CN117195855A - Work order duplicate checking method and device and related equipment - Google Patents

Abstract

The application provides a work order re-checking method, in particular to a work order re-checking device which acquires a work order to be checked and acquires a re-checking element appointed by a user, then the work order re-checking device uses an element mining model in a model library to mine element contents belonging to the re-checking element in the work order to be checked, and searches a target work order from a plurality of work orders stored in a database, the semantics of the element contents belonging to the re-checking element in the searched target work order is matched with the semantics of the element contents belonging to the re-checking element in the work order to be checked, so that the work order re-checking device provides the target work order for presenting to the user. Therefore, even if the keywords expressing the semantics are different in the two work orders, the work order duplicate checking device can also recognize the two work orders as duplicate work orders, so that the accuracy of work order duplicate checking can be effectively improved, and the work order duplicate checking effect can be improved. In addition, the application also provides a corresponding device and related equipment.

Description

Work order duplicate checking method and device and related equipment

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a work order duplication checking method, apparatus and related devices.

Background

A work order, which may be specifically referred to as a work order, is typically a task, job, or request submitted by a customer or an employee within an enterprise to a facilitator, enterprise department for a product or service problem, so that the facilitator or enterprise department performs a corresponding process flow according to the work order.

With the development of online services (such as the popularization of online hotlines, etc.), the number of worksheets is continuously accumulated. The number of case types reflected by the worksheets is generally limited compared to the number of worksheets, which means that the newly generated worksheets may be repeated with the historical worksheets (i.e., the worksheets generated during the past time period), so that the manpower cost required for processing the worksheets can be reduced by performing the concurrent processing of the newly generated work and the repeated historical worksheets.

Currently, it is generally determined whether a newly generated work order is repeated with a historical work order by means of keyword matching. However, the work order duplicate checking mode has low accuracy and poor duplicate checking effect.

Disclosure of Invention

The application provides a work order duplicate checking method which is used for checking the work order duplicate in a semantic matching mode, so that the accuracy of checking the work order duplicate is improved, and the duplicate checking effect is improved. Furthermore, the application also provides a work order duplicate checking device, a computing device, a computer readable storage medium and a computer program product.

In a first aspect, the present application provides a method for searching a work order, where the method for searching a work order may be executed by a corresponding work order searching device, specifically, the work order searching device obtains a work order to be searched, where the work order to be searched may be provided to the work order searching device through an information input interface by a user, for example, the work order searching device further obtains a user-specified searching element, for example, the user may specify one or more elements used when the work order is searched by the user through a configuration interface, and then, the work order searching device uses an element mining model in a model library to search element content belonging to the searching element in the work order to be searched, searches a target work order from a plurality of work orders stored in a database, where semantics of the element content belonging to the searching element in the target work order found matches with semantics of the element content belonging to the searching element in the work order to be searched, so that the work order searching device provides the target work order for presentation to the user, for example, the work order searching device may present the target work order to the user through an external client.

Therefore, the work order duplicate checking device can judge whether the work orders which are repeated with the work order to be checked exist in the plurality of work orders according to the mode that whether the semantics of the element content of the duplicate checking element are matched or not, so that the work order duplicate checking device can recognize the two work orders as duplicate work orders even if keywords expressing the semantics are different in the two work orders with the same semantics, and therefore the accuracy of work order duplicate checking and the work order duplicate checking effect can be effectively improved. And when the importance searching element designated by the user comprises a plurality of elements, the work order query is performed based on the plurality of importance searching elements, so that whether the work order to be searched is a repeated work order can be determined from the characteristic information of different dimensions, the accuracy of the work order repeat searching is higher, and the work order repeat searching can be performed by selecting the importance searching elements with different combinations according to different scenes, thereby improving the universality of the work order repeat searching.

In one possible implementation manner, the importance searching element designated by the user comprises a structured element and an unstructured element, so that in the process of searching the target work order, the work order weight searching device can specifically screen a plurality of work orders stored in the database according to the element content of the structured element in the work order to be searched to obtain a candidate work order set, the candidate work order set comprises at least one candidate work order, the semantics of the element content of the structured element in the candidate work order is matched with the semantics of the element content of the structured element in the work order to be searched, and therefore the work order weight searching device can determine the target work order from the at least one candidate work order, and the similarity of the semantics of the element content of the unstructured element in the target work order and the semantics of the element content of the unstructured element in the work order to be searched is larger than a preset threshold. Therefore, the work order duplicate checking device can determine the target work order which is duplicate with the work order to be checked from a plurality of work orders by utilizing the two-layer matching process.

Correspondingly, the semantics of the element content belonging to the structural element of the work order which does not exist in the database are matched with the semantics of the element content belonging to the structural element in the work order to be checked, or the similarity of the semantics of the element content which does not exist in the candidate work order and the semantics of the element content belonging to the unstructured element in the work order to be checked is larger than a preset threshold, and the work order checking device can determine that the work order which is repeated with the work order to be checked does not exist in the database.

