Data processing method and apparatus, storage medium, and electronic device

Abstract

The application relates to the technical field of data processing, in particular to a data processing method and device, a storage medium and an electronic device, which are beneficial to improving the accuracy of a quality inspection system. The data processing method comprises the following steps: first address data in a work order is acquired; second address data in communication data of a target user and a service representative is recognized; at least one first local address data is intercepted from the first address data, wherein the character length of the at least one first local address data is the same as that of the second address data; Chinese characters in the at least one first local address data and Chinese characters in the second address data are both converted into pinyin to obtain at least one first local address pinyin and second address pinyin; and finally, a first detection result is determined based on the at least one first local address pinyin and the second address pinyin, and whether the first address data filled in the work order is accurate is determined according to the first detection result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a data processing method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the rapid development of social economy, more and more attention is paid to customer service in various fields, and therefore the service of a seat emerges as the times require. The service of a seat is a way for a call center system to provide services for customers. In the call center system, the seat communicates with the customer through listening to the phone, text conversation and the like to understand the needs of the customer. For example, in the insurance field, if the vehicle of the customer has an accident and needs to be reported, the customer can contact the seat through the phone and tell the seat the location of the accident. After the seat communicates with the customer, the seat records the location of the accident in the work order. In order to ensure the service quality of the seat, the quality inspection system detects whether the location of the accident recorded in the work order by the seat is accurate.

[0003] At present, whether the location of the accident recorded in the work order by the seat is accurate is generally determined by comparing whether the location of the accident recorded in the work order by the seat and the location in the communication audio are completely consistent. Since the location described by the customer in the communication audio and the location of the accident recorded by the seat may not be completely consistent, the quality inspection system may misjudge that the address recorded by the seat is incorrect. Therefore, it is a hot issue to be solved to improve the detection accuracy of the quality inspection system. SUMMARY

[0004] In view of this, the embodiments of the present application provide a data processing method and device, a storage medium and an electronic device, which are beneficial to improve the detection accuracy of the quality inspection system.

[0005] In a first aspect, a data processing method provided by an embodiment of the present application comprises: obtaining first address data in a work order, wherein the first address data is address data recorded in the work order by a seat after communicating with a target user; identifying second address data in communication data of the seat and the target user, the communication data comprising at least one of the following data: audio data, video data and text data; extracting at least one first local address data from the first address data, the character length of the at least one first local address data being the same as the character length of the second address data; converting Chinese characters in the at least one first local address data and Chinese characters in the second address data into pinyin to obtain at least one first local address pinyin corresponding to the at least one first local address data and second address pinyin corresponding to the second address data; determining a first detection result based on the at least one first local address pinyin and the second address pinyin, and determining whether the first address data recorded in the work order is accurate according to the first detection result.

[0006] In a second aspect, an embodiment of the present application provides a data processing apparatus, comprising: an obtaining module configured to obtain first address data in a work order, wherein the first address data is address data filled in the work order after a service representative communicates with a target user; an identifying module configured to identify second address data in communication data of the service representative and the target user, the communication data comprising at least one of the following data: audio data, video data and text data; an intercepting module configured to intercept at least one first partial address data from the first address data, the character length of the at least one first partial address data being the same as the character length of the second address data; a converting module configured to convert Chinese characters in the at least one first partial address data and Chinese characters in the second address data into pinyin, to obtain at least one first partial address pinyin corresponding to the at least one first partial address data and second address pinyin corresponding to the second address data; and a detecting module configured to determine a first detection result based on the at least one first partial address pinyin and the second address pinyin, and determine whether the first address data filled in the work order is accurate according to the first detection result.

[0007] In a third aspect, an embodiment of the present application provides a computer readable storage medium, the storage medium storing instructions, when the instructions are executed by a processor of an electronic device, the electronic device is enabled to execute the data processing method mentioned in the first aspect.

[0008] In a fourth aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor; a memory for storing computer executable instructions; and the processor is configured to execute the computer executable instructions to implement the data processing method mentioned in the first aspect.

[0009] The data processing method provided in this application first obtains the first address data in the work order, then identifies the second address data in the communication data between the agent and the target user, extracts at least one first partial address data from the first address data, and the character length of the extracted at least one first partial address data is the same as the character length of the second address data. Then, the Chinese characters in the at least one first partial address data and the Chinese characters in the second address data are converted into Pinyin, resulting in at least one first partial address Pinyin corresponding to at least one first partial address data and a second address Pinyin corresponding to the second address data. Finally, based on the at least one first partial address Pinyin and the second address Pinyin, a first detection result is determined, and the accuracy of the first address data filled in the work order is determined according to the first detection result. Because directly comparing the first address data and the second address data with different character lengths will not result in a complete match even if the first address data and the second address data actually mean the same thing, i.e., the comparison will fail, and the quality inspection system will determine that the agent filled in the information incorrectly, leading to a misjudgment. In addition, many address names have homophones or similar pronunciations, which can also cause the quality inspection system to make misjudgments. Therefore, the data processing method provided in this application first truncates the first address data to obtain the first partial address data, making the character length of the first partial address data the same as that of the second address data, and converting the Chinese characters in the first partial address data and the Chinese characters in the second address data into pinyin. Then, by comparing the pinyin of the first partial address data with the pinyin of the second address data with the same character length, the first detection result can be obtained. In this way, if the first address data and the second address data actually mean the same thing, it can effectively avoid the failure of comparison due to problems such as different character lengths, homophones, etc., and greatly improve the probability of the comparison results being completely consistent, that is, improve the probability of successful comparison, thereby reducing the misjudgment of the quality inspection system and improving the accuracy of the quality inspection system. Attached Figure Description

[0010] FIG. 1 The diagram shown is an application scenario illustration of a data processing method provided in an embodiment of this application.

[0011] FIG. 2 The diagram shown is a flowchart of a data processing method provided in an embodiment of this application.

[0012] FIG. 3 The diagram shown is a structural schematic of a data processing device provided in an embodiment of this application.

[0013] FIG. 4 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation

[0014] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0015] In some application scenarios, for example, an insurance application scenario, if an accident occurs to the vehicle of a customer, the customer can contact an agent through a telephone and tell the agent the accident location. After the agent communicates with the customer, the agent records the accident location in a work order. In order to ensure the service quality of the agent, a quality inspection system detects whether the accident location recorded in the work order by the agent is accurate. Currently, whether the accident location recorded in the work order by the agent is accurate is generally determined by comparing whether the accident location recorded in the work order by the agent is completely consistent with the location described by the customer in the communication audio. However, the location described by the customer in the communication audio and the accident location recorded in the work order by the agent can not be completely consistent, which leads to the quality inspection system misjudging that the accident location recorded in the work order by the agent is incorrect, and further leads to a low detection accuracy of the quality inspection system.

[0016] For example, the location described by the customer in the communication audio can be “Guangxi”, and the agent needs to record the full name of the accident address “Guangxi Zhuang Autonomous Region” according to the filling requirements of the work order. The comparison result of the quality inspection system for “Guangxi” and “Guangxi Zhuang Autonomous Region” is definitely not completely consistent, which leads to the quality inspection system misjudging that the accident location recorded in the work order by the agent is incorrect.

[0017] The data processing method of the present application first intercepts the first address data to obtain the first local address data, so that the first local address data and the second address data have the same character length, and the Chinese characters in the first local address data and the Chinese characters in the second address data are both converted into pinyin. Then, the first detection result can be obtained by comparing the first local address pinyin and the second address pinyin with the same character length. In this way, if the first address data and the second address data actually mean the same thing, the comparison can be successfully avoided due to the problems of different character lengths, homophones, and homonyms, which greatly improves the probability of the comparison result being completely consistent, that is, the probability of successful comparison, thereby reducing the misjudgment of the quality inspection system and improving the detection accuracy of the quality inspection system.

[0018] Exemplarily, the customer describes a place in the communication audio as "Guangxi", and the agent needs to fill in the full name of the address "Guangxi Zhuang Autonomous Region" according to the filling requirements of the work order. The detection method of the present application will first intercept data with the same character length as the second address data (i.e., "Guangxi") in the first address data (i.e., "Guangxi Zhuang Autonomous Region") to obtain the first partial address data (i.e., "Guangxi"), and convert the Chinese characters in the first partial address data (i.e., "Guangxi") and the Chinese characters in the second address data (i.e., "Guangxi") into pinyin to obtain the first partial address pinyin (i.e., "guangxi") and the second address pinyin (i.e., "guangxi"). Then, based on the first partial address pinyin (i.e., "guangxi") and the second address pinyin (i.e., "guangxi"), the first detection result is obtained, that is, whether the first address data filled in the work order is accurate can be judged by comparing whether the first partial address pinyin (i.e., "guangxi") and the second address pinyin (i.e., "guangxi") are completely consistent. As can be seen, the first partial address pinyin (i.e., "guangxi") and the second address pinyin (i.e., "guangxi") are completely consistent, so the quality inspection system can determine that the first address data filled in the work order is accurate. In fact, "Guangxi" and "Guangxi Zhuang Autonomous Region" also represent an address, so the detection result of the quality inspection system is accurate. That is, the data processing method of the present application has higher accuracy than the method of directly comparing the first address data and the second address data for quality inspection.

[0019] The data processing method of the present application can also be used in other scenarios that need to detect address data, such as medical rescue scenarios, fire alarm scenarios, public security alarm scenarios, etc., which are not limited here.

[0020] Exemplary scenarios

[0021] FIG. 1 Fig. 1 shows an application scenario of the data processing method provided by an embodiment of the present application. FIG. 1 The scenario shown includes a call center server 110, a quality inspection system server 120 and a plurality of agent terminals 130 in communication connection with the call center server 110, and a plurality of client terminals 140 in communication connection with the plurality of agent terminals 130. Specifically, the client terminal 140 communicates with the agent terminal 130 to generate a work order and communication data, the agent terminal 130 sends the work order and the communication data to the call center server 110, and the call center server 110 sends the work order and the communication data of the agent terminal 130 to the quality inspection system server 120. The quality inspection system server 120 determines whether the first address data filled in the work order is accurate by using the data processing method of the present application.

[0022] In an embodiment of the present application, the agent terminal 130 can be a computer used by an agent, the agent terminal 130 can generate the communication data through the recording or video recording function of the computer, fill in the work order, and then send to the call center server 110. The client terminal 140 can be a mobile phone, smart watch or other device used by the target user.

[0023] In an embodiment of the present application, the agent terminal 130 can include a telephone and a computer used by an agent, the communication data between the agent terminal 130 and the client terminal 140 can be generated through the recording or video recording function of the telephone, and then sent to the call center server 110. The agent terminal 130 can fill in the work order through the work order filling interface in the computer, and then send to the call center server 110.

[0024] For example, in the insurance accident scenario, after the target user's motor vehicle sends an accident, the target user can contact the agent of the agent terminal 130 through the client terminal 140 to inform the agent of the accident address, and then the agent records the accident address in the work order to form the first address data in the work order. The recording, video recording or text data of the communication between the agent and the target user form the communication data. In the medical rescue scenario, after the target user finds that someone needs emergency rescue, the target user can contact the agent of the agent terminal 130 through the client terminal 140 to inform the agent of the specific address of the person needing rescue, and then the agent records the specific address of the person needing rescue in the work order to form the first address data in the work order. The recording, video recording or text data of the communication between the agent and the target user form the communication data.

[0025] Exemplary methods

[0026] FIG. 2 Fig. 1 shows a flowchart of a data processing method provided by an embodiment of the present application. As shown in the figure, FIG. 2 The data processing method includes the following steps.

[0027] Step 210, obtaining first address data in a work order.

[0028] Specifically, the first address data is address data filled in the work order after the agent communicates with the target user. The work order generally has specific filling requirements, for example, the full name of the address must be filled in to prevent misunderstanding by the personnel performing the work order. The filling format of the first address data in the work order can be: administrative division address-detailed address. For example, Shaanxi Province-Xi'an-Baqiao District-Panlong Hospital Intersection. For another example, Chongqing-Chongqing-Jiangbei District-Jianxin South Road. Among them, "Chongqing-Chongqing-Jiangbei District" is the administrative division address, and "Jianxin South Road" is the detailed address. The administrative division address and the detailed address are connected by "-" or separated by spaces. The administrative division address can also be a multi-level administrative division, and the multi-level administrative divisions can also be connected by "-" or separated by spaces.

[0029] In step 220, second address data in the communication data of the target user is identified.

[0030] Specifically, the communication data includes at least one of audio data, video data and text data. The second address data can be address data obtained by processing the communication data through automatic speech recognition (ASR) and natural language processing (NLP). For example, the second address data can be Chongqing. The second address data can also be Jiangbei.

[0031] In step 230, at least one first partial address data is extracted from the first address data.

[0032] Specifically, the character length of the at least one first partial address data is the same as the character length of the second address data. The character length of the second address data can be identified through optical character recognition (OCR) technology, and then the at least one first partial address data can be extracted from the first address data. For example, the second address data can be Chongqing, and the identified character length can be 4 (each Chinese character occupies 2 characters).

[0033] Specifically, the at least one first partial address data can be extracted from the beginning character position of the first address data, or can be extracted from a preset character position after the middle. The preset character position can be determined according to the filling format of the first address data. For example, the filling format of the first address data is multi-level administrative division, and the multi-level administrative division is connected by “-”, then the extraction can start from “-” after, that is, the preset character position is the character position where “-” is located.

[0034] Exemplarily, the character length of the second address data can be marked by using a key-value pair of {‘place name’: ‘place name length’}. For example, {‘Qingdao City’: 3, ‘Huadu District’: 3}.

[0035] Exemplarily, for the first address data: Chongqing City-Chongqing City-Jiangbei District-Jianxin South Road, the first four characters can be obtained as “Chongqing” from the beginning character position of the first address data. The first four characters can be obtained as “Chongqing”, “Jiangbei”, “Jianxin” from the preset character position “-” after.

[0036] In some embodiments, the extracting the at least one first partial address data from the first address data can be performed by: dividing the first address data according to a preset rule to obtain at least one first divided address data, wherein a character length of the at least one first divided address data is greater than or equal to a character length of the second address data; and extracting, from the at least one first divided address data, a partial address having the same character length as the second address to obtain the at least one first partial address data corresponding to the at least one first divided address data.

[0037] Specifically, the preset rule can be a division rule set in advance according to actual needs. For example, the preset rule can be to divide the first address data by using a separator in the first address data to obtain the at least one first divided address data. The separator includes at least one of the following symbols: semicolon, colon, comma, space. Since the first address data is filled according to a preset format, the type of the separator is confirmed when the first address data is filled. When the first address data is detected subsequently, the specific type of the separator can be determined according to the preset format, so that the first address data can be divided by using the separator in the first address data, thereby improving the accuracy of the first divided address data obtained by division.

[0038] For another example, the preset rule can be to divide the first address data according to a keyword. The keyword can be province, city, district, and county. For another example, the preset rule can be to divide the first address data by using a trained semantic division model. For another example, the preset rule can be to divide the first address data according to a set character length. The set character length can be determined according to actual needs, for example, can be 4 characters, 6 characters, etc.

[0039] Specifically, the dividing the first address data according to the preset rule can be performed by dividing the first address data into several parts, each part being a first divided address data. For example, the first address data is: Chongqing City-Chongqing City-Jiangbei District-Jianxin South Road. The first address data can be divided into four parts: Chongqing City, Chongqing City, Jiangbei District, and Jianxin South Road, thereby obtaining four first divided address data. The four first divided address data are: Chongqing City, Chongqing City, Jiangbei District, and Jianxin South Road, respectively.

[0040] Specifically, the extracting, from the at least one first divided address data, the data having the same character length as the second address data to obtain the at least one first partial address data corresponding to the at least one first divided address data can be performed by: traversing the at least one first divided address data, and extracting, for each first divided address data, the data having the same character length as the second address data to obtain the first partial address data. That is, each first divided address data corresponds to a first partial address data.

[0041] It can be seen that, in this example, since the first address data can contain multiple levels of administrative divisions, by dividing the first address data, multiple first divided address data can be obtained, each of which can correspond to an administrative division at a level, so that the multiple first divided address data can be compared with the second address data respectively, thereby improving the success probability of comparison, and further improving the accuracy of detection of the quality inspection system.

[0042] In some embodiments, the first address data is divided according to the preset rule to obtain at least one first divided address data, which can be performed as follows: the first address data is split into first standard address data and first detailed address data, wherein the first standard address data is used to represent address data determined based on administrative division addresses, and the first detailed address data is used to represent address data in the first address data other than the first standard address data; the first standard address data is divided according to the preset rule to obtain at least one first divided address data.

[0043] Specifically, the filling format of the first address data can be: administrative division address-detailed address. Therefore, the first address data (i.e., administrative division address-detailed address) can be split into first standard address data (i.e., administrative division address) and first detailed address data (i.e., detailed address) according to the delimiter “-”.

[0044] Exemplarily, the first address data is: Shandong Province-Qingdao City-Huangdao District-Huanghe Road and Caitou Road intersection, which is split into first standard address data: [‘Shandong Province’, ‘Qingdao City’, ‘Huangdao District’] and first detailed address data: [‘Huanghe Road and Caitou Road intersection’].

[0045] By splitting the first address data into first standard address data and first detailed address data, subsequent detection of the first standard address data and the first detailed address data can be facilitated, so that targeted detection can be performed during subsequent manual sampling inspection.

[0046] As can be seen, in this example, the first standard address data and the first detailed address data can correspond to a detection result respectively. During subsequent manual sampling inspection, data with a first standard address data miss (i.e., not completely consistent) and a first detailed address data miss can be preferentially selected for detection, thereby improving the detection accuracy of the quality inspection system and avoiding the waste of time of quality inspection personnel on the sampling inspection of some false quality inspection results, thereby playing a role in reducing costs and increasing efficiency.

