CN112445893A - Information searching method, device, equipment and storage medium - Google Patents
Information searching method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112445893A CN112445893A CN201910838558.XA CN201910838558A CN112445893A CN 112445893 A CN112445893 A CN 112445893A CN 201910838558 A CN201910838558 A CN 201910838558A CN 112445893 A CN112445893 A CN 112445893A
- Authority
- CN
- China
- Prior art keywords
- work order
- order data
- target
- data analysis
- analysis model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000007405 data analysis Methods 0.000 claims abstract description 229
- 238000012545 processing Methods 0.000 claims abstract description 97
- 238000013507 mapping Methods 0.000 claims abstract description 59
- 238000012423 maintenance Methods 0.000 claims description 82
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000002360 preparation method Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000012706 support-vector machine Methods 0.000 description 7
- 230000008439 repair process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses an information searching method, an information searching device, information searching equipment and a storage medium, wherein the method comprises the following steps: extracting target keywords of a task work order to be processed; searching target work order data matched with the target keywords based on an industry exclusive word bank, wherein the industry exclusive word bank is used for storing a mapping relation between the keywords and the work order data; and according to the target search task, analyzing and processing the target work order data by using the work order data analysis model, and generating a target search result according to the output result of the work order data analysis model, wherein the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data. Therefore, abundant reference information is provided for aftermarket service personnel, and the aftermarket service personnel are effectively helped to rapidly make a reasonable service scheme.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information search method, apparatus, device, and storage medium.
Background
The aftermarket service refers to various services provided for problems occurring during the use of the goods after the goods are sold, such as maintenance service, accessory service, and the like.
Taking maintenance service in market service as an example later, when a user needs to report and repair problems occurring in the using process of a commodity, the user can upload fault description information of the commodity through a maintenance service system; then, a background dispatching engineer correspondingly distributes a maintenance engineer and issues a task work order comprising the fault description information to the maintenance engineer; and after receiving the task work order, the maintenance engineer correspondingly formulates a maintenance scheme based on the fault description information in the task work order and goes to the site to carry out maintenance work.
However, the following problems are generally present when performing the above-described maintenance service: for a maintenance engineer, the actual fault situation cannot be known in detail generally according to the content in the task work order, so that the fault reason cannot be accurately pre-judged, and a reasonable maintenance scheme cannot be formulated correspondingly; thus, the progress of maintenance work is seriously affected, resulting in an extended maintenance service period, increased dead time of the malfunctioning device, and increased maintenance costs.
Therefore, how to provide abundant reference information for aftermarket service personnel and help the aftermarket service personnel to quickly establish a related service scheme becomes a problem to be solved urgently at present in the aftermarket service industry.
Disclosure of Invention
The embodiment of the application provides an information searching method, an information searching device, information searching equipment and a storage medium, which can provide abundant reference information for aftermarket service personnel and effectively help the aftermarket service personnel to quickly make a reasonable service scheme.
In view of the above, a first aspect of the present application provides an information searching method, including:
extracting target keywords of a task work order to be processed;
searching target work order data matched with the target keywords based on an industry exclusive word bank; the industry exclusive word bank is used for storing a mapping relation between the key words and the work order data;
and analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model, wherein the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
Optionally, the industry-specific lexicon is constructed in the following manner:
collecting a plurality of pieces of historical work order data;
performing data cleaning processing on the historical work order data to generate work order data meeting a preset data structure;
determining keywords associated with the work order data, establishing a mapping relation between the keywords and the work order data as a first mapping relation, and storing the first mapping relation to the industry exclusive word bank.
Optionally, the method further includes:
acquiring an industry high-frequency word as a keyword;
acquiring service processing data associated with the industry high-frequency words as work order data;
and establishing a mapping relation between the industry high-frequency words and the service processing data as a second mapping relation, and storing the second mapping relation to the industry exclusive word bank.
Optionally, the work order data analysis model includes a plurality of work order data analysis submodels, and different work order data analysis submodels correspond to different search tasks;
then, according to the target search task, analyzing and processing the target work order data by using a work order data analysis model, and obtaining an output result of the work order data analysis model as a target search result, including:
calling a work order data analysis sub-model corresponding to the target search task in the work order data analysis model;
and analyzing and processing the target work order data by utilizing the called work order data analysis submodel, and generating the target search result according to the output result of the work order data analysis submodel.
Optionally, when the target search task is recommending a similar historical work order, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining the similarity between the target work order data and the task work order to be processed by using the work order data analysis model as the similarity corresponding to the target work order data;
and sorting the similarity corresponding to each target work order data in a descending order, and taking the target work order data corresponding to the similarity of the top N bits as the target search result.
Optionally, when the target search task is a statistical fault cause, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining each fault reason related in the target work order data by using the work order data analysis model, and counting the occurrence frequency of each fault reason;
and generating a fault reason statistical chart according to each fault reason and the occurrence frequency thereof, and taking the fault reason statistical chart as the target search result.
Optionally, when the target search task is to determine to replace a spare part, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining each replacement spare part involved in the target work order data by using the work order data analysis model;
and generating a replacement spare part preparation list according to each replacement spare part as the target search result.
Optionally, when the target search task is backtracking of a related work order problem, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining potential faults involved in the target work order data using the work order data analysis model;
searching a maintenance scheme corresponding to the potential fault based on the industry exclusive word bank;
and generating the target search result according to the potential fault and the maintenance scheme corresponding to the potential fault.
Optionally, when the target search task is recommended by a maintenance engineer, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining each maintenance engineer related to the target work order data and the corresponding maintenance condition thereof by using the work order data analysis model;
and generating a maintenance engineer recommendation list as the target search result according to the maintenance engineers and the corresponding maintenance conditions thereof.
A second aspect of the present application provides an information search apparatus, the apparatus including:
the extraction module is used for extracting target keywords in the task work order to be processed;
the searching module is used for searching target work order data matched with the target keywords based on an industry exclusive word bank; the industry exclusive word bank is used for storing a mapping relation between the key words and the work order data;
the processing model is used for analyzing and processing the target work order data by using the work order data analysis model according to a target search task and generating a target search result according to an output result of the work order data analysis model; and the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
A third aspect of the application provides an electronic device comprising at least one processor, and at least one memory connected to the processor, a bus;
the processor and the memory complete mutual communication through the bus;
the processor is configured to call program instructions in the memory to perform the information search method of the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium for storing a computer program for executing the information search method of the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
the embodiment of the application provides an information searching method, which is characterized in that a work order searching engine is constructed based on an industry exclusive word bank and a work order data analysis model, and relevant workers can search self-required reference information for a to-be-processed task work order by using the work order searching engine. Specifically, in the information search method provided in the embodiment of the present application, a target keyword in a task work order to be processed is extracted first, and then target work order data matched with the extracted target keyword is searched based on an industry-specific word bank in which a mapping relationship between the keyword and the work order data is stored; and then according to the target search task, analyzing the target work order data by using the work order data analysis model, and finally generating a target search result according to the output result of the work order data analysis model, wherein the work order data analysis model can generate a search result corresponding to the search task according to the work order data. The information searching method searches the work order data related to the work order to be processed through the industry exclusive word bank, and generates a searching result corresponding to the target searching task selected by the user based on the searched work order data through the work order data analysis model; therefore, a mature and complete work order searching mechanism is provided for relevant workers, and the relevant workers can obtain sufficient reference information based on the information, so that the relevant workers can quickly make a reasonable service scheme conveniently, and the service efficiency and the service quality are improved.
Drawings
Fig. 1 is a schematic view of an application scenario of an information search method provided in an embodiment of the present application;
fig. 2 is a schematic flowchart of an information search method according to an embodiment of the present application;
FIG. 3 is a schematic view of a display interface of similar historical work order recommendation results provided by an embodiment of the present application;
FIG. 4 is a diagram illustrating a statistical chart of failure causes according to an embodiment of the present disclosure;
FIG. 5 is a schematic illustration of a replacement spare part preparation list provided by an embodiment of the present application;
fig. 6 is a schematic view of a display interface for backtracking a related work order problem provided in an embodiment of the present application;
fig. 7 is a schematic flowchart of a method for constructing an industry-specific thesaurus according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an information search apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an apparatus provided in an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, after-market service personnel often cannot obtain enough reference information before developing services, so that the formulation of a service scheme is influenced, and further the problems of low after-market service efficiency, poor service quality and the like are caused.
In view of the above technical problems, an embodiment of the present application provides an information search method, in which a work order search engine is built based on an industry-specific word bank and a work order data analysis model, and a relatively complete reference information search mechanism is provided for relevant workers through the work order search engine.
Specifically, in the information search method provided by the embodiment of the application, a target keyword is extracted from a task work order to be processed; then, searching target work order data matched with the extracted target keywords based on an industry exclusive word bank for storing a mapping relation between the keywords and the work order data; and then, according to the target search task, analyzing and processing the searched target work order data by using a work order data analysis model, and generating a target search result according to an output result of the work order data analysis model, wherein the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
According to the information searching method, the work order data related to the work orders to be processed are searched through the industry exclusive word bank, and the searching result corresponding to the target searching task selected by the user is generated based on the searched target work order data through the work order data analysis model. Therefore, related workers can quickly and effectively search the self-required reference information related to the work order of the task to be processed by utilizing the work order search engine consisting of the industry exclusive word bank and the work order data analysis model, so that the related workers can quickly make a reasonable service scheme, and the service efficiency and the service quality are improved.
It should be understood that the information search method provided in the embodiment of the present application may be applied to a server providing a data search service, where the server may specifically be an application server or a Web server, and when actually deployed, the server may be an independent server or a cluster server, and the server may search, correspondingly, work order data related to a to-be-processed work order for the to-be-processed work order uploaded by multiple terminal devices, and generate a target search result based on the searched work order data.
In order to facilitate understanding of the technical solutions provided in the embodiments of the present application, the following describes an information search method provided in the embodiments of the present application with reference to an actual application scenario.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of an information search method provided in an embodiment of the present application. The application scenario includes terminal device 110 and server 120. The terminal device 110 faces the relevant staff, and the relevant staff can transmit the job order of the task to be processed to the server 120 through the terminal device 110; in addition, the relevant staff can also select the target search task for the job order to be processed through the terminal device 110. The server 120 stores an industry-specific lexicon 121 and supports the operation of the work order data analysis model 122, and after receiving the work order of the task to be processed and the target search task transmitted by the terminal device 110, the server 120 can execute the information search method provided by the embodiment of the application for the work order of the task to be processed, so as to obtain a search result corresponding to the target search task.
Specifically, after receiving the to-be-processed job order allocated to the relevant worker, the relevant worker may upload the to-be-processed job order to the server 120 through the terminal device 110, and meanwhile, the relevant worker may select a target search task to be executed for the to-be-processed job order through the terminal device 110, for example, select to search historical job order data similar to the to-be-processed job order, select to search a fault reason corresponding to the to-be-processed job order, and the like.
After receiving the to-be-processed task work order and the target search task transmitted by the terminal device 110, the server 120 extracts a target keyword in the to-be-processed task work order, and then searches for target work order data matched with the extracted target keyword based on an industry-specific word bank 121 stored in the server, wherein a mapping relation between the keyword and the work order data is stored in the industry-specific word bank 121; further, the server 120 further analyzes and processes the found target work order data by using the work order data analysis model 122 according to the target search task, and generates a target search result according to the output result of the work order data analysis model 122, and the work order data analysis model 122 can generate a search result corresponding to the search task according to the work order data. Finally, the server 120 sends the obtained search result to the terminal device 110, so that the search result searched for the uploaded job order to be processed is shown to the relevant staff through the terminal device 110.
It should be understood that the application scenario shown in fig. 1 is only an example, and in practical application, the information search method provided in the embodiment of the present application may be applied to other application scenarios besides the application scenario shown in fig. 1, and no limitation is made to the application scenario to which the information search method provided in the embodiment of the present application is applied.
The information searching method provided by the present application is described below by way of an embodiment.
Referring to fig. 2, fig. 2 is a schematic flowchart of an information search method according to an embodiment of the present disclosure. For convenience of description, the following embodiments are described with a server as an execution subject. As shown in fig. 2, the information search method includes the steps of:
step 201: and extracting target keywords of the task work order to be processed.
When related workers need to search reference information related to a certain task work order to be processed, the related workers can transmit the task work order to be processed to a server through terminal equipment, and after the server obtains the task work order to be processed, target keywords of the task work order to be processed are extracted.
Specifically, when extracting a target keyword for a task work order to be processed, the server may first perform word segmentation, stop word introduction, feature processing, regular extraction, part-of-speech tagging and the like on a text corresponding to the task work order to be processed, so as to obtain a candidate keyword list corresponding to the task work order to be processed; and then, determining a target keyword of the task work order to be processed based on the candidate keyword list by adopting a keyword extraction algorithm.
It should be noted that the keyword extraction algorithm adopted by the server may specifically include: a TF-IDF (term frequency-inverse document frequency) algorithm, a TextRank algorithm, a semantic-based keyword extraction algorithm, a term position weighted TextRank algorithm, a document topic generation model (LDA) based keyword extraction algorithm, and the like, where the keyword extraction algorithm employed by the server is not limited.
It should be understood that the server may extract one target keyword or a plurality of target keywords for the job order to be processed, and the number of the target keywords extracted by the server is not limited at all.
Step 202: searching target work order data matched with the keywords based on an industry exclusive word bank; the industry exclusive word bank is used for storing the mapping relation between the keywords and the work order data.