In one possible implementation manner, when the work order duplication checking device acquires the duplication checking elements specified by the user, the configuration interface may be specifically generated, and the configuration interface is used for presenting a plurality of duplication checking elements to the user, for example, the configuration interface may be presented to the user through an externally provided client, so that the work order duplication checking device may determine the structural elements and the unstructured elements selected by the user in response to the selection operation of the user on the plurality of duplication checking elements in the configuration interface. Therefore, the user can customize the importance searching elements required by the work order searching through a man-machine interaction mode, so that the user experience is improved, the requirement of the user on selecting different combinations of the importance searching elements for the work order in different scenes can be met, and the flexibility of the work order searching is improved.

In one possible implementation manner, for the unstructured element, the work order duplicate checking device further determines a preset threshold value for measuring the semantic similarity of two work orders on the element content of the unstructured element in response to the configuration operation of the user on the unstructured element in the configuration interface, and the work order duplicate checking device further determines a calculation mode corresponding to the similarity in response to the selection operation of the user on multiple calculation modes in the configuration interface. Therefore, the work order duplicate checking device can support the user to customize the preset threshold value and the calculation mode, and the flexibility of work order duplicate checking can be further improved.

In one possible implementation, the unstructured elements include at least one of text vectors, picture vectors, and video vectors. Therefore, the work order duplicate checking device can deeply understand text information, picture information or video information in the work order to be checked, thereby being beneficial to improving the accuracy of work order duplicate checking.

In one possible implementation, the work order checking device may further generate a checking interface, where the checking interface is configured to present the target work order and the work order to be checked to the user, and combine the work order to be checked and the target work order in response to a confirmation operation of the user, so that the target work order and the work order to be checked are processed based on the same operation. Thus, the repeated processing operation for the work order does not need to be redesigned, and the processing efficiency of the work order can be improved.

The target work orders can be work orders which are repeated with the work orders to be checked and are not processed yet, so that unified processing of a plurality of repeated work orders can be realized through work order combination, and the processing efficiency of the work orders is improved. Alternatively, the target work order may be a historical work order, that is, a work order that has been processed in a past time period, so that by the work order merging, the to-be-checked heavy work order may be processed accordingly based on an operation of processing the target work order, so that a redesign of a processing operation of the to-be-checked heavy work order is not required.

The work order duplication checking device provided in the second aspect corresponds to the work order duplication checking method provided in the first aspect, so the technical effects of the work order duplication checking device in any one of the possible implementation manners of the second aspect and the second aspect may refer to the technical effects of the corresponding implementation manners of the first aspect and the first aspect, and are not described herein.

In a third aspect, the present application provides a cluster of computing devices, the cluster of computing devices comprising at least one computing device, each computing device comprising a processor and a memory; the memory is configured to store instructions that, when the cluster of computing devices is running, a processor in each computing device executes the instructions stored by the memory to cause the cluster of computing devices to perform the work order duplication method of the first aspect or any one of the possible implementations of the first aspect. It should be noted that the memory may be integrated into the processor or may be independent of the processor. Each computing device may also include a bus. The processor is connected with the memory through a bus. The memory may include a readable memory and a random access memory, among others.

In a fourth aspect, the present application provides a computer readable storage medium having instructions stored therein which, when run on a cluster of computing devices comprising at least one computing device, cause the cluster of computing devices to perform the method of the first aspect or any implementation of the first aspect.

In a fifth aspect, the application provides a computer program product comprising instructions which, when run on a cluster of computing devices comprising at least one computing device, cause the cluster of computing devices to perform the method of the first aspect or any implementation of the first aspect.

Further combinations of the present application may be made to provide further implementations based on the implementations provided in the above aspects.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those of ordinary skill in the art.

FIG. 1 is a schematic diagram of an exemplary application scenario provided in an embodiment of the present application;

fig. 2 is a schematic diagram of another exemplary application scenario provided in an embodiment of the present application;

FIG. 3 is a schematic flow chart of a method for checking a work order according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an information input interface according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a configuration interface according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a verification interface according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a computing device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a computing device cluster according to an embodiment of the present application.

Detailed Description

The terms first, second and the like in the description and in the claims and in the above-described figures, 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 terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which embodiments of the application have been described in connection with the description of the objects having the same attributes.

Referring to fig. 1, an exemplary application scenario is schematically illustrated. In the application scenario shown in fig. 1, the user 100 may provide (via a client or user terminal, etc.) one or more worksheets to the worksheet inspection device 200 to request an inspection of the worksheet. Illustratively, the worksheets provided by the users 100 may be worksheets related to enterprises or other institutions, such as worksheets generated by enterprise content for work arrangements, worksheets generated by public institutions based on complaint content on citizen lines, and the like. For convenience of distinction, the work order provided by the user 100 will be hereinafter referred to as a work order to be checked.

At this time, if the work order repeat checking device 200 checks a work order having the same keyword as that of the work order to be checked from a plurality of work orders by means of keyword matching, thereby implementing the work order repeat checking, the work order repeat checking effect may be poor. For example, assuming that a work order including a keyword "report XXX" is stored in the local database of the work order duplication checking device 200, and the work order to be checked includes a keyword "complaint XXX", at this time, the work order duplication checking device 200 checks duplication by means of keyword matching, because the keyword "report XXX" is not identical to the keyword "complaint XXX", the work order duplication checking device 200 is likely to determine that the two work orders are not repeated (actually should be repeated work orders), thereby resulting in lower duplication checking accuracy of the work order duplication checking device 200.

For this reason, in this embodiment, the work order duplication checking device 200 may perform duplication checking processing for the work order to be checked from the perspective of semantic matching. Specifically, the work order duplicate checking device 200 not only obtains the duplicate checking work order to be checked, but also obtains the duplicate checking element designated by the user 100, so that element content belonging to the duplicate checking element in the duplicate checking work order to be checked can be mined by using an element mining model in the model library, wherein the duplicate checking element is used for expressing semantic content of data in the work order, and different duplicate checking elements can express semantics of different aspects. For example, for the text "a complaint B", where the work order query device 200 determines that the heavy factor corresponding to "a" is a complaint person, the heavy factor corresponding to "complaint" is a work order type, and the heavy factor corresponding to "B" is a subject of concern. Then, the work order re-checking device 200 searches for whether a target work order exists in the plurality of work orders stored in the database, and the semantics of the element content belonging to the re-checking element in the target work order is matched with the semantics of the element content belonging to the re-checking element in the to-be-checked work order, so that after the target work order is searched, the work order re-checking device 200 provides the target work order to the user 100, for example, the target work order (and the to-be-checked re-work order) can be presented to the user 100 together.

In this way, the work order repeat checking device 200 can determine whether the work orders repeated with the work order to be checked exist in the plurality of work orders according to the mode of whether the semantics of the element content of the repeat checking element is matched, so that the work order repeat checking device 200 can recognize the two work orders as repeated work orders even if the keywords expressing the semantics are different in the two work orders with the same semantics, thereby effectively improving the accuracy of work order repeat checking and improving the work order repeat checking effect. And when the importance searching element designated by the user 100 comprises a plurality of elements, the work order query is performed based on the plurality of importance searching elements, so that whether the work order to be searched is a repeated work order can be determined from the characteristic information of different dimensions, the accuracy of the work order repeat searching is high, and the work order repeat searching can be performed by selecting different combinations of importance searching elements according to different scenes, thereby improving the universality of the work order repeat searching.

Taking the work order of checking the weight as an example of the work order including the keyword "complaint XXX", assuming that the work order including the keyword "report XXX" exists in the local database of the work order checking device 200, the work order checking device 200 matches according to the element content belonging to the checking weight element, so that it can be determined that the element content "complaint" and "report" belonging to the work order type element in the two work orders belong to the same semantic, and the element content "XXX" and "XXX" belonging to the factor of the incident responsibility main body belong to the same semantic, therefore, the work order checking device 200 can determine the two work orders as repeated work orders, thereby improving the accuracy rate of checking the work order.

Illustratively, the work order repeat checking device 200 may be implemented by hardware, or may be implemented by software. When implemented in software, the work order weight apparatus 200 may be an application running on a computing device, such as a computing engine, virtual machine, or the like. When implemented in hardware, work order weight apparatus 200 may include at least one computing device, such as a server or the like. Alternatively, the work order review device 200 may be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (programmable logic device, PLD). The PLD may be implemented as a complex program logic device (complex programmable logical device, CPLD), a field-programmable gate array (FPGA), a general-purpose array logic (generic array logic, GAL), or any combination thereof.

In actual deployment, the work order re-checking device 200 can be deployed on the user side, i.e. can serve as local equipment to provide local work order re-checking service for the user 100; alternatively, the work order duplication checking device 200 may be deployed in a cloud, such as public cloud, edge cloud or distributed cloud, for providing work order duplication checking service of the cloud for the user 100, and the deployment mode of the work order duplication checking device 200 is not limited in the present application.

It should be noted that the application scenario shown in fig. 1 is only an implementation example, and the work order repeat checking device 200 may be applied to other applicable scenarios during actual application. For example, in the application scenario shown in fig. 2, the work order re-checking device 200 is configured to provide the work order re-checking service in the cloud for the user 100, and the work order re-checking device 200 may provide the client 300 to the outside, so that the user 100 may request the work order re-checking device 200 to perform the work order re-checking through the client 300.

For ease of understanding, the process by which the work order checkweigher 200 provides the user 100 with the work order checkweigher service will be described in detail below with reference to the accompanying drawings.

Referring to fig. 3, a flowchart of a work order duplication checking method according to an embodiment of the present application is shown, and the method may be applied to the work order duplication checking device 200 shown in fig. 1 or fig. 2. For convenience of description, the following description will be given by taking an example applied to the scene shown in fig. 1. The work order duplicate checking device 200 may include an interaction module 201, an element mining module 202, and a duplicate checking module 203, and a model library and a database may be deployed locally on the work order duplicate checking device 200; further, the work order repeat device 200 may also include a model training module 204. The functions of the various modules in the work order checkweigher 200 are described with particular reference to the relevance of the embodiment shown in fig. 3. As shown in fig. 3, the method specifically may include:

S301: the interaction module 201 obtains the rework order to be checked.

As an implementation example, the interaction module 201 may provide an information input interface to the user 100, so that the user 100 provides one or more work orders to be reviewed to the work order review device 200 through the information input interface, and requests review processing for the work order with review. For example, the interaction module 201 may provide an information input interface as shown in fig. 4, on which a prompt message "please import a work order to be checked-! And is configured with an "import" control, so that after the "import" control is triggered by the user 100, one or more files of the work order to be checked are imported into the work order checking device 200 through the information input interface.

In this embodiment, the information input interface (and various interaction interfaces mentioned below) may be directly presented to the user 100 through a display configured in the interaction module 201, or may be presented to the user 100 through a client or a user terminal on the user side, etc., which is not limited in this embodiment.

The interaction module 201 may then forward the received rework sheet to be inspected to the element mining module 202.

S302: the interaction module 201 obtains the duplicate checking element specified by the user.

The heavy work order to be checked may include element contents belonging to one or more elements. For example, a work order for complaints may include element content of elements belonging to a complaint person, a complaint phone, a complaint address, a subject of liability for concern, emotion, topic, a work order category, a text token vector, a picture token vector, a video token vector, and the like.

In this embodiment, the work order review device 200 may support the user 100 to specify the elements to be used in review of the work order. For example, in a scenario of processing a complaint work order, the user 100 mainly processes a complaint work order of different persons in the same area within three months, so that a repeated work order for the same event can be subjected to deduplication processing, and at this time, the user can designate factors such as a utilization work order type, a work order responsibility subject, a complaint address, a work order generation time, a text vector, and the like as factors used for performing work order review.

As an implementation example, the work order review device 200 may generate, through the interaction module 201, a configuration interface as shown in fig. 5 for presenting a plurality of review elements to the user 100, where the presented plurality of review elements may include structured elements as well as unstructured elements. In this way, the user 100 may select a plurality of checkmarks on the presented configuration interface, e.g., the user 100 may click a select button of a portion or all of the checkmarks on the configuration interface, etc. Accordingly, the interaction module 201 may determine the weight factor selected by the user in response to the selection operation of the user 100. Wherein the number of the importance factors specified by the user 100 may be one or more. In actual application, the user 100 can flexibly select the combination of corresponding weight checking elements to check the work order according to the data characteristics in the work order generated by the actual application scene, so that the weight checking requirements of the work orders of various scenes can be supported, and the flexibility of checking the work orders is improved.

Further, the query specified by the user 100 may be a structured element or may be an unstructured element. The structural element refers to that the element content can be directly matched from a work order, such as complaints, complaint phones, complaint addresses, incident responsibility subjects, emotion, topics, work order categories and the like. Unstructured elements refer to elements whose content needs to be obtained through calculation, such as text token vectors, picture token vectors, video token vectors, and the like.

The interaction module 201 may then forward the obtained importance-checking element to the element mining module 202.

S303: the element mining module 202 uses the element mining model in the model library to mine out the element content belonging to the duplicate checking element specified by the user 100 in the work order to be checked acquired by the interaction module 201.

In this embodiment, the work order duplication checking device 200 may perform duplication checking processing on the work order based on duplication checking elements expressing the semantics of the work order. In one possible implementation, the element mining module 202 in the work order duplication checking device 200 may obtain one or more element mining models from a model library, where different element mining models are used to mine element content in a work order that belongs to different duplication checking elements. The model library may be deployed in the work order duplication checking device 200 (as shown in fig. 1), so that the element mining module 202 may obtain an element mining model by reading a local model library; alternatively, the model library is deployed independently of the worksheet duplication checking device 200, so that the element mining module 202 may interact with the device storing the model library through the interaction module 201 to obtain the element mining model. Then, the element mining module 202 uses the acquired one or more element mining models to mine out element contents belonging to the duplicate checking element in the duplicate checking work order. In other embodiments, the element mining module 202 may mine out element contents belonging to a plurality of duplicate elements in a work order, or the like, using one element mining model.

Before the work order re-checking device 200 provides the work order re-checking service, each element mining model in the model library may complete training in advance through at least one set of training samples, where the training samples may be, for example, a historical work order carrying element labels, and the element mining model may complete training by the work order re-checking device 200, or may complete training by other devices. Taking the example of training the model for mining the topic elements by the work order repeat unit 200, the model training module 204 in the work order repeat unit 200 may obtain a training sample, where the training sample includes a plurality of historical work orders carrying topic labels, so that the model training module 204 may train the model constructed in advance by using the training sample, so as to train to obtain the model for mining the topic elements. Illustratively, the element mining model may be constructed based on a deep learning network, for example, a bert model, a T5 model, and the like. Therefore, text information, picture information or video information in the work order to be checked can be deeply understood based on the element mining model, and the accuracy of work order check is improved. In practical applications, the element mining model may be constructed in other manners, such as a rule matching manner, which is not limited in this embodiment.

Then, the element mining module 202 may forward the to-be-inspected heavy work order and the mined element content belonging to the heavy inspection element specified by the user 100 to the heavy inspection module 203.

S304: the duplication checking module 203 searches for a target work order from the plurality of work orders stored in the database, where the semantics of the element content belonging to the duplication checking element in the target work order is matched with the semantics of the element content belonging to the duplication checking element in the work order to be checked.

In a specific implementation, the work order duplication checking device 200 may be deployed with a database locally, and the database may store element contents of unstructured elements of the work order and element contents of elements belonging to each structured element in the work order while storing the work order, so that the duplication checking module 203 may traverse a plurality of work orders in the database to determine the work order with duplication checking elements. In this way, the duplication checking module 203 determines whether the semantics of the work order on the element content belonging to the duplication checking element match by further comparing the semantics of the work order and the work order to be checked on the element content of the duplication checking element. And, when it matches, the duplicate checking module 203 determines the work order as a target work order that is duplicate with the work order to be checked; and when they do not match, the check repeat module 203 may determine that there is no work order in the database that is repeated with the work order to be checked. The duplication checking module 203 may determine whether the semantics of the two worksheets on the element content of the duplication checking element are matched based on a semantic analysis technology (latent sementic analysis, LSA), or may be implemented by other technologies, for example, determining by means of a semantic recognition model, etc.

As one implementation example, the duplicate elements specified by the user 100 may include structured elements as well as unstructured elements. The duplication checking module 203 may first screen a plurality of worksheets stored in the database according to the element content of the structural element in the to-be-checked duplication worksheets to obtain a candidate worksheet set, where the candidate worksheet set includes at least one candidate worksheet, that is, a worksheet screened out in the database, where the semantics of the element content of the structural element in the candidate worksheet is matched with the semantics of the element content of the structural element in the to-be-checked duplication worksheet, for example, the texts about the structural element in the two worksheets are the same or similar. Then, the duplication checking module 203 may calculate the similarity between the semantics of the element content belonging to the unstructured element in the to-be-checked duplication worksheet and the semantics of the element content belonging to the unstructured element (such as a picture characterization vector) in each candidate worksheet, so as to determine a candidate worksheet whose similarity is greater than a preset threshold (such as 0.85) from at least one candidate worksheet, and determine the candidate worksheet as a target worksheet that is repeated with the to-be-checked duplication worksheet.

Illustratively, when the unstructured element includes a plurality of elements, such as a text token vector, a picture token vector, and the like, the check and replay module 203 may calculate the semantic similarity of the two worksheets on the element content of the unstructured element by means of weighted summation. For example, the duplicate checking module 203 may calculate the similarity based on the following formula (1):

W＝α*A+β*B(1)

Wherein W is the whole semantically similar size of the element content of the unstructured element of the two worksheets, A is the similarity of the text token vector of the two worksheets, B is the similarity of the picture token vector of the two worksheets, alpha and beta are weight values, and the sum of the alpha and the beta is 1. In practical applications, the duplicate checking module 203 may also calculate the similarity of the two worksheets on the unstructured elements by adopting other calculation methods. Thus, the work order duplicate checking device 200 can accurately check the work order duplicate to be checked including the pictures and the videos.

Further, when the work order review is performed based on the element content of the unstructured element, the work order review device 200 may further support the configuration of the user 100 in the foregoing calculation manner of determining the preset threshold and the similarity of the target work order. For example, in the configuration interface shown in fig. 5, when the query element specified by the user includes an unstructured element, the user 100 may configure a threshold value used for measuring the semantic similarity of two worksheets on the element content of the unstructured element on the configuration interface, and the configuration interface may further present multiple computing manners for computing the similarity, so that the user 100 selects one computing manner from the multiple computing manners to perform worksheet query.

In addition, in the process of checking the work order, if the check module 203 does not find the work order matched semantically with the element content belonging to the structural element from the database according to the element content belonging to the structural element in the work order to be checked, or the semantically similarity between the work order to be checked and each candidate work order in the element content of the unstructured element is less than or equal to the preset threshold, the check module 203 may determine that the target work order repeated with the work order to be checked does not exist in the database. In practical application, for a work order to be checked, where there is no duplicate work order, the work order checking device 200 may further add one or more elements corresponding to the work order to be checked to the database, so as to enrich the database, so as to guide the checking process of other work orders based on the updated database.

It should be noted that, the above manner of determining the target work order is merely an exemplary illustration, and in practical application, the weight checking module 203 may determine the target work order by other manners, for example, after the weight checking module 203 calculates the semantically similar degree of each candidate work order and the to-be-checked weight work order in the element content of the unstructured element based on the above formula (1), the weight checking module may sort the similarity magnitudes corresponding to each candidate work order, and determine all the first N candidate work orders with the largest similarity degree as the target work order (N is a positive integer, for example, is 1).

In this embodiment, the worksheets in the database may be other worksheets to be checked that are not processed, for example, worksheets that are received in 24 hours but not processed yet, and the like. Thus, after the work order is subjected to the duplicate checking processing by the work order checking device 200, the duplicate work orders can be deleted, or batch processing of the same operation is performed on the duplicate work orders, so that the efficiency of processing the work orders by the user 100 is reduced, and the cost of processing the work orders is reduced.

For another example, the worksheets in the database may be, for example, historical worksheets, and, for example, worksheets processed in the past by the enterprise may be stored in the database in advance as historical worksheets. In this way, after searching the historical work order which is repeated with the work order to be checked from the database, the user 100 can perform corresponding processing on the work order to be checked based on the operation of processing the historical work order by the enterprise; or, the reasons why the history disposal cannot thoroughly solve the problem can be analyzed based on the processing process of the history worksheets by enterprises.

Illustratively, when the work order stored in the database is a historical work order, the work order duplication checking device 200 may further perform element mining on the historical work order by using an element mining model in the model library before the work order duplication checking, so as to obtain elements (including a structured element and an unstructured element) corresponding to each historical work order, so that the historical work order and the element can be stored in the database correspondingly. In this way, the duplication checking module 203 can determine the elements of each history work order and the element contents belonging to each element from the database when the work order is duplicated. In practical application, if the historical work order and a part of elements of the historical work order are stored in the database in advance, the work order checking device 200 can use the training element mining model to mine the elements of the historical work order in the database and then supplement the elements corresponding to the historical work order stored in the database.

Based on the above procedure, the duplicate checking module 203 may find a target work order from the database and send the target work order to the interaction module 201.

S305: the interaction module provides the target worksheet for presentation to the user 100.

In one possible implementation manner, when the work order re-checking device 200 determines the target work order repeated with the work order to be checked in the database, the work order re-checking device 200 may further bind and output the target work order and the work order to be checked, and present the relevant information of the target work order to the user 100 (or the technician), such as presenting the name of the target work order, the content of the work order, the similarity of the semantics of the work order to be checked and the target work order on unstructured elements, the time of finding the work order, the historical treatment content of the target work order, and the like, so as to further improve the accuracy of checking the work order by manually judging whether the two work orders are repeated.

For example, the interaction module 201 may generate a verification interface for presenting the to-be-checked heavy work order and the target work order to the user 100, where the verification interface may include, for example, the target work order and related information of the to-be-checked heavy work order as shown in fig. 6. In this way, after the user 100 views the target work orders that may be repeated with the work orders to be checked, it can manually determine whether the two work orders are repeated through the presented related information of the two work orders. And, as shown in fig. 6, the configuration interface may be further configured with a "parallel list" control, so that when the user 100 determines that the target work list is repeated with the to-be-checked duplicate work list, the user may click on the "parallel list" control. Accordingly, the interaction module 201 combines the to-be-checked heavy work order with the target work order based on the confirmation operation (i.e., the operation of clicking the "parallel order" control) of the user 100. Therefore, the repeated work orders to be checked can be correspondingly processed in the follow-up operation mode of the processing target work orders, so that the processing efficiency of the processing work orders is improved, the processing cost of the processing work orders is reduced, or the reasons of the repeated work orders can be analyzed, such as the root cause that the problem cannot be thoroughly solved by analyzing the history disposal. Meanwhile, the configuration interface may be further configured with a "no-single" control, and when the user 100 determines that the target and the work order to be checked are not repeated, the user may click on the "no-single" control, so as to individually process the work order to be checked later.

Further, after the work order re-checking device 200 completes the re-checking process for the work order to be checked, the work order re-checking device 200 can update the element mining model in the model library by using the work order to be checked as a new training sample, so as to maintain the vitality of the element mining model and maintain the reasoning precision of the element mining model at a higher level through dynamically updating the element mining model.

It should be noted that, in this embodiment, the work order check process executed by the work order check device 200 is described with respect to one work order to be checked, and in practical application, the number of work orders to be checked provided by the user 100 may be plural, so that the work order check device 200 may perform check processing for each work order provided by the user 100 in a similar manner as described above.

In the embodiments described above, the work order re-checking apparatus 200 related to the work order re-checking process may be software configured on a computing device or a computing device cluster, and by running the software on the computing device or the computing device cluster, the computing device or the computing device cluster may implement the functions of the work order re-checking apparatus 200 described above. The work order duplication checking device 200 related to the work order duplication checking process is described in detail below based on the angle of implementation of the hardware device.

Fig. 7 shows a schematic structural diagram of a computing device, where the work order weight checking apparatus 200 may be deployed, where the computing device may be a computing device (such as a server) in a cloud environment, or a computing device in an edge environment, or a terminal device, etc. may be specifically configured to implement the functions of the interaction module 201, the element mining module 202, the weight checking module 203, and the model training module 204 in the work order weight checking apparatus 200 in the embodiment shown in fig. 3.

As shown in fig. 7, computing device 600 includes a processor 610, a memory 620, a communication interface 630, and a bus 640. Communication between processor 610, memory 620, and communication interface 630 occurs via bus 640. Bus 640 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus. The communication interface 630 is used for communicating with the outside, for example, receiving a work order to be checked provided by the user, presenting a target work order to the user, and the like.

The processor 610 may be, among other things, a central processing unit (central processing unit, CPU), an application specific integrated circuit (application specific integrated circuit, ASIC), a graphics processor (graphics processing unit, GPU), or one or more integrated circuits. The processor 610 may also be an integrated circuit chip with signal processing capabilities. In implementation, the functions of the various modules in the work order checkweigher 200 may be performed by integrated logic circuitry of hardware in the processor 610 or by instructions in the form of software. The processor 610 may also be a general purpose processor, a data signal processor (digital signal process, DSP), a field programmable gate array (fieldprogrammable gate array, FPGA) or other programmable logic device, discrete gate or transistor logic devices, discrete hardware components, and may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present application. The method disclosed in the embodiment of the application can be directly embodied as a hardware decoding processor or implemented by a combination of hardware and software modules in the decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 620, and the processor 610 reads the information in the memory 620 and, in combination with its hardware, performs some or all of the functions in the work order repeat unit 200.

The memory 620 may include volatile memory (RAM), such as random access memory (random access memory). The memory 620 may also include a non-volatile memory (non-volatile memory), such as a read-only memory (ROM), a flash memory, an HDD, or an SSD.

The memory 620 has stored therein executable code that the processor 610 executes to perform the methods performed by the work order checkduplication apparatus 200 described above.

Specifically, in the case where the embodiment shown in fig. 3 is implemented, and in the case where the work order repeat unit 200 described in the embodiment shown in fig. 3 is implemented by software, software or program code required for performing the functions of the work order repeat unit 200 in fig. 3 is stored in the memory 620, the interaction of the work order repeat unit 200 with other devices is implemented through the communication interface 630, and the processor is configured to execute instructions in the memory 620 to implement a method performed by the work order repeat unit 200.

FIG. 8 illustrates a schematic diagram of a computing device cluster. The computing device cluster 70 shown in fig. 8 includes a plurality of computing devices, and the worksheet checking apparatus 200 may be distributed and deployed on the plurality of computing devices in the computing device cluster 70. As shown in fig. 8, the computing device cluster 70 includes a plurality of computing devices 700, each computing device 700 including a memory 720, a processor 710, a communication interface 730, and a bus 740, wherein the memory 720, the processor 710, and the communication interface 730 implement a communication connection between each other through the bus 740.

Processor 710 may employ CPU, GPU, ASIC or one or more integrated circuits. Processor 710 may also be an integrated circuit chip with signal processing capabilities. In implementation, some of the functions of worksheet inspection device 200 may be performed by instructions in the form of integrated logic circuits or software in hardware in processor 710. Processor 710 may also be a DSP, FPGA, general purpose processor, other programmable logic device, discrete gate or transistor logic device, discrete hardware components, and may implement or perform some of the methods, steps, and logic blocks disclosed in embodiments of the present application. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware decoding processor or in a combination of hardware and software modules in the decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 720, and in each computing device 700, the processor 710 reads the information in the memory 720, and in combination with the hardware, can perform part of the functions of the work order weight checking device 200.

The memory 720 may include ROM, RAM, static storage devices, dynamic storage devices, hard disks (e.g., SSDs, HDDs), etc. The memory 720 may store program code, for example, part or all of the program code for implementing the interaction module 201, part or all of the program code for implementing the element mining module 202, part or all of the program code for implementing the review module 203, part or all of the program code for implementing the model training module 204, and so forth. For each computing device 700, when the program code stored in the memory 720 is executed by the processor 710, the processor 710 performs a portion of the methods performed by the work order weight apparatus 200, such as a portion of the computing devices 700 that may be used to perform the methods performed by the interaction module 201 and the element mining module 202 described above, a portion of the computing devices 700 that may be used to perform the methods performed by the weight checking module 203 described above, and a portion of the computing devices 700 that may be used to perform the methods performed by the model training module 204 described above, based on the communication interface 730. Memory 720 may also store data such as: intermediate data or result data generated during execution by the processor 710, such as element content pertaining to the weight checking element, a target work order, etc.

The communication interface 703 in each computing device 700 is used to communicate with the outside, such as to interact with other computing devices 700, etc.

Bus 740 may be a peripheral component interconnect standard bus or an extended industry standard architecture bus, among others. For ease of illustration, bus 740 within each computing device 700 in FIG. 8 is represented by only one thick line, but does not represent only one bus or type of bus.

Communication paths are established between the plurality of computing devices 700 through a communication network to realize the functions of the work order repeat checking apparatus 200. Any computing device may be a computing device in a cloud environment (e.g., a server), or a computing device in an edge environment, or a terminal device.

The embodiment of the application also provides a computer readable storage medium. The computer readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), etc. The computer readable storage medium includes instructions that instruct a computing device to perform the above-described work order duplication checking method applied to the work order duplication checking apparatus 200.

Embodiments of the present application also provide a computer program product comprising instructions. The computer program product may be software or a program product containing instructions capable of running on a computing device or stored in any useful medium. The computer program product, when run on at least one computer device, causes the at least one computer device to perform the work order duplication method described above. It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computing device (which may be a personal computer, a training device, a network device, etc.) to execute the method according to the embodiments of the present application.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

Claims (15)

1. A work order duplication checking method, the method comprising:

acquiring a work order to be checked;

acquiring a duplicate checking element designated by a user;

excavating element contents belonging to the duplicate checking elements in the duplicate checking work order by using an element excavation model in a model library;

searching a target work order from a plurality of work orders stored in a database, wherein the semantics of the element content belonging to the duplicate checking element in the target work order is matched with the semantics of the element content belonging to the duplicate checking element in the work order to be checked;

and providing the target work order, wherein the target work order is used for being presented to the user.

2. The method of claim 1, wherein the importance-checking element comprises a structured element and an unstructured element, and wherein the locating the target work order from the plurality of work orders stored in the database comprises:

screening a plurality of worksheets stored in a database according to the element content of the structural element in the to-be-checked heavy worksheets to obtain a candidate worksheet set, wherein the candidate worksheet set comprises at least one candidate worksheet, and the semantics of the element content of the structural element in the candidate worksheet is matched with the semantics of the element content of the structural element in the to-be-checked heavy worksheet;

Respectively calculating the similarity between the semantics of the element content belonging to the unstructured element in the to-be-checked heavy work order and the semantics of the element content belonging to the unstructured element in each candidate work order;

determining the target work order from the at least one candidate work order, wherein the similarity between the semantics of the element content belonging to the unstructured element in the target work order and the semantics of the element content belonging to the unstructured element in the to-be-checked heavy work order is larger than a preset threshold value.

3. The method of claim 2, wherein the obtaining the user-specified weight factor comprises:

generating a configuration interface for presenting a plurality of importance-checking elements to the user;

and responding to the selection operation of the user on the configuration interface for the plurality of weight checking elements, and determining the structural elements and the unstructured elements selected by the user.

4. A method according to claim 3, characterized in that the method further comprises:

determining the preset threshold value in response to configuration operation of the user on the unstructured element in the configuration interface;

and responding to the selection operation of the user on the configuration interface for a plurality of calculation modes, and determining the calculation mode corresponding to the similarity.

5. The method of any of claims 2 to 4, wherein the unstructured element comprises at least one of a text vector, a picture vector, and a video vector.

6. The method according to any one of claims 1 to 5, further comprising:

generating a checking interface, wherein the checking interface is used for presenting the target work order and the work order to be checked to the user;

and responding to the confirmation operation of the user, and combining the to-be-checked heavy work order and the target work order so that the to-be-checked heavy work order and the target work order are processed based on the same operation.

7. The utility model provides a work order check heavy device which characterized in that, work order check heavy device includes:

the interaction module is used for acquiring the work order to be checked and the check factor appointed by the user;

the element mining module is used for mining element contents belonging to the weight checking elements in the weight checking work order to be checked by using element mining models in the model library;

the duplicate checking module is used for searching a target work order from a plurality of work orders stored in the database, and the semantics of the element content belonging to the duplicate checking element in the target work order is matched with the semantics of the element content belonging to the duplicate checking element in the work order to be checked;

The interaction module is further configured to provide the target worksheet, where the target worksheet is configured to be presented to the user.

8. The work order duplication checking apparatus of claim 7 wherein the duplication checking module is configured to:

screening a plurality of worksheets stored in a database according to the element content of the structural element in the to-be-checked heavy worksheets to obtain a candidate worksheet set, wherein the candidate worksheet set comprises at least one candidate worksheet, and the semantics of the element content of the structural element in the candidate worksheet is matched with the semantics of the element content of the structural element in the to-be-checked heavy worksheet;

respectively calculating the similarity between the semantics of the element content belonging to the unstructured element in the to-be-checked heavy work order and the semantics of the element content belonging to the unstructured element in each candidate work order;

determining the target work order from the at least one candidate work order, wherein the similarity between the semantics of the element content belonging to the unstructured element in the target work order and the semantics of the element content belonging to the unstructured element in the to-be-checked heavy work order is larger than a preset threshold value.

9. The worksheet repetition checking device of claim 8, wherein the interaction module is configured to:

generating a configuration interface for presenting a plurality of importance-checking elements to the user;

and responding to the selection operation of the user on the configuration interface for the plurality of weight checking elements, and determining the structural elements and the unstructured elements selected by the user.

10. The worksheet repetition checking device of claim 9, wherein the interaction module is further configured to:

determining the preset threshold value in response to configuration operation of the user on the unstructured element in the configuration interface;

and responding to the selection operation of the user on the configuration interface for a plurality of calculation modes, and determining the calculation mode corresponding to the similarity.

11. The worksheet repetition device of any of claims 8-10, wherein the unstructured elements comprise at least one of text vectors, picture vectors, and video vectors.

12. The worksheet repetition device of any of claims 7 to 11, wherein the interaction module is further configured to:

generating a checking interface, wherein the checking interface is used for presenting the target work order and the work order to be checked to the user;

And responding to the confirmation operation of the user, and combining the to-be-checked heavy work order and the target work order so that the to-be-checked heavy work order and the target work order are processed based on the same operation.

13. A cluster of computing devices, the cluster of computing devices comprising at least one computing device, each computing device comprising a processor and memory:

the memory is used for storing instructions;

the processor is configured to cause the cluster of computing devices to perform the method of any of claims 1-6 in accordance with the instructions.

14. A computer readable storage medium having instructions stored therein which, when run on a computing device, cause the computing device to perform the method of any of claims 1 to 6.

15. A computer program product containing instructions which, when run on a computing device, cause the computing device to perform the method of any of claims 1 to 6.