A work order generation method, device, equipment, medium and product

Abstract

The application discloses a work order generation method, device, equipment, medium and product, and relates to the technical field of artificial intelligence. The method comprises the following steps: receiving a creation trigger operation of a service work order, and acquiring voice data in a service process for a user; performing intent recognition on the voice data to obtain a corresponding business intent and a key data set; selecting a target work order template from a plurality of preset work order templates based on the business intent; and performing content filling on the target work order template based on the key data set to obtain a service work order corresponding to the voice data. The technical scheme provided by the application can improve the work order building efficiency in customer service, automatically generate a service work order, and improve the work efficiency of artificial attendants and the service experience of users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a work order generation method and device, equipment, medium and product. BACKGROUND

[0002] With the accelerated development of enterprise business online, service work orders have also been fully online. In view of the related problems not solved in the user online, the agent will generate and fill in the online work order to support the subsequent work order processing personnel to effectively understand the previous communication and better solve the customer problem.

[0003] The existing method of creating a service work order by an artificial agent is usually to rely on the understanding of the customer's problem according to the current consultation scene, and to fill in and transfer according to the work order template preset by the system. However, the existing method has the following problems: 1. Because there are many contents filled in the work order, the service time of the agent to the user is prolonged, resulting in user complaints; 2. The creation of the work order depends on the understanding of the user's problem by the agent and the memory of the conversation content, and in the face of each high-intensity incoming call, the pressure on the customer service to the customer is increased; 3. The subsequent work order processing personnel rely on the content filled in the work order, and there is no record of the user's communication in the early stage as an auxiliary processing, which may cause the time efficiency of the work order closed loop to be prolonged. Therefore, designing an automatic generation of a service work order to improve the work efficiency of the artificial agent and the service experience of the user has become a problem to be solved. SUMMARY

[0004] The present application provides a work order generation method, device, equipment, medium and product, which can improve the work order building efficiency in customer service, automatically generate a service work order, and improve the work efficiency of the artificial agent and the service experience of the user.

[0005] In a first aspect, the present application provides a work order generation method, which comprises:

[0006] receiving a creation trigger operation of a service work order, and obtaining voice data in a user service process;

[0007] performing intent recognition on the voice data to obtain a corresponding business intent and a key data set;

[0008] filtering a target work order template from a plurality of preset work order templates based on the business intent;

[0009] filling in the target work order template based on the key data set to obtain a service work order corresponding to the voice data.

[0010] Further, the key data set comprises user's basic information and business information; and the content filling of the target work order template based on the key data set to obtain a service work order corresponding to the voice data comprises: obtaining a plurality of table fields in the target work order template; classifying the table fields into a first field corresponding to the basic information and a second field corresponding to the business information; filling the first field with the basic information and filling the second field with the business information to obtain the service work order corresponding to the voice data.

[0011] Further, the number of the business information is a plurality; and the content filling of the second field based on the business information comprises: for any business information, matching a corresponding target field from the second field; obtaining a template requirement of the target field; modifying the business information based on the template requirement to obtain to-be-filled content; filling the to-be-filled content into a key-value filling position corresponding to the target field; and traversing all the business information to complete the content filling of the business information in the target work order template.

[0012] Further, the modification of the business information based on the template requirement to obtain to-be-filled content comprises: analyzing the template requirement and the business information to determine a modification direction of the modification of the business information; if the modification direction is to express the business information concisely, identifying redundant components and semantically similar sentences in the business information; deleting the redundant components in the business information and merging the semantically similar sentences in the business information to obtain the to-be-filled content; or if the modification direction is to express the business information clearly, identifying a plurality of entities in the business information and a semantic relationship between the plurality of entities; and expanding a sentence of the business information based on the plurality of entities and the semantic relationship to obtain the to-be-filled content.

[0013] Further, after the content filling of the target work order template based on the key data set, the method further comprises: determining whether there is a third field that is not filled in the target work order template; if there is, obtaining historical work order data corresponding to the business intent; analyzing the historical work order data to determine to-be-filled content of the third field; and filling the to-be-filled content into a key-value filling position corresponding to the third field.

[0014] Further, before the content filling of the target work order template based on the key data set, the method further comprises: data cleaning of the key data set to obtain a processed key data set.

[0015] In a second aspect, the present application provides a work order generation device, which comprises:

[0016] The voice data acquisition module is configured to receive a creation trigger operation of a service work order, and acquire voice data in a service process for a user.

