CN113704538A - Data processing method and device, electronic equipment and computer storage medium - Google Patents
Data processing method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN113704538A CN113704538A CN202111007135.7A CN202111007135A CN113704538A CN 113704538 A CN113704538 A CN 113704538A CN 202111007135 A CN202111007135 A CN 202111007135A CN 113704538 A CN113704538 A CN 113704538A
- Authority
- CN
- China
- Prior art keywords
- classification
- determining
- sub
- processing
- attribute information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000003672 processing method Methods 0.000 title abstract description 17
- 239000000463 material Substances 0.000 claims abstract description 344
- 238000012545 processing Methods 0.000 claims abstract description 140
- 238000000034 method Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 9
- 230000010365 information processing Effects 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000006243 chemical reaction Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000013499 data model Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 239000011365 complex material Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 241001149900 Fusconaia subrotunda Species 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000011162 core material Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a data processing method, a data processing device, electronic equipment and a computer storage medium, and relates to the field of artificial intelligence such as intelligent traffic. The specific implementation scheme is as follows: acquiring a first material for generating map data; determining attribute information influencing the processing difficulty of the first material; determining the processing difficulty degree classification of the first material according to the attribute information; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to a corresponding map data generating end. The embodiment of the disclosure can reduce the total proportion of the material returned to be redone or corrected during material processing, and improve the processing efficiency of the material.
Description
Technical Field
The present disclosure relates to the field of computer technology, and more particularly to the field of artificial intelligence, such as intelligent transportation.
Background
With the development of computer technology, network technology, mobile terminal technology and other technologies, the use times and use time of electronic map data are rapidly increased, and the dependence on electronic maps is stronger and stronger.
Because ground elements in the real environment change constantly, map data needs to be updated in time according to materials acquired by a map acquisition vehicle or other channels. When updating map data, it is necessary to convert the material of the map data that is actually collected. Due to the complexity and variability of the actual environment, errors always occur in the processing results of map data such as material conversion, and when an error occurs each time, the error operation and other operations processed in the same batch are reworked at the same time, so that the material conversion efficiency is reduced.
Disclosure of Invention
The disclosure provides a data processing method, a data processing device, an electronic device and a computer storage medium.
According to an aspect of the present disclosure, there is provided a data processing method including:
acquiring a first material for generating map data;
determining attribute information influencing the processing difficulty of the first material;
determining the processing difficulty degree classification of the first material according to the attribute information; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to the corresponding map data generation end.
According to another aspect of the present disclosure, there is provided a data processing apparatus including:
the acquisition module is used for acquiring a first material for generating map data;
the attribute information module is used for determining attribute information influencing the processing difficulty of the first material;
the difficulty degree classification module is used for determining the processing difficulty degree classification of the first material according to the attribute information; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to the corresponding map data generation end.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method in any of the embodiments of the present disclosure.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method in any of the embodiments of the present disclosure.
According to the technology disclosed by the invention, the materials can be distributed to the execution nodes matched with the difficulty level of the materials for processing, and the material processing efficiency is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of a data processing method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a data processing method according to another embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a data processing method according to an example of the present disclosure;
FIG. 4 is a schematic diagram of a data processing apparatus according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a data processing apparatus according to another embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a data processing apparatus according to yet another embodiment of the present disclosure;
fig. 7 is a block diagram of an electronic device for implementing a data processing method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
An embodiment of the present disclosure provides an information processing method, as shown in fig. 1, including:
step S11: acquiring a first material for generating map data;
step S12: determining attribute information influencing the processing difficulty of the first material;
step S13: determining the processing difficulty degree classification of the first material according to the attribute information; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to the corresponding map data generation end.
In this embodiment, the first material may be a material for generating an element in the map data, or may be a material for changing data of an existing map. The material may include a material for generating a road element, a material for generating a traffic sign element, a material for generating a building, a material for generating a point of interest, a material for generating a lane line, a material for generating a traffic light, and/or a material for generating a station element, etc., among others.
The first material may be a material for generating a general electronic data map or a material for generating a High Definition (High Definition) electronic map.
The first material may be a material for generating elements such as points, lines, and planes in the map.
Specifically, the first material may be an image captured by an ordinary camera or an image frame in a video. But also images shot by other special shooting devices or files in other formats.
The first material may be a plurality of materials or one material.
The obtaining of the first material for generating the map data may be extracting the first material for generating the map data or modifying the existing map data according to the video collected by the road image collecting vehicle. Therefore, the first material can be obtained according to the data uploaded by the user terminal. The first material may also be obtained based on other data.