[0047] In step 240, the Chinese characters in the at least one first local address data and the Chinese characters in the second address data are converted into pinyin, to obtain at least one first local address pinyin corresponding to the at least one first local address data and second address pinyin corresponding to the second address data.

[0048] Exemplarily, the first local address data is "Nanping Town", the Chinese characters in the first local address data are converted into pinyin to obtain the first local address pinyin "nanpingzhen". The second address data is "Nanping Town", and the Chinese characters in the second address data are converted into pinyin to obtain the second address pinyin "nanpingzhen".

[0049] In step 250, based on at least one first local address pinyin and second address pinyin, a first detection result is determined, and whether the first address data filled in the work order is accurate is determined according to the first detection result.

[0050] Exemplarily, the first local address data is "Nanping Town", and the second address data is "Nanping Town", if "Nanping Town" and "Nanping Town" are directly compared, the comparison result is definitely not completely consistent. However, if the first local address pinyin (i.e., nanpingzhen) is compared with the second address pinyin (i.e., nanpingzhen), it can be seen that the comparison result is completely consistent.

[0051] In actual application, there are homophonic, homophonic and other problems in place names. For example, "Nanping Town" and "Nanping Town" are completely homophonic, or "Huangdao District" is converted into "Huadu District" due to pronunciation problems. That is, in the process of converting speech into Chinese text by using ASR, the above conversion error often occurs. By converting Chinese characters into pinyin, the above conversion error is reduced, thereby improving the accuracy of subsequent address data detection.

[0052] In some embodiments, according to the first detection result, whether the first address data filled in the work order is accurate can be executed as: based on the first detailed address data and the second address data, a second detection result is determined, wherein the second detection result is used to represent whether the first detailed address data and the second address data match; based on the first detection result and the second detection result, whether the first address data filled in the work order is accurate is determined.

[0053] It can be seen that in the present example, by respectively determining the first detection result and the second detection result, the first address data has two-dimensional marking, and then the accuracy of the first address data filled by the agent can be determined from two dimensions, which more clearly reflects the different accuracy levels of the first address data, and facilitates the subsequent quality inspection personnel to preferentially carry out sampling inspection on the data which fails to match successfully in the first detection result and the second detection result, thereby improving the accuracy of sampling inspection.

[0054] In some embodiments, based on the first detailed address data and the second address data, determining the second detection result comprises: taking the first character in the first detailed address data as a starting point, intercepting N characters in the first detailed address data which have the same length as the second address data, wherein N is a positive integer; comparing the N characters with the second address data; if the N characters are completely consistent with all characters in the second address data, determining that the second detection result is that the first detailed address data and the second address data match.

[0055] Specifically, the specific value of N can be set according to actual conditions.

[0056] For example, the first detailed address data is: intersection of Huanghe Middle Road and Caitou Road, and N is set to 6, then the N characters intercepted in the first detailed address data are: Huanghe Middle.

[0057] It can be seen that, in this example, since the target user may not be able to accurately describe the specific address when describing the detailed address, by comparing the part of characters in the first detailed address data with the communication data, the probability of successful comparison can be improved, that is, the embodiment realizes fuzzy comparison of the first detailed address data, and solves the problem of insufficient generalization ability of the detailed address. In actual application, if the part of characters is successfully compared, the first detailed address data and the communication data will be successfully compared with high probability, therefore, the embodiment can further improve the accuracy of address data detection.

[0058] In some embodiments, the first detection result is used to represent whether the first local address pinyin and the second address pinyin match. Based on the first detection result and the second detection result, determining whether the first address data filled in the work order is accurate can be performed as follows: if the first detection result represents that the first local address pinyin and the second address pinyin match, it is determined that the first address data filled in the work order is accurate; or, if the first detection result represents that the first local address pinyin and the second address pinyin do not match, and the second detection result represents that the first detailed address data and the second address data match, it is determined that the first address data filled in the work order is accurate.

[0059] It can be seen that in this example, if the first detection result represents that the first local address pinyin and the second address pinyin match, it can be directly determined that the first address data filled in the work order is accurate, and it is not necessary to compare the first detailed address data and the second address data again, thereby reducing the steps of data processing and improving the data processing efficiency. If the first detection result represents that the first local address pinyin and the second address pinyin do not match, since the first local address is the address with the same character length as the second address which is obtained from the first segmented address, and the second segmented address is obtained according to the first standard address, the second address in the communication data may exist the case that it describes a detailed address instead of an administrative division address, and therefore it is still necessary to further determine whether the first detailed address matches the second address, so as to avoid errors and realize accurate identification of the first address data.

[0060] In some embodiments, based on the at least one first local address pinyin and the second address pinyin, determining the first detection result can be performed as follows: using the Levenshtein algorithm, respectively calculating the Levenshtein ratio of the at least one first local address pinyin and the second address pinyin to obtain the respective Levenshtein ratio of the at least one first local address pinyin; determining the maximum Levenshtein ratio in the respective Levenshtein ratio of the at least one first local address pinyin; and if the maximum Levenshtein ratio is greater than or equal to a preset threshold, determining that the first detection result is that the first local address pinyin and the second address pinyin match.

[0061] Specifically, the calculation formula of the Levenshtein ratio can be r=(sum-ldist) / sum, where sum refers to the total length of the string of the first local address pinyin and the second address pinyin, and ldist refers to the class edit distance, i.e. the minimum number of editing operations required to convert the first local address pinyin into the second address pinyin. The Levenshtein algorithm is an algorithm for calculating the Levenshtein ratio.

[0062] By way of example, the first address data can be: Chongqing-Nanchuan-Nanping. The plurality of first local address data are respectively: Chongqing, Nanchuan, and Nanping. The plurality of first local address pinyin are respectively: chongqing, nanchuan, and nanping. The second address pinyin can be: nanchuan. The Levenshtein ratio is calculated respectively for each first local address pinyin and the second address pinyin to obtain the respective Levenshtein ratio of each first local address pinyin. For example, the Levenshtein ratio of the first local address pinyin: chongqing and the second address pinyin: nanchuan is 0, the Levenshtein ratio of the first local address pinyin: nanchuan and the second address pinyin: nanchuan is 1, and the Levenshtein ratio of the first local address pinyin: nanping and the second address pinyin: nanchuan is 0.53.

[0063] For example, the conversion of "huaduqu" to "huangdaoqu" requires the insertion of "ng" after "hua" and the replacement of "u" with "a" plus "o", and the edit distance is 5, and the total length of characters is 17 (huaduqu) + 10 (huangdaoqu) = 17. The Levenshtein ratio is (17-5) / 17 = 0.71 (rounded to two decimal places).

[0064] The preset threshold value can be set according to actual conditions. Based on the Levenshtein ratios corresponding to the at least one first local address pinyin and the preset threshold value, the accuracy of the first address data filled by the agent can be detected by determining whether the average of the Levenshtein ratios corresponding to the at least one first local address pinyin is greater than or equal to the preset threshold value. If the average of the Levenshtein ratios corresponding to the at least one first local address pinyin is greater than or equal to the preset threshold value, it is determined that the first address data filled by the agent is accurate.

[0065] For example, { 'Shandong Province': 1, 'Qingdao City': 1, 'Huangdao District': 0.71}, the average Levenshtein ratio of the first address data is (1 + 1 + 0.71) / 3 = 0.9, and therefore, the average Levenshtein ratio of the first address data is greater than or equal to the set threshold value 0.9, that is, it is determined that the first address data filled by the agent is accurate.

[0066] As can be seen, in this example, the accuracy of the first address data filled by the agent is determined by calculating the Levenshtein ratio, which has a small amount of calculation and high calculation efficiency.

[0067] In some embodiments, the step of detecting the accuracy of the first address data filled by the agent based on the Levenshtein ratios corresponding to the at least one first local address pinyin and the preset threshold value can include determining the maximum Levenshtein ratio among the Levenshtein ratios corresponding to the at least one first local address pinyin, and if the maximum Levenshtein ratio is greater than or equal to the preset threshold value, determining that the first address data filled by the agent is accurate.

[0068] For example, the preset threshold value can be set to 0.9. For example, the three Levenshtein ratios calculated above are 0, 1, and 0.53, and the maximum Levenshtein ratio is 1, which is greater than the preset threshold value 0.9, and therefore, the first address data filled by the agent is accurate.

[0069] As can be seen, in this example, since the maximum Levenshtein ratio best represents whether the second address pinyin matches the first local address pinyin in actual application, the maximum Levenshtein ratio is compared with the preset threshold value, which further improves the accuracy of address data detection.

[0070] In some embodiments, the first detection result can be a hit and a miss. The second detection result can be a hit and a miss. The hit represents that the detection result of the first detailed address data is accurate, and the miss represents that the detection result of the first detailed address data is inaccurate.

[0071] Exemplarily, if the first detection result and the second detection result are both hits, it can be considered that the first address data filled by the agent is completely accurate. If the first detection result and the second detection result are both misses, it can be considered that the first address data filled by the agent is completely inaccurate. If the first detection result is a hit and the second detection result is a miss, or the first detection result is a miss and the second detection result is a hit, an accuracy percentage can be determined for the first address data filled by the agent.

[0072] In some embodiments, the communication data includes a plurality of sentences arranged in a communication time sequence. Identifying the second address data in the communication data of the agent and the target user can be performed as follows: determining a first address-related sentence in the plurality of sentences based on a preset keyword and a preset regular expression; determining at least one sentence from the first address-related sentence as a starting sentence and a preset number of sentences as a detection length; and extracting the second address data from the at least one sentence.

[0073] Specifically, the communication data includes a plurality of sentences arranged in a communication time sequence. Specifically, the preset keyword can be “address”. The preset regular expression can be “address please say”. The preset keyword and the preset regular expression can be set according to actual scenarios. The preset number of sentences can be set according to actual scenarios, for example, 3 sentences, 5 sentences, etc.

[0074] Specifically, the second address data can be extracted by using NLP.

[0075] Exemplarily, the extraction of the second address data can be through a network model recognition. The network model can be obtained by NLP annotation on a large amount of corpus and then training a pre-trained model.

[0076] Specifically, (1) a pre-training model and a label are created. (2) Geographical names in a national standard administrative division (including a township, a town and an administrative division above) are obtained and input into the pre-training model, such as Henan Province, Beijing, Jingdezhen City, Qingyang District, Zhangdazhuang Town, Liuyingwu Township and the like, and are all marked as a 'geographical name' label, and the pre-training model is trained. (3) Training corpus is obtained and manually annotated, such as 'I went to Beijing in the morning and returned to Shanghai in the afternoon', and 'Beijing' and 'Shanghai' are manually annotated as 'geographical name' labels and input into the pre-training model for training. (4) The pre-set model is trained according to the above steps, and when the pre-set model can output a geographical name label from the training model, the pre-set model is set as an entity recognition model. Then, the model is used to obtain geographical names in the Nth ASR translation text, such as: the customer said: Qingdao City Huandu District Huanghe Road and that starting road intersection. Then the NLP entity extraction can identify 'Qingdao City' and 'Huandu District' as geographical names (i.e., marked as second address data).

[0077] It can be seen that, in the present example, based on the pre-set keyword and the pre-set regular expression, the first address-related sentence appearing in multiple sentences is determined, then the first address-related sentence appearing for the first time is taken as a starting sentence, a pre-set number of sentences is taken as a detection length, at least one sentence is determined, and finally the second address data is extracted from the at least one sentence, thereby narrowing the range of extracting the second address data and improving the extraction efficiency of the second address data.

[0078] In some embodiments, taking the first address-related sentence appearing for the first time as a starting sentence and taking a pre-set number of sentences as a detection length to determine at least one sentence includes: taking the first address-related sentence appearing for the first time as a starting sentence and taking a pre-set number of sentences as a detection length to determine at least one pre-selected sentence; for each pre-selected sentence in the at least one pre-selected sentence, if the data source of the next sentence of the pre-selected sentence is a target user and the next sentence contains negative semantics, the pre-selected sentence and the next sentence of the pre-selected sentence are removed; and based on the at least one pre-selected sentence after the removal operation, at least one sentence is determined.