[0017] The voice data recognition module is configured to perform intent recognition on the voice data, and obtain a corresponding service intent and a key data set.

[0018] The work order template screening module is configured to screen a target work order template from a plurality of preset work order templates based on the service intent.

[0019] The work order content filling module is configured to perform content filling on the target work order template based on the key data set, and obtain a service work order corresponding to the voice data.

[0020] In a third aspect, the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the work order generation method according to any of the embodiments of the present application.

[0021] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions for enabling a processor to implement the work order generation method according to any of the embodiments of the present application when the computer instructions are executed by the processor.

[0022] In a fifth aspect, the present application provides a computer program product comprising a computer program, which implements the work order generation method according to any of the embodiments of the present application when executed by a processor.

[0023] To solve the defects of the prior art in the background art, the embodiments of the present application provide a work order generation method, and the execution of the method can bring the following beneficial effects: after a service representative receives a call from a user, the voice data in the service process for the user is acquired, the semantics of the voice data is analyzed, the service intent is accurately determined, and the key data set is extracted, which can reduce the work order classification errors caused by human understanding deviation. The target work order template is filled with content based on the extracted key data set, which can ensure that the information is accurately filled in the corresponding field. The work order generation method can improve the work order building efficiency in customer service, automatically generate a service work order, and improve the work efficiency of the service representative and the service experience of the user.

[0024] It should be noted that the computer instructions described above can be stored on a computer readable storage medium in whole or in part. The computer readable storage medium can be packaged together with the processor of the work order generation device, or can be packaged separately from the processor of the work order generation device, and the present application does not limit this.

[0025] The description of the second aspect, the third aspect, and the fifth aspect in the present application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second aspect, the third aspect, and the fifth aspect can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0026] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description.

[0027] It can be understood that, before using the technical solutions disclosed in the embodiments of the present application, the type, use range, and use scenario of the personal information involved in the present application should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0029] Figure 1 The first flowchart of a work order generation method provided by the embodiments of the present application;

[0030] Figure 2 The second flowchart of a work order generation method provided by the embodiments of the present application;

[0031] Figure 3 The structural diagram of a work order generation device provided by the embodiments of the present application;

[0032] Figure 4 The block diagram of an electronic device for implementing a work order generation method according to the embodiments of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", "target", and "original" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include", "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0035] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, analyzed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards in the relevant region.

[0036] Figure 1 A first flowchart of a work order generation method provided by an embodiment of the present application, the embodiment can be applied to the scenario of generating a corresponding service work order based on voice data in the process of serving a user after a representative receives a telephone call from the user. The work order generation method provided by the embodiment of the present application can be executed by a work order generation device provided by the embodiment of the present application, which can be realized by software and / or hardware and integrated in an electronic device executing the method.

[0037] Referring to Figure 1 The method of the embodiment includes but is not limited to the following steps:

[0038] S110, receiving a creation trigger operation of a service work order, and obtaining voice data in the process of serving a user.

[0039] In the embodiment of the present application, a user dials a representative telephone or other special line of an institution or enterprise, and transfers to a manual customer service to handle a to-be-done business. After the user agrees, the conversation in the service process can be recorded. When the manual customer service currently fails to solve the user's problem, the user is informed to register the current to-be-done business. At this time, the manual customer service manually triggers a virtual key for creating a service work order or performs a specific interactive behavior to trigger the creation operation of the service work order in the digital information processing system. The system is in a real-time monitoring and responding state, and when the system receives the creation trigger operation of the service work order, the voice data in the process of serving the user is obtained.

[0040] Optionally, the to-be-done business can be consulting service, technical support service, after-sales maintenance service, etc.

[0041] Further, after obtaining the voice data, general audio processing techniques can be used to perform preliminary noise reduction, gain adjustment, and other optimization processing on the voice data to ensure that the obtained voice data has clear and stable characteristics.

[0042] S120, intent recognition is performed on the voice data to obtain a corresponding service intent and a key data set.

[0043] In the embodiments of the present application, general natural language processing techniques and deep neural network models can be used to perform intent recognition analysis on the voice data. The voice data is first digitized and features are extracted to convert the voice signal into a structured data form that can be recognized and processed by a computer, such as extracting audio frequency, amplitude, and duration of the voice, and other key feature information. Subsequently, a pre-trained intent recognition model is used to analyze the vocabulary semantics, sentence structure, context, and language habits in the analysis process to determine the specific business intent corresponding to the voice data, such as business consultation intent, complaint intent, and business handling request intent.

[0044] Meanwhile, general named entity recognition techniques and information extraction algorithms can be used to further filter and extract a key data set from the voice data, which can include user's basic information and business information. The basic information can be name, ID number, account number, etc. The business information can be product name, service item, transaction amount, time node, etc.

[0045] S130, a target work order template is selected from a plurality of preset work order templates based on the service intent.

[0046] In the embodiments of the present application, the system pre-constructs and stores a plurality of preset work order template libraries for different business scenarios and needs. Each preset work order template can cover various information fields, processing flow nodes, and related specification requirements under a specific business type. When the service intent is determined, the system compares and matches the intent with the business type label, key feature information, and applicable scenario description corresponding to each preset work order template, and finally selects the target work order template with the highest matching degree from the plurality of preset work order templates.

[0047] For example, if the service intent is a user's application for credit card loss, the system will select a work order template specifically for credit card loss processing as the target work order template from a plurality of preset work order templates. The template will include specific information fields such as cardholder name, credit card number, loss time, and loss reason, so that the user's credit card loss business can be processed subsequently, ensuring the standardization, efficiency, and accuracy of the entire business operation.

[0048] S140, content filling is performed on the target work order template based on the key data set, to obtain a service work order corresponding to the voice data.

[0049] Specifically, content filling is performed on the target work order template based on the key data set, to obtain a service work order corresponding to the voice data, including: obtaining a plurality of table fields pre-set in the target work order template; the system can use a general classification algorithm to classify these table fields into first fields corresponding to basic information and second fields corresponding to business information according to the attributes and purposes of the fields; the system automatically fills the basic information into key-value filling positions corresponding to the first fields, to complete content filling of the first fields; the system automatically fills the business information into key-value filling positions corresponding to the second fields, to complete content filling of the second fields, to obtain a service work order corresponding to the voice data.

[0050] The first fields corresponding to the basic information usually include customer identity information such as customer name, ID number, contact number, and email address, for constructing a user profile and subsequent communication with the user. The second fields corresponding to the business information usually include the content of specific business matters, such as business type, business details, product or service number involved, transaction amount, and transaction time, for reflecting the core points of the user's pending business.

[0051] Further, before content filling is performed on the target work order template based on the key data set, it further includes: data cleaning (such as format checking and logical verification) is performed on the key data set, to obtain a processed key data set, to ensure that the data filled into the target work order template meets the field requirements and is reasonable and correct in business logic.

[0052] Further, after content filling is performed on the target work order template based on the key data set, it further includes: after completing the preliminary filling operation of the corresponding fields of the basic information and the business information, the system starts a comprehensive checking mechanism to determine whether there are third fields that are not filled in the table fields of the target work order template; if it is found in the checking process that there are unfilled fields, the system will start a data backtracking and mining process, that is, historical work order data corresponding to the current business intent is obtained, and the historical work order data is analyzed, and the system can determine the to-be-filled content of the third field according to past experience and rules; the to-be-filled content is written to the key-value filling position corresponding to the third field.

[0053] For example, if the current business intention is to handle the after-sales maintenance service of a certain product, and the unfilled field is "common failure reason speculation", the system analyzes the records of after-sales maintenance of similar products in the historical work order data, finds that in most cases when the same failure phenomenon occurs for the product, it is due to the aging or damage of a certain component, and then determines "aging or damage of a certain component" as the to-be-filled content of the third field.

[0054] The technical scheme provided by the embodiment receives a creation trigger operation of a service work order, acquires voice data in a service process for a user, performs intention recognition on the voice data to obtain a corresponding business intention and a key data set, screens a target work order template from a plurality of preset work order templates based on the business intention, and fills content of the target work order template based on the key data set to obtain a service work order corresponding to the voice data. After a service representative receives a telephone call from a user, the voice data in the service process for the user is acquired, the semantics of the voice data is analyzed, the business intention is accurately determined, and the key data set is extracted, so that work order classification errors caused by manual understanding deviation can be reduced. The target work order template is filled with content based on the extracted key data set, so that information can be accurately filled in the corresponding field. The application can improve the work order building efficiency in customer service, automatically generate a service work order, and improve the work efficiency of the service representative and the service experience of the user.

[0055] The work order generation method provided by the embodiment of the application is further described below, Figure 2 The second flowchart of the work order generation method provided by the embodiment of the application is shown in FIG. 6. The embodiment of the application is optimized on the basis of the above-mentioned embodiments, and the specific optimization is that the embodiment explains and describes in detail the process of filling content of the second field based on business information.

[0056] Referring to Figure 2 The method of the embodiment of the application includes but is not limited to the following steps:

[0057] S210, for any business information, a corresponding target field is matched from the second field.

[0058] In the embodiment of the application, when a specific business information needs to be processed, the system performs in-depth analysis on the business information, extracts its key features, key words, and semantic information, and other core elements. Then, the extracted elements are matched with each field name, field annotation, and business logic description associated therewith in the second field one by one. Through a general intelligent matching algorithm, the algorithm can consider multiple factors such as word similarity, semantic correlation, and business relevance, and accurately screen out the target field with the highest matching degree from the plurality of second fields.

[0059] For example, if the business information includes a refund amount of a credit card transaction, the system will find a related field such as "credit card refund amount", "transaction refund amount", "refund amount details" in the second field, and determine the most accurate "credit card refund amount" as the corresponding target field according to the matching algorithm.

[0060] S220, obtaining the template requirements of the target field.

[0061] In the embodiments of the present application, the system finds the related record of the target work order template from the preset storage unit, and then extracts the template requirement information about the target field from the record. The template requirements can include multiple aspects, including but not limited to data type requirements, format specification requirements, mandatory and optional attribute requirements, and value range requirements. For example, the data type requirement can be to require the data to be an integer type, a floating point type, a character type, or a date type, etc. The value range requirement can be the numerical range of the target field.

[0062] By obtaining these template requirements of the target field, a basis and standard are provided for subsequent data filling, data verification of the field, and ensuring the accuracy and standardization of the entire work order data, which guarantees the stable operation and efficient processing of the business process at the data level.

[0063] S230, modifying the business information based on the template requirements to obtain the to-be-filled content.

[0064] Specifically, modifying the business information based on the template requirements to obtain the to-be-filled content includes: analyzing the template requirements and the business information to determine the modification direction of modifying the business information; if the modification direction is to express the business information simply, identifying redundant components and semantically similar sentences in the business information; deleting the redundant components in the business information, and merging the semantically similar sentences in the business information to obtain the to-be-filled content; if the modification direction is to express the business information clearly, identifying multiple entities and semantic relationships between the multiple entities in the business information; based on the multiple entities and the semantic relationships, expanding the business information to obtain the to-be-filled content.

[0065] Among them, the redundant components refer to repeated expressions of words, phrases, or modifiers, intercalations, etc. that do not materially contribute to the expression of core semantics. Semantically similar sentences refer to at least two sentences with similar semantic structures, word usage, and logical relationships. Entities can be specific concepts or objects such as people, products, places, and times.

[0066] In the embodiments of the present application, the system comprehensively compares and comprehensively considers the template requirements and the business information, evaluates whether the business information meets the standards and specifications set by the template requirements from multiple dimensions, and then determines the specific modification direction of the business information. If the modification direction is determined to be simplified expression of the business information after analysis and judgment, the system will use general natural language processing technology and intelligent text analysis algorithm to identify redundant components and semantically similar sentences in the business information. The system will delete the redundant components and merge the semantically similar sentences, thereby obtaining concise, clear, and highlighted to-be-filled content.

[0067] For example, assuming that the business information is "The problem feedback by the customer is about product failure, and this problem has affected the normal use of the product, the customer wants to apply for a refund, and the customer has a demand for a refund", wherein the redundant components are "feedback problem", "problem", and "situation", and the semantically similar sentences are "the customer wants to apply for a refund" and "the customer has a demand for a refund". Then, the to-be-filled content after simplification is "The customer feedbacks product failure, which has affected the normal use, and wants to apply for a refund".

[0068] If the modification direction is clear expression of the business information, the system also uses general natural language processing technology to identify multiple entities involved in the business information, and then the system further analyzes the semantic relationship between the multiple entities. Based on the multiple entities and the semantic relationship, the system uses appropriate vocabulary, conjunctions, and grammatical structures to expand the business information to obtain clearer, more accurate, and complete to-be-filled content.

[0069] For another example, assuming that the business information is "Xiaoming bought a mobile phone at a store in Shanghai and will go to repair it tomorrow", wherein "Xiaoming", "a store in Shanghai", "mobile phone", and "tomorrow" are the entities involved. For example, "Xiaoming" has a subject-predicate relationship with "purchase" and "repair", "mobile phone" is the object of "purchase" and "repair", "a store in Shanghai" is the location of "purchase", and "tomorrow" is the time of "repair". Then, the to-be-filled content after expansion is "The customer Xiaoming bought a mobile phone at a store in Shanghai, and plans to go to the repair location to repair the mobile phone tomorrow".

[0070] S240, filling the to-be-filled content to the key-value filling position corresponding to the target field.

[0071] In the embodiments of the present application, the system will perform the filling operation according to the precise mapping relationship between the target field and the key-value filling position in the work order template. The system will accurately position and identify the specific position of the target field in the work order template and the corresponding key-value filling position, which involves deep analysis and traversal of the data structure of the work order template.

[0072] S250, traversing all service information, completing content filling of service information in the target work order template.

[0073] In the embodiment of the present application, the method logic according to the above steps is used to perform content filling operation on each service information.

[0074] The technical scheme provided by the embodiment fills the content in the target field corresponding to the second field for any service information, obtains the template requirement of the target field, modifies the service information based on the template requirement to obtain the to-be-filled content, writes the to-be-filled content to the key value filling position corresponding to the target field, and traverses all service information to complete content filling of service information in the target work order template. After the agent receives the call of the user, the present application fills the content in the target work order template based on the extracted service information, which can ensure that the information is accurately filled in the corresponding field. The system fills the content according to the template requirement and the data format specification, which avoids the format error or data filling error that may occur when filling the content manually. The present application can improve the work order building efficiency in customer service, automatically generate a service work order, and improve the work efficiency of the artificial agent and the service experience of the user.

[0075] Figure 3 A structural diagram of a work order generation device provided by the embodiment of the present application is shown in FIG. 3. Figure 3 As shown in FIG. 3, the device 300 can include:

[0076] The voice data acquisition module 310 is configured to receive a creation trigger operation of a service work order, and acquire voice data in a user service process.

[0077] The voice data recognition module 320 is configured to perform intent recognition on the voice data to obtain a corresponding business intent and a key data set.

[0078] The work order template screening module 330 is configured to screen a target work order template from a plurality of preset work order templates based on the business intent.

[0079] The work order content filling module 340 is configured to perform content filling on the target work order template based on the key data set to obtain a service work order corresponding to the voice data.

[0080] Further, the work order content filling module 340 can include a first filling unit and a second filling unit.

[0081] In an embodiment, the key data set includes basic information and service information of a user.

[0082] The first filling unit can be configured to acquire a plurality of table fields in the target work order template; classify the table fields into first fields corresponding to the basic information and second fields corresponding to the service information; perform content filling on the first fields based on the basic information, and perform content filling on the second fields based on the service information, to obtain the service work order corresponding to the voice data.

[0083] In an embodiment, the number of service information is a plurality.

[0084] Further, the first filling unit can be specifically configured to, for any service information, match a corresponding target field from the second field; acquire a template requirement of the target field; modify the service information based on the template requirement to obtain to-be-filled content; write the to-be-filled content to a key-value filling position corresponding to the target field; and traverse all service information to complete content filling of the service information in the target work order template.

[0085] Further, the first filling unit can be specifically configured to analyze the template requirement and the service information to determine a modification direction of the service information; if the modification direction is to express the service information in a concise manner, identify redundant components and semantically similar sentences in the service information; delete the redundant components in the service information, and merge the semantically similar sentences in the service information to obtain the to-be-filled content; or if the modification direction is to express the service information in a clear manner, identify a plurality of entities in the service information and a semantic relationship between the plurality of entities; and perform sentence expansion on the service information based on the plurality of entities and the semantic relationship to obtain the to-be-filled content.

[0086] The second filling unit can be configured to, after content filling is performed on the target work order template based on the key data set, determine whether there is a third field that is not filled in the target work order template; if there is, acquire historical work order data corresponding to the service intention; analyze the historical work order data to determine to-be-filled content of the third field; and write the to-be-filled content to a key-value filling position corresponding to the third field.

[0087] Further, the work order generation apparatus can further include a data cleaning module.

[0088] The data cleaning module is configured to, before content filling is performed on the target work order template based on the key data set, perform data cleaning on the key data set to obtain a processed key data set.

[0089] The work order generation apparatus provided in the embodiment can be applied to the work order generation method provided in any of the above embodiments, and has corresponding functions and advantages.

[0090] Figure 4 is a block diagram of an electronic device that implements a work order generation method according to an embodiment of the present application. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit the implementations of the present application described and / or claimed in this document.

[0091] As shown in Figure 4 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0093] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the work order generation method.

[0094] In some embodiments, the work order generation method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the above-described work order generation method can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the work order generation method by other means, e.g., with the aid of firmware.

[0095] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0096] Computer programs implementing methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0097] In the context of this application, a computer readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium can be a machine readable signal medium. More specific examples of a machine readable storage medium will include one or more lines of a program of instructions in a transitory signal form, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0098] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0099] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0100] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0101] Note that the above describes only the preferred embodiments of the present application and the principles of the technology applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, rearrangements and substitutions can be made by those skilled in the art without departing from the scope of the present application. For example, those skilled in the art can use the various forms of processes shown above to reorder, add or delete steps; can perform the steps described in the present application in parallel, sequentially or in different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0102] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for generating work orders, characterized in that, The method includes: Receive the creation trigger operation of the service work order and obtain the voice data during the service process for the user; The voice data is subjected to intent recognition to obtain the corresponding business intent and key dataset; Based on the stated business intent, a target work order template is selected from multiple preset work order templates; Based on the key dataset, the target work order template is populated with content to obtain the service work order corresponding to the voice data; The target work order template contains multiple pieces of business information. The process of filling content into the second field corresponding to each business information includes: for any given business information, matching the corresponding target field from the second field; obtaining the template requirements for the target field; modifying the business information based on the template requirements to obtain the content to be filled; filling the content to be filled into the key-value fill position corresponding to the target field; and iterating through all business information to complete the content filling of the business information in the target work order template. Modifying the business information based on the template requirements to obtain the content to be filled includes: analyzing the template requirements and the business information to determine the direction of modification; if the direction of modification is to simplify the expression of the business information, then identifying redundant components and semantically similar sentences in the business information; deleting redundant components and merging semantically similar sentences in the business information to obtain the content to be filled; if the direction of modification is to clearly express the business information, then identifying multiple entities and semantic relationships between multiple entities in the business information; expanding the business information based on the multiple entities and the semantic relationships to obtain the content to be filled.

2. The work order generation method according to claim 1, characterized in that, The key dataset includes basic user information and business information; Based on the key dataset, the target work order template is populated with content to obtain the service work order corresponding to the voice data, including: Retrieve multiple table fields from the target work order template; The table fields are categorized into a first field corresponding to the basic information and a second field corresponding to the business information; The first field is populated with content based on the basic information, and the second field is populated with content based on the business information to obtain the service order corresponding to the voice data.

3. The work order generation method according to claim 1, characterized in that, After populating the target work order template with content based on the key dataset, the process also includes: Determine whether there are any unfilled third fields in the table fields of the target work order template; If it exists, then retrieve the historical work order data corresponding to the business intent; Analyze the historical work order data to determine the content to be filled in the third field; Fill the content to be filled into the key value filling position corresponding to the third field.

4. The work order generation method according to claim 1, characterized in that, Before populating the target work order template with content based on the key dataset, the process also includes: The key dataset is cleaned to obtain the processed key dataset.

5. A work order generation device, characterized in that, The device includes: The voice data acquisition module is used to receive the creation trigger operation of service work orders and acquire voice data during the service process for users; The voice data recognition module is used to perform intent recognition on the voice data to obtain the corresponding business intent and key dataset; The work order template filtering module is used to filter out the target work order template from multiple preset work order templates based on the business intent; The work order content filling module is used to fill the content of the target work order template based on the key dataset to obtain the service work order corresponding to the voice data. The target work order template contains multiple pieces of business information; the work order content filling module includes a first filling unit. The first filling unit is specifically used to: match the corresponding target field from the second field for any business information; obtain the template requirements of the target field; modify the business information based on the template requirements to obtain the content to be filled; fill the content to be filled into the key-value filling position corresponding to the target field; traverse all business information to complete the content filling of the business information in the target work order template; The first filling unit is further specifically used to analyze the template requirements and the business information to determine the direction of modification for the business information; if the direction of modification is to simplify the expression of the business information, then it identifies redundant components and semantically similar sentences in the business information; deletes redundant components in the business information and merges semantically similar sentences in the business information to obtain the content to be filled; if the direction of modification is to clearly express the business information, then it identifies multiple entities and semantic relationships between multiple entities in the business information; and expands the business information based on the multiple entities and the semantic relationships to obtain the content to be filled.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that is executed by the at least one processor, which enables the at least one processor to perform the work order generation method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the work order generation method according to any one of claims 1 to 4.

8. A computer program product comprising a computer program that, when executed by a processor, implements the work order generation method according to any one of claims 1 to 4.

Images