CN116543770B - Method, device, equipment and storage medium for detecting span conflict - Google Patents
Method, device, equipment and storage medium for detecting span conflict Download PDFInfo
- Publication number
- CN116543770B CN116543770B CN202310819635.3A CN202310819635A CN116543770B CN 116543770 B CN116543770 B CN 116543770B CN 202310819635 A CN202310819635 A CN 202310819635A CN 116543770 B CN116543770 B CN 116543770B
- Authority
- CN
- China
- Prior art keywords
- driver
- conflict
- department
- keywords
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 11
- 230000007774 longterm Effects 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000007789 sealing Methods 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
Abstract
The application relates to a method, a device, equipment and a storage medium for detecting a ride control conflict. The main technical scheme comprises the following steps: obtaining driver line Cheng Luyin; performing voice recognition on driver Cheng Luyin and extracting feature keywords; matching the characteristic keywords with preset conflict keywords to obtain matched keywords; acquiring a weight value of a matching keyword; and calculating the department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflict according to the department-by-department conflict tendency score. According to the application, the acquired driver travel record is subjected to real-time voice recognition, and the characteristic keywords are timely matched with the preset conflict keywords, so that the driver conflict tendency is obtained, further the driver conflict is detected, the problem in the driver travel process is timely found, the emergency is conveniently treated, and further guarantee effect is provided for the safety of both drivers and passengers.
Description
Technical Field
The application relates to the technical field of driving, in particular to a method, a device, equipment and a storage medium for detecting a driver-to-driver conflict.
Background
With the continuous improvement of safety consciousness, drinking without driving has become a consensus, so that driving services are gradually known by the public. According to incomplete statistics of each-year driving service, the occurrence of traffic accidents caused by drunk driving exceeding 300 ten thousand causes can be avoided, and obviously, the driving has formed a new economic status and becomes an effective means for controlling drunk driving and reducing traffic safety accidents.
At present, the driving service is not formed into particularly perfect market and industry specifications in China, so the current situation of driver-to-driver conflict in the driving process is not clear. The driver-ride conflict refers to a conflict or tension between a driver-ride and a vehicle owner in the driving-ride service. The collision may be caused by special properties of the driving service, or may be caused by differences in culture, value, benefit and the like of both the driving driver and the vehicle owner, but for either reason, once the collision of the driver and the vehicle owner occurs, serious consequences may be caused.
As is well known, in the scene of the network about car, in order to detect the collision of the driver and the passenger, a related detection device is generally installed on the network about car, so as to further realize the detection of the collision of the driver and the passenger. However, in the scenario of the driving service, the owner of the vehicle does not have an obligation or desire to install the relevant detection device, and thus, the manner of installing the detection device is not applicable in the driving service. Of course, there are also conflicting problems that may exist by obtaining an assessment of the quality of service of the driver's representative instead of the driving service platform, or legal and safety problems that may exist in the representative driving service by means of some telephone interviews and expert consultations.
However, both the above-described methods based on quality of service evaluation and telephone interviews and expert consultations have drawbacks in that they are inferior in timeliness, cannot find problems in time, and cannot restrict the behavior of both drivers and passengers in time.
Disclosure of Invention
Based on the detection method, the device, the equipment and the storage medium for detecting the department-to-department conflict are provided, the department-to-department conflict is detected by calculating the department-to-department conflict tendency score, and the problem in the department-to-department conflict advancing process is found in time, so that the emergency is conveniently treated, and further guarantee effect is provided for the safety of the department-to-department parties.
In a first aspect, a method for detecting a span conflict is provided, the method comprising:
acquiring a driver travel Cheng Luyin, wherein the driver travel record is recorded when a driver drives a car to send the car to a destination;
performing voice recognition on driver Cheng Luyin and extracting feature keywords;
matching the characteristic keywords with preset conflict keywords to obtain matched keywords;
acquiring a weight value of a matching keyword;
and calculating the department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflict according to the department-by-department conflict tendency score.
According to one implementation manner in the embodiment of the application, the method for calculating the span conflict tendency score according to the matching keywords and the weight value and detecting the span conflict according to the span conflict tendency score comprises the following steps:
performing product operation on each matching keyword and the corresponding weight value to obtain each matching feature;
adding and calculating each matching characteristic score to obtain a department-multiplier conflict score;
adding the weight values to obtain weight scores;
dividing the department-multiplier conflict and the weight score to obtain department-multiplier conflict tendency score;
comparing the span conflict tendency with a preset tendency score;
and when the department and the department conflict tendency is larger than the preset tendency, determining that the department and the department conflict tendency exists between the two department and the department.
According to one possible implementation manner in the embodiment of the present application, when the collision tendency of the ride is greater than the preset tendency, the method further includes:
marking both sides of the driver and the passenger, and pushing a popup window to the terminals of both sides of the driver and the passenger;
and acquiring clicking results of both drivers and passengers on the popup window, and triggering control operation of both drivers and passengers according to the clicking results.
According to an implementation manner in the embodiment of the present application, the popup window includes a conflict button, and triggers a control operation for both sides of the driver and the passenger according to a click result, including:
When the clicking result is that any one of the both sides clicks the conflict button, performing responsibility judgment operation on the both sides according to a preset rule;
if the driver is judged to have responsibility, the history marking times of the driver are obtained;
if the historical marking times of the driver is 0 times, warning reminding control is carried out on the driver;
if the historical marking times of the driver is 1, short-term blocking control is carried out on the driver;
and if the historical mark times of the driver is 2 times, performing long-term control on the driver.
According to one implementation manner in the embodiment of the present application, the method further includes:
if the owner of the vehicle is judged to have responsibility, the history marking times of the owner of the vehicle are obtained;
comparing the historical marking times of the vehicle owners with preset marking times;
and when the historical marking times of the vehicle owners are larger than the preset marking times, pulling the vehicle owners into a blacklist.
According to an implementation manner in the embodiment of the application, the popup window further comprises a conflict-free button and a quick alarm button, and the control operation on both sides of the driver and passenger is triggered according to the clicking result, and further comprises:
when the clicking result is that both the driver and the passenger click the conflict-free button, removing the current marks of both the driver and the passenger;
When the clicking result is that any one of the driver and the passenger clicks the quick alarm button, the alarm telephone is automatically switched on, and the current position information of the driver and the passenger is automatically broadcasted.
According to one implementation manner in the embodiment of the present application, the method further includes:
monitoring a current journey order in real time, wherein the current journey order is an order sent by a car owner received by a driver through a terminal;
after the end of the current journey order is monitored, acquiring the end time of the current journey order;
judging the extension time of the current journey order according to the ending time, wherein the extension time is the continuous recording time after the current journey order is ended;
comparing the extension time with a preset delay time;
when the extension time is smaller than the preset delay time, continuing recording the current travel order and storing the current travel order to the cloud;
and when the extension time is longer than the preset delay time, ending the recording of the current journey order.
In a second aspect, there is provided a device for detecting a ride collision, the device comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a driver travel record, and the driver travel record is recorded in the process that a driver drives a car to send a main car to a destination;
The recognition module is used for carrying out voice recognition on the driver Cheng Luyin and extracting characteristic keywords;
the matching module is used for matching the characteristic keywords with preset conflict keywords to obtain matching keywords;
the second acquisition module is used for acquiring the weight value of the matching keyword;
and the detection module is used for calculating the department-multiplier conflict tendency score according to the matching keywords and the weight value and detecting department-multiplier conflicts according to the department-multiplier conflict tendency score.
In a third aspect, there is provided a computer device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores computer instructions executable by the at least one processor to enable the at least one processor to perform the method referred to in the first aspect above.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method referred to in the first aspect above.
According to the technical content provided by the embodiment of the application, the driver travel record is recorded in the process that a driver drives a car to send the car to a destination by acquiring the driver travel Cheng Luyin; performing voice recognition on driver Cheng Luyin and extracting feature keywords; matching the characteristic keywords with preset conflict keywords to obtain matched keywords;
Acquiring a weight value of a matching keyword; and calculating the department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflict according to the department-by-department conflict tendency score. According to the operation, the obtained driver travel record is subjected to real-time voice recognition, and the characteristic keywords are timely matched with the preset conflict keywords, so that the driver conflict tendency is obtained, the driver conflict is detected, the problem in the driver travel process is timely found, the emergency is conveniently treated, and further guarantee effect is provided for the safety of both drivers and passengers.
Drawings
FIG. 1 is an application environment diagram of a method for detecting a span conflict in one embodiment;
FIG. 2 is a flow chart of a method for detecting a span conflict in one embodiment;
FIG. 3 is a schematic flow chart of a method for detecting a span conflict in one embodiment;
FIG. 4 is a block diagram of a device for detecting a span conflict in one embodiment;
fig. 5 is a schematic structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The detection method of the span conflict provided by the application can be applied to an application environment shown in figure 1. Wherein the user terminal 102 communicates with the server 104 via a network. Specifically, the server 104 obtains the driver Cheng Luyin of the user terminal 102, and the driver travel record is a record recorded in the process that the driver drives the car to send the car to the destination; the server 104 performs voice recognition on the driver Cheng Luyin and extracts feature keywords; matching the characteristic keywords with preset conflict keywords to obtain matched keywords; acquiring a weight value of a matching keyword; and calculating the department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflict according to the department-by-department conflict tendency score. The user terminal 102 may be, but not limited to, a smart phone, a tablet computer, a portable wearable device, etc., the server 104 may be, but not limited to, a cloud server, and the server 104 may be implemented by a stand-alone server or a server cluster formed by a plurality of servers.
Fig. 2 is a flowchart of a method for detecting a span conflict according to an embodiment of the present application, where the method may be executed by the cloud server 104 in the application environment shown in fig. 1. As shown in fig. 2, the method may include the steps of:
Step 201: the driver line Cheng Luyin is obtained.
The driver travel record is recorded in the process that a driver drives to send a driver to a destination.
Here, the pilot driver and the car owner can install the pilot APP in advance, and can have the operation instruction of agreeing to record in the installation, and after the pilot driver and the car owner agree to record, in the follow-up pilot driving process, the pilot driver terminal can be in the state of recording all the time. Therefore, after the driver receives the order issued by the vehicle owner through the mobile phone terminal, the travel record can be acquired through the driver terminal APP in the process that the driver drives the vehicle to the destination, and is uploaded to the cloud server for storage in real time through the message transmission protocol, and the cloud server receives the driver Cheng Luyin acquired by the driver terminal APP. The message transmission protocol can be an mqtt protocol, which is a lightweight, simple, open and easy-to-implement message transmission protocol, is a client-server based message publish/subscribe transmission protocol, can be used for transmitting data among a plurality of devices, and works on the TCP/IP protocol family to realize data transmission on remote devices with lower hardware performance or worse network condition.
Step 203: the driver Cheng Luyin is subjected to voice recognition and feature keywords are extracted.
Here, the cloud server performs voice recognition on the driver Cheng Luyin through a voice recognition technology after receiving the driver travel record. The voice recognition technology can adopt a Google Assistant technology, the Google Assistant technology is mainly based on a Google voice recognition engine, can control the intonation of voice according to different situations, and generates a series of intonation words so that the voice becomes more natural. Therefore, high-accuracy recognition and voice synthesis of the driver and journey recording can be realized through the Google Assistant technology, more accurate feature keywords can be extracted, and the extracted feature keywords are persisted in an HBase database for storage. It should be noted that, since there may be multiple driving orders at the same time, one driving order corresponds to a set of feature keywords during storage.
Step 205: and matching the characteristic keywords with preset conflict keywords to obtain matched keywords.
The cloud server is preset with a conflict word stock, and a plurality of preset conflict keywords are arranged in the conflict word stock, wherein the preset conflict keywords comprise but are not limited to rough and curse human vocabulary, threat vocabulary and the like.
Here, based on the distributed task scheduling platform, the matching operation is performed every 30 seconds, that is, the feature keywords stored in the HBase database are matched with the preset conflict keywords in the conflict word stock, so as to obtain the matching keywords. For example, the preset conflict keywords in the conflict word library have "you move me again for trial" and the feature keywords stored in the HBase database also have the word, i.e. the matching is successful, so as to obtain the matching keywords "you move me again for trial". The distributed task scheduling platform can be xxl-job, xxl-job mainly comprises a scheduling center and an executor, is responsible for managing scheduling information, sends scheduling requests according to scheduling configuration, and does not bear business codes. By adopting the scheduling system, the system availability and stability of the whole cloud server can be improved, meanwhile, the performance of the scheduling system is not limited by a task module any more, and visual, simple and dynamic management scheduling information can be supported, including task creation, updating, deleting, task development, task alarming and the like.
Step 207: and obtaining a weight value of the matching keyword.
Here, corresponding weight values are preset for different matching keywords, and the staff preset different weight values in advance according to the conflict degree of the matching keywords. For example, the matching keywords are "how you do so" and "how you try me again", and it is obvious that the second matching keyword has a deeper degree of conflict, and the description has been put into operation, so the weight value of the second matching keyword will be set larger. It should be noted that, when the weight value is preset, the staff needs to ensure that the sum of the weight values is 1.
Step 209: and calculating the department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflict according to the department-by-department conflict tendency score.
The method comprises the steps of calculating a department-multiplier conflict tendency score according to a matching keyword and a weight value, and determining whether the department-multiplier conflict tendency exists between the department-multiplier and the user according to the size of the department-multiplier conflict tendency score after calculating the department-multiplier conflict tendency score so as to realize the detection of the department-multiplier conflict.
It can be seen that, according to the embodiment of the application, by acquiring the driver travel Cheng Luyin, the driver travel record is recorded when the driver drives the car to send the car to the destination; performing voice recognition on driver Cheng Luyin and extracting feature keywords; matching the characteristic keywords with preset conflict keywords to obtain matched keywords; acquiring a weight value of a matching keyword; and calculating the department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflict according to the department-by-department conflict tendency score. According to the operation, the obtained driver travel record is subjected to real-time voice recognition, and the characteristic keywords are timely matched with the preset conflict keywords, so that the driver conflict tendency is obtained, the driver conflict is detected, the problem in the driver travel process is timely found, the emergency is conveniently treated, and further guarantee effect is provided for the safety of both drivers and passengers.
In one embodiment, calculating a span conflict propensity score based on the matching keywords and the weight values, and detecting span conflicts based on the span conflict propensity score, comprises: performing product operation on each matching keyword and the corresponding weight value to obtain each matching feature; adding and calculating each matching characteristic score to obtain a department-multiplier conflict score; adding the weight values to obtain weight scores; dividing the department-multiplier conflict and the weight score to obtain department-multiplier conflict tendency score; comparing the span conflict tendency with a preset tendency score; and when the department and the department conflict tendency is larger than the preset tendency, determining that the department and the department conflict tendency exists between the two department and the department.
Here, since there may be a plurality of obtained matching keywords, product operation is performed on each matching keyword and the corresponding weight value to obtain each matching feature score, and sum operation is performed on each matching feature score to obtain the span conflict score. Assuming that the matching keywords have A1 and A2 … An respectively, the weight value corresponding to A1 is A1, the weight value corresponding to A2 is A2 … An is An, and the expression of S is as follows:
and adding the weight values to obtain a weight part, and assuming that the weight values are a1 and a2 … an, the weight part can be represented by W, and the expression of W is as follows:
W=a1+a2+…+an
Dividing the span conflict and the weight part to obtain a span conflict tendency part, and assuming that the span conflict tendency part is expressed by T, the expression of the T is as follows:
T= S/ W
comparing the department-multiplier conflict tendency with a preset tendency score, and determining the department-multiplier conflict tendency of the department-multiplier and the two parties when the department-multiplier conflict tendency score is larger than the preset tendency score.
The preset trend score is generally set to 0.6. Here, the tendency of the ride-on conflict is compared with the preset tendency score, namely, T is compared with 0.6, and when T is smaller than 0.6, no operation is performed, which means that the tendency of the ride-on conflict is basically not existed; when T is greater than or equal to 0.6, determining that the both sides of the ride have a ride conflict tendency.
According to the operation, the problem of the both sides of the driver is found in time by calculating the collision tendency score of the driver and the passenger when the collision tendency score of the driver and the passenger is larger than the preset tendency, so that the effect of further guaranteeing the safety of the both sides of the driver and the passenger is provided.
In one embodiment, when the ride-on conflict propensity score is greater than the preset propensity, the method further comprises: marking both sides of the driver and the passenger, and pushing a popup window to the terminals of both sides of the driver and the passenger; and acquiring clicking results of both drivers and passengers on the popup window, and triggering control operation of both drivers and passengers according to the clicking results.
After determining that the driver and the passenger have the collision and the tilting directions, the driver and the passenger can be marked, the popup window is pushed to the terminals of the driver and the passenger, the driver and the passenger can click after receiving the popup window, and the cloud server acquires the clicking results of the driver and the passenger on the popup window, so that the control operation of the driver and the passenger is conveniently triggered according to the clicking results. If both the driver and the passenger disappear in the popup window and the clicking operation is not performed, the default driver and the passenger have no conflict, and the marks of both the driver and the passenger are canceled.
After determining that the driver and the passenger have the driver and the passenger conflict, the operation also pushes the popup windows to the terminals of the driver and the passenger, and further controls the driver and the passenger by the clicking result of the driver and the passenger on the popup windows, so that misjudgment is avoided, and meanwhile, the safety of the driver and the passenger is ensured.
In one embodiment, triggering control operations on both sides of the driver and the passenger according to the clicking result comprises: when the clicking result is that any one of the both sides clicks the conflict button, performing responsibility judgment operation on the both sides according to a preset rule; if the driver is judged to have responsibility, the history marking times of the driver are obtained; if the historical marking times of the driver is 0 times, warning reminding control is carried out on the driver; if the historical marking times of the driver is 1, short-term blocking control is carried out on the driver; and if the historical mark times of the driver is 2 times, performing long-term control on the driver.
Here, the popup window includes a conflict button, and when the clicking result is that any one of the driver and the passenger clicks the conflict button, whether the driver clicks the conflict button or the vehicle owner clicks the conflict button, or both click the conflict button, the driver and the passenger perform the operation of judging the responsibility according to the preset rule. The preset rules comprise the recognition of the matching keywords which are spoken by the driver and the two parties, the severity of the matching keywords of the driver and the two parties, and the like.
In one implementation, if it is determined that the driver is responsible, the number of history marks of the driver is replaced; and if the historical marking times of the driver is 0 times, warning reminding control is carried out on the driver. Since the history marking number of the driver is 0, the history marking number is the first time, and the driver is possibly influenced by objective factors, so that the warning reminding control is only carried out on the driver.
In another implementation, if the number of history marks of the driver is 1, the short-term blocking control is performed on the driver. Here, if the number of history marks of the driver is 1, it is explained that it is possible that this driver is actually problematic, but not serious, and thus, short-term blocking control is performed thereon to show warning.
In another implementation, if the number of history marks of the driver is 2, the driver is subjected to long-term control. Here, if the number of history marks of the driver is 2, it is indicated that the driver has a serious problem subjectively, and is not suitable for the driver, so that the driver is directly subjected to long-term control.
After the fact that the driver is responsible is determined, the historical mark times of the driver are obtained, the driver is controlled to different degrees according to the historical mark times of the driver, and the situation that the driver is excessively light or excessively heavy is avoided due to one-time detection.
In one implementation, the method further comprises: if the owner of the vehicle is judged to have responsibility, the history marking times of the owner of the vehicle are obtained; comparing the historical marking times of the vehicle owners with preset marking times; and when the historical marking times of the vehicle owners are larger than the preset marking times, pulling the vehicle owners into a blacklist.
Wherein the preset number of marks is generally set to 2.
Specifically, when the vehicle owner is judged to be responsible, the historical marking times of the vehicle owner can be obtained, the historical marking times of the vehicle owner are compared with 2 times, if the historical marking times of the vehicle owner are more than 2 times, the vehicle owner is pulled into a blacklist, and the vehicle owner is not provided with driving service. Here, since the current development is mainly directed to management control of a driver of a representative, management control of a vehicle owner is still further perfected.
According to the operation, when the vehicle owner is judged to be in responsibility, the historical marking times of the vehicle owner can also be obtained, and the vehicle owner is managed and controlled according to the historical marking times of the vehicle owner so as to further improve the management of the driving service.
In one implementation, triggering control operations on both sides of the driver and the passenger according to the clicking result, and further includes: when the clicking result is that both the driver and the passenger click the conflict-free button, removing the current marks of both the driver and the passenger; when the clicking result is that any one of the driver and the passenger clicks the quick alarm button, the alarm telephone is automatically switched on, and the current position information of the driver and the passenger is automatically broadcasted.
The popup window further comprises a conflict-free button and a quick alarm button.
In one implementation, when the clicking result is that both the driver and the passenger click the conflict-free button, the current marks of both the driver and the passenger are removed. Here, when the driver and the owner click the collision-free button, the description is that the driver and the owner are involved in some keywords, but the collision does not occur, and therefore, the current mark for the driver and the owner is removed.
In another implementation manner, when the clicking result is that any one of the driver and the passenger clicks the quick alarm button, the alarm telephone is automatically turned on, and the current position information of the driver and the passenger is automatically broadcasted. Here, when the clicking result is that any one of the driver and the passenger clicks the quick alarm button, that is, whether the driver clicks the quick alarm button or the car owner clicks the quick alarm button, or both the driver and the car owner clicks the quick alarm button, the current situation is severe, and the current position information of the driver and the passenger can be automatically communicated and broadcast, so that the police can go to.
When the clicking result is that both the driver and the passenger click the conflict-free button, the current marks of both the driver and the passenger are removed so as to avoid misjudgment; when the clicking result is that any one of the two parties clicks the quick alarm button, the alarm telephone is automatically switched on, so that the police can go to the alarm to stop in time, and further, the safety of the two parties is ensured.
In one embodiment, the method further comprises: monitoring a current journey order in real time; after the end of the current journey order is monitored, acquiring the end time of the current journey order; judging the extension time of the current journey order according to the ending time, wherein the extension time is the continuous recording time after the current journey order is ended; comparing the extension time with a preset delay time; when the extension time is smaller than the preset delay time, continuing recording the current travel order and storing the current travel order to the cloud; and when the extension time is longer than the preset delay time, ending the recording of the current journey order.
The current journey order is an order sent by a car owner received by a driver through a terminal; the extension time is the continuous recording time after the current journey order is ended; the preset delay time is typically set to 10 minutes.
Here, after the driver receives the order issued by the vehicle owner through the mobile phone terminal, the driver terminal or the cloud server monitors the current journey order in real time. After the end of the current journey order is monitored, acquiring the end time of the current journey order, judging the extension time of the current journey order according to the end time, namely, calculating the difference between the time at the moment and the end time of the current journey order to obtain the extension time of the recording.
In one implementation, the extension time is compared with a preset delay time, and when the extension time is less than the preset delay time, the current trip order is continuously recorded and stored to the cloud. Here, assuming that the end time of the current trip order is 12:08, at this time is 12:12 of the same day, it is seen that at this time, the current trip order is ended for 4 minutes, that is, the extension time is 4 minutes, and the 4 minutes and the 10 minutes are compared, and obviously, the 4 minutes are less than 10 minutes, so that the current trip order is continuously recorded and uploaded to the cloud for storage in real time. It is emphasized that the current travel order is recorded and then uploaded to the cloud end in real time for storage, voice recognition of the driver travel record is also performed in real time, and matching of the feature keywords and the preset conflict keywords is performed according to preset time intervals, so that the driver and passenger conflict can be detected in time in the process of the current travel order, and the endangered situation can be processed in time.
In another implementation, the extension time is compared with a preset delay time, and when the extension time is greater than the preset delay time, the recording of the current trip order is ended. Here, assuming that the end time of the current trip order is 12:08, which is 12:22 of the same day at this time, it can be seen that the end time of the current trip order is 14 minutes, i.e., the extension time is 14 minutes, and comparing 14 minutes with 10 minutes, it is obvious that 14 minutes is greater than 10 minutes, thus ending the recording of the current trip order.
Through the operation, the driver and passenger travel recording is not stopped immediately after the order is ended, but is ended after the preset delay time, so that the collision of the driver and passenger due to price or partial behaviors after the journey is ended is avoided, and the comprehensive detection of the collision of the driver and passenger is realized.
In connection with the implementation of the above embodiment, a preferred method flow provided by the embodiment of the present application is described below by way of example with reference to fig. 3. As shown in fig. 3, the method may include the steps of:
step S301, a driver Cheng Luyin is acquired.
In step S302, the driver Cheng Luyin is subjected to voice recognition, and feature keywords are extracted.
Step S303, matching the characteristic keywords with preset conflict keywords to obtain matched keywords.
Step S304, obtaining the weight value of the matching keyword.
And step S305, performing product operation on each matching keyword and the corresponding weight value to obtain each matching feature.
And step S306, adding the matched feature scores to obtain the span conflict score.
Step S307, adding the weight values to obtain a weight score.
Step S308, division operation is carried out on the department-multiplier conflict and the weight score to obtain department-multiplier conflict tendency score.
Step S309, comparing the riders collision tendency with the preset tendency.
In step S310, when the ride collision tendency score is greater than the preset tendency, it is determined that there is a ride collision tendency between the two sides.
Step S311, marking both drivers and passengers and pushing popup windows to terminals of both drivers and passengers; when the click result is that any one of the both sides clicks the conflict button, executing step S312; when the clicking result is that both sides of the driver and the passenger click the conflict-free button, executing step S313; when the quick alarm button is clicked by either one of the driver and the passenger as a result of the clicking, step S314 is executed.
Step S312, performing a responsibility judging operation on the driver and passenger according to a preset rule, and executing step S3121 if the responsibility of the driver is judged; if it is determined that the vehicle owner has responsibility, step S3122 is performed.
Step S3121, obtaining the history marking times of the substituted driver, and if the history marking times of the substituted driver are 0 times, executing step S31211; if the number of history marks of the driver is 1, step S31212 is performed; if the number of history marks of the driver is 2, step S31213 is performed.
Step S31211, warning and reminding control is performed for the driver of the driver.
Step S31212, short-term control of the driver is performed.
And step S31213, performing long-term control on the driver.
Step S3122, the number of history marks of the vehicle owner is obtained.
Step S3123, the historical marking times of the vehicle owner and the preset marking times are compared.
In step S3124, when the number of historical marks of the vehicle owner is greater than the preset number of marks, the vehicle owner is pulled into the blacklist.
Step S313 is executed to remove the current marks of both the driver and the passenger.
Step S314 is executed to automatically make an alarm call and automatically broadcast the current location information of both parties.
It should be understood that, although the steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited in the present application, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.
The method embodiment can be applied to various application scenes, for example, the application scenes can include but are not limited to the application scenes for detecting the conflict between the driver and the passenger.
Fig. 4 is a schematic structural diagram of a detection device for a driver-to-passenger collision according to an embodiment of the present application, where the device may be disposed in a cloud server in the system shown in fig. 1, so as to execute a method flow shown in fig. 2-3. As shown in fig. 4, the apparatus may include: a first acquisition module 401, an identification module 403, a matching module 405, a second acquisition module 407, and a detection module 409. The main functions of each component module are as follows:
a first obtaining module 401, configured to obtain a driver travel Cheng Luyin, where a driver travel record is a record recorded during a process of driving a driver to send a main vehicle to a destination;
the recognition module 403 is configured to perform voice recognition on the driver Cheng Luyin and extract feature keywords;
the matching module 405 is configured to match the feature keyword with a preset conflict keyword, so as to obtain a matching keyword;
a second obtaining module 407, configured to obtain a weight value of the matching keyword;
the detection module 409 is configured to calculate a span conflict tendency score according to the matching keyword and the weight value, and detect a span conflict according to the span conflict tendency score.
In one embodiment, the detection module 409 is further configured to:
performing product operation on each matching keyword and the corresponding weight value to obtain each matching feature;
adding and calculating each matching characteristic score to obtain a department-multiplier conflict score;
adding the weight values to obtain weight scores;
dividing the department-multiplier conflict and the weight score to obtain department-multiplier conflict tendency score;
comparing the span conflict tendency with a preset tendency score;
and when the department and the department conflict tendency is larger than the preset tendency, determining that the department and the department conflict tendency exists between the two department and the department.
In one embodiment, the apparatus is further for:
marking both sides of the driver and the passenger, and pushing a popup window to the terminals of both sides of the driver and the passenger;
and acquiring clicking results of both drivers and passengers on the popup window, and triggering control operation of both drivers and passengers according to the clicking results.
In one embodiment, the popup window includes a conflict button, the device further configured to:
when the clicking result is that any one of the both sides clicks the conflict button, performing responsibility judgment operation on the both sides according to a preset rule;
if the driver is judged to have responsibility, the history marking times of the driver are obtained;
if the historical marking times of the driver is 0 times, warning reminding control is carried out on the driver;
If the historical marking times of the driver is 1, short-term blocking control is carried out on the driver;
and if the historical mark times of the driver is 2 times, performing long-term control on the driver.
In one embodiment, the apparatus is further for:
if the owner of the vehicle is judged to have responsibility, the history marking times of the owner of the vehicle are obtained;
comparing the historical marking times of the vehicle owners with preset marking times;
and when the historical marking times of the vehicle owners are larger than the preset marking times, pulling the vehicle owners into a blacklist.
In one embodiment, the pop-up window further comprises a conflict-free button and a quick alarm button, the apparatus further being for:
when the clicking result is that both the driver and the passenger click the conflict-free button, removing the current marks of both the driver and the passenger;
when the clicking result is that any one of the driver and the passenger clicks the quick alarm button, the alarm telephone is automatically switched on, and the current position information of the driver and the passenger is automatically broadcasted.
In one embodiment, the apparatus is further for:
monitoring a current journey order in real time, wherein the current journey order is an order sent by a car owner received by a driver through a terminal;
after the end of the current journey order is monitored, acquiring the end time of the current journey order;
Judging the extension time of the current journey order according to the ending time, wherein the extension time is the continuous recording time after the current journey order is ended;
comparing the extension time with a preset delay time;
when the extension time is smaller than the preset delay time, continuing recording the current travel order and storing the current travel order to the cloud;
and when the extension time is longer than the preset delay time, ending the recording of the current journey order.
The same and similar parts of the above embodiments are all referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.
It should be noted that, in the embodiment of the present application, the use of user data may be involved, and in practical application, user specific personal data may be used in the schemes described herein within the scope allowed by applicable legal regulations under the condition that the applicable legal regulations of the country are met (for example, the user explicitly agrees, the user is explicitly notified, the user is explicitly authorized, etc.).
According to an embodiment of the present application, the present application also provides a computer device, a computer-readable storage medium.
As shown in fig. 5, is a block diagram of a computer device according to an embodiment of the present application. Computer equipment is intended to represent various forms of digital computers or mobile devices. Wherein the digital computer may comprise a desktop computer, a portable computer, a workstation, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet, a smart phone, a wearable device, etc.
As shown in fig. 5, the apparatus 500 includes a computing unit 501, a ROM 502, a RAM 503, a bus 504, and an input/output (I/O) interface 505, the computing unit 501, the ROM 502, and the RAM 503 being connected to each other through the bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The computing unit 501 may perform various processes in the method embodiments of the present application according to computer instructions stored in a Read Only Memory (ROM) 502 or computer instructions loaded from a storage unit 508 into a Random Access Memory (RAM) 503. The computing unit 501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. The computing unit 501 may include, but is not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), as well as any suitable processor, controller, microcontroller, etc. In some embodiments, the methods provided by embodiments of the present application may be implemented as a computer software program tangibly embodied on a computer-readable storage medium, such as storage unit 508.
RAM 503 may also store various programs and data required for the operation of device 500. Part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509.
An input unit 506, an output unit 507, a storage unit 508, and a communication unit 509 in the device 500 may be connected to the I/O interface 505. Wherein the input unit 506 may be such as a keyboard, mouse, touch screen, microphone, etc.; the output unit 507 may be, for example, a display, a speaker, an indicator light, etc. The device 500 can exchange information, data, and the like with other devices through the communication unit 509.
It should be noted that the device may also include other components necessary to achieve proper operation. It is also possible to include only the components necessary to implement the inventive arrangements, and not necessarily all the components shown in the drawings.
Various implementations of the systems and techniques described here can be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof.
Computer instructions for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer instructions may be provided to the computing unit 501 such that the computer instructions, when executed by the computing unit 501, such as a processor, cause the steps involved in the method embodiments of the present application to be performed.
The computer readable storage medium provided by the present application may be a tangible medium that may contain, or store, computer instructions for performing the steps involved in the method embodiments of the present application. The computer readable storage medium may include, but is not limited to, storage media in the form of electronic, magnetic, optical, electromagnetic, and the like.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (7)
1. A method for detecting a ride-on conflict, the method comprising:
acquiring a driver travel record, wherein the driver travel record is recorded in the process that a driver drives a car to send a main car to a destination;
Performing voice recognition on the driver Cheng Luyin and extracting feature keywords, wherein the voice recognition technology adopts a Google Assistant technology, the Google Assistant technology is based on a Google voice recognition engine, and the tone of voice is controlled according to different situations and a series of words of language are generated;
matching the characteristic keywords with preset conflict keywords to obtain matched keywords;
acquiring a weight value of the matching keyword;
calculating a department-by-department conflict tendency score according to the matching keywords and the weight value, and detecting department-by-department conflicts according to the department-by-department conflict tendency score;
when the collision tendency of the drivers and the passengers is detected, marking the drivers and the passengers and pushing a popup window to the terminals of the drivers and the passengers, wherein the popup window comprises a collision button;
acquiring clicking results of the popup window by the driver and the multiplier, and performing responsibility judgment operation on the driver and the multiplier according to a preset rule when any one of the driver and the multiplier clicks a conflict button;
if the driver is judged to be responsible, the history mark times of the driver are obtained;
if the historical mark times of the driver is 0 times, warning reminding control is carried out on the driver;
If the historical mark times of the driver is 1, short-term blocking control is carried out on the driver;
if the historical mark times of the driver is 2 times, performing long-term sealing control on the driver;
if the owner of the vehicle is judged to have responsibility, the history marking times of the owner of the vehicle are obtained;
comparing the historical marking times of the vehicle owners with preset marking times;
and when the historical marking times of the vehicle owners are larger than the preset marking times, pulling the vehicle owners into a blacklist.
2. The method of claim 1, wherein the calculating a ride-on-conflict propensity score based on the matching keyword and the weight value, and the detecting a ride-on-conflict based on the ride-on-conflict propensity score, comprises:
performing product operation on each matching keyword and a corresponding weight value to obtain each matching feature;
adding and calculating each matching characteristic score to obtain a department-multiplier conflict score;
adding the weight values to obtain weight scores;
dividing the department-multiplier conflict with the weight score to obtain department-multiplier conflict tendency score;
comparing the department-multiplier conflict tendency with a preset tendency score;
And when the department and the department conflict tendency is larger than the preset tendency, determining that the department and the department conflict tendency exists between the two department and the department.
3. The method of claim 1, wherein the pop-up window further comprises a conflict-free button and a quick alarm button, the method further comprising:
when the clicking result is that both the driver and the passenger click the conflict-free button, removing the current marks of both the driver and the passenger;
when the clicking result is that any one of the driver and the passenger clicks the quick alarm button, the alarm telephone is automatically switched on, and the current position information of the driver and the passenger is automatically reported.
4. A method according to any one of claims 1-3, characterized in that the method further comprises:
monitoring a current journey order in real time, wherein the current journey order is an order sent by a car owner received by a driver through a terminal;
after the current journey order is monitored to be ended, acquiring the ending time of the current journey order;
judging the extension time of the current journey order according to the ending time, wherein the extension time is the continuous recording time after the current journey order is ended;
comparing the extension time with a preset delay time;
When the extension time is smaller than the preset delay time, continuing recording the current travel order and storing the current travel order to a cloud;
and ending the recording of the current journey order when the extension time is longer than the preset delay time.
5. A device for detecting a ride-on conflict, the device comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a driver travel record, and the driver travel record is recorded in the process that a driver drives a car to send a main car to a destination;
the recognition module is used for carrying out voice recognition on the driver Cheng Luyin and extracting characteristic keywords, wherein the voice recognition technology adopts a Google Assistant technology, the Google Assistant technology is based on a Google voice recognition engine, the intonation of voice is controlled according to different situations, and a series of words of language are generated;
the matching module is used for matching the characteristic keywords with preset conflict keywords to obtain matching keywords;
the second acquisition module is used for acquiring the weight value of the matching keyword;
the detection module is used for calculating a department-multiplier conflict tendency score according to the matching keywords and the weight value and detecting department-multiplier conflicts according to the department-multiplier conflict tendency score;
The control module is used for marking the driver and the passenger and pushing a popup window to the terminals of the driver and the passenger when the driver and the passenger have a driver and passenger conflict tendency, wherein the popup window comprises a conflict button; acquiring clicking results of the popup window by the driver and the multiplier, and performing responsibility judgment operation on the driver and the multiplier according to a preset rule when any one of the driver and the multiplier clicks a conflict button; if the driver is judged to be responsible, the history mark times of the driver are obtained; if the historical mark times of the driver is 0 times, warning reminding control is carried out on the driver; if the historical mark times of the driver is 1, short-term blocking control is carried out on the driver; if the historical mark times of the driver is 2 times, performing long-term sealing control on the driver; if the owner of the vehicle is judged to have responsibility, the history marking times of the owner of the vehicle are obtained; comparing the historical marking times of the vehicle owners with preset marking times; and when the historical marking times of the vehicle owners are larger than the preset marking times, pulling the vehicle owners into a blacklist.
6. A computer device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores computer instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.
7. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310819635.3A CN116543770B (en) | 2023-07-05 | 2023-07-05 | Method, device, equipment and storage medium for detecting span conflict |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310819635.3A CN116543770B (en) | 2023-07-05 | 2023-07-05 | Method, device, equipment and storage medium for detecting span conflict |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116543770A CN116543770A (en) | 2023-08-04 |
| CN116543770B true CN116543770B (en) | 2023-09-22 |
Family
ID=87454564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310819635.3A Active CN116543770B (en) | 2023-07-05 | 2023-07-05 | Method, device, equipment and storage medium for detecting span conflict |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116543770B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109192215A (en) * | 2018-09-14 | 2019-01-11 | 上海头趣科技有限公司 | A kind of voice-based net about vehicle monitoring and managing method and system |
| CN109584008A (en) * | 2018-11-27 | 2019-04-05 | 重庆理工大学 | Net based on speech recognition about vehicle abnormal driving environment monitor system and method |
| CN111953789A (en) * | 2020-08-17 | 2020-11-17 | 广西云森科技有限公司 | Voice recognition-based network car booking abnormal driving environment monitoring system and method |
| CN112037818A (en) * | 2020-08-30 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | Abnormal condition determining method and forward matching formula generating method |
| CN112650825A (en) * | 2020-12-30 | 2021-04-13 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining abnormal drive receiving behavior, storage medium and electronic equipment |
| CN113470696A (en) * | 2021-07-01 | 2021-10-01 | 首约科技(北京)有限公司 | Method for solving driver and passenger safety and improving service quality through real-time audio stream analysis |
| CN114239887A (en) * | 2021-11-17 | 2022-03-25 | 上海赛可出行科技服务有限公司 | Safety grading in-vehicle driver and passenger conflict identification method |
| CN115858743A (en) * | 2022-11-08 | 2023-03-28 | 北京云行在线软件开发有限责任公司 | Weighting fusion information extraction method for network appointment vehicle driving and taking conversation risk control |
-
2023
- 2023-07-05 CN CN202310819635.3A patent/CN116543770B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109192215A (en) * | 2018-09-14 | 2019-01-11 | 上海头趣科技有限公司 | A kind of voice-based net about vehicle monitoring and managing method and system |
| CN109584008A (en) * | 2018-11-27 | 2019-04-05 | 重庆理工大学 | Net based on speech recognition about vehicle abnormal driving environment monitor system and method |
| CN111953789A (en) * | 2020-08-17 | 2020-11-17 | 广西云森科技有限公司 | Voice recognition-based network car booking abnormal driving environment monitoring system and method |
| CN112037818A (en) * | 2020-08-30 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | Abnormal condition determining method and forward matching formula generating method |
| CN112650825A (en) * | 2020-12-30 | 2021-04-13 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining abnormal drive receiving behavior, storage medium and electronic equipment |
| CN113470696A (en) * | 2021-07-01 | 2021-10-01 | 首约科技(北京)有限公司 | Method for solving driver and passenger safety and improving service quality through real-time audio stream analysis |
| CN114239887A (en) * | 2021-11-17 | 2022-03-25 | 上海赛可出行科技服务有限公司 | Safety grading in-vehicle driver and passenger conflict identification method |
| CN115858743A (en) * | 2022-11-08 | 2023-03-28 | 北京云行在线软件开发有限责任公司 | Weighting fusion information extraction method for network appointment vehicle driving and taking conversation risk control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116543770A (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112329963A (en) | Data processing method, data processing apparatus, storage medium, and electronic device | |
| CN113538963A (en) | Method, apparatus, device and storage medium for outputting information | |
| CN110533094B (en) | Evaluation method and system for driver | |
| CN110390813B (en) | Big data processing system based on vehicle type identification | |
| Kim et al. | Use of digital tachograph data to provide traffic safety education and evaluate effects on bus driver behavior | |
| US20200126385A1 (en) | Information processing apparatus, information processing system and information processing method | |
| CN116543770B (en) | Method, device, equipment and storage medium for detecting span conflict | |
| CN114093143A (en) | Vehicle driving risk perception early warning method and device | |
| CN111612200B (en) | Order security prediction method, device, server and storage medium | |
| Yarlagadda et al. | Heterogeneity in the Driver Behavior: An Exploratory Study Using Real‐Time Driving Data | |
| CN115936522A (en) | Vehicle stop station evaluation method, device, equipment and storage medium | |
| CN113065821B (en) | Vehicle allocation behavior early warning method, device, equipment and storage medium | |
| CN114445710A (en) | Image recognition method, image recognition device, electronic equipment and storage medium | |
| US20220404161A1 (en) | System for generating guidance information | |
| CN114626798A (en) | Task flow determination method and device, computer readable storage medium and terminal | |
| WO2023272833A1 (en) | Data detection method, apparatus and device and readable storage medium | |
| KR20210054109A (en) | Method and system for managing grade of risk alarm | |
| CN111611804A (en) | Danger identification method and device, electronic equipment and storage medium | |
| CN115440035B (en) | Traffic event early warning method and device, electronic equipment and storage medium | |
| Yawovi et al. | AiDashcam: A Vehicle Collision Responsibility Evaluation System Based on Object Detection and OpenStreetMap | |
| CN113947945B (en) | Vehicle driving alarm method and device, electronic equipment and readable storage medium | |
| CN114170030B (en) | Method, apparatus, electronic device and medium for remote damage assessment of vehicle | |
| CN112829751B (en) | Method and device for evaluating safety of vehicle state | |
| CN116721556B (en) | Vehicle management and control method, system, equipment and medium | |
| van Leeuwen et al. | Adopting ai to support situational awareness in emergency response: a reflection by professionals |
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 |