An electronic equipment after-sales service retrieval system and method based on a data center system

Abstract

The present invention relates to the field of after-sales service retrieval, and specifically to an electronic equipment after-sales service retrieval system and method based on a data center system, comprising a retrieval set construction module, a directional retrieval set analysis module, a first database storage module, a retrieval content analysis module, a priority analysis module and a response push module; the retrieval set construction module is used to extract the retrieval content of each type of fault problem corresponding to the user based on the electronic equipment after-sales service platform to construct a retrieval set; the directional retrieval set analysis module is used to screen the directional retrieval set; the first database storage module is used to associate the retrieval content in the directional retrieval set with the corresponding type of fault problem and store it in the first database; the retrieval content analysis module is used to determine the difference items and similar items of the retrieval content in the target set where each type of fault problem to be analyzed is located; the response push module is used to perform matching analysis and response push when new real-time user retrieval content is added to the after-sales platform.

Description

Technical Field

[0001] The present invention relates to the technical field of after-sales service retrieval, and in particular to an after-sales service retrieval system and method for electronic equipment based on a data center system. Background Art

[0002] The after-sales service management system of the consumer electronics industry is a comprehensive platform that integrates customer information management, service request processing, maintenance management, spare parts management, service marketing and other functions. Through this system, enterprises can realize digital management of the entire after-sales service process, improve service efficiency and quality, and enhance customer satisfaction; the existing platform can provide users with fault content retrieval based on input questions, so that the platform provides corresponding after-sales methods based on the user's search content and finally determines the after-sales solution, but this process requires users to input the search content in a clear direction and comprehensive content, which causes different users to have more search content deviations for the same type of electronic equipment failures, and it is not easy for the system to quickly locate the real problem of the equipment for these contents; it greatly increases the after-sales processing time and reduces the processing efficiency; at the same time, the non-standardization of the user's fault description often requires manual intervention to finally determine the after-sales solution, and this situation causes a waste of after-sales manpower resources for some simple fault problems and problems that users can repair independently based on text guidance. Summary of the invention

[0003] The object of the present invention is to provide an electronic equipment after-sales service retrieval system and method based on a data center system to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for after-sales service retrieval of electronic equipment based on a data center system, comprising the following analysis steps:

[0005] Step S100: obtaining after-sales events recorded by the electronic equipment after-sales service platform based on the data center system, marking electronic equipment failure problems in the after-sales events, classifying failure problems that implement the same after-sales solution in the after-sales events into the same type, extracting the search content of the user corresponding to each type of failure problem based on the electronic equipment after-sales service platform to construct a search set, and filtering the targeted search set;

[0006] The difference in search content is due to the different understanding of electronic devices and subjective differences among users, which leads to differences in the search content and content input order of users for equipment failures on the after-sales service platform, resulting in different order and scope of the platform pushing the processing solution information;

[0007] Step S200: associating the search content in the targeted search set with the corresponding type of fault problem and storing them in the first database, and removing the targeted search set, the fault problem type corresponding to other search sets is the fault problem type to be analyzed, marking the search set recorded with the fault problem type to be analyzed as the target set, and determining the difference items and similar items of the search content in the target set where each type of fault problem to be analyzed is located;

[0008] Step S300: extracting after-sales solutions for after-sales events under all to-be-analyzed fault types where the difference item records are located, analyzing the active index of the difference item based on the after-sales solution, and prioritizing the difference items based on the active index to generate an active sequence; and updating the difference items and similar items in the target set where the similar to-be-analyzed fault problems are located;

[0009] Step S400: Based on the updated similar items and difference items, matching analysis is performed and response push is performed when real-time user search content is added to the after-sales platform.