[0079] Specifically, the at least one pre-selected sentence is a sentence intercepted by taking the first address-related sentence appearing for the first time as a starting sentence and taking a pre-set number of sentences as a detection length.

[0080] For example, the communication data of the agent and the target user can include the following data, and each pre-selected sentence in the following data has a corresponding start time (i.e., beginTime), channel (i.e., channelId), end time (i.e., endTime), role (i.e., role) and sentence text (i.e., text).

[0081] [{"beginTime":860,

[0082] "channelId":1,

[0083] "endTime":4140,

[0084] "role":"0",

[0085] Hello, this is the customer service department of XXX company. How can I help you?

[0086] {"beginTime":4760,

[0087] "channelId":0,

[0088] "endTime":9240,

[0089] "role":"1",

[0090] Hello, I've been in a traffic accident and need to file an insurance claim.

[0091] {"beginTime":10880,

[0092] "channelId":1,

[0093] "endTime":14320,

[0094] "role":"0",

[0095] Okay, could you please specify the address of the traffic accident in which district or county of Chongqing?

[0096] {"beginTime":15830,

[0097] "channelId":0,

[0098] "endTime":19640,

[0099] "role":"1",

[0100] "text":"Nanchuan is located in Nanping Town"},

[0101] {"beginTime":20120,

[0102] "channelId":0,

[0103] "endTime":23590,

[0104] "role":"0",

[0105] "text":"South Ping Town under Nanchuan, is on which road?"},

[0106] {"beginTime":25780,

[0107] "channelId":0,

[0108] "endTime":26640,

[0109] "role":"1",

[0110] "text":"is not South Ping Town"},

[0111] {......}

[0112] It can be seen from the above communication data that, for the current pre-selected sentence "South Ping Town under Nanchuan, is on which road?", the next sentence (i.e., "is not South Ping Town") of the current pre-selected sentence is from the target user, and the next sentence contains the negative semantics "not", so the current pre-selected sentence can be removed, i.e., deleted.

[0113] Exemplarily, whether the next sentence contains the negative semantics can be determined by a negative semantics recognition model based on the BERT algorithm.

[0114] It can be seen that in this example, since in actual application, for each current pre-selected sentence in the at least one pre-selected sentence, if the next sentence of the current pre-selected sentence is from the target user and the next sentence contains the negative semantics, the current pre-selected sentence is removed, and then the at least one pre-selected sentence after the removal operation is used to determine the at least one sentence in the text format, the range of extracting the second address data is further narrowed, and the extraction efficiency of the second address data is improved.

[0115] In summary, the data processing method provided in the embodiments of the present application first acquires the first address data in the work order, then identifies the second address data in the communication data between the agent and the target user, extracts at least one first partial address data from the first address data, the character length of the at least one first partial address data is the same as the character length of the second address data, then converts the Chinese characters in the at least one first partial address data and the Chinese characters in the second address data into pinyin, obtains at least one first partial address pinyin corresponding to the at least one first partial address data and second address pinyin corresponding to the second address data, and finally determines the first detection result based on the at least one first partial address pinyin and the second address pinyin, and determines whether the first address data filled in the work order is accurate according to the first detection result. If the first address data and the second address data are directly compared in terms of character length, even if the first address data and the second address data actually mean the same, the comparison result is not completely consistent, that is, the comparison is not successful, and the quality inspection system will determine that the agent fills in incorrectly, resulting in a false judgment. In addition, many address names have homophones and homonyms, which will also cause the quality inspection system to make a false judgment. Therefore, the data processing method provided in the present application first extracts the first address data to obtain the first partial address data, so that the character length of the first partial address data is the same as that of the second address data, and converts the Chinese characters in the first partial address data and the Chinese characters in the second address data into pinyin, and then the first detection result can be obtained by comparing the first partial address pinyin and the second address pinyin with the same character length, so that if the first address data and the second address data actually mean the same, the comparison can be effectively avoided due to the different character lengths, homophones and homonyms, greatly improving the probability that the comparison result is completely consistent, that is, improving the probability of successful comparison, thereby reducing the false judgment of the quality inspection system and improving the accuracy of the quality inspection system.

[0116] The method embodiments of the present application are described in detail above FIG. 2 , and the device embodiments of the present application are described in detail below FIG. 3 . It should be understood that the description of the method embodiments corresponds to the description of the device embodiments, and therefore, the parts not described in detail can be referred to the foregoing method embodiments.

[0117] Exemplary apparatuses

[0118] FIG. 3 Fig. 1 shows a structure schematic diagram of a data processing device provided in an embodiment of the present application. As shown in Fig. 1, the data processing device 100 provided in the embodiment of the present application includes an acquisition module 110, an identification module 120, an extraction module 130, a conversion module 140 and a detection module 150. FIG. 3

[0119] ​In particular, the acquisition module 310 is configured to acquire first address data in the work order, where the first address data is address data filled in the work order by the agent after communicating with the target user. The identification module 320 is configured to identify second address data in the communication data of the agent and the target user, where the communication data includes at least one of audio data, video data, and text data. The interception module 330 is configured to intercept at least one first partial address data from the first address data, where the character length of the at least one first partial address data is the same as that of the second address data. The conversion module 340 is configured to convert Chinese characters in the at least one first partial address data and Chinese characters in the second address data into pinyin to obtain at least one first partial address pinyin corresponding to the at least one first partial address data and second address pinyin corresponding to the second address data. The detection module 350 is configured to determine a first detection result based on the at least one first partial address pinyin and the second address pinyin, and determine whether the first address data filled in the work order is accurate according to the first detection result.

[0120] In some embodiments, the interception module 340 is further configured to segment the first address data according to a preset rule to obtain at least one first segmented address data, where the character length of the at least one first segmented address data is greater than or equal to the character length of the second address data; and intercept, from the at least one first segmented address data, a partial address having the same character length as the second address to obtain at least one first partial address data corresponding to the at least one first segmented address data.

[0121] In some embodiments, the interception module 340 is further configured to split the first address data into first standard address data and first detailed address data, where the first standard address data is used to represent address data determined based on administrative division addresses, and the first detailed address data is used to represent address data in the first address data other than the first standard address data; and segment the first standard address data according to a preset rule to obtain at least one first segmented address data.

