CN113837404A

CN113837404A - False elevator maintenance work order identification method, device, equipment and storage medium

Info

Publication number: CN113837404A
Application number: CN202111005400.8A
Authority: CN
Inventors: 刘佳
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Ping An International Smart City Technology Co Ltd
Priority date: 2021-08-30
Filing date: 2021-08-30
Publication date: 2021-12-24

Abstract

The application relates to the technical field of artificial intelligence, and discloses a false elevator maintenance work order identification method, a false elevator maintenance work order identification device, computer equipment and a storage medium, wherein the false elevator maintenance work order identification method comprises the following steps: through the effective screening of the elevator maintenance work order, the standardized elevator maintenance work order is obtained and used as an effective work order, and the accuracy of elevator maintenance work order identification is improved. The project information in the effective work order is converted into a discrete value, whether the discrete value of the project information is in a reasonable range or not is judged through the recognition model, and the project information is digitalized, so that the recognition accuracy of the false work order is improved. The effective work order with abnormal project information with abnormal discrete values is used as the undetermined work order, and then the false work order is recognized through the weighted value of the abnormal project information in each undetermined work order, so that the monitoring timeliness of the elevator maintenance work order is guaranteed, and the elevator maintenance work order recognition accuracy is improved.

Description

False elevator maintenance work order identification method, device, equipment and storage medium

Technical Field

The application relates to the technical field of artificial intelligence, in particular to a false elevator maintenance work order identification method and device, computer equipment and a storage medium.

Background

According to public data display of the State market supervision and management Bureau, the holding capacity of the elevator in China is increased year by year, the use safety of the elevator is more and more emphasized by people, and the use safety of the elevator depends on regular and regular maintenance of the elevator by an elevator maintenance party.

However, some elevator maintenance parties forge a false elevator maintenance order in order to save maintenance cost, and after an elevator accident occurs, the behavior of forging the false elevator maintenance order can be discovered by performing case investigation on the elevator maintenance party. Therefore, the false elevator maintenance work order in the conventional supervision mode through the elevator maintenance work order cannot be found in time, so that the problem that the supervision of the elevator maintenance work order has hysteresis is caused.

Disclosure of Invention

The application provides a false elevator maintenance work order identification method, a false elevator maintenance work order identification device, computer equipment and a storage medium, and solves the problem that in the supervision process of an elevator maintenance work order, the false elevator maintenance work order cannot be found in time, so that the supervision of the elevator maintenance work order has hysteresis.

In a first aspect, an embodiment of the present application provides a method for identifying a false elevator maintenance work order, including:

the method comprises the steps that a plurality of elevator maintenance work orders are effectively screened based on project information in the elevator maintenance work orders to obtain an effective work order set; the effective work order set comprises a plurality of effective work orders;

performing discrete value conversion on the item information in each effective work order to obtain a discrete value set corresponding to each effective work order; information in the discrete value set corresponds to project information in the effective work order one by one;

determining an undetermined work order set with abnormal project information from a plurality of effective work orders according to the discrete value set of each effective work order by using a decision tree algorithm in a pre-trained recognition model;

and identifying a false work order from the undetermined work order set according to the weight value of the abnormal item information in each undetermined work order in the undetermined work order set.

In a second aspect, an embodiment of the present application further provides an apparatus for identifying a false elevator maintenance work order, including:

the elevator maintenance work order screening system comprises an acquisition module, a selection module and a selection module, wherein the acquisition module is used for effectively screening a plurality of elevator maintenance work orders based on project information in the plurality of elevator maintenance work orders to obtain an effective work order set; the effective work order set comprises a plurality of effective work orders;

the conversion module is used for carrying out discrete value conversion on the project information in each effective work order to obtain discrete values corresponding to the project information in the effective work orders one by one; a plurality of discrete values of each effective work order form a corresponding discrete value set;

the analysis module is used for determining a pending work order set with abnormal project information from a plurality of effective work orders according to the discrete value set of each effective work order by utilizing a decision tree algorithm in a pre-trained recognition model;

and the identification module is used for identifying the false work order from the undetermined work order set according to the weight value of the abnormal item information in each undetermined work order in the undetermined work order set.

In a third aspect, the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method for identifying a false elevator maintenance work order when executing the computer program.

In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of the method for identifying a false elevator maintenance work order are implemented.