[0010] Furthermore, screening the targeted search set includes the following specific steps:

[0011] Step S110: extract keywords from the search contents of different user records corresponding to each type of fault problem, and enter the extracted keywords into a search set with user after-sales events as unit keyword groups; each type of fault problem corresponds to a search set, and a search set contains several unit keyword groups;

[0012] Step S120: Mark the search set with the same keywords in each unit keyword group as the first directional search set and mark the fault problem type corresponding to the first directional search set as the first directional fault type; remove the first directional search set and the remaining search sets as the second search set; obtain the number N of the i-th keyword in each unit keyword group in the second search set recorded in the unit keyword group in the second search set i , and the number M of records in the second search set when traversing all second search sets i , using the formula:

[0013] Z i =M i / N i ,

[0014] Calculate the search index Z of the i-th keyword in each unit keyword group of the second search set i , traverse the keywords in each keyword group, when the search index corresponding to each keyword in the second search set satisfies Z i ≠M i and 0 <Z i<1, the second search set is marked as a second directional search set, and the fault problem type corresponding to the second directional search set is a second directional fault type;

[0015] The purpose of analyzing the directional search set is to enable the platform to quickly and effectively locate the direction of the service required by the user when the user searches based on the service platform; and to analyze M i It can be determined that the keyword is unique for this type of fault problem and analyze N i The keyword can be determined to point to the characteristics of the corresponding fault problem.

[0016] Step S130: The first directed search set and the second directed search set constitute a directed search set.

[0017] Furthermore, step S200 includes the following specific steps:

[0018] The other search sets are the remaining search sets in the second search set excluding the second directional search set;

[0019] Mark the target set to record the keywords in all keyword groups as similar items, as well as the search index Z i =1 / N i The keywords are similar items;

[0020] Excluding the keywords that have been marked as similar items in the target set, the remaining keywords are the difference items corresponding to the target set and the fault problem type to be analyzed.

[0021] Furthermore, step S300 includes the following specific steps:

[0022] Step S310: extracting the implementation content of the after-sales plan, dividing the after-sales plan into user-independent feasible plans and after-sales necessary participation plans based on the implementation content, and distinguishing and marking each type of after-sales plan;

[0023] Step S320: Obtain the number of types U1 of the fault type to be analyzed when the after-sales solution of each difference item in the target set of records under each fault type to be analyzed is marked as a user-independent feasible solution; and the number of types U2 of the fault type to be analyzed when it is marked as a necessary after-sales participation solution; calculate the active index Q of each difference item in the target set of records under each fault type to be analyzed using the formula: Q=U1 / U2;

[0024] Step S330: sorting all difference items recorded in the target set under the same fault type to be analyzed from large to small according to the corresponding active index Q to generate an active sequence;

[0025] Step S340: When the activity index Q of the difference term is 0, the difference term is updated to a similar term.

[0026] If Q is 0, it means that the after-sales solution corresponding to the difference item does not exist and is not marked as a user-independent feasible solution; then when the difference item is input in real time, it is not possible to make directional judgments and push notifications on the user-independent feasible solutions. Therefore, treating such difference items as similar items can maximize the accuracy of the platform's push analysis based on user input content.

[0027] Furthermore, step S400 includes the following specific processes:

[0028] When adding real-time user search content to the after-sales platform to extract keywords, the platform will perform a matching analysis for each new keyword. The matching analysis process is as follows:

[0029] When the search content is a keyword, when the keyword is a similar item in the historical record, the after-sales solution corresponding to the similar item in the historical record is matched and pushed; when the keyword is a different item in the historical record, the after-sales solution marked as the user-autonomous feasible type in the active sequence with the highest priority corresponding to the different item is matched and pushed; when the keyword is any keyword in the first database of the historical record, the keyword is continuously monitored and acquired;

[0030] If the user actively triggers a response based on the platform response push, the push ends;

[0031] If the user does not actively trigger a response based on the platform response push, then continue to obtain the nth keyword, and form a real-time keyword group with the nth keyword and the first n-1 keywords. Match the same items with the real-time keyword group and push the corresponding after-sales plan. If there is no same, jump to the first database for retrieval. If there is an identical keyword group, respond and push the corresponding after-sales plan; if there is no same keyword group, continue monitoring;

[0032] When the nth keyword in the real-time keyword group is a difference item, the target set of the real-time keyword group is matched and recorded. When the target set is unique, the after-sales solution corresponding to the target set is pushed in response; when the target set is not unique, the response is pushed based on the matching method of the n-1th keyword as a difference item;

