CN110175218B

CN110175218B - Method, device and equipment for generating navigation broadcast content and computer storage medium

Info

Publication number: CN110175218B
Application number: CN201910300542.3A
Authority: CN
Inventors: 黄际洲; 张昊
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-04-15
Filing date: 2019-04-15
Publication date: 2020-08-28
Anticipated expiration: 2039-04-15
Also published as: CN110175218A

Abstract

The invention provides a method, a device, equipment and a computer storage medium for generating navigation broadcast contents, wherein the method comprises the following steps: determining an induction point in the current navigation route; acquiring broadcast materials and broadcast content templates of the guidance points in the navigation route; generating navigation broadcast contents of the induction points by using the broadcast materials and the broadcast content templates of the induction points; the broadcast materials of the induction points are obtained by mining from the network media information. The mode of broadcasting the material in order to generate the navigation and broadcast content of mining the guidance point from the network media information for its source of information of navigation and broadcast content is abundanter and comprehensive, and the content timeliness is higher, compares among the prior art through the mode update rate that the road network was gathered faster.

Description

Method, device and equipment for generating navigation broadcast content and computer storage medium

[ technical field ] A method for producing a semiconductor device

The present invention relates to the field of computer application technologies, and in particular, to a method, an apparatus, a device, and a computer storage medium for generating a navigation broadcast content.

[ background of the invention ]

This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

When people are unfamiliar with traffic regulations, road conditions and the like in the traveling process, accidents such as getting lost, accidents and violation of regulations can be caused. The navigation tool is used as an important auxiliary tool for people going out, and can prompt a user in time through navigation broadcasting modes such as texts, images and voice to guide the user to make correct judgment.

The existing navigation broadcasting contents are only limited to information collected by a road network, such as road traffic instructions, traffic restriction rules and the like, so that the broadcasting contents such as 'turning right at a front intersection', 'a camera is arranged at a position 100 meters ahead', and the like are very rigid.

[ summary of the invention ]

In view of this, the present invention provides a method, an apparatus, a device and a computer storage medium for generating navigation broadcast content, so as to provide users with richer and more flexible navigation broadcast content.

The specific technical scheme is as follows:

in one aspect, the present invention provides a method for generating a navigation broadcast content, the method including:

determining an induction point in the current navigation route;

acquiring broadcast materials and broadcast content templates of the guidance points in the navigation route;

generating navigation broadcast contents of the induction points by using the broadcast materials and the broadcast content templates of the induction points;

the broadcast materials of the induction points are obtained by mining from the network media information.

According to a preferred embodiment of the invention, the method further comprises:

when the user position reaches the broadcast position of the induction point, sending the navigation broadcast content of the induction point to the client; alternatively, the first and second electrodes may be,

and sending the navigation broadcast content of each induction point in the navigation route to the client so that the client broadcasts the navigation broadcast content of the induction point when the user position reaches the broadcast position of the induction point.

According to a preferred embodiment of the present invention, the acquiring the broadcast material and the broadcast content template of the guidance point in the navigation route includes:

inquiring broadcast materials of the induction points from a broadcast material library;

and inquiring the broadcast content template of the induction point from the broadcast template library.

According to a preferred embodiment of the present invention, the broadcast material of the induction point is mined in the following manner:

identifying text content of a route description class from the network media information;

acquiring text contents related to roads from the recognized text contents by utilizing a pre-established road dictionary;

and carrying out abstract extraction on the text content related to the road and matching the text content to the induction points to obtain the broadcast materials of the matched induction points.

According to a preferred embodiment of the present invention, the identifying the text content of the route description class from the network information published by the user includes:

recognizing the text content of the route description class from the network media information by utilizing a pre-established classification model;

and the classification model is obtained by training according to the pre-labeled route description text and the non-route description text.

According to a preferred embodiment of the present invention, the extracting the summary of the text content related to the road and matching the extracted summary to the guidance point to obtain the broadcast material of the matched guidance point includes:

abstracting the text content related to the road;

matching the extracted abstract content related to the road to an induction point on the road to obtain a broadcast material matched to the induction point;

and adding the broadcast materials of all the induction points into a broadcast material library.

According to a preferred embodiment of the present invention, matching the extracted summary content related to the road to the induction point on the road includes:

if the text content from which the abstract content comes only contains road information, matching the extracted abstract content to an induction point of the road entrance;

and if the text content from which the abstract content is sourced comprises roads and POI (point of interest) information on the roads, matching the extracted abstract content with the induction points near the POI.

According to a preferred embodiment of the present invention, the broadcast content template of the guidance point is obtained by mining in the following manner:

analyzing the historical track behaviors of each user to obtain an abnormal track;

combining broadcast materials of preamble induction points of abnormal tracks to obtain more than one induction point information set, and recording abnormal track scenes corresponding to the induction point information sets;

and carrying out statistical analysis on the induction point information sets corresponding to the same abnormal track scene, and extracting the broadcast content templates of the induction points.

According to a preferred embodiment of the present invention, generating the navigation broadcast content of the guidance point by using the broadcast material and the broadcast content template of the guidance point includes:

determining variable parameters in a broadcast content template of the induction points by using the broadcast materials of the induction points, and generating navigation broadcast contents of the induction points;

the broadcast content template comprises variable parameters or comprises variable parameters and fixed parameters.

In a second aspect, the present invention provides a method for mining a broadcast material, including:

recognizing the text content of the route description class from the network information issued by the user by utilizing a pre-established classification model;

abstracting the text content related to the road;

In a third aspect, the present invention provides an apparatus for generating a navigation broadcasting content, the apparatus comprising:

the determining unit is used for determining a guidance point in the current navigation route;

the acquisition unit is used for acquiring broadcast materials and broadcast content templates of the guidance points in the navigation route;

the generating unit is used for generating the navigation broadcast content of the induction points by utilizing the broadcast materials and the broadcast content templates of the induction points;

According to a preferred embodiment of the invention, the apparatus further comprises:

the sending unit is used for sending the navigation broadcast content of the induction point to the client when the user position reaches the broadcast position of the induction point; or sending the navigation broadcast content of each induction point in the navigation route to the client, so that the client broadcasts the navigation broadcast content of the induction point when the user position reaches the broadcast position of the induction point.

the material mining unit is used for mining the broadcast materials of the induction points in the following modes:

In a fourth aspect, the present invention provides an excavation apparatus for broadcasting a material, the apparatus comprising:

the text recognition unit is used for recognizing the text content of the route description class from the network media information;

the text acquisition unit is used for acquiring text contents related to roads from the recognized text contents by utilizing a pre-established road dictionary;

the abstract extraction unit is used for extracting the abstract of the text content related to the road;

and the induction point matching unit is used for matching the extracted abstract content to the induction points to obtain the broadcast materials of the matched induction points.

According to a preferred embodiment of the present invention, the text recognition unit is specifically configured to: recognizing the text content of the route description class from the network information issued by the user by utilizing a pre-established classification model;

In a fifth aspect, the present invention provides an apparatus comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method as described above.

In a sixth aspect, the present invention provides a storage medium containing computer-executable instructions for performing the method as described above when executed by a computer processor.

According to the technical scheme, the broadcasting materials of the induction points are mined from the network media information to generate the navigation broadcasting content, so that the source of the information of the navigation broadcasting content is richer and more comprehensive, and compared with the prior art, the method for acquiring through a road network is more flexible and changeable.

[ description of the drawings ]

Fig. 1 is a flowchart of a method for generating navigation broadcast content according to an embodiment of the present invention;

fig. 2 is a flowchart of a method for mining broadcast materials of a guidance point according to an embodiment of the present invention;

fig. 3 is a flowchart of a method for mining a broadcast content template of a navigation point according to an embodiment of the present invention;

fig. 4 is a structural diagram of a device for generating navigation broadcast content according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an excavating device for broadcasting a material according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an excavating device for broadcasting a content template according to an embodiment of the present invention;

FIG. 7 illustrates a block diagram of an exemplary computer system/server suitable for use in implementing embodiments of the present invention.

[ detailed description ] embodiments

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.

As described in the background art, the navigation broadcast content in the prior art is only limited to road network collected content such as road traffic instructions, traffic restriction rules, etc., and the broadcast content is relatively rigid content such as "turn right at a front intersection", "a camera is located 100 meters ahead", etc. But in the user's actual trip, the user is interested in information about driving safety such as "whether the road is flat", "whether the street lamp is in question", etc., as well as road traffic instructions, traffic regulations, etc., and is also or more valuable to the user. However, such information cannot be broadcasted in the prior art manner.

With the rapid development of network media, users can conveniently and rapidly publish information through self media, traditional network media and the like, and can easily acquire information through various network media. For example, the user issues information such as "serious accident occurs due to unlighted street lamps" or "pothole over mountain section a in south of china, failure, occurrence of rollover accident" on the social media. In addition, the user may also report information through a map application, for example, report information such as "serious accident occurs due to unlighted large street lamps in the heaven", "uneven and impassable mountain road section a in south of the china", and occurrence of rollover accident "through the map application. The invention can make full use of the information to carry out navigation broadcasting.

Fig. 1 is a flowchart of a method for generating a navigation broadcast content according to an embodiment of the present invention, and as shown in fig. 1, the method specifically includes the following steps:

in 101, an inducement point in the current navigation route is determined.

The 'induction point' referred in the invention refers to a position point set in each path by a navigation system, and navigation broadcasting needs to be carried out on a user at the induction point. Induction points may include, but are not limited to: the traffic light comprises position points such as intersections, turning points, position points of traffic lights, position points of cameras arranged on roads, position points corresponding to traffic signs, position points needing lane change and the like, which can influence the driving of users.

The guidance point may be manually set by a user and stored in the database of the navigation system, or may be preset in another manner and stored in the database of the navigation system, which is not limited in this application. In this step, after the user acquires and selects one navigation route by inputting the start position and the end position, the guidance point in the navigation route may be determined by matching a database storing navigation point information in the navigation system.

In 102, broadcast materials and broadcast content templates of the guidance points in the navigation route are obtained, wherein the broadcast materials of the guidance points are obtained by mining from network media information.

And if one induction point exists in the navigation route, respectively acquiring the broadcast material and the broadcast content template of the induction point in the navigation route. And if more than one induction point exists in the navigation route, respectively acquiring the broadcast material and the broadcast content template of each induction point aiming at each induction point so as to generate the navigation broadcast content of each induction point.

Specifically, the broadcast material of the guidance point may be searched from the broadcast material library. And inquiring the broadcast content template of the induction point from the broadcast template library.

The broadcast material library stores broadcast materials of all the induction points, and the broadcast template library stores broadcast content templates of all the induction points. The broadcast material of each induction point in the broadcast material library and the broadcast content template of each induction point in the broadcast template library can adopt the establishment mode in the prior art. But preferably the excavation provided by the embodiments of the present invention. The following details are provided for the broadcast material of the guidance point and the mining process of the broadcast content template provided by the embodiment of the present invention.

Fig. 2 is a flowchart of a method for mining broadcast material of a guidance point according to an embodiment of the present invention, and as shown in fig. 2, the method may include the following steps:

in 201, textual content of a route description class is identified from network media information.

First, network media information is obtained. Network media information in this application may include, but is not limited to: information published by a user from media, such as blogs, micro letters, video websites, etc., information published on traditional network media, such as news-like websites/applications, information reported by a user in a map-like application, etc.

In the application, recently issued network media information can be acquired through the open interface of the network media, and the acquisition of the network media information is completed after a series of filtering mechanisms such as anti-cheating and the like.

In view of the fact that the obtained network media information is possibly massive, the content with the broadcasting value needs to be extracted from the network media information, the network media information often has the broadcasting value for the text of the route description class, and the information about driving experience, accidents and the like, such as 'serious accidents caused by unlighted heaven street lamps', 'no pothole in the mountain section A in the south of Jinan, unsmooth failure and overturning accidents', and the like. Therefore, in this step, the text content of the route description class can be identified from the network information published by the user by using the pre-established classification model.

The classification model is obtained by training according to the pre-labeled route description text and the non-route description text. Specifically, route description type texts can be collected and labeled in advance to serve as positive samples, non-route description type texts are collected randomly to serve as negative samples, and a classification model is trained. The classification model establishes the probability relation between words and categories after performing word segmentation processing on positive samples and negative samples. After a text is input, whether the text belongs to the route description class text or not can be output through the classification model. The classification model can adopt a naive Bayes classification model, a support vector machine classification model, a k nearest neighbor classification model and the like.

At 202, text content related to the road is obtained from the recognized text content using a pre-established road dictionary.

Not all text contents of the route description classes have navigation broadcasting values, and some text contents of the route description classes cannot be related to specific roads, for example, the text contents of the road depression are too difficult to walk, so that the text contents also have no navigation broadcasting values. Therefore, in this step, the text content related to the road can be acquired from the recognized text content by using the road dictionary established in advance.

The road dictionary may include names of roads, the obtained route description text may be matched with the road dictionary, and if the names of the roads are hit, the text content related to the roads is considered. A variety of names such as official names, alias names, history names, etc. of roads may be included in the road dictionary so as to be suitable for different road calling.

In 203, abstract extraction is performed on the text content related to the road and the text content is matched to the induction point, so that a broadcast material of the matched induction point is obtained.

First, abstract extraction is performed on the text content related to the road. The present mature abstract extraction technology can be adopted in the application to extract the key content of the text and compress the text amount. Therefore, the abstract extraction mode is not limited in the present application.

And then, matching the extracted abstract content related to the road to an induction point on the road to obtain a broadcast material matched to the induction point. Wherein, the summary content can be matched to the induction points of the road entrance. Preferably, the induction point matched with the abstract content can be determined according to the text content from which the abstract content is sourced, that is, the matched induction point is determined according to the context of the abstract content. This preferred embodiment is explained in detail below:

and if the text content from which the abstract content is sourced only contains the road information, matching the extracted abstract content to the induction point of the road entrance. For example, a summary is extracted from a text that the user can never know where the end of the user is, no street lamp, and all the users are big cars and long-distance lamps, and all the users feel deeply panic, and the user can match the summary to an induction point of an entrance of the closing loop line.

If the text content from which the abstract content is sourced comprises a road and POI (Point Of interest) on the road, matching the extracted abstract content to an induction point near the POI. For example, the abstract of "no street lights on the Tianfu avenue, no speed bump" is extracted from the text "no street lights on the Chengdu aves are on the kendy, no speed bump, one white Lace automobile knocks down two passersby, and two people die in the spot due to an excessive injury potential", and the text relates to POI kendy, so that the abstract can be matched to an induction point on the Tianfu avenue that is 50 meters away from the kendy.

If the induction point corresponding to the abstract content is obtained in the above mode, the abstract content is used as the broadcast material of the induction point. If more than one abstract content corresponding to one induction point is obtained through the method, one abstract content is selected from the obtained abstract contents to serve as the broadcast material of the induction point, or part or all of the obtained abstract contents are selected from the obtained abstract contents to serve as the broadcast material of the induction point after being combined. And adding the broadcast materials of all the induction points into a broadcast material library. If one induction point is obtained to correspond to one broadcast material by the method of the embodiment shown in fig. 2, each broadcast material in the broadcast material library may use the induction point as a primary key or an index. In addition, broadcast materials of all guidance points such as lane driving directions, lane restriction regulations, cameras, traffic signs and the like acquired through a traditional road acquisition mode in the prior art can be added into a broadcast material library together. Similarly, if a plurality of broadcast materials corresponding to one induction point are stored together with the broadcast materials obtained in the prior art, one broadcast material can be selected from the plurality of broadcast materials, or the plurality of broadcast materials are combined into one broadcast material.

An example is listed below for the flow shown in fig. 2:

the following text contents of the route description class are identified from the reported contents of the blog, the microblog and the like from the media, and the text contents related to the road are obtained from the text contents by utilizing the pre-established road dictionary. Assume that the text content related to the "closing ring line" is acquired as follows:

"107 province (circle line in Guanzhong) Weinan city boundary shows that there is no street lamp in the boundary of the boundary with the Tong region in the village in the township city at night, there is no speed bump, and there are villages on both sides of the road".

The total length of the closing loop line is nearly 500 kilometers, no street lamps are arranged, dust on part of road sections flies, the road sections are repaired and repaired forever, the traffic flow is large, and 70 percent of the road sections are small to large trucks.

"go and close the middle loop independently at night each time, all look like never knowing where the end is, without street lamp, all are big car multi-distance lights, all feel deeply panic.

After the text content is abstracted, an abstract that no street lamp exists at night and more cars exist in the closed loop is obtained, and the abstract can be used as a broadcast material of a guidance point of an entrance of the closed loop. Compared with the prior art in which the method of acquiring the induction on-demand newspaper material from the network media information is simply based on the road network information acquisition, the method obviously enables the content dimensionality to be richer and more comprehensive.

Fig. 3 is a flowchart of a method for mining a broadcast content template of a navigation point according to an embodiment of the present invention, and as shown in fig. 3, the method may include the following steps:

in 301, historical trajectory behavior of each user is analyzed to obtain an abnormal trajectory.

The abnormal trajectory may include, but is not limited to: violation travel trajectories, yaw travel trajectories, obvious unreasonable travel trajectories, and the like.

In the step, the historical track behaviors of each user can be matched with road information, traffic light information, traffic rules and the like, and the illegal running track can be found. Such as a running track of speeding, a running track of illegal steering, a running track of running a red light, a running track of reversing, a running track of illegal reversing, an illegal lane change, etc. The historical navigation driving track of the user can be compared with the historical navigation track to find the yaw driving track. And the obvious unreasonable driving track such as high speed and same high speed, such as returning to the intersection for straight running after turning right at the intersection, can be found through a preset Bad Case (Bad Case) rule.

Besides the above automatic matching or comparison to obtain the abnormal trajectory, the abnormal trajectory may also be obtained by combining or manually analyzing the historical navigation driving trajectory.

The abnormal trajectory may be in units of links or in units of two adjacent induction points. For example, assuming that a violation occurs in the road section L in the historical navigation driving track of a certain user, the road section L is determined to be an abnormal track. For another example, assuming that yaw occurs at the road segments M and N in the historical navigation driving trajectory of a certain user, the road segments M and N are determined to be abnormal trajectories. For another example, assuming that an illegal lane change occurs between the guidance point m and the guidance point n in the road segment X in the historical navigation driving track of a certain user, the track between the guidance point m and the guidance point n in the road segment X is determined to be an abnormal track.

That is, the abnormal trajectory obtained in this step may be one or more road segments, or may be a partial range in one road segment.

In 302, broadcast materials of the preamble induction points of the abnormal track are combined to obtain information sets of the induction points, and abnormal track scenes corresponding to the information sets of the induction points are recorded.

In the step, broadcast materials of the preorder induction points of one abnormal track are combined to obtain more than one induction point information set. The preamble induction points of the abnormal track can be induction points with set duration, set distance or set number before the abnormal track. In the combination, the combination may be performed in the order in which the user passes through the respective induction points, and the induction points included in the respective combinations are continuous.

The broadcast material of each induction point can be obtained from the broadcast material library, and the broadcast material library can be obtained by mining in the mode shown in the embodiment of the figure 2.

For example, a user passes 3 induction points within a distance of 500 meters before a retrograde abnormal trajectory on a main road, and the sequence of passing by the user is: induction point a, induction point b and induction point c, the broadcast material of every induction point is as follows:

induction points a: broadcasting a material a1, and broadcasting a material a 2;

induction points b: the broadcast of the material b1 is presented,

induction points c: broadcast material c1, broadcast material c 2.

Combining the above modes to obtain the following induction point information sets:

set 1: the broadcasting material a1, the broadcasting material b1 and the broadcasting material c 1;

set 2: the broadcasting material a1, the broadcasting material b1 and the broadcasting material c 2;

set 3: the broadcasting material a2, the broadcasting material b1 and the broadcasting material c 1;

set 4: the broadcasting material a2, the broadcasting material b1 and the broadcasting material c 2;

set 5: broadcasting a material a1 and broadcasting a material b 1;

and 6, set: broadcasting a material a2 and broadcasting a material b 1;

set 7: broadcasting a material b1 and broadcasting a material c 1;

set 8: broadcasting a material b1 and broadcasting a material c 2;

set 9: broadcasting the material a 1;

set 10: broadcasting the material a 2;

set 11: broadcasting the material b 1;

set 12: broadcasting the material c 1;

set 13: the material c2 is broadcasted.

And obtaining an abnormal track scene corresponding to the set according to the abnormal track and the road network information of the abnormal track. Assuming that the abnormal track scenes corresponding to the 13 sets are as follows: the distance between the tunnel exit and the crossroad is less than 100 meters, the road grade reaches the national road grade, and the GPS signal in the tunnel is poor.

In 303, the information sets of the guidance points corresponding to the same abnormal track scene are subjected to statistical analysis, and broadcast content templates of the guidance points are extracted.

And performing statistical analysis on all induction point information sets corresponding to the same abnormal track scene to obtain an induction point information set with occurrence times meeting preset requirements, for example, an induction point information set with the maximum occurrence times. The broadcast content template is constructed by utilizing the broadcast materials contained in the induction point information set, and the broadcast content template can be used as the broadcast content template of the first induction point in the corresponding induction point information set.

The finally constructed broadcast content template may include variable parameters and fixed parameters, or may include only variable parameters. The variable parameters include one or more induction point identifiers, and are used for determining the variable parameters in the broadcast content template from the broadcast materials of the corresponding induction points according to the induction point identifiers when navigation broadcast contents are generated for the induction points (in step 103 shown in fig. 1).

Wherein the fixed parameters can be added manually or combined with a broadcast content template generated by adopting a method in the prior art.

The broadcast content template generated according to the flow shown in fig. 3 and the broadcast content template generated by the method in the prior art can be added to the broadcast template library together after the priority relationship is established. That is, one induction point in the broadcast template library may correspond to more than one broadcast content template. Each broadcast content template in the broadcast template library can take an induction point as a main key or index.

With continued reference to fig. 1.

In 103, the navigation broadcast content of the guidance point is generated by using the broadcast material and the broadcast content template of the guidance point.

The broadcast content template comprises variable parameters and also can comprise variable parameters and fixed parameters. And determining the variable parameters in the broadcast content template of the induction points by utilizing the broadcast materials of the induction points according to the identification of the induction points contained in the variable parameters in the broadcast content template, and generating the navigation broadcast content of the induction points.

For example, suppose that for a certain guidance point a, the broadcast content template corresponding to the guidance point obtained by querying the broadcast template library is: "[ induction points a ], [ induction points b ], [ induction points c ], please slow down in advance to avoid danger. Wherein the 'mark' is variable parameter, the induction point a, the induction point b and the induction point c are three adjacent induction points, wherein the induction point a is the position before entering the tunnel, the induction point b is the position in the tunnel, and the induction point c is the position after exiting the tunnel.

The broadcast material that obtains the guidance point a correspondence through inquiring broadcast material storehouse is: "enter tunnel soon, please turn on the car light"; the broadcast material that the induction point b corresponds is: "GPS signal difference in tunnel, unable to accurately locate you"; the broadcast material that the induction point c corresponds is: and turning right to enter the general road after leaving the tunnel for 55 meters.

Then, after the broadcast material of the induction point is used as a variable parameter in the template, the navigation broadcast content of the induction point a is obtained as 'about to enter a tunnel, please turn on a car light, the GPS signal in the tunnel is poor, the car cannot be accurately positioned, and the car turns right to enter a general soldier road after exiting the tunnel for 55 meters'.

For a comparison, in the prior art, an induction point a before entering the tunnel reports that "the vehicle lamp is about to enter the tunnel and please turn on", an induction point b in the tunnel reports that "the GPS signal in the tunnel is poor and cannot be accurately positioned", and an induction point c out of the tunnel reports that "the vehicle enters the general soldier road by turning right after exiting the tunnel for 55 meters". Because the GPS signal in the tunnel is weak, the position of the vehicle cannot be accurately identified, so the GPS signal replies after the user exits the tunnel, but if the vehicle speed of the user is slightly high, the user can easily pass through a right-turn intersection before the broadcasting is finished. Or the user can realize that the intersection is about to be missed and turn the direction urgently, which can cause accidents such as car rollover, rear-end collision and the like. It is clear that this broadcasting in the prior art is not reasonable.

If the method is adopted, the guidance point a before the user drives into the tunnel reports that the vehicle is about to enter the tunnel, the vehicle lamp is started, the GPS signal in the tunnel is poor, the vehicle can not be accurately positioned, and the vehicle turns right to enter the general soldier road after exiting the tunnel by 55 meters. The user is thus aware of and has sufficient preparation to turn right 55 meters out of the tunnel for proper travel. Obviously, the method fully considers the logical relationship among the induction points and the optimal broadcasting time, so that the user is more leisurely and safely in the driving process.

If the broadcast template library is inquired to obtain that more than one broadcast content template exists in one induction point, one navigation broadcast content used for generating the induction point can be selected according to the priority of the broadcast content template.

At 104, the navigation broadcast content of the guidance point is sent to the client.

The method can be realized at the server side. After the navigation broadcast contents of the induction points are generated at the server side, when the position of a user reaches the broadcast position of the induction points, the navigation broadcast contents of the induction points are issued to the client side of the user, so that the client side can conduct navigation broadcast. Or after the user selects the navigation route, the navigation broadcast contents of the various guidance points related to the navigation route are sent to the client, and when the position of the client reaches the broadcast position of the guidance points, the navigation broadcast contents of the guidance points are broadcast.

The broadcast position of each induction point can be determined according to different strategies, the strategies are configured in advance, and different configurations can be carried out according to different types of the induction points. For example, for some intersections, guidance points needing lane changing, turning points and the like, broadcasting can be carried out in advance when the guidance points are away from the guidance points by a certain distance; for guidance points such as traffic lights, the information can be broadcast at the guidance point position, and the like.

In the embodiment of the invention, the navigation broadcast content is broadcast preferably in a voice broadcast mode, so that the attention of a user is not dispersed in the driving process. However, other modes such as video broadcasting, text broadcasting, etc. may be adopted besides the voice broadcasting mode, and the present invention is not limited thereto.

The above is a detailed description of the method provided by the present invention, and the following is a detailed description of the apparatus provided by the present invention with reference to the examples.

Fig. 4 is a structural diagram of a device for generating a navigation broadcast content according to an embodiment of the present invention, and as shown in fig. 4, the device includes: the determining unit 01, the acquiring unit 02 and the generating unit 03 may further include a transmitting unit 04, a material mining unit 05 and a template mining unit 06.

The determination unit 01 is responsible for determining the inducement points in the current navigation route.

The acquisition unit 02 is responsible for acquiring broadcast materials and broadcast content templates of the guidance points in the navigation route.

And the generating unit 03 is used for generating the navigation broadcast content of the induction points by utilizing the broadcast materials and the broadcast content templates of the induction points.

The broadcast content template may include variable parameters, or include variable parameters and fixed parameters. The generation unit 03 can determine the variable parameters in the broadcast content template of the induction points by using the broadcast materials of the induction points according to the identification of the induction points contained in the variable parameters in the broadcast content template, and generate the navigation broadcast content of the induction points.

The broadcast materials of the induction points are obtained by pre-mining from the network media information. The broadcast content template of the induction point is obtained by pre-mining the historical track behaviors of each user.

The sending unit 04 is used for sending the navigation broadcast content of the guidance point to the client when the user position reaches the broadcast position of the guidance point; or the navigation broadcast content of each induction point in the navigation route is sent to the client, so that when the client reaches the broadcast position of the induction point at the user position, the navigation broadcast content of the induction point is broadcast.

The broadcast materials of each induction point in the broadcast material library can be established by adopting a mode in the prior art, for example, the broadcast materials are established by utilizing the collected information in the road network information collection process. As a preferred embodiment, the material mining unit 05 may pre-mine the broadcast material of the induction point in the following manner:

and (4) carrying out abstract extraction on the text content related to the road and matching the text content to the induction points to obtain the broadcast materials of the matched induction points.

The template mining unit 06 pre-mines the broadcast content templates of the guidance points in the following manner:

Fig. 5 is a schematic structural diagram of a broadcast material mining device according to an embodiment of the present invention, that is, a schematic structural diagram of the material mining unit 05, where as shown in fig. 5, the broadcast material mining device may include: a text recognition unit 51, a text acquisition unit 52, a digest extraction unit 53, and an induction point matching unit 54.

The text recognition unit 51 is responsible for recognizing the text content of the route description class from the network media information.

Network media information in this application may include, but is not limited to: information published by a user from media, such as blogs, micro letters, video websites, etc., information published on traditional network media, such as news-like websites/applications, information reported by a user in a map-like application, etc.

As a preferred embodiment, the text recognition unit 51 may recognize the text content of the route description class from the network media information by using a pre-established classification model; the classification model is obtained by training according to a pre-labeled route description text and a non-route description text. Specifically, route description type texts can be collected and labeled in advance to serve as positive samples, non-route description type texts are collected randomly to serve as negative samples, and a classification model is trained. The classification model establishes the probability relation between words and categories after performing word segmentation processing on positive samples and negative samples. After a text is input, whether the text belongs to the route description class text or not can be output through the classification model. The classification model can adopt a naive Bayes classification model, a support vector machine classification model, a k nearest neighbor classification model and the like.

The text acquiring unit 52 is responsible for acquiring text contents related to roads from the recognized text contents using a road dictionary established in advance.

The abstract extracting unit 53 is responsible for abstracting text contents related to roads.

The present mature abstract extraction technology can be adopted in the application to extract the key content of the text and compress the text amount. Therefore, the abstract extraction mode is not limited in the present application.

The induction point matching unit 54 is responsible for matching the extracted summary content to an induction point to obtain a broadcast material of the matched induction point.

Specifically, the induction point matching unit 54 may extract the text content related to the road; matching the extracted abstract content related to the road to an induction point on the road to obtain a broadcast material matched to the induction point; and adding the broadcast materials of all the induction points into a broadcast material library.

Wherein, matching the extracted summary content related to the road to the induction point on the road may include: if the text content from which the abstract content comes only contains the road information, matching the extracted abstract content with an induction point of the road entrance; and if the text content from which the abstract content is sourced comprises roads and POI (point of interest) information on the roads, matching the extracted abstract content with the induction points near the POI.

If an abstract content corresponding to an induction point is obtained through the device, the abstract content is used as a broadcast material of the induction point. If more than one abstract content corresponding to one induction point is obtained through the device, one abstract content is selected from the obtained abstract contents to serve as the broadcast material of the induction point, or part or all of the obtained abstract contents are selected from the obtained abstract contents to serve as the broadcast material of the induction point after being combined. And adding the broadcast materials of all the induction points into a broadcast material library. If a broadcast material is corresponding to one induction point obtained by the device, the induction point can be used as a main key or an index for each broadcast material in the broadcast material library. In addition, broadcast materials of all guidance points such as lane driving directions, lane restriction regulations, cameras, traffic signs and the like acquired through a traditional road acquisition mode in the prior art can be added into a broadcast material library together. Similarly, if a plurality of broadcast materials corresponding to one induction point are stored together with the broadcast materials obtained in the prior art, one broadcast material can be selected from the plurality of broadcast materials, or the plurality of broadcast materials are combined into one broadcast material.

Fig. 6 is a schematic structural diagram of an excavating device for a broadcast content template according to an embodiment of the present invention, that is, a schematic structural diagram of the template excavating unit 06, as shown in fig. 6, the excavating device for a broadcast content template may include: a trajectory analysis unit 61, a material combination unit 62, and a statistical analysis unit 63.

The track analysis unit 61 is responsible for analyzing the historical track behaviors of each user to obtain an abnormal track.

Wherein, the abnormal trajectory may include: a violation travel trajectory, a yaw travel trajectory, or an apparently unreasonable travel trajectory. The abnormal trajectory may be in units of links or in units of two adjacent induction points.

The material combination unit 62 is responsible for combining broadcast materials of the preamble induction points of the abnormal track to obtain more than one induction point information sets, and recording abnormal track scenes corresponding to the induction point information sets.

Specifically, the material combining unit 62 may combine the broadcast materials of the induced points by the set time length, the set distance, or the set number before the abnormal trajectory in the order in which the user passes through the induced points.

The statistical analysis unit 63 is responsible for performing statistical analysis on the guidance point information sets corresponding to the same abnormal track scene and extracting broadcast content templates of the guidance points.

Specifically, the statistical analysis unit 63 may perform statistical analysis on the guidance point information sets corresponding to the same abnormal track scene to obtain guidance point information sets whose occurrence times meet preset requirements, construct a broadcast content template by using broadcast materials included in the guidance point information sets, and use the broadcast content template as a broadcast content template of a first guidance point in the corresponding guidance point information sets.

The finally constructed broadcast content template may include variable parameters and fixed parameters, or may include only variable parameters. The variable parameters include more than one induction point identifier, and the generation unit 03 determines the variable parameters in the broadcast content template from the broadcast materials corresponding to the induction points according to the induction point identifier when generating the navigation broadcast content for the induction points.

Fig. 7 illustrates a block diagram of an exemplary computer system/server 012 suitable for use in implementing embodiments of the invention. The computer system/server 012 shown in fig. 7 is only an example, and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.

As shown in fig. 7, the computer system/server 012 is embodied as a general purpose computing device. The components of computer system/server 012 may include, but are not limited to: one or more processors or processing units 016, a system memory 028, and a bus 018 that couples various system components including the system memory 028 and the processing unit 016.

Bus 018 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Computer system/server 012 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer system/server 012 and includes both volatile and nonvolatile media, removable and non-removable media.

System memory 028 can include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)030 and/or cache memory 032. The computer system/server 012 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 034 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be connected to bus 018 via one or more data media interfaces. Memory 028 can include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the present invention.

Program/utility 040 having a set (at least one) of program modules 042 can be stored, for example, in memory 028, such program modules 042 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof might include an implementation of a network environment. Program modules 042 generally perform the functions and/or methodologies of embodiments of the present invention as described herein.

The computer system/server 012 may also communicate with one or more external devices 014 (e.g., keyboard, pointing device, display 024, etc.), hi the present invention, the computer system/server 012 communicates with an external radar device, and may also communicate with one or more devices that enable a user to interact with the computer system/server 012, and/or with any device (e.g., network card, modem, etc.) that enables the computer system/server 012 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 022. Also, the computer system/server 012 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 020. As shown, the network adapter 020 communicates with the other modules of the computer system/server 012 via bus 018. It should be appreciated that although not shown in fig. 7, other hardware and/or software modules may be used in conjunction with the computer system/server 012, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 016 executes programs stored in the system memory 028, thereby executing various functional applications and data processing, such as implementing the method flow provided by the embodiment of the present invention.

The computer program described above may be provided in a computer storage medium encoded with a computer program that, when executed by one or more computers, causes the one or more computers to perform the method flows and/or apparatus operations shown in the above-described embodiments of the invention. For example, the method flows provided by the embodiments of the invention are executed by one or more processors described above.

With the development of time and technology, the meaning of media is more and more extensive, and the propagation path of computer programs is not limited to tangible media any more, and can also be downloaded from a network directly and the like. Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

As can be seen from the above description, the above method, apparatus, device and computer storage medium provided by the present invention may have the following advantages:

1) the broadcasting materials of the guidance points are mined from the network media information to generate the navigation broadcasting content, so that the information of the navigation broadcasting content is richer and more comprehensive in source.

2) The mode of discovering the broadcast material of the induction point from the network media information to generate the navigation broadcast content has higher content timeliness, and compared with the mode of collecting through a road network in the prior art, the updating speed is higher.

3) The method for generating the navigation broadcast content by utilizing the broadcast content template of the historical track behavior mining induction point of the user enables the form of the navigation broadcast content to be more flexible and meets the actual driving requirements of the user better.

4) Through carrying out unusual analysis to user's historical orbit action to broadcast the material to the preorder induction point of unusual orbit and make up and statistical analysis, thereby extract the broadcast content template of induction point, make the navigation based on this broadcast content template generation broadcast the content and fully considered the interrelationship between the induction point, compare the single navigation of aiming at the induction point in prior art and broadcast the content, can guide the user to make correct driving decision more excellently.

In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.

The units described as separate parts may or may not be physically separate, and parts displayed as units 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.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. A method for generating a navigation broadcast content, the method comprising:

determining an induction point in the current navigation route;

the broadcast materials of the induction points are obtained by mining from the network media information;

the broadcast content template of the induction point is obtained by mining in the following mode:

2. The method of claim 1, further comprising:

3. The method of claim 1, wherein obtaining the announcement material and the announcement content template of the guidance point in the navigation route comprises:

4. The method of claim 1, wherein the broadcast material of the induction point is mined by:

5. The method of claim 4, wherein identifying textual content of a route description class from the network media information comprises:

6. The method of claim 4, wherein the step of abstracting and matching the text content related to the road to the induction points comprises the steps of:

abstracting the text content related to the road;

7. The method of claim 6, wherein matching the extracted summary content associated with the link to the induction point on the link comprises:

8. The method of claim 1, wherein generating the navigation announcement content of the guidance point using the announcement material and the announcement content template of the guidance point comprises:

9. An apparatus for generating a navigation broadcast content, the apparatus comprising:

the template mining unit is used for mining the broadcast content templates of the induction points in the following modes:

10. The apparatus of claim 9, further comprising:

11. The apparatus of claim 9, further comprising:

12. An excavating equipment for broadcasting material, the equipment comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

13. A storage medium containing computer-executable instructions for performing the method of any one of claims 1-8 when executed by a computer processor.