diagnostic result texts; and A final diagnosis result is output based on the diagnosis result text.

10. A data diagnosis system, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the data diagnosis method according to any one of claims 1 to 9.

11. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the data diagnosis method according to any one of claims 1 to 9.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program is at least used to implement the data diagnosis method according to any one of claims 1 to 9.

Images