Data sampling detection method and device

Abstract

The embodiment of the present application provides a data sampling detection method and device, the method comprising: obtaining the data to be detected; determining the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions, wherein the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs; determining sample data from the data to be detected according to the sampling inspection priority of the data to be detected; and sending the sample data to the terminal device for quality inspection. In this way, since the data to be detected with a higher sampling inspection priority is given priority, the data related to the key indicator problem can be set with a higher priority to achieve focused monitoring of the key indicator problem.

Description

Technical Field

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

[0002] Service quality inspection is an important quality control link in the operation of the customer service system. Service quality inspection mainly relies on manual listening and analysis of customer service personnel's recordings to find out various problems in the customer service personnel's service in order to further improve the service quality.

[0003] Since the amount of customer service data is often large, random sampling is usually used to extract sample data from a large amount of customer service data, and the extracted sample data is sent to the quality inspection terminal for quality inspectors to conduct quality inspections and find defective samples with quality problems. Subsequently, the defect rate and pass rate can be calculated based on the number of defective samples and the number of sample data, thereby achieving quality control of the customer service system.

[0004] However, the random sampling method used to extract sample data from a large amount of customer service data has a certain degree of randomness and cannot focus on monitoring key indicator issues. Summary of the invention

[0005] The embodiments of the present application provide a data sampling detection method and device to solve the problem that key indicator issues cannot be monitored in a focused manner in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a data sampling detection method, the method comprising:

[0007] Obtain the data to be tested;

[0008] Determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions, wherein the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs;

[0009] Determining sample data from the data to be detected according to the sampling priority of the data to be detected;

[0010] The sample data is sent to the terminal device for quality inspection.

[0011] In an optional implementation manner, determining the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions includes:

[0012] Determining the average weight of the data to be detected according to the weights of the data to be detected in the different dimensions;

[0013] Sorting the data to be detected according to the average weight of the data to be detected;

[0014] According to the sorting result of the data to be detected, a sampling priority of the data to be detected is determined.

[0015] In an optional implementation manner, before determining the average weight of the data to be detected, the method further includes:

[0016] Obtaining default values ​​of weight indicators of the data to be detected in the different dimensions;

[0017] The weights of the data to be detected in the different dimensions are determined according to the offset value of the data to be detected relative to the default value.

[0018] In an optional implementation manner, determining sample data from the data to be detected according to the sampling priority of the data to be detected includes:

[0019] Determining a target sampling quantity of the data to be detected;

[0020] According to the sampling priorities from high to low, the target sampling quantity of data to be detected is determined from the data to be detected as the sample data.

[0021] In an optional implementation manner, before determining the sampling priority of the data to be detected, the method further includes:

[0022] According to the allocation rules of multiple dimensions, the data to be detected is filtered to remove useless data in the data to be detected.

[0023] In an optional implementation manner, filtering the data to be detected to remove useless data in the data to be detected includes:

[0024] Get multiple allocation rules configured in the quality inspection plan;

[0025] The data to be detected are filtered respectively using the multiple allocation rules to remove useless data in the data to be detected.

[0026] In an optional implementation, the allocation rules include business allocation rules and system allocation rules.

[0027] In an optional implementation, the business allocation rules include data source rules, business line rules, business classification rules and duration rules, and the system allocation rules include object rules, invalid data removal rules and key item error count rules.

[0028] In an optional implementation manner, after sending the sample data to a terminal device for quality inspection, the method further includes:

[0029] Receive the quality inspection result of the sample data sent by the terminal device.

[0030] In an optional implementation, the quality inspection result of the sample data is determined based on whether the sample data passes a key item.

[0031] In an optional implementation manner, after receiving the quality inspection result of the sample data sent by the terminal device, the method further includes:

[0032] Determine the object corresponding to the sample data that does not pass the key item;

[0033] Accumulate the number of critical item errors of the subject during the target period;

[0034] The key item error count rule is updated according to the key item error count accumulated in the target period.

[0035] In a second aspect, an embodiment of the present application provides a data sampling detection device, the device comprising:

[0036] An acquisition module, used for acquiring data to be detected;

[0037] A processing module, used to determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions; determine sample data from the data to be detected according to the sampling priority of the data to be detected, and the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs;

[0038] The sending module is used to send the sample data to the terminal device for quality inspection.

[0039] In an optional implementation, the processing module is specifically used to determine the average weight of the data to be detected according to the weights of the data to be detected in the different dimensions; sort the data to be detected according to the average weight of the data to be detected; and determine the sampling priority of the data to be detected according to the sorting result of the data to be detected.

[0040] In an optional implementation manner, the acquisition module is further used to obtain default values ​​of weight indicators of the data to be detected in the different dimensions;

[0041] The processing module is further used to determine the weights of the data to be detected in the different dimensions according to the offset value of the data to be detected relative to the default value.

[0042] In an optional implementation, the processing module is specifically used to determine a target sampling quantity of the data to be detected; and determine the target sampling quantity of data to be detected from the data to be detected as the sample data according to a sampling priority from high to low.

[0043] In an optional implementation, the processing module is further used to filter the data to be detected according to allocation rules of multiple dimensions, so as to remove useless data in the data to be detected.

[0044] In an optional implementation, the processing module is specifically used to obtain multiple allocation rules configured in the quality inspection plan; use the multiple allocation rules to filter the data to be detected respectively, and remove useless data in the data to be detected.

[0045] In an optional implementation, the allocation rules include business allocation rules and system allocation rules.

[0046] In an optional implementation, the business allocation rules include data source rules, business line rules, business classification rules and duration rules, and the system allocation rules include object rules, invalid data removal rules and key item error count rules.

[0047] In an optional implementation, the device further includes:

[0048] The receiving module is used to receive the quality inspection result of the sample data sent by the terminal device.

[0049] In an optional implementation, the quality inspection result of the sample data is determined based on whether the sample data passes a key item.

[0050] In an optional embodiment, the processing module is also used to determine the object corresponding to the sample data that does not pass the key item; accumulate the number of key item errors of the object within the target period; and update the key item error number rule based on the number of key item errors accumulated for the object within the target period.

[0051] In a third aspect, the present application further provides an electronic device, comprising: a processor, and a memory;

[0052] The memory is used to store a computer program of the processor; the processor is configured to implement any possible method in the first aspect by executing the computer program.

[0053] In a fourth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method described in any one of the first aspects.

[0054] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium storing computer instructions, on which a computer program is stored, and when the computer program is executed by a processor, any possible method in the first aspect is implemented.

[0055] The data sampling detection method and device provided in the embodiment of the present application first obtain the data to be detected. Secondly, according to the weights of the data to be detected in different dimensions, the sampling priority of the data to be detected is determined, and the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs. Thirdly, according to the sampling priority of the data to be detected, the sample data is determined from the data to be detected. Finally, the sample data is sent to the terminal device for quality inspection. In this way, since the data to be detected with a higher priority is sampled and detected first, the data related to the key indicator problem can be set with a higher priority to achieve key indicator problem monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0057] Figure 1 A schematic diagram of an application scenario of a data sampling detection method provided in an embodiment of the present application;

[0058] Figure 2 A flow chart of a data sampling detection method provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of data filtering provided in an embodiment of the present application;

[0060] Figure 4 A schematic diagram of weight calculation provided in an embodiment of the present application;

[0061] Figure 5 A flowchart of another data sampling detection method provided in an embodiment of the present application;

[0062] Figure 6 A signaling interaction diagram of a data sampling detection method provided in an embodiment of the present application;

[0063] Figure 7 A schematic diagram of the structure of a data sampling detection device provided in an embodiment of the present application;

[0064] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0066] Service quality inspection is an important quality control link in the operation of the customer service system. Service quality inspection mainly relies on manual listening and analysis of customer service personnel's recordings to find out various problems in the customer service personnel's service in order to further improve the service quality.

[0067] Since the amount of customer service data is often large, random sampling is usually used to extract sample data from a large amount of customer service data, and the extracted sample data is sent to the quality inspection terminal for quality inspectors to conduct quality inspections and find defective samples with quality problems. Subsequently, the defect rate and pass rate can be calculated based on the number of defective samples and the number of sample data, thereby achieving quality control of the customer service system.

