Maintenance application method and device, computer equipment and storage medium

Abstract

The application relates to a maintenance application method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: if a system repair event is detected, determining repair information according to the system repair event; searching, through a support vector machine (SVM) model, a historical maintenance database to check whether a similar maintenance record corresponding to the repair information exists; if the similar maintenance record exists, determining a maintenance application for reminding a maintenance personnel based on the repair information and the similar maintenance record. The application reduces the time and energy consumed by the staff in the process of performing the maintenance application.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a repair application method, apparatus, computer equipment, and storage medium. Background Technology

[0002] As computer systems become increasingly feature-rich, the probability of system malfunctions also increases. When a malfunction occurs, staff need to select the appropriate maintenance personnel based on the type of malfunction and explain the problem to the personnel to ensure they can properly troubleshoot the issue.

[0003] However, during the process of submitting a repair request, staff not only need to select the corresponding repair personnel according to the type of abnormality, but also need to explain the abnormality to the repair personnel. This results in staff consuming a lot of time and energy during the repair request process. Summary of the Invention

[0004] Therefore, it is necessary to provide a maintenance application method, apparatus, computer equipment, and storage medium that can reduce the time and effort spent by staff in the maintenance application process, thereby addressing the aforementioned technical problems.

[0005] Firstly, this application provides a method for determining a repair request. The method includes:

[0006] If a system repair event is detected, the repair information is determined based on the system repair event;

[0007] Using a support vector machine (SVM) model, we search the historical maintenance database to find if there are similar maintenance records corresponding to the reported maintenance information.

[0008] If such a request exists, a repair application will be determined based on the repair information and similar repair records to remind repair personnel.

[0009] In one embodiment, the historical maintenance database contains at least one candidate repair vector and a candidate repair record corresponding to each candidate repair vector.

[0010] Using a Support Vector Machine (SVM) model, we search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information, including:

[0011] Perform vector transformation on the repair information to obtain the target repair vector;

[0012] The SVM model is used to determine the similarity between the target repair request vector and each candidate repair request vector in the historical maintenance database; and based on the similarity, the database is searched to see if there are similar repair records corresponding to the repair request information.

[0013] In one embodiment, based on the degree of similarity, the system searches the historical maintenance database for similar maintenance records corresponding to the reported maintenance information, including:

[0014] From the candidate repair request vectors in the historical repair database, find similar repair vectors with a similarity greater than a preset similarity threshold;

[0015] The candidate repair record corresponding to each similar repair vector in the historical repair database is taken as at least one similar repair record corresponding to the repair information.

[0016] In one embodiment, the repair information is vector-converted to obtain the target repair vector, including:

[0017] Remove stop words from the repair request information to obtain the processed repair request information;

[0018] The processed repair information is segmented into word groups to obtain repair phrases.

[0019] Based on the vector transformation model, the repair request phrases are transformed into vectors to obtain the target repair request vector of the repair information.

[0020] In one embodiment, the method further includes:

[0021] Receive target repair records from maintenance personnel;

[0022] Update the historical maintenance database based on the target repair vector and target maintenance record of the repair information.

[0023] In one embodiment, a system repair event is detected, including:

[0024] If a new repair request email is detected in the target mailbox, it is determined that a system repair event has occurred.

[0025] Accordingly, the repair information is determined based on the system repair event, including:

[0026] Determine the repair information based on the newly added repair email corresponding to the system repair event.

[0027] In one embodiment, the repair information is determined based on the newly added repair email corresponding to the system repair event, including:

[0028] Take a screenshot of the repair request email to obtain a screenshot of the repair request email;

[0029] Extract text information from screenshots of repair requests in emails to obtain the repair information.

[0030] In one embodiment, the method further includes:

[0031] If it does not exist, a repair request will be determined based on the repair information to remind the repair personnel.

[0032] Secondly, this application also provides a repair request determining device. The device includes:

[0033] The first determining module is used to determine the repair information based on the system repair event if a system repair event is detected.

[0034] The search module is used to search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information, using a support vector machine (SVM) model.

[0035] The second determination module is used to determine, if present, a repair request to remind repair personnel based on the repair information and similar repair records.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement a repair application determination method as described above.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements a repair application determination method as described above.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements a repair application determination method that achieves one aspect of the above.

[0039] The aforementioned repair application method, device, computer equipment, and storage medium search the historical repair database for similar repair records based on the repair request information. If similar records are found, a repair application is generated to remind repair personnel. Since staff only need to report the repair event to the system during this process, they do not need to select the corresponding repair personnel according to the anomaly type, nor do they need to explain the anomaly to the repair personnel, thus reducing the time and effort spent by staff in processing repair applications. Furthermore, this application can also search the historical repair database for similar repair records and generate a repair application to remind repair personnel along with the repair request information, ensuring that repair personnel can perform repairs based on similar repair records, thereby improving the repair effect and efficiency. Attached Figure Description

[0040] Figure 1 An application environment diagram for a repair application determination method provided in this application embodiment;

[0041] Figure 2 A flowchart illustrating a method for determining a repair request, as provided in this application embodiment;

[0042] Figure 3 A flowchart illustrating a method for searching a historical maintenance database, as provided in this application embodiment;

[0043] Figure 4 A flowchart for determining repair information is provided in an embodiment of this application;

[0044] Figure 5 A flowchart illustrating another method for determining a repair request provided in this application embodiment;

[0045] Figure 6 A structural block diagram of a first type of repair application determining device provided in this application embodiment;

[0046] Figure 7 A structural block diagram of a second repair application determination device provided in this application embodiment;

[0047] Figure 8 A structural block diagram of a third repair application determination device provided in this application embodiment;

[0048] Figure 9 A structural block diagram of the fourth repair application determination device provided in this application embodiment;

[0049] Figure 10 A structural block diagram of the fifth repair application determination device provided in this application embodiment;

[0050] Figure 11 A structural block diagram of the sixth repair application determination device provided in the embodiments of this application;

[0051] Figure 12 A structural block diagram of the seventh repair application determination device provided in the embodiments of this application;

[0052] Figure 13 A structural block diagram of the eighth repair application determination device provided in this application embodiment;

[0053] Figure 14 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application. In the description of this application, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0056] Based on the above, the repair request determination method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, in one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 1 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data acquired through a repair request determination method. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a repair request determination method.

[0057] This application discloses a repair application method, apparatus, computer equipment, and storage medium. The computer equipment determines the repair information and uses an SVM model to search the historical repair database for similar repair records corresponding to the repair information. If similar records exist, a repair application is determined to remind the repair personnel.

[0058] In one embodiment, such as Figure 2 As shown, Figure 2 This application provides a flowchart of a method for determining a repair request, which is an embodiment of the present application. Figure 1The method for determining a repair request executed by computer equipment may include the following steps:

[0059] Step 201: If a system repair event is detected, determine the repair information based on the system repair event.

[0060] It should be noted that a system repair incident refers to a repair request submitted by staff based on an abnormal error in the system; furthermore, system repair incidents can take many forms, such as email, desktop pop-up, or SMS message.

[0061] Based on the above, it can be understood that there are many forms of system repair events, and the form of system repair events may vary depending on the system with abnormal errors or the specific abnormal errors that occur.

[0062] As one implementation method, when it is determined that the form of the system repair event is email, it is checked in real time whether the pre-set target email has received the repair email from the staff. If so, it means that a system repair event has been detected. The repair email from the staff is the system repair event, and the content recorded in the repair email from the staff is the repair information.

[0063] As another implementation method, when it is determined that the manifestation of the system repair event is a system desktop pop-up, it is determined in real time whether a repair pop-up appears on the system desktop. If so, it means that a system repair event has been detected. The repair pop-up on the system desktop is the system repair event, and the content recorded in the repair pop-up on the system desktop is the repair information.

[0064] As another implementation method, when it is determined that the form of the system repair event is a terminal short message, it is determined in real time whether the pre-set terminal device has received the repair short message from the staff. If so, it means that a system repair event has been detected. The repair short message from the staff is the system repair event, and the content recorded in the repair short message from the staff is the repair information.

[0065] To further clarify, repair information refers to the content related to system errors recorded in system repair events. For example, repair information may include, but is not limited to, the system error time, the system error address, and the consequences caused by the system error.

[0066] As one implementation method, when the form of system repair event is determined to be email, the repair information may include, but is not limited to: the initiator of the repair email, the time the repair email was sent, and the body of the repair email.

[0067] As another implementation method, when the system repair event is determined to be manifested in the form of a system desktop pop-up, the repair information may include, but is not limited to: the pop-up time of the repair pop-up on the system desktop, the content recorded in the repair pop-up, etc.

[0068] As another implementation method, when the form of the system repair event is determined to be a terminal short message, the repair information may include, but is not limited to: the sending time of the repair short message reported by the staff, the sender of the repair short message, and the text of the repair short message.

[0069] In one embodiment of this application, when it is necessary to determine the repair information based on the system repair event, the system repair event can be screenshotted, and the text content can be recognized based on the screenshot of the system repair event to obtain the text content contained in the system repair event, which is the repair information.

[0070] As one implementation method, system repair events are presented in the form of emails. When it is necessary to determine the repair information based on the system repair event, a screenshot of the repair email provided by the staff is taken. The screenshot of the repair email is then subjected to text content recognition to obtain the text content contained in the repair email, which is the repair information.

[0071] As another implementation method, the system repair event is presented as a system desktop pop-up. When it is necessary to determine the repair information based on the system repair event, a screenshot of the repair pop-up window on the system desktop is taken. The screenshot of the repair pop-up window is then subjected to text content recognition to obtain the text content contained in the repair pop-up window, which is the repair information.

[0072] As another implementation method, the system repair event is represented in the form of a terminal short message. When it is necessary to determine the repair information based on the system repair event, the repair short message fed back by the staff is taken as a screenshot. The text content of the repair short message is then recognized by the screenshot to obtain the text content contained in the repair short message, which is the repair information.

[0073] Step 202: Use the Support Vector Machine (SVM) model to search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information; if they exist, proceed to step 203; if they do not exist, proceed to step 204.

[0074] The historical maintenance database contains at least one candidate repair vector and the corresponding candidate repair record for each candidate repair vector.

[0075] It should be noted that the SVM model can filter the candidate repair vectors contained in the historical repair database based on the repair information, and then determine whether there are similar repair records corresponding to the repair information in the historical repair database.

[0076] In one embodiment of this application, a pre-set similarity threshold can be used to determine the similarity between the target repair vector corresponding to the target repair and each candidate repair vector in the historical repair database based on the SVM model. Based on the relationship between the similarity between each candidate repair vector and the target repair vector corresponding to the target repair and the similarity threshold, similar repair vectors with a similarity greater than the preset similarity threshold can be determined.

[0077] For example, if the pre-set similarity threshold is 0.5, and the historical maintenance database contains three candidate repair vectors: candidate repair vector A, candidate repair vector B, and candidate repair vector C; according to the SVM model, the similarity between the target repair vector corresponding to the target repair and each candidate repair vector in the historical maintenance database is determined as follows: the similarity between the target repair vector corresponding to the target repair and candidate repair vector A is 0.6; the similarity between the target repair vector corresponding to the target repair and candidate repair vector B is 0.2; the similarity between the target repair vector corresponding to the target repair and candidate repair vector C is 0.2. Since the similarity between candidate repair vector A and the target repair vector corresponding to the target repair is greater than the similarity threshold, repair vector A is selected as the similar maintenance record corresponding to the repair information.

[0078] Step 203: Based on the repair information and similar repair records, determine the repair request to remind the repair personnel.

[0079] It should be noted that if a similar repair record corresponding to the repair request exists in the historical maintenance database, the repair request used to remind maintenance personnel will include both the repair request information and the similar repair record. Furthermore, to ensure that the repair request includes both the repair request information and the similar repair record when a similar repair record exists in the historical maintenance database, it is necessary to pre-set an application template that includes both fields for filling in the repair request information and the similar repair record. By filling in the repair request information and the similar repair record in the corresponding fields of the application template, the repair request used to remind maintenance personnel can be obtained.

[0080] To further explain, after determining the repair request to remind the maintenance personnel, the maintenance personnel who can handle the error type can be selected based on the error type of the system abnormality recorded in the repair information, and the repair request to remind the maintenance personnel can be sent to the corresponding maintenance personnel to ensure that the maintenance personnel can successfully resolve the system abnormality.

[0081] Step 204: Based on the repair information, determine the repair request to remind the repair personnel.

[0082] It should be noted that if no similar repair record corresponding to the repair information exists in the historical repair database, the repair request used to remind repair personnel will only contain the repair information. Furthermore, to ensure that the repair request includes the repair information even when no similar repair record exists in the historical repair database, it is necessary to pre-set an application template that includes a space for filling in the repair information. By filling in the repair information in the corresponding space of the application template, the repair request used to remind repair personnel can be obtained.

[0083] The aforementioned repair application method searches the historical repair database for similar repair records based on the repair request information. If similar records are found, a repair application is generated to remind repair personnel. Since staff only need to report the repair event to the system during this process, they do not need to select the corresponding repair personnel based on the anomaly type, nor do they need to explain the anomaly to the repair personnel, thus reducing the time and effort spent by staff in processing repair applications. Furthermore, this application can also search the historical repair database for similar repair records and generate a repair application to remind repair personnel along with the repair request information, ensuring that repair personnel can perform repairs based on similar records, thereby improving repair effectiveness and efficiency.

[0084] As computer systems become increasingly feature-rich, the probability of system malfunctions also rises. When such malfunctions occur, the numerous functions of a computer system necessitate a detailed explanation of the problem to maintenance personnel. This ensures that maintenance staff can accurately identify the malfunctioning function and effectively address the issue. Consequently, this process consumes a significant amount of time and effort for staff. To address this problem, the computer equipment in this embodiment can... Figure 3 The method shown searches the historical repair database for similar repair records corresponding to the reported repair information. This involves the following steps:

[0085] Step 301: Perform vector transformation on the repair information to obtain the target repair vector of the repair information.

[0086] It should be noted that, in order to ensure that the SVM model can determine the similarity between the target repair vector and each candidate repair vector in the historical maintenance database, the repair information needs to be vectorized first. This ensures that the SVM model can compare the similarity between the target repair vector and each candidate repair vector in the historical maintenance database, and determine the similarity between the target repair vector and each candidate repair vector in the historical maintenance database.

[0087] Specifically, vector conversion of repair information may include the following steps: removing stop words from the repair information to obtain processed repair information; performing word segmentation on the processed repair information to obtain repair word groups; and performing vector conversion on the repair word groups based on the vector conversion model to obtain the target repair vector of the repair information.

[0088] In one embodiment of this application, a stop word database can be pre-set. The stop word database is used to filter stop words in the repair information and delete the filtered stop words. The stop word database contains at least one stop word. Stop words refer to function words or non-search words that do not need to be used when searching in the historical repair database, such as words like "can I?", "next", and "follow-up".

[0089] To further explain, word segmentation refers to dividing each character in the repair report information into independent word groups, thus obtaining the repair report word group.

[0090] It should be noted that there are many methods for word segmentation, such as jieba segmentation, ltp segmentation, and ir segmentation. Specifically, the repair information can be segmented using jieba (a word segmentation tool) to obtain the segmented repair phrase; or, the repair information can be segmented using ltp (a Chinese language processing system) to obtain the segmented repair phrase; or, the repair information can be segmented using ir (a word segmentation tool) to obtain the segmented repair phrase.

[0091] To further explain, since the SVM model calculates the distance between the target repair vector and each candidate repair vector in the historical maintenance database, and uses the distance between each vector as the similarity between the target repair vector and each candidate repair vector in the historical maintenance database, the target repair vector of the repair information output by the vector transformation model needs to be able to perform the distance calculation between vectors to ensure that the SVM model can find whether there is a similar repair record corresponding to the repair information in the historical maintenance database.

[0092] Because the one-hot encoding model cannot perform distance calculations between vectors, it is impossible to find similar repair records in the historical repair database based on the vector output by the one-hot encoding model. For example, a phrase converted into a vector using the one-hot encoding model might result in a vector like [0,0,0.....,1,0,0....]. Since only one position in this vector is 1, the dot product of this vector with other vectors will always result in zero, making it impossible to perform distance calculations between vectors.

[0093] Among them, the vector transformation model can be the word2vec (a related model used to generate word vectors) model.

[0094] Step 302: Using the SVM model, determine the similarity between the target repair vector and each candidate repair vector in the historical maintenance database; and based on the similarity, search the historical maintenance database to see if there are similar maintenance records corresponding to the repair information.

[0095] It should be noted that when it is necessary to search the historical maintenance database for similar maintenance records corresponding to the repair information, the following steps can be performed: From each candidate repair vector in the historical maintenance database, find the similarity vector with a similarity greater than the preset similarity threshold; and take the candidate repair records corresponding to each similar repair vector in the historical maintenance database as at least one similar repair record corresponding to the repair information.

[0096] For example, if the historical maintenance database contains three candidate repair vectors, namely candidate repair vector A, candidate repair vector B, and candidate repair vector C, and the similarity between the target repair vector and the three candidate repair vectors is determined to be 0.6, 0.8, and 0.2 respectively using the SVM model, with a preset similarity threshold of 0.5, then the similarity between candidate repair vector A and candidate repair vector B is greater than the preset similarity threshold. Therefore, repair vector A and candidate repair vector B are selected as similar maintenance vectors. Furthermore, the candidate repair record corresponding to repair vector A and the candidate repair record corresponding to candidate repair vector B are at least one similar maintenance record corresponding to the repair information.

[0097] The above-mentioned repair application method determines whether there is a similar repair record corresponding to the repair information in the historical repair database. If there is a similar repair record, it can be used as a repair reference to ensure the effectiveness and efficiency of subsequent repairs of computer system anomalies. If there is no similar repair record, it can remind repair personnel that the anomaly to be repaired is a newly added problem that requires special attention.

[0098] When a problem occurs in a computer system, staff need to contact maintenance personnel promptly to ensure they are aware of the issue. However, due to the heavy workloads of both maintenance and staff, it's difficult for them to communicate simultaneously, thus impacting the repair progress. Therefore, the computer equipment in this embodiment can... Figure 4 The method shown determines the repair information based on the system repair event. Furthermore, when the system repair event is presented as an email, the specific steps include:

[0099] Step 401: If a new repair request email is detected in the target mailbox, it is determined that a system repair event exists.

[0100] The target email address refers to the email address used to uniformly receive repair requests from staff, and the repair requests email refers to emails sent by staff to the target email address that record abnormal computer system problems.

[0101] In one embodiment of this application, when it is necessary to detect whether there are any new repair requests in the target mailbox, a virtual artificial intelligence can be pre-set. This virtual artificial intelligence can be represented as a virtual human account, which logs into the target mailbox and monitors the number of emails in the inbox. If the number of emails in the inbox at the current moment is greater than the number of emails in the inbox at the previous moment, it indicates that a new repair request has been detected in the target mailbox. If the number of emails in the inbox at the current moment is equal to the number of emails in the inbox at the previous moment, it indicates that no new repair requests have been detected in the target mailbox.

[0102] Furthermore, if a new repair request email is detected in the target mailbox, the new repair request email is considered a system repair event.

[0103] Step 402: Determine the repair information based on the newly added repair email corresponding to the system repair event.

[0104] It should be noted that when it is necessary to determine the repair information, the following steps may be included: take a screenshot of the repair email to obtain a screenshot of the repair email; extract the text information from the screenshot of the repair email to obtain the repair information of the repair email.

[0105] The repair information may include, but is not limited to: the initiator of the repair email, the time the repair email was sent, and the body of the repair email.

[0106] The aforementioned repair request method identifies system repair events by detecting whether new repair requests exist in the target email address, ensuring timely discovery of user-reported repair requests and guaranteeing the timeliness of computer system repairs. Furthermore, by taking screenshots of the repair requests and extracting text information from them, the repair information in the emails is obtained, further ensuring the effectiveness and efficiency of subsequent repairs to computer system malfunctions.

[0107] In this embodiment, as Figure 5 As shown, Figure 5 A flowchart of another repair request determination method provided in this application embodiment shows that when it is necessary to determine a repair request to remind repair personnel, the method may specifically include the following steps:

[0108] Step 501: If a system repair event is detected, determine the repair information based on the system repair event.

[0109] Step 502: Remove stop words from the repair report to obtain the processed repair report.

[0110] Step 503: Perform word segmentation on the processed repair information to obtain repair phrases.

[0111] Step 504: Based on the vector transformation model, perform vector transformation on the repair report phrase to obtain the target repair report vector of the repair information.

[0112] Step 505: Using the SVM model, determine the similarity between the target repair vector and each candidate repair vector in the historical maintenance database.

[0113] Step 506: From the candidate repair vectors in the historical repair database, find similar repair vectors with a similarity greater than a preset similarity threshold.

[0114] Step 507: Select the candidate repair record corresponding to each similar repair vector in the historical repair database as at least one similar repair record corresponding to the repair information. If a similar repair record exists, proceed to step 508; otherwise, proceed to step 509.

[0115] Step 508: Based on the repair information and similar repair records, determine the repair request to remind the repair personnel.

[0116] Step 509: Based on the repair information, determine the repair request to remind the repair personnel.

[0117] It should be noted that when maintenance personnel complete the repair work on abnormal problems in computer equipment based on the repair request, this application also includes: receiving the target repair record fed back by the maintenance personnel; and updating the historical repair database according to the target repair vector and target repair record of the repair information.

[0118] The aforementioned repair application method searches the historical repair database for similar repair records based on the repair request information. If similar records are found, a repair application is generated to remind repair personnel. Since staff only need to report the repair event to the system during this process, they do not need to select the corresponding repair personnel based on the anomaly type, nor do they need to explain the anomaly to the repair personnel, thus reducing the time and effort spent by staff in processing repair applications. Furthermore, this application can also search the historical repair database for similar repair records and generate a repair application to remind repair personnel along with the repair request information, ensuring that repair personnel can perform repairs based on similar records, thereby improving repair effectiveness and efficiency.

[0119] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0120] Based on the same inventive concept, this application also provides a maintenance request determination apparatus for implementing the maintenance request determination method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more maintenance request determination apparatus embodiments provided below can be found in the limitations of the maintenance request determination method described above, and will not be repeated here.

[0121] In one embodiment, such as Figure 6 As shown, a repair request determination device is provided, comprising: a first determination module 10, a search module 20, and a second determination module 30, wherein:

[0122] The first determining module 10 is used to determine the repair information based on the system repair event if a system repair event is detected.

[0123] The search module 20 is used to search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information using a support vector machine (SVM) model.

[0124] The second determining module 30 is used to determine, if present, a repair request to remind repair personnel based on the repair information and similar repair records.

[0125] The aforementioned repair request device searches the historical repair database for similar repair records based on the repair request information. If similar records are found, a repair request is generated to remind repair personnel. Since staff only need to report the repair event to the system during this process, they do not need to select the corresponding repair personnel based on the type of anomaly, nor do they need to explain the anomaly to the repair personnel, thus reducing the time and effort spent by staff in processing repair requests. Furthermore, this application can also search the historical repair database for similar repair records and generate a repair request to remind repair personnel along with the repair request information, ensuring that repair personnel can perform repairs based on similar records, thereby improving repair effectiveness and efficiency.

[0126] In one embodiment, such as Figure 7 As shown, a repair request determining device is provided. The lookup module 20 in this device includes a conversion unit 21 and a first determining unit 22, wherein:

[0127] The conversion unit 21 is used to perform vector conversion on the repair information to obtain the target repair vector of the repair information.

[0128] The first determining unit 22 is used to determine the similarity between the target repair vector and each candidate repair vector in the historical maintenance database through an SVM model; and based on the similarity, to search whether there is a similar maintenance record corresponding to the repair information in the historical maintenance database.

[0129] In one embodiment, such as Figure 8 As shown, a repair request determination device is provided. The first determination unit 22 of this device includes: a search subunit 221 and a determination subunit 222, wherein:

[0130] The search subunit 221 is used to search for similar repair vectors with a similarity greater than a preset similarity threshold from each candidate repair vector in the historical repair database.

[0131] The subunit 222 is used to select the candidate repair record corresponding to each similar repair vector in the historical repair database as at least one similar repair record corresponding to the repair information.

[0132] In one embodiment, such as Figure 9As shown, a repair request determination apparatus is provided. The conversion unit 21 in this apparatus includes: a removal subunit 211, a processing subunit 212, and a conversion subunit 213, wherein:

[0133] The removal subunit 211 is used to remove stop words from the repair information to obtain the processed repair information.

[0134] The word segmentation subunit 212 is used to segment the processed repair information into word groups.

[0135] The transformation subunit 213 is used to perform vector transformation on the repair report phrase based on the vector transformation model to obtain the target repair report vector of the repair information.

[0136] In one embodiment, such as Figure 10 As shown, a maintenance request determining device is provided, which further includes: a receiving module 40 and an updating module 50, wherein:

[0137] The receiving module 40 is used to receive the target maintenance record fed back by the maintenance personnel.

[0138] The update module 50 is used to update the historical maintenance database based on the target repair vector and target maintenance record of the repair information.

[0139] In one embodiment, such as Figure 11 As shown, a repair request determining device is provided. The first determining module 10 of this device includes a second determining unit 11 and a third determining unit 12, wherein:

[0140] The second determining unit 11 is used to determine that a system repair event exists if a new repair request email is detected in the target mailbox.

[0141] The third determining unit 12 is used to determine the repair information based on the newly added repair email corresponding to the system repair event.

[0142] In one embodiment, such as Figure 12 As shown, a repair application determining device is provided. The third determining unit 12 in this device includes: a screenshot subunit 121 and an extraction subunit 122, wherein:

[0143] The screenshot subunit 121 is used to take a screenshot of the repair request email to obtain a screenshot of the repair request email.

[0144] Extraction subunit 122 is used to extract text information from the screenshot of the repair request email to obtain the repair information of the repair request email.

[0145] In one embodiment, such as Figure 13As shown, a maintenance request determining device is provided, which further includes: a third determining module 60, wherein:

[0146] The third determination module 60 is used to determine, based on the repair information, a repair request to remind the repair personnel if the request does not exist.

[0147] The aforementioned repair application determines that each module in the device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0148] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 14 As shown. The computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a repair request determination method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0149] Those skilled in the art will understand that Figure 14 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0151] If a system repair event is detected, the repair information is determined based on the system repair event;

[0152] Using a support vector machine (SVM) model, we search the historical maintenance database to find if there are similar maintenance records corresponding to the reported maintenance information.

[0153] If such a request exists, a repair application will be determined based on the repair information and similar repair records to remind repair personnel.

[0154] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0155] Perform vector transformation on the repair information to obtain the target repair vector;

[0156] The SVM model is used to determine the similarity between the target repair request vector and each candidate repair request vector in the historical maintenance database; and based on the similarity, the database is searched to see if there are similar repair records corresponding to the repair request information.

[0157] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0158] From the candidate repair request vectors in the historical repair database, find similar repair vectors with a similarity greater than a preset similarity threshold;

[0159] The candidate repair record corresponding to each similar repair vector in the historical repair database is taken as at least one similar repair record corresponding to the repair information.

[0160] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0161] Remove stop words from the repair request information to obtain the processed repair request information;

[0162] The processed repair information is segmented into word groups to obtain repair phrases.

[0163] Based on the vector transformation model, the repair request phrases are transformed into vectors to obtain the target repair request vector of the repair information.

[0164] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0165] Receive target repair records from maintenance personnel;

[0166] Update the historical maintenance database based on the target repair vector and target maintenance record of the repair information.

[0167] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0168] If a new repair request email is detected in the target mailbox, it is determined that a system repair event has occurred.

[0169] Accordingly, the repair information is determined based on the system repair event, including:

[0170] Determine the repair information based on the newly added repair email corresponding to the system repair event.

[0171] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0172] Take a screenshot of the repair request email to obtain a screenshot of the repair request email;

[0173] Extract text information from screenshots of repair requests in emails to obtain the repair information.

[0174] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0175] If it does not exist, a repair request will be determined based on the repair information to remind the repair personnel.

[0176] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0177] If a system repair event is detected, the repair information is determined based on the system repair event;

[0178] Using a support vector machine (SVM) model, we search the historical maintenance database to find if there are similar maintenance records corresponding to the reported maintenance information.

[0179] If such a request exists, a repair application will be determined based on the repair information and similar repair records to remind repair personnel.

[0180] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0181] Using a Support Vector Machine (SVM) model, we search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information, including:

[0182] Perform vector transformation on the repair information to obtain the target repair vector;

[0183] The SVM model is used to determine the similarity between the target repair request vector and each candidate repair request vector in the historical maintenance database; and based on the similarity, the database is searched to see if there are similar repair records corresponding to the repair request information.

[0184] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0185] From the candidate repair request vectors in the historical repair database, find similar repair vectors with a similarity greater than a preset similarity threshold;

[0186] The candidate repair record corresponding to each similar repair vector in the historical repair database is taken as at least one similar repair record corresponding to the repair information.

[0187] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0188] Remove stop words from the repair request information to obtain the processed repair request information;

[0189] The processed repair information is segmented into word groups to obtain repair phrases.

[0190] Based on the vector transformation model, the repair request phrases are transformed into vectors to obtain the target repair request vector of the repair information.

[0191] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0192] Receive target repair records from maintenance personnel;

[0193] Update the historical maintenance database based on the target repair vector and target maintenance record of the repair information.

[0194] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0195] If a new repair request email is detected in the target mailbox, it is determined that a system repair event has occurred.

[0196] Accordingly, the repair information is determined based on the system repair event, including:

[0197] Determine the repair information based on the newly added repair email corresponding to the system repair event.

[0198] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0199] Take a screenshot of the repair request email to obtain a screenshot of the repair request email;

[0200] Extract text information from screenshots of repair requests in emails to obtain the repair information.

[0201] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0202] If it does not exist, a repair request will be determined based on the repair information to remind the repair personnel.

[0203] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0204] If a system repair event is detected, the repair information is determined based on the system repair event;

[0205] Using a support vector machine (SVM) model, we search the historical maintenance database to find if there are similar maintenance records corresponding to the reported maintenance information.

[0206] If such a request exists, a repair application will be determined based on the repair information and similar repair records to remind repair personnel.

[0207] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0208] Using a Support Vector Machine (SVM) model, we search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information, including:

[0209] Perform vector transformation on the repair information to obtain the target repair vector;

[0210] The SVM model is used to determine the similarity between the target repair request vector and each candidate repair request vector in the historical maintenance database; and based on the similarity, the database is searched to see if there are similar repair records corresponding to the repair request information.

[0211] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0212] From the candidate repair request vectors in the historical repair database, find similar repair vectors with a similarity greater than a preset similarity threshold;

[0213] The candidate repair record corresponding to each similar repair vector in the historical repair database is taken as at least one similar repair record corresponding to the repair information.

[0214] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0215] Remove stop words from the repair request information to obtain the processed repair request information;

[0216] The processed repair information is segmented into word groups to obtain repair phrases.

[0217] Based on the vector transformation model, the repair request phrases are transformed into vectors to obtain the target repair request vector of the repair information.

[0218] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0219] Receive target repair records from maintenance personnel;

[0220] Update the historical maintenance database based on the target repair vector and target maintenance record of the repair information.

[0221] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0222] If a new repair request email is detected in the target mailbox, it is determined that a system repair event has occurred.

[0223] Accordingly, the repair information is determined based on the system repair event, including:

[0224] Determine the repair information based on the newly added repair email corresponding to the system repair event.

[0225] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0226] Take a screenshot of the repair request email to obtain a screenshot of the repair request email;

[0227] Extract text information from screenshots of repair requests in emails to obtain the repair information.

[0228] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0229] If it does not exist, a repair request will be determined based on the repair information to remind the repair personnel.

[0230] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0231] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0232] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0233] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining a repair request, characterized in that, The method includes: If a new repair request email is detected in the target mailbox, it is determined that a system repair event exists. The repair request email is then taken as a screenshot to obtain a repair request screenshot. Text information is extracted from the repair request screenshot to obtain the repair information of the repair request email. If a repair pop-up window is detected on the system desktop, it is determined that a system repair event exists. The repair pop-up window is then taken as a screenshot to obtain a repair screenshot. The text information of the repair screenshot is then extracted to obtain the repair information of the repair pop-up window. If a repair request SMS is received, it is determined that there is a system repair event. The repair request SMS is then taken as a screenshot. The text information of the repair request SMS is extracted from the screenshot to obtain the repair information of the repair request SMS. The repair information is vectorized to obtain the target repair vector, including: removing stop words from the repair information to obtain the processed repair information; performing word segmentation on the processed repair information to obtain repair word groups; and performing vector transformation on the repair word groups based on the vector transformation model to obtain the target repair vector; wherein, the repair information includes the system error time and the system error address; Using a Support Vector Machine (SVM) model, the system searches the historical maintenance database for similar maintenance records corresponding to the reported maintenance information. This includes: determining the similarity between the target reported maintenance vector and each candidate reported maintenance vector in the historical maintenance database based on the SVM model, where the distance between each vector is the similarity between the target reported maintenance vector and each candidate reported maintenance vector in the historical maintenance database; and determining similar maintenance vectors with a similarity greater than a preset similarity threshold based on the relationship between the similarity between each candidate reported maintenance vector in the historical maintenance database and the target reported maintenance vector. If a similar repair record exists corresponding to the repair request, a repair application to remind the repair personnel is determined based on the repair request and the similar repair record; if no similar repair record exists in the historical repair database, the repair application to remind the repair personnel contains only the repair request.

2. The method of claim 1, wherein, The method further includes: Receive target repair records from maintenance personnel; Update the historical repair database based on the target repair vector and target repair record of the repair information.

3. A repair application determining apparatus characterized by comprising: The device includes: The first determining module is used to determine that a system repair event exists if a new repair request email is detected in the target mailbox, to take a screenshot of the repair request email to obtain a repair screenshot of the repair request email, and to extract text information from the repair screenshot of the repair request email to obtain the repair information of the repair request email. If a repair pop-up window is detected on the system desktop, it is determined that a system repair event exists. The repair pop-up window is then taken as a screenshot to obtain a repair screenshot. The text information of the repair screenshot is then extracted to obtain the repair information of the repair pop-up window. If a repair request SMS is received, it is determined that there is a system repair event. The repair request SMS is then taken as a screenshot. The text information of the repair request SMS is extracted from the screenshot to obtain the repair information of the repair request SMS. The repair information is vectorized to obtain the target repair vector, including: removing stop words from the repair information to obtain the processed repair information; performing word segmentation on the processed repair information to obtain repair word groups; and performing vector transformation on the repair word groups based on the vector transformation model to obtain the target repair vector; wherein, the repair information includes the system error time and the system error address; The search module is used to search the historical maintenance database for similar maintenance records corresponding to the reported maintenance information using a support vector machine (SVM) model. This includes: determining the similarity between the target reported maintenance vector and each candidate reported maintenance vector in the historical maintenance database based on the SVM model, where the distance between each vector is the similarity between the target reported maintenance vector and each candidate reported maintenance vector in the historical maintenance database; and determining similar maintenance vectors with a similarity greater than a preset similarity threshold based on the relationship between the similarity between each candidate reported maintenance vector in the historical maintenance database and the target reported maintenance vector and a similarity threshold. The second determining module is used to determine a repair application to remind the repair personnel based on the repair information and the similar repair record if a similar repair record corresponding to the repair information exists; if no similar repair record corresponding to the repair information exists in the historical repair database, the repair application to remind the repair personnel only contains the repair information.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

6. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

Images