According to the identification method and device, the computer equipment and the storage medium of the false elevator maintenance work order, the standard elevator maintenance work order is obtained as the effective work order through effective screening of the elevator maintenance work order, and the accuracy of elevator maintenance work order identification is improved. The project information in the effective work order is converted into a discrete value, whether the discrete value of the project information is in a reasonable range or not is judged through the recognition model, and the project information is digitalized, so that the recognition accuracy of the false work order is improved. The effective work order with abnormal project information with abnormal discrete values is used as the undetermined work order, and then the false work order is recognized through the weighted value of the abnormal project information in each undetermined work order, so that the monitoring timeliness of the elevator maintenance work order is guaranteed, and the elevator maintenance work order recognition accuracy is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is an application environment schematic diagram of a data entry reminding method according to an embodiment of the present application;

fig. 2 is a flowchart illustrating an implementation of a data entry reminding method according to an embodiment of the present application;

fig. 3 is a flowchart of step S10 in a data entry reminding method according to an embodiment of the present application;

fig. 4 is a flowchart of step S30 in a data entry reminding method according to an embodiment of the present application;

fig. 5 is a flowchart of step S40 in a data entry reminding method according to an embodiment of the present application;

FIG. 6 is a flowchart illustrating steps S51-S52 of a method for reminding data entry according to another embodiment of the present application;

fig. 7 is a schematic structural diagram of an identification device for a false elevator maintenance work order according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a computer device provided by an embodiment of the present application.

Detailed Description

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 some, but not all, embodiments of the present application. 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 method for identifying the false elevator maintenance work order provided by the embodiment of the application can be applied to the application environment shown in fig. 1. As shown in fig. 1, a client (computer device) communicates with a server through a network. The client (computer device) includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, cameras, and portable wearable devices. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. The identification method of the false elevator maintenance work order provided by the embodiment can be executed by the server, for example, a user sends a plurality of elevator maintenance work orders to be processed to the server through the client, the server executes the identification method of the false elevator maintenance work order provided by the embodiment based on the elevator maintenance work orders to be processed, so as to obtain an identification result of whether the elevator maintenance work order is the false work order, and finally, the identification result can be sent to the client.

In some scenarios other than fig. 1, the client may also execute the identification method of the false elevator maintenance work order, obtain an identification result of whether the elevator maintenance work order is the false work order by executing the identification method of the false elevator maintenance work order provided by this embodiment directly according to a plurality of determined elevator maintenance work orders, and then send the identification result to the server for storage.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

It is understood that a Decision Tree (Decision Tree) is a common prediction model in machine learning, and represents a mapping relationship between object attributes and object values. The decision tree is a graphical method for intuitively applying probability analysis, and the decision tree is constructed on the basis of the known occurrence probability of various conditions to obtain the probability that the expected value of the net present value is greater than or equal to zero, evaluate the risk of the project and judge the feasibility of the project. This decision branch is called a decision tree because it is drawn to resemble a branch of a tree.

It can be understood that the elevator maintenance work order is used for monitoring and controlling elevator maintenance and is also an important basis for elevator maintenance records, the information of a plurality of items recorded by the elevator maintenance work order generally comprises a maintenance unit, a maintenance record, maintenance personnel, elevator equipment, elevator fault data, elevator maintenance items and the like, and there is a possibility that the information recorded by the elevator maintenance work order files in different regions is different. The following false elevator maintenance work order is referred to as a false work order for short, and is convenient to understand.

Fig. 2 shows a flowchart of an implementation of a method for identifying a false elevator maintenance work order according to an embodiment of the present application. As shown in fig. 2, the technical scheme of the method for identifying the false elevator maintenance work order mainly comprises the following steps of S10-S40:

step S10, effectively screening a plurality of elevator maintenance work orders based on project information in the elevator maintenance work orders to obtain an effective work order set; the valid work order set comprises a plurality of valid work orders.

In step S10, the plurality of item information records are used for the identification processing of the elevator maintenance work order based on the elevator maintenance work order, and for this reason, the authenticity and integrity of the plurality of item information records of the elevator maintenance work order are the basis for ensuring the accuracy of the identification processing of the elevator maintenance work order. The effective work order which can be used for identifying the elevator maintenance work order is screened out by checking a plurality of items of information of the elevator maintenance work order.

Here, a plurality of elevator maintenance work orders can be sent to the server by the client, when the elevator maintenance work orders are specifically implemented, the client provides and fills in a plurality of item information for elevator maintenance personnel by displaying pages of the elevator maintenance work orders, the elevator maintenance personnel fill in according to all items of the detected elevators, each elevator can perform elevator maintenance in different time periods according to maintenance requirements, and a corresponding elevator maintenance work order is generated in each elevator maintenance process. The elevator maintenance work order can be uploaded in real time, and can also be locally stored by elevator maintenance personnel and uploaded within a reasonable time range.

In one embodiment, the plurality of elevator maintenance work orders have certain relevance, and the relevance is embodied by the item content, including the same maintenance personnel or the same elevator equipment in the item content.

In one embodiment, the elevator maintenance work order can be recorded in an Excel form file or an XML file according to requirements, wherein the Excel form file is simple in input mode, and the efficiency of manual recording is improved. The content recorded by the elevator maintenance work order is divided according to the project information, different pieces of project information correspond to different recorded contents, such as Zhang III of maintenance personnel and I-elevator of maintenance equipment, and the multi-dimensional division is favorable for analysis and calculation.

Fig. 3 shows a flowchart of step S10 in a data entry reminding method according to an embodiment of the present application.

As shown in fig. 3, as one embodiment, step S10 includes:

step S101, carrying out item information identification on each elevator maintenance work order to obtain an item information set of each elevator maintenance work order;

and S102, when the project information set of the elevator maintenance work order contains preset necessary project information, taking the elevator maintenance work order as an effective work order to obtain an effective work order set.

In step S101, item information of each elevator maintenance work order is identified, and each item information of the elevator maintenance work orders is divided and sorted to obtain an item information set corresponding to the elevator maintenance work orders.

In step S102, matching preset necessary item information with the item information included in the item information set, querying whether the item information set of the elevator maintenance work order includes the preset necessary item information, taking the elevator maintenance work order including the preset necessary item information as an effective work order, and forming an effective work order set from the screened effective work orders.

In one embodiment, the preset necessary item information is determined by the recognition model in the pre-training process, and the item information with a certain weight value is kept as the necessary item information in the process of recognizing the false work order through the training of a plurality of sample work orders.

In another embodiment, the elevator maintenance work order of which the project information set lacks preset necessary project information is taken as an invalid work order, the invalid work order is returned, and the example of the missing necessary project information is added to improve the invalid work order by an elevator maintenance worker.

Step S20, performing discrete value conversion on the item information in each effective work order to obtain a discrete value set corresponding to each effective work order; information in the discrete value set is used for describing discrete relations among item information in the effective work order;

in step S20, the item information in the valid work orders is not independent, and each item information in the plurality of valid work orders is converted into a one-to-one discrete value, and the plurality of discrete values form a discrete value set describing a discrete relationship between the item information in the valid work orders and are used for analyzing abnormal item information in each valid work order.

When the item information is a numerical value, converting the numerical value into a discrete value; and when the item information is an event, converting the item information into a discrete value by utilizing preset hierarchical identification.

In an embodiment, when the item information is an event, the preset classification identification is classified according to the content of the event, for example, the item information of the item "travelling cable inspection" is "no damage", and the item information may also be "slight skin wear, severe skin wear, and cable damage", and the damage degree is preset as required for classification identification for processing discrete value conversion when the item information is an event. When the item information is a numerical value, for example, the item information of the item "engaging length of the landing door locking member" is "9 mm", the numerical value of the item information is directly used to be converted into a discrete value.

Step S30, determining an undetermined work order set with abnormal project information from a plurality of effective work orders according to the discrete value set of each effective work order by using a decision tree algorithm in a pre-trained recognition model;

in step S30, a plurality of discrete values in the discrete value set of the valid work orders are determined by the pre-trained recognition model, abnormal item information corresponding to the discrete value abnormality is determined as an undetermined work order, and a plurality of work orders to be determined including the abnormal item information form an undetermined work order set.

In one embodiment, the pre-trained recognition model is trained based on a plurality of sample work orders, a reasonable range of discrete values corresponding to the item information in the sample work orders is determined through a decision tree algorithm, then the weight of each item information is calculated through a multiple linear regression algorithm, and the false work orders are recognized according to the weights of the item information which is not in the reasonable range.

The pre-trained recognition model can match a reasonable range of discrete values corresponding to discrete values of the project information according to the discrete relationship among the project information in the described effective work orders in the discrete value set of each effective work order, so that the project information corresponding to the discrete values which are not in the reasonable range is found out to be used as abnormal project information, and the to-be-determined work orders are determined to form a to-be-determined work order set to wait for the recognition of the false work orders according to the abnormal project information.

And matching corresponding project information weight according to the abnormal project information of each undetermined work order in the undetermined work order set, and when the proportion of the abnormal project information of the undetermined work order reaches the standard of the false work order, determining the undetermined work order as the false work order, thereby screening the false work order from the undetermined work order set.

Fig. 4 is a flowchart illustrating that, according to the discrete value set of each valid work order, a decision tree algorithm in a pre-trained recognition model is used to determine a pending work order set with abnormal item information from a plurality of valid work orders. As shown in fig. 4, as one embodiment, step S30 includes:

s301, based on the reasonable range of each item information measured and calculated by a pre-trained recognition model, screening discrete values which do not conform to the corresponding reasonable range in the discrete value set through the decision tree algorithm;

and step S302, according to the item information corresponding to the discrete value which does not conform to the corresponding reasonable range, the item information is used as abnormal item information, and a corresponding set of the to-be-determined work orders is determined.

In step S301, based on the reasonable range of each item information measured by the pre-trained recognition model, discrete values corresponding to the plurality of item information of the valid work order are matched, whether the discrete values belong to the reasonable range corresponding to the item information is detected by the decision tree algorithm, and item information corresponding to discrete values that do not conform to the corresponding reasonable range in the discrete value set is screened.

In one embodiment, the item information screening manner corresponding to the discrete value which does not conform to the corresponding reasonable range in the discrete value set, for example, the reasonable range of the item information of the item "gap between the car door vane and the landing sill" is "5-10", the discrete value corresponding to the discrete value set is "9", the reasonable range corresponding to the item information of the item 'mutual rubbing condition of the car door vane and the landing sill' is '1', the item information is classified into 'level 1 can not mutually rub and touch, level 2 is about to rub and touch, level 3 slightly rubs and touches mutually, level 4 seriously rubs and touches', and if the discrete value corresponding to the discrete value set is '2', the discrete value and the item information corresponding to the item 'gap between the car door vane and the landing sill' and the item 'mutual rubbing condition between the car door vane and the landing sill' are screened.

It will be appreciated that decision tree algorithm is a method of approximating discrete function values, which is a typical classification method, by first processing the data, using an inductive algorithm to generate readable rules and decision trees, and then using the decisions to analyze the new data.

In step S302, item information corresponding to a discrete value that does not conform to a corresponding reasonable range is screened as abnormal item information, where the abnormal item information is used to determine that there is a probability that an effective work order corresponding to the abnormal item information will be a false work order, and thus, the effective work order corresponding to the abnormal item information is used as an undetermined work order for detection, and a plurality of work orders to be determined form an undetermined work order set.

And step S40, identifying a false work order from the undetermined work order set according to the weight value of the abnormal item information in each undetermined work order in the undetermined work order set.

In step S40, by analyzing the weight value of the abnormal item information in the pending work order, it is determined whether the pending work order is a false work order according to the weight value occupied by the abnormal item information.

Fig. 5 shows a flowchart for identifying a false work order from the pending work order set according to a weight value of abnormal item information in each pending work order in the pending work order set, provided by an embodiment of the present application. As shown in fig. 5, as one embodiment, step S40 includes:

step S401, inquiring a weight value of item information corresponding to abnormal item information in each pending work order in the pending work order set through the pre-trained recognition model;

and S402, identifying a false work order from the pending work order set according to the weight value of the abnormal item information.

In step S401, the weight value of the item information corresponding to the abnormal item information is queried by matching the abnormal item information with the weight value of the item information corresponding to the recognition model trained in advance.

In step S402, the identification model after pre-training is used to determine whether the pending work order belongs to a false work order according to the weight value of the abnormal item information, and when the weight value of the abnormal item information of the pending work order reaches the determination standard of the identification model for the false work order, the pending work order is considered as the false work order, and the false work order is screened from the pending work order set.

In an embodiment, the to-be-determined work order includes a plurality of pieces of abnormal item information, and a weight value corresponding to each piece of abnormal item information is obtained by querying the recognition model trained in advance. For example, the item information corresponding to the item "car door knife and landing door sill gap" and the item "car door knife and landing door sill mutual rubbing condition" is abnormal item information, and the sum of the weighted values of the item "car door knife and landing door sill gap" and the item "car door knife and landing door sill mutual rubbing condition" is 4%, and the sum of the weighted values is less than 50% of the judgment standard of the identification model for the false work order, and the to-be-determined work order is not the false work order.

Fig. 6 is a flowchart of a data entry reminding method according to another embodiment of the present application. As shown in fig. 6, unlike the embodiment shown in fig. 4, in step S30, before determining the pending work order set having abnormal item information from the plurality of valid work orders according to the discrete value sets corresponding to all item information in each valid work order by using the decision tree algorithm in the recognition model trained in advance, the method further includes steps S51 to S52, specifically:

step S51, pre-training the recognition model by using a decision tree algorithm based on a plurality of sample work orders, and measuring a reasonable range corresponding to each item information by using the decision tree algorithm; and the identification model determines a pending work order set with the abnormal project information according to the reasonable range of each project information.

And step S52, determining the weight values of the plurality of item information in the identification of the false work orders by utilizing a multiple linear regression algorithm according to the plurality of reasonable ranges.

In step S51, the recognition model is pre-trained by a plurality of the sample workflows to improve the recognition accuracy of the false workflows of the recognition model. And calculating a reasonable range corresponding to each item information by using a decision tree algorithm through a plurality of sample work orders.

It can be understood that the decision tree algorithm is to input training data under the selected characteristics into the decision tree algorithm for training, the decision tree algorithm will continuously select a partition mode with the largest entropy reduction to distinguish samples, and continuously iterate until all sub-branches are the same sample label set. After training, the test data can be retrieved according to the judgment condition of the fork node until the final leaf node, and the label of the leaf is returned to be used as the label threshold of the test data.

In one embodiment, the sample work orders comprise positive sample work orders and negative sample work orders, and a plurality of confirmed false work orders are obtained, so that a plurality of false work order files are used as negative samples, and other elevator maintenance work order files are used as positive samples, wherein all elevator maintenance work orders are real elevator maintenance work order files.

In another embodiment, the item information of the positive samples of the elevator maintenance work order files is input into a decision tree algorithm for training by using the decision tree algorithm, and the decision tree algorithm continuously selects entropy subtraction according to the data of the same item information in the positive samples to obtain a sample discrete value set. After the positive samples of the plurality of elevator maintenance work order files are trained, the test data can be retrieved according to the judgment conditions of the project information until the reasonable range of the project information is finally determined.

In step S52, a multiple linear regression algorithm is used to determine the weight values of the plurality of item information in the identification of the false work order according to the reasonable ranges corresponding to the plurality of item information.

It can be understood that, the multiple linear regression algorithm is to input data of a plurality of items of information into the identification model, calculate the error between the calculated value and the real item information, then continuously decrease the gradient and adjust the weight value of each element, and reduce the error until the error is smaller than the required value. So far, we can see the weight values corresponding to different item information, namely the importance degree of the influence of the item information on the identification result.

In one embodiment, the relevance of a plurality of negative samples is calculated by using the multiple linear regression algorithm, the item information in the negative samples of the elevator maintenance work order file is analyzed, and the weight value of the item information in the preliminary analysis model is obtained. Inputting the project information of the negative samples and the reasonable range of the project information of the positive samples of the elevator maintenance work orders into the analysis model, calculating the error between the project information of the negative samples and the predicted label value of the project information of the positive samples by using a multiple linear regression algorithm, then continuously reducing the gradient and adjusting the weight value of each project information, and reducing the error until the error is smaller than the required value.

In another embodiment, the method carries out review according to the recognition result of the false elevator maintenance work order file, adjusts the item information and the weight value of the item information output by the analysis model in the pre-training according to the review result, carries out review, and finely adjusts the item information with lower weight value.

In one embodiment, a device for identifying a false elevator maintenance work order is provided, and the device for identifying the false elevator maintenance work order corresponds to the method for identifying the false elevator maintenance work order in the embodiment one to one. As shown in fig. 7, the device for identifying the false elevator maintenance work order comprises an acquisition module 11, a conversion module 12, an analysis module 13 and an identification module 14, wherein the detailed description of each functional module is as follows:

the obtaining module 11 is used for effectively screening a plurality of elevator maintenance work orders based on project information in the plurality of elevator maintenance work orders to obtain an effective work order set; the effective work order set comprises a plurality of effective work orders;

the conversion module 12 is used for performing discrete value conversion on the project information in each effective work order to obtain discrete values corresponding to the project information in the effective work orders one by one; a plurality of discrete values of each effective work order form a corresponding discrete value set;

the analysis module 13 determines a pending work order set with abnormal item information from the plurality of effective work orders according to the discrete value set of each effective work order by using a decision tree algorithm in a pre-trained recognition model;

and the identification module 14 is used for identifying a false work order from the pending work order set according to the weight value of the abnormal item information in each pending work order in the pending work order set.

For the specific limitation of the identification device of the false elevator maintenance work order, reference may be made to the above limitation on the identification method of the false elevator maintenance work order, and details are not described here. All or part of each module in the device for identifying the false elevator maintenance order can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a client or a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a readable storage medium and an internal memory. The readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the readable storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of identifying a false elevator maintenance order.

In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the method for identifying a false elevator maintenance order in the above embodiments is implemented.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, implements the method for identifying a false elevator maintenance work order in the above-described embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A method for identifying a false elevator maintenance work order is characterized by comprising the following steps:

performing discrete value conversion on the item information in each effective work order to obtain a discrete value set corresponding to each effective work order; information in the discrete value set is used for describing discrete relations among item information in the effective work order;

2. The method for identifying the false elevator maintenance work order according to claim 1, wherein the step of effectively screening the plurality of elevator maintenance work orders based on the item information in the plurality of elevator maintenance work orders to obtain an effective work order set comprises the following steps:

carrying out item information identification on each elevator maintenance work order to obtain an item information set of each elevator maintenance work order;

and when the project information set of the elevator maintenance work order contains preset necessary project information, taking the elevator maintenance work order as an effective work order to obtain an effective work order set.

3. The method for identifying the false elevator maintenance work order of claim 1, wherein the step of converting the discrete values of the item information in each of the valid work orders to obtain the discrete value set corresponding to each of the valid work orders comprises the steps of:

when the item information is a numerical value, converting the numerical value into a discrete value;

and when the item information is an event, converting the item information into a discrete value by utilizing preset hierarchical identification.

4. The method for identifying the false elevator maintenance work order according to claim 1, wherein the step of determining the pending work order set with abnormal item information from the plurality of valid work orders according to the discrete value sets corresponding to all item information in each valid work order by using a decision tree algorithm in the pre-trained identification model comprises:

based on the reasonable range of each item information measured and calculated by the pre-trained recognition model, screening discrete values which do not conform to the corresponding reasonable range in the discrete value set through the decision tree algorithm;

and according to the item information corresponding to the discrete value which does not conform to the corresponding reasonable range, taking the item information as abnormal item information and determining a corresponding set of the to-be-determined work orders.

5. The method for identifying the false elevator maintenance work order of claim 1, wherein the identifying the false work order from the pending work order set according to the weight value of the abnormal item information in each pending work order in the pending work order set comprises:

inquiring the weight value of the item information corresponding to the abnormal item information in each pending work order in the pending work order set through the pre-trained recognition model;

and identifying a false work order from the set of the to-be-determined work orders according to the weight value of the abnormal project information.

6. The method for identifying the false elevator maintenance work order according to claim 4, wherein before the step of determining the pending work order set with abnormal item information from the plurality of valid work orders according to the discrete value set corresponding to all item information in each valid work order by using the decision tree algorithm in the pre-trained identification model, the method further comprises:

pre-training the recognition model based on a plurality of sample worksheets, and measuring out a reasonable range corresponding to each item information by using a decision tree algorithm; and the identification model determines a pending work order set with the abnormal project information according to the reasonable range of each project information.

7. The method for identifying the false work order for elevator maintenance according to claim 6, wherein before the step of querying the weight value of the item information corresponding to the abnormal item information in each pending work order in the pending work order set through the pre-trained identification model, and identifying the false work order from the pending work order set according to the weight value of the abnormal item information, the method further comprises:

and determining the weight values of the plurality of items of information in the identification of the false work orders by utilizing a multiple linear regression algorithm according to the plurality of reasonable ranges.

8. An apparatus for identifying a false elevator maintenance order, comprising:

9. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the method of identifying a false elevator maintenance work order according to any one of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the method for identifying a false elevator maintenance work order according to any one of claims 1 to 7.