[0068] However, the random sampling method used to extract sample data from a large amount of customer service data has a certain degree of randomness and cannot focus on monitoring key indicators. At the same time, it is also impossible to analyze and sample the customer service data to be tested from multiple dimensions, and it is impossible to effectively determine the service quality in each dimension, and it is impossible to accurately locate the defects in customer service quality.

[0069] To solve the above problems, the embodiments of the present application provide a data sampling detection method and device, which determines the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions, and preferentially samples the data to be detected with a higher detection priority, so that the data related to the key indicator problem can be set with a higher priority to achieve key monitoring of the key indicator problems.

[0070] The following describes the application scenarios of the method for generating simulation scenarios involved in the present application.

[0071] Figure 1 A schematic diagram of an application scenario of a data sampling detection method provided in an embodiment of the present application. Figure 1As shown, the server 101 can obtain the customer service data to be tested from the service terminal such as the terminal device 102. Subsequently, the server 101 can determine the priority of the customer service data to be tested, and extract sample data from the customer service data to be tested according to the priority of the customer service data to be tested. Finally, the server 101 sends the extracted sample data to the quality inspection terminal such as the terminal device 103, so that the terminal device 103 can perform quality inspection on the extracted sample data and feed back the quality inspection result to the server 101.

[0072] Among them, the terminal device can be a tablet computer (pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in a smart home, etc. In the embodiment of the present application, the device for realizing the function of the terminal can be a terminal, or a device that can support the terminal to realize the function, such as a chip system, which can be installed in the terminal. In the embodiment of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0073] The server can be, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of computers or network servers based on cloud computing. Cloud computing is a type of distributed computing, a super virtual computer consisting of a group of loosely coupled computers.

[0074] It should be understood that the application scenario of the technical solution of this application can be Figure 1 The present invention is applicable to the scenarios in the present invention, but is not limited to this, and can also be applied to other scenarios that require data sampling quality inspection.

[0075] It can be understood that the above-mentioned data sampling detection method can be implemented by the data sampling detection device provided in the embodiment of the present application, and the data sampling detection device can be part or all of a certain device, such as a server or a chip of the server.

[0076] The following takes a server integrated or installed with relevant execution codes as an example to describe the technical solution of the embodiment of the present application in detail with a specific embodiment. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0077] Figure 2The present invention provides a flow chart of a data sampling detection method. This embodiment relates to the process of how the server determines sample data in the data to be detected. Figure 2 As shown, the method includes:

[0078] S201, obtaining data to be detected.

[0079] In the present application, when sampling detection of data is required, the server can obtain the data to be detected.

[0080] The embodiment of the present application does not limit the type of data to be detected, and can be determined according to actual conditions. For example, in a customer service system, a server can obtain customer service data.

[0081] It should be understood that the embodiments of the present application do not limit how to obtain the data to be detected. In some embodiments, the server may pre-store the data to be detected sent by each terminal device, and when data sampling detection is required, the data to be detected can be directly obtained from the server's memory. In other embodiments, when data sampling detection is required, the server may send an acquisition request to each terminal to obtain the data to be detected stored on each terminal device.

[0082] Optionally, after the server obtains the data to be detected, it can also filter the data to be detected to remove useless data in the data to be detected. In some embodiments, the server can first obtain multiple allocation rules configured in the quality inspection plan, and then use the multiple allocation rules to filter the data to be detected respectively to remove useless data in the data to be detected. In this way, data that meets the allocation rules can be filtered out for the next step of data sampling.

[0083] Among them, the allocation rules include business allocation rules and system allocation rules. Business rules rely on various attribute dimensions of the data to be detected for calculation and analysis, while system rules mainly calculate and analyze from specific processing logic or data.

[0084] It should be understood that in the embodiment of the present application, multiple allocation rules can be configured under one quality inspection scheme, and the data to be detected must simultaneously meet all the allocation rules configured under the scheme to pass the data filtering. If the data to be detected does not meet any of the data to be detected, the data to be detected can be determined as useless data and directly discarded.

[0085] In some embodiments, the business allocation rules include data source rules, business line rules, business classification rules and duration rules, and the system allocation rules include object rules, invalid data removal rules and key item error count rules.

[0086] Among them, the data source rule is used to classify and filter the data to be tested according to the business party to which the data to be tested belongs. The business line rule is used to classify and filter the data to be tested according to the business to which the data to be tested belongs. The business classification rule is used to classify and filter the data to be tested according to the business classification to which the data to be tested belongs in the external system. The object rule may include a weekly new employee rule and a weekly old employee rule.

[0087] The weekly new employee rule is used to determine whether the customer service to which the data to be tested belongs is a new employee. If so, the data to be tested is classified, and a specific amount of data to be tested is extracted for each new employee on a weekly basis, so that new employees are given special attention and full coverage. The weekly old employee rule is used to group the data to be tested according to the customer service to which the data to be tested belongs, and a specified amount of data to be tested is extracted for each customer service on a weekly basis, so that the data to be tested is covered by all customers and the customer service level is improved.

[0088] In the invalid data removal rule, if the data to be detected is text data, the total number of customer service and customer service statements in the data to be detected is filtered, and it must be greater than the specified number to meet the rule. If the data to be detected is voice data, the duration of the data to be detected must be greater than the specified duration to meet the rule. By removing the invalid data rule, useless data can be effectively filtered out.

[0089] The key item error count rule is based on customer service as the dimension and weekly as the unit. If the key item of the customer service data to be tested fails during quality inspection, the key item error count will be accumulated by 1. If the accumulated key item error count exceeds the specified error count, the number of random inspections for the customer service will be increased in the next cycle to achieve the purpose of focusing on specific customer service.

[0090] For example, Figure 3 A schematic diagram of data filtering provided in an embodiment of the present application, such as Figure 3 As shown in the figure, three business allocation rules and four system allocation rules are configured in the quality inspection plan. The three business allocation rules are data source rule, business line rule and duration rule, and the four system allocation rules are weekly new employee rule, weekly old employee rule, invalid data removal rule and key item error count rule. After obtaining the data to be tested, the server filters them from the three business allocation rules and four system allocation rules under the quality inspection plan respectively. If the above allocation rules are met, the data to be tested is output and the number of data to be tested is accumulated. If the above allocation rules are not met, the data to be tested is discarded.

[0091] S202. Determine a sampling priority of the data to be detected according to weights of the data to be detected in different dimensions, wherein different dimensions of the data to be detected correspond to different business evaluation features of the customer service system to which the data to be detected belongs.

[0092] In this step, after the server obtains the data to be detected, it can determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions.

[0093] It should be understood that the embodiments of the present application do not limit how to determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions. In some embodiments, the server can first determine the average weight of the data to be detected according to the weights of the data to be detected in different dimensions. Subsequently, the server sorts the data to be detected according to the average weight of the data to be detected. Finally, the server determines the sampling priority of the data to be detected based on the sorting result of the data to be detected.

[0094] In some embodiments, a descending order may be adopted, where the data to be detected with a larger average weight is ranked higher, and correspondingly, the data to be detected with a higher ranking has a higher priority.

[0095] In some embodiments, before the server determines the sampling priority of the data to be detected, it can first obtain the default value of the weight indicator of the data to be detected in different dimensions, and then determine the weight of the data to be detected in different dimensions based on the offset value of the data to be detected relative to the default value.

[0096] Among them, the embodiment of the present application does not limit the different dimensions of the data to be detected, and the default values ​​of the weight indicators under different dimensions, and can be specifically set according to actual conditions.

[0097] The embodiments of the present application do not limit the business evaluation features included in the customer service system. By way of example, they may include personnel, customer service team, customer service company, satisfaction, business classification, call duration, and number of customer messages.

[0098] For example, Figure 4 A schematic diagram of weight calculation provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, when the server calculates the weight of the data to be detected, it can determine the weights in seven dimensions, including the weight of the customer service personnel, the weight of the team to which the customer service belongs, the weight of the company to which the customer service belongs, the weight of the satisfaction, the weight of the business classification, the weight of the call duration, and the weight of the number of customer messages.

[0099] For example, the default value of the weight index of the customer service staff weight may be 200, and the weight index of the customer service staff weight may be dynamically set to focus on a specific customer service staff. Accordingly, the customer service staff weight server_weight may be determined by formula (1).

[0100] server_weight = if (specify customer service?, specify weight, 200) (1)

[0101] Wherein, formula (1) is used to determine whether the data to be detected is a designated customer service. If so, the customer service personnel weight is the designated weight 200. If not, it is determined that the data to be detected has an offset value relative to the default value, and the customer service personnel weight can be determined to be 0.

[0102] For example, the default value of the weight index of the customer service team weight can be 60, and the weight index of the customer service team weight can be dynamically set to focus on the specified team. Accordingly, the customer service team weight server_group_weight can be determined by formula (2).

[0103] server_group_weight = if (specify group?, specify weight, 60) (2)

[0104] Among them, formula (2) is used to determine whether the data to be detected is a specified team. If so, the weight of the team to which the customer service belongs is the specified weight 60. If not, it is determined that the data to be detected has an offset value relative to the default value, and it can be determined that the weight of the team to which the customer service belongs is 0.

[0105] For example, the default value of the weight index of the customer service company weight may be 20, and the weight index of the customer service company weight may be dynamically set to focus on a specified company. Accordingly, the customer service company weight server_company_weight may be determined by formula (3).

[0106] server_company_weight = if (specify company?, specify weight, 20) (3)

[0107] Among them, formula (3) is used to determine whether the data to be detected is a specified company. If so, the weight of the company to which the customer service belongs is the specified weight 20. If not, it is determined that the data to be detected has an offset value relative to the default value, and it can be determined that the weight of the company to which the customer service belongs is 0.

[0108] For example, the default value of the weight index of the satisfaction weight can be determined according to the degree of satisfaction (50 for very dissatisfied, 20 for dissatisfied, and 0 for others), so as to focus on the dissatisfied data to be tested. Correspondingly, the weight satisfaction_weight of the company to which the customer service belongs can be determined by formula (4).

[0109] satisfaction_weight = fun(satisfaction, 50, 20, 0) (4)

[0110] Wherein, formula (4) is used to determine the satisfaction weight according to the satisfaction degree.

[0111] For example, the default value of the weight index of the business category weight may be 50, and the weight index of the business category weight may be dynamically set to focus on the business category. Accordingly, the business category weight biz_type_weight may be determined by formula (5).

[0112] biz_type_weight = if(specify business category?, specify weight, 50) (5)

[0113] Wherein, formula (5) is used to determine whether the data to be detected is a specified business classification, and if so, the business classification weight is a specified weight of 50. If not, it is determined that the data to be detected has an offset value relative to the default value, and the business classification weight can be determined to be 0.

[0114] For example, when the call duration is less than 30 seconds, the default value of the weight index of the call duration weight may be 10, and when the call duration is greater than 600 seconds, the default value of the weight index of the call duration weight may be 50. Accordingly, the call duration weight duration_weight may be determined by formula (6).

[0115] duration_weight = linear_fun(call duration, [30, 10], [600, 50]) (6)

[0117] Wherein, formula (6) is used to determine the call duration weight based on the call duration. For call durations between 30 seconds and 600 seconds, it can be determined by the offset value of the data to be detected relative to the default value, that is, the intermediate state increases linearly.

[0118] Exemplarily, when the number of customer messages is less than 10, the default value of the weight index of the customer message weight may be 10, and when the number of customer messages is greater than 50, the default value of the weight index of the customer message weight may be 50. Accordingly, the customer message weight customer_msg_weight may be determined by formula (7).

[0119] customer_msg_weight = linear_fun(number of customer messages, [10,10], [50,50]) (7)

[0121] Wherein, formula (7) is used to determine the weight of the number of customer messages based on the number of customer messages. For the number of customer messages between 10 and 50, it can be determined by the offset value of the data to be detected relative to the default value, that is, the intermediate state increases linearly.

[0122] S203: Determine sample data from the data to be detected according to the sampling priority of the data to be detected.

[0123] In this step, after the server determines the sampling priority of the data to be detected, the server can determine the sample data from the data to be detected according to the sampling priority of the data to be detected.

[0124] It should be understood that the embodiments of the present application do not limit the determination of sample data from the data to be detected. In some embodiments, the server may first determine the target sampling quantity of the data to be detected, and then the server determines the target sampling quantity of the data to be detected as sample data from the data to be detected according to the sampling priority from high to low.

[0125] Exemplarily, if the target sampling quantity is 50, the server extracts 50 items with the highest priority from the data to be detected as sample data according to the sampling priority from high to low.

[0126] S204: Send the sample data to the terminal device.

[0127] In this step, after the server determines the sample data from the data to be detected, the sample data can be sent to the terminal device so that the terminal device can perform manual quality inspection.

[0128] In some embodiments, the quality inspection result of the sample data is determined based on whether the sample data passes the key item. After the terminal device determines the quality inspection result, the quality inspection result of the sample data can be sent to the server.

[0129] In some embodiments, the server may determine the object corresponding to the sample data that does not pass the key item. Subsequently, the key item error times of the object are accumulated within the target period. Recently, the key item error times rule is updated according to the key item error times accumulated for the object within the target period.

[0130] The target period may be a day or a week, which is not limited in the embodiment of the present application.

[0131] For example, when the sample data assigned daily is quality checked, if the sample data triggers a red indicator and fails the key item, the sample data will be directly quality checked and fail. After receiving the quality check result, the server can add 1 to the cumulative number of customer service failures corresponding to the sample data. If the cumulative counting is performed with the day as the target period, after the number of key item errors of the object accumulated in one day exceeds the art threshold, the key item error number rule can be updated to focus on the object.

[0132] The data sampling detection method provided in the embodiment of the present application first obtains the data to be detected. Secondly, according to the weights of the data to be detected in different dimensions, the sampling priority of the data to be detected is determined, and the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs. Thirdly, according to the sampling priority of the data to be detected, the sample data is determined from the data to be detected. Finally, the sample data is sent to the terminal device for quality inspection. In this way, since the data to be detected with a higher priority is sampled and detected first, the data related to the key indicator problem can be set with a higher priority to achieve focused monitoring of the key indicator problem.

[0133] Based on the data sampling detection method of the above embodiment, how to specifically determine the sample data is described below. Figure 5 A flow chart of another data sampling detection method provided in an embodiment of the present application is as follows: Figure 5 As shown, the method includes:

[0134] S301, obtaining data to be detected.

[0135] S302: Obtain default values ​​of weight indicators of the data to be detected in different dimensions.

[0136] S303: Determine the weights of the data to be detected in different dimensions according to the offset value of the data to be detected relative to the default value.

[0137] S304: Determine the average weight of the data to be detected according to the weights of the data to be detected in different dimensions.

[0138] S305 , sorting the data to be detected according to the average weight of the data to be detected.

[0139] S306: Determine the sampling priority of the data to be detected according to the sorting result of the data to be detected.

[0140] S307: Determine the target sampling quantity of the data to be detected.

[0141] S308 . According to the sampling priorities from high to low, determine the target sampling quantity of data to be detected from the data to be detected as sample data.

[0142] S309: Send the sample data to the terminal device.

[0143] The technical terms, technical effects, technical features, and optional implementation methods of S301-S309 can be referred to Figure 2 It is understood that S201-S204 shown in the figure will not be repeated here for the repeated contents.

[0144] On the basis of the data sampling detection method of the above embodiment, after the server sends the sample data to the terminal device for quality inspection, the terminal device can feed back the quality inspection result to the server so that the server can perform relevant processing according to the subsequent quality inspection result. Figure 6 A signaling interaction diagram of a data sampling detection method provided in an embodiment of the present application, such as Figure 6 As shown, the method includes:

[0145] S401: The server obtains data to be detected.

[0146] S402. The server determines the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions. The different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs.

[0147] S403: The server determines sample data from the data to be detected according to the sampling priority of the data to be detected.

[0148] S404: The server sends sample data to the terminal device.

[0149] S405. The terminal device generates a quality inspection result based on whether the sample data passes the key items.

[0150] S406: The terminal device sends the quality inspection result to the server.

[0151] S407: The server determines the object corresponding to the sample data that does not pass the key item.

[0152] S408: The server accumulates the number of key item errors of the object within the target period.

[0153] S409: The server updates the key item error count rule according to the key item error count of the accumulated object within the target period.

[0154] The technical terms, technical effects, technical features, and optional implementation methods of S401-S409 can be referred to Figure 2 It is understood that S201-S204 shown in the figure will not be repeated here for the repeated contents.

[0155] The data sampling detection method provided in the embodiment of the present application first obtains the data to be detected. Secondly, according to the weights of the data to be detected in different dimensions, the sampling priority of the data to be detected is determined, and the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs. Thirdly, according to the sampling priority of the data to be detected, the sample data is determined from the data to be detected. Finally, the sample data is sent to the terminal device for quality inspection. In this way, since the data to be detected with a higher priority is sampled and detected first, the data related to the key indicator problem can be set with a higher priority to achieve focused monitoring of the key indicator problem.

[0156] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0157] Figure 7 The following is a schematic diagram of the structure of a data sampling detection device provided in an embodiment of the present application. The data sampling detection device can be implemented by software, hardware, or a combination of both, such as the server or server chip in the above embodiment to execute the data sampling detection method in the above embodiment. Figure 7 , the data sampling detection device 500 comprises:

[0158] The acquisition module 501 is used to acquire data to be detected.

[0159] Processing module 502 is used to determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions; determine sample data from the data to be detected according to the sampling priority of the data to be detected, and the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs.

[0160] The sending module 503 is used to send the sample data to the terminal device for quality inspection.

[0161] In an optional implementation, the processing module 502 is specifically used to determine the average weight of the data to be detected according to the weights of the data to be detected in different dimensions; sort the data to be detected according to the average weight of the data to be detected; and determine the sampling priority of the data to be detected according to the sorting result of the data to be detected.

[0162] In an optional implementation, the acquisition module 501 is further used to obtain default values ​​of weight indicators of the data to be detected in different dimensions;

[0163] The processing module 502 is further used to determine the weights of the data to be detected in different dimensions according to the offset value of the data to be detected relative to the default value.

[0164] In an optional implementation, the processing module 502 is specifically used to determine a target sampling number of data to be detected; and determine the target sampling number of data to be detected from the data to be detected as sample data according to the sampling priority from high to low.

[0165] In an optional implementation manner, the processing module 502 is further configured to filter the data to be detected according to allocation rules of multiple dimensions, and remove useless data from the data to be detected.

[0166] In an optional implementation, the processing module 502 is specifically used to obtain multiple allocation rules configured in the quality inspection plan; use the multiple allocation rules to filter the data to be detected respectively, and remove useless data in the data to be detected.

[0167] In an optional implementation, the allocation rules include business allocation rules and system allocation rules.

[0168] In an optional implementation, the business allocation rules include data source rules, business line rules, business classification rules and duration rules, and the system allocation rules include object rules, invalid data removal rules and key item error count rules.

[0169] In an optional implementation, the device further includes:

[0170] The receiving module 504 is used to receive the quality inspection result of the sample data sent by the terminal device.

[0171] In an optional implementation, the quality inspection result of the sample data is determined based on whether the sample data passes the key items.

[0172] In an optional implementation, the processing module 502 is further used to determine the object corresponding to the sample data that does not pass the key item; accumulate the number of key item errors of the object within the target period; and update the key item error number rule based on the number of key item errors accumulated for the object within the target period.

[0173] Need to explain, Figure 5 The data sampling detection device provided in the exemplary embodiment can be used to execute the method provided in any of the above embodiments. The specific implementation method and technical effect are similar and will not be described in detail here.

[0174] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device may include: at least one processor 601 and a memory 602. Figure 6 An electronic device is an example of a processor.

[0175] The memory 602 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0176] The memory 602 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0177] The processor 601 is used to execute the computer execution instructions stored in the memory 602 to implement the above data sampling detection method;

[0178] The processor 601 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0179] Optionally, in a specific implementation, if the communication interface, the memory 602 and the processor 601 are implemented independently, the communication interface, the memory 602 and the processor 601 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0180] Optionally, in a specific implementation, if the communication interface, the memory 602 and the processor 601 are integrated on a chip, the communication interface, the memory 602 and the processor 601 can communicate through an internal interface.

[0181] The present application embodiment also provides a chip, including a processor and an interface. The interface is used to input and output data or instructions processed by the processor. The processor is used to execute the method provided in the above method embodiment. The chip can be applied to a data sampling detection device.

[0182] The present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program information, and the program information is used for the above-mentioned data sampling detection method.

[0183] The embodiment of the present application also provides a program, which, when executed by a processor, is used to execute the data sampling detection method provided by the above method embodiment.

[0184] The embodiment of the present application also provides a program product, such as a computer-readable storage medium, in which instructions are stored. When the program product is run on a computer, the computer executes the data sampling detection method provided by the above method embodiment.

[0185] In the above embodiments, it 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 instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data sampling detection method, characterized in that: The method comprises: Obtain the data to be tested; Determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions, wherein the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs; Determining sample data from the data to be detected according to the sampling priority of the data to be detected; Sending the sample data to a terminal device; The step of determining the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions includes: Determining the average weight of the data to be detected according to the weights of the data to be detected in the different dimensions; Sorting the data to be detected according to the average weight of the data to be detected; Determining a sampling priority of the data to be detected according to a sorting result of the data to be detected; Before determining the average weight of the data to be detected, the method further includes: Obtain default values ​​of weight indicators of the data to be detected in the different dimensions; determine whether there is an offset value for the data to be detected relative to the default value; if there is an offset value, the weight of the data to be detected in the different dimensions is 0; if there is no offset value, the weight of the data to be detected in the different dimensions is the default value.

2. The method according to claim 1, characterized in that The step of determining sample data from the data to be detected according to the sampling priority of the data to be detected includes: Determining a target sampling quantity of the data to be detected; According to the sampling priorities from high to low, the target sampling quantity of data to be detected is determined from the data to be detected as the sample data.

3. The method according to claim 1, characterized in that Before determining the sampling priority of the data to be detected, the method further includes: According to the allocation rules of multiple dimensions, the data to be detected is filtered to remove useless data in the data to be detected.

4. The method according to claim 3, characterized in that The filtering of the data to be detected to remove useless data in the data to be detected includes: Get multiple allocation rules configured in the quality inspection plan; The data to be detected are filtered respectively using the multiple allocation rules to remove useless data in the data to be detected.

5. The method according to claim 3, characterized in that: The allocation rules include business allocation rules and system allocation rules.

6. The method according to claim 5, characterized in that The business allocation rules include data source rules, business line rules, business classification rules and duration rules, and the system allocation rules include object rules, invalid data removal rules and key item error count rules.

7. The method according to claim 5, characterized in that After sending the sample data to the terminal device for quality inspection, the method further includes: Receive the quality inspection result of the sample data sent by the terminal device.

8. The method according to claim 7, characterized in that The quality inspection result of the sample data is determined based on whether the sample data passes the key items.

9. The method according to claim 8, characterized in that After receiving the quality inspection result of the sample data sent by the terminal device, the method further includes: Determine the object corresponding to the sample data that does not pass the key item; Accumulate the number of critical item errors of the subject during the target period; The key item error count rule is updated according to the key item error count accumulated in the target period.

10. A data sampling detection device, characterized in that: The device comprises: An acquisition module, used for acquiring data to be detected; A processing module, used to determine the sampling priority of the data to be detected according to the weights of the data to be detected in different dimensions; determine sample data from the data to be detected according to the sampling priority of the data to be detected, and the different dimensions of the data to be detected correspond to different business evaluation characteristics of the customer service system to which the data to be detected belongs; A sending module, used for sending the sample data to a terminal device; A processing module, specifically used to determine the average weight of the data to be detected according to the weights of the data to be detected in the different dimensions; Sorting the data to be detected according to the average weight of the data to be detected; Determining a sampling priority of the data to be detected according to a sorting result of the data to be detected; The acquisition module is further used to obtain the default values ​​of the weight indicators of the data to be detected in the different dimensions; The processing module is also used to determine whether there is an offset value for the data to be detected relative to the default value. If there is an offset value, the weight of the data to be detected in the different dimensions is 0; if there is no offset value, the weight of the data to be detected in the different dimensions is the default value.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 9.

13. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method as claimed in any one of claims 1 to 9.

Images