[0122] In some embodiments, the interception module 340 is further configured to determine a second detection result based on the first detailed address data and the second address data, where the second detection result is used to represent whether the first detailed address data and the second address data match; and determine whether the first address data filled in the work order is accurate based on the first detection result and the second detection result.

[0123] In some embodiments, the intercepting module 340 is further configured to intercept, starting from the first character in the first detailed address data, N characters in the first detailed address data, where N is a positive integer, and the N characters have the same length as the second address data; compare the N characters with the second address data; and if all characters in the N characters are identical to all characters in the second address data, determine that the second detection result is that the first detailed address data matches the second address data.

[0124] In some embodiments, the first detection result is used to represent whether the first local address pinyin and the second address pinyin match. The intercepting module 340 is further configured to, if the first detection result represents that the first local address pinyin and the second address pinyin match, determine that the first address data filled in the work order is accurate; or, if the first detection result represents that the first local address pinyin and the second address pinyin do not match, and the second detection result represents that the first detailed address data matches the second address data, determine that the first address data filled in the work order is accurate.

[0125] In some embodiments, the detecting module 350 is further configured to calculate, using the Levenshtein algorithm, a Levenshtein ratio of each of the at least one first local address pinyin and the second address pinyin, to obtain a respective Levenshtein ratio of each of the at least one first local address pinyin; determine a maximum Levenshtein ratio in the respective Levenshtein ratios of the at least one first local address pinyin; and if the maximum Levenshtein ratio is greater than or equal to a preset threshold value, determine that the first detection result is that the first local address pinyin and the second address pinyin match.

[0126] In some embodiments, the communication data includes a plurality of sentences arranged in chronological order of communication time. The identifying module 320 is further configured to determine, based on a preset keyword and a preset regular expression, a first address-related sentence that first appears in the plurality of sentences; determine, starting from the first address-related sentence and with a preset number of sentences as a detection length, at least one sentence; and extract the second address data from the at least one sentence.

[0127] In some embodiments, the identifying module 320 is further configured to determine, starting from the first address-related sentence and with a preset number of sentences as a detection length, at least one preselected sentence; for each preselected sentence in the at least one preselected sentence, if data of a next sentence of the preselected sentence is from the target user and the next sentence contains negative semantics, perform a removal operation on the preselected sentence and the next sentence of the preselected sentence; and determine, based on the at least one preselected sentence after the removal operation, the at least one sentence.

[0128] Exemplary electronic devices

[0129] FIG. 4Fig. 1 shows a structural schematic diagram of an electronic device according to an embodiment of the present application. As shown in Fig. 1, the electronic device 100 includes one or more processors 101 and memories 102, and computer program instructions stored in the memories 102, which, when executed by the processors 101, cause the processors 101 to perform the data processing method according to any of the embodiments of the present application. FIG. 4 As shown in Fig. 4, the electronic device 400 includes one or more processors 401 and memories 402, and computer program instructions stored in the memories 402, which, when executed by the processors 401, cause the processors 401 to perform the data processing method according to any of the embodiments of the present application.

[0130] The processor 401 can be a central processing unit (CPU) or other forms of processing units having data processing capability and / or instruction execution capability, and can control other components in the electronic device to perform desired functions.

[0131] The memory 402 can include one or more computer program products, which can include various forms of computer readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM), cache memory, and / or the like. The non-volatile memory may, for example, include read only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer readable storage media, and the processor 401 can execute the program instructions to implement the steps in the data processing method according to the embodiments of the present application and / or other desired functions.

[0132] In one example, the electronic device 400 can further include an input device 403 and an output device 404, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown in the figure). FIG. 4

[0133] In addition, the input device 403 can further include, for example, a keyboard, a mouse, a microphone, and / or the like.

[0134] The output device 404 can output various information to the outside. The output device 404 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and / or the like.

[0135] Of course, in order to simplify the figure, FIG. 4 In the figure, only some of the components in the electronic device 400 related to the present application are shown, and components such as buses, input / output interfaces, and the like are omitted. In addition, according to specific application circumstances, the electronic device 400 can further include any other appropriate components.

[0136] Exemplary computer-readable storage media

[0137] ​In addition to the above method and device, the embodiments of the present application can also be a computer program product, comprising computer program instructions, which, when executed by a processor, cause the processor to perform the steps in the data processing method of any of the above embodiments.

[0138] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server.

[0139] In addition, the embodiments of the present application can also be a computer readable storage medium, which stores computer program instructions, which, when executed by a processor, cause the processor to perform the steps in the data processing method according to various embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0140] The computer readable storage medium can take any combination of one or more of the following readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium, for example, can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a RAM, a ROM, an erasable programmable read only memory (EPROM) or a flash memory, an optical fiber, a portable compact disc read only memory (Compact Disk Read Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0141] The basic principles of the present application are described above in combination with specific embodiments, but it should be noted that the advantages, advantages, effects, etc. mentioned in the present application are only examples and are not limiting, and these advantages, advantages, effects, etc. cannot be considered as the must-have of each embodiment of the present application. In addition, the above-mentioned specific details are only for the purpose of example and for the purpose of understanding, and are not limited to the present application, and the above-mentioned details do not limit the present application to the must-use of the above-mentioned specific details.

[0142] The block diagrams of the devices, apparatuses, equipment, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connection, arrangement, configuration must be as shown in the block diagrams. These devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner as will be appreciated by those skilled in the art. Words such as "include," "contain," "have," etc. are open-ended words that are to be interpreted to mean "including but not limited to," and are to be taken in a non-limiting sense. The words "or" and "and" as used herein are to be interpreted as the word "and / or," and are to be taken in a non-limiting sense, unless the context clearly indicates otherwise. The word "such as" as used herein is to be interpreted as the phrase "such as but not limited to," and is to be taken in a non-limiting sense.

[0143] It is also to be noted that in the devices, apparatuses and methods of the present application, the various components or steps can be decomposed and / or recombined. These decompositions and / or recombinations are to be considered as equivalents of the present application.

[0144] The above description of disclosed aspects is given for illustrative purposes and is not intended to limit the application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0145] The above description has been given for the purpose of illustration and description. Furthermore, this description does not purport to be exhaustive or to limit the application to the precise forms disclosed. Although several example aspects and embodiments have been discussed above, various modifications, substitutions, changes, additions and sub-combinations are possible.

[0146] The above is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method, characterized in that, include: Obtain the first address data in the work order, wherein the first address data is the address data filled in the work order by the agent after communicating with the target user according to a preset filling format; Identify second address data in the communication data between the agent and the target user, the communication data including at least one of the following: audio data, video data, and text data; At least one first local address data is extracted from the first address data, wherein the character length of the at least one first local address data is the same as the character length of the second address data; The Chinese characters in the at least one first local address data and the Chinese characters in the second address data are all converted into Pinyin to obtain at least one first local address Pinyin corresponding to the at least one first local address data and the second address Pinyin corresponding to the second address data; Based on the at least one first local address pinyin and the second address pinyin, a first detection result is determined, and based on the first detection result, it is determined whether the first address data filled in the work order is accurate.

2. The data processing method according to claim 1, characterized in that, Extracting at least one first local address data from the first address data includes: The first address data is divided according to a preset rule to obtain at least one first segmented address data, wherein the character length of the at least one first segmented address data is greater than or equal to the character length of the second address data; From the at least one first segmented address data, extract local addresses with the same character length as the second address to obtain at least one first local address data that corresponds one-to-one with the at least one first segmented address data.

3. The data processing method according to claim 2, characterized in that, The step of segmenting the first address data according to a preset rule to obtain at least one first segmented address data includes: The first address data is split into first standard address data and first detailed address data, wherein the first standard address data is used to characterize address data determined based on administrative division address, and the first detailed address data is used to characterize address data other than the first standard address data in the first address data; The first standard address data is divided according to the preset rules to obtain at least one first segmented address data.

4. The data processing method according to claim 3, characterized in that, The step of determining whether the first address data filled in the work order is accurate based on the first detection result includes: Based on the first detailed address data and the second address data, a second detection result is determined, wherein the second detection result is used to characterize whether the first detailed address data and the second address data match; Based on the first detection result and the second detection result, determine whether the first address data filled in the work order is accurate.

5. The data processing method according to claim 4, characterized in that, The step of determining the second detection result based on the first detailed address data and the second address data includes: Starting from the first character in the first detailed address data, extract N characters from the first detailed address data that have the same character length as the second address data, where N is a positive integer; Compare the N characters with the second address data; If the N characters are completely identical to all the characters in the second address data, then the second detection result is determined to be a match between the first detailed address data and the second address data.

6. The data processing method according to claim 4, characterized in that, The first detection result is used to characterize whether the first local address pinyin and the second address pinyin match; the step of determining whether the first address data filled in the work order is accurate based on the first detection result and the second detection result includes: If the first detection result indicates that the first local address pinyin and the second address pinyin match, then it is determined that the first address data filled in the work order is accurate; or, If the first detection result indicates that the first local address pinyin and the second address pinyin do not match, and the second detection result indicates that the first detailed address data and the second address data match, then it is determined that the first address data filled in the work order is accurate.

7. The data processing method according to any one of claims 1 to 6, characterized in that, The step of determining the first detection result based on the at least one first local address pinyin and the second address pinyin includes: Using the Levinstein algorithm, the Levinstein ratios of the at least one first local address pinyin and the second address pinyin are calculated respectively to obtain the Levinstein ratios corresponding to each of the at least one first local address pinyin. Determine the largest Levin-Stanby among the Levin-Stanby corresponding to each of the at least one first local address pinyin; If the maximum Levinstein ratio is greater than or equal to a preset threshold, the first detection result is determined to be a match between the first local address pinyin and the second address pinyin.

8. The data processing method according to any one of claims 1 to 6, characterized in that, The communication data includes multiple sentences arranged in chronological order of communication. The second address data for identifying the communication data between the agent and the target user includes: Based on preset keywords and preset regular expressions, determine the sentence that first appears related to the address among the multiple sentences; Using the first occurrence of the address-related sentence as the starting sentence, and using a preset number of sentences as the detection length, at least one sentence is determined. Extract the second address data from the at least one sentence.

9. The data processing method according to claim 8, characterized in that, The step of determining at least one sentence, starting with the sentence related to the first occurrence of the address and using a preset number of sentences as the detection length, includes: Using the first occurrence of the address-related sentence as the starting sentence, and using a preset number of sentences as the detection length, at least one pre-selected sentence is determined. For each of the at least one preselected sentences, if the data source of the next sentence of the preselected sentence is the target user, and the next sentence contains negative semantics, then a removal operation is performed on the preselected sentence and the next sentence of the preselected sentence; The at least one sentence is determined based on the at least one pre-selected sentence after the removal operation.

10. A data processing apparatus, characterized in that, include: The acquisition module is configured to acquire the first address data in the work order, wherein the first address data is the address data filled in the work order by the agent after communicating with the target user according to a preset filling format; The identification module is configured to identify second address data in the communication data between the agent and the target user, the communication data including at least one of the following: audio data, video data, and text data; The interception module is configured to extract at least one first local address data from the first address data, wherein the character length of the at least one first local address data is the same as the character length of the second address data; The conversion module is configured to convert Chinese characters in the at least one first local address data and Chinese characters in the second address data into Pinyin, thereby obtaining at least one first local address Pinyin corresponding to the at least one first local address data and a second address Pinyin corresponding to the second address data; The detection module is configured to determine a first detection result based on the at least one first local address pinyin and the second address pinyin, and to determine whether the first address data filled in the work order is accurate based on the first detection result.

11. A computer-readable storage medium, characterized in that, The storage medium stores instructions that, when executed by the processor of the electronic device, enable the electronic device to perform the data processing method according to any one of claims 1 to 9.

12. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store executable instructions for a computer; The processor is configured to execute the computer-executable instructions to implement the data processing method according to any one of claims 1 to 9.

Images