[0033] When all real-time keyword groups are difference items, match and record the target set of real-time keyword groups. When the target set is unique, respond to push the after-sales solution marked as user-independent feasible class corresponding to the target set; when the target set is not unique, calculate the real-time push index Y of the real-time keyword group in the corresponding target set, Y=Q1*...*Q n , select the after-sales solution marked as user-autonomous feasible in the target set corresponding to the maximum value of the real-time push index Ymax for response push;

[0034] After each response push, monitor whether the user actively triggers a response. If not, continue monitoring and end the push when triggered. Obtain the minimum number of keywords w recorded by the platform to determine the after-sales solution based on the search content. When the minimum number of keywords is reached, the after-sales service platform stops responding to the push, 2≤n≤w.

[0035] Determining the minimum number of keywords can maximize the efficiency of the platform's matching solutions based on user analysis and retrieval of content. Because the more keywords there are, the smaller the number of solutions automatically matched by the system will be. In this case, the role of the retrieval platform will be reduced. Therefore, this application is based on efficient, fast and clear-directed data analysis to push after-sales solutions that users can complete fault maintenance through self-debugging, which greatly improves the manpower savings of the after-sales service platform regarding after-sales personnel.

[0036] An electronic equipment after-sales service retrieval system based on a data center system, comprising a retrieval set construction module, a directional retrieval set analysis module, a first database storage module, a retrieval content analysis module, a priority analysis module and a response push module;

[0037] The retrieval set building module is used to extract the retrieval content of the user corresponding to each type of fault problem based on the electronic equipment after-sales service platform to build a retrieval set;

[0038] The directed search set analysis module is used to screen the directed search set;

[0039] The first database storage module is used to associate the search content in the directional search set with the corresponding type of fault problem and store it in the first database;

[0040] The search content analysis module is used to determine the difference items and similar items of the search content in the target set where each type of fault problem to be analyzed is located;

[0041] The priority analysis module is used to prioritize the difference items based on the activity index to generate an activity sequence;

[0042] The response push module is used to perform matching analysis and response push when new real-time user search content is added to the after-sales platform.

[0043] Further, the directed retrieval set analysis module includes a retrieval set classification unit, a retrieval index calculation unit and a directed retrieval set output unit;

[0044] The search set classification unit is used to classify the search set into a first directional search set and a second search set;

[0045] The search index calculation unit is used to calculate the search index of the keyword based on the second search set;

[0046] The directed search set output unit is used to determine a second directed search set based on the search index, and to form a directed search set with the first directed search set and the second directed search set.

[0047] Further, the priority analysis module includes an after-sales solution distinguishing marking unit, an active index calculating unit, an active sequence building unit and a difference item updating unit;

[0048] The after-sales solution distinguishing marking unit is used to classify after-sales solutions into user-independent feasible solutions and after-sales necessary participation solutions based on the implementation content, and distinguish and mark each type of after-sales solution;

[0049] The activity index calculation unit is used to calculate the activity index of each difference item in the record target set under each fault type to be analyzed;

[0050] The active sequence construction unit is used to sort all difference items recorded in the target set under the same fault type to be analyzed from large to small according to the corresponding active index to generate an active sequence;

[0051] The difference item updating unit is used for updating the difference item to a similar item when the activity index of the difference item is 0.

[0052] Further, the response push module includes a keyword response unit, a matching analysis unit and a response cutoff unit;

[0053] The keyword response unit is used to transmit signals for matching analysis when keywords can be extracted from newly added real-time user search content;

[0054] The matching analysis unit is used to analyze the real-time input keywords and the historical record keywords and push the recorded after-sales solutions;

[0055] The response cutoff unit is used to monitor whether the user actively triggers a response after each response push, continue monitoring if not triggered, and end the push when triggered; and obtain the platform record of the minimum number of keywords for determining the after-sales solution based on the search content. When the minimum number of keywords is reached, the after-sales service platform stops responding to the push.

[0056] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention classifies the search set, determines the keywords that can directly locate the after-sales solution, stores them in the first database, and further divides the keywords into similar items and difference items, and implements real-time matching of different analysis solutions; when the matching conditions are met, the solution that the corresponding user can solve the problem independently is pushed, which saves the system from further pushing the cumbersome process of after-sales personnel to assist users in solving simple problems; improves the efficiency of after-sales processing and improves the rationality and efficiency of the after-sales platform based on human resource management; standardizes the clear directionality of the keyword differences of different users under the same fault problem, and quickly locates the real problem of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0058] Figure 1 It is a structural schematic diagram of an after-sales service retrieval system and method for electronic equipment based on a data center system of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 The present invention provides a technical solution: a method for after-sales service retrieval of electronic equipment based on a data center system, comprising the following analysis steps:

[0061] Step S100: obtaining after-sales events recorded by the electronic equipment after-sales service platform based on the data center system, marking electronic equipment failure problems in the after-sales events, classifying failure problems that implement the same after-sales solution in the after-sales events into the same type, extracting the search content of the user corresponding to each type of failure problem based on the electronic equipment after-sales service platform to construct a search set, and filtering the targeted search set;

[0062] The difference in search content is due to the different understanding of electronic devices and subjective differences among users, which leads to differences in the search content and content input order of users for equipment failures on the after-sales service platform, resulting in different order and scope of the platform pushing the processing solution information;

[0063] Step S200: associating the search content in the targeted search set with the corresponding type of fault problem and storing them in the first database, and removing the targeted search set, the fault problem type corresponding to other search sets is the fault problem type to be analyzed, marking the search set recorded with the fault problem type to be analyzed as the target set, and determining the difference items and similar items of the search content in the target set where each type of fault problem to be analyzed is located;

[0064] Step S300: extracting after-sales solutions for after-sales events under all to-be-analyzed fault types where the difference item records are located, analyzing the active index of the difference item based on the after-sales solution, and prioritizing the difference items based on the active index to generate an active sequence; and updating the difference items and similar items in the target set where the similar to-be-analyzed fault problems are located;

[0065] Step S400: Based on the updated similar items and difference items, matching analysis is performed and response push is performed when real-time user search content is added to the after-sales platform.

[0066] Screening a targeted search collection includes the following specific steps:

[0067] Step S110: extract keywords from the search contents of different user records corresponding to each type of fault problem, and enter the extracted keywords into a search set with user after-sales events as unit keyword groups; each type of fault problem corresponds to a search set, and a search set contains several unit keyword groups;

[0068] Step S120: Mark the search set with the same keywords in each unit keyword group as the first directional search set and mark the fault problem type corresponding to the first directional search set as the first directional fault type; remove the first directional search set and the remaining search sets as the second search set; obtain the number N of the i-th keyword in each unit keyword group in the second search set recorded in the unit keyword group in the second search set i , and the number M of records in the second search set when traversing all second search sets i , using the formula:

[0069] Z i =M i / N i ,

[0070] Calculate the search index Z of the i-th keyword in each unit keyword group of the second search set i , traverse the keywords in each keyword group, when the search index corresponding to each keyword in the second search set satisfies Z i ≠M i and 0 <Z i<1, the second search set is marked as a second directional search set, and the fault problem type corresponding to the second directional search set is a second directional fault type;

[0071] As shown in the embodiment: the second search set is composed of keyword group 1, keyword group 2, and keyword group 3;

[0072] Keyword group 1 records keyword 1, keyword 2, and keyword 3;

[0073] Keyword group 2 records keyword 1, keyword 2, keyword 3, and keyword 4;

[0074] Keyword 2 and keyword 4 are recorded in keyword group 3;

[0075] If we calculate keyword 1 in keyword group 1, we know that N1=2, and keyword 1 is not recorded in other second search sets, so M1=1; then the search index of keyword 1 is calculated to be 1 / 2; satisfying Z i ≠M i and 0 <Z i <1;

[0076] All keywords in the second search set are calculated in sequence. If all keywords meet the requirements, the second search set is a targeted search set. The purpose of analyzing the targeted search set is to enable the platform to quickly and effectively locate the direction of the service required by the user when the user searches based on the service platform; and i It can be determined that the keyword is unique for this type of fault problem and analyze N i The keyword can be determined to point to the characteristics of the corresponding fault problem.

[0077] Step S130: The first directed search set and the second directed search set constitute a directed search set.

[0078] Step S200 includes the following specific steps:

[0079] The other search sets are the remaining search sets in the second search set excluding the second directional search set;

[0080] Mark the target set to record the keywords in all keyword groups as similar items, as well as the search index Z i =1 / N i The keywords when are similar items;

[0081] Excluding the keywords that have been marked as similar items in the target set, the remaining keywords are the difference items corresponding to the target set and the fault problem type to be analyzed.

[0082] Step S300 includes the following specific steps:

[0083] Step S310: extracting the implementation content of the after-sales plan, dividing the after-sales plan into user-independent feasible plans and after-sales necessary participation plans based on the implementation content, and distinguishing and marking each type of after-sales plan;

[0084] User-independent feasible solutions refer to solutions that record specific user-operable execution steps in the implementation content and can solve fault problems; on the contrary, after-sales necessary participation solutions refer to solutions that record the steps that after-sales personnel need to perform to solve fault problems in the implementation content;

[0085] Step S320: Obtain the number of types U1 of the fault type to be analyzed when the after-sales solution of each difference item in the target set of records under each fault type to be analyzed is marked as a user-independent feasible solution; and the number of types U2 of the fault type to be analyzed when it is marked as a necessary after-sales participation solution; calculate the active index Q of each difference item in the target set of records under each fault type to be analyzed using the formula: Q=U1 / U2;

[0086] Step S330: sorting all difference items recorded in the target set under the same fault type to be analyzed from large to small according to the corresponding active index Q to generate an active sequence;

[0087] Step S340: When the activity index Q of the difference term is 0, the difference term is updated to a similar term.

[0088] If Q is 0, it means that the after-sales solution corresponding to the difference item does not exist and is not marked as a user-independent feasible solution; then when the difference item is input in real time, it is not possible to make directional judgments and push notifications on the user-independent feasible solutions. Therefore, treating such difference items as similar items can maximize the accuracy of the platform's push analysis based on user input content.

[0089] Step S400 includes the following specific processes:

[0090] When adding real-time user search content to the after-sales platform to extract keywords, the platform will perform a matching analysis for each new keyword. The matching analysis process is as follows:

[0091] When the search content is a keyword, when the keyword is a similar item in the historical record, the after-sales solution corresponding to the similar item in the historical record is matched and pushed; when the keyword is a different item in the historical record, the after-sales solution marked as the user-autonomous feasible type in the active sequence with the highest priority corresponding to the different item is matched and pushed; when the keyword is any keyword in the first database of the historical record, the keyword is continuously monitored and acquired;

[0092] If the user actively triggers a response based on the platform response push, the push ends;

[0093] If the user does not actively trigger a response based on the platform response push, then continue to obtain the nth keyword, and form a real-time keyword group with the nth keyword and the first n-1 keywords. Match the same items with the real-time keyword group and push the corresponding after-sales plan. If there is no same, jump to the first database for retrieval. If there is an identical keyword group, respond and push the corresponding after-sales plan; if there is no same keyword group, continue monitoring;

[0094] When the nth keyword in the real-time keyword group is a difference item, the target set of the real-time keyword group is matched and recorded. When the target set is unique, the after-sales solution corresponding to the target set is pushed in response; when the target set is not unique, the response is pushed based on the matching method of the n-1th keyword as a difference item;

[0095] When all real-time keyword groups are difference items, match and record the target set of real-time keyword groups. When the target set is unique, respond to push the after-sales solution marked as user-independent feasible class corresponding to the target set; when the target set is not unique, calculate the real-time push index Y of the real-time keyword group in the corresponding target set, Y=Q1*...*Q n , select the after-sales solution marked as user-autonomous feasible in the target set corresponding to the maximum value of the real-time push index Ymax for response push;

[0096] After each response push, monitor whether the user actively triggers a response. If not, continue monitoring and end the push when triggered. Obtain the minimum number of keywords w recorded by the platform to determine the after-sales solution based on the search content. When the minimum number of keywords is reached, the after-sales service platform stops responding to the push, 2≤n≤w.

[0097] Determining the minimum number of keywords can maximize the efficiency of the platform's matching solutions based on user analysis and retrieval of content. Because the more keywords there are, the smaller the number of solutions automatically matched by the system will be. In this case, the role of the retrieval platform will be reduced. Therefore, this application is based on efficient, fast and clear-directed data analysis to push after-sales solutions that users can complete fault maintenance through self-debugging, which greatly improves the manpower savings of the after-sales service platform regarding after-sales personnel.

[0098] An electronic equipment after-sales service retrieval system based on a data center system, comprising a retrieval set construction module, a directional retrieval set analysis module, a first database storage module, a retrieval content analysis module, a priority analysis module and a response push module;

[0099] The retrieval set building module is used to extract the retrieval content of the user corresponding to each type of fault problem based on the electronic equipment after-sales service platform to build a retrieval set;

[0100] The directed search set analysis module is used to screen the directed search set;

[0101] The first database storage module is used to associate the search content in the directional search set with the corresponding type of fault problem and store it in the first database;

[0102] The search content analysis module is used to determine the difference items and similar items of the search content in the target set where each type of fault problem to be analyzed is located;

[0103] The priority analysis module is used to prioritize the difference items based on the activity index to generate an activity sequence;

[0104] The response push module is used to perform matching analysis and response push when new real-time user search content is added to the after-sales platform.

[0105] The directed retrieval set analysis module includes a retrieval set classification unit, a retrieval index calculation unit and a directed retrieval set output unit;

[0106] The search set classification unit is used to classify the search set into a first directional search set and a second search set;

[0107] The search index calculation unit is used to calculate the search index of the keyword based on the second search set;

[0108] The directed search set output unit is used to determine a second directed search set based on the search index, and to form a directed search set with the first directed search set and the second directed search set.

[0109] The priority analysis module includes an after-sales solution distinguishing marking unit, an active index calculating unit, an active sequence building unit and a difference item updating unit;

[0110] The after-sales solution distinguishing marking unit is used to classify after-sales solutions into user-independent feasible solutions and after-sales necessary participation solutions based on the implementation content, and distinguish and mark each type of after-sales solution;

[0111] The activity index calculation unit is used to calculate the activity index of each difference item in the record target set under each fault type to be analyzed;

[0112] The active sequence construction unit is used to sort all difference items recorded in the target set under the same fault type to be analyzed from large to small according to the corresponding active index to generate an active sequence;

[0113] The difference item updating unit is used for updating the difference item to a similar item when the activity index of the difference item is 0.

[0114] The response push module includes a keyword response unit, a matching analysis unit and a response cutoff unit;

[0115] The keyword response unit is used to transmit signals for matching analysis when keywords can be extracted from newly added real-time user search content;

[0116] The matching analysis unit is used to analyze the real-time input keywords and the historical record keywords and push the recorded after-sales solutions;

[0117] The response cutoff unit is used to monitor whether the user actively triggers a response after each response push, continue monitoring if not triggered, and end the push when triggered; and obtain the platform record of the minimum number of keywords for determining the after-sales solution based on the search content. When the minimum number of keywords is reached, the after-sales service platform stops responding to the push.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0119] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for after-sales service retrieval of electronic equipment based on a data center system, characterized in that: The analysis steps include: Step S100: obtaining after-sales events recorded by the electronic equipment after-sales service platform based on the data center system, wherein the after-sales events mark electronic equipment failure problems, classifying failure problems that implement the same after-sales solution in the after-sales events into the same type, extracting the search content of the user corresponding to each type of failure problem based on the electronic equipment after-sales service platform to construct a search set, and screening the targeted search set; The screening of the targeted search set comprises the following specific steps: Step S110: extract keywords from the search contents of different user records corresponding to each type of fault problem, and enter the extracted keywords into a search set with user after-sales events as unit keyword groups; each type of fault problem corresponds to a search set, and a search set contains several unit keyword groups; Step S120: Mark the search set with the same keywords in each unit keyword group as the first directional search set and mark the fault problem type corresponding to the first directional search set as the first directional fault type; remove the first directional search set and the remaining search sets as the second search set; obtain the number N of the i-th keyword in each unit keyword group in the second search set recorded in the unit keyword group in the second search set i , and the number M of records in the second search set when traversing all second search sets i , using the formula: Z i =M i / N i , Calculate the search index Z of the i-th keyword in each unit keyword group of the second search set i , traverse the keywords in each keyword group, when the search index corresponding to each keyword in the second search set satisfies Z i ≠M i and 0 <Z i <1, the second search set is marked as a second directional search set, and the fault problem type corresponding to the second directional search set is a second directional fault type; Step S130: the first directional search set and the second directional search set constitute a directional search set; Step S200: associating the search content in the targeted search set with the corresponding type of fault problem and storing them in the first database, and removing the targeted search set, the fault problem type corresponding to other search sets is the fault problem type to be analyzed, marking the search set recorded with the fault problem type to be analyzed as the target set, and determining the difference items and similar items of the search content in the target set where each type of fault problem to be analyzed is located; Step S300: extracting after-sales solutions for after-sales events of all the fault types to be analyzed where the difference item records are located, analyzing the active index of the difference item based on the after-sales solution, and prioritizing the difference item based on the active index to generate an active sequence; And update the difference items and similar items in the target set of similar fault problems to be analyzed; Step S400: Based on the updated similar items and difference items, matching analysis is performed and response push is performed when real-time user search content is added to the after-sales platform.

2. According to claim 1, a method for after-sales service retrieval of electronic equipment based on a data center system is characterized in that: The step S200 includes the following specific steps: The other search sets are the remaining search sets in the second search set excluding the second directional search set; Mark the target set to record the keywords in all keyword groups as similar items, as well as the search index Z i =1 / N i The keywords are similar items; Excluding the keywords that have been marked as similar items in the target set, the remaining keywords are the difference items corresponding to the target set and the fault problem type to be analyzed.

3. The method for after-sales service retrieval of electronic equipment based on a data center system according to claim 2, characterized in that: The step S300 includes the following specific steps: Step S310: extracting the implementation content of the after-sales plan, dividing the after-sales plan into user-independent feasible plans and after-sales necessary participation plans based on the implementation content, and distinguishing and marking each type of after-sales plan; Step S320: Obtain the number of types of faults to be analyzed U1 when the after-sales solutions of each difference item in the target set of records under each fault type to be analyzed are marked as user-independent feasible solutions; and the number of types of faults to be analyzed U2 when they are marked as after-sales necessary participation solutions; using the formula: Q = U1 / U2; Calculate the active index Q of each difference item in the target set for each fault type to be analyzed; Step S330: sorting all difference items recorded in the target set under the same fault type to be analyzed from large to small according to the corresponding active index Q to generate an active sequence; Step S340: when the activity index Q of the difference item is 0, the difference item is updated to a similar item.

4. The method for after-sales service retrieval of electronic equipment based on a data center system according to claim 3, characterized in that: The step S400 includes the following specific processes: When the after-sales platform adds real-time user search content to extract keywords, the platform performs a matching analysis for each new keyword. The matching analysis process is as follows: When the search content is a keyword, when the keyword is a similar item in the historical record, the after-sales solution corresponding to the similar item in the historical record is matched and pushed in response; when the keyword is a different item in the historical record, the after-sales solution marked as user-autonomous feasible type in the active sequence with the highest priority corresponding to the different item is matched and pushed in response; when the keyword is any keyword in the first database of the historical record, the keyword is continuously monitored and acquired; If the user actively triggers a response based on the platform response push, the push ends; If the user does not actively trigger a response based on the platform response push, then continue to obtain the nth keyword, and form a real-time keyword group with the nth keyword and the first n-1 keywords. Match the same items with the real-time keyword group and push the corresponding after-sales plan. If there is no same, jump to the first database for retrieval. If there is an identical keyword group, respond and push the corresponding after-sales plan; if there is no same keyword group, continue monitoring; When the nth keyword in the real-time keyword group is a difference item, the target set of the real-time keyword group is matched and recorded. When the target set is unique, the after-sales solution corresponding to the target set is pushed in response; when the target set is not unique, the response is pushed based on the matching method of the n-1th keyword as a difference item; When all real-time keyword groups are difference items, match and record the target set of real-time keyword groups. When the target set is unique, respond to push the after-sales solution marked as user-independent feasible class corresponding to the target set; when the target set is not unique, calculate the real-time push index Y of the real-time keyword group in the corresponding target set, Y=Q1*...*Q n , select the after-sales solution marked as user-autonomous feasible in the target set corresponding to the maximum value of the real-time push index Ymax for response push; After each response push, monitor whether the user actively triggers a response. If not, continue monitoring and end the push when triggered. Obtain the minimum number of keywords w recorded by the platform to determine the after-sales solution based on the search content. When the minimum number of keywords is reached, the after-sales service platform stops responding to the push, 2≤n≤w.

5. An electronic equipment after-sales service retrieval system based on a data center system, such as using an electronic equipment after-sales service retrieval method based on a data center system according to any one of claims 1 to 4, characterized in that: It includes a retrieval set construction module, a directional retrieval set analysis module, a first database storage module, a retrieval content analysis module, a priority analysis module and a response push module; The search set building module is used to extract the search content of each type of fault problem corresponding to the user based on the electronic equipment after-sales service platform to build a search set; The directed search set analysis module is used to screen the directed search set; The first database storage module is used to associate the search content in the directional search set with the corresponding type of fault problem and store it in the first database; The search content analysis module is used to determine the difference items and similar items of the search content in the target set of each type of fault problem to be analyzed; The priority analysis module is used to prioritize the difference items based on the activity index to generate an activity sequence; The response push module is used to perform matching analysis and response push when new real-time user search content is added to the after-sales platform.

6. The electronic equipment after-sales service retrieval system based on a data center system according to claim 5, characterized in that: The directed retrieval set analysis module includes a retrieval set classification unit, a retrieval index calculation unit and a directed retrieval set output unit; The search set classification unit is used to classify the search set into a first directional search set and a second search set; The retrieval index calculation unit is used to calculate the retrieval index of the keyword based on the second retrieval set; The directed search set output unit is used to determine a second directed search set based on the search index, and to form a directed search set with the first directed search set and the second directed search set.

7. The electronic equipment after-sales service retrieval system based on a data center system according to claim 6, characterized in that: The priority analysis module includes an after-sales solution distinguishing marking unit, an active index calculating unit, an active sequence building unit and a difference item updating unit; The after-sales solution distinguishing marking unit is used to classify after-sales solutions into user-independent feasible solutions and after-sales necessary participation solutions based on the implementation content, and distinguish and mark each type of after-sales solution; The activity index calculation unit is used to calculate the activity index of each difference item in the record target set under each fault type to be analyzed; The active sequence construction unit is used to sort all difference items recorded in the target set under the same fault type to be analyzed from large to small according to the corresponding active index to generate an active sequence; The difference item updating unit is used for updating the difference item to a similar item when the activity index of the difference item is 0.

8. The electronic equipment after-sales service retrieval system based on a data center system according to claim 7, characterized in that: The response push module includes a keyword response unit, a matching analysis unit and a response cutoff unit; The keyword response unit is used to transmit a signal for matching analysis when keywords can be extracted from newly added real-time user search content; The matching analysis unit is used to analyze the real-time input keywords and the historical record keywords and push the recorded after-sales solutions; The response cutoff unit is used to monitor whether the user actively triggers a response after each response push, continue monitoring if not triggered, and end the push when triggered; and obtain the platform record of the minimum number of keywords for determining the after-sales solution based on the search content. When the minimum number of keywords is reached, the after-sales service platform stops responding to the push.

Images