In this embodiment, the processing difficulty level classification may be determined according to the conversion result of the material that has been converted. For example, the determination may be made specifically based on a rework rate, an error rate, or a rework rate of the processing result. For example, according to the historical data, if the error rate of a batch of historical materials which are converted for the first time is ten percent, the ten percent of error materials are selected as the data with high processing difficulty.
The processing difficulty level classification of the first material may be a difficulty level of converting the first material. The processing difficulty level classification can be expressed by the material processing difficulty level or the material processing simplicity level.
The processing difficulty level classification of the first material may be a processing difficulty level of the material in a small step in the map data generation step, or a processing difficulty level of the material in all or part of discontinuous steps in the map data generation step.
The attribute information affecting the processing difficulty of the first material may be a file characteristic of the first material or a characteristic of the content of the first material, or may be a characteristic affecting the difficulty of converting the first material into map data or changing the map data.
The attribute information affecting the processing difficulty of the first material may include the complexity of the material, the integrity of the material file, the definition of the material file, light in the material file, and the like. The attribute information of the first material may be one kind or plural kinds. The specific type of the attribute information can be determined by the first material and other materials processed in the same batch with the first material, or can be determined by summarizing the attribute information of the historical materials. The plurality of materials processed in the same batch may be a plurality of materials distributed to different or the same map data generation end in the same batch for processing. When there are a plurality of types of attribute information, the processing difficulty of the first material can be determined by integrating various types of attribute information.
Attribute information affecting the ease of processing of the first material is determined and can be summarized according to the processing results of the historical materials. And comparing the material with the conversion result which is not wrong in the historical materials with the material with the error, determining the difference information between the material with the conversion result which is not wrong and the material with the conversion result which is wrong, and taking the difference information as candidate attribute information. When the first material also has the candidate attribute information, the candidate attribute information is used as the attribute information of the first material.
In one embodiment, a set of attributes can be established that affect the error rate of historical material. When the first material has the attributes in the attribute set, the attributes in the attribute set are used as attribute information influencing the processing difficulty of the first material.
In one embodiment, the processing difficulty level classification of the first material is determined according to the attribute information, which may be determining the processing difficulty level classification of the first material according to a corresponding relationship between a plurality of preset attributes and preset difficulty levels.
The treatment difficulty score classification can be expressed as a numerical value, with higher values being more difficult or simpler. Or may be represented by a hard, medium, easy, etc. direct partition. It can also be represented by a scale.
The corresponding map data generation side may be a corresponding map data generation node, and may correspond to a hardware or software processing device of the generation side. For example, in a case where the first material is difficult, the first material is distributed to a generation side corresponding to a higher-level hardware processing apparatus or a production side corresponding to a higher-level software processing apparatus.
The corresponding map data generation end can also be the generation end of the adopted specific material conversion rule. For example, in the case where the first material is simpler, the first material is distributed to the generation side where the conversion rule is looser.
The corresponding map data generation end can also be a generation end operated by a specific operator. For example, in the case where the first material is difficult, the first material is distributed to the generation side of the operator operation of the higher skill level.
In one embodiment of the present disclosure, the first material may be lane information material. For example, the first material may include information of an arrow in a lane, a lane type, and the like. In the navigation electronic map making, the making process of the lane information material can be as follows: collecting image materials and identifying the contents of lane information to label the contents of the image materials; verifying and judging the validity of the material according to the marked image material content and the image material data condition, and adding an identifier of the validity; the final data is formed by automatic or manual operation according to the material identification push production.
The verification and judgment of materials such as lanes and the like are one of the most important links for updating the whole map, but because errors are likely to occur in the processing process of the materials, the improvement of the processing efficiency of the materials has certain difficulty. For example, in the manual processing scenario, assume that the primary operator has taken a task package in which 100 lane change image materials need to be verified, 2 complex materials and 98 simple materials. Due to the fact that the skill of an operator is insufficient, 2 complex materials are misjudged, all materials of the whole task package are reworked, most of the materials which are processed correctly also need to be reprocessed, and the material processing efficiency is reduced.
In this embodiment, the difficulty level of the first material can be determined according to the attribute information related to the processing difficulty level of the first material, and the material distribution can be performed according to the difficulty level, so that the materials with higher difficulty level can be centralized, and the simple materials can be centralized. Simple material is not returned with errors in the more difficult material because it is processed with the more difficult material. The overall correction and redo proportion of the materials processed in the same batch is reduced, and the processing, conversion and use efficiency of the materials is improved.
When the method and the device are applied to processing of materials such as lanes, difficulty degree division can be carried out on the materials of lane information, production operation or tasks can be distributed according to the difficulty degree of the materials of the lane information, and intelligent production pushing with maximized production efficiency and quality benefits is met.
In one embodiment, in a case where the attribute information includes a plurality of types, determining the processing difficulty classification of the first material according to the attribute information includes:
determining the corresponding sub-classification of each attribute information;
and determining the treatment difficulty degree classification according to all the sub-classifications.
In this embodiment, the sub-category corresponding to the attribute information may be one of the sub-categories that all the materials processed in the same batch as the first material may have under the attribute information, or one of the sub-categories that the historical material may have under the attribute information.
For example, regarding the number of lane lines of the attribute information, the minimum number of lane lines is 2 and the maximum number of lane lines is 3 among all the materials processed in the same batch as the first material, and the sub-classification corresponding to the attribute information, which is the number of lane lines, may be 2 or 3. The sub-classification of the lane number attribute information of the first material may be 2 or 3.
For example, the number of signs in all the materials processed in the same batch as the first material may be 2, 4, or 5 for the number of attribute information signs, and the sub-category corresponding to the attribute information, i.e., the number of signs, may be 2, 4, or 5. The sub-classification of the lane number attribute information of the first material may be 2, 4, or 5.
In this embodiment, each attribute information of the first material corresponds to one sub-classification according to the objective condition of the first material, and all the sub-classifications may be a set formed by the sub-classifications corresponding to each attribute information of the first material.
For example, the attribute information of the first material is A, B, C. Attribute information A, B, C in all material processed in the same batch of the first material, there may be sub-categories including: the sub-classification of a includes a1, a 2; the sub-classification of B includes B1, B2; the sub-classifications of C include C1, C2, C3. For the objective condition of the first material, it is determined that the sub-classification corresponding to the attribute a of the first material is a2, the sub-classification corresponding to the attribute B is B1, and the sub-classification corresponding to the attribute C is C1, so that all the sub-classifications of the first material include a2, B1, and C1.
In this embodiment, the processing difficulty level classification is determined according to all the sub-classifications, and the difficulty level of each sub-classification under the corresponding attribute information may be determined first, and then the overall processing difficulty level of the first material is determined by combining all the sub-classifications.
And determining the processing difficulty degree classification according to all the sub-classifications, and determining a key sub-classification which is relatively decisive for the processing difficulty degree classification in all the sub-classifications. And determining the processing difficulty of the first material according to the key sub-classification.
And determining the processing difficulty degree classification according to all the sub-classifications, and determining the overall processing difficulty degree of the first material according to the weight set for each attribute information and the sub-classification corresponding to the attribute information.
In this embodiment, the sub-classifications corresponding to the multiple kinds of attribute information are determined, and the processing difficulty of the first material is determined according to all the sub-classifications of the first material, so that the accuracy of the determination result of the processing difficulty is improved.
In one embodiment, determining a processing ease classification from all of the sub-classifications includes:
obtaining the normalized scores of all the sub-classifications according to the sub-classifications;
and determining the classification of the treatment difficulty degree according to the normalized score.
In this embodiment, each sub-category under each attribute information may correspond to one normalized score.
And adding the normalized scores of all the sub-classifications to obtain the normalized values of all the sub-classifications. The normalized scores of the sub-classifications corresponding to various attribute information of the first material may be added to obtain the normalized scores of all the sub-classifications.
The normalized score of each sub-category may be the score of the sub-category under various different attribute information, and is converted into the score obtained by the same scoring dimension.
And determining the processing difficulty degree classification according to the total score, wherein the processing difficulty degree classification corresponding to the total score can be determined according to a preset corresponding relation.
And determining the classification of the difficulty degree of processing according to the total score, or performing certain conversion on the total score, and further determining the classification of the difficulty degree of processing according to the conversion result.
In this embodiment, the total score of all the sub-classifications of the first material can be determined according to all the sub-classifications corresponding to the attribute information of the first material, and the processing difficulty classification can be determined according to the total score. The abstract attribute information and the abstract sub-classification are converted into absolute numerical values or symbols representing the material processing difficulty, so that the relative processing difficulty of the first material and other materials can be clearly distinguished.
In one embodiment, all normalized scores are determined by:
determining the sum of preset scores of all the sub-classifications;
determining a preset highest score and a preset lowest score according to the sub-classification of the first material and/or the second material under the attribute information; the second material comprises other materials distributed in the same batch with the first material;
and determining a normalized score according to the sum of the preset scores, the preset highest score and the preset lowest score.
In a specific embodiment, all attribute information can be determined for the same batch of materials, and all corresponding sub-classifications under each attribute information can also be determined. Therefore, for the same batch of materials, all attribute information and the sub-classifications corresponding to the attribute information can be determined in advance according to the specific conditions of a plurality of materials, a limited number of sub-classification combinations are formed according to the limited sub-classifications, and various processing difficulty classifications are determined according to the material number corresponding to the various sub-classification combinations.
For example, for the same batch of materials, there is attribute information A, B, C, and the sub-categories existing under each attribute information are: the sub-classification of the attribute information A comprises A1 and A2; the sub-classification of the attribute information B includes B1, B2; the sub-classification of the attribute information C includes C1, C2, C3. If one sub-classification is extracted from all the sub-classifications corresponding to each attribute information to form one sub-classification combination, and a total of 2 × 2 × 3 to 12 sub-classification combinations can be formed, 12 levels of processing difficulty can be set in advance. And then determining the difficulty level corresponding to the sub-classification combination of the first material according to the sub-classification corresponding to each attribute information of the first material.
The difficulty level corresponding to each sub-classification combination can be determined by the specific sub-classification included in the sub-classification combination. The relative difficulty of each sub-classification can be determined by all sub-classifications under the same attribute information. The sub-classification with the largest processing difficulty exists in all sub-classifications under the same attribute information, and a preset highest score is correspondingly set; and correspondingly setting a preset lowest score for the sub-classification with the lowest processing difficulty.
Due to the fact that the attribute information is different, the corresponding sub-classifications under the attribute information are different, and the preset highest score and the preset lowest score corresponding to each attribute information may be different. When the processing difficulty score classification of the first material is determined, the method and the device can determine the processing difficulty score classification according to the normalized scores of the sub-classifications corresponding to the attribute information, so that different objective abstract information can be converted into relatively specific numerical values or symbolic information, and a clear judgment result can be obtained.
In this embodiment, the normalized score may be calculated according to the sub-classification combination condition of the first material and the second material processed in the same batch. Namely, the preset highest score and the preset lowest score of various sub-classification combinations of the first material and the second material processed in the same batch are determined, and the normalized score is calculated according to the highest score and the lowest score of all the materials.
The normalized score can also be calculated according to the sub-classifications under the same attribute information, that is, the highest score and the lowest score corresponding to the sub-classifications under the attribute information are respectively used as a preset highest score and a preset lowest score, and then the normalized score is calculated for each sub-classification.
In one embodiment, determining a treatment difficulty classification based on the normalized scores includes:
determining a target range of the fraction of the normalized score in all the scores;
and determining the classification of the processing difficulty according to the preset corresponding relation and the target range.
In this embodiment, the target range of the normalized score in all scores may be related to the proportion of the materials with the same score in all the materials of the batch, or related to the highest score and the lowest score of all the scores.
The correspondence relationship may be, for example, that the target range 0.1 to 0.2 corresponds to the processing difficulty level classification D.
In this embodiment, the processing difficulty level classification is determined according to the target range and the preset corresponding relationship, so that the processing difficulty level classification can be determined quickly.
In one embodiment, the predetermined correspondence is determined according to the manner shown in fig. 2:
step S21: determining a plurality of ranges according to the total scores of the first material and the second material, wherein the plurality of ranges comprise a target range;
step S22: determining an amount of material included in each of a plurality of ranges;
step S23: and determining a preset corresponding relation according to the number of the materials, the number of the first materials and the number of the second materials, wherein the preset corresponding relation comprises that the target range corresponds to the processing difficulty and the processing easiness of the first materials in a classified manner.
In this embodiment, a range may be created according to a fraction ratio, or a fraction paragraph may be directly divided, and different fraction paragraphs correspond to different fraction ranges.
In this embodiment, the preset corresponding relationship is created in advance, so that the processing difficulty and difficulty degree classification information of the material can be quickly obtained according to the calculated score.
In one embodiment, the data processing method further comprises:
according to the processing difficulty degree classification, the first materials are distributed to the corresponding map data generation end;
and obtaining the map data generated by the map data generating terminal according to the first material.
In this embodiment, the first material and a plurality of other materials classified with the same difficulty level may be sent to the corresponding map data generation end as one batch. In this case, for example, the first material is transmitted to the map data generating side together with 99 materials classified by the same difficulty level. Under the condition that the difficulty of the 100 materials is higher, the more materials in the 100 materials possibly have errors in the processing process, so that under the condition of errors, the 100 materials can be returned to be reprocessed or corrected at the same time, and the quantity of the materials which are not subjected to errors and are returned together with the materials which are subjected to errors is reduced. Under the condition that the difficulty of the 100 materials is low, the materials with errors do not exist in the 100 materials, so that the 100 materials do not need to be returned.
Furthermore, for the materials processed by the map data generation end in the same batch at the same time, the difficulty level is basically consistent, the error probability is basically consistent, more error materials may exist during returning, or the processing results of all the materials are correct.
In this embodiment, the first material is distributed to the corresponding map data generation end, that is, the material processing node, according to the processing difficulty classification, so that after the first material is processed, the material with high difficulty in the material processed in the same batch with the first material in the same node is not returned and the other material processed in the same batch with the first material is also returned because the difference between the difficulty of the other material processed in the same node and the difficulty of the first material is too large, so that the total modification amount of the map data generation end is reduced.
The embodiment of the disclosure extracts the objective sub-classification of the first material to calculate the total score of the first material by determining the sub-classification of the attribute information of the strategy as a calculation reference factor. And judging the classification of the difficulty degree of the treatment according to the total score condition. And after the classified grouping is carried out according to the processing difficulty degree (the data packets classified according to the processing difficulty degree), the data packets can be used as the skill pool of the staff for distribution tasks. That is, under the condition that the first material is difficult to process, the first material can be distributed to the skill corresponding map data generating end with a higher skill level; in the case where the first material is more tractable, the first material may be distributed to map data generating ends of lower skill levels.
In one example of the present disclosure, the data processing method is applied to the judgment of the difficulty of processing classification of the image material of the lane information.
In this example, through statistics and comparison of the historical material and the batch of material to be processed, the material integrity, the material type and the material content of the image material of the lane information determine the difficulty level of material processing. Therefore, the processing difficulty degree classification of the material can be confirmed through the sub-classification by using the three types of attribute information as reference factors for determining the difficulty degree. In this example, the content of the material may interpret the subdivided attribute, for example, the material content may be further refined attribute information for the sub-category corresponding to the material type.
In this example, the integrity of the material may be determined according to whether the target object in the image material is occluded or not and the situation of the occlusion. In the real world, the image acquisition effect is not ideal enough due to the fact that vehicles cover and shield the naturally-existing road materials. Therefore, for the image materials with incomplete lane attribute collection, the operation difficulty of manual verification is inevitably increased, and the historical track image at the position and the images of the front track and the rear track collected back and forth by the same batch of collection vehicles may need to be called for comprehensive judgment.
In this example, the material type may be determined according to the type of the target object in the image material. For example, when the lane type material has depth information (i.e., data in the Z-axis direction depending on the situation of the acquisition device), the number of used image materials needs to be further traced and confirmed, such as a bus lane, whether the material conversion needs image materials acquired all day long or needs image materials acquired in a specific time period, and further tracing and confirmation is needed, so that the processing difficulty is high; and under the condition that the image material of the number of lanes has no depth information, the image material does not need to be traced and confirmed, so the processing difficulty is low.
In the present disclosed example, in the case where the image material is lane information image material, the sub-classification of the material content may include: lane number, lane type, lane marking pattern, lane representation color, lane arrow.
For a target object in the lane information image material, the integrity of the material is affected by the number of lanes. When the number of lanes is greater than 4, capping in different situations is likely to occur, that is, incomplete material is likely to occur. The material type may be a lane type. The lane type may be classified into a general lane type and a special lane type. The special lane types may include: a bus Lane, an HOV (High-Occupancy Vehicle Lane, shared or multi-occupant Lane) Lane, a tidal Lane, a variable Lane, etc. The material content may include lane markings and lane arrows. Wherein the lane markings can be divided into normal markings and special markings (long solid line/dashed solid line of the fingers, etc. or the color is not white). The lane arrows may be divided into empty and non-empty arrows.
In this example, a data model supporting lane information material distribution can be constructed according to business requirements and data characteristic information, and the data model can correspondingly distribute materials according to the difficulty of material processing. The Data Model (Data Model) is an abstraction of Data features, describes static features, dynamic behaviors and constraints of the system from an abstraction level, and provides an abstract framework for information representation and operation of the database system. In this example, the data model modeling may include the following basic requirements:
difficulty level check table with lane information: the difficulty level of the material, the total score of the material, and the verification state (namely the state that the material cannot be pushed to the downstream and is verified or not) are stored;
configuration material table with lane information: the information situation of the core material (several types of material in general) is stored.
In this example, when the difficulty level classification of the material is determined, the difficulty level coefficient may be normalized, the sub-classifications of the attribute information of the material are used as the influence factors, the total score of the material is calculated, and the lane information material difficulty level coefficient floating interval is determined according to the sub-classifications of each attribute information.
The specific effect of this example using normalization is to generalize the statistical distribution of the uniform samples. The normalization is a statistical probability distribution between (0-1), and the normalization is a statistical coordinate distribution between (-1 to + 1). I.e., normalized, the integral of the fractional function at (- ∞, + ∞) is 1. The normalized calculation formula may be:
wherein x isnormalizationMay be a normalized score of a sub-classification, and x may be a preset score of a sub-classification, a preset score of a sub-classification.
In this example, the attribute information that affects the material processing difficulty classification may include material integrity, material type, and material content, and the sub-classifications under each attribute information may be specifically shown in table 1 below:
TABLE 1
In this example, scores of sub-classifications under each attribute information may be determined, and then a preset highest score and a preset lowest score of the attribute information may be determined according to the scores of the sub-classifications. The normalized score for each seed classification combination is calculated by the formula previously described.
For example, the sub-classifications and corresponding preset scores of the lane information of the material under the material integrality, the material type and the material content are respectively as follows: the collection is complete 5 points, the number of lanes (change) is 2 points, and the material content is 5 lanes is 3 points.
The lowest score of the known overall comprehensive material is 9 scores and the highest score is 100 scores.
The difficulty score is: ((5+2+3) -9)/(100-9) ═ 0.01.
In other implementation manners, the normalized score of each sub-classification may be calculated for different sub-classifications, and after the sub-classifications corresponding to all the attribute information of the material are determined, the normalized scores of the sub-classifications of the material are added to obtain the normalized score of the material.
And calculating a final coefficient score according to the final coefficient score for the massive lane information materials processed in the same batch, then performing packet aggregation according to the operation content of the task packet, and dividing a reasonable difficulty degree interval according to the skill scale of personnel. For example, 4 grades, primary grade, middle grade, high grade and highest grade are divided, and the score of each grade is calculated. The divided intervals can be adjusted and adapted at different stages due to the skill condition of the personnel.
In one example of the present disclosure, the data processing method may include the steps shown in fig. 3:
step S31: and acquiring lane information materials.
Step S32: attribute information of the lane information material is determined. The attribute information may include material integrity, material type, and material content.
Step S33: and calculating the material score.
Step S34: and determining the classification of the processing difficulty of the materials according to the material scores.
Step S35: and classifying according to the processing difficulty and matching with a personnel skill pool.
Step S36: and carrying out intelligent distribution according to the matching result.
An embodiment of the present disclosure further provides a data processing apparatus, as shown in fig. 4, including:
an obtaining module 41, configured to obtain a first material used for generating map data;
an attribute information module 42, configured to determine attribute information that affects the processing difficulty of the first material;
a difficulty degree classification module 43, configured to determine, according to the attribute information, a processing difficulty degree classification of the first material; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to the corresponding map data generation end.
In one embodiment, in the case where the attribute information includes a plurality of types, as shown in fig. 5, the difficulty degree classification module includes:
a sub-classification unit 51, configured to determine a sub-classification corresponding to each attribute information;
and a sub-classification information processing unit 52 for determining a processing difficulty classification from all the sub-classifications.
In one embodiment, the sub-classification information processing unit is further configured to:
obtaining the normalized scores of all the sub-classifications according to the sub-classifications;
and determining the classification of the treatment difficulty degree according to the normalized score.
In one embodiment, all normalized scores are determined by:
determining the sum of preset scores of all the sub-classifications;
determining a preset highest score and a preset lowest score according to the sub-classification of the first material and/or the second material under the attribute information; the second material comprises other materials distributed in the same batch with the first material;
and determining a normalized score according to the sum of the preset scores, the preset highest score and the preset lowest score.
In one embodiment, the sub-classification information processing unit is further configured to:
determining a target range of the fraction of the normalized score in all the scores;
and determining the classification of the processing difficulty according to the preset corresponding relation and the target range.
In one embodiment, the predetermined correspondence is determined according to the following manner:
determining a plurality of ranges according to the total scores of the first material and the second material, wherein the plurality of ranges comprise a target range;
determining an amount of material included in each of a plurality of ranges;
and determining a preset corresponding relation according to the number of the materials, the number of the first materials and the number of the second materials, wherein the preset corresponding relation comprises that the target range corresponds to the processing difficulty and the processing easiness of the first materials in a classified manner.
In one embodiment, as shown in fig. 6, the data processing apparatus further includes:
the distribution module 61 is used for distributing the first material to the corresponding map data generation end according to the classification of the processing difficulty;
and the map data module 62 is configured to obtain map data generated by the map data generating terminal according to the first material.
The embodiment of the disclosure can be applied to the field of computers, and especially can be applied to the field of artificial intelligence such as intelligent traffic.
The functions of each unit, module or sub-module in each apparatus in the embodiments of the present disclosure may refer to the corresponding description in the above method embodiments, and are not described herein again.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the electronic device 700 includes a computing unit 701, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
A number of components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (17)
1. A method of data processing, comprising:
acquiring a first material for generating map data;
determining attribute information influencing the processing difficulty of the first material;
determining the processing difficulty degree classification of the first material according to the attribute information; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to a corresponding map data generating end.
2. The method of claim 1, wherein, in the case that the attribute information includes a plurality of types, the determining a processing difficulty classification of the first material according to the attribute information includes:
determining the corresponding sub-classification of each attribute information;
and determining the processing difficulty degree classification according to all the sub-classifications.
3. The method of claim 2, wherein said determining the processing ease classification from all sub-classifications comprises:
obtaining the normalized scores of all the sub-classifications according to the sub-classifications;
and determining the processing difficulty degree classification according to the normalized score.
4. The method of claim 3, wherein all of the normalized scores are determined by:
determining the sum of preset scores of all the sub-classifications;
determining a preset highest score and a preset lowest score according to the sub-classification of the first material and/or the second material under the attribute information; the second material comprises other materials distributed in the same batch with the first material;
and determining the normalized score according to the sum of the preset scores, the preset highest score and the preset lowest score.
5. The method of claim 4, wherein said determining the treatment difficulty classification from the normalized score comprises:
determining a target range of the fraction of the normalized score in all the scores;
and determining the processing difficulty degree classification according to a preset corresponding relation and the target range.
6. The method of claim 5, wherein the preset correspondence is determined according to:
determining a plurality of ranges according to the total scores of the first material and the second material, wherein the plurality of ranges comprise the target range;
determining an amount of material included in each of a plurality of ranges;
and determining the preset corresponding relation according to the material quantity, the first material quantity and the second material quantity, wherein the preset corresponding relation comprises the classification correspondence of the target range and the processing difficulty and the easiness of the first material.
7. The method of any of claims 1-6, wherein the method further comprises:
according to the processing difficulty degree classification, the first material is distributed to a corresponding map data generation end;
and obtaining the map data generated by the map data generating terminal according to the first material.
8. A data processing apparatus comprising:
the acquisition module is used for acquiring a first material for generating map data;
the attribute information module is used for determining attribute information influencing the processing difficulty of the first material;
the difficulty degree classification module is used for determining the processing difficulty degree classification of the first material according to the attribute information; and the processing difficulty and the processing easiness classification are used for representing that the first material is distributed to a corresponding map data generating end.
9. The apparatus of claim 8, wherein in the case that the attribute information includes a plurality of kinds, the difficulty degree classification module includes:
the sub-classification unit is used for determining the sub-classification corresponding to each attribute information;
and the sub-classification information processing unit is used for determining the processing difficulty classification according to all the sub-classifications.
10. The apparatus of claim 9, wherein the sub-classification information processing unit is further configured to:
obtaining the normalized scores of all the sub-classifications according to the sub-classifications;
and determining the processing difficulty degree classification according to the normalized score.
11. The apparatus of claim 10, wherein all of the normalized scores are determined by:
determining the sum of preset scores of all the sub-classifications;
determining a preset highest score and a preset lowest score according to the sub-classification of the first material and/or the second material under the attribute information; the second material comprises other materials distributed in the same batch with the first material;
and determining the normalized score according to the sum of the preset scores, the preset highest score and the preset lowest score.
12. The apparatus of claim 11, wherein the sub-classification information processing unit is further configured to:
determining a target range of the fraction of the normalized score in all the scores;
and determining the processing difficulty degree classification according to a preset corresponding relation and the target range.
13. The apparatus of claim 12, wherein the preset correspondence is determined according to:
determining a plurality of ranges according to the total scores of the first material and the second material, wherein the plurality of ranges comprise the target range;
determining an amount of material included in each of a plurality of ranges;
and determining the preset corresponding relation according to the material quantity, the first material quantity and the second material quantity, wherein the preset corresponding relation comprises the classification correspondence of the target range and the processing difficulty and the easiness of the first material.
14. The apparatus of any one of claims 8-13, wherein the apparatus further comprises:
the distribution module is used for distributing the first material to a corresponding map data generation end according to the processing difficulty degree classification;
and the map data module is used for acquiring the map data generated by the map data generating end according to the first material.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111007135.7A CN113704538A (en) | 2021-08-30 | 2021-08-30 | Data processing method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111007135.7A CN113704538A (en) | 2021-08-30 | 2021-08-30 | Data processing method and device, electronic equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113704538A true CN113704538A (en) | 2021-11-26 |
Family
ID=78657008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111007135.7A Pending CN113704538A (en) | 2021-08-30 | 2021-08-30 | Data processing method and device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704538A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012032619A1 (en) * | 2010-09-08 | 2012-03-15 | クラリオン株式会社 | Map data processing apparatus, updated map data distribution apparatus, map data updating system, and map data updating method |
| US20130076766A1 (en) * | 2011-09-28 | 2013-03-28 | Denso Corporation | Map data distribution apparatus, electronic apparatus, and map update system |
| WO2017041396A1 (en) * | 2015-09-10 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Driving lane data processing method, device, storage medium and apparatus |
| US20180253621A1 (en) * | 2016-08-24 | 2018-09-06 | Google Inc. | Change Direction Based Imagery Acquisition Tasking System |
| WO2018163906A1 (en) * | 2017-03-06 | 2018-09-13 | 株式会社ミックウェア | Information processing device, information processing system, and information processing program |
| CN109844734A (en) * | 2017-08-25 | 2019-06-04 | 腾讯科技（深圳）有限公司 | A kind of method and terminal, computer storage medium of picture file management |
| CN112182409A (en) * | 2020-11-03 | 2021-01-05 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and computer storage medium |
| CN112380317A (en) * | 2021-01-18 | 2021-02-19 | 腾讯科技（深圳）有限公司 | High-precision map updating method and device, electronic equipment and storage medium |
| CN112784175A (en) * | 2020-12-24 | 2021-05-11 | 北京百度网讯科技有限公司 | Method, device and equipment for processing point of interest data and storage medium |
| US20210209160A1 (en) * | 2020-09-25 | 2021-07-08 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for identifying map region words |
-
2021
- 2021-08-30 CN CN202111007135.7A patent/CN113704538A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012032619A1 (en) * | 2010-09-08 | 2012-03-15 | クラリオン株式会社 | Map data processing apparatus, updated map data distribution apparatus, map data updating system, and map data updating method |
| US20130076766A1 (en) * | 2011-09-28 | 2013-03-28 | Denso Corporation | Map data distribution apparatus, electronic apparatus, and map update system |
| WO2017041396A1 (en) * | 2015-09-10 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Driving lane data processing method, device, storage medium and apparatus |
| US20180253621A1 (en) * | 2016-08-24 | 2018-09-06 | Google Inc. | Change Direction Based Imagery Acquisition Tasking System |
| WO2018163906A1 (en) * | 2017-03-06 | 2018-09-13 | 株式会社ミックウェア | Information processing device, information processing system, and information processing program |
| CN109844734A (en) * | 2017-08-25 | 2019-06-04 | 腾讯科技（深圳）有限公司 | A kind of method and terminal, computer storage medium of picture file management |
| US20210209160A1 (en) * | 2020-09-25 | 2021-07-08 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for identifying map region words |
| CN112182409A (en) * | 2020-11-03 | 2021-01-05 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and computer storage medium |
| CN112784175A (en) * | 2020-12-24 | 2021-05-11 | 北京百度网讯科技有限公司 | Method, device and equipment for processing point of interest data and storage medium |
| CN112380317A (en) * | 2021-01-18 | 2021-02-19 | 腾讯科技（深圳）有限公司 | High-precision map updating method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113902897B (en) | Training of target detection model, target detection method, device, equipment and medium | |
| CN108470022B (en) | Intelligent work order quality inspection method based on operation and maintenance management | |
| CN106919957B (en) | Method and device for processing data | |
| CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
| CN106599915A (en) | Vehicle-mounted laser point cloud classification method | |
| CN110796066B (en) | Lane line group construction method and device | |
| CN114003613A (en) | High-precision map lane line updating method and device, electronic equipment and storage medium | |
| CN114880337B (en) | Map data integrated updating method, device, equipment and storage medium | |
| CN114021156A (en) | Method, device and equipment for organizing vulnerability automatic aggregation and storage medium | |
| CN113298910A (en) | Method, apparatus and storage medium for generating traffic sign line map | |
| CN114626457A (en) | Target detection method and device and electronic equipment | |
| CN109977131A (en) | A kind of house type matching system | |
| CN113989760A (en) | Method, device and equipment for detecting lane line by high-precision map and storage medium | |
| CN113704538A (en) | Data processing method and device, electronic equipment and computer storage medium | |
| CN114724113B (en) | Road sign recognition method, automatic driving method, device and equipment | |
| CN113420174B (en) | Difficult sample mining method, device, equipment and storage medium | |
| CN115019057A (en) | Image feature extraction model determining method and device and image identification method and device | |
| CN113902898A (en) | Training of target detection model, target detection method, device, equipment and medium | |
| CN114092057A (en) | Project model construction method and device, terminal equipment and storage medium | |
| CN113963011A (en) | Image recognition method and device, electronic equipment and storage medium | |
| CN114049686A (en) | Signature recognition model training method and device and electronic equipment | |
| CN113504865A (en) | Work order label adding method, device, equipment and storage medium | |
| CN113033431A (en) | Optical character recognition model training and recognition method, device, equipment and medium | |
| CN111612023A (en) | Classification model construction method and device | |
| CN113990068B (en) | Traffic data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |