CN111582962A

CN111582962A - Service state identification method and device

Info

Publication number: CN111582962A
Application number: CN201910118176.XA
Authority: CN
Inventors: 郭瑞
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2019-02-15
Filing date: 2019-02-15
Publication date: 2020-08-25
Anticipated expiration: 2039-02-15
Also published as: CN111582962B

Abstract

The application provides a service state identification method and a service state identification device, wherein the method comprises the following steps: dividing the obtained running track of the target service provider into a plurality of track subsections, and determining the prediction probability that each track subsection of the target service provider is respectively marked as each service state; determining a plurality of service state sequences consisting of service states respectively corresponding to the track subsections; for each service state sequence, determining the matching probability of the driving track of the target service provider and the service state sequence based on the service state prediction probability of each track subsection of the target service provider, the total number of reference service providers and the number of reference service providers conforming to the service state sequence; and selecting a target service state sequence with matching probability meeting preset conditions, and determining the service state matched with the running track of the target service provider based on the service state of each track sub-segment in the target service state sequence so as to accurately identify the service state of the target service provider.

Description

Service state identification method and device

Technical Field

The application relates to the technical field of internet, in particular to a service state identification method and device.

Background

With the rapid development and popularization of the internet, various internet service products are also developed, such as taxi taking platforms. At present, a taxi taking platform becomes an important mode for public trip, and a passenger often reserves a taxi through the taxi taking platform to take a taxi.

For the taxi taking platform, the server of the taxi taking platform can receive a riding request of a passenger end, further generate a riding order and send the riding order to a driver end. However, some abnormal service states may occur during the process of executing the riding order at the driver end: one is a skip list state, namely, a driver end finishes a riding order in advance, but continues to provide riding service later, the cost of the riding service is privately settled between a passenger end and the driver end, and a skip single line is a trading behavior between the driver and the passenger seemingly, but actually, a platform for taking a car after skipping cannot monitor the subsequent behaviors of the driver and the passenger, so that huge potential safety hazards are brought; the other is a single-swiping state, the processes of sending a riding request by the passenger end, dispatching a riding order by the server and executing the riding order by the driver end are normal, but in fact, the driver end user and the passenger end user are the same person or related persons, so that the driver does not really provide riding service for the passenger end, which reduces the resource allocation efficiency between the vehicle and the passenger. However, the server cannot effectively identify the abnormal service state at present.

Disclosure of Invention

In view of this, an object of the present invention is to provide a method and an apparatus for identifying a service state, so that a server can effectively identify abnormal service states such as a skip list and a refresh list, and further improve security and resource allocation efficiency.

In a first aspect, the present application provides a service status identification method, including:

dividing the obtained driving track of the target service provider into a plurality of track subsections, and determining the prediction probability that each track subsection of the target service provider is respectively marked as each service state;

determining a plurality of service state sequences consisting of service states respectively corresponding to the track subsections;

for each service state sequence, determining the matching probability of the driving track of the target service provider and the service state sequence based on the prediction probability of the service state corresponding to each track sub-segment marked as the service state sequence by the target service provider, the total number of reference service providers and the number of reference service providers conforming to the service state sequence in the historical time period;

and selecting a target service state sequence with the matching probability meeting preset conditions from the multiple service state sequences, and determining the service state matched with the driving track of the target service provider based on the service state corresponding to each track subsection in the target service state sequence.

In a possible embodiment, the method further comprises:

acquiring order information of the target providing terminal;

the dividing of the acquired driving track of the target service provider into a plurality of track subsections comprises:

matching the running track of the target service provider with the running track corresponding to each service order in the order information, and determining a running track section and a tour track section in the running track of the target service provider;

dividing each single track segment into a plurality of track subsections, and dividing each tour track segment into a plurality of track segments.

In a possible implementation manner, after dividing the acquired driving trajectory of the target service provider into a plurality of trajectory subsections, the method further includes:

determining track information corresponding to each track sub-section, and determining order information corresponding to each track sub-section;

the determining the prediction probability that each track sub-segment of the target service provider is respectively marked as each service state comprises:

and for each track subsection, determining the prediction probability of each service state marked by the track subsection of the target service provider based on the track information and the order information of the target service provider corresponding to the track subsection, the reference track information and the reference order information of the reference service provider corresponding to the track subsection and a pre-trained service state prediction model.

In a possible embodiment, the track information includes at least one of the following information:

the position coordinates of each track point; driving through the time point of each track point; a running speed;

the order information includes at least one of the following information:

service provider information; service request side information; the starting time of the order; the duration of the order; an order travel route; an order starting location and a destination location.

In a possible embodiment, the determining a plurality of service state sequences composed of service states corresponding to the respective track subsections includes:

and randomly selecting one service state from the multiple service states corresponding to each track subsection, and forming a service state sequence by the service states corresponding to the selected track subsections.

In a possible embodiment, the determining, based on the predicted probability that the target service provider is marked as the service state corresponding to each track sub-segment in the service state sequence, the total number of reference service providers, and the number of reference service providers meeting the service state sequence in a historical time period, the matching probability of the driving track of the target service provider and the service state sequence includes:

determining the state transition probability of the service state sequence based on the total number of the reference service providing terminals and the number of the reference service providing terminals which accord with the service state sequence in the historical time period;

and multiplying the prediction probability of the service state corresponding to each track subsection with the state transition probability to obtain the matching probability of the running track of the target service providing end and the service state sequence.

In a possible embodiment, the determining the state transition probability of the service state sequence based on the total number of the reference service providers and the number of the reference service providers conforming to the service state sequence in the historical time period includes:

and determining the ratio of the number of the reference service providing terminals which accord with the service state sequence in the historical time period to the total number of the reference service providing terminals as the state transition probability of the service state sequence.

In a possible embodiment, the selecting a target service state sequence from a plurality of service state sequences, where the matching probability meets a preset condition, includes:

and selecting the target service state sequence with the highest matching probability from the plurality of service state sequences.

In a possible implementation manner, the service state includes an abnormal service state and a normal service state, and the abnormal service state is a list-refreshing state or a list-skipping state;

the determining the service state matched with the driving track of the target service provider based on the service state corresponding to each track sub-segment in the target service state sequence comprises:

determining the occurrence probability that the driving track of the target service providing end is marked as the abnormal service state based on the total number of the service states and the number of the abnormal service states included in the target service state sequence;

and if the occurrence probability is greater than a set threshold value, determining that the service state matched with the running track of the target service provider is an abnormal service state.

In a possible implementation manner, if it is determined that the service state matched with the driving track of the target service provider is an abnormal service state, the method further includes:

and sending prompt information for prompting the abnormal service state to the target service provider.

In a second aspect, the present application provides a service status identification apparatus, including:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a driving track of a target service provider and dividing the acquired driving track of the target service provider into a plurality of track subsections;

a prediction probability determination module, configured to determine a prediction probability that each track sub-segment of the target service provider is respectively marked as each service state;

the service state sequence determining module is used for determining a plurality of service state sequences consisting of service states respectively corresponding to the track subsections;

a matching probability determination module, configured to determine, for each service state sequence, a matching probability between a driving trajectory of the target service provider and the service state sequence based on a prediction probability that the target service provider is marked as a service state corresponding to each trajectory sub-segment in the service state sequence, a total number of reference service providers, and a number of reference service providers that meet the service state sequence in a historical time period;

and the service state determining module is used for selecting a target service state sequence with the matching probability meeting a preset condition from the multiple service state sequences, and determining a service state matched with the driving track of the target service provider based on the service state corresponding to each track sub-segment in the target service state sequence.

In one possible design, the obtaining module is further configured to:

acquiring order information of the target providing terminal;

the acquiring module, when dividing the acquired driving track of the target service provider into a plurality of track subsections, is specifically configured to:

In one possible design, the obtaining module is further configured to: determining track information corresponding to each track sub-section, and determining order information corresponding to each track sub-section;

the prediction probability determining module, when determining the prediction probability that each track sub-segment of the target service provider is respectively marked as each service state, is specifically configured to:

In one possible design, the trajectory information includes at least one of the following information:

the order information includes at least one of the following information:

In one possible design, when determining a plurality of service state sequences composed of service states corresponding to respective track subsections, the service state sequence determination module is specifically configured to:

In a possible design, the matching probability determining module, when determining the matching probability between the driving trajectory of the target service provider and the service state sequence based on the predicted probability that the target service provider is marked as the service state corresponding to each trajectory sub-segment in the service state sequence, the total number of reference service providers, and the number of reference service providers that meet the service state sequence in the historical time period, is specifically configured to:

In one possible design, when determining the state transition probability of the service state sequence based on the total number of the reference service providers and the number of the reference service providers conforming to the service state sequence in the historical time period, the matching probability determination module is specifically configured to:

In one possible design, when the target service state sequence with the matching probability meeting the preset condition is selected from multiple service state sequences, the service state determination module is specifically configured to:

In one possible design, the service state includes an abnormal service state and a normal service state, and the abnormal service state is a list-swiping state or a list-jumping state;

the service state determination module, when determining a service state matched with the driving trajectory of the target service provider based on the service state corresponding to each trajectory sub-segment in the target service state sequence, is specifically configured to:

In one possible design, the apparatus further includes:

and the sending module is used for sending prompt information for prompting the abnormal service state to the target service provider after determining that the service state matched with the driving track of the target service provider is the abnormal service state.

In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the processor and the memory communicate with each other through the bus, and the machine-readable instructions are executed by the processor to perform the steps of the service state identification method according to the first aspect or any one of the possible implementation manners of the first aspect.

In a fourth aspect, this application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the service state identification method in the first aspect or any one of the possible implementation manners of the first aspect are performed.

In the embodiment of the application, the matching probability of the running track of the target service provider and the service state sequence is determined through the service state prediction probability corresponding to each track sub-segment of the target service provider, the total number of the reference service providers and the number of the reference service providers which accord with the service state sequence in a historical time period, the target service state sequence is screened out according to the matching probability, and the service state of the whole running track can be determined according to the service state of each track sub-segment in the target service state sequence. By adopting the mode, the service state predicted by the target service provider in each track subsection and the overall situation of the service state of other reference service providers in the whole travel track are combined, compared with the prior art, the identification process of the service state of the target service provider considers more comprehensive factors not only for the local situation of the service state of the target service provider but also the overall situation of the service state of other reference service providers in the travel track, so that the service state of the target service provider in the whole travel track can be accurately identified, the abnormal service state of the target service provider can be effectively identified, and the safety and the service resource allocation efficiency in the service process are improved.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

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 it will be apparent to those skilled in the art that other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a block diagram of a service system provided by some embodiments of the present application;

fig. 2 is a flowchart illustrating a service status identification method provided by an embodiment of the present application;

fig. 3 is another flowchart illustrating a service status identification method provided by an embodiment of the present application;

fig. 4 is a flowchart illustrating a specific preprocessing procedure in a service status identification method according to an embodiment of the present application;

fig. 5 is a flowchart illustrating a specific implementation process of a matching probability determination method in a service state identification method according to an embodiment of the present application;

fig. 6 is a schematic structural diagram illustrating a service status identification apparatus provided in an embodiment of the present application;

fig. 7 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, 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 should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, 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.

To enable those skilled in the art to utilize the present disclosure, the following embodiments are presented in conjunction with a specific application scenario, "a taxi hiring scenario". 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 an online taxi hiring scenario, it should be understood that this is merely one exemplary embodiment. The method and the device can be applied to any other transportation types or other service scenes, such as online meal ordering scenes and the like.

The terms "passenger side," "service requester terminal" are used interchangeably in this application to refer to an individual, entity or tool that can request or subscribe to a service. The terms "driver side," "service provider side," and "service provider terminal" are used interchangeably in this application to refer to an individual, entity, or tool that can provide a service.

It is worth noting that before the application is filed, the service system is difficult to identify the service state of the target service provider, so that the abnormal service state which may occur at the target service provider cannot be effectively identified, and further, the security in the service process is difficult to be ensured or the service resource configuration is unreasonable. For the problem, in this embodiment, the matching probability between the running track of the target service provider and the service state sequence is determined according to the service state prediction probability corresponding to each track sub-segment of the target service provider, the total number of the reference service providers, and the number of the reference service providers which accord with the service state sequence in the historical time period, and then the target service state sequence is screened out according to the matching probability, so that the service state of the whole running track can be determined according to the service state of each track sub-segment in the target service state sequence.

By adopting the mode, the service state predicted by the target service provider in each track subsection and the overall situation of the service state of other reference service providers in the whole travel track are combined, so that not only the local situation of the service state of the target service provider but also the overall situation of the service state of other reference service providers in the travel track is considered, and more comprehensive factors are considered in the identification process of the service state of the target service provider, so that the service state of the target service provider in the whole travel track can be accurately identified, the abnormal service state of the target service provider can be effectively identified, and the safety and the service resource allocation efficiency in the service process are improved.

Before introducing the service state identification method provided by the present application, an exemplary description will be given of a service system to which the present application is applicable. Referring to fig. 1, a block diagram of a service system provided in some embodiments of the present application is shown. For example, the service system may be an online transportation service platform for transportation services such as taxi cab, designated drive service, express, carpool, bus service, driver rental, or regular service, or any combination thereof. The service system may include one or more of a server 110, a network 120, a service requester terminal 130, a service provider terminal 140, and a database 150, and the server 110 may include a processor therein to perform an instruction operation.

In some embodiments, the server 110 may be a single server or a group of servers. The set of servers can be centralized or distributed (e.g., the servers 110 can be a distributed system). In some embodiments, the server 110 may be local or remote to the terminal. For example, the server 110 may access information and/or data stored in the service requester terminal 130, the service provider terminal 140, or the database 150, or any combination thereof, via the network 120. As another example, the server 110 may be directly connected to at least one of the service requester terminal 130, the service provider terminal 140, and the database 150 to access stored information and/or data.

In some embodiments, the server 110 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. For example, the processor may predict the service state of the service provider terminal 140 and the like based on the travel track and order information and the like acquired from the service provider terminal 140.

Network 120 may be used for the exchange of information and/or data. In some embodiments, one or more components in the service system 100 (e.g., the server 110, the service requester terminal 130, the service provider terminal 140, and the database 150) may send information and/or data to other components over the network 120. For example, the server 110 may acquire a travel track or order information or the like from the service provider terminal 140 via the network 120. In some embodiments, the network 120 may be any type of wired or wireless network, or combination thereof.

In some embodiments, the service requester terminal 130 may comprise a mobile device, a tablet computer, a laptop computer, or a built-in device in a motor vehicle, etc., or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof.

In some embodiments, the service provider terminal 140 may be a similar or identical device as the service requestor terminal 130. In some embodiments, the service provider terminal 140 may be a device with location technology for locating the location of the service provider and/or the service provider terminal. In some embodiments, the service requester terminal 130 and/or the service provider terminal 140 may communicate with other locating devices to determine the location of the service requester, service requester terminal 130, service provider, or service provider terminal 140, or any combination thereof.

Database 150 may store data and/or instructions. In some embodiments, the database 150 may store data obtained from the service requester terminal 130 and/or the service provider terminal 140. In some embodiments, database 150 may store data and/or instructions for the exemplary methods described herein.

In some embodiments, a database 150 may be connected to the network 120 to communicate with one or more components in the service system 100 (e.g., the server 110, the service requester terminal 130, the service provider terminal 140, etc.). One or more components in the service system 100 may access data or instructions stored in the database 150 via the network 120. In some embodiments, the database 150 may be directly connected to one or more components in the service system 100 (e.g., the server 110, the service requestor terminal 130, the service provider terminal 140, etc.); alternatively, in some embodiments, database 150 may also be part of server 110.

The service state identification method provided by the present application is described in detail with reference to the above application background and the related description of the service system.

The first embodiment is as follows:

referring to fig. 2, a schematic flow chart of a service state identification method provided in an embodiment of the present application is shown, where the service state identification method may be executed by a server in the service system of fig. 1, and a specific execution process includes the following steps:

step S201, dividing the acquired driving track of the target service provider into a plurality of track subsections, and determining a prediction probability that each track subsection of the target service provider is respectively marked as each service state.

It should be noted that the travel track may be a travel track of the target service provider in the target time period. Specifically, after acquiring a driving track of a target service providing end in a target time period, a server divides the driving track into a plurality of track sub-segments, and then determines the prediction probability that each track sub-segment in the track sub-segments is respectively marked as each service state.

In one example, the service state includes a normal service state and an abnormal service state, and the abnormal service state includes, for example, a skip list state, a refresh list state, and the like. Correspondingly, the determined prediction probability may include a probability that the target service provider is in a normal service state and a probability that the target service provider is in an abnormal service state in the driving process of a certain track sub-segment.

In this embodiment, the prediction probability may be calculated by the server through a service state prediction model trained in advance. The service state prediction model is, for example, a Gradient Boosting Decision Tree (GBDT) model, or other machine learning models. In an example, the server may calculate, by using the GBDT model, a probability that the target service provider is in a normal service state and a probability that the target service provider is in an abnormal service state in each track sub-segment.

Of course, the sum of the prediction probability of the normal service state and the prediction probability of the abnormal service state in one track sub-segment is not necessarily 100%, and there is a possibility that the predicted result also includes states such as "incomplete", "indeterminable", and the like.

For example, the GBDT model outputs a predicted probability of a normal service state of 30% and a predicted probability of an abnormal service state of 60%, where the remaining 10% is the service state for "incomplete" and/or "indeterminate" situations.

Step S202, determining a plurality of service state sequences formed by service states respectively corresponding to the track subsections.

In this embodiment, each track sub-segment may correspond to two different service states, i.e., a normal service state or an abnormal service state, and the number of the track sub-segments divided in step S201 is multiple, so that the track sub-segments may form multiple different service state sequences.

For example, the driving track of the target service provider in the target time period is divided into three track subsections A, B, C, and for the three track subsections A, B, C, the plurality of service state sequences include: "a normal service state-B normal service state-C normal service state", "a abnormal service state-B abnormal service state-C abnormal service state", "a normal service state-B normal service state-abnormal service state", "a normal service state-B abnormal service state-C abnormal service state", "a abnormal service state-B normal service state-C normal service state", "a abnormal service state-B abnormal service state-C abnormal service state", "a abnormal service state-B abnormal service state-C normal service state", "a normal service state-B abnormal service state-C normal service state", "a abnormal service state-B normal service state-C abnormal service state", and "eight service state sequences in total.

Step S203, aiming at each service state sequence, determining the matching probability of the running track of the target service provider and the service state sequence based on the prediction probability of the service state corresponding to each track sub-segment marked in the service state sequence by the target service provider, the total number of the reference service providers and the number of the reference service providers conforming to the service state sequence in the historical time segment.

For each service state sequence in step S202, the matching probability that the whole travel trajectory composed of a plurality of trajectory sub-segments can be matched with the service state sequence is determined by using the two different service state prediction probabilities corresponding to each trajectory sub-segment in step S201, the total number of other reference service providers that also pass through the trajectory sub-segment, and the number of reference service providers that meet the service state sequence in the reference service providers. Wherein the reference service providers pass through the track sub-segments in the historical time period before the target time period.

Of course, the reference service providers may also include the target service provider. It can be understood that, if the target service provider has also passed through the track sub-segment in the historical time period before the target time period, the target service provider is taken as one of the plurality of reference service providers.

In this step, it can also be understood that the above-mentioned values such as the probability and the number (i.e. the service state prediction probability corresponding to each track sub-segment, the total number of other reference service providers that have passed through the track sub-segment, and the number of reference service providers that meet the service state sequence in these reference service providers) are taken into consideration in the process of determining the matching probability. For example, the values may be extracted at a certain ratio and then the matching probability may be calculated by a probability calculation such as multiplication and/or addition.

For example, the traveling track of the target service provider in the target time segment is divided into A, B, C three track subsections, that is, the target service provider passes through A, B, C three track subsections in the target time segment, and through step S201, six probabilities are determined, that the probability value of the target service provider in the normal service state during the traveling of the segment a is a1 and the probability value of the target service provider in the abnormal service state is a2, the probability value of the target service provider in the normal service state during the traveling of the segment B is B1 and the probability value of the target service provider in the abnormal service state is B2, and the probability value of the target service provider in the normal service state during the traveling of the segment C is C1 and the probability value of the target service provider in the abnormal service state is C2. It is known that, in a historical period before a target period, the total number of reference service providers traveling from the a subsegment to the B subsegment is i, wherein the number of reference service providers meeting "a abnormal service state — B normal service state" is j, wherein the number of reference service providers meeting "a abnormal service state — B abnormal service state" is k, the total number of reference service providers traveling from the B subsegment to the C subsegment in the historical period is x, wherein the number of reference service providers meeting "B normal service state — C abnormal service state" is y, and wherein the number of reference service providers meeting "B abnormal service state — C abnormal service state" is z.

If a certain service state sequence is 'A abnormal service state-B normal service state-C abnormal service state', the matching probability of the whole travel track of the target service provider in the target time period and the service state sequence 'A abnormal service state-B normal service state-C abnormal service state' is determined by using a2, B1, C2, i, j, x and y in the numerical values, namely, the numerical values a2, B1, C2, i, j, x and y are used as factors required by the process of determining the matching probability.

Similarly, if a certain service state sequence is "a abnormal service state-B abnormal service state-C abnormal service state", the matching probability of the overall travel track of the target service provider in the target time period and the service state sequence "a abnormal service state-B abnormal service state-C abnormal service state" is determined by using a2, B2, C2, i, k, x and z among the above numerical values, that is, the numerical values a2, B2, C2, i, k, x and z are used as factors required for the process of determining the matching probability.

And S204, selecting a target service state sequence with matching probability meeting preset conditions from the multiple service state sequences, and determining a service state matched with the driving track of the target service provider based on the service state corresponding to each track sub-segment in the target service state sequence.

In this step, a target service state sequence with a matching probability meeting a preset condition is selected from the service state sequences (for example, the eight service state sequences in step S202). For example, the preset condition may be a plurality of preset conditions, such as a target service state sequence with the maximum matching probability value, a target service state sequence with the matching probability value greater than a preset value, and the like. Accordingly, the sequence with the maximum matching probability can be selected from the service state sequences as the target service state sequence, and the sequence with the matching probability larger than a certain preset value can also be selected from the service state sequences as the target service state sequence.

In an embodiment, if the matching probability is in a numerical form, the matching probabilities of the multiple service state sequences may be directly compared, and the service state sequence with the maximum matching probability value is determined to be the target service state sequence, that is, the target service state sequence of the whole track segment to be recognized.

In another embodiment, the matching probability is represented in the form of a graph, for example, a line graph, and then the service state sequence with the maximum matching probability value can be found through the line graph, and the service state sequence with the maximum matching probability value is determined as a target service state sequence, that is, a target service state sequence of the whole track segment to be identified.

Then, according to whether the service state corresponding to each track sub-segment in the target service state sequence is abnormal or normal, the service state matched with the overall driving track before the track sub-segment is divided in step S201 is determined.

For example, in the service states corresponding to the track sub-segments, when the number of abnormal service states is greater than the number of normal service states, the overall service state matched with the overall driving track composed of the track sub-segments may be determined to be the abnormal service state. For example, assuming that the target service state sequence is "a normal service state-B abnormal service state-C abnormal service state-D normal service state-E abnormal service state-F abnormal service state", where the number of normal service states is 2, and the number of abnormal service states is 4, so that the number of abnormal service states is greater than the number of normal service states, it is determined that the overall service state matched by the overall driving trajectory composed of the trajectory sub-segments is the abnormal service state.

Of course, when the ratio of the number of abnormal service states in the service states corresponding to the track subsections exceeds a certain preset range, the overall service state matched with the overall driving track formed by the track subsections is determined to be the abnormal service state. For example, assuming that the preset range of the ratio of the number of abnormal service states is 80% to 100%, and the target service state sequence is "a normal service state-B abnormal service state-C abnormal service state-D normal service state-E abnormal service state", wherein the number of normal service states is 2, and the number of abnormal service states is 3, so that the ratio of the number of abnormal service states is 60%, and 60% is not within the preset range of 80% to 100%, it is determined that the overall service state matched by the overall driving trajectory composed of the trajectory sub-segments is the normal service state.

In addition, in the embodiment of the application, if the service state matched with the driving track of the target driver is determined to be the abnormal service state, prompt information for prompting the abnormal service state is sent to the target driver. Specifically, the server may send a prompt message to a target driver in an abnormal service state. For example, when the server recognizes that the target driver is in an abnormal service state or in an abnormal service state within a certain period of time before, the server pushes a message to the target driver end to prompt the target driver to stop the abnormal service state or avoid entering the abnormal service state later. For another example, when the server recognizes that the target driver is in the abnormal service state for a period of time longer than a preset period of time (for example, 1 week in 1 month, the target driver is in the abnormal service state), the order dispatch amount to the target driver may be reduced.

In this embodiment, the prediction probability obtained in step S201 is only the initial local prediction value, and is one of the multiple factors considered for determining the final overall probability in the subsequent step S203. Therefore, the matching probability of the driving track of the target service provider and the service state sequence is determined through the service state prediction probability corresponding to each track sub-segment of the target service provider, the total number of the reference service providers and the number of the reference service providers which accord with the service state sequence in the historical time period, the target service state sequence is screened out according to the matching probability, and the service state of the whole driving track can be determined according to the service state of each track sub-segment in the target service state sequence. By adopting the mode, the service states predicted by the target service provider in each track subsection and the overall situation of the service states of other reference service providers in the whole travel track are combined, compared with the prior art, the identification process of the service states of the target service provider considers more comprehensive factors not only for the local situation of the service states of the target service provider but also the overall situation of the service states of the other reference service providers in the travel track, so that the service states of the target service provider in the whole travel track can be accurately identified, the abnormal service states of the target service provider such as skip list and refresh list can be effectively identified, and the safety and the service resource allocation efficiency in the service process are improved.

Example two:

in the second embodiment, a specific process of service status identification is mainly described in detail. In the present embodiment, the target service provider is taken as a target driver, and the reference service provider is taken as a reference driver for example. Referring to fig. 3, a specific implementation process of the service status identification method includes the following steps:

step S301, the server acquires track information of the target driver driving in the target time period and order information of the target driver in the target time period.

The target time period may be a current time period, or may be a time period arbitrarily selected from previous time periods. Therefore, the track information and the order information in the target time period may be current track information and order information, or track information and order information in a certain time period in history, and the like. For example, the target time period may be within 5 hours from the current time to the time before the current time, may be within 24 hours of a day of the last month, or may be a target time period in various cases such as within one week of the current week.

The order information may include, among other things, driver information, passenger information, order start time, order duration, order route, order start location, and the like. This order information may be obtained directly from the database of the service system described above in connection with fig. 1.

It should be noted that the track information may include positioning data, time data, a driving route, a driving speed, a driving track, a stopping point information, and the like. The process of acquiring the trajectory information may be acquired through a Positioning System (e.g., Global Positioning System (GPS), beidou satellite navigation System, base station, satellite, etc.), various sensors (e.g., three-axis gyroscope, four-axis gyroscope, etc.), and a database of the service System described in fig. 1.

Step S302, the server matches the driving track in the target driver track information with the driving track corresponding to each service order in the order information to determine the running track section and the tour track section in the driving track of the target driver.

The process of this step can also be understood as a process in which the server preprocesses the driving track in the target driver track information, and as shown in fig. 4, a specific process of the preprocessing may include the following steps:

step S401, the server filters the positioned track data in the driving track to clear up the track data obviously wrong in the track.

For example, two sections of track data located far away in a short time, positioning data deviating from the overall track route, and the like may be obviously incorrect track data.

And S402, identifying the stopping section of the filtered driving track by the server.

In this step, the server detects the stopping area of the filtered driving track according to the driving speed of the target driver to obtain a plurality of stopping sections. For example, in the case that the driving speed of the target driver is lower than 120m per hour, it is determined that the target driver is located in a stopping section, where the information of the stopping section (including a stopping Point) may include environment information around the stopping section, Point of Interest (POI) (such as school, cell, gas station, restaurant, bus station, subway station, and the like), and a location of the stopping section, where the location may be one longitude and latitude data or an area surrounded by a plurality of longitude and latitude data.

Step S403, the server segments the filtered driving track by matching the driving track corresponding to each service order in the order information with the filtered driving track based on the information of the plurality of stay segments, so as to obtain a stay segment, a running order track segment, and a tour track segment.

In this step, when the driving trajectory is matched, the matching of the trajectory points may be performed, which may include the matching of the position coordinate points, or may include the matching of the time points. It should be noted that, in the matching process of the time points, the order information includes the execution time period of each service order, and then the time points in the execution time period of the service order and the time points passing through the track points in the travel track can be matched.

And S404, the server determines a track segment to be identified from the plurality of the separated running track segments and the plurality of tour track segments.

That is, the present embodiment mainly identifies the service state for the track segment to be identified. Of course, service state identification may also be performed on all the separated running route segments and all the separated tour route segments, that is, all the separated running route segments and all the separated tour route segments are taken as the track segments to be identified.

Step S405, the server matches the track segment to be recognized with the road network based on the road condition information and/or the road network information, so that the track segment to be recognized is matched to the most reasonable road.

The track segment to be identified can be matched to the most reasonable and most likely to travel on the road through the step, wherein the road matching method can comprise a road matching method based on the geographic position, a road matching method based on the topological structure, a road matching method based on the probability, a road matching method combining the methods and the like. In a possible implementation manner, as a preferable scheme, in the above step, a track segment to be identified is selected from the segmented running list track segment and tour track segment, and then only the road matching and subsequent processing procedures need to be performed on the track segment to be identified, thereby saving unnecessary calculation processing procedures.

It should be noted that the contents of the menu track segment and the patrol track segment are different, that is, the menu track segment is a process of executing an order by the target driver, and the patrol track segment is a process of not executing the order by the target driver, for example, a process of searching for the order while driving, or a process of going to a private destination of the target driver after finishing the order execution process. The order refreshing state means that the processes of sending a riding request by a passenger end, dispatching a riding order by a server and executing the riding order by a driver end are normal, but in fact, a user at the driver end and a user at the passenger end are the same person or related persons, so that the driver does not really provide riding service for the passenger end; the skip order state means that the driver end finishes the riding order in advance, but continues to provide the riding service later, and the cost of the riding service is privately settled between the passenger end and the driver end, for example, a target driver registers two or more riding platforms at the same time, listens to the order on the two or more riding platforms at the same time, and then selects one of the orders pushed by the platforms, which not only wastes the resources of the riding platforms, but also reduces the service efficiency of the riding platforms.

Thus, the swipe state in the abnormal service state is performed for the fraction of the running track, and the skip state in the abnormal service state is performed for the fraction of the patrol track. The running track segment and the tour track segment need to be distinguished due to different driving purposes and different service contents. By distinguishing the running order track section and the tour track section in the driving track, the following specific identification process is divided into two different preconditions of running order and tour, so that the subsequent processes of probability prediction, probability matching and the like of the track section to be identified are more targeted and more accurate.

After the preprocessing process in step S302 is completed, as shown in fig. 3, the following steps are continuously performed:

step S303, the server divides each matched ticker track segment into a plurality of track sub-segments, and divides each matched tour track segment into a plurality of track segments.

If all the separated running single track sections and all the patrol track sections are track sections to be identified, the server divides each matched running single track section into a plurality of track subsections and divides each matched patrol track section into a plurality of track sections.

Of course, if the track segment to be identified is only one or some of the driving tracks of all the separated running track segments and all the tour track segments, the server only divides the track segment to be identified into a plurality of track sub-segments.

For the specific process of dividing the track subsegments, the method of distance equal division and time equal division can be adopted, and the method of road network information matching and the like can also be adopted. Specifically, the server may divide the matched track segment to be identified according to the road name, the road distribution condition, and the region division condition in the road network information, so as to obtain a plurality of track subsections. The server can divide the matched track segment to be recognized into a plurality of track sub-segments according to a time equal division mode or a distance equal division mode. Of course, the server may also divide the matched track segment to be recognized into a plurality of track sub-segments according to a random division or equal division manner.

Step S304, the server determines track information corresponding to each track sub-segment and determines order information corresponding to each track sub-segment.

Wherein the order information comprises at least one of the following information: driver information, service requester information, order start time, order duration, order travel route, order start location, and destination location. The track information includes at least one of the following information: the position coordinates of each track point, the time point of driving through each track point and the driving speed. The driving speed may be an instantaneous speed of the track point or an average speed of the track subsections.

Step S305, aiming at each track sub-section, the server determines the prediction probability of the track sub-section of the target driver marked as each service state based on the track information and the order information of the target driver corresponding to the track sub-section, the reference track information and the reference order information of the reference driver corresponding to the track sub-section and a pre-trained service state prediction model.

In this step, the server may predict the probability of the abnormal service state of the target driver during the driving process corresponding to each track sub-segment by using a service state prediction model trained in advance, so as to obtain the prediction probability of each track sub-segment.

And S306, determining the matching probability of the running track of the target service provider and the service state sequence.

In a possible implementation manner, referring to fig. 5, a specific flowchart of the matching probability determining method provided in the embodiment of the present application is shown, where a specific implementation process of the matching probability determining method includes the following steps:

step S501, a service state is selected from a plurality of service states corresponding to each track sub-segment, and the service states corresponding to the selected track sub-segments form a service state sequence.

For example, if the plurality of track sub-segments is A, B, C, the plurality of service state sequences includes: "a normal service state-B normal service state-C normal service state", "a abnormal service state-B abnormal service state-C abnormal service state", "a normal service state-B normal service state-abnormal service state", "a normal service state-B abnormal service state-C abnormal service state", "a abnormal service state-B normal service state-C normal service state", "a abnormal service state-B abnormal service state-C abnormal service state", "a abnormal service state-B abnormal service state-C normal service state", "a normal service state-B abnormal service state-C normal service state", "a abnormal service state-B normal service state-C abnormal service state", and "eight service state sequences in total.

Step S502, aiming at each service state sequence, determining the state transition probability of the service state sequence based on the total number of reference drivers and the number of reference drivers in the historical time period, wherein the reference drivers are in line with the service state sequence.

In some embodiments, the ratio between the number of reference drivers that meet the sequence of service states over the historical period of time and the total number of reference drivers is determined as the state transition probability for the sequence of service states.

For example, also A, B, C are three trajectory subsections, it is known that the total number of reference drivers traveling from the a subsection to the B subsection is i, wherein the number of reference drivers complying with the "a abnormal service state — B normal service state" is j, wherein the number of reference drivers complying with the "a abnormal service state — B abnormal service state" is k, the total number of reference drivers traveling from the B subsection to the C subsection within the history period is x, wherein the number of reference drivers complying with the "B normal service state — C abnormal service state" is y, and wherein the number of reference drivers complying with the "B abnormal service state — C abnormal service state" is z.

If the service state sequence is "a abnormal service state-B normal service state-C abnormal service state", the state transition probability of the service state sequence includes: j/i and y/x; if the service state sequence is "a abnormal service state-B abnormal service state-C abnormal service state", the state transition probability of the service state sequence includes: k/i and z/x.

And S503, multiplying the predicted probability and the state transition probability of the service state corresponding to each track sub-segment to obtain the matching probability of the driving track of the target driver and the service state sequence.

Specifically, for each state sequence, the service state prediction probability corresponding to each track subsection in the state sequence is multiplied by the state transition probability to obtain the matching probability of the driving track of the target driver and the service state sequence, that is, the final overall probability that the service state of the target driver in the whole track subsection to be recognized conforms to the state sequence.

For example, A, B, C are the three trajectory subsections, six probabilities are determined by the above steps, wherein the probability that the service state of the target driver in the section a is 10% and the probability that the target driver is in the normal service state is 20%, the probability that the service state of the target driver in the section B is in the normal service state is 30% and the probability that the target driver is in the abnormal service state is 40%, and the probability that the service state of the target driver in the section C is in the normal service state is 50% and the probability that the target driver is in the abnormal service state is 60%. For a certain sequence of service states such as "a abnormal service state — B normal service state — C abnormal service state", it is assumed that the total number of reference drivers driven from a sub-segment to B sub-segment in the history period is 10, and wherein the number of reference drivers conforming to "a abnormal service state — B normal service state" is 7, it is assumed that the total number of reference drivers driven from B sub-segment to C sub-segment in the history period is 11, and wherein the number of reference drivers conforming to "B normal service state — C abnormal service state" is 8. The matching probability of the driving track of the target driver in the target time period and the service state sequence of "a abnormal service state-B normal service state-C abnormal service state" is: 10% × 20% × 30% × 7/10 × 8/11.

After the completion of step S306, as shown in fig. 3, the following steps are continued:

step S307 is to select a target service state sequence with the highest matching probability from the plurality of service state sequences.

In one possible embodiment, after the matching probability of the driving trajectory of the target driver to the service state sequence is obtained, the target service state sequence with the highest matching probability is selected from the service state sequences.

And step S308, determining the occurrence probability that the driving track of the target driver is marked as the abnormal service state based on the total number of the service states and the number of the abnormal service states included in the target service state sequence.

In some embodiments, in the target service state sequence, a ratio of the number of abnormal service states to the total number of service states, that is, an occurrence probability that the trajectory segment to be identified of the target driver is marked as an abnormal service state, is calculated.

Step S309 is to compare the occurrence probability with a set threshold value, and determine whether the occurrence probability is greater than the set threshold value. If yes, go to step S310; if not, step S311 is performed.

And step S310, determining that the service state matched with the driving track of the target driver is an abnormal service state.

And step 311, determining that the service state matched with the driving track of the target driver is a normal service state.

In practical application, aiming at a track segment to be identified of a target driver, if the track segment to be identified is a tour track segment, the abnormal service state is a skip state, namely the running state reported to a server by the target driver is a tour state, and the actual running state of the target driver is a skip state; if the track segment to be identified is the ticket running track segment, the abnormal service state is the ticket refreshing state, namely the running state reported to the server by the target driver is the ticket running state, and the actual running state of the target driver is the tour state.

Example three:

in the third embodiment, a service state prediction model trained in advance and a training process thereof are mainly described in detail.

In some embodiments, the pre-trained service state prediction model is a binary model, which may be any binary model, such as a GBDT model. Specifically, the server may input, to the pre-trained GBDT model, target driver order information and trajectory information corresponding to each trajectory sub-segment, reference trajectory information and reference order information of a reference driver corresponding to the trajectory sub-segment, road condition information, and road network information, to obtain a predicted probability that the driving process of the target driver corresponding to each trajectory sub-segment output by the GBDT model is in an abnormal service state and a predicted probability that the driving process of the target driver corresponding to the trajectory sub-segment is in a normal service state.

The reference trajectory information and the reference order information of the reference driver may be a travel trajectory in a target time period (for example, a current time period), may also be a travel trajectory in a historical time period before the target time period, and may also include the above two time periods at the same time.

In this embodiment, the reference trajectory information and the reference order information of the reference driver corresponding to the trajectory sub-segment may be obtained by all driver historical trajectory information and/or current trajectory information accumulated in the taxi taking platform database.

For the training mode of the service state prediction model trained in advance, the training process can be executed in the following mode:

firstly, a training sample set is obtained, wherein the training sample set comprises training sample information and service state labels respectively corresponding to different track subsections, and the training sample information comprises sample track information and sample order information of a sample driver, and sample reference track information and sample reference order information of a sample reference driver.

Then, training sample information corresponding to a plurality of track subsections is selected from the training sample set, then characteristic information of the training sample information corresponding to each track subsection is extracted, the extracted characteristic information is input into a service state prediction model to be trained, and prediction probability of each track subsection marked as each service state is output.

And then, based on the output prediction probability, determining a prediction service state corresponding to each track sub-segment, and calculating a loss value of the training process of the round based on the prediction service state and the service state label corresponding to each track sub-segment.

If the calculated loss value is larger than the set threshold value, adjusting model parameters of the service state prediction model to be trained, selecting training sample information corresponding to a plurality of track subsections from the training sample set again and executing the training process until the calculated loss value is not larger than the set threshold value; and if the calculated loss value is not greater than the set threshold value, determining that the service state prediction model to be trained is trained.

Example four:

based on the same technical concept as the above embodiment, a service state identification device corresponding to the service state identification method is also provided in the embodiment of the present application, and since the principle of solving the problem of the device in the embodiment of the present application is similar to that of the service state identification method in the embodiment of the present application, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

Referring to fig. 6, which is a schematic structural diagram of a service status identification apparatus provided in an embodiment of the present application, a service status identification apparatus 60 includes: an acquisition module 61, a prediction probability determination module 62, a service state sequence determination module 63, a matching probability determination module 64, and a service state determination module 65.

The obtaining module 61 is configured to obtain a driving track of the target service provider, and divide the obtained driving track of the target service provider into a plurality of track sub-segments. The prediction probability determination module 62 is configured to determine a prediction probability that each track sub-segment of the target service provider is respectively marked as each service state. The service state sequence determining module 63 is configured to determine a plurality of service state sequences composed of service states corresponding to the track subsections respectively.

The matching probability determination module 64 is configured to determine, for each service state sequence, a matching probability between the driving trajectory of the target service provider and the service state sequence based on the predicted probability that the target service provider is marked as the service state corresponding to each trajectory sub-segment in the service state sequence, the total number of reference service providers, and the number of reference service providers meeting the service state sequence in the historical time period.

The service state determining module 65 is configured to select a target service state sequence with a matching probability meeting a preset condition from the multiple service state sequences, and determine a service state matched with the driving trajectory of the target service provider based on the service state corresponding to each trajectory sub-segment in the target service state sequence.

In some embodiments, the obtaining module 61 is further configured to: and obtaining order information of the target providing terminal. When dividing the acquired driving track of the target service provider into a plurality of track subsections, the acquiring module 61 is specifically configured to: matching the running track of the target service provider with the running track corresponding to each service order in the order information, and determining a running track segment and a tour track segment in the running track of the target service provider; dividing each single track segment into a plurality of track subsections, and dividing each tour track segment into a plurality of track segments.

Furthermore, the obtaining module 61 is further configured to: determining track information corresponding to each track sub-section, and determining order information corresponding to each track sub-section. When determining the prediction probability that each track sub-segment of the target service provider is respectively marked as each service state, the prediction probability determination module 62 is specifically configured to: and for each track subsection, determining the prediction probability of each service state marked by the track subsection of the target service provider based on the track information and the order information of the target service provider corresponding to the track subsection, the reference track information and the reference order information of the reference service provider corresponding to the track subsection and a pre-trained service state prediction model.

Wherein the track information comprises at least one of the following information: the position coordinates of each track point, the time point of driving through each track point and the driving speed. The order information includes at least one of the following information: service provider information, service requester information, order start time, order duration, order travel route, order start location, and destination location.

When determining a plurality of service state sequences composed of service states respectively corresponding to the track subsections, the service state sequence determining module 63 is specifically configured to: and randomly selecting one service state from the multiple service states corresponding to each track subsection, and forming a service state sequence by the service states corresponding to the selected track subsections.

When determining the matching probability between the driving trajectory of the target service provider and the service state sequence based on the predicted probability that the target service provider is marked as the service state corresponding to each trajectory sub-segment in the service state sequence, the total number of reference service providers, and the number of reference service providers meeting the service state sequence in the historical time period, the matching probability determining module 64 is specifically configured to: and determining the state transition probability of the service state sequence based on the total number of the reference service providers and the number of the reference service providers which accord with the service state sequence in the historical time period. And multiplying the predicted probability and the state transition probability of the service state corresponding to each track subsection to obtain the matching probability of the running track of the target service providing end and the service state sequence.

When determining the state transition probability of the service state sequence based on the total number of the reference service providers and the number of the reference service providers conforming to the service state sequence in the historical time period, the matching probability determination module 64 is specifically configured to: and determining the ratio of the number of the reference service providers which accord with the service state sequence in the historical time period to the total number of the reference service providers as the state transition probability of the service state sequence.

When the target service state sequence with the matching probability meeting the preset condition is selected from the multiple service state sequences, the service state determining module 65 is specifically configured to: and selecting the target service state sequence with the highest matching probability from the plurality of service state sequences.

The service state comprises an abnormal service state and a normal service state, and the abnormal service state is a list refreshing state or a list jumping state. The service state determining module 65 is specifically configured to, when determining the service state matched with the driving track of the target service provider based on the service state corresponding to each track sub-segment in the target service state sequence: and determining the occurrence probability that the driving track of the target service providing end is marked as the abnormal service state based on the total number of the service states and the number of the abnormal service states included in the target service state sequence. And if the occurrence probability is greater than a set threshold value, determining that the service state matched with the driving track of the target service provider is an abnormal service state.

The service state identification means 60 further comprises: and the sending module 66 is configured to send prompt information for prompting that the abnormal service state occurs to the target service provider after determining that the service state matched with the driving track of the target service provider is the abnormal service state.

Example five:

the embodiment of the application also provides the electronic equipment. Referring to fig. 7, a schematic structural diagram of an electronic device 70 provided in the embodiment of the present application includes a processor 71, a memory 72, and a bus 73. The memory 72 is used for storing execution instructions, and includes a memory 721 and an external memory 722; the memory 721 is also referred to as an internal memory, and is used for temporarily storing the operation data in the processor 71 and the data exchanged with the external memory 722 such as a hard disk, the processor 71 exchanges data with the external memory 722 through the memory 721, and when the electronic device 70 operates, the processor 71 communicates with the memory 72 through the bus 73, so that the processor 71 executes the following instructions:

The specific processing flow of the processor 71 may refer to the descriptions of the embodiments corresponding to fig. 2 to fig. 5, and is not described herein again.

The electronic device provided by the application can combine the service state predicted by the target service provider in each track subsection and the overall situation of the service state of other reference service providers in the whole travel track, compared with the prior art, not only the local situation of the service state of the target service provider but also the overall situation of the service state of other reference service providers in the travel track section are considered, so that more comprehensive factors are considered in the identification process of the service state of the target service provider, the service state of the target service provider in the whole travel track can be accurately identified, the abnormal service states of the target service provider such as skip list and swipe list can be effectively identified, and the safety and the service resource allocation efficiency in the service process are improved.

Example six:

an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the service state identification method.

Specifically, the storage medium can be a general storage medium, such as a removable disk, a hard disk, and the like, and when a computer program on the storage medium is executed, the service state identification method can be executed to more accurately identify the service state of the target service provider in the whole travel track, so as to effectively identify abnormal service states of the target service provider, such as a skip order, a refresh order, and the like, thereby improving the security and the service resource allocation efficiency in the service process.

Based on the same technical concept, embodiments of the present application further provide a computer program product, which includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the service state identification method, and specific implementation may refer to the above method embodiments, and will not be described herein again.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on 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: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

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.

Claims

1. A service status identification method, comprising:

2. The method of claim 1, further comprising:

acquiring order information of the target providing terminal;

3. The method of claim 2, wherein after dividing the acquired travel track of the target service provider into a plurality of track subsections, further comprising:

4. The method of claim 3, wherein the trajectory information comprises at least one of:

the order information includes at least one of the following information:

5. The method of claim 1, wherein determining a plurality of service state sequences comprising service states corresponding to respective track subsegments comprises:

6. The method of claim 1, wherein determining the matching probability of the driving trajectory of the target service provider with the service state sequence based on the predicted probability that the target service provider is marked as the service state corresponding to each trajectory sub-segment in the service state sequence, the total number of reference service providers, and the number of reference service providers meeting the service state sequence in a historical time period comprises:

7. The method of claim 6, wherein determining the state transition probability for the service state sequence based on the total number of reference service providers and the number of reference service providers that fit the service state sequence in the historical time period comprises:

8. The method of claim 1, wherein the selecting the target service state sequence with the matching probability meeting a preset condition from the plurality of service state sequences comprises:

9. The method of claim 1 or 8, wherein the service state comprises an abnormal service state and a normal service state, the abnormal service state being a refresh state or a skip state;

10. The method of claim 9, wherein if it is determined that the service state matched with the driving trajectory of the target service provider is an abnormal service state, the method further comprises:

11. A service status recognition apparatus, comprising:

12. The apparatus of claim 11, wherein the obtaining module is further configured to:

acquiring order information of the target providing terminal;

13. The apparatus of claim 12, wherein the obtaining module is further configured to:

14. The apparatus of claim 13, wherein the trajectory information comprises at least one of:

the order information includes at least one of the following information:

15. The apparatus according to claim 11, wherein the service status sequence determining module, when determining a plurality of service status sequences including service statuses corresponding to the respective track subsections, is specifically configured to:

16. The apparatus as claimed in claim 11, wherein the matching probability determining module, when determining the matching probability between the driving trajectory of the target service provider and the service state sequence based on the predicted probability that the target service provider is marked as the service state corresponding to each trajectory sub-segment in the service state sequence, the total number of reference service providers, and the number of reference service providers conforming to the service state sequence in the historical time period, is specifically configured to:

17. The apparatus as claimed in claim 16, wherein the matching probability determining module, when determining the state transition probability of the service state sequence based on the total number of reference service providers and the number of reference service providers conforming to the service state sequence in the historical time period, is specifically configured to:

18. The apparatus of claim 11, wherein the service state determining module, when selecting the target service state sequence with the matching probability meeting the preset condition from the multiple service state sequences, is specifically configured to:

19. The apparatus of claim 11 or 18, wherein the service state comprises an abnormal service state and a normal service state, the abnormal service state being a refresh state or a skip state;

20. The apparatus of claim 19, wherein the apparatus further comprises:

21. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the service status identification method according to any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the service status identification method according to one of the claims 1 to 10.