CN111611353B - Screening method, screening device, electronic equipment and computer readable storage medium - Google Patents
Screening method, screening device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111611353B CN111611353B CN201910139175.3A CN201910139175A CN111611353B CN 111611353 B CN111611353 B CN 111611353B CN 201910139175 A CN201910139175 A CN 201910139175A CN 111611353 B CN111611353 B CN 111611353B
- Authority
- CN
- China
- Prior art keywords
- target
- work order
- order data
- keywords
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a screening method, a screening device, electronic equipment and a computer readable storage medium, wherein the screening method comprises the following steps: acquiring work order data in an online service process, and performing word segmentation on the work order data; performing target processing on each candidate keyword in the work order data to obtain at least one new work order data; classifying the work order data and at least one new work order data by using a target classification model to obtain a classification result; the classification processing result is used for representing whether the work order data and the new work order data are safety work orders or not; determining target keywords in the candidate keywords based on the classification processing result; the target keyword is used for representing that the work order data is not a security class work order. The embodiment of the application can screen the worksheet data in a machine learning mode to determine whether the worksheet data is a safety worksheet, thereby relieving the technical problems of lower screening efficiency and poor accuracy when the emergency safety worksheets are screened by the prior art.
Description
Technical Field
The present application relates to the field of data processing technology, and in particular, to a screening method, apparatus, electronic device, and computer readable storage medium.
Background
An online service mode exists in a customer service system of the network taxi-taking platform, and the online service mode mainly solves the problem of a user in a text information mode, for example, the user can reflect various service problems in an online service mode, and customer service staff can solve and process the problems reflected by the user online.
In order to ensure the service quality of the network taxi, the network taxi platform usually screens out abnormal worksheets from a large number of worksheets based on the security class problem fed back by users to customer service. The screening method of the abnormal work orders of the current network about car platform is mainly a manual method. Along with the continuous increase of the number of service worksheets, the efficiency and the accuracy of the manual screening mode are low, and the actual requirements cannot be met.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a screening method, an apparatus, an electronic device, and a computer readable storage medium, which can screen work order data in a machine learning manner to determine whether the work order data to be processed is a safety work order, so as to alleviate the technical problems of low screening efficiency and poor accuracy when the emergency safety work order is screened in the prior art.
According to one aspect of the application, an electronic device is provided that may include one or more storage media and one or more processors in communication with the storage media. One or more storage media store machine-readable instructions executable by a processor. When the electronic device is in operation, the processor and the storage medium communicate over the bus, and the processor executes the machine-readable instructions to perform one or more of the following:
acquiring work order data in an online service process, and performing word segmentation on the work order data; each worksheet data comprises session data between a session service provider and a target object, wherein the target object comprises an order service provider and/or an order service requester; performing target processing on each candidate keyword in the work order data to obtain at least one new work order data; the target processing is to delete or replace alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work order data; classifying the work order data and the at least one new work order data by using a target classification model to obtain a classification processing result; the classification processing result is used for representing whether the work order data and the new work order data are safety class work orders or not; determining a target keyword from the candidate keywords based on the classification processing result; the target keywords are used to characterize that the worksheet data is not a security class worksheet.
In a preferred embodiment of the present application, classifying the work order data and the at least one new work order data using a target classification model includes: if the number of the candidate keywords exceeds the preset number, processing the at least one new work order data to obtain at least one data to be batched, wherein each data to be batched comprises a plurality of new work order data and one work order data; and classifying the new work order data and the work order data in each piece of data to be processed by using a target classification model to obtain a classification processing result.
In a preferred embodiment of the present application, processing the at least one new worksheet data to obtain at least one data to be processed includes: acquiring a candidate keyword set; the candidate keyword set comprises a plurality of keywords used for representing that the work order data are not safety work orders, and each keyword in the candidate keyword set comprises a weight value used for representing the importance degree of the keyword; and processing the at least one new work order data based on the candidate keyword set to obtain the at least one data to be processed.
In a preferred embodiment of the present application, processing the at least one new worksheet data based on the candidate keyword set, to obtain at least one data to be processed includes: determining a first target candidate keyword from the candidate keywords, wherein the first target candidate keyword is a keyword contained in the candidate keyword set; sorting the first target alternative keywords according to the weight values of the first target alternative keywords to obtain a first sorting result; determining a target sorting result based on the first sorting result and a second sorting result, wherein the first sorting result is positioned before the second sorting result, the second sorting result is a result obtained after sorting a second target alternative keyword, and the second target alternative keyword is other keywords except the first target alternative keyword in the alternative keywords; and classifying the new work order data corresponding to each keyword in the target sequencing result according to the sequencing order in the target sequencing result to obtain the at least one data to be processed.
In a preferred embodiment of the present application, the candidate keyword set is determined by the following method, which specifically includes: acquiring historical work order data, wherein the historical work order data is session data between a session service provider and a target object, and the target object comprises an order service provider and a service requester; and determining a candidate keyword set based on the historical worksheet data.
In a preferred embodiment of the present application, determining a candidate keyword set based on the historical worksheet data includes: performing word segmentation on each historical worksheet data to obtain word segmentation results, wherein the word segmentation results comprise a plurality of word segments; determining target word segmentation in the word segmentation results, wherein the target word segmentation is the word segmentation with the occurrence frequency higher than a preset threshold in the word segmentation results of each historical work order data; converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data; and determining the candidate keyword set by utilizing the target data.
In a preferred embodiment of the present application, determining the candidate keyword set using the target data includes: determining a training sample and a test sample based on the target data; training the initial classification prediction model by using the training sample to obtain a target classification prediction model; processing the test sample by using the target classification prediction model to obtain a weight value of each target word; and determining the candidate keyword set based on the weight value of each target word.
In a preferred embodiment of the present application, performing word segmentation on each of the historical worksheet data to obtain a word segmentation result includes: determining a preset word segmentation template; and performing word segmentation processing on each historical work order data according to the preset word segmentation template through a word segmentation device to obtain word segmentation results.
In a preferred embodiment of the present application, the method further comprises: constructing a training sample according to word segmentation results of each historical work order data and label information of each historical work order data, wherein the label information is used for representing whether the historical work order data is a safety work order; and training an initial model of the target classification model by using the training sample to obtain the target classification model.
In a preferred embodiment of the present application, the classifying the work order data and the at least one new work order data by using the objective classification model further includes: if the number of the candidate keywords does not exceed the preset number, the at least one new work order data and the work order data are used as data to be processed in a batch mode; and classifying the new work order data and the work order data in the data to be processed by using a target classification model to obtain a classification processing result.
In a preferred embodiment of the present application, performing the target processing on each candidate keyword in the work order data includes: and replacing the candidate keywords Ai in the work order data with preset data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, the number of the candidate keywords is I, and the preset data is useless vocabulary.
In a preferred embodiment of the present application, performing the target processing on each candidate keyword in the work order data includes: deleting the candidate keywords Ai in the work order data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, and the number of the candidate keywords is I.
In a preferred embodiment of the present application, the classification processing result includes a plurality of sub-processing results, where the plurality of sub-processing results includes a first sub-processing result and a second sub-processing result, and the classification processing result of the work order data is the first sub-processing result, and each new work order data corresponds to one second sub-processing result.
In a preferred embodiment of the present application, determining a target keyword among the candidate keywords based on the classification processing result includes: calculating a change value between each second sub-processing result and each first sub-processing result to obtain a plurality of change values; and determining the target keyword based on the plurality of variation values.
In a preferred embodiment of the present application, determining the target keyword based on the plurality of variation values includes: determining a first target change value in the plurality of change values, wherein the first target change value is the first N largest change values in the plurality of change values, and N is a positive integer greater than zero; determining new work order data corresponding to the first target change value; and determining the target keywords according to the replaced or deleted third target alternative keywords in the corresponding new work order data.
In a preferred embodiment of the present application, determining the target keyword according to the third target candidate keyword after replacement or deletion in the corresponding new work order data includes: if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set, and the fourth target candidate keywords comprise keywords recorded in the candidate keyword set, determining the first M keywords with the largest weight values in the fourth target candidate keywords; the candidate keyword set comprises a plurality of keywords used for representing whether the worksheet data is a safety worksheet or not, each keyword in the candidate keyword set comprises a weight value, the weight value is used for representing the importance degree of the keyword, and the fourth target candidate keyword is a keyword except the third target candidate keyword in the plurality of change values; and determining the keywords contained in the candidate keyword set in the first M keywords with the maximum weight values and the third target candidate keywords as target keywords.
In a preferred embodiment of the present application, the replacing or deleting the candidate keywords in the corresponding new work order data further includes: and if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set and the fourth target candidate keywords do not comprise keywords recorded in the candidate keyword set, determining the third target candidate keywords after being replaced or deleted in the corresponding new work order data as the target keywords.
According to another aspect of the present application, there is also provided a screening apparatus including: the system comprises an acquisition unit, a word segmentation unit and a word segmentation unit, wherein the acquisition unit is used for acquiring work order data in an online service process and performing word segmentation on the work order data; each worksheet data comprises session data between a session service provider and a target object, wherein the target object comprises an order service provider and/or an order service requester; the keyword processing unit is used for carrying out target processing on each candidate keyword in the work order data to obtain at least one new work order data; the target processing is to delete or replace alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work order data; the classification unit is used for classifying the work order data and the at least one new work order data by utilizing a target classification model to obtain a classification processing result; the classification processing result is used for representing whether the work order data and the new work order data are safety class work orders or not; a determining unit configured to determine a target keyword among the candidate keywords based on the classification processing result; the target keywords are used to characterize that the worksheet data is not a security class worksheet.
In a preferred embodiment of the present application, the classification unit includes: the processing module is used for processing the at least one new work order data to obtain at least one to-be-processed data if the number of the candidate keywords exceeds the preset number, wherein each to-be-processed data comprises a plurality of new work order data and one work order data; and the first classification module is used for classifying the new work order data and the work order data in each piece of data to be processed by utilizing a target classification model to obtain a classification processing result.
In a preferred embodiment of the present application, the processing module is configured to: acquiring a candidate keyword set; the candidate keyword set comprises a plurality of keywords used for representing that the work order data are not safety work orders, and each keyword in the candidate keyword set comprises a weight value used for representing the importance degree of the keyword; and processing the at least one new work order data based on the candidate keyword set to obtain the at least one data to be processed.
In a preferred embodiment of the present application, the processing module is further configured to: determining a first target candidate keyword from the candidate keywords, wherein the first target candidate keyword is a keyword contained in the candidate keyword set; sorting the first target alternative keywords according to the weight values of the first target alternative keywords to obtain a first sorting result; determining a target sorting result based on the first sorting result and a second sorting result, wherein the first sorting result is positioned before the second sorting result, the second sorting result is a result obtained after sorting a second target alternative keyword, and the second target alternative keyword is other keywords except the first target alternative keyword in the alternative keywords; and classifying the new work order data corresponding to each keyword in the target sequencing result according to the sequencing order in the target sequencing result to obtain the at least one data to be processed.
In a preferred embodiment of the present application, the apparatus further determines the candidate keyword set by specifically including: acquiring historical work order data, wherein the historical work order data is session data between a session service provider and a target object, and the target object comprises an order service provider and a service requester; and determining a candidate keyword set based on the historical worksheet data.
In a preferred embodiment of the application, the device is further adapted to: performing word segmentation on each historical worksheet data to obtain word segmentation results, wherein the word segmentation results comprise a plurality of word segments; determining target word segmentation in the word segmentation results, wherein the target word segmentation is the word segmentation with the occurrence frequency higher than a preset threshold in the word segmentation results of each historical work order data; converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data; and determining the candidate keyword set by utilizing the target data.
In a preferred embodiment of the application, the device is further adapted to: determining a training sample and a test sample based on the target data; training the initial classification prediction model by using the training sample to obtain a target classification prediction model; processing the test sample by using the target classification prediction model to obtain a weight value of each target word; and determining the candidate keyword set based on the weight value of each target word.
In a preferred embodiment of the application, the device is further adapted to: determining a preset word segmentation template; and performing word segmentation processing on each historical work order data according to the preset word segmentation template through a word segmentation device to obtain word segmentation results.
In a preferred embodiment of the application, the device is further adapted to: constructing a training sample according to word segmentation results of each historical work order data and label information of each historical work order data, wherein the label information is used for representing whether the historical work order data is a safety work order; and training an initial model of the target classification model by using the training sample to obtain the target classification model.
In a preferred embodiment of the present application, the classification unit further includes: the first determining module is used for taking the at least one new work order data and the work order data as one piece of data to be processed if the number of the candidate keywords does not exceed the preset number; and the second classification module is used for classifying the new work order data and the work order data in the data to be processed by utilizing a target classification model to obtain a classification processing result.
In a preferred embodiment of the present application, the keyword processing unit is configured to: and replacing the candidate keywords Ai in the work order data with preset data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, the number of the candidate keywords is I, and the preset data is useless vocabulary.
In a preferred embodiment of the present application, the keyword processing unit is further configured to: deleting the candidate keywords Ai in the work order data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, and the number of the candidate keywords is I.
In a preferred embodiment of the present application, the classification processing result includes a plurality of sub-processing results, where the plurality of sub-processing results includes a first sub-processing result and a second sub-processing result, and the classification processing result of the work order data is the first sub-processing result, and each new work order data corresponds to one second sub-processing result.
In a preferred embodiment of the present application, the determining unit includes: the calculating module is used for calculating the change value between each second sub-processing result and each first sub-processing result to obtain a plurality of change values; and the second determining module is used for determining the target keyword based on the plurality of change values.
In a preferred embodiment of the present application, the determining module is configured to: determining a first target change value in the plurality of change values, wherein the first target change value is the first N largest change values in the plurality of change values, and N is a positive integer greater than zero; determining new work order data corresponding to the first target change value; and determining the target keywords according to the replaced or deleted third target alternative keywords in the corresponding new work order data.
In a preferred embodiment of the present application, the determining module is further configured to: if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set, and the fourth target candidate keywords comprise keywords recorded in the candidate keyword set, determining the first M keywords with the largest weight values in the fourth target candidate keywords; the candidate keyword set comprises a plurality of keywords used for representing whether the worksheet data is a safety worksheet or not, each keyword in the candidate keyword set comprises a weight value, the weight value is used for representing the importance degree of the keyword, and the fourth target candidate keyword is a keyword except the third target candidate keyword in the plurality of change values; and determining the keywords contained in the candidate keyword set in the first M keywords with the maximum weight values and the third target candidate keywords as target keywords.
In a preferred embodiment of the present application, the determining module is further configured to: and if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set and the fourth target candidate keywords do not comprise keywords recorded in the candidate keyword set, determining the third target candidate keywords after being replaced or deleted in the corresponding new work order data as the target keywords.
According to another aspect of the present application, there is also provided an electronic apparatus including: the screening method comprises the steps of a screening method described by fir tree when the electronic device is running, the screening method comprises the steps of a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and the processor and the storage medium are communicated through the bus when the electronic device is running, and the processor executes the machine-readable instructions to execute the steps of the screening method described by fir tree when the machine-readable instructions are executed.
According to another aspect of the present application there is also provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the screening method described above.
The method comprises the steps of firstly obtaining work order data in an online service process, performing word segmentation processing on the work order data, and then sequentially replacing or deleting each alternative keyword in the work order data to obtain at least one new work order data; then, classifying the work order data and at least one new work order data by using a target classification model to obtain a classification result; finally, determining target keywords from the candidate keywords based on the classification processing result. According to the method, the device and the system, the worksheet data can be screened in a machine learning mode to determine whether the worksheet data are safety worksheets, so that the technical problems that screening efficiency is low and accuracy is poor when emergency safety worksheets are screened in the prior art are solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic structural diagram of an electronic device according to an embodiment of the present application;
FIG. 2 is a flow chart of a screening method according to an embodiment of the present application;
FIG. 3 is a flow chart of a first alternative screening method provided by an embodiment of the present application;
FIG. 4 is a flow chart of a second alternative screening method provided by an embodiment of the present application;
FIG. 5 is a flow chart of a third alternative screening method provided by an embodiment of the present application;
FIG. 6 is a flow chart of a fourth alternative screening method provided by an embodiment of the present application;
FIG. 7 is a flowchart of a fifth alternative screening method provided by an embodiment of the present application;
FIG. 8 is a flowchart of another screening method according to an embodiment of the present application;
Fig. 9 shows a schematic diagram of a screening apparatus according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the term "comprising" will be used in embodiments of the application to indicate the presence of the features stated hereafter, but not to exclude the addition of other features.
The terms "service" and "order" are used interchangeably herein to refer to a service request initiated by a passenger, a service requester, a driver, a service provider, or a vendor, etc., or any combination thereof. Accepting the "service" or "order" may be a passenger, a service requester, a driver, a service provider, a vendor, or the like, or any combination thereof. The service may be charged or free.
Example 1:
fig. 1 shows a schematic diagram of exemplary hardware and software components of an electronic device 100 that may implement the screening methods provided by the present application, according to some embodiments of the present application.
The electronic device 100 may be a general purpose computer or a special purpose computer, both of which may be used to implement the screening method of the present application. Although only one computer is shown, the functionality described herein may be implemented in a distributed fashion across multiple similar platforms for convenience to balance processing loads.
