Method and device for automatically creating and distributing work orders

Abstract

The invention discloses a work order automatic creation and distribution method and device, and the method comprises the steps: obtaining target recording information; performing voice-to-text conversion on the target recording information to obtain target text information corresponding to the target recording information; performing keyword extraction on the target text information to obtain a plurality of target keywords; determining a target blank work order template corresponding to the target text information based on the plurality of target keywords; filling the target blank work order template with the target text information to obtain a target generated work order; and distributing the target generated work order to the target work order processing equipment. The work order creating and distributing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for automatically creating and distributing work orders. Background Art

[0002] The main solutions for creating work orders are as follows: (1) Manually filling out forms or documents: This is one of the most traditional ways. Users create work orders by filling out pre-designed forms or documents, and then submitting them to relevant departments or personnel for processing. (2) Email: Users can send work order requests via email, which usually requires sending the request to a specific email address, which is then automatically processed by the corresponding team or system. (3) Telephone: Some organizations provide telephone hotlines or customer service support, and users can submit work order requests over the phone. This method allows immediate communication with customer service personnel, but may lack the function of convenient tracking and recording. (4) Online forms: Many organizations provide online work order creation forms, where users can fill in relevant information on the website or application and submit work order requests. (5) Mobile applications: Some organizations provide mobile applications that allow users to create and track work orders through mobile phones or tablets. (6) Self-service portals: Many organizations provide self-service portals that allow users to log in and create, track and manage their work order requests. However, the efficiency of work order creation and distribution in existing technologies is low. Summary of the invention

[0003] The embodiments of the present application provide a method and device for automatically creating and distributing work orders, which can improve the efficiency of work order creation and distribution.

[0004] In a first aspect, the method for automatically creating and distributing work orders provided by the present application includes:

[0005] Get the target recording information;

[0006] Performing voice-to-text conversion on the target recording information to obtain target text information corresponding to the target recording information;

[0007] Extracting keywords from the target text information to obtain multiple target keywords;

[0008] Determining a target blank work order template corresponding to the target text information based on multiple target keywords;

[0009] Fill the target text information into the target blank work order template to obtain a target generated work order;

[0010] The target generated work order is distributed to the target work order processing device.

[0011] Optionally, determining a target blank work order template corresponding to the target text information based on multiple target keywords includes:

[0012] Obtaining a preset keyword template correspondence relationship, wherein the keyword template correspondence relationship includes a plurality of preset keyword sets and corresponding blank work order templates, wherein the preset keyword set includes a first preset number of keywords;

[0013] Get the occurrence frequency of multiple target keywords;

[0014] Determine a second preset number of target keywords ranked top in descending order of appearance frequency among the plurality of target keywords as the current keyword set;

[0015] Calculating the set similarity between the current keyword set and each of the preset keyword sets;

[0016] If the maximum value of the set similarities is higher than the preset similarity, the blank work order template corresponding to the preset keyword set having the highest set similarity with the current keyword set is determined as the target blank work order template corresponding to the target text information.

[0017] Optionally, the method for automatically creating and distributing a work order includes:

[0018] If the maximum value in the set similarities is not higher than the preset similarity, obtaining a target user portrait of the target user of the target recording information;

[0019] Inputting the target text information and the target user portrait of the target user into a preset user intention analysis model to obtain the prediction probability of each predicted user intention output by the preset user intention analysis model;

[0020] Determining the matching probability of each blank work order template based on the predicted probability of each predicted user intention, wherein different predicted user intentions correspond to different blank work order templates;

[0021] Adding the matching probability of the blank work order template and the set similarity corresponding to the preset keyword set corresponding to the blank work order template to obtain the template priority of the blank work order template;

[0022] The blank work order template with the highest template priority is determined as the target blank work order template corresponding to the target text information.

[0023] Optionally, the calculating the set similarity between the current keyword set and each of the preset keyword sets includes:

[0024] Compare each keyword in the current keyword set with each keyword in the preset keyword set to obtain the same quantity ratio of the same keywords in the current keyword set and the preset keyword set;

[0025] The same quantity ratio corresponding to the preset keyword set is determined as the set similarity corresponding to the preset keyword set, and the set similarity between the current keyword set and each of the preset keyword sets is obtained.

