CN112116154A - Data processing method, data processing apparatus, storage medium, and electronic device - Google Patents
Data processing method, data processing apparatus, storage medium, and electronic device Download PDFInfo
- Publication number
- CN112116154A CN112116154A CN202010988184.2A CN202010988184A CN112116154A CN 112116154 A CN112116154 A CN 112116154A CN 202010988184 A CN202010988184 A CN 202010988184A CN 112116154 A CN112116154 A CN 112116154A
- Authority
- CN
- China
- Prior art keywords
- task
- historical
- user
- probability
- issued
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 30
- 238000003672 processing method Methods 0.000 title abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 43
- 230000033001 locomotion Effects 0.000 claims description 42
- 230000006870 function Effects 0.000 claims description 14
- 230000006399 behavior Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 description 19
- 238000010586 diagram Methods 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000638 solvent extraction Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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]
- G06Q30/0639—Item locations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a data processing method, a data processing device, a storage medium and electronic equipment. After the task characteristics of the task to be issued and the user characteristics of the task issuer are obtained, the target probability for representing the task to be issued as the task of the preset type is obtained according to the task characteristics of the task to be issued and the user characteristics of the task issuer based on the pre-trained probability prediction model. And if the target probability meets a preset probability condition, sending a preset message to the task issuing terminal, wherein the preset message is used for prompting the risk of the task to be issued to the task issuer. The method of the embodiment of the invention can identify the possibility of risk of the task with higher accuracy before the task is issued, thereby prompting the task issuer in time.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a data processing method, a data processing apparatus, a storage medium, and an electronic device.
Background
With the continuous development of the technical field of computers and the technical field of internet, more and more users select online platforms to distribute tasks to meet some requirements of the users. The online platform brings convenience to daily life of people, but some abnormal task issuing behaviors can cause certain risks in the task executing process. It is therefore necessary how to identify the possibility of a task being at risk before it is released.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a data processing method, a data processing apparatus, a storage medium, and an electronic device, which are used for identifying the possibility of risk of a task with high accuracy before the task is issued, so as to prompt a task issuer in time.
According to a first aspect of embodiments of the present invention, there is provided a data processing method, the method including:
acquiring task characteristics of a task to be issued and user characteristics of a target user, wherein the target user is a user who issues the task to be issued;
based on a pre-trained probability prediction model, determining a target probability of the task to be issued according to the task characteristics and the user characteristics, wherein the target probability is used for representing the probability that the task to be issued is a task of a preset type;
and responding to the target probability meeting a preset probability condition, and sending a preset message to a task issuing terminal so as to prompt the risk of the task to be issued.
According to a second aspect of embodiments of the present invention, there is provided a data processing apparatus, the apparatus comprising:
the data acquisition unit is used for acquiring task characteristics of a task to be issued and user characteristics of a target user, wherein the target user is a user who issues the task to be issued;
the probability prediction unit is used for determining the target probability of the task to be issued according to the task characteristics and the user characteristics based on a pre-trained probability prediction model, wherein the target probability is used for representing the probability that the task to be issued is a task of a preset type;
and the message sending unit is used for responding to the condition that the target probability meets the preset probability, and sending a preset message to the task issuing terminal so as to prompt the risk of the task to be issued.
According to a third aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method according to the first aspect.
According to a fourth aspect of embodiments of the present invention, there is provided an electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to the first aspect.
After the task characteristics of the task to be issued and the user characteristics of the task issuer are obtained, the target probability for representing the task to be issued as the task of the preset type is obtained according to the task characteristics of the task to be issued and the user characteristics of the task issuer based on the pre-trained probability prediction model. And if the target probability meets a preset probability condition, sending a preset message to the task issuing terminal, wherein the preset message is used for prompting the risk of the task to be issued to the task issuer. The method of the embodiment of the invention can identify the possibility of risk of the task with higher accuracy before the task is issued, thereby prompting the task issuer in time.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a hardware system architecture of an embodiment of the present invention;
FIG. 2 is a flow chart of a data processing method of the first embodiment of the present invention;
FIG. 3 is a flow chart of training a probabilistic predictive model in an alternative implementation of the first embodiment of the invention;
FIG. 4 is a diagram illustrating a first movement path and a second movement path according to the first embodiment of the present invention;
FIG. 5 is a data flow diagram of the method of the first embodiment of the present invention to obtain the target probability of the task to be processed;
FIG. 6 is a schematic diagram of a data processing apparatus according to a second embodiment of the present invention;
fig. 7 is a schematic view of an electronic device according to a third embodiment of the present invention.
Detailed Description
The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present invention.
Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.
