CN111611804A - Danger identification method and device, electronic equipment and storage medium - Google Patents
Danger identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111611804A CN111611804A CN201910141131.4A CN201910141131A CN111611804A CN 111611804 A CN111611804 A CN 111611804A CN 201910141131 A CN201910141131 A CN 201910141131A CN 111611804 A CN111611804 A CN 111611804A
- Authority
- CN
- China
- Prior art keywords
- information
- danger
- service provider
- confidence
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000008569 process Effects 0.000 claims description 31
- 238000013527 convolutional neural network Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 230000003993 interaction Effects 0.000 claims description 16
- 230000002452 interceptive effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 5
- 231100001267 hazard identification Toxicity 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 8
- 230000001568 sexual effect Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007794 irritation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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]
- G06Q30/0609—Buyer or seller confidence or verification
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application provides a danger identification method and device, electronic equipment and a storage medium, and belongs to the technical field of safety. According to the method, the text information to be recognized is recognized through the at least two information recognition models to obtain at least two recognition results, and the danger degree of the service provider is determined through at least one danger characteristic information in each recognition result, so that the danger degree of the service provider can be comprehensively judged based on different recognition results of different information recognition models, and the accuracy of determining the danger of the service provider can be improved.
Description
Technical Field
The present application relates to the field of security technologies, and in particular, to a method and an apparatus for risk identification, an electronic device, and a storage medium.
Background
Taking a car booking scene as an example, in order to further ensure the riding safety of passengers, a dialogue between the passengers and the driver in the riding process can be generally acquired to judge whether contradictions occur between the driver and the passengers, in the prior art, whether the driver is dangerous or not is judged by extracting keywords in the dialogue, but the driver is obviously inaccurate if the driver is determined to be dangerous only according to a few keywords, in some cases, the dialogue between the driver and the passengers does not include some dialogues with irritation, at this time, whether the driver is dangerous or not may not be judged, and in actual situations, the driver may have high danger, so that the safety of the passengers is threatened. Therefore, the accuracy of the manner of determining the risk of the driver in the prior art is low, so that the safety of the passenger cannot be guaranteed.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a method and an apparatus for identifying a risk, an electronic device, and a storage medium, so as to solve the problem that the driver's risk cannot be accurately determined and the safety of the passenger cannot be ensured in the prior art.
In a first aspect, an embodiment of the present application provides a risk identification method, where the method includes: acquiring text information to be identified, wherein the text information to be identified is interactive information between a service provider and a service requester in the process of providing service; respectively inputting the text information to be recognized into at least two information recognition models, and recognizing the text information to be recognized through each information recognition model to obtain at least two recognition results, wherein each recognition result comprises at least one piece of dangerous characteristic information; determining a degree of risk of the service provider based on the at least one risk characteristic information in each identification result.
In the implementation process, the text information to be recognized is recognized through the at least two information recognition models to obtain at least two recognition results, and the risk degree of the service provider is determined through at least one piece of risk characteristic information in each recognition result.
Optionally, a first information recognition model and a second information recognition model of the at least two information recognition models belong to the same type of model, and the first information recognition model and the second information recognition model are obtained by training a plurality of text messages corresponding to different danger characteristic information.
Optionally, a third information recognition model and a fourth information recognition model of the at least two information recognition models belong to different types of models, and the third information recognition model and the fourth information recognition model are obtained by training based on a plurality of text messages corresponding to the same risk feature information.
In the implementation process, different types or the same type of information identification models can be trained according to actual needs, so that interactive information between the service provider and the service requester can be identified through the models subsequently, and the accuracy of information identification can be improved.
Optionally, each recognition result further includes a confidence corresponding to each dangerous feature information, and determining the degree of danger of the service provider based on at least one dangerous feature information in each recognition result includes: and determining the danger degree of the service provider based on the confidence corresponding to the at least one danger characteristic information in each recognition result.
In the implementation process, the risk degree of the service provider is determined according to the confidence degrees corresponding to the risk characteristic information, that is, different risk degrees of the service provider can be determined based on the confidence degrees corresponding to different risk characteristic information, so that the accuracy of determining the risk of the service provider can be improved.
Optionally, determining the risk level of the service provider based on the confidence corresponding to the at least one risk characteristic information in each recognition result includes: summing the confidence degrees corresponding to the dangerous feature information in the at least two recognition results to obtain the confidence degree sum corresponding to all the dangerous feature information; and determining the danger degree of the service provider according to the confidence sums corresponding to all the dangerous characteristic information.
In the implementation process, the risk degree of the service provider is determined according to the confidence sum corresponding to the risk characteristic information, so that the accuracy of determining the risk of the service provider can be improved.
Optionally, determining the risk level of the service provider according to the confidence sums corresponding to all the risk characteristic information includes: when the confidence coefficient sum corresponding to all the dangerous feature information is greater than or equal to a preset confidence coefficient, determining the danger degree of the service provider as a first danger level; and when the confidence coefficient sum corresponding to all the dangerous characteristic information is smaller than the preset confidence coefficient, determining the danger degree of the service provider as a second danger level, wherein the danger degree corresponding to the second danger level is smaller than the danger degree corresponding to the first danger level.
In the implementation process, the danger degree of the service provider is classified into danger levels according to the confidence sum corresponding to the danger characteristic information, so that different danger warning modes can be adopted for the service provider or the service requester based on different danger levels in the follow-up process.
Optionally, determining the risk level of the service provider based on the confidence corresponding to the at least one risk characteristic information in each recognition result includes: summing the confidence degrees corresponding to the same dangerous feature information in the at least two recognition results to obtain a target confidence degree corresponding to each dangerous feature information; determining target dangerous feature information with the maximum target confidence degree from the target confidence degrees corresponding to each piece of dangerous feature information; determining a degree of risk of the service provider based on the target risk characteristic information.
In the implementation process, the danger degree of the service provider is determined according to the target danger characteristic information with the maximum target confidence, so that the danger degree of the service provider can be determined according to different target danger characteristic information, and the accuracy of determining the danger of the service provider is improved.
Optionally, after determining the risk level of the service provider based on the at least one risk characteristic information in each identification result, the method further includes: and sending corresponding danger prompt information to the service requester based on the danger degree of the service provider.
In the implementation process, the danger prompt information is sent to the service requester to prompt the service requester to be away from the service provider as soon as possible, so that the service requester can take safety protection measures in time and ensure the safety of the service requester.
Optionally, the at least two information recognition models include: at least two of the convolutional neural network model CNN, the long-short term memory network model LSTM, and the pattern model.
Optionally, the interaction information includes interaction information between the service provider and the service requester in a time period before a trip in providing a service is started.
In the implementation process, by acquiring the interaction information between the service provider and the service requester in the time period before the start of the journey, the problem that the safety of the service requester cannot be guaranteed in advance because the danger degree of the service provider is identified only when the personal safety of the service requester is threatened in the journey can be avoided.
In a second aspect, an embodiment of the present application provides a danger identification apparatus, including:
the information acquisition module is used for acquiring text information to be identified, wherein the text information to be identified is interactive information between a service provider and a service requester in the process of providing service;
the identification module is used for respectively inputting the text information to be identified into at least two information identification models, identifying the text information to be identified through each information identification model, and obtaining at least two identification results, wherein each identification result comprises at least one piece of dangerous characteristic information;
and the danger degree determining module is used for determining the danger degree of the service provider based on at least one piece of danger characteristic information in each identification result.
Optionally, a first information recognition model and a second information recognition model of the at least two information recognition models belong to the same type of model, and the first information recognition model and the second information recognition model are obtained by training a plurality of text messages corresponding to different danger characteristic information.
Optionally, a third information recognition model and a fourth information recognition model of the at least two information recognition models belong to different types of models, and the third information recognition model and the fourth information recognition model are obtained by training based on a plurality of text messages corresponding to the same risk feature information.
Optionally, each recognition result further includes a confidence corresponding to each piece of dangerous feature information, and the dangerous degree determining module is configured to determine the dangerous degree of the service provider based on the confidence corresponding to at least one piece of dangerous feature information in each recognition result.
Optionally, the risk level determining module is specifically configured to:
summing the confidence degrees corresponding to the dangerous feature information in the at least two recognition results to obtain the confidence degree sum corresponding to all the dangerous feature information;
and determining the danger degree of the service provider according to the confidence sums corresponding to all the dangerous characteristic information.
Optionally, the risk level determining module is further configured to:
when the confidence coefficient sum corresponding to all the dangerous feature information is greater than or equal to a preset confidence coefficient, determining the danger degree of the service provider as a first danger level;
and when the confidence coefficient sum corresponding to all the dangerous characteristic information is smaller than the preset confidence coefficient, determining the danger degree of the service provider as a second danger level, wherein the danger degree corresponding to the second danger level is smaller than the danger degree corresponding to the first danger level.
Optionally, the risk level determining module is further configured to:
summing the confidence degrees corresponding to the same dangerous feature information in the at least two recognition results to obtain a target confidence degree corresponding to each dangerous feature information;
determining target dangerous feature information with the maximum target confidence degree from the target confidence degrees corresponding to each piece of dangerous feature information;
determining a degree of risk of the service provider based on the target risk characteristic information.
Optionally, the apparatus further comprises:
and the danger prompting module is used for sending corresponding danger prompting information to the service requester based on the danger degree of the service provider.
Optionally, the at least two information recognition models include: at least two of the convolutional neural network model CNN, the long-short term memory network model LSTM, and the pattern model.
Optionally, the interaction information includes interaction information between the service provider and the service requester in a time period before a trip in providing a service is started.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method as provided in the first aspect are executed.
In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the method as provided in the first aspect.
Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 illustrates a schematic diagram of exemplary hardware and software components of an electronic device that may implement the concepts of the present application, according to some embodiments of the present application;
fig. 2 is a flowchart of a risk identification method according to an embodiment of the present application;
fig. 3 is a block diagram of a risk identification device according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
In order to enable those skilled in the art to understand the present disclosure, the following embodiments are given in conjunction with a specific application scenario "net appointment". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of a net appointment, it should be understood that this is only one exemplary embodiment. The application can be applied to any other traffic type. The present application may also include any service system for providing services, for example, a system for sending and/or receiving couriers, a service system for business transactions between buyers and sellers. Applications of the system or method of the present application may include web pages, plug-ins for browsers, client terminals, customization systems, internal analysis systems, or artificial intelligence robots, among others, or any combination thereof.
It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.
The terms "driver," "provider," "service provider," and "service provider" are used interchangeably in this application to refer to an individual, entity, or tool that can provide a service. The terms "passenger," "requestor," "service person," "service requestor," and "customer" are used interchangeably in this application to refer to an individual, entity, or tool that can request or order a service.
Referring to fig. 1, fig. 1 shows a schematic diagram of exemplary hardware and software components of an electronic device 100, which may implement the concepts of the present application, according to some embodiments of the present application. For example, a processor may be used on the electronic device 100 and to perform the functions herein.
The electronic device 100 may be a general-purpose computer or a special-purpose computer, both of which may be used to implement the data processing method of the present application. Although only a single computer is shown, for convenience, the functions described herein may be implemented in a distributed fashion across multiple similar platforms to balance processing loads.
For example, the 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 a storage medium 140 of different form, such as a disk, ROM, or RAM, or any combination thereof. Illustratively, 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 the computer and other Input/output devices (e.g., keyboard, display screen).
For ease of illustration, only one processor is depicted in electronic device 100. However, it should be noted that the electronic device 100 in the present application may also comprise a plurality of processors, and thus the steps performed by one processor described in the present application may also be performed by a plurality of processors in combination or individually. For example, if the processor of the electronic device 100 executes steps a and B, it should be understood that steps a and B may also be executed by two different processors together or separately in one processor. For example, a first processor performs step a and a second processor performs step B, or the first processor and the second processor perform steps a and B together.
Referring to fig. 2, fig. 2 is a flowchart of a method for identifying a risk according to an embodiment of the present application, where the method includes the following steps:
step S110: and acquiring text information to be recognized.
In order to facilitate understanding of the embodiments of the present application, a network appointment scene is taken as an example for description in the embodiments of the present application. In the scene of the online taxi appointment, in order to judge whether the driver can cause danger to the passengers or not and ensure the safety of the passengers, dialogue data between the driver and the passengers can be obtained to analyze the dialogue data so as to judge whether contradictions or other situations occur between the driver and the passengers or not and further judge the danger degree of the driver.
It is understood that in the car booking scenario, the service provider may refer to a driver, and the service requester may refer to a passenger, so the text information to be recognized may refer to dialogue data between the driver and the passenger obtained directly through voice recognition conversion, that is, the text information to be recognized is interaction information between the service provider and the service requester during the service providing process, and the dialogue data between the driver and the passenger is generally voice information, which may be obtained as follows: the driver is when the service begins, but install the recording equipment that the network car booking platform automatic control started driver terminal on driver terminal, and recording equipment can record all speech information between driving in-process driver and passenger, and after the service, network car booking platform automatic control closed recording equipment to speech information who will acquire sends the server and carries out subsequent processing.
The server may perform voice recognition on the voice information, that is, convert the voice information into text information, that is, text information to be recognized, that is, the server may obtain interactive voice information between the service provider and the service requester during the service providing process, and then perform voice recognition on the interactive voice information to obtain text information to be recognized. The speech recognition method can be as follows: and recognizing the speech information to be recognized by adopting an acoustic model or a speech recognition system, and the like.
It should be noted that the text information to be recognized includes, in addition to the text information obtained by converting the voice information between the driver and the passenger through the recording device in the service process, information for text communication between the passenger and the driver, such as text information communicated through short messages or WeChat messages.
Step S120: and respectively inputting the text information to be recognized into at least two information recognition models, and recognizing the text information to be recognized through each information recognition model to obtain at least two recognition results.
The at least two information identification models can be different information identification models, so that the identification results of the text information to be identified can be different, and the danger degree of the service provider can be determined by combining different identification results subsequently.
Each recognition result comprises at least one piece of danger characteristic information, and in a car appointment scene, the danger characteristic information can include but is not limited to: drunkenness, order cutting (off-line transaction), asking for contact information, people and vehicle inconsistency, sexual disturbance, order cancellation induction, car calling on behalf of people and the like.
The information identification model can carry out semantic understanding on the text information to be identified, and then obtains the meaning corresponding to whether the text information to be identified has dangerous characteristic information or not, namely, identifies whether a driver is drunk or not in the text information to be identified, and whether both sides reach offline transaction or not, and the like, thereby obtaining the corresponding identification result.
Step S130: determining a degree of risk of the service provider based on the at least one risk characteristic information in each identification result.
Judging the danger degree of the service provider from at least one piece of dangerous characteristic information in each identification result, wherein if the number of dangerous characteristic information in a plurality of identification results is large, the danger degree of the possible service provider is high, and if the number of dangerous characteristic information is small, the danger degree of the possible service provider is relatively low; or each recognition result comprises the danger characteristic information of drunkenness, which indicates that the danger degree of the service provider is higher.
Therefore, in this embodiment, the text information to be recognized is recognized by the at least two information recognition models to obtain at least two recognition results, and the risk level of the service provider is determined by the at least one risk feature information in each recognition result, so that the risk level of the service provider can be comprehensively determined based on different recognition results of different information recognition models, and the accuracy of determining the risk of the service provider can be improved.
As a possible implementation, the at least two information recognition models include: at least two of Convolutional Neural Networks (CNN), Long-Short term memory Networks (LSTM), and pattern models.
Of course, the above information recognition model is only an example, and in practical applications, it may also include other models, such as other Neural Network models, for example, Recurrent Neural Network (RNN), which are not listed here.
As another embodiment, the at least two information recognition models may be different models of the same type, that is, a first information recognition model and a second information recognition model of the at least two information recognition models belong to the same type of model, and the first information recognition model and the second information recognition model are obtained by training based on a plurality of text information corresponding to different danger characteristic information. For example, the first information recognition model and the second information recognition model both belong to CNN models, but are obtained by training different dangerous feature information, for example, a plurality of text information corresponding to two dangerous feature information of drunkenness and order cutting (offline transaction) is used for training to obtain a first CNN model (i.e., a first information recognition model), a plurality of text information corresponding to three dangerous feature information of a required contact way and a person-vehicle inconsistency is used for training to obtain a second CNN model (i.e., a second information recognition model), and a plurality of text information corresponding to three dangerous feature information of sexual disturbance, an induced cancellation order and a person-vehicle substitution is used for training to obtain a third CNN model (i.e., other information recognition models).
Or, when at least two information recognition models are different types of models, each information recognition model is obtained by training a plurality of pieces of text information corresponding to the same danger characteristic information, for example, the plurality of pieces of text information corresponding to the seven danger characteristic information are respectively input into the CNN model, the LSTM model and the pattern model, and the three models are respectively trained to obtain the trained three models.
Of course, when the information recognition models are different types of models, the different types of models may be input with a plurality of pieces of text information corresponding to different sets of danger feature information for training, that is, a third information recognition model and a fourth information recognition model of the at least two information recognition models belong to different types of models, and the third information recognition model and the fourth information recognition model are obtained by training based on a plurality of pieces of text information corresponding to the same set of danger feature information. For example, the different types of information recognition models include a CNN model, an LSTM model, and a pattern model, and the three models are trained respectively to obtain the trained three models, where the third information recognition model may be the CNN model, and the fourth information recognition model may be the LSTM model. It can be understood that, during training, for example, a plurality of text messages corresponding to two dangerous feature messages of drunkenness and order cutting (offline transaction) may be used for training to obtain a CNN model (i.e., a third information recognition model), a plurality of text messages corresponding to three dangerous feature messages of a required contact and a person-vehicle inconsistency may be used for training to obtain an LSTM model (i.e., a fourth information recognition model), and a plurality of text messages corresponding to three dangerous feature messages of sexual disturbance, an induced cancellation of an order, and a person-vehicle call may be used for training to obtain a patterrn model.
In the implementation process, different types or the same type of information identification models can be trained according to actual needs, so that interactive information between the service provider and the service requester can be identified through the models subsequently, and the accuracy of information identification can be improved.
Therefore, at least two trained information recognition models can be obtained in the above manner, and then the information to be recognized is recognized through the at least two information recognition models to obtain at least two recognition results, wherein each recognition result includes at least one piece of danger characteristic information.
In addition, in a possible embodiment, the determining the risk level of the service provider based on the at least one risk characteristic information in each recognition result includes: each recognition result further comprises a confidence corresponding to each dangerous characteristic information, and the danger degree of the service provider is determined based on the confidence corresponding to at least one dangerous characteristic information in each recognition result.
The confidence coefficient may refer to a danger value corresponding to each dangerous feature information, the greater the confidence coefficient is, the greater the danger degree is, and each information recognition model may output the confidence coefficient corresponding to each dangerous feature information.
When the risk degree of the service provider is determined, the confidence degrees corresponding to the risk feature information in the at least two recognition results may be summed to obtain the confidence degree sum corresponding to all the risk feature information, and then the risk degree of the service provider is determined according to the confidence degree sum corresponding to all the risk feature information.
Taking the above three models as examples, namely the CNN model, the LSTM model and the pattern model, respectively, if the CNN model identifies the dangerous feature information in the text information to be identified and the corresponding confidence coefficient is: drunk (0.8), cut list (0.1), ask for contact (0.2), people and vehicles nonconformity (0), sexual disturbance (0.5), induced cancellation order (0.1), person and vehicle calling (0) instead, the LSTM model identifies that dangerous characteristic information and corresponding confidence coefficient in the text information to be identified are: drunk wine (0.6), cut list (0.2), ask for contact (0.5), people and vehicles are not inconsistent (0.2), sexual disturbance (0.4), the order is cancelled in the inducement (0), the person is called the car (0.1) instead of the others, the pattern model identifies that dangerous characteristic information and corresponding confidence coefficient in the text information to be identified are: drunkenness (0.7), cutting a bill (0.2), asking for contact (0.2), people and vehicles discordance (0.3), sexual disturbance (0.6), order induction cancellation (0.2) and calling for a car (0.3) by a person. The confidence sum of all the dangerous characteristic information is 6.1.
In the above manner, the confidence sums corresponding to all the dangerous feature information may be obtained, and then the danger level of the service provider is determined based on the confidence sums corresponding to all the dangerous feature information, for example, if the confidence sum is greater than the preset confidence level, for example, if the preset confidence level is 5, it indicates that the danger level of the service provider is higher. Therefore, the accuracy of determining the risk of the service provider can be improved by determining the risk degree of the service provider according to the confidence sum corresponding to the risk characteristic information.
Certainly, the risk degree of the service provider may be divided according to risk levels, for example, when the confidence sum corresponding to all the dangerous feature information is greater than or equal to the preset confidence, the risk degree of the service provider is determined to be a first risk level, and when the confidence sum corresponding to all the dangerous feature information is less than the preset confidence, the risk degree of the service provider is determined to be a second risk level, and the risk degree corresponding to the second risk level is less than the risk degree corresponding to the first risk level. For example, the sum of the confidence degrees corresponding to all the dangerous characteristic information calculated as above is 6.1, and the preset confidence degree is 5, at this time, the danger degree of the service provider is a first danger level, and the first danger level may indicate that the service requester is in a very dangerous situation.
In the implementation process, the danger degree of the service provider is classified into danger levels according to the confidence sum corresponding to the danger characteristic information, so that different danger warning modes can be adopted for the service provider or the service requester based on different danger levels in the follow-up process. For example, the alarm telephone can be directly and automatically dialed when the first danger level is reached, and the information of serious alarm can be directly sent to the service provider when the second danger level is reached, and the service requester is prompted to contact relatives and friends as soon as possible, get off the vehicle in time or prompt the prompt information of alarm and the like.
In a possible embodiment, the determining the risk level of the service provider based on the at least one risk characteristic information in each recognition result may further include: summing the confidence degrees corresponding to the same dangerous feature information in the at least two recognition results to obtain a target confidence degree corresponding to each dangerous feature information; determining target dangerous feature information with the maximum target confidence degree from the target confidence degrees corresponding to each piece of dangerous feature information; determining a degree of risk of the service provider based on the target risk characteristic information.
For example, the target confidence degrees corresponding to the obtained dangerous feature information in the above manner are: drunkenness (2.1), cutting a bill (0.5), asking for contact (0.9), people and vehicles discordance (0.5), sexual disturbance (1.5), order induction cancellation (0.2) and calling for a car (0.4) for a person.
Then, the target confidence degrees corresponding to the dangerous feature information are arranged according to a descending order to obtain the target dangerous feature information with the maximum target confidence degree, namely the target dangerous feature information with the maximum target confidence degree is drunk, the dangerous level corresponding to the dangerous feature information can be preset, for example, the dangerous level corresponding to sexual disturbance is the highest, for example, the first dangerous level, then the dangerous level is drunk, and the corresponding dangerous level is the second dangerous level, so that the service provider is identified as drunk, and the dangerous degree is the second dangerous level.
According to the embodiment, the danger degree of the service provider can be determined according to the target danger characteristic information with the maximum target confidence degree, so that the danger degree of the service provider can be determined according to different target danger characteristic information, and the accuracy of determining the danger of the service provider is improved.
Of course, determining the risk level of the service provider based on the confidence level corresponding to at least one piece of dangerous feature information in each recognition result is not only the above-mentioned example, but also may determine the risk level of the service provider in other manners, for example, comprehensively considering the confidence levels corresponding to the dangerous feature information, that is, determining whether the confidence level occupied by the dangerous feature information with higher risk level is higher, if so, indicating that the risk level of the service provider is relatively lower, and other embodiments are not listed one by one here.
After the danger degree of the service provider is determined, in order to ensure the safety of the service requester, corresponding danger prompt information can be sent to the service requester based on the danger degree of the service provider, if the danger degree of the driver is determined to be high, danger prompt information of ' the danger degree of the driver is high, a driver is required to contact relatives and friends or call an alarm phone ' can be sent to a passenger in time, if the danger degree of the driver is determined to be low, the danger prompt information of ' the danger degree of the driver is low, but in order to ensure your safety, the driver is required to be informed of parking and getting off at a safe place in time, and the passenger can take measures to ensure the safety of the passenger after receiving the danger prompt information.
Certainly, the corresponding danger characteristic information can be sent to the passenger, for example, if the driver is identified to be in a drunk state at present and please get off the vehicle in time, or when the corresponding danger characteristic information is identified, corresponding warning information can be sent to the service provider, for example, if the current background identifies that the passenger is harassed by nature and please stop the vehicle in time, or else, the background takes an automatic warning measure, a certain warning effect can be formed on the driver by the method, and the passenger can also obtain the danger prompt information, so that the safety of the passenger can be ensured in time.
It should be noted that, through the above embodiment, the danger degree of the service requester can also be determined, and if the danger characteristic information that the service requester is the "car to be called" is identified, a prompt message of "please complete the relevant information of the person to be called" can be sent to the service requester, and a prompt message of "the passenger is the car to be called" can also be sent to the service provider.
In addition, in order to avoid the problem that the safety of the passenger cannot be guaranteed in advance because the danger degree of the driver is recognized only when the personal safety of the passenger is threatened in the process of the journey, the interactive information between the driver and the passenger can be recognized before the journey is started, namely the interactive information of the embodiment can comprise the interactive information between the service provider and the service requester in the time period before the driving starts in the process of providing the service.
The time period before the driving starts can refer to the time period from when the driver receives the order of the passenger to when the driver triggers the travel starting on the network appointment platform after the passenger gets on the vehicle, information interaction can be carried out between the driver and the passenger in the time period through a telephone or a communication platform provided by the network appointment platform, so that the interaction information between the driver and the passenger in the time period can be obtained, if the danger degree of the driver is higher according to the interaction information in the time period, corresponding prompt information can be sent to the passenger, for example, the driver is relatively dangerous, the order is recommended to be cancelled in time, the passenger does not need to get on the vehicle, and therefore any dangerous condition in the subsequent travel process after the passenger gets on the vehicle can be avoided, and the safety of the passenger is guaranteed.
Referring to fig. 3, fig. 3 is a block diagram of a danger identification apparatus 200 according to an embodiment of the present disclosure, the apparatus includes:
the information obtaining module 210 is configured to obtain text information to be identified, where the text information to be identified is interaction information between a service provider and a service requester in a service providing process;
the identification module 220 is configured to input the text information to be identified into at least two information identification models respectively, identify the text information to be identified through each information identification model, and obtain at least two identification results, where each identification result includes at least one piece of danger feature information;
a risk level determining module 230, configured to determine a risk level of the service provider based on the at least one risk characteristic information in each identification result.
Optionally, a first information recognition model and a second information recognition model of the at least two information recognition models belong to the same type of model, and the first information recognition model and the second information recognition model are obtained by training a plurality of text messages corresponding to different danger characteristic information.
Optionally, a third information recognition model and a fourth information recognition model of the at least two information recognition models belong to different types of models, and the third information recognition model and the fourth information recognition model are obtained by training based on a plurality of text messages corresponding to the same risk feature information.
Optionally, each recognition result further includes a confidence corresponding to each dangerous feature information, and the dangerous degree determining module 230 is configured to determine the dangerous degree of the service provider based on the confidence corresponding to at least one dangerous feature information in each recognition result.
Optionally, the risk level determining module 230 is specifically configured to:
summing the confidence degrees corresponding to the dangerous feature information in the at least two recognition results to obtain the confidence degree sum corresponding to all the dangerous feature information;
and determining the danger degree of the service provider according to the confidence sums corresponding to all the dangerous characteristic information.
Optionally, the risk level determining module 230 is further configured to:
when the confidence coefficient sum corresponding to all the dangerous feature information is greater than or equal to a preset confidence coefficient, determining the danger degree of the service provider as a first danger level;
and when the confidence coefficient sum corresponding to all the dangerous characteristic information is smaller than the preset confidence coefficient, determining the danger degree of the service provider as a second danger level, wherein the danger degree corresponding to the second danger level is smaller than the danger degree corresponding to the first danger level.
Optionally, the risk level determining module 230 is further configured to:
summing the confidence degrees corresponding to the same dangerous feature information in the at least two recognition results to obtain a target confidence degree corresponding to each dangerous feature information;
determining target dangerous feature information with the maximum target confidence degree from the target confidence degrees corresponding to each piece of dangerous feature information;
determining a degree of risk of the service provider based on the target risk characteristic information.
Optionally, the apparatus further comprises:
and the danger prompting module is used for sending corresponding danger prompting information to the service requester based on the danger degree of the service provider.
Optionally, the at least two information recognition models include: at least two of the convolutional neural network model CNN, the long-short term memory network model LSTM, and the pattern model.
Optionally, the interaction information includes interaction information between the service provider and the service requester in a time period before a trip in providing a service is started.
The embodiment of the present application provides a readable storage medium, and when being executed by a processor, the computer program performs the method process performed by the electronic device in the method embodiment shown in fig. 2.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method, and will not be described in too much detail herein.
In summary, the embodiments of the present application provide a method, an apparatus, an electronic device, and a storage medium for identifying a risk, in which at least two information identification models identify text information to be identified, obtain at least two identification results, and determine a risk level of a service provider according to at least one risk feature information in each identification result, so that the risk level of the service provider can be comprehensively determined based on different identification results of different information identification models, and thus accuracy of determining a risk of the service provider can be improved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (22)
1. A method for hazard identification, the method comprising:
acquiring text information to be identified, wherein the text information to be identified is interactive information between a service provider and a service requester in the process of providing service;
respectively inputting the text information to be recognized into at least two information recognition models, and recognizing the text information to be recognized through each information recognition model to obtain at least two recognition results, wherein each recognition result comprises at least one piece of dangerous characteristic information;
determining a degree of risk of the service provider based on the at least one risk characteristic information in each identification result.
2. The method according to claim 1, wherein a first information recognition model and a second information recognition model of the at least two information recognition models belong to the same type of model, and the first information recognition model and the second information recognition model are obtained by training based on a plurality of text messages corresponding to different danger characteristic information.
3. The method according to claim 1, wherein a third information recognition model and a fourth information recognition model of the at least two information recognition models belong to different types of models, and the third information recognition model and the fourth information recognition model are obtained by training based on a plurality of text messages corresponding to the same danger characteristic information.
4. The method of claim 1, wherein each recognition result further comprises a confidence corresponding to each dangerous characteristic information, and determining the degree of danger of the service provider based on at least one dangerous characteristic information in each recognition result comprises:
and determining the danger degree of the service provider based on the confidence corresponding to the at least one danger characteristic information in each recognition result.
5. The method of claim 4, wherein determining the risk level of the service provider based on the confidence level corresponding to the at least one risk characteristic information in each recognition result comprises:
summing the confidence degrees corresponding to the dangerous feature information in the at least two recognition results to obtain the confidence degree sum corresponding to all the dangerous feature information;
and determining the danger degree of the service provider according to the confidence sums corresponding to all the dangerous characteristic information.
6. The method of claim 5, wherein determining the risk level of the service provider according to the confidence sums corresponding to all the risk characteristic information comprises:
when the confidence coefficient sum corresponding to all the dangerous feature information is greater than or equal to a preset confidence coefficient, determining the danger degree of the service provider as a first danger level;
and when the confidence coefficient sum corresponding to all the dangerous characteristic information is smaller than the preset confidence coefficient, determining the danger degree of the service provider as a second danger level, wherein the danger degree corresponding to the second danger level is smaller than the danger degree corresponding to the first danger level.
7. The method of claim 4, wherein determining the risk level of the service provider based on the confidence level corresponding to the at least one risk characteristic information in each recognition result comprises:
summing the confidence degrees corresponding to the same dangerous feature information in the at least two recognition results to obtain a target confidence degree corresponding to each dangerous feature information;
determining target dangerous feature information with the maximum target confidence degree from the target confidence degrees corresponding to each piece of dangerous feature information;
determining a degree of risk of the service provider based on the target risk characteristic information.
8. The method according to any one of claims 1-7, wherein after determining the risk level of the service provider based on the at least one risk characteristic information in each recognition result, further comprising:
and sending corresponding danger prompt information to the service requester based on the danger degree of the service provider.
9. The method according to any of claims 1-7, wherein the at least two information recognition models comprise: at least two of the convolutional neural network model CNN, the long-short term memory network model LSTM, and the pattern model.
10. The method according to any of claims 1-7, wherein the interaction information comprises interaction information between the service provider and the service requester during a time period before a trip in the process of providing the service is started.
11. A hazard identification device, the device comprising:
the information acquisition module is used for acquiring text information to be identified, wherein the text information to be identified is interactive information between a service provider and a service requester in the process of providing service;
the identification module is used for respectively inputting the text information to be identified into at least two information identification models, identifying the text information to be identified through each information identification model, and obtaining at least two identification results, wherein each identification result comprises at least one piece of dangerous characteristic information;
and the danger degree determining module is used for determining the danger degree of the service provider based on at least one piece of danger characteristic information in each identification result.
12. The apparatus according to claim 11, wherein a first information recognition model and a second information recognition model of the at least two information recognition models belong to a same type of model, and the first information recognition model and the second information recognition model are obtained by training based on a plurality of text messages corresponding to different danger characteristic information.
13. The apparatus according to claim 11, wherein a third information recognition model and a fourth information recognition model of the at least two information recognition models belong to different types of models, and the third information recognition model and the fourth information recognition model are obtained by training based on a plurality of text messages corresponding to the same danger characteristic information.
14. The apparatus of claim 11, wherein each recognition result further comprises a confidence level corresponding to each dangerous feature information, and the danger level determining module is configured to determine the danger level of the service provider based on the confidence level corresponding to at least one dangerous feature information in each recognition result.
15. The apparatus according to claim 14, wherein the risk level determining module is specifically configured to:
summing the confidence degrees corresponding to the dangerous feature information in the at least two recognition results to obtain the confidence degree sum corresponding to all the dangerous feature information;
and determining the danger degree of the service provider according to the confidence sums corresponding to all the dangerous characteristic information.
16. The apparatus of claim 15, wherein the risk level determination module is further configured to:
when the confidence coefficient sum corresponding to all the dangerous feature information is greater than or equal to a preset confidence coefficient, determining the danger degree of the service provider as a first danger level;
and when the confidence coefficient sum corresponding to all the dangerous characteristic information is smaller than the preset confidence coefficient, determining the danger degree of the service provider as a second danger level, wherein the danger degree corresponding to the second danger level is smaller than the danger degree corresponding to the first danger level.
17. The apparatus of claim 14, wherein the risk level determination module is further configured to:
summing the confidence degrees corresponding to the same dangerous feature information in the at least two recognition results to obtain a target confidence degree corresponding to each dangerous feature information;
determining target dangerous feature information with the maximum target confidence degree from the target confidence degrees corresponding to each piece of dangerous feature information;
determining a degree of risk of the service provider based on the target risk characteristic information.
18. The apparatus of any of claims 11-17, further comprising:
and the danger prompting module is used for sending corresponding danger prompting information to the service requester based on the danger degree of the service provider.
19. The apparatus according to any of claims 11-17, wherein the at least two information recognition models comprise: at least two of the convolutional neural network model CNN, the long-short term memory network model LSTM, and the pattern model.
20. The apparatus according to any of claims 11-17, wherein the interaction information comprises interaction information between the service provider and the service requester during a time period before a trip in providing a service is started.
21. An electronic device comprising a processor and a memory, said memory storing computer readable instructions which, when executed by said processor, perform the steps of the method of any of claims 1-10.
22. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141131.4A CN111611804A (en) | 2019-02-25 | 2019-02-25 | Danger identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141131.4A CN111611804A (en) | 2019-02-25 | 2019-02-25 | Danger identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111611804A true CN111611804A (en) | 2020-09-01 |
Family
ID=72205129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910141131.4A Pending CN111611804A (en) | 2019-02-25 | 2019-02-25 | Danger identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111611804A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503879A (en) * | 2023-05-22 | 2023-07-28 | 广东骏思信息科技有限公司 | Threat behavior identification method and device applied to e-commerce platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516989A (en) * | 2015-11-27 | 2016-04-20 | 努比亚技术有限公司 | Method and device for identifying bad conversation |
| CN108073804A (en) * | 2016-11-14 | 2018-05-25 | 百度在线网络技术（北京）有限公司 | A kind of Risk Identification Method and device |
| US20180174589A1 (en) * | 2016-12-19 | 2018-06-21 | Samsung Electronics Co., Ltd. | Speech recognition method and apparatus |
| CN108694940A (en) * | 2017-04-10 | 2018-10-23 | 北京猎户星空科技有限公司 | A kind of audio recognition method, device and electronic equipment |
-
2019
- 2019-02-25 CN CN201910141131.4A patent/CN111611804A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516989A (en) * | 2015-11-27 | 2016-04-20 | 努比亚技术有限公司 | Method and device for identifying bad conversation |
| CN108073804A (en) * | 2016-11-14 | 2018-05-25 | 百度在线网络技术（北京）有限公司 | A kind of Risk Identification Method and device |
| US20180174589A1 (en) * | 2016-12-19 | 2018-06-21 | Samsung Electronics Co., Ltd. | Speech recognition method and apparatus |
| CN108694940A (en) * | 2017-04-10 | 2018-10-23 | 北京猎户星空科技有限公司 | A kind of audio recognition method, device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503879A (en) * | 2023-05-22 | 2023-07-28 | 广东骏思信息科技有限公司 | Threat behavior identification method and device applied to e-commerce platform |
| CN116503879B (en) * | 2023-05-22 | 2024-01-19 | 广东骏思信息科技有限公司 | Threat behavior identification method and device applied to e-commerce platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111599164B (en) | Driving abnormity identification method and system | |
| CN111260102A (en) | User satisfaction prediction method and device, electronic equipment and storage medium | |
| CN111598368B (en) | Risk identification method, system and device based on stop abnormality after stroke end | |
| CN111145510A (en) | Alarm receiving processing method, device and equipment | |
| CN111353092A (en) | Service pushing method, device, server and readable storage medium | |
| CN108763251B (en) | Personalized recommendation method and device for nuclear product and electronic equipment | |
| CN111598641A (en) | Order risk verification method and system | |
| CN111209902B (en) | Method, device, server and readable storage medium for assisting law enforcement | |
| CN111489522A (en) | Method, device and system for outputting information | |
| CN115249481A (en) | Emotion recognition-based collection method and system, computer equipment and storage medium | |
| CN111144906A (en) | Data processing method and device and electronic equipment | |
| CN113139852B (en) | Overload prevention method and device for shared vehicle and electronic equipment | |
| CN111611804A (en) | Danger identification method and device, electronic equipment and storage medium | |
| CN111612200A (en) | Order security prediction method, device, server and storage medium | |
| CN111598274A (en) | Risk identification method, system and device based on exception cancellation and storage medium | |
| CN111414732A (en) | Text style conversion method and device, electronic equipment and storage medium | |
| CN111598642A (en) | Risk judgment method, system, device and storage medium | |
| CN115983804A (en) | Man-machine cooperation task processing method and device, electronic equipment and storage medium | |
| CN110782061A (en) | Method and system for predicting malignant event | |
| CN111835730B (en) | Service account processing method and device, electronic equipment and readable storage medium | |
| CN112633537A (en) | Order processing method and device for taxi, and electronic equipment | |
| CN114943455A (en) | Method and device for preventing rule violation of foreground and background, electronic equipment and storage medium | |
| CN111145490B (en) | Alarm method, device, server and system | |
| CN111401030B (en) | Method and device for identifying service abnormality, server and readable storage medium | |
| CN110852517B (en) | Abnormal behavior early warning method and device, data processing equipment and storage medium |
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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240220 |
|
| AD01 | Patent right deemed abandoned |