For example, electronic device 100 may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140.
The processor 102 may be a central processing unit (CPU, central Processing Unit) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.
The storage medium 104 may include one or more computer program products, which may include various forms of computer-readable storage media, such as magnetic disks, ROM, or RAM, or any combination thereof. By way of example, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application may be implemented in accordance with these program instructions. The electronic device 100 also includes an Input/Output (I/O) interface 150 between a computer and other Input/Output devices (e.g., keyboard, display screen).
The storage medium 140 stores machine-readable instructions executable by the processor 120, which when executed by the electronic device, cause the processor 120 to communicate with the storage medium 140 via a bus, and the processor executes the machine-readable instructions to perform the steps of the screening method described below. In addition, the storage medium may also be referred to as a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, performs the steps of the screening method described below.
In particular, when the electronic device is operating, the processor 120 and the storage medium 140 communicate over a bus, and the processor 120 executes machine readable instructions.
The acquiring unit in the processor 120 is configured to acquire worksheet data in an online service process, and perform word segmentation processing on the worksheet data; each of the worksheets data includes session data between a session service provider and a target object, the target object including an order service provider and/or an order service requester.
Then, a keyword processing unit in the processor 120 performs target processing on each candidate keyword in the work order data to obtain at least one new work order data; the target processing is to delete or replace the alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work order data.
Next, the classification unit in the processor 120 classifies the work order data and the at least one new work order data by using a target classification model to obtain a classification processing result; and the classification processing result is used for representing whether the work order data and the new work order data are safety work orders or not.
Finally, a determining unit in the processor 120 determines a target keyword among the candidate keywords based on the classification processing result; the target keywords are used to characterize that the worksheet data is not a security class worksheet.
For ease of illustration, only one processor is depicted in the electronic device 100. It should be noted, however, that the electronic device 100 of the present application may also include a plurality of processors, and thus steps performed by one processor described in the present application may also be performed jointly by a plurality of processors or separately. For example, if the processor of the electronic device 100 performs step a and step B, it should be understood that step a and step B may also be performed by two different processors together or performed separately in one processor. For example, the first processor performs step a, the second processor performs step B, or the first processor and the second processor together perform steps a and B.
Example 2:
see a flow chart of a screening method shown in fig. 2.
The screening method shown in fig. 2 is illustrated by taking application to a server side as an example, and includes the following steps:
step S202, acquiring work order data in an online service process, and performing word segmentation on the work order data; each of the worksheets data includes session data between a session service provider and a target object, the target object including an order service provider and/or an order service requester.
In the process of executing the service order, the service requester can communicate with the session service provider through a telephone service mode or an online service mode. The session communication content may be used as work order data for the service order.
In the process of executing the service order, the order service provider can also communicate with the session service provider through a telephone service mode or an online service mode. The session communication content may be used as work order data for the service order.
Step S204, performing target processing on each candidate keyword in the work order data to obtain at least one new work order data; the target processing is to delete or replace the alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work order data.
In the present embodiment, the data included in the work order data is session data (or dialogue information) between the session service provider and the target object.
The candidate keywords are keywords obtained after word segmentation processing is performed on the work order data, and the candidate keywords may include keywords capable of determining whether the work order data are safety type work orders.
In this embodiment, the candidate keywords in the worksheet data may be replaced with useless vocabulary, so as to obtain new worksheet data; alternatively, the candidate keywords in the worksheet data may be deleted to obtain new worksheet data.
One purpose of performing target processing on the candidate keywords is to determine, in the case where the work order data does not contain the candidate keywords, the probability that the work order data is determined to be an unsafe class work order.
Step S206, classifying the work order data and the at least one new work order data by using a target classification model to obtain a classification processing result; and the classification processing result is used for representing whether the work order data and the new work order data are safety work orders or not.
In this embodiment, after the new work order data and the work order data are obtained, the target classification model may be used to classify the new work order data and the work order data, so as to obtain a classification result.
The classification processing result corresponding to the new work order data is the classification processing result obtained after the candidate keywords are removed, and the classification processing result can determine the influence degree of the candidate keywords on the classification processing result.
Step S208, determining a target keyword from the candidate keywords based on the classification processing result; the target keywords are used to characterize that the worksheet data is not a security class worksheet.
In this embodiment, after the classification processing result of the new work order data and the work order data is obtained, the target keyword capable of representing the work order data as the non-security work order may be determined from the candidate keywords in combination with the classification processing result.
The method comprises the steps of firstly obtaining work order data in an online service process, performing word segmentation processing on the work order data, and then sequentially replacing or deleting each alternative keyword in the work order data to obtain at least one new work order data; then, classifying the work order data and at least one new work order data by using a target classification model to obtain a classification result; finally, determining target keywords from the candidate keywords based on the classification processing result. According to the method, the device and the system, the worksheet data can be screened in a machine learning mode to determine whether the worksheet data are safety worksheets, so that the technical problems that screening efficiency is low and accuracy is poor when emergency safety worksheets are screened in the prior art are solved.
As is clear from the above description, in the present embodiment, session data between a session service provider (i.e., customer service) and a target object can be recorded in real time during execution of a service order. And takes the session data as work order data for the service order. After the above-described work order data is obtained, the work order data may be stored in a data platform. The session data may be voice call information, or text communication information. The target objects include an order service provider (i.e., the driver of the net car platform) and/or a service requester (passenger).
After the execution instruction of the above steps S202 to S208 is acquired, the work order data is acquired from the data platform as work order data to be processed. Then, word segmentation processing is carried out on the work order data to obtain word segmentation results, wherein the word segmentation results comprise at least one word. The at least one word is an alternative keyword in the work order data.
Then, target processing can be performed on each candidate keyword in the work order data.
In the present embodiment, the target processing can be performed for each candidate keyword in the work order data in the following two ways.
In a first mode, as shown in fig. 3, step S204, performing target processing on each candidate keyword in the work order data includes the following steps:
step S301, replacing the candidate keywords Ai in the worksheet data with preset data to obtain new worksheet data corresponding to the candidate keywords Ai, where I sequentially takes 1 to I, and the number of the candidate keywords I, and the preset data is useless vocabulary.
In this embodiment, the useless vocabulary refers to a vocabulary that does not affect whether the work order data is a safety type work order. Alternatively, in this embodiment, the useless word may be selected as "OOV", and other useless words may be selected in addition, which is not limited in this embodiment.
For example, I candidate keywords are included in the work order data. Then the alternative keyword A1 in the work order data can be replaced by OOV, and a new work order data B1 is obtained after replacement; then, replacing the alternative keyword A2 in the work order data with OOV, and obtaining new work order data B2 after replacement; and so on, each candidate keyword in A1 to AI is replaced by "OOV" in the manner described above, and new work order data B1 to BI are obtained after the replacement.
It should be noted that, if the candidate keywords Ai in the work order data appear multiple times, each candidate keyword Ai in the work order data needs to be replaced with a useless vocabulary (e.g., OOV).
As is clear from the above description, in this embodiment, the replacement process is sequentially performed on each candidate keyword in the work order data, and after the candidate keyword is replaced, the influence of the candidate keyword on the classification processing result of the work order data can be determined, so as to determine whether the candidate keyword is a target keyword. The method for mining the target keywords by removing the candidate keywords to evaluate the change of the classification processing result of the worksheet data greatly improves the mining efficiency of the keywords, and can also ensure that the keywords really play a key role in the safety worksheet and reflect the essence of the safety worksheet.
In a second mode, as shown in fig. 4, step S204, performing target processing on each candidate keyword in the work order data includes the following steps:
step S401, deleting the candidate keywords Ai in the worksheet data to obtain new worksheet data corresponding to the candidate keywords Ai, where I sequentially takes 1 to I, and the number of the candidate keywords is I.
In this embodiment, the work order data includes I candidate keywords. Then the alternative keyword A1 in the work order data can be deleted, and a new work order data B1 is obtained after deletion; then, deleting the alternative keyword A2 in the work order data to obtain new work order data B2; and so on, deleting each candidate keyword in A1 to AI in the above-described manner to obtain new worksheet data B1 to BI after deletion.
It should be noted that, if the candidate keywords Ai in the work order data appear multiple times, each candidate keyword Ai in the work order data needs to be deleted.
As is clear from the above description, in the present embodiment, the deletion process is performed on each candidate keyword in the work order data in turn, and after the candidate keyword is deleted, the influence of the candidate keyword on the classification processing result of the work order data can be determined, thereby determining whether the candidate keyword is a target keyword. The method for mining the target keywords by removing the candidate keywords to evaluate the change of the classification processing result of the worksheet data greatly improves the mining efficiency of the keywords, and can also ensure that the keywords really play a key role in the safety worksheet and reflect the essence of the safety worksheet.
Further, in this embodiment, the target processing may be performed on each candidate keyword in the work order data in combination of the first and second modes, for example, a part of the candidate keywords may be subjected to the replacement processing, a part of the candidate keywords may be subjected to the deletion processing, and the like.
In the present invention, after at least one new work order data is obtained in the above-described manner, the target classification model is used to classify the work order data and the at least one new work order data to obtain a classification result.
In an alternative embodiment, as shown in fig. 5, step S206, classifying the worksheet data and the at least one new worksheet data using the objective classification model further includes:
step S501, if the number of the candidate keywords does not exceed the preset number, using the at least one new work order data and the work order data as one data to be processed;
and step S502, classifying the new work order data and the work order data in the data to be processed by using a target classification model to obtain a classification processing result.
In order to improve the evaluation speed and efficiency, the invention adopts a batch mode to process one piece of dialogue data at a time, wherein the first line of record in the batch is complete data (i.e. work order data), and the other lines of data are data after the candidate keywords are removed or replaced (i.e. at least one new work order data).
Alternatively, the size of the batch may be chosen to be 64, and up to 63 candidate keywords may be evaluated at a time. If the number of the alternative keywords outside the stop words is less than 63 in the work order data, at least one new work order data and work order data can be used as data to be processed in a batch, and then the target classification model is utilized to classify the new work order data and the work order data in the data to be processed in a batch, so that a classification processing result is obtained.
In an alternative embodiment, as shown in fig. 6, step S206, classifying the work order data and the at least one new work order data using the objective classification model includes the steps of:
step S601, if the number of the candidate keywords exceeds a preset number, processing the at least one new work order data to obtain at least one to-be-processed data, where each to-be-processed data includes a plurality of new work order data and one work order data;
and step S602, classifying the new work order data and the work order data in each piece of data to be processed by using a target classification model to obtain a classification processing result.
In order to improve the evaluation speed and efficiency, the invention adopts a batch mode to process one piece of dialogue data at a time, wherein the first line of record in the batch is complete data (i.e. work order data), and the other lines of data are data after the candidate keywords are removed or replaced (i.e. at least one new work order data).
Alternatively, the size of the batch may be chosen to be 64, and up to 63 candidate keywords may be evaluated at a time. In this embodiment, if more than 63 alternative keywords are removed from the work order data, batch processing may be performed on at least one new work order data. For example, at least one new work order data is batched to obtain at least one data to be batched. For example, each piece of data to be batched may include one piece of work order data and 63 pieces of new work order data.
In this embodiment, when executing step S601, at least one new work order data may be processed in combination with the candidate keyword set to obtain at least one data to be processed, which specifically includes:
firstly, acquiring a candidate keyword set; the candidate keyword set comprises a plurality of keywords used for representing that the work order data are not safety work orders, and each keyword in the candidate keyword set comprises a weight value used for representing the importance degree of the keyword;
and then, processing the at least one new work order data based on the candidate keyword set to obtain the at least one data to be processed.
The candidate keyword set in the invention is a pre-constructed word set, the candidate keyword set contains a large number of keywords, and the keywords are used for representing that the work order data is a non-security work order. And in the candidate keyword set, each keyword corresponds to a weight value, and the weight value is used for representing the importance degree of the keyword.
In this embodiment, the candidate keyword set may be determined by the following method, which specifically includes:
and acquiring historical work order data, wherein the historical work order data is session data between a session service provider and a target object, and the target object comprises an order service provider and a service requester. Specifically, in this embodiment, the already-annotated work order data, i.e., the historical work order data, may be pulled from the data platform. These historical worksheet data include An Quanlei worksheets and non-security class worksheets, and the labels thereof are classified into two categories. For example, the label of the security class work order is "1", and the label of the non-security class work order is "0". After the historical worksheet data is obtained, a candidate keyword set may be constructed based on the historical worksheet data.
When a candidate keyword set is constructed based on historical work order data, word segmentation processing can be performed on each historical work order data to obtain a word segmentation result, wherein the word segmentation result comprises a plurality of word segments. In this embodiment, a "jieba word segmentation device" may be used to perform word segmentation processing, so as to obtain a word segmentation result.
When word segmentation is carried out on each historical worksheet data, a preset word segmentation template can be determined first; and then, word segmentation is carried out on each historical work order data through a word segmentation device according to a preset word segmentation template, so that a word segmentation result is obtained.
The preset word segmentation template is added with new words under a certain network taxi scene, such as new words of service score, windward, customer service of XX network taxi platform and the like, and the keywords can be acquired more accurately by setting the new words through the preset word segmentation template.
After the word segmentation result is obtained, determining a target word in the word segmentation result, wherein the target word is a word with the occurrence frequency higher than a preset threshold value in the word segmentation result of each historical work order data. In this embodiment, after the word segmentation result is obtained, the occurrence frequency of each word segment in the word segmentation result may be counted, and then the first N word segments with the highest occurrence frequency may be selected as the target word segment. After the word segmentation result is obtained, the occurrence frequency of each word segment in the word segmentation result can be counted, and then the word segment with the occurrence frequency higher than a preset threshold value is used as a target word segment.
After obtaining the target word, converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data; and finally, determining the candidate keyword set by utilizing the target data.
For example, the vector group may be expressed as: [1,0,1, …,0], wherein each value in the vector group indicates whether its corresponding target segment appears in the historical worksheet data, e.g., "1" indicates appearance and "0" indicates absence.
Assuming that the number of target words is 10, taking the first historical work order data C1 as an example, it is assumed that the vector group corresponding to the first historical work order data C1 is expressed as: [1,0,1,1,0,1,0,1,0,0], wherein a first vector value "1" in the vector group indicates that the first historical work order data C1 has a first target word, a second vector value "0" in the vector group indicates that the first historical work order data C1 has no second target word, and so on, and other vector values in the vector group indicate that the first historical work order data C1 has no (or has) target word corresponding to it, which will not be described one by one.
In this embodiment, the number of target words is not necessarily 10, alternatively, the number of target words may be 5 ten thousand, which may be specifically set according to actual needs, and this embodiment is not specifically limited thereto.
In this embodiment, after the above-mentioned one-hot type target data is obtained, the candidate keyword set may be determined using the one-hot type target data.
Specifically, when the candidate keyword set is determined using the target data, first, a training sample and a test sample are determined based on the target data. In this embodiment, one-hot form of target data may be divided into training samples and test samples.
And then training the initial classification prediction model by using the training sample to obtain a target classification prediction model. And then, processing the test sample by using the target classification prediction model to obtain the weight value of each target word.
In this embodiment, the target classification prediction model may be selected as a logistic regression model (Logistic Regression, abbreviated as LR). In addition, other models may be selected, and this embodiment is not particularly limited.
And finally, determining the candidate keyword set based on the weight value of each target word. The weight value predicted by the target classification prediction model can be used as the importance degree of the target word segmentation.
In this embodiment, after the candidate keyword set is obtained in the above-described manner, at least one new work order data may be processed based on the candidate keyword set to obtain at least one data to be processed.
In this embodiment, if the number of candidate keywords is large, the keywords included in the candidate keyword set among the candidate keywords may be preferentially processed. Because the keywords included in the candidate keyword set are more likely to be target keywords. Therefore, by adopting the processing mode, the generation effect of the target keywords can be further improved, the accuracy of the recall safety work order is improved, the manpower resources are saved, and the working efficiency is improved.
In an alternative embodiment, as shown in fig. 7, the processing the at least one new worksheet data based on the candidate keyword set to obtain at least one data to be processed includes the following steps:
step S701, determining a first target candidate keyword among the candidate keywords, where the first target candidate keyword is a keyword included in the candidate keyword set.
In this embodiment, the candidate keywords may be compared with the keywords in the candidate keyword set, so that the keywords included in the candidate keyword set are selected from among the candidate keywords, which is referred to as a first target candidate keyword.
Step S702, sorting the first target candidate keywords according to the weight values of the first target candidate keywords, to obtain a first sorting result.
In this embodiment, as can be seen from the above description, the keywords in the candidate keyword set all include the corresponding weight values. At this time, the weight value of the same keyword in the candidate keyword set as the first target candidate keyword may be used as the weight value of the first target candidate keyword.
And then, sorting the first target candidate keywords according to the weight values of the first target candidate keywords to obtain a first sorting result. For example, ordering is from high to low, or ordering is from low to high.
Step S703, determining a target ranking result based on the first ranking result and the second ranking result, where the first ranking result is located before the second ranking result, and the second ranking result is a result obtained after ranking a second target candidate keyword, and the second target candidate keyword is another keyword in the candidate keywords except the first target candidate keyword.
After the first ranking result is obtained, the other candidate keywords (namely, the second target candidate keyword) except the first target candidate keyword in the candidate keywords are randomly ranked, and then a second ranking result is obtained.
Then, the first sorting result and the second sorting result can be connected to obtain a target sorting result. Preferably, the first sorting result may be located before the second sorting result, and in addition, the first sorting result may be located after the second sorting result, which is not specifically limited in this embodiment.
Step S704, classifying the new work order data corresponding to each keyword in the target sequencing result according to the sequencing order in the target sequencing result, to obtain the at least one data to be processed.
For example, 63 new work order data are allowed to be included in one batch data. Then the plurality of keywords are grouped in order of order in the target ranking result, e.g., the 1 st through 63 st keywords are grouped, the 64 th through 126 th keywords are grouped, and so on. Then, the new work order data corresponding to the 1 st to 63 st keywords are used as data to be processed and the work order data are used as data to be processed. Then, the new work order data corresponding to the 64 th to 126 th keywords are used as data to be processed and the work order data are used as another data to be processed. Similarly, the processing modes are adopted for the new work order data corresponding to other keywords, and are not described one by one.
As can be seen from the above description, in this embodiment, the batch processing manner is introduced to process the work order data and the new work order data, so that the target keyword is determined, and the efficiency of acquiring the target keyword can be improved.
In this embodiment, after at least one piece of data to be processed is obtained in the above-described manner, classification processing may be performed on the new work order data and the work order data in each piece of data to be processed by using the target classification model, so as to obtain a classification processing result.
Alternatively, in the present embodiment, the selected object classification model may be a HAN (Hierarchical Attention Network) model. Before classifying new work order data and work order data in the batch processing data by utilizing the target classification model, training an initial model of the target classification model, and obtaining the target classification model after training, wherein the training process is described as follows:
constructing a training sample according to word segmentation results of each historical work order data and label information of each historical work order data, wherein the label information is used for representing whether the historical work order data is a safety work order; and then, training an initial model of the target classification model by using the training sample to obtain the target classification model.
As is clear from the above description, in the present embodiment, when a candidate keyword set is constructed, historical work order data is acquired from a data platform. After word segmentation is carried out on the historical worksheet data, an initial model of the target classification model can be trained by using word segmentation results and label information, and the target classification model is obtained.
Preferably, in this embodiment, the target classification model is selected as the HAN model, and the HAN model is used as a dialogue classification training model, which is a top-down text representation model based on vectors, and has good performance in classification tasks.
After the classification processing is performed on the work order data and at least one new work order data in the manner described above to obtain the classification processing result, the target keyword may be determined among the candidate keywords based on the classification processing result.
In this embodiment, the classification processing result includes a plurality of sub-processing results, where the plurality of sub-processing results may be divided into a first sub-processing result and a second sub-processing result, where the classification processing result of the work order data is the first sub-processing result, and each new work order data corresponds to one second sub-processing result.
That is, the result of the classification processing of the work order data by the target classification model is the first sub-processing result; the result of the classification processing of each new work order data by the target classification model is a second sub-processing result.
It should be noted that, because each piece of data to be processed includes work order data, the target classification model obtains a first sub-processing result when classifying the work order data in each piece of data to be processed. And the obtained first sub-processing results may be the same or different, but the difference between the first sub-processing results is within a preset requirement range.
Based on this, step S208 of determining a target keyword among the candidate keywords based on the classification processing result includes the steps of:
step S2081, calculating a change value between each second sub-processing result and each first sub-processing result to obtain a plurality of change values;
and step S2082, determining the target keyword based on the plurality of variation values.
In this embodiment, after the classification processing result of each piece of data to be processed is obtained, a change value between each second sub-processing result and each first sub-processing result in the classification processing result may be calculated, so as to obtain a plurality of change values.
After obtaining the plurality of change values, a first target change value may be determined from the plurality of change values, where the first target change value is a first N largest change value of the plurality of change values, and N is a positive integer greater than zero. And then, determining new work order data corresponding to the first target change value. And determining alternative keywords (marked as third target alternative keywords) which are replaced or deleted in the new work order data corresponding to the first target change value. And finally, determining target keywords according to the third target candidate keywords after replacement or deletion in the corresponding new work order data.
According to the method, the device and the system, the worksheet data can be screened in a machine learning mode to determine whether the worksheet data are safety worksheets, so that the technical problems that screening efficiency is low and accuracy is poor when emergency safety worksheets are screened in the prior art are solved.
Optionally, in this embodiment, determining the target keyword according to the third target candidate keyword after replacement or deletion in the corresponding new work order data includes:
firstly, if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set, and the fourth target candidate keywords comprise keywords recorded in the candidate keyword set, determining the keywords with the maximum first M weight values in the fourth target candidate keywords; the candidate keyword set comprises a plurality of keywords used for representing whether the worksheet data is a safety worksheet or not, each keyword in the candidate keyword set comprises a weight value, the weight value is used for representing the importance degree of the keyword, and the fourth target candidate keyword is a keyword except the third target candidate keyword in the plurality of change values.
Specifically, after the third target candidate keyword is obtained, if keywords not recorded in the candidate keyword set are included in the third target candidate keyword, it is necessary to replace these keywords with keywords in the candidate keyword set.
At this time, in this embodiment, new work order data corresponding to a plurality of change values may be determined, and further, alternative keywords after replacement or deletion in the new work order data may be determined. Then, if it is determined that, in addition to the third target candidate keyword, other keywords in the candidate keyword set are included, then it is possible to determine, among the keywords, the keywords having the maximum M weight values, where M is the number of keywords that are not recorded in the candidate keyword set and are included in the third target candidate keyword. And finally, determining the keywords contained in the candidate keyword set in the first M keywords with the maximum weight values and the third target candidate keywords as target keywords.
In this embodiment, if the third target candidate keyword includes M keywords not recorded in the candidate keyword set and the fourth target candidate keyword does not include keywords recorded in the candidate keyword set, the third target candidate keyword after being replaced or deleted in the corresponding new work order data is determined as the target keyword.
That is, if the keywords corresponding to the plurality of variation values do not include keywords recorded in the candidate keyword set, at this time, the third target candidate keyword may be determined as the target keyword.
Example 3:
the screening method will be described below with reference to fig. 8.
As shown in fig. 8, in the present embodiment, first, it is necessary to train an initial model of the target classification model and construct a candidate keyword set. As shown in fig. 8, the process is described as follows:
first, the already marked work order data (i.e., the historical work order data described above) is pulled from the database of the data platform, and these work orders include An Quanlei work orders and non-safety class work orders, the labels of which are two categories. Then, these work order data are subjected to word segmentation processing. In the embodiment, a jieba word segmentation device is adopted to segment the work order data, so that a word segmentation result is obtained. In the word segmentation process, new words under a certain network taxi scene can be added as word lists, such as 'service division', 'windward', 'certain customer service', and the like, so that keywords can be acquired more accurately.
Thereafter, a candidate set of keywords is generated. Specifically, the occurrence frequency of each word segment can be counted in the word segment result, and then 5 ten thousand words with the highest occurrence frequency are selected from the word segment result according to the occurrence frequency, wherein the words basically cover 99% of the words. After obtaining the target word, converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data; and finally, determining the candidate keyword set by utilizing the target data.
For example, the vector group may be expressed as: [1,0,1, …,0], wherein each value in the vector group indicates whether its corresponding target segment appears in the historical worksheet data, e.g., "1" indicates appearance and "0" indicates absence.
Then, a Logistic Regression (LR) model is used for training to obtain a target classification prediction model. And then, processing the test sample by using the target classification prediction model to obtain weight values of all target words, wherein the size of the weight values can be regarded as the importance degree of the words.
Thereafter, an initial model of the object classification model is trained. When training the initial model, training the initial model by using the word segmentation result and the label information of each work order data. Wherein the selected object classification model may be a HAN (Hierarchical Attention Network) model.
After the candidate keyword set is constructed and the target classification model is trained, the steps described in any of the foregoing embodiments 2 may be performed by using the target classification model, which will not be described in detail herein.
It should be noted that, in this embodiment, in order to improve the evaluation speed and improve the efficiency, the present invention processes one piece of dialogue data at a time by adopting a batch manner, the first line of record in the batch is complete data, the other lines of data are all data after removing or replacing potential keywords, the size of the batch is 64, and 63 potential keywords can be evaluated at most at a time, if the dialogue record is too long, the first 63 words in the candidate keyword library are required to be selected as potential keywords, and the first 63 words in the candidate keyword library are required to be used as potential keywords, and if the number of the removed stop words in the dialogue is less than 63, the potential keyword library is not required to be used as the yellow marker 2 in fig. 8.
According to the method, the device and the system, the worksheet data can be screened in a machine learning mode to determine whether the worksheet data are safety worksheets, so that the technical problems that screening efficiency is low and accuracy is poor when emergency safety worksheets are screened in the prior art are solved.
Example 4:
fig. 9 is a block diagram illustrating a screening apparatus implementing functions corresponding to the steps performed by the above-described method in accordance with some embodiments of the present application. The apparatus may be understood as a server or a processor of a server, or may be understood as a component, which is independent from the server or the processor and performs the functions of the present application under the control of the server, where the screening apparatus may include an acquisition unit 910, a keyword processing unit 920, a classification unit 930, and a determination unit 940.
An acquiring unit 910, configured to acquire work order data in an online service process, and perform word segmentation processing on the work order data; each worksheet data comprises session data between a session service provider and a target object, wherein the target object comprises an order service provider and/or an order service requester;
a keyword processing unit 920, configured to perform target processing on each candidate keyword in the work order data, so as to obtain at least one new work order data; the target processing is to delete or replace alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work order data;
A classification unit 930, configured to perform classification processing on the work order data and the at least one new work order data by using a target classification model, so as to obtain a classification processing result; the classification processing result is used for representing whether the work order data and the new work order data are safety class work orders or not;
a determining unit 940 configured to determine a target keyword among the candidate keywords based on the classification processing result; the target keywords are used to characterize that the worksheet data is not a security class worksheet.
The method comprises the steps of firstly obtaining work order data in an online service process, performing word segmentation processing on the work order data, and then sequentially replacing or deleting each alternative keyword in the work order data to obtain at least one new work order data; then, classifying the work order data and at least one new work order data by using a target classification model to obtain a classification result; finally, determining target keywords from the candidate keywords based on the classification processing result. According to the method, the device and the system, the worksheet data can be screened in a machine learning mode to determine whether the worksheet data are safety worksheets, so that the technical problems that screening efficiency is low and accuracy is poor when emergency safety worksheets are screened in the prior art are solved.
Optionally, the classification unit includes: the processing module is used for processing the at least one new work order data to obtain at least one to-be-processed data if the number of the candidate keywords exceeds the preset number, wherein each to-be-processed data comprises a plurality of new work order data and one work order data; and the first classification module is used for classifying the new work order data and the work order data in each piece of data to be processed by utilizing a target classification model to obtain a classification processing result.
Optionally, the processing module is configured to: acquiring a candidate keyword set; the candidate keyword set comprises a plurality of keywords used for representing that the work order data are not safety work orders, and each keyword in the candidate keyword set comprises a weight value used for representing the importance degree of the keyword; and processing the at least one new work order data based on the candidate keyword set to obtain the at least one data to be processed.
Optionally, the processing module is further configured to: determining a first target candidate keyword from the candidate keywords, wherein the first target candidate keyword is a keyword contained in the candidate keyword set; sorting the first target alternative keywords according to the weight values of the first target alternative keywords to obtain a first sorting result; determining a target sorting result based on the first sorting result and a second sorting result, wherein the first sorting result is positioned before the second sorting result, the second sorting result is a result obtained after sorting a second target alternative keyword, and the second target alternative keyword is other keywords except the first target alternative keyword in the alternative keywords; and classifying the new work order data corresponding to each keyword in the target sequencing result according to the sequencing order in the target sequencing result to obtain the at least one data to be processed.
Optionally, the apparatus further determines the candidate keyword set by specifically including: acquiring historical work order data, wherein the historical work order data is session data between a session service provider and a target object, and the target object comprises an order service provider and a service requester; and determining a candidate keyword set based on the historical worksheet data.
Optionally, the device is further configured to: performing word segmentation on each historical worksheet data to obtain word segmentation results, wherein the word segmentation results comprise a plurality of word segments; determining target word segmentation in the word segmentation results, wherein the target word segmentation is the word segmentation with the occurrence frequency higher than a preset threshold in the word segmentation results of each historical work order data; converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data; and determining the candidate keyword set by utilizing the target data.
Optionally, the device is further configured to: determining a training sample and a test sample based on the target data; training the initial classification prediction model by using the training sample to obtain a target classification prediction model; processing the test sample by using the target classification prediction model to obtain a weight value of each target word; and determining the candidate keyword set based on the weight value of each target word.
Optionally, the device is further configured to: determining a preset word segmentation template; and performing word segmentation processing on each historical work order data according to the preset word segmentation template through a word segmentation device to obtain word segmentation results.
Optionally, the device is further configured to: constructing a training sample according to word segmentation results of each historical work order data and label information of each historical work order data, wherein the label information is used for representing whether the historical work order data is a safety work order; and training an initial model of the target classification model by using the training sample to obtain the target classification model.
Optionally, the classification unit further comprises: the first determining module is used for taking the at least one new work order data and the work order data as one piece of data to be processed if the number of the candidate keywords does not exceed the preset number; and the second classification module is used for classifying the new work order data and the work order data in the data to be processed by utilizing a target classification model to obtain a classification processing result.
Optionally, the keyword processing unit is configured to: and replacing the candidate keywords Ai in the work order data with preset data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, the number of the candidate keywords is I, and the preset data is useless vocabulary.
Optionally, the keyword processing unit is further configured to: deleting the candidate keywords Ai in the work order data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, and the number of the candidate keywords is I.
Optionally, the classification processing result includes a plurality of sub-processing results, where the plurality of sub-processing results includes a first sub-processing result and a second sub-processing result, and the classification processing result of the work order data is the first sub-processing result, and each new work order data corresponds to one second sub-processing result.
Optionally, the determining unit includes: the calculating module is used for calculating the change value between each second sub-processing result and each first sub-processing result to obtain a plurality of change values; and the second determining module is used for determining the target keyword based on the plurality of change values.
Optionally, the determining module is configured to: determining a first target change value in the plurality of change values, wherein the first target change value is the first N largest change values in the plurality of change values, and N is a positive integer greater than zero; determining new work order data corresponding to the first target change value; and determining the target keywords according to the replaced or deleted third target alternative keywords in the corresponding new work order data.
Optionally, the determining module is further configured to: if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set, and the fourth target candidate keywords comprise keywords recorded in the candidate keyword set, determining the first M keywords with the largest weight values in the fourth target candidate keywords; the candidate keyword set comprises a plurality of keywords used for representing whether the worksheet data is a safety worksheet or not, each keyword in the candidate keyword set comprises a weight value, the weight value is used for representing the importance degree of the keyword, and the fourth target candidate keyword is a keyword except the third target candidate keyword in the plurality of change values; and determining the keywords contained in the candidate keyword set in the first M keywords with the maximum weight values and the third target candidate keywords as target keywords.
Optionally, the determining module is further configured to: and if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set and the fourth target candidate keywords do not comprise keywords recorded in the candidate keyword set, determining the third target candidate keywords after being replaced or deleted in the corresponding new work order data as the target keywords.
The modules may be connected or communicate with each other via wired or wireless connections. The wired connection may include a metal cable, optical cable, hybrid cable, or the like, or any combination thereof. The wireless connection may include a connection through a LAN, WAN, bluetooth, zigBee, or NFC, or any combination thereof. Two or more modules may be combined into a single module, and any one module may be divided into two or more units.
The application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the screening method of any of the above method embodiments.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the method embodiments, and are not repeated in the present disclosure. In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, and for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (34)
1. A method of screening comprising:
acquiring work order data in an online service process, and performing word segmentation on the work order data; each worksheet data comprises session data between a session service provider and a target object, wherein the target object comprises an order service provider and/or an order service requester;
performing target processing on each candidate keyword in the work order data to obtain at least one new work order data; the target processing is to delete the alternative keywords or replace the alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work data;
classifying the work order data and the at least one new work order data by using a target classification model to obtain classification processing results respectively corresponding to the work order data and the new work order data; the classification processing result is used for representing whether the work order data and the new work order data are safety class work orders or not;
Determining target keywords in the candidate keywords based on classification processing results respectively corresponding to the work order data and the new work order data; the target keywords are used for representing that the work order data is not a security class work order; the classification processing results respectively corresponding to the work order data and the new work order data are used for reflecting the influence degree of the alternative keywords on the classification processing results of the work order data;
the classifying processing of the work order data and the at least one new work order data by using the target classification model comprises the following steps:
if the number of the candidate keywords exceeds the preset number, processing the at least one new work order data to obtain at least one data to be batched, wherein each data to be batched comprises a plurality of new work order data and one work order data;
and classifying the new work order data and the work order data in each piece of data to be processed by using a target classification model to obtain a classification processing result.
2. The method of claim 1, wherein processing the at least one new work order data to obtain at least one data to be processed comprises:
Acquiring a candidate keyword set; the candidate keyword set comprises a plurality of keywords used for representing that the work order data are not safety work orders, and each keyword in the candidate keyword set comprises a weight value used for representing the importance degree of the keyword;
and processing the at least one new work order data based on the candidate keyword set to obtain the at least one data to be processed.
3. The method of claim 2, wherein processing the at least one new worksheet data based on the candidate keyword set to obtain at least one data to be processed comprises:
determining a first target candidate keyword from the candidate keywords, wherein the first target candidate keyword is a keyword contained in the candidate keyword set;
sorting the first target alternative keywords according to the weight values of the first target alternative keywords to obtain a first sorting result;
determining a target sorting result based on the first sorting result and a second sorting result, wherein the first sorting result is positioned before the second sorting result, the second sorting result is a result obtained after sorting a second target alternative keyword, and the second target alternative keyword is other keywords except the first target alternative keyword in the alternative keywords;
And classifying the new work order data corresponding to each keyword in the target sequencing result according to the sequencing order in the target sequencing result to obtain the at least one data to be processed.
4. The method according to claim 2, characterized in that the candidate keyword set is determined by, in particular,:
acquiring historical work order data, wherein the historical work order data is session data between a session service provider and a target object, and the target object comprises an order service provider and a service requester;
and determining a candidate keyword set based on the historical worksheet data.
5. The method of claim 4, wherein determining a set of candidate keywords based on the historical worksheet data comprises:
performing word segmentation on each historical worksheet data to obtain word segmentation results, wherein the word segmentation results comprise a plurality of word segments;
determining target word segmentation in the word segmentation results, wherein the target word segmentation is the word segmentation with the occurrence frequency higher than a preset threshold in the word segmentation results of each historical work order data;
converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data;
And determining the candidate keyword set by utilizing the target data.
6. The method of claim 5, wherein determining the set of candidate keywords using the target data comprises:
determining a training sample and a test sample based on the target data;
training the initial classification prediction model by using the training sample to obtain a target classification prediction model;
processing the test sample by using the target classification prediction model to obtain a weight value of each target word;
and determining the candidate keyword set based on the weight value of each target word.
7. The method of claim 5, wherein performing word segmentation on each of the historical worksheets to obtain word segmentation results comprises:
determining a preset word segmentation template;
and performing word segmentation processing on each historical work order data according to the preset word segmentation template through a word segmentation device to obtain word segmentation results.
8. The method of claim 5, wherein the method further comprises:
constructing a training sample according to word segmentation results of each historical work order data and label information of each historical work order data, wherein the label information is used for representing whether the historical work order data is a safety work order;
And training an initial model of the target classification model by using the training sample to obtain the target classification model.
9. The method of claim 1, wherein classifying the work order data and the at least one new work order data using a target classification model further comprises:
if the number of the candidate keywords does not exceed the preset number, the at least one new work order data and the work order data are used as data to be processed in a batch mode;
and classifying the new work order data and the work order data in the data to be processed by using a target classification model to obtain a classification processing result.
10. The method of claim 1, wherein targeting each alternative keyword in the work order data comprises:
and replacing the candidate keywords Ai in the work order data with preset data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, the number of the candidate keywords is I, and the preset data is useless vocabulary.
11. The method of claim 1, wherein targeting each alternative keyword in the work order data comprises:
Deleting the candidate keywords Ai in the work order data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, and the number of the candidate keywords is I.
12. The method of claim 1, wherein the classification result comprises a plurality of sub-process results, the plurality of sub-process results comprising a first sub-process result and a second sub-process result, wherein the classification result of the work order data is the first sub-process result, and each new work order data corresponds to a second sub-process result.
13. The method of claim 12, wherein determining the target keyword among the candidate keywords based on classification processing results respectively corresponding to the work order data and the new work order data comprises:
calculating a change value between each second sub-processing result and each first sub-processing result to obtain a plurality of change values;
and determining the target keyword based on the plurality of variation values.
14. The method of claim 13, wherein determining the target keyword based on the plurality of variance values comprises:
determining a first target change value in the plurality of change values, wherein the first target change value is the first N largest change values in the plurality of change values, and N is a positive integer greater than zero;
Determining new work order data corresponding to the first target change value;
and determining the target keywords according to the replaced or deleted third target alternative keywords in the corresponding new work order data.
15. The method of claim 14, wherein determining the target keyword from a third target candidate keyword after replacement or deletion in the corresponding new work order data comprises:
if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set, and the fourth target candidate keywords comprise keywords recorded in the candidate keyword set, determining the first M keywords with the largest weight values in the fourth target candidate keywords; the candidate keyword set comprises a plurality of keywords used for representing whether the worksheet data is a safety worksheet or not, each keyword in the candidate keyword set comprises a weight value, the weight value is used for representing the importance degree of the keyword, and the fourth target candidate keyword is a keyword except the third target candidate keyword in the plurality of change values;
and determining the keywords contained in the candidate keyword set in the first M keywords with the maximum weight values and the third target candidate keywords as target keywords.
16. The method of claim 15, wherein replacing or deleting the candidate keywords in the corresponding new work order data as the target keywords further comprises:
and if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set and the fourth target candidate keywords do not comprise keywords recorded in the candidate keyword set, determining the third target candidate keywords after being replaced or deleted in the corresponding new work order data as the target keywords.
17. A screening apparatus, comprising:
the system comprises an acquisition unit, a word segmentation unit and a word segmentation unit, wherein the acquisition unit is used for acquiring work order data in an online service process and performing word segmentation on the work order data; each worksheet data comprises session data between a session service provider and a target object, wherein the target object comprises an order service provider and/or an order service requester;
the keyword processing unit is used for carrying out target processing on each candidate keyword in the work order data to obtain at least one new work order data; the target processing is to delete the alternative keywords or replace the alternative keywords with useless words, wherein the alternative keywords are words obtained after word segmentation processing is carried out on the work data;
The classification unit is used for classifying the work order data and the at least one new work order data by utilizing a target classification model to obtain classification processing results respectively corresponding to the work order data and the new work order data; the classification processing result is used for representing whether the work order data and the new work order data are safety class work orders or not;
a determining unit, configured to determine a target keyword from the candidate keywords based on classification processing results respectively corresponding to the worksheet data and the new worksheet data; the target keywords are used for representing that the work order data is not a security class work order; the classification processing results respectively corresponding to the work order data and the new work order data are used for reflecting the influence degree of the alternative keywords on the classification processing results of the work order data;
the classification unit includes:
the processing module is used for processing the at least one new work order data to obtain at least one to-be-processed data if the number of the candidate keywords exceeds the preset number, wherein each to-be-processed data comprises a plurality of new work order data and one work order data;
and the first classification module is used for classifying the new work order data and the work order data in each piece of data to be processed by utilizing a target classification model to obtain a classification processing result.
18. The apparatus of claim 17, wherein the processing module is configured to:
acquiring a candidate keyword set; the candidate keyword set comprises a plurality of keywords used for representing that the work order data are not safety work orders, and each keyword in the candidate keyword set comprises a weight value used for representing the importance degree of the keyword;
and processing the at least one new work order data based on the candidate keyword set to obtain the at least one data to be processed.
19. The apparatus of claim 18, wherein the processing module is further configured to:
determining a first target candidate keyword from the candidate keywords, wherein the first target candidate keyword is a keyword contained in the candidate keyword set;
sorting the first target alternative keywords according to the weight values of the first target alternative keywords to obtain a first sorting result;
determining a target sorting result based on the first sorting result and a second sorting result, wherein the first sorting result is positioned before the second sorting result, the second sorting result is a result obtained after sorting a second target alternative keyword, and the second target alternative keyword is other keywords except the first target alternative keyword in the alternative keywords;
And classifying the new work order data corresponding to each keyword in the target sequencing result according to the sequencing order in the target sequencing result to obtain the at least one data to be processed.
20. The apparatus of claim 18, wherein the apparatus further determines the candidate keyword set by:
acquiring historical work order data, wherein the historical work order data is session data between a session service provider and a target object, and the target object comprises an order service provider and a service requester;
and determining a candidate keyword set based on the historical worksheet data.
21. The apparatus of claim 20, wherein the apparatus is further configured to:
performing word segmentation on each historical worksheet data to obtain word segmentation results, wherein the word segmentation results comprise a plurality of word segments;
determining target word segmentation in the word segmentation results, wherein the target word segmentation is the word segmentation with the occurrence frequency higher than a preset threshold in the word segmentation results of each historical work order data;
converting the target word into one-hot target data, wherein the target data comprises a plurality of vector groups, and a vector value in each vector group represents whether the target word appears in each historical worksheet data;
And determining the candidate keyword set by utilizing the target data.
22. The apparatus of claim 21, wherein the apparatus is further configured to:
determining a training sample and a test sample based on the target data;
training the initial classification prediction model by using the training sample to obtain a target classification prediction model;
processing the test sample by using the target classification prediction model to obtain a weight value of each target word;
and determining the candidate keyword set based on the weight value of each target word.
23. The apparatus of claim 21, wherein the apparatus is further configured to:
determining a preset word segmentation template;
and performing word segmentation processing on each historical work order data according to the preset word segmentation template through a word segmentation device to obtain word segmentation results.
24. The apparatus of claim 21, wherein the apparatus is further configured to:
constructing a training sample according to word segmentation results of each historical work order data and label information of each historical work order data, wherein the label information is used for representing whether the historical work order data is a safety work order;
and training an initial model of the target classification model by using the training sample to obtain the target classification model.
25. The apparatus of claim 17, wherein the classification unit further comprises:
the first determining module is used for taking the at least one new work order data and the work order data as one piece of data to be processed if the number of the candidate keywords does not exceed the preset number;
and the second classification module is used for classifying the new work order data and the work order data in the data to be processed by utilizing a target classification model to obtain a classification processing result.
26. The apparatus of claim 17, wherein the keyword processing unit is configured to:
and replacing the candidate keywords Ai in the work order data with preset data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, the number of the candidate keywords is I, and the preset data is useless vocabulary.
27. The apparatus of claim 17, wherein the keyword processing unit is further configured to:
deleting the candidate keywords Ai in the work order data to obtain new work order data corresponding to the candidate keywords Ai, wherein I sequentially takes 1 to I, and the number of the candidate keywords is I.
28. The apparatus of claim 17, wherein the classification result comprises a plurality of sub-process results including a first sub-process result and a second sub-process result, wherein the classification result of the work order data is the first sub-process result, and each new work order data corresponds to a second sub-process result.
29. The apparatus according to claim 28, wherein the determining unit comprises:
the calculating module is used for calculating the change value between each second sub-processing result and each first sub-processing result to obtain a plurality of change values;
and the second determining module is used for determining the target keyword based on the plurality of change values.
30. The apparatus of claim 29, wherein the means for determining is configured to:
determining a first target change value in the plurality of change values, wherein the first target change value is the first N largest change values in the plurality of change values, and N is a positive integer greater than zero;
determining new work order data corresponding to the first target change value;
and determining the target keywords according to the replaced or deleted third target alternative keywords in the corresponding new work order data.
31. The apparatus of claim 30, wherein the means for determining is further configured to:
if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set, and the fourth target candidate keywords comprise keywords recorded in the candidate keyword set, determining the first M keywords with the largest weight values in the fourth target candidate keywords; the candidate keyword set comprises a plurality of keywords used for representing whether the worksheet data is a safety worksheet or not, each keyword in the candidate keyword set comprises a weight value, the weight value is used for representing the importance degree of the keyword, and the fourth target candidate keyword is a keyword except the third target candidate keyword in the plurality of change values;
and determining the keywords contained in the candidate keyword set in the first M keywords with the maximum weight values and the third target candidate keywords as target keywords.
32. The apparatus of claim 31, wherein the means for determining is further configured to:
and if the third target candidate keywords comprise M keywords which are not recorded in the candidate keyword set and the fourth target candidate keywords do not comprise keywords recorded in the candidate keyword set, determining the third target candidate keywords after being replaced or deleted in the corresponding new work order data as the target keywords.
33. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating over the bus when the electronic device is running, the processor executing the machine-readable instructions to perform the steps of the screening method of any one of claims 1 to 16 when executed.
34. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the screening method according to any of claims 1 to 16.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910139175.3A CN111611353B (en) | 2019-02-25 | 2019-02-25 | Screening method, screening device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910139175.3A CN111611353B (en) | 2019-02-25 | 2019-02-25 | Screening method, screening device, electronic equipment and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111611353A CN111611353A (en) | 2020-09-01 |
CN111611353B true CN111611353B (en) | 2023-08-18 |
Family
ID=72199950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910139175.3A Active CN111611353B (en) | 2019-02-25 | 2019-02-25 | Screening method, screening device, electronic equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111611353B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112559896B (en) * | 2021-02-20 | 2021-06-22 | 腾讯科技(深圳)有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
CN113528583A (en) * | 2021-07-15 | 2021-10-22 | 澳门大学 | Automatic microinjection method, device, system, equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106600298A (en) * | 2016-12-23 | 2017-04-26 | 国网山东省电力公司信息通信公司 | Electric power information system customer service knowledge base construction method based on work order data analysis |
WO2017190527A1 (en) * | 2016-05-06 | 2017-11-09 | 华为技术有限公司 | Text data classification method and server |
CN108416375A (en) * | 2018-02-13 | 2018-08-17 | 中国联合网络通信集团有限公司 | Work order sorting technique and device |
CN108549647A (en) * | 2018-01-17 | 2018-09-18 | 中移在线服务有限公司 | The method without accident in mark language material active predicting movement customer service field is realized based on SinglePass algorithms |
CN108876121A (en) * | 2018-05-31 | 2018-11-23 | 康键信息技术(深圳)有限公司 | Worksheet method, apparatus, computer equipment and storage medium |
CN108897798A (en) * | 2018-06-12 | 2018-11-27 | 广东电网有限责任公司 | Method and device for classifying customer service work orders and electronic equipment |
-
2019
- 2019-02-25 CN CN201910139175.3A patent/CN111611353B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017190527A1 (en) * | 2016-05-06 | 2017-11-09 | 华为技术有限公司 | Text data classification method and server |
CN106600298A (en) * | 2016-12-23 | 2017-04-26 | 国网山东省电力公司信息通信公司 | Electric power information system customer service knowledge base construction method based on work order data analysis |
CN108549647A (en) * | 2018-01-17 | 2018-09-18 | 中移在线服务有限公司 | The method without accident in mark language material active predicting movement customer service field is realized based on SinglePass algorithms |
CN108416375A (en) * | 2018-02-13 | 2018-08-17 | 中国联合网络通信集团有限公司 | Work order sorting technique and device |
CN108876121A (en) * | 2018-05-31 | 2018-11-23 | 康键信息技术(深圳)有限公司 | Worksheet method, apparatus, computer equipment and storage medium |
CN108897798A (en) * | 2018-06-12 | 2018-11-27 | 广东电网有限责任公司 | Method and device for classifying customer service work orders and electronic equipment |
Non-Patent Citations (1)
Title |
---|
顾斌 ; 彭涛 ; 车伟 ; .基于词典扩充的电力客服工单情感倾向性分析.现代电子技术.2017,第40卷(第11期),第163-171页. * |
Also Published As
Publication number | Publication date |
---|---|
CN111611353A (en) | 2020-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110995459B (en) | Abnormal object identification method, device, medium and electronic equipment | |
US11048854B2 (en) | System and method of highlighting influential samples in sequential analysis | |
CN108345587B (en) | Method and system for detecting authenticity of comments | |
CN110968695A (en) | Intelligent labeling method, device and platform based on active learning of weak supervision technology | |
US9122995B2 (en) | Classification of stream-based data using machine learning | |
CN112270546A (en) | Risk prediction method and device based on stacking algorithm and electronic equipment | |
US9269057B1 (en) | Using specialized workers to improve performance in machine learning | |
CA3166347A1 (en) | Video generation method and apparatus, and computer system | |
CN113283795B (en) | Data processing method and device based on two-classification model, medium and equipment | |
CN111611353B (en) | Screening method, screening device, electronic equipment and computer readable storage medium | |
CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
CN113850666A (en) | Service scheduling method, device, equipment and storage medium | |
CN111582645B (en) | APP risk assessment method and device based on factoring machine and electronic equipment | |
US10762089B2 (en) | Open ended question identification for investigations | |
CN112632179A (en) | Model construction method and device, storage medium and equipment | |
CN111860853A (en) | Online prediction system, online prediction equipment, online prediction method and electronic equipment | |
CN114186024A (en) | Recommendation method and device | |
CN116340831B (en) | Information classification method and device, electronic equipment and storage medium | |
US8918406B2 (en) | Intelligent analysis queue construction | |
CN111782774B (en) | Method and device for recommending problems | |
CN116823164A (en) | Business approval method, device, equipment and storage medium | |
US20220318681A1 (en) | System and method for scalable, interactive, collaborative topic identification and tracking | |
CN116795978A (en) | Complaint information processing method and device, electronic equipment and medium | |
CN114266496A (en) | Policy landing effect evaluation method and system based on policy completeness analysis | |
KR102078541B1 (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |