Work order processing method and device

Abstract

The invention provides a work order processing method and device. The method comprises the following steps: acquiring work order data; performing fault information extraction on the work order data to obtain fault information; matching the fault information with a work order instance in a previously established fault feature database to obtain a matched work order instance; wherein the fault feature database is established based on work order instances and corresponding processing strategies; and calling and executing a corresponding processing strategy according to the matched work order instance. According to the invention, fault information extraction is carried out on the obtained work order data to clarify the fault core content, remove irrelevant information interference and improve the accuracy and efficiency of subsequent processing, and the extracted fault information is matched with the work order instances in the fault feature database to improve the accuracy and efficiency of subsequent processing. According to the invention, the verified processing strategy corresponding to the work order instance is rapidly positioned and matched, the accuracy of work order processing is improved, the possibility of error processing is reduced, the time and cost for analyzing and solving problems from the beginning are reduced, and the fault processing speed and success rate are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a work order processing method and device. Background Art

[0002] As the business scale expands, the number of work orders generated in customer service has increased dramatically. The traditional manual work order processing method is not only time-consuming, but also prone to errors, and cannot meet the needs of efficient and accurate services. There are many repeated or similar problems. The traditional work order processing method usually relies on manual operation, which has problems such as slow processing speed, prone to errors, and heavy workload, making it difficult to meet the growing work order processing needs of enterprises. Therefore, it is particularly important to develop an intelligent work order system that can automatically identify and handle common problems.

[0003] In the prior art, although there have been preliminary attempts at automated processing, most of them rely on preset rules, have limited processing capabilities for the complex and changeable actual work order content, lack the ability to self-optimize and learn, and have slow processing speeds, are prone to errors, and have a large workload. They cannot automatically analyze and process work orders submitted by customers, and the same problem requires repeated manual processing, with strong manual intervention, making it difficult to meet the growing work order processing needs of enterprises. Summary of the invention

[0004] The present invention provides a work order processing method and device, which are used to solve the defect of limited processing capability for complex and changeable actual work order content in the prior art, improve work order processing efficiency, reduce manual intervention, and enhance customer service quality.

[0005] The present invention provides a work order processing method, comprising: acquiring work order data; extracting fault information from the work order data to obtain fault information; matching the fault information with a work order instance in a previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and a corresponding processing strategy; and calling and executing the corresponding processing strategy according to the matching work order instance.

[0006] According to a work order processing method provided by the present invention, fault information is extracted from work order data to obtain fault information, including: based on the work order data being in a picture format, feature extraction is performed on the work order data to obtain a feature vector; using natural language processing technology to extract fault information from the feature vector to obtain fault information; based on the work order data being in a text format, using natural language processing technology to extract fault information from the work order data to obtain fault information; using word embedding technology to convert the fault information into a vector.

[0007] According to a work order processing method provided by the present invention, natural language processing technology is used to extract fault information from work order data in feature vector or text format to obtain fault information, including: performing word segmentation on the feature vector or text format to obtain multiple word segments; performing part-of-speech tagging on each word segment to obtain a part-of-speech tag; performing entity recognition on the word segment based on the part-of-speech tag to obtain an entity recognition result; based on the entity recognition result, performing fault information extraction on each word segment to obtain fault information.

[0008] According to a work order processing method provided by the present invention, after extracting fault information from work order data and obtaining the fault information, the method comprises: using a previously established sentiment dictionary to identify the context of each participle and determine the context sentiment tendency of each participle; wherein the context sentiment tendency includes a positive sentiment tendency corresponding to positive words and a negative sentiment tendency corresponding to negative words, and the sentiment dictionary is constructed based on the previously collected positive words and negative words, the positive words are used to characterize the urgency and importance of the fault, and the negative words are used to characterize the fault and the problems existing in the fault; according to the context sentiment tendency of each participle, in combination with a preset weight allocation rule, a sentiment score is determined; wherein the preset weight allocation rule is used to limit the allocation weight corresponding to the context sentiment tendency; and according to the sentiment score, the corresponding work order data is prioritized; Matching the fault information with the work order instance in the previously established fault feature database includes: selecting the work order data with the highest priority based on the priority sorting result; matching the fault information corresponding to the selected work order data with the work order instance in the previously established fault feature database.

[0009] According to a work order processing method provided by the present invention, fault information is matched with a work order instance in a previously established fault feature database to obtain a matching work order instance, including: using Jaccard similarity to determine the similarity between the fault information and the work order instance in the previously established fault feature database; determining whether the similarity exceeds a preset threshold, and based on the similarity exceeding the preset threshold, using the corresponding work order instance as a matching work order instance.

[0010] According to a work order processing method provided by the present invention, the preset threshold is obtained based on feedback information obtained by executing a processing strategy corresponding to previously acquired work order data and optimizing the corresponding previously preset threshold; the previously preset threshold is a preset threshold used to determine a matching work order instance that matches the previously acquired work order data.

[0011] According to a work order processing method provided by the present invention, after calling and executing a corresponding processing strategy based on a matching work order instance, the method includes: obtaining feedback information based on the execution of the corresponding processing strategy; and optimizing the corresponding processing strategy in a fault feature database based on the feedback information.

[0012] The present invention also provides a work order processing device, including: a data acquisition module, which acquires work order data; an information extraction module, which extracts fault information from the work order data to obtain fault information; a work order matching module, which matches the fault information with a work order instance in a previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; and the work order processing module, which calls and executes the corresponding processing strategy according to the matching work order instance.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the work order processing methods described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the work order processing method as described above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the work order processing method as described above is implemented.

[0016] The work order processing method and device provided by the present invention extract fault information from the acquired work order data to clarify the core content of the fault, remove irrelevant information interference, improve the accuracy and efficiency of subsequent processing, and match the extracted fault information with the work order instance in the fault feature database to quickly locate the verified processing strategy corresponding to the matching work order instance, thereby improving the accuracy of work order processing, reducing the possibility of erroneous processing, reducing the time and cost of analyzing and solving problems from scratch, and improving the speed and success rate of fault processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the work order processing method provided by the present invention; Figure 2 This is the second flow chart of the work order processing method provided by the present invention; Figure 3 It is a structural schematic diagram of the work order processing device provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Figure 1 A schematic diagram of a work order processing method provided by the present invention is shown, and the method includes the following steps: S11, obtain work order data; S12, extracting fault information from the work order data to obtain fault information; S13, matching the fault information with the work order instance in the previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; S14: According to the matching work order instance, the corresponding processing strategy is called and executed.

[0021] It should be noted that the step numbers "S1N" in this manual do not represent the order of the work order processing method. Figure 2 The work order processing method of the present invention is described.

[0022] Step S11, obtaining work order data.

[0023] It should be noted that the work order data may be data submitted by users based on the preset platform, including information such as customer questions, processing process, and resolution results, and is specifically determined based on the work order data actually received from users. In addition, the preset platform may be a designated platform or another user platform, which is not further limited here.

[0024] In an optional embodiment, after obtaining the work order data, the process includes: preprocessing the work order data, wherein the preprocessing includes at least one of data cleaning and text conversion. It should be added that, through data cleaning, special characters, punctuation marks and other elements in the work order description that may interfere with subsequent processing can be removed, noise interference can be reduced, and subsequent text analysis and understanding can be made more accurate and efficient; through text conversion, standardized text representation can be used to reduce format interference, making it easier to quickly extract and understand the main content of the work order.

[0025] Step S12, extracting fault information from the work order data to obtain fault information.

[0026] In a possible implementation, the work order data is in a picture format, and fault information is extracted from the work order data to obtain fault information, including: extracting features from the work order data to obtain feature vectors; and using natural language processing technology (Natural Language Processing, referred to as NLP) to extract fault information from the feature vectors to obtain fault information.

[0027] Furthermore, feature extraction is performed on the work order data, including: inputting the work order data into a feature extraction model to obtain a feature vector output by the feature extraction model; wherein the feature extraction model is trained based on historical work order data and feature labels corresponding to the historical work order data.

[0028] It should be added that the feature extraction model can adopt a convolutional neural network (CNN) model or other models that can be used to extract feature vectors, which is not further limited here.

