Work order management method and device based on AI analysis, equipment and storage medium

Abstract

The invention provides a work order management method and device based on AI analysis, equipment and a storage medium, and the method comprises the steps: creating a first work order based on work order description information and a first work order type, and determining a first property item line based on the first work order type; first description information and second description information are obtained through analysis of the first NLP model, and a second property item line is determined according to the second description information; and analyzing a first emotion category and a second emotion category based on the second NLP model, determining a corresponding first target label and a corresponding second target label, determining a first account based on the first target label and then allocating a first work order, and determining a second account based on the second target label and then creating and allocating a second work order. The emotion category can be analyzed from the description information through the second NLP model, accurate matching of the response account is realized according to the target label corresponding to the emotion category, the second work order can be automatically created and allocated for allocation, manual work order transfer is not needed, and the work order management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a work order management method, device, equipment, and storage medium based on AI analysis. Background Art

[0002] Property work orders are important tools used by property management companies to record, track and handle various work items. Common property work orders include complaint work orders and maintenance work orders initiated by owners, as well as various internal work orders initiated by managers according to the approval process. In property management companies, due to the large number of work order types and managers, in order to improve management efficiency, it is necessary to quickly determine the respondent for each work order.

[0003] When creating a property work order, you usually select the work order type of the property work order. In related technologies, artificial intelligence technology can be used to analyze the work order type to determine the responding personnel and realize the automatic allocation of work orders. However, even for the same type of property work orders, there are usually multiple managers who can respond. If the initiator of the work order has certain requirements for the responding personnel, for example, a maintenance work order may require a highly professional maintenance personnel, or a maintenance personnel with a fast response speed. For example, an internal work order may require skipping multiple internal process nodes. According to related technologies, a responding personnel is randomly assigned based on the identification of the work order type. The responding personnel transfer the work order or create a new work order according to the needs of the initiator. Manual intervention is still required in the work order management process, and the management efficiency is low. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a work order management method, device, equipment, and storage medium based on AI analysis, which can realize accurate management of property work orders through analysis of AI models and improve the management efficiency of property work orders.

[0005] In a first aspect, an embodiment of the present invention provides a work order management method based on AI analysis, which is applied to a work order management system, wherein the work order management system is preset with a first NLP model, a second NLP model, and a plurality of available property lines, each of the available property lines is associated with a plurality of available accounts and a plurality of optional work order types, each of the available accounts is associated with a plurality of response capability tags, and the method comprises:

[0006] Creating a first work order based on the work order description information and the first work order type, and determining a first property line based on the first work order type, wherein the work order description information is used to indicate a root cause for creating the first work order;

[0007] Inputting the work order description information and the available property line into the first NLP model, and when the first NLP model extracts first description information and at least one second description information from the work order description information, obtaining second property lines identified based on each of the second description information, wherein the first description information can be used to identify the first property line;

[0008] identifying a first emotion category from the first description information based on the second NLP model, and identifying a second emotion category from the second description information;

[0009] Determine at least one first target tag based on the first emotion category and a first mapping table, determine a first account based on the first target tag and the first property line, and assign the first work order to the first account, wherein the first mapping table records a mapping relationship between optional emotion categories and the responsiveness tags;

[0010] Based on any of the second description information, at least one second target tag is determined based on the corresponding second emotion category and the first mapping table, a second account is determined based on the second target tag and the second property line, and a second work order is created and assigned to the second account.

[0011] According to some embodiments of the present invention, after inputting the work order description information into the first NLP model, the method further includes:

[0012] When the first NLP model outputs the first property line and at least one of the second property lines, obtaining a recognition log of the first NLP model based on the work order description information;

[0013] Based on the identification log, the identification participles used to identify the first property line are combined into the first description information, and the identification participles used to identify the second property line are combined into the second description information, wherein the identification participles are obtained by splitting based on the work order description information.

[0014] According to some embodiments of the present invention, each of the optional work order types is pre-associated with at least one preset operation word, and creating a second work order and allocating it to the second account includes:

[0015] Determine the optional work order type of the second property line as a candidate work order type;

[0016] Extracting at least one description operation word from the second description information, and determining a second work order type from the plurality of candidate work order types based on the description operation word, wherein the description operation word is semantically identical or semantically similar to any of the preset operation words of the second work order type;

[0017] When the second description information records a historical work order, determining the available account to which the historical work order is assigned as a third account, and determining the third account as a work order object;

[0018] The second work order is constructed based on the second work order type and the third account, and the second work order is assigned to the second account.

[0019] According to some embodiments of the present invention, after allocating the second work order to the second account, the method further includes:

[0020] When the second emotion category is used to indicate a negative emotion, determining a scoring base based on the second emotion category and a preset second mapping table, wherein the second mapping table records a mapping relationship between the optional emotion category and the optional base;

[0021] After the first work order is completed, obtaining first evaluation information based on feedback of the first work order, and inputting the first evaluation information into the second NLP model to determine a third emotion category;

[0022] When the third emotion category is used to indicate a positive emotion, a target assessment score is determined based on a preset correction coefficient and the score base;

[0023] Apply the target assessment score to the third account.

[0024] According to some embodiments of the present invention, the optional emotion category is pre-associated with a response priority, determining a first account based on the first target tag and the first property line, and assigning the first work order to the first account includes:

[0025] When a plurality of candidate accounts are matched based on the first target tag and the first property line, a work order queue of each of the candidate accounts is obtained, wherein the work order queue includes a plurality of work orders to be processed that are arranged in order, and each of the work orders to be processed is associated with a corresponding fourth emotion category;

[0026] traversing each of the work order queues based on the first emotion category;

[0027] When the first emotion category matches the same fourth emotion category, the next one of the to-be-processed work orders corresponding to the matched fourth emotion category is determined as the target ranking;

[0028] When the first emotion category does not match the same fourth emotion category, determining the response priorities corresponding to the respective fourth emotion categories, and determining the target ranking of the first work order based on the response priorities corresponding to the first emotion category;

[0029] The candidate account corresponding to the frontmost target ranking is determined as the first account, and the first work order is inserted into the work order queue of the first account based on the target ranking.

[0030] According to some embodiments of the present invention, after creating the second work order and assigning it to the second account, the method further includes:

[0031] Determine a first capability tag and a second capability tag from the plurality of response capability tags associated with the first account, and determine a third capability tag and a fourth capability tag from the plurality of response capability tags associated with the second account, wherein the first capability tag and the third capability tag are used to indicate business capabilities, and the second capability tag and the fourth capability tag are used to indicate work order acceptance capabilities;

[0032] updating the second capability tag based on the updated work order queue of the first account, and updating the fourth capability tag based on the updated work order queue of the second account;

[0033] Obtaining second evaluation information for the second work order feedback, and inputting the second evaluation information into the second NLP model to determine a fifth emotion category;

[0034] Determine at least one third target tag based on the third emotion category and the first mapping table, and determine at least one fourth target tag based on the fifth emotion category and the first mapping table;

[0035] The first capability tag is updated based on the third target tag, and the third capability tag is updated based on the fourth target tag.

[0036] According to some embodiments of the present invention, before allocating the first work order to the first account, the method further includes:

[0037] Determining a first work order process based on the first work order type, wherein the first work order process includes a plurality of first process nodes;

[0038] Inputting the first description information and each of the first process nodes into the first NLP model, and identifying the target node corresponding to the first description information through the first NLP model;

[0039] The first work order is configured based on the target node.

[0040] In a second aspect, an embodiment of the present invention provides a work order management device based on AI analysis, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the work order management method based on AI analysis as described in the first aspect above.

[0041] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a work order management device based on AI analysis as described in the second aspect above.

[0042] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the work order management method based on AI analysis as described in the first aspect above.

[0043] The work order management method based on AI analysis according to an embodiment of the present invention has at least the following beneficial effects: creating a first work order based on work order description information and a first work order type, determining a first property line based on the first work order type, wherein the work order description information is used to indicate a root cause for the creation of the first work order; inputting the work order description information and the available property lines into the first NLP model, when the first NLP model extracts the first description information and at least one second description information from the work order description information, obtaining second property lines identified based on each of the second description information, wherein the first description information can be used to identify the first property line; based on the second NLP model The method comprises the following steps: identifying a first emotion category from the first description information, and identifying a second emotion category from the second description information; determining at least one first target tag based on the first emotion category and the first mapping table, determining a first account based on the first target tag and the first property line, and assigning the first work order to the first account, wherein the first mapping table records the mapping relationship between the optional emotion category and the responsiveness tag; based on any of the second description information, determining at least one second target tag based on the corresponding second emotion category and the first mapping table, determining a second account based on the second target tag and the second property line, creating a second work order and assigning it to the second account. According to the technical solution of the embodiment of the present invention, it is possible to obtain at least one second description information by analyzing the work order description information through the first NLP model, analyze the emotion category from the description information through the second NLP model, and determine the target tag that meets the emotion category, realize accurate matching of the account through the target tag, and automatically create a second work order for assignment after identifying the second account, without the need for manual work order transfer, thereby improving the work order management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a schematic diagram of a work order management system provided by an embodiment of the present invention;

[0045] Figure 2 is a flow chart of a work order management method based on AI analysis provided by another embodiment of the present invention;

[0046] Figure 3 is a complete flow chart of a work order management method based on AI analysis provided by another embodiment of the present invention;

[0047] Figure 4 It is a structural diagram of a work order management device based on AI analysis provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0048] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0049] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0050] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0051] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0052] The following is an explanation of the professional terms that appear in this application:

[0053] Property line: usually used in property management or related industries. It refers to a department or business area within a property company that is divided according to functions or businesses and is responsible for specific property management matters. The property line covers many aspects of property management, including but not limited to customer service, facility management, safety management, environmental maintenance, and financial management.

[0054] Natural Language Processing (NLP) model: NLP model is an important direction in the field of computer science and artificial intelligence. It studies various theories and methods that can achieve effective communication between humans and computers using natural language. Simply put, the goal of NLP is to enable computers to "understand" human language, understand its meaning, and respond accordingly or perform specific tasks.

[0055] Embodiments of the present invention provide a work order management method, apparatus, device, and storage medium based on AI analysis, wherein the work order management method based on AI analysis includes: creating a first work order based on work order description information and a first work order type, and determining a first property line based on the first work order type, wherein the work order description information is used to indicate a root cause of creation of the first work order; inputting the work order description information and the available property line into the first NLP model, and when the first NLP model extracts the first description information and at least one second description information from the work order description information, obtaining second property lines identified based on each of the second description information, wherein the first description information can be used to identify the first property line; Based on the second NLP model, a first emotion category is identified from the first description information, and a second emotion category is identified from the second description information; at least one first target tag is determined based on the first emotion category and the first mapping table, a first account is determined based on the first target tag and the first property line, and the first work order is assigned to the first account, wherein the first mapping table records the mapping relationship between the optional emotion category and the responsiveness tag; based on any second description information, at least one second target tag is determined based on the corresponding second emotion category and the first mapping table, a second account is determined based on the second target tag and the second property line, a second work order is created and assigned to the second account. According to the technical solution of the embodiment of the present invention, at least one second description information can be obtained by analyzing the work order description information through the first NLP model, the emotion category can be analyzed from the description information through the second NLP model, and the target tag that meets the emotion category can be determined, and the accurate matching of the account can be achieved through the target tag, and after the second account is identified, a second work order is automatically created for assignment, without the need for manual work order transfer, thereby improving the work order management efficiency.

[0056] First, refer to Figure 1 , Figure 1 This is a schematic diagram of a work order management system provided in an embodiment of the present invention. The work order management system 10 can be communicatively connected with a user terminal 20. The user terminal 20 can be an owner's mobile phone, a manager's office computer, etc. The owner's mobile phone can initiate a work order through the property APP, and the office computer can directly access the work order management system 10 to initiate a work order. This embodiment does not limit the initiating terminal of the first work order.

[0057] The following is based on the Figure 1 The work order management system shown further illustrates the technical solution of the embodiment of the present invention.

[0058] Refer to 1 and Figure 2 , Figure 2 A flowchart of a work order management method based on AI analysis provided in an embodiment of the present invention. The work order management system of this embodiment is preset with a first NLP model, a second NLP model and multiple available property lines, each available property line is associated with multiple available accounts and multiple optional work order types, each available account is associated with multiple response capability tags, and the work order management method based on AI analysis includes but is not limited to the following steps:

[0059] S10, creating a first work order based on the work order description information and the first work order type, and determining a first property line based on the first work order type, wherein the work order description information is used to indicate a root cause for creating the first work order;

[0060] S20, inputting the work order description information and the available property lines into the first NLP model, when the first NLP model extracts the first description information and at least one second description information from the work order description information, obtaining the second property lines respectively identified based on the respective second description information, wherein the first description information can be used to identify the first property line;

[0061] S30, identifying a first emotion category from the first description information and identifying a second emotion category from the second description information based on a second NLP model;

[0062] S40, determining at least one first target tag based on the first emotion category and the first mapping table, determining a first account based on the first target tag and the first property line, and assigning the first work order to the first account, wherein the first mapping table records a mapping relationship between optional emotion categories and responsiveness tags;

[0063] S50, based on any second description information, determine at least one second target tag based on the corresponding second emotion category and the first mapping table, determine a second account based on the second target tag and the second property line, create a second work order and assign it to the second account.

[0064] It should be noted that the available property lines are various lines of the property management company, such as the cleaning line, maintenance line, customer service line, financial line, etc. Work orders initiated for cleaning issues can be assigned to the cleaning line for response. For example, if there is a hygiene problem in a certain area within the community, a work order initiated for damage to property equipment can be assigned to the maintenance line for response.

[0065] It should be noted that the available accounts can be the accounts of managers of each line, and each available account corresponds to a manager who can respond to property work orders. Each available property line can include multiple available accounts, and each available account can correspond to multiple available property lines. For example, senior managers can be associated with the cleaning line and the maintenance line, and when the owner initiates a complaint about cleaning and maintenance, the senior manager will handle it. That is, the available property lines and available accounts in this embodiment can be a many-to-many relationship, which will not be repeated later.

[0066] It should be noted that the optional work order types can be pre-set, such as complaint work orders, maintenance work orders, internal process work orders, etc. Each optional work order type corresponds to only one optional property line, ensuring that the first property line can be matched according to the first work order type. For example, the complaint work order corresponds to the customer service line, the maintenance work order corresponds to the maintenance line, and the internal process work order can determine the corresponding optional property line according to the specific process, for example, the budget approval work order initiated corresponds to the financial line.

[0067] It should be noted that the responsiveness tag is used to characterize the responsiveness of the available account, for example Figure 1 As shown, the response capability label may include strong professional ability, quick response, good service attitude, etc., and may be pre-set according to the actual situation of each available account. For example, a label of strong professional ability may be added to the available account of a senior maintenance employee. The response capability label of each available account may also be dynamically adjusted. For example, when an available account has no work orders being processed, a label of quick response is automatically added to it to indicate that the available account can respond to work orders quickly. The specific response capability label may be set according to the actual situation and is not limited here.

[0068] It should be noted that if Figure 1As shown, when creating the first work order, a visualization page can be constructed on the user terminal, and the type options can be displayed in the visualization page, and the optional work order types can be used as optional options of the type options. Of course, since the optional work order types involve internal processes and owner processes, after logging into the user account on the user terminal, the optional work order types can be screened first, and the optional work order types that the user account can select can be filled into the type options. In addition, the visualization interface can also display an input box, and the user can enter the work order description information in the input box, and prompt information can be displayed in the input box to prompt the user to describe the root cause of the creation, such as displaying "Please enter the reason for creating the work order" in the input box, and stopping displaying the prompt information after the user starts to enter, and using the text entered by the user in the input box as the work order description information.

[0069] It should be noted that the work order description information is used to indicate the root cause of the creation of the work order. The user can describe it in any text, such as "filing a complaint about xx incident", "requesting repair for damaged xx equipment", "improper handling of xx work order, complaining to relevant personnel, requiring more professional personnel to handle it", "applying for payment from the budget obtained from the approval of xx work order", etc. This embodiment does not limit the specific content of the work order description information, as long as it can characterize the root cause of the creation of the work order and the user's intention.

[0070] It should be noted that if Figure 1 As shown, after selecting the first work order type and inputting the work order description information, a first work order is created. The first work order can be created by the user terminal and then sent to the work order management system, or the work order management system can create the first work order after obtaining the above information. According to the description of the above embodiment, each optional work order type corresponds to only one optional property line. After the user selects the first work order type, the optional property line corresponding to the first work order type is determined as the first property line.

[0071] For example, taking the example of a work order management system with customer service, cleaning, maintenance, finance and human resources lines, the optional work order types corresponding to the customer service line include complaint work orders and consultation work orders, the optional work order types corresponding to the cleaning line include cleaning work orders, the optional work order types corresponding to the maintenance line include maintenance work orders, equipment maintenance work orders and inspection work orders, the optional work order types corresponding to the finance line include budget approval work orders, expense reimbursement work orders and compensation expenditure work orders, and the optional work order types corresponding to the human resources line include personnel recruitment work orders and personnel appointment work orders. Figure 1 As shown, the first work order type selected in the user terminal 20 is a complaint work order, and the customer service line corresponding to the complaint work order is determined as the first property line. If the first work order type is a maintenance work order, the maintenance line corresponding to the maintenance work order is determined as the first property line, and so on.

[0072] It should be noted that the first NLP model of this embodiment can use the optional property line as the classification basis to identify the work order description information to obtain multiple property lines. This embodiment does not involve the improvement of the NLP model. The first NLP model and the second NLP model are pre-trained models. Those skilled in the art are familiar with how to configure the NLP model, which will not be repeated later.

[0073] It should be noted that if the first NLP model only identifies a first property line, it can be determined that the first work order is a newly created work order and there are no other related work orders, such as no further complaints due to improper handling of the previous work order, or it is not a secondary approval initiated based on a previous process work order, etc. In this case, the work order description information is directly input into the second NLP model for emotion recognition, and the first target label is determined and then assigned. If the first NLP model identifies a second property line other than the first property line, step S50 is executed to create a second work order for each second property line. It is worth noting that if the first NLP model identifies the first property line multiple times, for example, the word "complaint" is mentioned multiple times in the work order description information, thereby identifying multiple customer service lines, this embodiment does not need to create multiple work orders, but instead uses the subsequent second NLP model to filter out the corresponding first account from the customer service line when determining the emotion category. Therefore, the first property line and the second property line in this embodiment are different optional property lines, and the second property line is an optional property line other than the first property line, that is, there can be multiple second property lines, and each second property line can be different.

[0074] Exemplarily, referring to the various examples of optional property lines mentioned above, when the first work order type selects a complaint work order, the first property line is the customer service line, and the work order description information is "xx equipment has not been properly repaired for a long time, complain to the maintenance personnel, and continue repairs", and the second property line identified by the first NLP model is the maintenance line.

[0075] It should be noted that when the first NLP model is identifying, it usually splits the input text into multiple participles and combines them to identify the category to which each group of associated participles belongs. This embodiment uses the optional property line as the classification basis. When part of the text of the work order description information is used to identify the second property line, the corresponding text is determined as the second description text. Since the work order description information will definitely identify the first property line, after obtaining the output result of the first NLP model, this embodiment excludes the first property line and uses the remaining identified optional property lines as the second property line. For example, in the above example, the customer service line is identified through "complaints". Since the customer service line has been determined as the first property line by the first work order type, it will not be counted. The maintenance line is identified through "maintenance", and the maintenance line is determined as the second property line.

[0076] It should be noted that if Figure 1 As shown, after identifying the second property line, although this embodiment does not obtain the first property line identified by the first NLP model, the first description information and the second description information can be obtained according to the work order description information, and the text that can identify the first property line is determined as the first description information, and the text that identifies the second property line is determined as the second description information. It is worth noting that this embodiment does not divide the work order description information into the first description information and the second description information. There can be repeated texts between the first description information and the second description information. For example, in the above example, the first description information can be "xx equipment has been poorly maintained for a long time, complain to the maintenance personnel", and the second description information can be "xx equipment has been poorly maintained for a long time, continue to maintain". Of course, if multiple second property lines are identified, the corresponding second description information can be obtained respectively. For example, in the above example, if the work order description information is "xx equipment has been poorly maintained for a long time, complain to the maintenance personnel, continue to maintain, and claim related expenses", in addition to the maintenance line being determined as the second property line, the financial line can also be identified as the second property line based on the second description information "xx equipment has been poorly maintained for a long time, claim related expenses".

[0077] It should be noted that if Figure 1 As shown, in this embodiment, the first description information and the second description information are input into the second NLP model for emotion recognition. Those skilled in the art are familiar with how to use the NLP model for emotion classification, and the specific algorithm will not be described in detail here. The optional emotion categories of this embodiment can be common emotion categories in the property field, such as "anxious", "angry", "peaceful", "picky", etc., which can characterize the emotions of the owner or manager when initiating a work order. In this embodiment, the mapping relationship of the response capability labels corresponding to each optional emotion category is recorded in the first mapping table, so as to determine which responding personnel with which capabilities are required to respond to each emotion, so as to achieve accurate matching of the work order. Therefore, after determining the first emotion category and the second emotion category, this embodiment determines the corresponding first target label and second target label according to the first mapping table, and determines the first account from each optional account of the first property line according to the first target label. The number of first target labels can be multiple, and the first account can include all first target labels, and the same applies to the second account.

[0078] For example, Figure 1As shown, continuing to refer to the above example, when the first description information is "xx equipment has been poorly maintained for a long time, and complaints are made to maintenance personnel", the first emotion category can be determined to be "losing patience", and the first target label is determined to be "strong professional ability" and "quick response" according to the first mapping table. An optional account with both of the above first target labels is selected from the customer service line as the first account. When the number of first accounts is multiple, any one can be selected, and no further restrictions are made here. Similarly, the second emotion category can also include multiple ones. For example, when the second description information is "xx equipment has been poorly maintained for a long time, and claims are made for related expenses", the second emotion category can be determined to be "angry" and "losing patience", and the corresponding second target labels are "strong professional ability", "quick response" and "good service attitude". The corresponding second account can be matched according to the above three labels.

[0079] It should be noted that if Figure 1 As shown, since the first work order initiated by the user is a work order, but requires multiple lines to respond, it can be determined that multiple work orders are needed to solve the problem raised by the user. Therefore, this embodiment automatically constructs a second work order for each second property line, for example, a maintenance work order is constructed for the above-mentioned maintenance line, and a claim work order is constructed for the above-mentioned financial line. The user only needs to input information once, and the work order management system automatically analyzes the user's actual needs through the NLP model, thereby automatically adding work orders, and there is no need for work order responders to perform manual operations, thereby effectively improving the work order processing efficiency; at the same time, the user's emotions are judged through the work order description information, and the response capability label of the management personnel who respond to the first work order or the second work order is determined according to the emotion category, and the accurate matching of the responding personnel is achieved through label recognition from the corresponding property line, effectively improving the accuracy of the work order response.

[0080] In addition, in one embodiment, referring to Figure 3 In step S20, after the work order description information is input into the first NLP model, the following steps are also included but not limited to:

[0081] S21, when the first NLP model outputs the first property line and at least one second property line, obtaining a recognition log of the first NLP model based on the work order description information;

[0082] S22, based on the recognition log, combining the recognition participles used to identify the first property line into the first description information, and combining the recognition participles used to identify the second property line into the second description information, wherein the recognition participles are obtained by splitting based on the work order description information.

[0083] It should be noted that this embodiment needs to utilize the recognition process of the first NLP model to obtain first descriptive information related to the first property line and second descriptive information related to the second property line. The first descriptive information is used as the basis for the subsequent identification of the first emotion category by the first property line, and the second descriptive information is used as the basis for the identification of the second emotion category by the second property line. Therefore, it is necessary to ensure that the first descriptive information is only associated with the first property line as much as possible, and the second descriptive information is only associated with the second property line, so as to avoid misidentification of emotions.

[0084] Exemplarily, when the work order description information is "The work order creator filled in a lot of incorrect information, resulting in the budget approval work order being rejected, and a complaint was made to the previous work order creator, re-approval was initiated, and a request was made to expedite the processing", and the first description information is "The work order creator filled in a lot of incorrect information, resulting in the budget approval work order being rejected, and a complaint was made to the previous work order creator", it can be determined that the first emotion category is anger. If the first description information is not accurately extracted, and the extracted first description information is "re-approval, request to expedite the processing", then the corresponding first emotion category is anxiety. Therefore, the first description information and the second description information of this embodiment can have a greater impact on the recognition accuracy of the emotion category, and the accuracy of the extraction needs to be ensured.

[0085] It should be noted that in order to extract accurate first description information and second description information, after inputting the work order description information into the first NLP model, this embodiment uses the output result to reversely query the recognition log of the first NLP model after obtaining the output result of the first NLP model (i.e., each property line). Taking the first property line as an example, the recognition log is queried based on the recognition result of the first property line, and the recognition participle used to obtain the recognition result is determined from the recognition log, and the corresponding recognition participle is used to form the first description information. The second description information is similar, ensuring that the text of the first description information or the second description information is related to the identified property line to ensure the accuracy of the recognition.

[0086] Exemplarily, continuing to refer to the above-mentioned work order description information, taking the first work order type as budget approval, the corresponding first property line is the finance line, and the first NLP model is used to identify that the text of the finance line is "The work order creator filled in a lot of incorrect information, resulting in the budget approval work order being rejected, and the approval was re-initiated, requesting to speed up the processing." Similarly, the second property line is the customer service line, and the corresponding second description information is "The work order creator filled in a lot of incorrect information, resulting in the budget approval work order being rejected, and a complaint was made to the previous work order creator" to ensure the accuracy of the description information.

[0087] In addition, in one embodiment, referring to Figure 3Each optional work order type is pre-associated with at least one preset operation word. In step S50, a second work order is created and assigned to a second account, including but not limited to the following steps:

[0088] S51, determining the optional work order type of the second property line as the candidate work order type;

[0089] S52, extracting at least one description operation word from the second description information, and determining a second work order type from a plurality of candidate work order types based on the description operation word, wherein the description operation word is semantically identical or semantically similar to any preset operation word of the second work order type;

[0090] S53, when the second description information records a historical work order, determining the available account to which the historical work order is assigned as a third account, and determining the third account as a work order object;

[0091] S54, constructing a second work order based on the second work order type and the third account, and assigning the second work order to the second account.

[0092] It should be noted that, according to the description of the above embodiment, each optional property line is provided with a unique optional work order type. In order to construct a second work order, it is necessary to identify the optional work order type to which the second work order belongs. This embodiment configures a preset operation word for each optional work order type, and the work order type can be preliminarily screened through the preset operation word. After determining the second property line, all optional work order types associated with the second property line are first determined as candidate work order types to narrow the selection range of work order types.

[0093] It should be noted that after determining the second description information, description operation words can be extracted from the second description information by semantic recognition, and the description operation words can be preset operation words associated with the candidate work order type, or synonyms of the preset operation words. Exemplarily, referring to the example of the second description information being "xx equipment has been poorly maintained for a long time, continue to maintain", the description operation words are usually verbs in the text, and in this example, it is maintenance, and the preset operation words that can be paired can include "repair", "maintenance", "repair" and other identical or similar words.

[0094] It should be noted that after determining the type of the second work order, since the second work order is a derivative work order of the first work order, it is necessary to determine whether the second work order has an associated work order object. If the first work order is a secondary operation initiated based on a historical work order, the available account corresponding to the historical work order is the third account of this embodiment. The third account is determined as the work order object, and a new work order is constructed as the second work order according to the second work order type, and the third account is used as the work order object of the second work order. The second account can conduct relevant assessments on the third account based on the second work order, such as assessing the customer service personnel who were complained about in the complaint work order, or assessing the maintenance personnel who handled the previous maintenance work order improperly.

[0095] In addition, in one embodiment, referring to Figure 3 After executing step S54, the following steps are also included but not limited to:

[0096] S55, when the second emotion category is used to indicate negative emotion, determining a scoring base based on the second emotion category and a preset second mapping table, wherein the second mapping table records a mapping relationship between optional emotion categories and optional bases;

[0097] S56, after the first work order is completed, obtaining first evaluation information based on feedback of the first work order, and inputting the first evaluation information into the second NLP model to determine a third emotion category;

[0098] S57, when the third emotion category is used to indicate a positive emotion, determining a target assessment score based on a preset correction coefficient and a score base, and the correction coefficient is less than 1;

[0099] S58, applying the target assessment score to the third account.

[0100] It should be noted that when the second emotion category is used to indicate negative emotions, such as anger, rage, and anxiety, it can be determined that the third account handled the historical work order improperly, and the third account needs to be assessed. This embodiment records the optional base corresponding to each optional emotion category through the second mapping table, and determines a scoring base for subsequent scoring through the second emotion category. For example, when the second emotion category is loss of patience, the corresponding optional base is 80 points, and when the second emotion category is anger, the corresponding optional base is 100 points. Since the scoring base is used for punitive assessment of the third account, the target assessment score can be used as a subtraction, such as subtracting the target assessment score from the monthly assessment score of the third account. Therefore, the larger the target assessment score, the higher the degree of punishment for the third account. A higher optional base can be set in the second mapping table for stronger negative emotions.

[0101] It should be noted that the first work order is an associated work order of the historical work order, that is, the matters handled by the first work order are related to the historical work order. For example, after the approval work order is re-initiated due to incorrect information, the first work order is the re-initiated approval work order, and the historical work order is the approval work order with the last incorrect information filled in. For another example, when the equipment repair is unsuccessful and requires continued repair, the first work order is the re-initiated repair work order, and the historical work order is the repair work order initiated last time. The processing of the first work order can affect the emotions of the user who initiated the work order. If the first evaluation information obtained by the first work order is a positive evaluation, the score base can be lowered to the target assessment score using a correction coefficient with a value less than 1. The description of the above embodiment can be referred to for determining the third emotion category by the second NLP model, and will not be repeated here.

[0102] In addition, in one embodiment, referring to Figure 3 , the optional emotion category is pre-associated with a response priority, in step S40, determining a first account based on the first target tag and the first property line, and assigning the first work order to the first account, including:

[0103] S41, when multiple candidate accounts are matched based on the first target tag and the first property line, a work order queue of each candidate account is obtained, wherein the work order queue includes multiple work orders to be processed that are arranged in order, and each work order to be processed is associated with a corresponding fourth emotion category;

[0104] S42, traversing each work order queue based on the first emotion category;

[0105] S43, when the first emotion category matches the same fourth emotion category, the next one of the to-be-processed work orders corresponding to the matched fourth emotion category is determined as the target sorting;

[0106] S44, when the first emotion category does not match the same fourth emotion category, determining the response priority corresponding to each fourth emotion category, and determining the target ranking of the first work order based on the response priority corresponding to the first emotion category;

[0107] S45, determining the candidate account corresponding to the frontmost target ranking as the first account, and inserting the first work order into the work order queue of the first account based on the target ranking.

[0108] It should be noted that the first account includes all the first target tags, and when there are many optional accounts in the first property line, it is likely that multiple candidate accounts will be matched based on the first target tag. This embodiment dynamically allocates the first work order in each work order queue according to the work order load and the urgency of the work order of each candidate account, determines the target ranking of the first work order in each work order queue, and then inserts the first work order into the work order queue with the highest target ranking, to ensure that the first work order can be responded to as soon as possible.

[0109] It should be noted that each to-be-processed work order in the work order queue is obtained based on the method of the above embodiment, so the fourth emotion category is equivalent to the above first emotion category, which will not be repeated later.

[0110] It should be noted that since the emotion category represents the emotion of the user who initiated the work order, the stronger the corresponding emotion category, the higher the urgency of the work order, and the more it needs to be prioritized to ensure user experience. After determining the first emotion category, the work order queues of each candidate account are traversed based on the first emotion category. When the work order queue includes the same emotion category and the work order queue is sorted, the first work order can be inserted after the pending work order of the corresponding fourth emotion category. For example, the work order queue includes 5 pending work orders, the fourth emotion category corresponding to the third pending work order is anger, and the first emotion category is also anger. Then, the target ranking of the first work order can be determined to be 4. If the fourth emotion category corresponding to the third and fourth pending work orders is anger, the target ranking of the first work order is 5, and so on. When the work order queue does not include the same fourth emotion category as the first emotion category, the pending work order corresponding to the candidate account is not associated with the same emotion, then the response priority of each fourth emotion category can be determined, and the position of the first work order can be determined by comparing the response priority. Sorting according to priority is a technology well known to those skilled in the art and will not be elaborated here.

[0111] It is worth noting that the present embodiment prioritizes matching whether the emotion categories are the same, rather than directly using priority to match all situations. This is because different emotion categories may have the same priority. If only sorting is performed based on a single dimension of priority, work orders with the same emotion will be discontinuous in the work order queue, causing work orders with the same emotion to be processed in an alternate order, which is not rational when processing multiple work orders. Therefore, the present embodiment first compares the emotion categories, and then performs priority sorting if the comparison is unsuccessful, to ensure that work orders with the same emotion are continuous in the work order queue.

[0112] It should be noted that after determining the target ranking corresponding to each work order queue, the account with the highest target ranking can be used as the first account.

[0113] In addition, in one embodiment, referring to Figure 3 After executing step S50, the following steps are also included but not limited to:

[0114] S61, determining a first capability tag and a second capability tag from a plurality of response capability tags associated with the first account, and determining a third capability tag and a fourth capability tag from a plurality of response capability tags associated with the second account, wherein the first capability tag and the third capability tag are used to indicate business capabilities, and the second capability tag and the fourth capability tag are used to indicate work order acceptance capabilities;

[0115] S62, updating the second capability tag based on the updated work order queue of the first account, and updating the fourth capability tag based on the updated work order queue of the second account;

[0116] S63, obtaining second evaluation information for the second work order feedback, and inputting the second evaluation information into the second NLP model to determine a fifth emotion category;

[0117] S64, determining at least one third target tag based on the third emotion category and the first mapping table, and determining at least one fourth target tag based on the fifth emotion category and the first mapping table;

[0118] S65: Update the first capability tag based on the third target tag, and update the third capability tag based on the fourth target tag.

[0119] It should be noted that if Figure 1 As shown, the response capability label may include acceptance capability and business capability. For example, labels representing business capability include technical expertise, proficiency in processes, and rich experience, and labels representing work order acceptance capability may include fast response speed, no work orders at present, and high timeliness rate, etc. This embodiment divides the response capability label into two dimensions: business capability and work order acceptance capability. It can dynamically update the response capability label of each available account according to the processing status of the work order, increase the optional accounts that can be assigned, improve the description ability of the response capability label for the optional accounts, and ensure the accuracy of work order assignment.

[0120] It should be noted that the second capability tag and the fourth capability tag are the same, and the only difference is the object to which they belong. The second capability tag and the fourth capability tag can be updated in real time according to the number of work orders in their respective work order queues.

[0121] Exemplarily, the response capability labels of optional account A include fast response speed and professional skills. When optional account A is assigned more work orders, its "fast response speed" label is removed to avoid work orders with response speed requirements being assigned to optional account A, which affects the processing efficiency of work orders. Similarly, when optional account A has fewer remaining work orders, the "fast response speed" label can be re-added.

[0122] It should be noted that the first capability label and the third capability label are business capability labels, the third emotion category is obtained based on the first evaluation information of user feedback, and the first mapping table records the response capability labels corresponding to each optional emotion category. The corresponding business capability label can be preset for each optional account, and then dynamically updated according to the evaluation information of the work order. The specific update direction can be determined according to the corresponding emotion category. Labels can be added in the case of positive emotions and removed in the case of negative emotions.

[0123] For example, refer to Figure 1Taking the first capability label as an example, if the third emotion category is satisfaction with professionalism, the response capability label recorded in the first mapping table is high professionalism, and the corresponding response capability label is added to the first account; for another example, if the third emotion category is anger, if the first account has the label of "good service attitude", then remove the label to achieve dynamic update of the label. Of course, it is also possible to update by accumulating the number of times, for example, after accumulating multiple times of the same negative emotion, remove the label to avoid the special evaluation of a single user affecting the objectivity of the response capability label of the optional account.

[0124] In addition, in one embodiment, referring to Figure 3 In step S40, before allocating the first work order to the first account, the following steps are also included but not limited to:

[0125] S46, determining a first work order process based on the first work order type, wherein the first work order process includes a plurality of first process nodes;

[0126] S47, inputting the first description information and each first process node into a first NLP model, and identifying a target node corresponding to the first description information through the first NLP model;

[0127] S48, configuring a first work order based on the target node.

[0128] It should be noted that each type of work order includes its own work order process. For example, a complaint work order has a corresponding complaint process, and an approval work order has a corresponding approval process. This embodiment can not only realize the accurate allocation of response personnel, but also automatically identify the target node to which the first work order belongs, ensuring that the first work order can be directly allocated to the corresponding target node for work order flow. After determining the first work order process, this embodiment inputs the first process node into the first NLP model as a classification basis. The first description information is a description of the requirements for the first work order. Therefore, the first description information can be secondary identified to determine the target node, thereby realizing automatic matching of the process.

[0129] Exemplarily, the work order description information is "Approval work order A was rejected during approval by Department X, and after modification, it jumped to this department for re-examination", and multiple first process nodes of the approval work order are input into the first NLP model as a classification basis, and the above description information is input into the first NLP model for identification, and "Department X" is determined as the target node based on "Approval by Department X" and "Re-examination", and the approval work order is configured to the target node, thereby eliminating the preceding node, so that after the first account obtains the first work order, it can know the current processing node based on the target node, thereby realizing accurate allocation of the work order.

[0130] like Figure 4 As shown, Figure 4: is a structural diagram of a work order management device based on AI analysis provided by an embodiment of the present invention. The present invention also provides a work order management device based on AI analysis, including:

[0131] The processor 401 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0132] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the work order management method based on AI analysis in the embodiment of this application;

[0133] Input / output interface 403, used to implement information input and output;

[0134] Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0135] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0136] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0137] An embodiment of the present application also provides an electronic device, including the work order management device based on AI analysis as described above.

[0138] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned work order management method based on AI analysis is implemented.

[0139] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are implemented to be located in one place, or may also be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0140] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0141] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions under the shared conditions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A work order management method based on AI analysis, characterized in that: Applied to a work order management system, the work order management system is preset with a first NLP model, a second NLP model and a plurality of available property lines, each of the available property lines is associated with a plurality of available accounts and a plurality of optional work order types, each of the available accounts is associated with a plurality of response capability tags, the method comprises: Creating a first work order based on the work order description information and the first work order type, and determining a first property line based on the first work order type, wherein the work order description information is used to indicate a root cause for creating the first work order; Inputting the work order description information and the available property line into the first NLP model, and when the first NLP model extracts first description information and at least one second description information from the work order description information, obtaining second property lines identified based on each of the second description information, wherein the first description information can be used to identify the first property line; identifying a first emotion category from the first description information based on the second NLP model, and identifying a second emotion category from the second description information; Determine at least one first target tag based on the first emotion category and a first mapping table, determine a first account based on the first target tag and the first property line, and assign the first work order to the first account, wherein the first mapping table records a mapping relationship between optional emotion categories and the responsiveness tags; Based on any of the second description information, at least one second target tag is determined based on the corresponding second emotion category and the first mapping table, a second account is determined based on the second target tag and the second property line, and a second work order is created and assigned to the second account.

2. The work order management method based on AI analysis according to claim 1 is characterized in that: After inputting the work order description information into the first NLP model, the method further includes: When the first NLP model outputs the first property line and at least one of the second property lines, obtaining a recognition log of the first NLP model based on the work order description information; Based on the identification log, the identification participles used to identify the first property line are combined into the first description information, and the identification participles used to identify the second property line are combined into the second description information, wherein the identification participles are obtained by splitting based on the work order description information.

3. The work order management method based on AI analysis according to claim 1 is characterized in that: Each of the optional work order types is pre-associated with at least one preset operation word, and creating a second work order and allocating it to the second account includes: Determine the optional work order type of the second property line as a candidate work order type; Extracting at least one description operation word from the second description information, and determining a second work order type from the plurality of candidate work order types based on the description operation word, wherein the description operation word is semantically identical or semantically similar to any of the preset operation words of the second work order type; When the second description information records a historical work order, determining the available account to which the historical work order is assigned as a third account, and determining the third account as a work order object; The second work order is constructed based on the second work order type and the third account, and the second work order is assigned to the second account.

4. The work order management method based on AI analysis according to claim 3 is characterized in that: After allocating the second work order to the second account, the method further includes: When the second emotion category is used to indicate a negative emotion, determining a scoring base based on the second emotion category and a preset second mapping table, wherein the second mapping table records a mapping relationship between the optional emotion category and the optional base; After the first work order is completed, obtaining first evaluation information based on feedback of the first work order, and inputting the first evaluation information into the second NLP model to determine a third emotion category; When the third emotion category is used to indicate a positive emotion, a target assessment score is determined based on a preset correction coefficient and the score base; Apply the target assessment score to the third account.

5. The work order management method based on AI analysis according to claim 4 is characterized in that: The optional emotion category is pre-associated with a response priority, determining a first account based on the first target tag and the first property line, and allocating the first work order to the first account includes: When a plurality of candidate accounts are matched based on the first target tag and the first property line, a work order queue of each of the candidate accounts is obtained, wherein the work order queue includes a plurality of work orders to be processed that are arranged in order, and each of the work orders to be processed is associated with a corresponding fourth emotion category; traversing each of the work order queues based on the first emotion category; When the first emotion category matches the same fourth emotion category, the next one of the to-be-processed work orders corresponding to the matched fourth emotion category is determined as the target ranking; When the first emotion category does not match the same fourth emotion category, determining the response priorities corresponding to the respective fourth emotion categories, and determining the target ranking of the first work order based on the response priorities corresponding to the first emotion category; The candidate account corresponding to the frontmost target ranking is determined as the first account, and the first work order is inserted into the work order queue of the first account based on the target ranking.

6. The work order management method based on AI analysis according to claim 5 is characterized in that: After creating the second work order and assigning it to the second account, the method further includes: Determine a first capability tag and a second capability tag from the plurality of response capability tags associated with the first account, and determine a third capability tag and a fourth capability tag from the plurality of response capability tags associated with the second account, wherein the first capability tag and the third capability tag are used to indicate business capabilities, and the second capability tag and the fourth capability tag are used to indicate work order acceptance capabilities; updating the second capability tag based on the updated work order queue of the first account, and updating the fourth capability tag based on the updated work order queue of the second account; Obtaining second evaluation information for the second work order feedback, and inputting the second evaluation information into the second NLP model to determine a fifth emotion category; Determine at least one third target tag based on the third emotion category and the first mapping table, and determine at least one fourth target tag based on the fifth emotion category and the first mapping table; The first capability tag is updated based on the third target tag, and the third capability tag is updated based on the fourth target tag.

7. The work order management method based on AI analysis according to claim 1, characterized in that: Before allocating the first work order to the first account, the method further includes: Determining a first work order process based on the first work order type, wherein the first work order process includes a plurality of first process nodes; Inputting the first description information and each of the first process nodes into the first NLP model, and identifying the target node corresponding to the first description information through the first NLP model; The first work order is configured based on the target node.

8. A work order management device based on AI analysis, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the work order management method based on AI analysis as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: Including the work order management device based on AI analysis as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the work order management method based on AI analysis as described in any one of claims 1 to 7.

Images