Unless the context clearly requires otherwise, throughout the description, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the embodiment of the present invention, the task to be issued and the historical task are taken as car booking tasks for example, but those skilled in the art will readily understand that the method of the embodiment of the present invention is also applicable when the task to be issued and the historical task are other types of tasks and order distribution tasks.
In daily life, a user may generate some abnormal task issuing behaviors in a task issuing process, and the abnormal task issuing behaviors may cause a certain risk to the task in an executing process. For example, the user C1 cannot release the car reservation request due to some conditions of the user C, the friend user C2 of the user C1 helps the user C1 to release the car reservation request through the account of the user C, and the user C2 does not actually take a car. That is, the user C2 helps the user C1 to issue a call-by-order task for the car-booking service, and the user who issued the task is not the user who actually takes the car. However, the online car booking platform cannot determine whether the user C1 gets into the car or not and whether an accident occurs in the car taking process, so that the call-replacing task may have a certain risk in the execution process. It is therefore essential for the online platform how to identify the possibility of a task being at risk before it is released.
FIG. 1 is a diagram of a hardware system architecture of an embodiment of the present invention. The hardware system architecture shown in fig. 1 includes at least one task issuing terminal, at least one task processing terminal, and at least one server, and fig. 1 illustrates one task issuing terminal 11, one task processing terminal 12, and one server 13 as an example. The task distribution terminal 11, the task processing terminal 12, and the server 13 shown in fig. 1 may be communicatively connected via a network. In the embodiment of the invention, the task issuing terminal 11 is also a user terminal, and a user can issue a riding demand through a riding order on an online taxi appointment platform through the task issuing terminal 11. After obtaining the car booking order through the on-line car booking platform, the server 13 may allocate the car booking order to the task processing terminal 12, so that a car booking service provider (i.e., a driver) holding the task issuing terminal 12 may provide car booking service for the user according to an appointed time of the car booking order.
In the embodiment of the present invention, the server 13 may obtain, before the task to be issued is issued, the task feature of the task to be issued and the user feature of the target user, which are set by the target user (that is, a task issuer) through the task issuing terminal 11, and determine, according to the task feature of the task to be issued and the user feature of the target user, a target probability for representing a probability that the task to be issued is a predetermined type of task based on a probability prediction model trained in advance. If the target probability meets the predetermined probability condition, the server 13 may send a predetermined message to the task issuing terminal 11 to prompt the risk of the task to be issued. In an alternative implementation manner, in response to that the target probability meets a predetermined probability condition, the server 13 may set the task issuing mode of the task to be issued to an issuing mode corresponding to a predetermined type.
Fig. 2 is a flowchart of a data processing method according to a first embodiment of the present invention. As shown in fig. 2, the method of the present embodiment includes the following steps:
step S201, acquiring task features of a task to be issued and user features of a target user.
In this embodiment, the target user is also the user who issues the task to be issued. In this step, the server may obtain the task feature of the task to be published and the user feature of the target user after the user sets the task feature of the task to be published and before the task to be published is published.
The task features are used for representing real-time data of the task to be published, and may specifically include a start position, an end position, a start time (or a time period), and the like of the task to be published. In this embodiment, the starting location may be represented by an embedded vector, where the embedded vector may include category information of an area where the starting location is located (e.g., a business area, a residential area, an entertainment area, etc.), the number of interest points of other categories in the area where the starting location is located, and a distance distribution between the starting location and the interest points of other categories, where the distance distribution may specifically be a sum of distances, an average value of distances, and the like, and this embodiment is not limited. Similarly, the termination position may also be represented by an embedded vector, which may also include category information of the area where the termination position is located, the number of interest points of other categories within the area where the termination position is located, and the distance distribution between the termination position and the interest points of other categories. Therefore, the starting position and the ending position can be objectively described through association among other interest points in the region, and the accuracy of task features is improved. The starting time may also be represented by a vector, and specifically, a time period in which the starting time is located may be determined, so that a corresponding vector is determined according to the time period in which the starting time is located. For example, the starting time of the task to be processed is 10:20, and the time period is divided by hours, that is, the time period divided in advance includes 24 time periods of 0:00-0:59, 1:00-1:59, …, and 23:00-23:59, the server may determine that the starting time of the task to be processed belongs to the time period of 10:00-10:59, thereby determining that the vector corresponding to the starting time of the task to be processed is (0,0, …,1,0, …, 0), wherein the length of the vector is 24 and 1 is the 11 th element in the vector.
The user characteristics are used for representing the historical behaviors and the user portrait of the target user, and specifically may include the historical behavior characteristics of the target user and the user portrait data. The historical behavior characteristics are determined according to the historical task characteristics of at least one historical task which is issued by the target user in a historical manner, and specifically include regional distribution, time period distribution and the like of the historical task which is issued by the target user. Historical behavior features and user profile data may also be represented by vectors.
Optionally, the task characteristics of the task to be published may further include other data, for example, a distance between a start position of the task to be processed and a start position of a previous history task, a distance between an end position of the task to be processed and an end position of a previous history task, and the like. It is to be readily understood that the previous historical task refers to at least one historical task issued by the target user.
Step S202, based on a pre-trained probability prediction model, determining the target probability of the task to be issued according to the task characteristics and the user characteristics.
In this step, the server may input a vector determined according to the task characteristics and the user characteristics into a pre-trained probability prediction model, thereby obtaining a target probability of the task to be issued. The target probability is used for representing the probability that the task to be issued is the task of the preset type. In this embodiment, the tasks of the predetermined type are also called tasks. Generally, no matter whether the tasks are called instead, the user has a large possibility of selecting a default task issuing mode (namely, a task issuing mode corresponding to a common task) to issue the tasks, and the earlier the actual task type of the tasks to be issued is determined, the more the online platform can adopt a corresponding processing mode to the tasks to be issued, so that the safety guarantee for the riding user is enhanced. Therefore, in the embodiment, the task type of the task to be issued can be determined based on the probability prediction model, so that the timeliness of the on-line platform for processing the task to be issued is improved according to the task type in the follow-up process.
In this embodiment, the initial model corresponding to the consumption parameter prediction model may be a tree model, a bayesian classifier, a neural network, or the like, which is not limited in this embodiment. Taking a Neural Network as an example, the Neural Network is called an Artificial Neural Network (ANN) and is an information processing model formed by interconnecting a large number of processing units. Common artificial Neural networks include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and the like. The ANN has the characteristics of nonlinearity (suitable for processing nonlinear information), non-limitation (namely, the overall behavior of a system depends on the interaction between processing units), extraordinary qualitative (namely, self-adaptation, self-organization and self-learning capabilities, and can continuously perform self-learning in the process of processing information) and non-convexity (the activation function of the model has a plurality of extreme values, so that the model has a plurality of stable equilibrium states, and the change of the model is various), and therefore, the ANN can be widely applied to various fields to perform more accurate data prediction.
FIG. 3 is a flowchart of training a probabilistic predictive model in an alternative implementation of the first embodiment of the invention. As shown in fig. 3, in an alternative implementation manner of the present embodiment, the probabilistic predictive model may be trained through the following steps:
in step S301, a history task set is acquired.
In the present embodiment, the historical tasks in the historical task set are training samples for being used as a probabilistic predictive model. The historical task set comprises historical task characteristics of a plurality of historical tasks, and the historical task characteristics specifically comprise a starting position, an ending position, a historical starting time (or a time period), a first movement track and a second movement track of the historical tasks.
The starting position and the ending position of the historical task can also be represented by embedded vectors including category information of an area where the starting position or the ending position is located, the number of interest points of other categories in the area where the ending position is located, and distance distribution between the ending position and the interest points of other categories, and the historical starting time can also be represented by the vectors. In this embodiment, the first movement track is used to represent the movement track of a historical user (i.e., a user who issues a historical task) corresponding to a historical task, and the second movement track is used to represent the movement track of a task processing resource (i.e., a car booking service provider) corresponding to a historical task.
Optionally, similar to the task feature of the task to be issued, the historical task feature may further include other data, for example, a distance between a starting position of each historical task and a starting position of a previous historical task, a distance between an ending position of the task to be processed and an ending position of the previous historical task, and the like. It is easy to understand that the previous historical task refers to at least one historical task issued by the historical user corresponding to each historical task, and the issuing time of the previous historical task is earlier than that of the historical task.
Step S302, a sample set is determined according to the historical task characteristics of each historical task in the historical task set, the historical user characteristics of the corresponding historical user and the type identification.
In this step, the server may first determine the type identifier of each historical task according to the first movement trajectory and the second movement trajectory corresponding to each historical task, and then determine the historical task feature and the type identifier of each historical task as a training sample, so that a sample set may be determined according to each training sample.
Specifically, the server may determine the type identifier of the historical task according to the similarity between the first movement track and the second movement track. In this embodiment, the similarity may be reflected by a cosine value of an included angle between the first movement track and the second movement track, an SPD (Sum-of-Pairs Distance), an euclidean Distance, and the like, and this embodiment is not limited.
Fig. 4 is a schematic diagram of a first movement track and a second movement track according to the first embodiment of the invention. As shown in fig. 4, l1 is the first movement trace, and l2 is the second movement trace. When the similarity of l1 and l2 is reflected by the cosine value of the included angle, aiAnd bi(i is an integer of 1 or more)The positions reached by the movement along l1 and along l2 respectively at the same time. The first similarity s1 can be calculated by the following formula:
s1＝n1[cos(a1a2,b1b2)+cos(a2a3,b2b3)+…+cos(aiai+1,bibi+1)]；
where n1 is a predetermined coefficient greater than 0, and may be determined according to a value of i, for example, n1 is 1/i, aiai+1Is formed by aiPoint of direction ai+1Vector of (a), bibi+1Is composed of biDirection bi+1Vector of (a), cos (a)iai+1,bibi+1) Is aiai+1And bibi+1The cosine value of the included angle. When the similarity of l1 and l2 is reflected by the SPD, biIs a on l1iDistance l2 is the shortest distance point, where aiMay be an inflection point of l 2. The similarity s1 can be obtained by the following formula:
wherein d isl1,l2Is a distance of l1 to l2, dl2,l1Is the distance l2 to l 1. With dl1,l2For example, dl1,l2Can be obtained by the following formula:
where n2 is a predetermined coefficient greater than 0, and may be determined according to a value of i, for example, n2 is 1/i, and d isai,biIs aiAnd biThe distance of (c). After acquiring the SPD, the server can calculate [ (1/2) × (l1+ l2) -SPD]/[1/2(l1+l2)]Similarity of l1 to l2 was determined.
If the similarity between the first moving track and the second moving track meets the preset similarity condition, and the moving tracks of the historical users and the task processing resources are approximately the same, the server can determine that the users taking the vehicle actually are the historical users, and determine that the type identifier of the historical task is the type identifier of the task of the non-preset type; otherwise, the moving tracks of the historical user and the task processing resources are different, the server can determine that the user taking the car actually is not the historical user, and determine that the type identifier of the historical task is the type identifier of the task of the preset type.
Alternatively, the task type of the historical task may be represented by 0 and 1, where 0 may represent that the historical task is a non-predetermined type task, that is, the historical task is a non-substitute task, and 1 may represent that the historical task is a predetermined type task, that is, the historical task is a substitute task. Thus, the server may determine the historical tasks with the type identification of 1 as positive samples and the historical tasks with the type identification of 0 as negative samples.
It is easy to understand that the server may determine the sample set according to the historical task features and the type identifications corresponding to all the historical tasks, or may determine the sample set according to the historical task features and the type identifications corresponding to part of the historical tasks, which is not limited in this embodiment.
Step S303, training the probability prediction model according to the sample set until the loss function of the probability prediction model reaches the expectation.
In this step, the server may randomly divide the sample set into a training sample set and a testing sample set, where the training sample set and the testing sample set each include at least one training sample. And then, training the probability prediction model by taking the historical task characteristics of each historical task in the training sample set as input and the corresponding type identification as output. After the probability prediction model is trained based on the training sample set, the server may further obtain a corresponding output value (i.e., a predicted value) based on the probability prediction model by using the historical task feature of at least one historical task in the test sample set as an input, so as to determine an error value of the classification model according to the output value and the type identifier of the at least one historical task, so as to determine whether the loss function reaches an expectation. It is easy to understand that different probability prediction models have different loss functions, and therefore, different error values are determined.
Fig. 5 is a data flow diagram for acquiring the target probability of the task to be processed by the method according to the first embodiment of the present invention. As shown in fig. 5, in this embodiment, the server may obtain task features 51 of the task to be processed, which may specifically include a start position, an end position, a start time, and the like of the task to be processed, then analyze the task features 51, and obtain feature representations 52, which may specifically include an embedded vector corresponding to the start position, an embedded vector corresponding to the end position, and a vector corresponding to the start time. Similarly, the server may simultaneously obtain the user characteristics 53 of the target user, which may specifically include the historical behavior characteristics of the target user and the user portrait data, and then parse the task characteristics 53 to obtain the feature representation 54, which may specifically include a vector corresponding to the historical behavior characteristics and a vector corresponding to the user portrait data. Further, the server may stitch the feature representation 52 and the feature representation 54 to obtain a feature representation 55, and then input the feature representation 55 into a probability prediction model 56 to obtain a target probability 57 of the task to be processed.
Step S203, responding to the target probability meeting the predetermined probability condition, and sending a predetermined message to the task issuing terminal.
In this step, if the target probability of the task to be issued meets the predetermined probability condition, it indicates that the task to be issued has a high possibility of being a predetermined type of task, so the server may send a predetermined message to the task issuing terminal of the task to be issued to prompt the task risk of the task to be issued. The predetermined message may be "there may be a risk of using a car in the current mode, please use the call-over function".
Optionally, in this embodiment, the server may further modify a task publishing mode of the task to be published. The method of this embodiment may further include the steps of:
and S204, in response to the target probability meeting a preset probability condition, modifying the task issuing mode of the task to be issued into an issuing mode corresponding to a preset type.
If the target probability of the task to be issued meets the preset probability condition, the server can modify the task mode of the task to be issued into an issuing mode corresponding to the preset type. Optionally, the server may modify the task issuing mode of the task to be issued into the issuing mode corresponding to the predetermined type after receiving the feedback information, which is sent by the task issuing terminal and used for representing that the target user confirms the modification mode.
After the task features of the task to be issued and the user features of the task issuer are obtained, the target probability for representing that the task to be issued is the task of the preset type is obtained according to the task features of the task to be issued and the user features of the task issuer based on the pre-trained probability prediction model. And if the target probability meets a preset probability condition, sending a preset message to the task issuing terminal, wherein the preset message is used for prompting the risk of the task to be issued to the task issuer. The method of the embodiment can identify the possibility of risk of the task with higher accuracy before the task is published, so that the task publisher can be prompted in time.
Fig. 6 is a schematic diagram of a data processing apparatus according to a second embodiment of the present invention. As shown in fig. 6, the apparatus of the present embodiment includes a data acquisition unit 601, a probability prediction unit 602, and a message transmission unit 603.
The data obtaining unit 601 is configured to obtain task features of a task to be published and user data of a target user, where the target user is a user publishing the task to be published. The probability prediction unit 602 is configured to determine, based on a pre-trained probability prediction model, a target probability of the task to be issued according to the task features and the user data, where the target probability is used to represent a probability that the task to be issued is a predetermined type of task. The message sending unit 603 is configured to send a predetermined message to the task issuing terminal in response to that the target probability meets a predetermined probability condition, so as to prompt the risk of the task to be issued.
Further, the task features are used for representing real-time data of the task to be issued, and the user data are used for representing historical behaviors of the target user and a user portrait.
Further, the positive sample and the negative sample used for training the probability prediction model are determined according to a first movement track and a second movement track of a historical task, the first movement track is a movement track of a historical user corresponding to the historical task, and the second movement track is a movement track of task processing resources corresponding to the historical task.
Further, the model training unit 604 for training the probabilistic predictive model includes a task obtaining subunit, a set determining subunit, and a model training subunit.
The task obtaining subunit is used for obtaining a historical task set. The set determining subunit is configured to determine a sample set according to the historical task features of each historical task in the historical task set and the corresponding type identifier, where the type identifier is determined according to the first movement trajectory and the second movement trajectory. And the model training subunit is used for training the probability prediction model according to the sample set until a loss function of the probability prediction model reaches an expectation.
Further, the model training subunit comprises a set partitioning module, a model training module and a model detection module.
The set dividing module is configured to randomly divide the sample set into a training sample set and a testing sample set, where the training sample set and the testing sample set both include the historical task feature of at least one historical task and the corresponding type identifier. And the model training module is used for training the probability prediction model by taking each historical task characteristic in the training sample set as input and taking the corresponding type identifier as output. And the model detection module is used for taking at least one historical task feature in the test sample set as input, acquiring a corresponding output value based on the probability prediction model, and determining an error value according to the output value and the corresponding type identifier so as to judge whether the loss function achieves the expectation.
Further, the apparatus further comprises a mode modification unit 605.
The mode modifying unit 605 is configured to modify the task issuing mode of the task to be issued to an issuing mode corresponding to the predetermined type in response to that the target probability satisfies the predetermined probability condition.
After the task features of the task to be issued and the user features of the task issuer are obtained, the target probability for representing that the task to be issued is the task of the preset type is obtained according to the task features of the task to be issued and the user features of the task issuer based on the pre-trained probability prediction model. And if the target probability meets a preset probability condition, sending a preset message to the task issuing terminal, wherein the preset message is used for prompting the risk of the task to be issued to the task issuer. The device of the embodiment can identify the possibility of risk of the task with high accuracy before the task is published, so that the task publisher can be prompted in time.
Fig. 7 is a schematic view of an electronic device according to a third embodiment of the present invention. The electronic device shown in fig. 7 is a general-purpose data processing apparatus comprising a general-purpose computer hardware structure including at least a processor 701 and a memory 702. The processor 701 and the memory 702 are connected by a bus 703. The memory 702 is adapted to store instructions or programs executable by the processor 701. The processor 701 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 701 implements the processing of data and the control of other devices by executing commands stored in the memory 702 to thereby execute the method flows of the embodiments of the present invention as described above. The bus 703 connects the above components together, as well as connecting the above components to the display controller 704 and the display device and input/output (I/O) device 705. Input/output (I/O) devices 705 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, input/output (I/O) devices 705 are connected to the system through an input/output (I/O) controller 706.
The memory 702 may store, among other things, software components such as an operating system, communication modules, interaction modules, and application programs. Each of the modules and applications described above corresponds to a set of executable program instructions that perform one or more functions and methods described in embodiments of the invention.
The flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention described above illustrate various aspects of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
Also, as will be appreciated by one skilled in the art, aspects of embodiments of the present invention may be embodied as a system, method or computer program product. Accordingly, various aspects of embodiments of the invention may take the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a "circuit," module "or" system. Further, aspects of the invention may take the form of: a computer program product embodied in one or more computer readable media having computer readable program code embodied thereon.
Any combination of one or more computer-readable media may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of embodiments of the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to: electromagnetic, optical, or any suitable combination thereof. The computer readable signal medium may be any of the following computer readable media: is not a computer readable storage medium and may communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including: object oriented programming languages such as Java, Smalltalk, C + +, PHP, Python, and the like; and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package; executing in part on a user computer and in part on a remote computer; or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (14)
1. A method of data processing, the method comprising:
acquiring task characteristics of a task to be issued and user characteristics of a target user, wherein the target user is a user who issues the task to be issued;
based on a pre-trained probability prediction model, determining a target probability of the task to be issued according to the task characteristics and the user characteristics, wherein the target probability is used for representing the probability that the task to be issued is a task of a preset type;
and responding to the target probability meeting a preset probability condition, and sending a preset message to a task issuing terminal so as to prompt the risk of the task to be issued.
2. The method of claim 1, wherein the task features are used for characterizing real-time data of the task to be published, and the user features are used for characterizing historical behaviors and user portrayal of the target user.
3. The method according to claim 1, wherein the positive sample and the negative sample for training the probabilistic predictive model are determined according to a first movement track and a second movement track of a historical task, the first movement track is a movement track of a historical user corresponding to the historical task, and the second movement track is a movement track of a task processing resource corresponding to the historical task.
4. The method of claim 3, wherein the probabilistic predictive model is trained by:
acquiring a historical task set;
determining a sample set according to the historical task characteristics of each historical task in the historical task set, the corresponding historical user characteristics of the historical user and the type identifier, wherein the type identifier is determined according to the first moving track and the second moving track;
and training the probability prediction model according to the sample set until a loss function of the probability prediction model reaches an expectation.
5. The method of claim 4, wherein training the probabilistic predictive model based on the set of samples until a loss function of the probabilistic predictive model is expected comprises:
randomly dividing the sample set into a training sample set and a testing sample set, wherein the training sample set and the testing sample set both comprise the historical task features of at least one historical task and the corresponding type identifications;
training the probability prediction model by taking each historical task characteristic in the training sample set as input and the corresponding type identifier as output;
and taking at least one historical task feature in the test sample set as an input, acquiring a corresponding output value based on the probability prediction model, and determining an error value according to the output value and the corresponding type identifier so as to judge whether the loss function achieves the expectation.
6. The method of claim 1, further comprising:
and in response to the target probability meeting the preset probability condition, modifying the task issuing mode of the task to be issued into an issuing mode corresponding to the preset type.
7. A data processing apparatus, characterized in that the apparatus comprises:
the data acquisition unit is used for acquiring task characteristics of a task to be issued and user characteristics of a target user, wherein the target user is a user who issues the task to be issued;
the probability prediction unit is used for determining the target probability of the task to be issued according to the task characteristics and the user characteristics based on a pre-trained probability prediction model, wherein the target probability is used for representing the probability that the task to be issued is a task of a preset type;
and the message sending unit is used for responding to the condition that the target probability meets the preset probability, and sending a preset message to the task issuing terminal so as to prompt the risk of the task to be issued.
8. The apparatus of claim 7, wherein the task features are used for characterizing real-time data of the task to be published, and the user features are used for characterizing historical behaviors and user portrayal of the target user.
9. The apparatus of claim 7, wherein the positive sample and the negative sample for training the probabilistic predictive model are determined according to a first movement trajectory and a second movement trajectory of a historical task, the first movement trajectory is a movement trajectory of a historical user corresponding to the historical task, and the second movement trajectory is a movement trajectory of a task processing resource corresponding to the historical task.
10. The apparatus of claim 9, wherein the model training unit for training the probabilistic predictive model comprises:
the task acquisition subunit is used for acquiring a historical task set;
a set determining subunit, configured to determine a sample set according to history task features and corresponding type identifiers of each history task in the history task set, where the type identifiers are determined according to the first movement trajectory and the second movement trajectory;
and the model training subunit is used for training the probability prediction model according to the sample set until a loss function of the probability prediction model reaches an expectation.
11. The apparatus of claim 10, wherein the model training subunit comprises:
the set dividing module is used for randomly dividing the sample set into a training sample set and a testing sample set, wherein the training sample set and the testing sample set respectively comprise the historical task features of at least one historical task and the corresponding type identifications;
the model training module is used for training the probability prediction model by taking the characteristics of each historical task in the training sample set as input and the corresponding type identifier as output;
and the model detection module is used for taking at least one historical task feature in the test sample set as input, acquiring a corresponding output value based on the probability prediction model, and determining an error value according to the output value and the corresponding type identifier so as to judge whether the loss function achieves the expectation.
12. The apparatus of claim 7, further comprising:
and the mode modifying unit is used for modifying the task issuing mode of the task to be issued into the issuing mode corresponding to the preset type in response to the target probability meeting the preset probability condition.
13. A computer-readable storage medium on which computer program instructions are stored, which, when executed by a processor, implement the method of any one of claims 1-6.
14. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010988184.2A CN112116154B (en) | 2020-09-18 | 2020-09-18 | Data processing method, data processing device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010988184.2A CN112116154B (en) | 2020-09-18 | 2020-09-18 | Data processing method, data processing device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116154A true CN112116154A (en) | 2020-12-22 |
| CN112116154B CN112116154B (en) | 2024-05-14 |
Family
ID=73799820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010988184.2A Active CN112116154B (en) | 2020-09-18 | 2020-09-18 | Data processing method, data processing device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116154B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579910A (en) * | 2020-12-28 | 2021-03-30 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
| CN112633537A (en) * | 2020-12-24 | 2021-04-09 | 汉海信息技术(上海)有限公司 | Order processing method and device for taxi, and electronic equipment |
| CN113129114A (en) * | 2021-05-13 | 2021-07-16 | 北京大米科技有限公司 | Service recommendation method and device, readable storage medium and electronic equipment |
| CN113158415A (en) * | 2021-02-23 | 2021-07-23 | 电子科技大学长三角研究院(衢州) | Vehicle track similarity evaluation method based on error analysis |
| CN115455129A (en) * | 2022-10-14 | 2022-12-09 | 阿里巴巴（中国）有限公司 | POI processing method and device, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103312780A (en) * | 2013-05-13 | 2013-09-18 | 济南政和科技有限公司 | Cluster type information issuing method of portal website in county and municipal institutions |
| CN106845999A (en) * | 2017-02-20 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Risk subscribers recognition methods, device and server |
| US20180299284A1 (en) * | 2014-12-02 | 2018-10-18 | Kevin Sunlin Wang | Method and System For Avoidance of Accidents |
| CN109525487A (en) * | 2019-01-17 | 2019-03-26 | 深圳市沃特沃德股份有限公司 | Mission bit stream distribution method, device, readable storage medium storing program for executing and computer equipment |
| CN109741065A (en) * | 2019-01-28 | 2019-05-10 | 广州虎牙信息科技有限公司 | A kind of payment risk recognition methods, device, equipment and storage medium |
| US20190250893A1 (en) * | 2018-02-09 | 2019-08-15 | International Business Machines Corporation | Automated management of undesired code use based on predicted valuation and risk analysis |
| CN110175689A (en) * | 2018-11-29 | 2019-08-27 | 腾讯科技（深圳）有限公司 | A kind of method of probabilistic forecasting, the method and device of model training |
| CN110322055A (en) * | 2019-06-18 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of method and system improving data risk model scoring stability |
| CN110866664A (en) * | 2018-08-27 | 2020-03-06 | 中国石油化工股份有限公司 | Risk quantification control method and system for petrochemical production process |
| CN110909775A (en) * | 2019-11-08 | 2020-03-24 | 支付宝(杭州)信息技术有限公司 | Data processing method and device and electronic equipment |
| CN110930176A (en) * | 2019-09-23 | 2020-03-27 | 平安科技（深圳）有限公司 | Prediction method, prediction device, electronic device and storage medium |
-
2020
- 2020-09-18 CN CN202010988184.2A patent/CN112116154B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103312780A (en) * | 2013-05-13 | 2013-09-18 | 济南政和科技有限公司 | Cluster type information issuing method of portal website in county and municipal institutions |
| US20180299284A1 (en) * | 2014-12-02 | 2018-10-18 | Kevin Sunlin Wang | Method and System For Avoidance of Accidents |
| CN106845999A (en) * | 2017-02-20 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Risk subscribers recognition methods, device and server |
| US20190250893A1 (en) * | 2018-02-09 | 2019-08-15 | International Business Machines Corporation | Automated management of undesired code use based on predicted valuation and risk analysis |
| CN110866664A (en) * | 2018-08-27 | 2020-03-06 | 中国石油化工股份有限公司 | Risk quantification control method and system for petrochemical production process |
| CN110175689A (en) * | 2018-11-29 | 2019-08-27 | 腾讯科技（深圳）有限公司 | A kind of method of probabilistic forecasting, the method and device of model training |
| CN109525487A (en) * | 2019-01-17 | 2019-03-26 | 深圳市沃特沃德股份有限公司 | Mission bit stream distribution method, device, readable storage medium storing program for executing and computer equipment |
| CN109741065A (en) * | 2019-01-28 | 2019-05-10 | 广州虎牙信息科技有限公司 | A kind of payment risk recognition methods, device, equipment and storage medium |
| CN110322055A (en) * | 2019-06-18 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of method and system improving data risk model scoring stability |
| CN110930176A (en) * | 2019-09-23 | 2020-03-27 | 平安科技（深圳）有限公司 | Prediction method, prediction device, electronic device and storage medium |
| CN110909775A (en) * | 2019-11-08 | 2020-03-24 | 支付宝(杭州)信息技术有限公司 | Data processing method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 刘芳;蔡志平;肖侬;王志英;陈勇;: "基于神经网络的安全风险概率预测模型", 计算机科学, no. 12 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633537A (en) * | 2020-12-24 | 2021-04-09 | 汉海信息技术(上海)有限公司 | Order processing method and device for taxi, and electronic equipment |
| CN112579910A (en) * | 2020-12-28 | 2021-03-30 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
| CN113158415A (en) * | 2021-02-23 | 2021-07-23 | 电子科技大学长三角研究院(衢州) | Vehicle track similarity evaluation method based on error analysis |
| CN113129114A (en) * | 2021-05-13 | 2021-07-16 | 北京大米科技有限公司 | Service recommendation method and device, readable storage medium and electronic equipment |
| CN115455129A (en) * | 2022-10-14 | 2022-12-09 | 阿里巴巴（中国）有限公司 | POI processing method and device, electronic equipment and storage medium |
| CN115455129B (en) * | 2022-10-14 | 2023-08-25 | 阿里巴巴（中国）有限公司 | POI processing method, POI processing device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116154B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112116154B (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| Haq et al. | Comparing offline and online testing of deep neural networks: An autonomous car case study | |
| CN112116158B (en) | Data processing method, data processing apparatus, storage medium, and electronic device | |
| CN113240909A (en) | Vehicle monitoring method, equipment, cloud control platform and vehicle road cooperative system | |
| CN108416376B (en) | SVM-based logistics man-vehicle tracking monitoring management system and method | |
| CN110059894B (en) | Equipment state evaluation method, device, system and storage medium | |
| CN110929799B (en) | Method, electronic device, and computer-readable medium for detecting abnormal user | |
| CN110288995B (en) | Interaction method and device based on voice recognition, storage medium and electronic equipment | |
| CN109726655A (en) | Customer service evaluation method, device, medium and equipment based on Emotion identification | |
| CN109660533B (en) | Method and device for identifying abnormal flow in real time, computer equipment and storage medium | |
| CN112329963A (en) | Data processing method, data processing apparatus, storage medium, and electronic device | |
| CN114997414B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN113051911A (en) | Method, apparatus, device, medium, and program product for extracting sensitive word | |
| CN112579910A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN115994611A (en) | Training method, prediction method, device and storage medium for category prediction model | |
| CN109933926B (en) | Method and apparatus for predicting flight reliability | |
| CN113447037B (en) | Stroke yaw detection method and device | |
| CN115907898A (en) | Method for recommending financial products to reinsurance client and related equipment | |
| CN113496167B (en) | Method and device for determining movement track of target | |
| CN115439076A (en) | Vehicle state data processing method and device, electronic equipment and storage medium | |
| US20200312171A1 (en) | Systems and methods for dynamically detecting moving object trajectory conflict using estimated times of arrival | |
| CN114141236A (en) | Language model updating method and device, electronic equipment and storage medium | |
| CN113554062A (en) | Training method, device and storage medium of multi-classification model | |
| Huang et al. | Digital Twin Edge Services With Proximity-Aware Longitudinal Lane Changing Model for Connected Vehicles | |
| US11831531B2 (en) | Methods and systems for determining severity of disruptions in communication networks in non-homogenous environments |
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 |