[0029] In another possible implementation, the work order data is in text format, and fault information is extracted from the work order data to obtain fault information, which also includes: using natural language processing technology to extract fault information from the work order data to obtain fault information; and using word embedding technology to convert the fault information into a vector.

[0030] It should be added that word embedding technology is used to convert fault information into vectors, including: inputting the fault information into a word embedding model to obtain fault information in vector form output by the word embedding model; wherein the word embedding model is trained based on historical fault information extracted based on historical work order data and feature labels corresponding to the historical fault information.

[0031] It is worth noting that the fault information used in training is extracted from historical work order data using NLP technology, which makes it easier for the word embedding model to learn the contextual relationship of words. By using historical fault information and the feature labels corresponding to the historical fault information, combined with the previously configured model parameters, the word embedding model is trained to continuously adjust the vector representation of the fault information and minimize the loss function, so that the word embedding model can better capture the semantic associations and contextual information between words, and provide more valuable vector representations for subsequent text analysis and understanding.

[0032] In an optional embodiment, natural language processing technology is used to extract fault information from work order data in feature vector or text format to obtain fault information, including: segmenting the work order data in feature vector or text format to obtain multiple segmentations; performing part-of-speech tagging on each segmentation to obtain a part-of-speech tag; performing entity recognition on the segmentation based on the part-of-speech tag to obtain an entity recognition result; based on the entity recognition result, performing fault information extraction on each segmentation to obtain fault information.

[0033] Furthermore, the word segmentation can use a preset word segmentation tool, such as Jieba word segmentation, etc., which is not further restricted here. For example, the work order data obtained is "the server hard disk fault light is on, and it is required to be processed as soon as possible. If you need on-site processing, please contact me during working hours." After data cleaning, using word segmentation, the obtained words include "server", "hard disk", "fault", "light", "lit", "requirement", "as soon as possible", "process", "as needed", "on-site", "process", "please", "in", "working hours", "with", "me" and "contact".

[0034] Accordingly, the part of speech of each participle is marked to determine the part of speech of each participle, such as noun, verb, adjective, etc., to help better understand the role of words in sentences, provide important clues for subsequent entity recognition, and improve the accuracy and efficiency of entity recognition.

[0035] In addition, based on the part-of-speech tags, entity recognition is performed on the segmented words to obtain entity recognition results, including: inputting the segmented words and the part-of-speech tags corresponding to each segmented word into an entity recognition model to obtain the entity recognition results output by the entity recognition model; wherein the entity recognition model is trained based on segmented word training data and the entity tags corresponding to the segmented word training data, and the segmented word training data includes training segmented words and the parts of speech corresponding to the training segmented words.

[0036] It should be noted that the entity recognition model can adopt a deep learning model such as BiLSTM-CRF, etc., which can be selected and trained according to actual design requirements. The model can be trained by using a large amount of word segmentation training data labeled with entity labels so that the model can learn entity features and automatically identify entities in work order data.

[0037] In addition, assuming that the word segmentation includes "server", "hard disk", "fault", "light", "light up", "requirement", "as soon as possible", "process", "as needed", "on-site", "processing", "please", "in", "working hours", "with", "me" and "contact", accordingly, the entity recognition results include device entities (server, hard disk, etc.), fault type entities (fault light lights up, etc.), action entities (processing, on-site, etc.), and time entities (working hours, etc.).

[0038] In an optional embodiment, after fault information is extracted from work order data and fault information is obtained, the following steps include: using a previously established sentiment dictionary to identify the context of each participle and determine the contextual sentiment tendency of each participle; wherein the contextual sentiment tendency includes a positive sentiment tendency corresponding to positive words and a negative sentiment tendency corresponding to negative words, and the sentiment dictionary is constructed based on the previously collected positive words and negative words, and the positive words are used to characterize the urgency and importance of the fault, and the negative words are used to characterize the fault and the problems existing in the fault; according to the contextual sentiment tendency of each participle, combined with a preset weight allocation rule, a sentiment score is determined; wherein the preset weight allocation rule is used to limit the allocation weight corresponding to the contextual sentiment tendency; and according to the sentiment score, the corresponding work order data is prioritized.

[0039] It should be noted that positive and negative words can be set according to the actual work order data involved and the actual design requirements. For example, if the work order data is "The server hard disk fault light is on, please handle it as soon as possible. If you need on-site processing, please contact me during working hours", "as soon as possible" and "required" may be regarded as positive words expressing urgency and importance, while "fault" and "problem" may be regarded as negative words, which are not further limited here. Prioritize and respond quickly through sentiment analysis to determine the urgency of the work order, so as to allocate resources and arrange work more reasonably, ensure that high-urgency work orders can be handled first, and improve the efficiency of fault handling and service quality.

[0040] In addition, a previously established sentiment dictionary is used to identify the context of each word segment and determine the contextual sentiment tendency of each word segment, including: inputting each word segment into a language model to use a preset context window to identify the context of each word segment, and combining the previously established sentiment dictionary to determine the contextual sentiment tendency; wherein the language model is previously trained based on word segmentation training data and the sentiment tendency labels corresponding to the word segmentation training data.

[0041] It should be added that the contextual sentiment tendency is determined based on the contextual segmentations of each segmentation. For example, if there are positive words in the upper and lower segmentations of any segmentation, the positive sentiment tendency of the current segmentation may be enhanced. If there are negative words in the context segmentation, the negative sentiment tendency of the current segmentation may be enhanced. In addition, the language model can be selected based on actual design requirements. It can be a pre-trained Transformer model, such as the Bidirectional Encoder Representations from Transformers (BERT) model, the Generative Pretrained Transformer (GPT) model, etc., or a traditional language model, such as the n-gram model, which is not further limited here.

[0042] In an optional embodiment, the sentiment score is determined according to the contextual sentiment tendency of each participle in combination with a preset weight allocation rule, including: assigning an initial weight to each participle based on the preset weight allocation rule; adjusting the initial weight assigned to each participle according to the contextual sentiment tendency of each participle, and using the adjusted weight in combination with the sentiment tendency to determine the sentiment score of each participle; determining the sentiment score of the corresponding work order data based on the sentiment scores of all participles of the same work order data.

[0043] It should be noted that the design of the preset allocation rules can be specifically set according to actual design requirements or prior experience. For example, the negative weight of "serious failure" can be relatively high, and the positive weight of "quick resolution" can also be high; or, the preset allocation rules are used to limit the weight allocation according to the statistical results of the emotional tendencies of each participle. For example, if the statistical results of the positive emotional tendencies in each participle are higher than the statistical results of the negative emotional tendencies, it means that the positive emotional tendencies have a greater influence, and the corresponding weights can be appropriately increased. No further limitations are made here.

[0044] In addition, it is worth noting that when adjusting the initial weight assigned to each participle according to the sentiment tendency of its context, the weight adjustment can be configured based on the frequency of the participle in the context of the sentiment tendency. For example, if the frequency of the participle in a positive context is higher, the product weight can be further increased. If the frequency of the participle in a negative context is higher, the negative weight can be further increased. The weight adjustment can be specifically configured according to actual design or prior experience, and is not further limited here.

[0045] Step S13, matching the fault information with the work order instance in the previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy.

[0046] In an optional embodiment, matching fault information with work order instances in a previously established fault feature database includes: selecting the work order data with the highest priority based on the priority sorting result; matching the fault information corresponding to the selected work order data with the work order instances in the previously established fault feature database. It should be noted that the priority sorting result is used to determine the urgency of the work order, and high-priority work orders are processed first, thereby reducing the impact of the fault on the business and improving customer satisfaction.

[0047] Specifically, the fault information is matched with the work order instance in the previously established fault feature database to obtain a matching work order instance, including: using Jaccard similarity to determine the similarity between the fault information and the work order instance in the previously established fault feature database; determining whether the similarity exceeds a preset threshold, and based on the similarity exceeding the preset threshold, using the corresponding work order instance as a matching work order instance.

[0048] It should be noted that by utilizing the Jaccard similarity, a set-based similarity measure is used to compare the fault information with a large number of work order instances in the fault feature database in a relatively short period of time, and to quickly match the instances that are most similar to the current fault information, thereby more accurately reflecting the essential characteristics of the fault and better distinguishing different degrees of similarity; by determining whether the similarity exceeds a preset threshold, the matching work order instance can be quickly determined, and its processing solution can be directly referenced to quickly locate the work order processing strategy, thereby improving the accuracy and reliability of work order processing.

[0049] Further, refer to Figure 2 The preset threshold is obtained based on the feedback information obtained by executing the corresponding processing strategy of the previously obtained work order data and optimizing the corresponding previously preset threshold; the previously preset threshold is a preset threshold used to determine the matching work order instance that matches the previously obtained work order data.

[0050] It should be noted that by using the feedback information after executing the processing strategy, the pros and cons of the processing strategy are comprehensively evaluated, and the preset thresholds are continuously optimized to make the preset thresholds more suitable for specific fault scenarios and processing requirements, thereby improving the accuracy of work order instance matching. In addition, the feedback information includes correction suggestions and customer satisfaction.

[0051] In an alternative embodiment, continue to refer to Figure 2, after using Jaccard similarity to determine the similarity between the fault information and the work order instance in the previously established fault feature database, it includes: determining that the similarity does not exceed a preset threshold, and processing the work order data using a preset processing method. It should be added that the preset processing method can be manual processing or further intelligent analysis and processing, and the intelligent analysis and processing can be further analyzing the work order fault type to determine the corresponding processing method according to the work order fault type. The specific configuration can be based on actual design requirements and is not further limited here.

[0052] Furthermore, after the work order data is processed using a preset processing method, it includes: storing the fault description corresponding to the work order data and the preset processing method in a fault feature database to optimize the fault feature database.

[0053] Step S14: According to the matching work order instance, the corresponding processing strategy is called and executed.

[0054] It should be added that the matching work order instances usually represent problems that have been successfully solved and their processing strategies have been verified in practice. Therefore, the processing strategies are quickly located based on the matching work order instances to improve the accuracy and reliability of fault handling.

[0055] In an optional embodiment, after calling and executing the corresponding processing strategy based on the matching work order instance, it includes: obtaining feedback information based on the execution of the corresponding processing strategy; optimizing the corresponding processing strategy in the fault feature database based on the feedback information, improving the fault feature database, and improving the accuracy and efficiency of future fault processing.

[0056] In summary, the embodiments of the present invention extract fault information from the acquired work order data to clarify the core content of the fault, remove irrelevant information interference, improve the accuracy and efficiency of subsequent processing, and match the extracted fault information with the work order instance in the fault feature database to quickly locate the verified processing strategy corresponding to the matching work order instance, thereby improving the accuracy of work order processing, reducing the possibility of erroneous processing, reducing the time and cost of analyzing and solving problems from scratch, and improving the speed and success rate of fault processing.

[0057] The work order processing device provided by the present invention is described below. The work order processing device described below and the work order processing method described above can be referenced to each other.

[0058] Figure 3 A schematic diagram of the structure of a work order processing device is shown, the device comprising: Data acquisition module 31, acquiring work order data; The information extraction module 32 extracts fault information from the work order data to obtain fault information; The work order matching module 33 matches the fault information with the work order instance in the previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; The work order processing module 34 calls and executes the corresponding processing strategy according to the matching work order instance.

[0059] It should be noted that the work order data may be data submitted by users based on the preset platform, including information such as customer questions, processing process, and resolution results, and is specifically determined based on the work order data actually received from users. In addition, the preset platform may be a designated platform or another user platform, which is not further limited here.

[0060] In an optional embodiment, the device further includes: a preprocessing module, which preprocesses the work order data after obtaining the work order data, and the preprocessing includes at least one of data cleaning and text conversion. It should be added that through data cleaning, special characters, punctuation marks and other elements in the work order description that may interfere with subsequent processing can be removed, noise interference can be reduced, and subsequent text analysis and understanding can be more accurate and efficient; through text conversion, standardized text representation is used to reduce format interference, which facilitates rapid extraction and understanding of the main content of the work order.

[0061] In a possible implementation, the work order data is in a picture format, and the information extraction module 32 includes: a feature extraction unit, which performs feature extraction on the work order data to obtain a feature vector; an information extraction unit, which uses natural language processing technology (Natural Language Processing, referred to as NLP) to extract fault information from the feature vector to obtain fault information.

[0062] Furthermore, the feature extraction unit is used to: input the work order data into the feature extraction model to obtain a feature vector output by the feature extraction model; wherein the feature extraction model is trained based on historical work order data and feature labels corresponding to the historical work order data.

[0063] It should be added that the feature extraction model can adopt a convolutional neural network (CNN) model or other models that can be used to extract feature vectors, which is not further limited here.

[0064] In another possible implementation, the work order data is in text format, and the information extraction module 32 further includes: an information extraction unit, which uses natural language processing technology to extract fault information from the work order data to obtain fault information; and a word embedding unit, which uses word embedding technology to convert the fault information into a vector.

[0065] It should be added that the word embedding unit is used to: input the fault information into the word embedding model to obtain the fault information in the vector form output by the word embedding model; wherein the word embedding model is trained based on the historical fault information and the feature labels corresponding to the historical fault information.

[0066] It is worth noting that the fault information used in training is extracted from historical work order data using NLP technology, which makes it easier for the word embedding model to learn the contextual relationship of words. By using historical fault information and the feature labels corresponding to the historical fault information, combined with the previously configured model parameters, the word embedding model is trained to continuously adjust the vector representation of the fault information to minimize the loss function, thereby facilitating the word embedding model to better capture the semantic associations and contextual information between words, and provide more valuable vector representations for subsequent text analysis and understanding.

[0067] In an optional embodiment, the feature extraction unit and / or the word embedding unit includes: a word segmentation subunit, which performs word segmentation on the work order data in the feature vector or text format to obtain multiple word segments; a part-of-speech tagging subunit, which performs part-of-speech tagging on each word segment to obtain a part-of-speech tag; an entity recognition subunit, which performs entity recognition on the word segmentation based on the part-of-speech tag to obtain an entity recognition result; and an information extraction subunit, which extracts fault information from each word segmentation based on the entity recognition result to obtain fault information.

[0068] Furthermore, the word segmentation can use a preset word segmentation tool, such as Jieba word segmentation, etc., and no further restrictions are made here. Accordingly, the part of speech of each word is marked to determine the part of speech of each word, such as noun, verb, adjective, etc., to help better understand the role of the word in the sentence, provide important clues for subsequent entity recognition, and improve the accuracy and efficiency of entity recognition.

[0069] In addition, the entity recognition subunit is used to: input each participle and the part-of-speech tag corresponding to each participle into the entity recognition model to obtain the entity recognition result output by the entity recognition model; wherein the entity recognition model is trained based on the participle training data and the entity tags corresponding to the participle training data, and the participle training data includes the training participles and the parts of speech corresponding to the training participles.

[0070] In an optional embodiment, the device further includes: a sentiment recognition module, which extracts fault information from the work order data and obtains the fault information, and then uses a previously established sentiment dictionary to identify the context of each participle and determine the contextual sentiment tendency of each participle; wherein the contextual sentiment tendency includes a positive sentiment tendency corresponding to positive words and a negative sentiment tendency corresponding to negative words, and the sentiment dictionary is constructed based on the positive words and negative words collected previously, and the positive words are used to characterize the urgency and importance of the fault, and the negative words are used to characterize the fault and the problems existing in the fault; a sentiment scoring module, which determines the sentiment score according to the contextual sentiment tendency of each participle and in combination with a preset weight allocation rule; wherein the preset weight allocation rule is used to limit the allocation weight corresponding to the contextual sentiment tendency; a sorting module, which prioritizes the corresponding work order data according to the sentiment score.

[0071] It should be noted that positive words and negative words can be set according to the actual work order data involved and actual design requirements, and no further restrictions are made here.

[0072] In addition, the emotion recognition module includes: a emotion analysis unit, which inputs each word segment into a language model to use a preset context window to identify the context of each word segment, and determines the emotion tendency in combination with a previously established emotion dictionary; wherein the language model is previously trained based on word segmentation training data and the emotion tendency labels corresponding to the word segmentation training data.

[0073] In an optional embodiment, the sentiment scoring module includes: a weight allocation unit, which allocates an initial weight to each participle based on a preset weight allocation rule; a weight adjustment unit, which adjusts the initial weight allocated to each participle according to the contextual sentiment tendency of each participle; a sentiment scoring unit, which uses the adjusted weight and the sentiment tendency to determine the sentiment score of each participle; and a score synthesis unit, which determines the sentiment score of the corresponding work order data based on the sentiment scores of all participles of the same work order data.

[0074] It should be noted that the design of the preset allocation rules can be specifically set according to actual design requirements or prior experience. For example, the negative weight of "serious failure" can be relatively high, and the positive weight of "quick resolution" can also be high; or, the preset allocation rules are used to limit the weight allocation according to the statistical results of the emotional tendencies of each participle. For example, if the statistical results of the positive emotional tendencies in each participle are higher than the statistical results of the negative emotional tendencies, it means that the positive emotional tendencies have a greater influence, and the corresponding weights can be appropriately increased. No further limitations are made here.

[0075] In addition, it should be noted that when adjusting the weights of each participle previously assigned based on preset allocation rules according to the identified context, the weight adjustment can be based on the frequency configuration of the participle in the context of sentiment tendency. For example, if the frequency of the participle appearing in the positive context is higher, the product weight can be further increased. If the frequency of the participle appearing in the negative context is higher, the negative weight can be further increased. The weight adjustment can be specifically configured according to the actual design or prior experience, and is not further limited here.

[0076] In an optional embodiment, the work order matching module 33 is used to: select the work order data with the highest priority based on the priority sorting result; and match the fault information corresponding to the selected work order data with the work order instance in the previously established fault feature database. It should be noted that the urgency of the work order is determined through the priority sorting result, and high-priority work orders are processed first, thereby reducing the impact of the fault on the business and improving customer satisfaction.

[0077] Specifically, the work order matching module 33 includes: a similarity determination unit, which uses Jaccard similarity to determine the similarity between the fault information and the work order instance in the previously established fault feature database; a threshold matching unit, which determines whether the similarity exceeds a preset threshold, and based on the similarity exceeding the preset threshold, uses the corresponding work order instance as a matching work order instance.

[0078] Furthermore, the preset threshold is obtained based on feedback information obtained by executing the corresponding processing strategy of the previously acquired work order data and optimizing the corresponding previously preset threshold; the previously preset threshold is a preset threshold used to determine the matching work order instance that matches the previously acquired work order data.

[0079] In an optional embodiment, the device also includes: other processing modules, after using Jaccard similarity to determine the similarity between the fault information and the work order instance in the previously established fault feature database, determine that the similarity does not exceed a preset threshold, and process the work order data using a preset processing method.

[0080] Furthermore, the device also includes: a storage module, after processing the work order data using a preset processing method, storing the fault description corresponding to the work order data and the preset processing method in the fault feature database to optimize the fault feature database.

[0081] In an optional embodiment, the device also includes: an information acquisition module, which obtains feedback information based on the execution of the corresponding processing strategy after calling and executing the corresponding processing strategy according to the matching work order instance; an optimization module, which optimizes the corresponding processing strategy in the fault feature database according to the feedback information, improves the fault feature database, and improves the accuracy and efficiency of future fault processing.

[0082] To summarize, the embodiments of the present invention use the information extraction module to extract fault information from the work order data acquired by the data acquisition module to clarify the core content of the fault, remove irrelevant information interference, and improve the accuracy and efficiency of subsequent processing; and use the work order matching module to match the extracted fault information with the work order instance in the fault feature database to quickly locate the verified processing strategy corresponding to the matching work order instance, improve the accuracy of work order processing by the work order processing module, reduce the possibility of erroneous processing, reduce the time and cost of analyzing and solving problems from scratch, and improve the speed and success rate of fault processing.

[0083] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the work order processing method, which includes: obtaining work order data; extracting fault information from the work order data to obtain fault information; matching the fault information with the work order instance in the previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; and calling and executing the corresponding processing strategy according to the matching work order instance.

[0084] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0085] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the work order processing method provided by the above methods, which method includes: obtaining work order data; extracting fault information from the work order data to obtain fault information; matching the fault information with the work order instance in a previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; and calling and executing the corresponding processing strategy according to the matching work order instance.

[0086] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the work order processing method provided by the above-mentioned methods, the method comprising: obtaining work order data; extracting fault information from the work order data to obtain fault information; matching the fault information with a work order instance in a previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; and calling and executing the corresponding processing strategy according to the matching work order instance.

[0087] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0088] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A work order processing method, characterized in that: include: Get work order data; Extracting fault information from the work order data to obtain fault information; Matching the fault information with a work order instance in a previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; According to the matching work order instance, the corresponding processing strategy is called and executed.

2. The work order processing method according to claim 1, characterized in that: Extracting fault information from the work order data to obtain fault information includes: Based on the fact that the work order data is in a picture format, feature extraction is performed on the work order data to obtain a feature vector; and fault information is extracted from the feature vector using natural language processing technology to obtain fault information; Based on the fact that the work order data is in text format, natural language processing technology is used to extract fault information from the work order data to obtain fault information; The fault information is converted into a vector using word embedding technology.

3. The work order processing method according to claim 2, characterized in that: By using natural language processing technology, fault information is extracted from the work order data in the feature vector or text format to obtain fault information, including: Segmenting the work order data in the feature vector or text format to obtain multiple segmented words; Performing part-of-speech tagging on each of the participles to obtain a part-of-speech tag; Based on the part-of-speech tag, entity recognition is performed on the word segmentation to obtain an entity recognition result; Based on the entity recognition result, fault information is extracted from each of the segmented words to obtain fault information.

4. The work order processing method according to claim 3, characterized in that: After extracting fault information from the work order data to obtain the fault information, the following steps are included: Using a previously established sentiment dictionary, the context of each of the segmented words is identified, and the context sentiment tendency of each of the segmented words is determined; wherein the context sentiment tendency includes a positive sentiment tendency corresponding to a positive word and a negative sentiment tendency corresponding to a negative word, and the sentiment dictionary is constructed based on the previously collected positive words and negative words, the positive words are used to characterize the urgency and importance of the fault, and the negative words are used to characterize the fault and the problems existing in the fault; Determine the sentiment score according to the context sentiment tendency of each of the segmented words in combination with a preset weight allocation rule; wherein the preset weight allocation rule is used to limit the allocation weight corresponding to the context sentiment tendency; Prioritize the corresponding work order data according to the sentiment score; Matching the fault information with a work order instance in a previously established fault feature database to determine the similarity between the fault information and the work order instance in the previously established fault feature database includes: Based on the priority sorting results, select the work order data with the highest priority; The fault information corresponding to the selected work order data is matched with the work order instance in the previously established fault feature database.

5. The work order processing method according to claim 1, characterized in that: Matching the fault information with a work order instance in a previously established fault feature database to obtain a matching work order instance, including: Using Jaccard similarity, determining the similarity between the fault information and the work order instance in the previously established fault feature database; It is determined whether the similarity exceeds a preset threshold, and based on the similarity exceeding the preset threshold, the corresponding work order instance is used as a matching work order instance.

6. The work order processing method according to claim 5, characterized in that: The preset threshold is obtained by optimizing the corresponding preset threshold based on the feedback information obtained by executing the processing strategy corresponding to the work order data obtained previously; The previously preset threshold is a preset threshold used when determining a matching work order instance that matches the previously acquired work order data.

7. The work order processing method according to claim 1, characterized in that: After calling and executing the corresponding processing strategy according to the matching work order instance, it includes: Obtain feedback information based on the execution of corresponding processing strategies; According to the feedback information, the corresponding processing strategy in the fault feature database is optimized.

8. A work order processing device, characterized in that: include: Data acquisition module, to obtain work order data; An information extraction module extracts fault information from the work order data to obtain fault information; A work order matching module matches the fault information with a work order instance in a previously established fault feature database to obtain a matching work order instance; wherein the fault feature database is established based on the work order instance and the corresponding processing strategy; The work order processing module calls and executes the corresponding processing strategy according to the matching work order instance.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the work order processing method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the work order processing method according to any one of claims 1 to 7 is implemented.

Images