[0026] Optionally, distributing the target generated work order to a target work order processing device includes:

[0027] Build work order processing queues corresponding to each work order processing device;

[0028] Obtaining the number of work orders to be processed in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device;

[0029] Determine the device priority based on the number of pending work orders in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device, wherein the smaller the number of pending work orders, the higher the device priority, and the higher the average work order processing speed of the work order processing device, the higher the device priority;

[0030] Determine the work order processing device with the highest device priority as the target work order processing device;

[0031] Distribute the target generated work order to the work order processing queue of the target work order processing device.

[0032] Optionally, distributing the target generated work order to a work order processing queue of the target work order processing device includes:

[0033] Inputting the target speech information into an emotion recognition model to obtain a predicted emotion category of the target speech information;

[0034] When the predicted emotion category of the target voice information belongs to a preset emotion category set, the target generated work order corresponding to the target voice information is distributed to the first of the work order processing queues of the target work order processing device.

[0035] Optionally, the method for automatically creating and distributing work orders includes:

[0036] Acquire a speech data set, wherein the speech data set includes a plurality of speech samples, each speech sample includes a speech signal and an emotion label;

[0037] Preprocessing the speech signal;

[0038] Use the MFCC algorithm to extract the MFCC features of the speech signal;

[0039] Combine MFCC features with emotion labels to construct a training set;

[0040] Construct a recurrent neural network and train it based on the training set to obtain an emotion recognition model.

[0041] In a second aspect, the automatic creation and distribution device of a work order provided by the present application includes:

[0042] An acquisition module is used to obtain target recording information;

[0043] A conversion module, used to convert the target recording information into text to obtain target text information corresponding to the target recording information;

[0044] An extraction module, used to extract keywords from the target text information to obtain multiple target keywords;

[0045] A determination module, configured to determine a target blank work order template corresponding to the target text information based on a plurality of target keywords;

[0046] A filling module, used to fill the target text information into the target blank work order template to obtain a target generated work order;

[0047] A distribution module is used to distribute the target generated work order to a target work order processing device.

[0048] Optionally, determining a target blank work order template corresponding to the target text information based on multiple target keywords includes:

[0049] Obtaining a preset keyword template correspondence relationship, wherein the keyword template correspondence relationship includes a plurality of preset keyword sets and corresponding blank work order templates, wherein the preset keyword set includes a first preset number of keywords;

[0050] Get the occurrence frequency of multiple target keywords;

[0051] Determine a second preset number of target keywords ranked top in descending order of appearance frequency among the plurality of target keywords as the current keyword set;

[0052] Calculating the set similarity between the current keyword set and each of the preset keyword sets;

[0053] If the maximum value of the set similarities is higher than the preset similarity, the blank work order template corresponding to the preset keyword set having the highest set similarity with the current keyword set is determined as the target blank work order template corresponding to the target text information.

[0054] Optionally, the method for automatically creating and distributing a work order includes:

[0055] If the maximum value in the set similarities is not higher than the preset similarity, obtaining a target user portrait of the target user of the target recording information;

[0056] Inputting the target text information and the target user portrait of the target user into a preset user intention analysis model to obtain the prediction probability of each predicted user intention output by the preset user intention analysis model;

[0057] Determining the matching probability of each blank work order template based on the predicted probability of each predicted user intention, wherein different predicted user intentions correspond to different blank work order templates;

[0058] Adding the matching probability of the blank work order template and the set similarity corresponding to the preset keyword set corresponding to the blank work order template to obtain the template priority of the blank work order template;

[0059] The blank work order template with the highest template priority is determined as the target blank work order template corresponding to the target text information.

[0060] Optionally, the calculating the set similarity between the current keyword set and each of the preset keyword sets includes:

[0061] Compare each keyword in the current keyword set with each keyword in the preset keyword set to obtain the same quantity ratio of the same keywords in the current keyword set and the preset keyword set;

[0062] The same quantity ratio corresponding to the preset keyword set is determined as the set similarity corresponding to the preset keyword set, and the set similarity between the current keyword set and each of the preset keyword sets is obtained.

[0063] Optionally, distributing the target generated work order to a target work order processing device includes:

[0064] Build work order processing queues corresponding to each work order processing device;

[0065] Obtaining the number of work orders to be processed in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device;

[0066] Determine the device priority based on the number of pending work orders in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device, wherein the smaller the number of pending work orders, the higher the device priority, and the higher the average work order processing speed of the work order processing device, the higher the device priority;

[0067] Determine the work order processing device with the highest device priority as the target work order processing device;

[0068] Distribute the target generated work order to the work order processing queue of the target work order processing device.

[0069] Optionally, the step of distributing the target generated work order to a work order processing queue of the target work order processing device includes:

[0070] Inputting the target speech information into an emotion recognition model to obtain a predicted emotion category of the target speech information;

[0071] When the predicted emotion category of the target voice information belongs to a preset emotion category set, the target generated work order corresponding to the target voice information is distributed to the first of the work order processing queues of the target work order processing device.

[0072] Optionally, the method for automatically creating and distributing work orders includes:

[0073] Acquire a speech data set, wherein the speech data set includes a plurality of speech samples, each speech sample includes a speech signal and an emotion label;

[0074] Preprocessing the speech signal;

[0075] Use MFCC algorithm to extract MFCC features of speech signal;

[0076] Combine MFCC features with emotion labels to construct a training set;

[0077] Construct a recurrent neural network and train it based on the training set to obtain an emotion recognition model.

[0078] On the third aspect, the electronic device provided in the present application includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the method for automatically creating and distributing work orders provided in the present application.

[0079] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the method for automatically creating and distributing work orders provided in the present application.

[0080] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implements the steps in the method for automatically creating and distributing work orders provided in the present application.

[0081] In this application, compared with the related art, the target recording information is obtained; the target recording information is converted into text by voice to obtain the target text information corresponding to the target recording information; the target text information is extracted by keywords to obtain multiple target keywords; the target blank work order template corresponding to the target text information is determined based on the multiple target keywords; the target text information is filled into the target blank work order template to obtain the target generated work order; the target generated work order is distributed to the target work order processing device. This application can improve the efficiency of work order creation and distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0083] Figure 1 This is a schematic diagram of a scenario of an automatic creation and distribution system for work orders provided in an embodiment of the present application;

[0084] Figure 2 It is a flowchart of an embodiment of a method for automatically creating and distributing work orders provided in an embodiment of the present application;

[0085] Figure 3 This is a schematic diagram of information flow for automatic creation and distribution of work orders in one embodiment of a method for automatic creation and distribution of work orders provided in an embodiment of the present application;

[0086] Figure 4 It is a structural diagram of an automatic creation and distribution device for work orders provided in an embodiment of the present application;

[0087] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0088] It should be noted that the principle of the present application is illustrated by implementing it in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application, and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0089] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0090] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0091] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0092] In order to improve the effect of automatic creation and distribution of work orders, the embodiments of the present application provide a method for automatic creation and distribution of work orders, an automatic creation and distribution device for work orders, an electronic device, a computer-readable storage medium, and a computer program product. The method for automatic creation and distribution of work orders can be executed by the automatic creation and distribution device for work orders, or by an electronic device integrated with the automatic creation and distribution device for work orders.

[0093] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0094] Please refer to Figure 1 ,This application also provides an automatic creation and distribution system for a work order, such as Figure 1 As shown, the automatic creation and distribution system of the work order includes an electronic device 100, and the automatic creation and distribution device of the work order provided in the present application is integrated in the electronic device 100.

[0095] Among them, the electronic device 100 can be any device equipped with a processor and has processing capabilities, such as mobile electronic devices with processors such as smart phones, tablet computers, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, industrial equipment, etc.

[0096] In addition, if Figure 1 As shown, the automatic creation and distribution system of the work order may further include a memory 200 for storing original data, intermediate data and result data.

[0097] In the embodiment of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0098] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume. The physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

[0099] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is pre-divided into stripes. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0100] It should be noted that Figure 1 The scenario diagram of the automatic creation and distribution system of work orders shown is merely an example. The automatic creation and distribution system of work orders and the scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art will appreciate that with the evolution of the automatic creation and distribution system of work orders and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0101] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0102] Please refer to Figure 2 , Figure 2: is a flowchart of an embodiment of the method for automatically creating and distributing work orders provided in an embodiment of the present application, such as Figure 2 As shown, the process of the automatic creation and distribution method of the work order provided by this application is as follows:

[0103] 201. Obtain target recording information.

[0104] In a specific embodiment, the target recording information is a recording of a conversation between a target user and a customer service agent, wherein the recording of the conversation includes the words spoken by the user and the words spoken by the customer service agent.

[0105] In another specific embodiment, in order to reduce the difficulty of subsequent judgment, a recording of a call between a target user and a customer service agent is obtained. Voiceprint recognition is performed on the recording of the call between the two parties to obtain a recording of the customer service agent's call in the recording of the call between the two parties, and the recording of the customer service agent's call in the recording of the call between the two parties is removed from the recording of the call between the two parties to obtain the target recording information belonging to the target user. Since the voice of the customer service agent can be recorded in advance, it is convenient for voiceprint recognition, so that only the user's recording is retained.

[0106] In a specific embodiment, a customer service agent reference voice signal pre-recorded by a customer service agent in a recording of a call between two parties is obtained, the call recording between the two parties is split into multiple voice segment signals, the customer service agent reference voice signal and each voice segment signal are respectively input into a voiceprint recognition model to obtain a voiceprint recognition result. Voiceprint recognition includes whether each voice segment signal matches the customer service agent reference voice signal. The voice segment signal that matches the customer service agent reference voice signal is removed from the call recording between the two parties to obtain target recording information belonging to the target user.

[0107] Voiceprint Recognition (VPR), also known as speaker recognition, has two categories, namely speaker identification and speaker verification. The former is used to determine which of several people a certain speech segment is said by, which is a "multiple-choice" problem; while the latter is used to confirm whether a certain speech segment is said by a specified person, which is a "one-to-one discrimination" problem. Different tasks and applications will use different voiceprint recognition technologies. For example, identification technology may be needed to narrow the scope of criminal investigation, while verification technology may be needed for bank transactions.

[0108] 202. Perform voice-to-text conversion on the target recording information to obtain target text information corresponding to the target recording information.

[0109] 203. Perform keyword extraction on the target text information to obtain multiple target keywords.

[0110] Keyword extraction is a technique involving natural language processing that aims to identify the most representative words or phrases from a text. This process can be performed based on different algorithms and methods, including graph-based ranking algorithms, statistical methods, machine learning methods, etc.

[0111] 204. Determine a target blank work order template corresponding to the target text information based on multiple target keywords.

[0112] In a specific embodiment, determining a target blank work order template corresponding to target text information based on multiple target keywords includes:

[0113] (1) Obtain the preset keyword template correspondence.

[0114] The keyword-template correspondence relationship includes a plurality of preset keyword sets and corresponding blank work order templates, wherein the preset keyword set includes a first preset number of keywords.

[0115] The first preset number can be set according to the specific situation, for example, the first preset number is 2 or 3, etc. For example, the preset keyword set includes set-top box and fault. The blank work order template corresponding to the preset keyword set is blank work order template A. The blank work order template contains multiple items to be filled in, which can be set according to the specific situation.

[0116] (2) Obtain the occurrence frequency of multiple target keywords.

[0117] (3) A second preset number of target keywords ranked top in descending order of appearance frequency among the multiple target keywords are determined as the current keyword set.

[0118] Specifically, the second preset number is greater than the first preset number and is less than the total number of the plurality of target keywords.

[0119] (4) Calculate the set similarity between the current keyword set and each preset keyword set.

[0120] In the embodiment of the present application, the set similarity between the current keyword set and each preset keyword set is calculated, including: comparing each keyword in the current keyword set with each keyword in the preset keyword set, obtaining the same number ratio of the same keywords in the current keyword set and the preset keyword set; determining the same number ratio corresponding to the preset keyword set as the set similarity corresponding to the preset keyword set, and obtaining the set similarity between the current keyword set and each preset keyword set. The same number ratio is the ratio of the number of the same keywords to the first preset number.

[0121] (5) If the maximum value of the set similarity is higher than the preset similarity, the blank work order template corresponding to the preset keyword set with the highest set similarity to the current keyword set is determined as the target blank work order template corresponding to the target text information.

[0122] The preset similarity may be 80% or other values, which are set according to specific circumstances.

[0123] Furthermore, the method for automatically creating and distributing work orders includes:

[0124] (1) If the maximum value in the set similarity is not higher than the preset similarity, the target user portrait of the target user of the target recording information is obtained.

[0125] In the embodiment of the present application, user feature information of N users in a preset historical time period is obtained, and based on the user feature information of the N users, M first user feature clusters are obtained, and the feature average vectors of the M first user feature clusters are calculated, and the feature average vectors of the M first user feature clusters are determined as M preset user portraits. User feature information of the target user is obtained, and the feature similarity between the user feature information of the target user and each preset user portrait is calculated to obtain M feature portrait similarities, and the user portrait with the highest feature portrait similarity is determined as the target user portrait of the target user. Among them, the user feature information includes age, hobbies, personality, number of complaints, etc.

[0126] Further, user feature information of N users in a preset historical time period is obtained, and M first user feature clusters are obtained based on the user feature information of the N users, including: randomly dividing the user feature information of the N users into K feature information sets, each feature information set contains N / K user feature information. The K feature information sets are clustered respectively to obtain M second user feature clusters in each feature information set, and each second user feature cluster contains N / QK user feature information. Each second user feature cluster is determined as a target user feature cluster, and the feature cluster similarity between the target user feature cluster and the second user feature clusters in the K feature information sets is calculated respectively, and the second user feature clusters with the greatest similarity to the target user feature cluster in each feature information set are merged to obtain the first user feature cluster corresponding to the target user feature cluster, and M first user feature clusters corresponding to the M second user feature clusters are obtained, and each merged feature set contains N / M user feature information.

[0127] Specifically, the feature cluster similarities between the target user feature cluster and the second user feature cluster in the K feature information sets are calculated respectively, including: calculating the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster, and determining the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster as the feature cluster similarity between the target user feature cluster and the second user feature cluster.

[0128] (2) Input the target text information and the target user portrait of the target user into a preset user intention analysis model to obtain the prediction probability of each predicted user intention output by the preset user intention analysis model.

[0129] (3) Determine the matching probability of each blank work order template based on the predicted probability of each predicted user intention, where different predicted user intentions correspond to different blank work order templates.

[0130] Specifically, the predicted probability of the predicted user intention is the matching probability of the blank work order template corresponding to the predicted user intention. The corresponding relationship between the predicted user intention and the blank work order template is preset.

[0131] (4) The matching probability of the blank work order template and the set similarity corresponding to the preset keyword set corresponding to the blank work order template are added together to obtain the template priority of the blank work order template.

[0132] (5) The blank work order template with the highest template priority is determined as the target blank work order template corresponding to the target text information.

[0133] 205. Fill the target text information into the target blank work order template to obtain the target generated work order.

[0134] In an embodiment of the present application, each attribute information in the target text information is obtained, and each attribute information in the target text information is filled into the corresponding to-be-filled items in the target blank work order template to obtain a target generated work order.

[0135] 206. Distribute the target generated work order to the target work order processing device.

[0136] In an embodiment of the present application, the target generated work order is distributed to the target work order processing device, including:

[0137] (1) Construct a work order processing queue corresponding to each work order processing device.

[0138] There are multiple work orders to be processed stored in the work order processing queue in sequence.

[0139] (2) Obtain the number of pending work orders in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device.

[0140] (3) Determine the device priority based on the number of pending work orders in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device.

[0141] Among them, the fewer the number of work orders to be processed, the higher the device priority, and the higher the average work order processing speed of the work order processing device, the higher the device priority.

[0142] (4) The work order processing device with the highest device priority is determined as the target work order processing device.

[0143] (5) Distribute the target generated work order to the work order processing queue of the target work order processing device.

[0144] Furthermore, the target generated work order is distributed to the work order processing queue of the target work order processing device, including: inputting the target voice information into the emotion recognition model to obtain the predicted emotion category of the target voice information; when the predicted emotion category of the target voice information belongs to a preset emotion category set, the target generated work order corresponding to the target voice information is distributed to the first of the work order processing queue of the target work order processing device.

[0145] The preset emotion category set may include emotion categories such as anger type, irritability type, etc.

[0146] Furthermore, the method for automatically creating and distributing work orders includes:

[0147] (1) Obtain a speech dataset, where the speech dataset includes multiple speech samples, each of which contains a speech signal and an emotion label.

[0148] (2) Preprocess the speech signal.

[0149] (3) Use the MFCC algorithm to extract the MFCC features of the speech signal.

[0150] (4) Combine MFCC features with emotion labels to construct a training set.

[0151] (5) Construct a recurrent neural network and train it based on the training set to obtain an emotion recognition model.

[0152] When the emotion recognition model is obtained, the target speech information is input into the emotion recognition model to obtain the predicted emotion category of the target speech information.

[0153] In an embodiment of the present application, the automatic creation and distribution device of the work order can be a phone box device, which can collect telephone signals and directly store the telephone voice and communication signaling status signals in the device for playback by the voice file management and playback module or transmission to the storage system, while the upper-level application software on the computer can use the communication interface to control the storage, management, playback and signal status acquisition of the entire voice file; the telephone recording device can also include multiple voice and communication signaling status signal acquisition modules, so that the recording of multiple calls can be completed, and high-quality voice files and accurate telephone information can be obtained, such as the time of picking up and hanging up the phone, incoming calls, outgoing calls, and transfer numbers.

[0154] The phone box device will record every incoming call or outgoing call, and record the call history. The recording will be saved on the server. The phone box provides an external interface, and the upper-level application can be connected to the phone box system software.

[0155] The phone box device integrates language recognition function, which recognizes the call recording into text for automatic work order creation. The working principle of speech-to-text software is to pick up these vibrations and then convert them into digital language through an analog-to-digital converter. The analog-to-digital converter extracts the sound from the audio file, measures the waveform in great detail, and then filters them to distinguish the relevant sounds. The sound is then divided into one hundredth or one thousandth of a second and then matched with phonemes. Phonemes are the sound units of all languages ​​that can distinguish words from the meaning of words.

[0156] like Figure 3 As shown, the user calls the agent phone to report the fault problem. The phone box device connects the agent phone and the recording server system to save the call records. The call records and recordings are sent by configuring the application system interface on the recording system.

[0157] For example:

[0158] [settings]

[0159] JaveURL_1=http: / / 145.170.42.70

[0160] JaveURL_2=http: / / 145.170.42.71

[0161] The phone box device calls the application system through the request interface to parse the incoming call number, and uses the incoming call number to query the corresponding user information in the system database. The acquired call recording is sent to the voice recognition system, and the recording is converted into text. The text is extracted and analyzed by keywords to map it to the form for creating a work order. Finally, the form content is used to match the dispatch rules and automatically dispatch the work order to the engineer for processing.

[0162] Furthermore, the target generated work order is distributed to the target work order processing device by polling allocation, random allocation, shortest queue time first (SPTF), shortest estimated processing time first (SPT), skill matching allocation, priority allocation, etc.

[0163] 1. Round Robin: The round robin algorithm assigns tickets to different handlers or teams one by one in a pre-set order. This method is simple and direct, but does not take into account the complexity of the ticket or the workload of the handler.

[0164] 2. Random Assignment: The random assignment algorithm randomly selects a handler or team to handle the work order. Although simple, it may lead to uneven workload distribution.

[0165] 3. Shortest Queue Time First (SPTF): The SPTF algorithm will prioritize assigning work orders to the processing personnel or teams with the lightest current workload. This can minimize the waiting time of work orders.

[0166] 4. Shortest Estimated Processing Time First (SPT): The SPT algorithm assigns work orders based on the estimated processing time of the processing personnel or team, giving priority to the personnel or team with the shortest processing time. This can minimize the processing time of the work order.

[0167] 5. Skill matching allocation: The skill matching algorithm will match the needs of the work order with the skills of the processing personnel or team, and give priority to the processing personnel or team with corresponding skills. This ensures that the work order can be handled professionally.

[0168] 6. Priority allocation: According to the priority or importance of the work order, high-priority work orders are assigned to the processing personnel or teams first. This ensures that urgent work orders are processed in a timely manner

[0169] In order to facilitate better implementation of the automatic creation and distribution method of work orders provided in the embodiment of the present application, the embodiment of the present application also provides an automatic creation and distribution device of work orders based on the automatic creation and distribution method of work orders. The meanings of the terms are the same as those in the automatic creation and distribution method of work orders. For specific implementation details, please refer to the description in the above method embodiment.

[0170] Please refer to Figure 4 , Figure 4 A schematic diagram of the structure of an automatic creation and distribution device for a work order provided in an embodiment of the present application, wherein the automatic creation and distribution device for a work order may include:

[0171] The acquisition module 701 is used to acquire target recording information;

[0172] The conversion module 702 is used to convert the target recording information into text to obtain the target text information corresponding to the target recording information;

[0173] An extraction module 703 is used to extract keywords from the target text information to obtain multiple target keywords;

[0174] A determination module 704, configured to determine a target blank work order template corresponding to the target text information based on a plurality of target keywords;

[0175] A filling module 705 is used to fill the target text information into the target blank work order template to obtain a target generated work order;

[0176] The distribution module 706 is used to distribute the target generated work order to the target work order processing device.

[0177] Optionally, determining a target blank work order template corresponding to the target text information based on multiple target keywords includes:

[0178] Obtaining a preset keyword template correspondence relationship, wherein the keyword template correspondence relationship includes a plurality of preset keyword sets and corresponding blank work order templates, wherein the preset keyword set includes a first preset number of keywords;

[0179] Get the occurrence frequency of multiple target keywords;

[0180] Determine a second preset number of target keywords ranked top in descending order of appearance frequency among the plurality of target keywords as the current keyword set;

[0181] Calculating the set similarity between the current keyword set and each of the preset keyword sets;

[0182] If the maximum value of the set similarities is higher than the preset similarity, the blank work order template corresponding to the preset keyword set having the highest set similarity with the current keyword set is determined as the target blank work order template corresponding to the target text information.

[0183] Optionally, the method for automatically creating and distributing a work order includes:

[0184] If the maximum value in the set similarities is not higher than the preset similarity, obtaining a target user portrait of the target user of the target recording information;

[0185] Inputting the target text information and the target user portrait of the target user into a preset user intention analysis model to obtain the prediction probability of each predicted user intention output by the preset user intention analysis model;

[0186] Determining the matching probability of each blank work order template based on the predicted probability of each predicted user intention, wherein different predicted user intentions correspond to different blank work order templates;

[0187] Adding the matching probability of the blank work order template and the set similarity corresponding to the preset keyword set corresponding to the blank work order template to obtain the template priority of the blank work order template;

[0188] The blank work order template with the highest template priority is determined as the target blank work order template corresponding to the target text information.

[0189] Optionally, the calculating the set similarity between the current keyword set and each of the preset keyword sets includes:

[0190] Compare each keyword in the current keyword set with each keyword in the preset keyword set to obtain the same quantity ratio of the same keywords in the current keyword set and the preset keyword set;

[0191] The same quantity ratio corresponding to the preset keyword set is determined as the set similarity corresponding to the preset keyword set, and the set similarity between the current keyword set and each of the preset keyword sets is obtained.

[0192] Optionally, distributing the target generated work order to a target work order processing device includes:

[0193] Build work order processing queues corresponding to each work order processing device;

[0194] Obtaining the number of work orders to be processed in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device;

[0195] Determine the device priority based on the number of pending work orders in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device, wherein the smaller the number of pending work orders, the higher the device priority, and the higher the average work order processing speed of the work order processing device, the higher the device priority;

[0196] Determine the work order processing device with the highest device priority as the target work order processing device;

[0197] Distribute the target generated work order to the work order processing queue of the target work order processing device.

[0198] Optionally, the step of distributing the target generated work order to a work order processing queue of the target work order processing device includes:

[0199] Inputting the target speech information into an emotion recognition model to obtain a predicted emotion category of the target speech information;

[0200] When the predicted emotion category of the target voice information belongs to a preset emotion category set, the target generated work order corresponding to the target voice information is distributed to the first of the work order processing queues of the target work order processing device.

[0201] Optionally, the method for automatically creating and distributing work orders includes:

[0202] Acquire a speech data set, wherein the speech data set includes a plurality of speech samples, each speech sample includes a speech signal and an emotion label;

[0203] Preprocessing the speech signal;

[0204] Use MFCC algorithm to extract MFCC features of speech signal;

[0205] Combine MFCC features with emotion labels to construct a training set;

[0206] Construct a recurrent neural network and train it based on the training set to obtain an emotion recognition model.

[0207] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described in detail here.

[0208] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the processor is used to execute the steps in the method for automatically creating and distributing work orders provided in this embodiment by calling a computer program stored in the memory.

[0209] Please refer to Figure 5 , Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0210] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0211] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0212] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0213] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0214] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0215] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the automatic creation and distribution method of the work order provided in this application, such as:

[0216] Obtain target recording information; perform speech-to-text conversion on the target recording information to obtain target text information corresponding to the target recording information; perform keyword extraction on the target text information to obtain multiple target keywords; determine a target blank work order template corresponding to the target text information based on the multiple target keywords; fill the target text information into the target blank work order template to obtain a target generated work order; distribute the target generated work order to a target work order processing device.

[0217] It should be noted that the electronic device provided in the embodiment of the present application and the method for automatically creating and distributing work orders in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0218] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on a processor of an electronic device provided in an embodiment of the present application, the processor of the electronic device executes the steps in the method for automatically creating and distributing work orders provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0219] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the above-mentioned method for automatically creating and distributing work orders.

[0220] The above is a detailed introduction to the method and device for automatically creating and distributing work orders provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0221] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A method for automatically creating and distributing work orders, characterized in that: include: Get the target recording information; Performing voice-to-text conversion on the target recording information to obtain target text information corresponding to the target recording information; Extracting keywords from the target text information to obtain multiple target keywords; Determining a target blank work order template corresponding to the target text information based on multiple target keywords; Fill the target text information into the target blank work order template to obtain a target generated work order; The target generated work order is distributed to the target work order processing device.

2. The method for automatically creating and distributing work orders according to claim 1, characterized in that: The step of determining a target blank work order template corresponding to the target text information based on multiple target keywords includes: Obtaining a preset keyword template correspondence relationship, wherein the keyword template correspondence relationship includes a plurality of preset keyword sets and corresponding blank work order templates, wherein the preset keyword set includes a first preset number of keywords; Get the occurrence frequency of multiple target keywords; Determine a second preset number of target keywords ranked top in descending order of appearance frequency among the plurality of target keywords as the current keyword set; Calculating the set similarity between the current keyword set and each of the preset keyword sets; If the maximum value of the set similarities is higher than the preset similarity, the blank work order template corresponding to the preset keyword set having the highest set similarity with the current keyword set is determined as the target blank work order template corresponding to the target text information.

3. The method for automatically creating and distributing work orders according to claim 2, characterized in that: The method for automatically creating and distributing a work order includes: If the maximum value in the set similarities is not higher than the preset similarity, obtaining a target user portrait of the target user of the target recording information; Inputting the target text information and the target user portrait of the target user into a preset user intention analysis model to obtain the prediction probability of each predicted user intention output by the preset user intention analysis model; Determining the matching probability of each blank work order template based on the predicted probability of each predicted user intention, wherein different predicted user intentions correspond to different blank work order templates; Adding the matching probability of the blank work order template and the set similarity corresponding to the preset keyword set corresponding to the blank work order template to obtain the template priority of the blank work order template; The blank work order template with the highest template priority is determined as the target blank work order template corresponding to the target text information.

4. The method for automatically creating and distributing work orders according to claim 3, characterized in that: The calculating the set similarity between the current keyword set and each of the preset keyword sets includes: Compare each keyword in the current keyword set with each keyword in the preset keyword set to obtain the same quantity ratio of the same keywords in the current keyword set and the preset keyword set; The same quantity ratio corresponding to the preset keyword set is determined as the set similarity corresponding to the preset keyword set, and the set similarity between the current keyword set and each of the preset keyword sets is obtained.

5. The method for automatically creating and distributing work orders according to claim 4, characterized in that: The step of distributing the target generated work order to a target work order processing device includes: Build work order processing queues corresponding to each work order processing device; Obtaining the number of work orders to be processed in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device; Determine the device priority based on the number of pending work orders in the work order processing queue of the work order processing device and the average work order processing speed of the work order processing device, wherein the smaller the number of pending work orders, the higher the device priority, and the higher the average work order processing speed of the work order processing device, the higher the device priority; Determine the work order processing device with the highest device priority as the target work order processing device; Distribute the target generated work order to the work order processing queue of the target work order processing device.

6. The method for automatically creating and distributing work orders according to claim 5, characterized in that: The step of distributing the target generated work order to the work order processing queue of the target work order processing device includes: Inputting the target speech information into an emotion recognition model to obtain a predicted emotion category of the target speech information; When the predicted emotion category of the target voice information belongs to a preset emotion category set, the target generated work order corresponding to the target voice information is distributed to the first of the work order processing queues of the target work order processing device.

7. The method for automatically creating and distributing work orders according to claim 6, characterized in that: The method for automatically creating and distributing work orders includes: Acquire a speech data set, wherein the speech data set includes a plurality of speech samples, each speech sample includes a speech signal and an emotion label; Preprocessing the speech signal; Use the MFCC algorithm to extract the MFCC features of the speech signal; Combine MFCC features with emotion labels to construct a training set; Construct a recurrent neural network and train it based on the training set to obtain an emotion recognition model.

8. A device for automatically creating and distributing work orders, characterized in that: include: An acquisition module is used to obtain target recording information; A conversion module, used to convert the target recording information into text to obtain target text information corresponding to the target recording information; An extraction module, used to extract keywords from the target text information to obtain multiple target keywords; A determination module, configured to determine a target blank work order template corresponding to the target text information based on a plurality of target keywords; A filling module, used to fill the target text information into the target blank work order template to obtain a target generated work order; A distribution module is used to distribute the target generated work order to a target work order processing device.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the method for automatically creating and distributing work orders as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method for automatically creating and distributing work orders as described in any one of claims 1 to 7.

Images