After acquiring a target keyword of a task work order to be processed, the server searches work order data matched with the target keyword based on an industry exclusive word bank to serve as target work order data; specifically, the server may first search the keyword in the industry-specific lexicon, and then obtain the work order data having a mapping relationship with the searched keyword as the target work order data, where the target work order data thus searched is actually the work order data related to the task work order to be processed.
It should be noted that the industry exclusive lexicon stores a large number of mapping relationships between keywords and work order data; the keywords related in the industry-specific thesaurus may specifically include: extracting and processing the historical work order data to obtain keywords, high-frequency words in the industry field and the like; the work order data related in the industry-specific thesaurus may specifically include: the work order data obtained by performing data cleaning and data integration processing on historical work order data, mature business processing data in the industry field and the like. The next embodiment will describe in detail the construction method of the industry-specific thesaurus, and refer to the related description in this embodiment in detail.
It should be understood that, in practical applications, the industry-specific thesaurus may be specifically deployed on a server for executing the information search method provided in the embodiment of the present application, and may also be deployed on other servers. When the industry-specific word bank is deployed on a server for executing the information searching method provided by the embodiment of the application, the server can directly call the industry-specific word bank and search target work order data matched with the keywords of the task work order to be processed based on the industry-specific word bank. When the industry-specific word bank is deployed on other servers, the server for executing the information search method provided by the embodiment of the application can communicate with the server to call the industry-specific word bank deployed on the server, so that target work order data matched with the keywords of the task work orders to be processed are searched based on the industry-specific word bank.
It should be noted that the mapping relationship between the keyword and the work order data stored in the industry exclusive lexicon actually refers to the mapping relationship between the keyword and the work order data identifier, and the work order data identifier may be a number pre-allocated to each work order data; the server can determine a target work order data identifier matched with the target keyword based on the industry exclusive word stock, and then the server can call a database for storing the work order data, and search the target work order data in the database for storing the work order data according to the target work order data identifier matched with the target keyword. It should be understood that the database for storing the work order data may be specifically deployed on a server for executing the information search method provided in the embodiment of the present application, and may also be deployed on other servers.
It should be understood that, in practical applications, the server may search only one piece of target work order data matched with the task work order to be processed based on the industry-specific thesaurus, or may search a plurality of pieces of target work order data matched with the task work order to be processed, where no limitation is imposed on the number of pieces of target work order data searched by the server based on the industry-specific thesaurus.
Step 203: according to a target search task, analyzing and processing the target work order data by using a work order data analysis model, and generating a target search result according to an output result of the work order data analysis model; and the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
After the server finds the target work order data related to the work order of the task to be processed based on the industry exclusive word stock, the server can further call a work order data analysis model to analyze and process the target work order data found in the step 202 by the server according to the target search task specified by the related staff, further obtain an output result of the work order data analysis model, and generate a target search result according to the output result. And finally, the server sends the target search result to the terminal equipment so as to show the target search result to the user through the terminal equipment.
It should be understood that, in practical application, the relevant staff may select the target search task to be performed on the task work order to be processed while uploading the task work order to be processed. In addition, the relevant staff may also select the target search task based on the searched target work order data after the server completes the search of the target work order data based on the industry-specific thesaurus, for example, the server may return the target work order data searched in step 202 to the terminal device, and further, the relevant staff may further select the target search task based on the target work order data searched by the terminal device. The time for the relevant staff to select the target search task is not limited at all.
The work order data analysis model is a model that can generate a search result corresponding to a search task from the work order data, and may be an independent model dedicated to processing a specific search task or a comprehensive model for compatibly processing a plurality of search tasks. When the work order data analysis model is an independent model dedicated to processing a certain specific search task, the server only supports the user to select the specific search task as the target search task, and the server can directly utilize the work order data analysis model to generate a target search result based on the target work order data found in step 202. When the work order data analysis model is a comprehensive model for compatibly processing multiple search tasks, the server may support a user to select any one or more search tasks from the multiple search tasks as a target search task, and the server needs to call a processing logic corresponding to the target search task in the work order data analysis model according to the target search task selected by the user, and generate a target search result based on the target work order data found in step 202.
When the worksheet data analysis model is an independent model dedicated to processing a certain specific search task, the model may specifically be an independent model dedicated to recommending similar historical worksheets, an independent model dedicated to counting failure causes, an independent model dedicated to determining replacement spare parts, an independent model dedicated to backtracking related worksheets, an independent model dedicated to recommending maintenance engineers, or the like; in other words, in practical applications, the search tasks supported by the work order data analysis model may be set according to actual requirements, and the search tasks are only examples, and no limitation is made on the search tasks specifically processed by the work order data analysis model.
It should be noted that the work order data analysis model may specifically be a bp (back propagation) neural network model, a Naive Bayes (NB) model, a Support Vector Machine (SVM) model, or the like, and the model structure of the work order data analysis model in the embodiment of the present application is not limited at all.
The BP neural network model is a multilayer feedforward neural network obtained by training according to an error back propagation algorithm, and is the most widely applied neural network at present; the calculation process of the BP neural network consists of a forward calculation process and a backward calculation process. The classification principle of the NB model is that the prior probability of a certain object is calculated by utilizing a Bayesian formula, namely the probability that the object belongs to a certain class, and then the class with the maximum posterior probability is selected as the class to which the object belongs. The SVM model is a generalized linear classifier for binary classification of data in a supervised learning mode, a decision boundary of the SVM model is a maximum edge distance hyperplane for solving a learning sample, the SVM model calculates empirical risks by using a hinge loss function, and a regularization term is added into a solving system to optimize structural risks, so that the SVM model is a classifier with sparsity and robustness.
In addition, when the work order data analysis model is trained, a large number of training samples related to specific search tasks can be obtained, the pre-constructed initial work order data analysis model is trained, for example, when the specific search tasks supported by the work order data analysis model are statistical failure causes, the server can obtain a large number of training samples including the work order data and the corresponding failure causes, and the pre-constructed initial work order data analysis model is repeatedly and iteratively trained by using the training samples. Further, judging the model performance of the work order data analysis model based on the Precision (Precision) and/or Recall (Recall) of the work order data analysis model; in other words, in the process of training the work order data analysis model, if the accuracy and/or the recall rate of the work order data analysis model is found to reach the preset conditions, the work order data analysis model can be considered to have met the training end conditions, the work order data analysis model has better processing performance at present, the training of the work order data analysis model can be ended, and the work order data analysis model is put into practical use.
In the case where the work order data analysis model is a comprehensive model for compatibly processing a plurality of search tasks, the work order data analysis model may include a plurality of work order data analysis submodels, and different work order data analysis submodels correspond to different search tasks. Correspondingly, when the work order data analysis model is used for generating a search result corresponding to the search task based on the target work order data, the server can call a work order data analysis sub-model corresponding to the target search task in the work order data analysis model, and further, the work order data analysis sub-model is used for analyzing and processing the target work order data, and the output result of the work order data analysis sub-model is the target search result.
For example, assuming that the work order data analysis model supports five search tasks of processing and recommending similar historical work orders, counting failure causes, determining and replacing spare parts, tracing related work order problems and recommending the work order by a maintenance engineer, correspondingly, the work order data analysis model comprises a work order data analysis submodel for recommending similar historical work orders, a work order data analysis submodel for counting failure causes, a work order data analysis submodel for determining and replacing spare parts, a work order data analysis submodel for tracing related work order problems and a work order data analysis submodel for recommending the maintenance engineer; assuming that the target search task selected by the user is similar historical work order recommendation, the server calls a work order data analysis sub-model for recommending similar historical work orders in the work order data analysis model, and correspondingly processes the target work order data searched by the server by utilizing an industry exclusive word bank so as to determine the similar historical work order; and when the target search task selected by the user is other search tasks, the server correspondingly calls the work order data analysis sub-model corresponding to the search task in the work order data analysis model for processing.
It should be understood that when the work order data analysis model can support processing of multiple search tasks, a user can select one or more search tasks from the multiple search tasks as target search tasks, when the user selects one of the search tasks as a target search task, the server directly calls the work order data analysis submodel corresponding to the target search task in the work order data analysis model to process, when the user selects multiple search tasks as target search tasks, the server needs to call a plurality of work order data analysis submodels corresponding to the target search tasks in the work order data analysis model to process, and finally, processing results generated by the work order data analysis submodels are all used as target search results.
It should be noted that, in practical applications, each work order data analysis submodel in the work order data analysis model may be constructed based on different model structures, or may be constructed based on the same model structure; when each work order data analysis submodel has the same model structure, each work order data analysis submodel generally has different model parameters.
It should be noted that each work order data analysis submodel in the work order data analysis model may specifically be a BP neural network model, an NB model, an SVM model, or the like, and the model structure of each work order data analysis submodel in the work order data analysis model is not limited at all here.
In addition, when the work order data analysis model is trained, each work order data analysis submodel needs to be trained in advance, and specifically, when each work order data analysis submodel is trained, a training sample corresponding to a search task supported by the work order data analysis submodel needs to be obtained first; for example, when a work order data analysis submodel for recommending similar historical work orders is trained, a large number of training samples including a plurality of pieces of work order data and the similarity among the plurality of pieces of work order data need to be obtained; when a work order data analysis submodel for counting fault reasons is trained, a large number of training samples comprising work order data and corresponding fault reasons are required to be obtained; for the work order data analysis submodel for determining the replacement spare parts, a large number of training samples comprising the work order data and the related replacement spare parts are required to be obtained; when a work order data analysis submodel for backtracking related work order problems is trained, a large number of training samples comprising work order data and related potential faults thereof need to be obtained; when a work order data analysis submodel for recommending a maintenance engineer is trained, a large amount of work order data, related maintenance engineers and maintenance conditions corresponding to the maintenance engineers need to be acquired; and so on. And after the training sample is obtained, repeatedly and iteratively training the corresponding work order data analysis submodel by using the obtained training sample until the work order data analysis submodel meets the training ending condition.
When the training of the work order data analysis model is judged to be finished, the accuracy and/or recall rate of each work order data analysis submodel is comprehensively considered, and the model performance of the work order data analysis model is comprehensively judged based on the accuracy and/or recall rate; in other words, in the process of training the work order data analysis model, if it is determined that the accuracy and/or the recall rate of each work order data analysis submodel all meet the preset conditions, the whole work order data analysis model can be considered to have met the training end conditions, each work order data analysis submodel in the work order data analysis model has better processing performance, and at this time, the training of the work order data analysis model can be ended and put into practical application.
In order to facilitate understanding of the specific processing logic of the work order data analysis processing model, the following description is provided for processing modes adopted by the work order data analysis model when processing several common search tasks. It should be understood that, the work order data analysis model hereinafter may be specifically an independent model dedicated to processing a certain specific search task, or may be an integrated model for compatibly processing a plurality of search tasks, and when the work order data analysis model is an integrated model, it is necessary to invoke a work order data analysis sub-model corresponding to the search task for processing when it is specifically applied.
When the target search task is a recommended similar historical work order, the server needs to determine the similarity between target work order data and a to-be-processed task work order by using a work order data analysis model, and the similarity is used as the similarity corresponding to the target work order data; furthermore, the similarity corresponding to each target work order data is sorted in a descending order, and the target work order data corresponding to the similarity of the top N (N is a positive integer greater than or equal to 1) bits is used as a target search result.
Specifically, the server may calculate, by using the work order data analysis model, a similarity between each item standard work order data searched in step 202 and the task work order to be processed, and use the similarity thus calculated as a similarity corresponding to each item standard work order data; and then, sequencing the similarity according to the sequence of the similarity from large to small, and selecting the target work order data corresponding to N similarity in the front sequence as a target search result.
Referring to fig. 3, fig. 3 is a schematic view of a display interface of similar historical work order recommendation results. As shown in fig. 3, on the similar historical work order recommendation result display interface, the similarity between each item of standard work order data in the target search result and the to-be-processed task work order, the work order number, the fault name, the work order title, and the details of each item of standard work order data are displayed, and the related worker triggers and clicks the detail display control in the column where the target work order data is located, so that the detailed content of the item of standard work order data, such as the solution involved in the target work order data, is correspondingly displayed.
It should be understood that, in practical applications, the value of N may be set according to practical situations, and the value of N is not specifically limited herein. In addition, the historical work order recommendation result display interface shown in fig. 3 is only an example, and in practical applications, the historical work order recommendation result display interface may be represented in other forms, and the representation form of the historical work order recommendation result display interface is not limited at all.
When the target search task is the statistical fault reason, the server needs to determine each fault reason related in the target work order data by using the work order data analysis model and count the occurrence frequency of each fault reason; furthermore, a fault reason statistical chart is generated according to each fault reason and the occurrence frequency thereof and used as a target search result.
Specifically, the server generally relates to relevant fault reasons in target work order data searched based on an industry exclusive word bank, and when a target search task selected by a user is a statistic fault reason, the server can utilize a work order data analysis model to count each fault reason related in the target work order data and count the occurrence frequency of each fault reason in the target work order data; and then, according to the counted fault reasons and the occurrence frequency corresponding to each fault reason, a fault reason statistical chart is obtained through sorting and is used as a target search result, and the fault reason statistical chart can show the possible occurrence probability of each fault reason.
Referring to fig. 4, fig. 4 is a diagram illustrating a statistical chart of the causes of a fault. As shown in fig. 4, the fault cause statistical chart shows the occurrence probability of each fault cause, which is determined based on the historical occurrence frequency of the fault cause in the target work order data. It should be understood that the fault cause statistical chart shown in fig. 4 is only an example, and in practical applications, the fault cause statistical chart may also be specifically expressed in the form of a sector chart, a bar chart, or the like, and the specific representation form of the fault cause statistical chart is not limited in any way herein.
When the target search task is to determine to replace spare parts, the server needs to determine each replaced spare part related in the target work order data by using the work order data analysis model; further, a replacement spare part preparation list is generated as a target search result from each replacement spare part involved in the target work order data.
Specifically, the server generally relates to replacement spare parts used in a historical service task in target work order data searched based on an industry-specific word stock, and when the target search task selected by a user is to determine the replacement spare parts, the server can use a work order data analysis model to count all the replacement spare parts related in the target work order data and count the historical use times of all the replacement spare parts; furthermore, a replacement spare part preparation list is obtained through sorting according to the counted historical use times of each replacement spare part and each replacement spare part, the replacement spare part preparation list can comprise the historical use times corresponding to each replacement spare part and each replacement spare part related in the target work order data, and therefore replacement parts required to be prepared for related workers are prompted, and the occurrence of human accidents of missing the replacement spare parts is prevented.
Referring to fig. 5, fig. 5 is a schematic illustration of a replacement spare part preparation list. As shown in fig. 5, the replacement parts list includes the replacement parts related to the target work order data and the respective historical usage times of each replacement part. It should be understood that the replacement spare part preparation list shown in fig. 5 is only an example, and in practical applications, the replacement spare part preparation list may also be in other forms, and the specific form of the replacement spare part preparation list is not limited herein.
When the target search task is backtracking of related work order problems, the server can determine potential faults related to target work order data by using a work order data analysis model; then, searching a maintenance scheme corresponding to the related potential fault based on the industry exclusive word bank; and further, generating a target search result according to the latent fault and the maintenance scheme corresponding to the latent fault.
Specifically, in some cases, the occurrence of some root cause faults may also correspondingly cause the generation of latent faults related to the root cause faults, and such latent faults may explode simultaneously with the root cause faults or after the root cause faults are solved; the server generally relates to related potential faults in target work order data searched based on the industry exclusive word bank, when a target search task selected by a user is backtracking of related work order problems, the server can determine the potential faults related to the target work order data by using a work order data analysis model, and searches a maintenance scheme corresponding to the potential faults based on the industry exclusive word bank; furthermore, the work order data analysis model may generate a target search result based on the latent fault and the maintenance plan corresponding to the latent fault. Therefore, a maintenance engineer can repair the root fault and the related potential faults at one time without repeatedly going to the site for fault maintenance, and the fault maintenance efficiency is greatly improved.
Referring to fig. 6, fig. 6 is a schematic view of a display interface for backtracking related work order problems. As shown in fig. 6, potential faults related to the target work order task and the historical occurrence times corresponding to each potential fault are displayed on the display interface, and the relevant worker triggers and clicks the column where the potential fault is located, so that a detailed solution corresponding to the potential fault is triggered and displayed.
It should be understood that the display interface for the backtracking related work order problem shown in fig. 6 is only an example, and in practical applications, the display interface for the backtracking related work order problem may also be represented in other forms, and no limitation is made to the specific representation form of the display interface for the backtracking related work order problem here.
When the target search task is recommended by a maintenance engineer, the server can determine each maintenance engineer and each corresponding maintenance condition related to the target work order data by using the work order data analysis model; and further, generating a maintenance engineer recommendation list as a target search result according to each maintenance engineer and the corresponding maintenance condition thereof.
Specifically, the server generally relates to related maintenance engineers and maintenance conditions of the related maintenance engineers in target worksheet data searched based on an industry-specific thesaurus, when a target search task selected by a user is recommended to a maintenance engineer, the server can determine the maintenance conditions of the maintenance engineers and the maintenance engineers related to the target worksheet data by using a worksheet data analysis model, and the maintenance conditions in the maintenance engineering can be determined according to evaluation of a customer on the maintenance engineers, one-time repair rate of the maintenance engineers, and average repair time of the maintenance engineers; further, the service engineer recommendation list is sorted and obtained according to the service condition of each service engineer, and for example, a service engineer with a good service condition may be displayed in the front of the service engineer recommendation list, and a service engineer with a bad service condition may be displayed in the rear of the service engineer recommendation list. Therefore, a proper maintenance engineer is intelligently recommended for the dispatching engineer, and the working pressure of the dispatching engineer is reduced.
It should be understood that, in practical applications, in addition to designing the work order data analysis model or the work order data analysis submodel for the above several exemplary search tasks, the work order data analysis model or the work order data analysis submodel for other search tasks may also be designed according to practical requirements, and no limitation is made on the search tasks that can be processed by the work order data analysis model or the work order data analysis submodel in the embodiments of the present application.
It should be noted that, the information search method provided by the embodiment of the present application may search the reference information based on the job order of the task to be processed, and may also search the reference information directly based on the keyword input by the user; specifically, the server can directly acquire a keyword input by a user, then search target work order data related to the keyword based on an industry-specific word stock, and further generate a target search result corresponding to a target search task based on the target work order data by using the work order data analysis model.
According to the information searching method, the work order data related to the work orders to be processed are searched through the industry exclusive word bank, and the searching result corresponding to the target searching task selected by the user is generated based on the searched work order data through the work order data analysis model. Therefore, related workers can quickly and effectively search the self-required reference information related to the work order of the task to be processed by utilizing the work order search engine consisting of the industry exclusive word bank and the work order data analysis model, so that the related workers can quickly make a reasonable service scheme, and the service efficiency and the service quality are improved.
The method for constructing the industry-specific lexicon in the above embodiment is described below by an embodiment.
Referring to fig. 7, fig. 7 is a schematic flow chart of the industry-specific thesaurus construction method provided in the embodiment of the present application. For convenience of description, the following embodiments are described with a server as an execution subject. As shown in fig. 7, the method for constructing the industry-specific thesaurus includes the following steps:
step 701: multiple pieces of historical work order data are collected.
In an actual application scene, a server can collect a large amount of historical work order data from each information system; for example, the server may obtain the historical worksheet data stored therein from a Customer Relationship Management (CRM) system, a service provider Management system, or an enterprise self-built information Management system, etc. The historical work order data collected by the server specifically comprises a service request work order, a fault work order, a spare part replacement work order and the like, namely the server can correspondingly collect the work order data of a specific type according to the actual application requirement as the historical work order data according to which the industry exclusive word bank is constructed, and no limitation is made on the type of the historical work order data collected by the server.
In specific implementation, the server may adopt an Extract transform load (ELT) technology to Extract, convert, and load the historical work order data from the source end to the destination end. Of course, the server may also collect the historical work order data in other manners, and the manner of collecting the historical work order data is not limited herein.
Step 702: and carrying out data cleaning processing on the historical work order data to generate work order data meeting a preset data structure.
After the server collects a large amount of historical work order data, the server needs to further perform data cleaning processing on the historical work order data collected by the server, so that the collected historical work order data are organically fused, and the fused work order data meet a preset data structure.
In one possible implementation, the data structure formed by performing the data cleaning process on the historical work order data may include the following attribute information: the system comprises a work order number, an equipment code, an equipment model, an equipment category, a fault classification, a fault level, a fault description, a processing scheme, user feedback information, maintenance evaluation information, a maintenance engineer, a replacement spare part list, fault time, repair completion time, repair duration and the like. Of course, in practical applications, the data structure obtained by performing data cleaning processing on the historical work order data may include other attribute information in addition to the attribute information, and any limitation is not made on the attribute information included in the work order data satisfying the preset data structure obtained by performing data cleaning processing on the historical work order data.
Step 703: determining keywords associated with the work order data, establishing a mapping relation between the keywords and the work order data as a first mapping relation, and storing the first mapping relation to the industry exclusive word bank.
After historical work order data are subjected to data cleaning to obtain work order data meeting a preset data structure, keywords related to the work order data can be further determined, a mapping relation between the work order data and the keywords is established to serve as a first mapping relation, the first mapping relation is further stored to an industry exclusive word bank, the related keywords are determined according to the work order data obtained based on the step 702, and the mapping relation between the keywords and the work order data is stored to the industry exclusive word bank.
During specific implementation, the server can firstly extract keywords to obtain a keyword candidate list aiming at large text character data in the work order data, such as fault description information, a processing scheme, user feedback information, maintenance evaluation information and the like; specifically, the server may perform processing such as chinese coding problem processing, chinese word segmentation, stop word introduction, feature processing, regular extraction, part of speech tagging on the large text character data in the work order data, so as to extract keywords from the large text character data to form a keyword candidate list. Further, the server may perform new word exploration, word frequency statistics, part of speech tagging, expert summary, and the like on the keyword candidate list to further determine keywords associated with the work order data based on the keyword candidate list. And finally, establishing a mapping relation between the keywords obtained through the processing and the work order data, and importing the mapping relation into an industry exclusive word bank.
It should be noted that the first mapping relationship between the keyword and the work order data stored in the industry exclusive word library is substantially the first mapping relationship between the keyword and the work order data identifier, that is, the server may generate the work order data identifier corresponding to each work order data when generating each work order data, and after determining the first mapping relationship between the keyword and the work order data, store the first mapping relationship between the keyword and the work order data identifier corresponding to the work order data into the industry exclusive word library.
Optionally, in order to ensure the industriality, high efficiency and comprehensiveness of the industry exclusive lexicon, in the process of constructing the industry exclusive lexicon by the server, an industry high-frequency word can be acquired as a keyword, and business processing data associated with the industry high-frequency word is acquired as work order data; and further, establishing a mapping relation between the industry high-frequency words and the business processing data as a second mapping relation, and storing the second mapping relation into an industry exclusive word bank.
The high-frequency words in the industry specifically include: the words in the industry fault name word bank, the names of spare parts, the high-frequency combination words, the words in the synonym word bank, the words in the stop word bank, the words in the abbreviation word bank and the like. The business processing data associated with the industry high-frequency word may specifically include: the service processing data associated with the industry high-frequency word may specifically include other service processing data, and no limitation is made on the introduced service processing data associated with the industry high-frequency word.
It should be noted that the second mapping relationship between the industry high-frequency words and the service processing data stored in the industry exclusive lexicon is substantially the second mapping relationship between the industry high-frequency words and the service processing data identifiers, that is, the server generates identifiers corresponding to the service processing data when sorting the service processing data, and stores the second mapping relationship between the industry high-frequency words and the service processing data identifiers corresponding to the service processing data into the industry exclusive lexicon after determining the second mapping relationship between the industry high-frequency words and the service processing data.
Therefore, the content stored in the industry exclusive word bank is enriched from multiple angles, so that the situation that more abundant target work order data can be searched based on the industry exclusive word bank is guaranteed, and the situation that more target work order data are referred to in the finally generated target search result is guaranteed to be more accurate.
The construction method based on the industry exclusive word stock can ensure that the constructed industry exclusive word stock contains more reference information, so that more abundant target work order data can be obtained when the industry exclusive word stock is used for searching the target work order data, more basic reference data can be provided for the subsequent processing of a work order data analysis model, and the finally generated target search result is more accurate.
Aiming at the information searching method described above, the application also provides a corresponding information searching device, so as to facilitate the application and implementation of the methods in practice.
Referring to fig. 8, fig. 8 is a schematic structural diagram of an information search apparatus 800 corresponding to the method shown in fig. 2, where the information search apparatus 800 includes:
an extraction module 801, configured to extract a target keyword in a task work order to be processed;
a searching module 802, configured to search, based on an industry-specific lexicon, target work order data matched with the target keyword; the industry exclusive word bank is used for storing a mapping relation between the key words and the work order data;
the processing model 803 is used for analyzing and processing the target work order data by using a work order data analysis model according to a target search task and generating a target search result according to an output result of the work order data analysis model; and the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
Optionally, the apparatus further comprises:
the acquisition module is used for acquiring a plurality of pieces of historical work order data;
the data cleaning module is used for cleaning the historical work order data to generate work order data meeting a preset data structure;
the first storage module is used for determining keywords related to the work order data, establishing a mapping relation between the keywords and the work order data as a first mapping relation, and storing the first mapping relation to the industry exclusive lexicon.
Optionally, the apparatus further comprises:
the acquisition module is used for acquiring high-frequency words of the industry as keywords; acquiring service processing data associated with the industry high-frequency words as work order data;
and the second storage module is used for establishing a mapping relation between the industry high-frequency words and the service processing data as a second mapping relation and storing the second mapping relation to the industry exclusive word bank.
Optionally, the work order data analysis model includes a plurality of work order data analysis submodels, and different work order data analysis submodels correspond to different search tasks; the processing module 803 is specifically configured to:
calling a work order data analysis sub-model corresponding to the target search task in the work order data analysis model;
and analyzing and processing the target work order data by utilizing the called work order data analysis submodel, and generating the target search result according to the output result of the work order data analysis submodel.
Optionally, when the target search task is recommending a similar historical work order, the processing module 803 is specifically configured to:
determining the similarity between the target work order data and the task work order to be processed by using the work order data analysis model as the similarity corresponding to the target work order data;
and sorting the similarity corresponding to each target work order data in a descending order, and taking the target work order data corresponding to the similarity of the top N bits as the target search result.
Optionally, when the target search task is a statistical failure cause, the processing module 803 is specifically configured to:
determining each fault reason related in the target work order data by using the work order data analysis model, and counting the occurrence frequency of each fault reason;
and generating a fault reason statistical chart according to each fault reason and the occurrence frequency thereof, and taking the fault reason statistical chart as the target search result.
Optionally, when the target search task is to determine to replace a spare part, the processing module 803 is specifically configured to:
determining each replacement spare part involved in the target work order data by using the work order data analysis model;
and generating a replacement spare part preparation list according to each replacement spare part as the target search result.
Optionally, when the target search task is backtracking of a related work order problem, the processing module 803 is specifically configured to:
determining potential faults involved in the target work order data using the work order data analysis model;
searching a maintenance scheme corresponding to the potential fault based on the industry exclusive word bank;
and generating the target search result according to the potential fault and the maintenance scheme corresponding to the potential fault.
Optionally, when the target search task is recommended by a maintenance engineer, the processing module 803 is specifically configured to:
determining each maintenance engineer related to the target work order data and the corresponding maintenance condition thereof by using the work order data analysis model;
and generating a maintenance engineer recommendation list as the target search result according to the maintenance engineers and the corresponding maintenance conditions thereof.
The information searching device searches the work order data related to the work order to be processed through the industry exclusive word bank, and generates a searching result corresponding to the target searching task selected by the user based on the searched work order data through the work order data analysis model. Therefore, related workers can quickly and effectively search the self-required reference information related to the work order of the task to be processed by utilizing the work order search engine consisting of the industry exclusive word bank and the work order data analysis model, so that the related workers can quickly make a reasonable service scheme, and the service efficiency and the service quality are improved.
The information search device comprises a processor and a memory, wherein the extracting module, the searching module, the processing module and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, rich reference information is provided for aftermarket service personnel by adjusting kernel parameters, and the aftermarket service personnel are helped to quickly make a reasonable service scheme.
An embodiment of the present invention provides a storage medium having a program stored thereon, the program implementing the information search method when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the information searching method is executed when the program runs.
An embodiment of the present invention provides an apparatus, and referring to fig. 9, an apparatus 900 includes at least one processor 901, and at least one memory 902 and a bus 903 connected to the processor; the processor 901 and the memory 902 complete communication with each other through the bus 903; the processor 901 is used to call program instructions in the memory 902 to execute the above-described information search method. The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
extracting target keywords of a task work order to be processed;
searching target work order data matched with the target keywords based on an industry exclusive word bank; the industry exclusive word bank is used for storing a mapping relation between the key words and the work order data;
according to a target search task, analyzing and processing the target work order data by using a work order data analysis model, and generating a target search result according to an output result of the work order data analysis model; and the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
Optionally, the industry-specific lexicon is constructed in the following manner:
collecting a plurality of pieces of historical work order data;
performing data cleaning processing on the historical work order data to generate work order data meeting a preset data structure;
determining keywords associated with the work order data, establishing a mapping relation between the keywords and the work order data as a first mapping relation, and storing the first mapping relation to the industry exclusive word bank.
Optionally, the method further includes:
acquiring an industry high-frequency word as a keyword; acquiring service processing data associated with the industry high-frequency words as work order data;
and establishing a mapping relation between the industry high-frequency words and the service processing data as a second mapping relation, and storing the second mapping relation to the industry exclusive word bank.
Optionally, the work order data analysis model includes a plurality of work order data analysis submodels, and different work order data analysis submodels correspond to different search tasks;
then, according to the target search task, analyzing and processing the target work order data by using a work order data analysis model, and obtaining an output result of the work order data analysis model as a target search result, including:
calling a work order data analysis sub-model corresponding to the target search task in the work order data analysis model;
and analyzing and processing the target work order data by utilizing the called work order data analysis submodel, and generating the target search result according to the output result of the work order data analysis submodel.
Optionally, when the target search task is recommending a similar historical work order, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining the similarity between the target work order data and the task work order to be processed by using the work order data analysis model as the similarity corresponding to the target work order data;
and sorting the similarity corresponding to each target work order data in a descending order, and taking the target work order data corresponding to the similarity of the top N bits as the target search result.
Optionally, when the target search task is a statistical fault cause, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining each fault reason related in the target work order data by using the work order data analysis model, and counting the occurrence frequency of each fault reason;
and generating a fault reason statistical chart according to each fault reason and the occurrence frequency thereof, and taking the fault reason statistical chart as the target search result.
Optionally, when the target search task is to determine to replace a spare part, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining each replacement spare part involved in the target work order data by using the work order data analysis model;
and generating a replacement spare part preparation list according to each replacement spare part as the target search result.
Optionally, when the target search task is backtracking of a related work order problem, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining potential faults involved in the target work order data using the work order data analysis model;
searching a maintenance scheme corresponding to the potential fault based on the industry exclusive word bank;
and generating the target search result according to the potential fault and the maintenance scheme corresponding to the potential fault.
Optionally, when the target search task is recommended by a maintenance engineer, the analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model includes:
determining each maintenance engineer related to the target work order data and the corresponding maintenance condition thereof by using the work order data analysis model;
and generating a maintenance engineer recommendation list as the target search result according to the maintenance engineers and the corresponding maintenance conditions thereof.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (12)
1. An information search method, characterized in that the method comprises:
extracting target keywords of a task work order to be processed;
searching target work order data matched with the target keywords based on an industry exclusive word bank; the industry exclusive word bank is used for storing a mapping relation between the key words and the work order data;
and analyzing and processing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model, wherein the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
2. The method of claim 1, wherein the industry-specific thesaurus is constructed by:
collecting a plurality of pieces of historical work order data;
performing data cleaning processing on the historical work order data to generate work order data meeting a preset data structure;
determining keywords associated with the work order data, establishing a mapping relation between the keywords and the work order data as a first mapping relation, and storing the first mapping relation to the industry exclusive word bank.
3. The method of claim 2, further comprising:
acquiring an industry high-frequency word as a keyword;
acquiring service processing data associated with the industry high-frequency words as work order data;
and establishing a mapping relation between the industry high-frequency words and the service processing data as a second mapping relation, and storing the second mapping relation to the industry exclusive word bank.
4. The method of claim 1, wherein the work order data analysis model includes a plurality of work order data analysis submodels, different work order data analysis submodels corresponding to different search tasks;
then, according to the target search task, analyzing and processing the target work order data by using a work order data analysis model, and obtaining an output result of the work order data analysis model as a target search result, including:
calling a work order data analysis sub-model corresponding to the target search task in the work order data analysis model;
and analyzing and processing the target work order data by utilizing the called work order data analysis submodel, and generating the target search result according to the output result of the work order data analysis submodel.
5. The method according to claim 1 or 4, wherein when the target search task is recommending a similar historical work order, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model comprises:
determining the similarity between the target work order data and the task work order to be processed by using the work order data analysis model as the similarity corresponding to the target work order data;
and sorting the similarity corresponding to each target work order data in a descending order, and taking the target work order data corresponding to the similarity of the top N bits as the target search result.
6. The method according to claim 1 or 4, wherein when the target search task is a cause of statistical failure, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model comprises:
determining each fault reason related in the target work order data by using the work order data analysis model, and counting the occurrence frequency of each fault reason;
and generating a fault reason statistical chart according to each fault reason and the occurrence frequency thereof, and taking the fault reason statistical chart as the target search result.
7. The method as claimed in claim 1 or 4, wherein when the target search task is to determine to replace spare parts, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model comprises:
determining each replacement spare part involved in the target work order data by using the work order data analysis model;
and generating a replacement spare part preparation list according to each replacement spare part as the target search result.
8. The method according to claim 1 or 4, wherein when the target search task is backtracking of related work order problems, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model comprises:
determining potential faults involved in the target work order data using the work order data analysis model;
searching a maintenance scheme corresponding to the potential fault based on the industry exclusive word bank;
and generating the target search result according to the potential fault and the maintenance scheme corresponding to the potential fault.
9. The method according to claim 1 or 4, wherein when the target search task is recommended by a maintenance engineer, the analyzing the target work order data by using a work order data analysis model according to the target search task, and generating a target search result according to an output result of the work order data analysis model comprises:
determining each maintenance engineer related to the target work order data and the corresponding maintenance condition thereof by using the work order data analysis model;
and generating a maintenance engineer recommendation list as the target search result according to the maintenance engineers and the corresponding maintenance conditions thereof.
10. An information search apparatus, characterized in that the apparatus comprises:
the extraction module is used for extracting target keywords in the task work order to be processed;
the searching module is used for searching target work order data matched with the target keywords based on an industry exclusive word bank; the industry exclusive word bank is used for storing a mapping relation between the key words and the work order data;
the processing model is used for analyzing and processing the target work order data by using the work order data analysis model according to a target search task and generating a target search result according to an output result of the work order data analysis model; and the work order data analysis model is used for generating a search result corresponding to the search task according to the work order data.
11. An electronic device, comprising at least one processor, and at least one memory, bus connected to the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to call program instructions in the memory to perform the information search method of any one of claims 1 to 9.
12. A computer-readable storage medium for storing a computer program for executing the information search method according to any one of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910838558.XA CN112445893A (en) | 2019-09-05 | 2019-09-05 | Information searching method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910838558.XA CN112445893A (en) | 2019-09-05 | 2019-09-05 | Information searching method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112445893A true CN112445893A (en) | 2021-03-05 |
Family
ID=74733185
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910838558.XA Pending CN112445893A (en) | 2019-09-05 | 2019-09-05 | Information searching method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112445893A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016188279A1 (en) * | 2015-05-25 | 2016-12-01 | 阿里巴巴集团控股有限公司 | Generating method and device for fault spectra, and detecting method and device based on fault spectra |
CN106600298A (en) * | 2016-12-23 | 2017-04-26 | 国网山东省电力公司信息通信公司 | Electric power information system customer service knowledge base construction method based on work order data analysis |
CN107562726A (en) * | 2017-09-06 | 2018-01-09 | 国家电网公司 | A kind of electric service search engine based on hot word |
CN108388564A (en) * | 2017-02-03 | 2018-08-10 | 百度在线网络技术(北京)有限公司 | Inquiry processing method, device and its equipment |
CN109885768A (en) * | 2019-02-18 | 2019-06-14 | 中国联合网络通信集团有限公司 | Worksheet method, apparatus and system |
CN109905269A (en) * | 2018-01-17 | 2019-06-18 | 华为技术有限公司 | The method and apparatus for determining network failure |
-
2019
- 2019-09-05 CN CN201910838558.XA patent/CN112445893A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016188279A1 (en) * | 2015-05-25 | 2016-12-01 | 阿里巴巴集团控股有限公司 | Generating method and device for fault spectra, and detecting method and device based on fault spectra |
CN106600298A (en) * | 2016-12-23 | 2017-04-26 | 国网山东省电力公司信息通信公司 | Electric power information system customer service knowledge base construction method based on work order data analysis |
CN108388564A (en) * | 2017-02-03 | 2018-08-10 | 百度在线网络技术(北京)有限公司 | Inquiry processing method, device and its equipment |
CN107562726A (en) * | 2017-09-06 | 2018-01-09 | 国家电网公司 | A kind of electric service search engine based on hot word |
CN109905269A (en) * | 2018-01-17 | 2019-06-18 | 华为技术有限公司 | The method and apparatus for determining network failure |
CN109885768A (en) * | 2019-02-18 | 2019-06-14 | 中国联合网络通信集团有限公司 | Worksheet method, apparatus and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11372896B2 (en) | Method and apparatus for grouping data records | |
CA3042926A1 (en) | Technology incident management platform | |
US20190087490A1 (en) | Text classification method and apparatus | |
US9459950B2 (en) | Leveraging user-to-tool interactions to automatically analyze defects in IT services delivery | |
US20170109657A1 (en) | Machine Learning-Based Model for Identifying Executions of a Business Process | |
US20170109676A1 (en) | Generation of Candidate Sequences Using Links Between Nonconsecutively Performed Steps of a Business Process | |
US20170109668A1 (en) | Model for Linking Between Nonconsecutively Performed Steps in a Business Process | |
US20170109667A1 (en) | Automaton-Based Identification of Executions of a Business Process | |
CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
US20180046956A1 (en) | Warning About Steps That Lead to an Unsuccessful Execution of a Business Process | |
CN104933100A (en) | Keyword recommendation method and device | |
US20170109636A1 (en) | Crowd-Based Model for Identifying Executions of a Business Process | |
US20120150825A1 (en) | Cleansing a Database System to Improve Data Quality | |
US20150149463A1 (en) | Method and system for performing topic creation for social data | |
US20170109638A1 (en) | Ensemble-Based Identification of Executions of a Business Process | |
US11790380B2 (en) | Systems and methods for finding an interaction subset within a set of interactions | |
US20220284340A1 (en) | Determining digital personas utilizing data-driven analytics | |
CN110880124A (en) | Conversion rate evaluation method and device | |
Atoum et al. | Towards resolving software quality-in-use measurement challenges | |
CN117668205B (en) | Smart logistics customer service processing method, system, equipment and storage medium | |
US20170109640A1 (en) | Generation of Candidate Sequences Using Crowd-Based Seeds of Commonly-Performed Steps of a Business Process | |
CN115118574A (en) | Data processing method, device and storage medium | |
US9443214B2 (en) | News mining for enterprise resource planning | |
CN107016028B (en) | Data processing method and apparatus thereof | |
US20170109637A1 (en) | Crowd-Based Model for Identifying Nonconsecutive Executions of a Business Process |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |